This action might not be possible to undo. Are you sure you want to continue?

Licence Toolbox home page Discussion group

LGPL http://www.petercorke.com/vision http://groups.google.com.au/group/robotics-tool-box

Copyright c 2011 Peter Corke peter.i.corke@gmail.com September 2011 http://www.petercorke.com

Preface

This, the third release of the Toolbox, represents a decade of development. The last release was in 2005 and this version captures a large number of changes over that period but with extensive work over the last two years to support my new book “Robotics, Vision & Control” shown to the left.

Peter C0rke

Robotics,

Vision and Control

The practice of robotics and computer vision each involve the application of computational algorithms to data. The research community has developed a very large body of algorithms but for a newcomer to the ﬁeld this can be quite daunting. For more than 10 years the author has maintained two opensource matlab® Toolboxes, one for robotics and one for vision. They provide implementations of many important algorithms and allow users to work with real problems, not just trivial examples. This new book makes the fundamental algorithms of robotics, vision and control accessible to all. It weaves together theory, algorithms and examples in a narrative that covers robotics and computer vision separately and together. Using the latest versions of the Toolboxes the author shows how complex problems can be decomposed and solved using just a few simple lines of code. The topics covered are guided by real problems observed by the author over many years as a practitioner of both robotics and computer vision. It is written in a light but informative style, it is easy to read and absorb, and includes over 1000 matlab® and Simulink® examples and ﬁgures. The book is a real walk through the fundamentals of mobile robots, navigation, localization, armrobot kinematics, dynamics and joint level control, then camera models, image processing, feature extraction and multi-view geometry, and ﬁnally bringing it all together with an extensive discussion of visual servo systems.

Corke

Robotics,

Vision and Control

Peter Corke

1

Robotics, Vision and Control

isbn 978-3-642-20143-1

9 783642 201431

›

springer.com

The Machine Vision Toolbox (MVTB) provides many functions that are useful in machine vision and vision-based control. It is a somewhat eclecFUNDAMENTAL tic collection reﬂecting my personal interest in areas ALGORITHMS IN MATLAB® of photometry, photogrammetry, colorimetry. It includes over 100 functions spanning operations such 123 as image ﬁle reading and writing, acquisition, display, ﬁltering, blob, point and line feature extraction, mathematical morphology, homographies, visual Jacobians, camera calibration and color space conversion. The Toolbox, combined R with MATLAB and a modern workstation computer, is a useful and convenient environment for investigation of machine vision algorithms. For modest image sizes the processing rate can be sufﬁciently “real-time” to allow for closed-loop control. Focus of attention methods such as dynamic windowing (not provided) can be used to increase the processing rate. With input from a ﬁrewire or web camera (support provided) and output to a robot (not provided) it would be possible to implement a visual R servo system entirely in MATLAB . An image is usually treated as a rectangular array of scalar values representing intenR sity or perhaps range. The matrix is the natural datatype for MATLAB and thus makes the manipulation of images easily expressible in terms of arithmetic statements R in MATLAB language. Many image operations such as thresholding, ﬁltering and R statistics can be achieved with existing MATLAB functions. The Toolbox extends this core functionality with M-ﬁles that implement functions and classes, and mex-ﬁles for some compute intensive operations. It is possible to use mex-ﬁles to interface with image acquisition hardware ranging from simple framegrabbers to robots. Examples for ﬁrewire cameras under Linux are provided. The routines are written in a straightforward manner which allows for easy underR standing. MATLAB vectorization has been used as much as possible to improve efﬁciency, however some algorithms are not amenable to vectorization. If you have the

Machine Vision Toolbox for MATLAB

R

3

Copyright c Peter Corke 2011

though this is much less signiﬁcant today than it was in the past. This is extravagant on storage. is open-source. This toolbox is not a clone of the Mathwork’s own Image Processing Toolbox (IPT) although there are many functions in common.MATLAB compiler available then this can be used to compile bottleneck functions. R R Machine Vision Toolbox for MATLAB R 4 Copyright c Peter Corke 2011 . contains many functions that are useful for image feature extraction and control. This toolbox predates IPT by many years. This toolbox considers images generally as arrays of double precision numbers. Some particularly compute intensive functions are provided as mex-ﬁles and may need to be compiled for the particular platform. nearly 400 ﬁgures and 1000 code examples) of how to use the Toolbox functions to solve many types of problems in robotics. It was developed under Unix and Linux systems and some functions rely on tools and utilities that exist only in that environment. However the book “Robotics. The manual is now auto-generated from the comments in the MATLAB code itself which reduces the effort in maintaining code and a separate manual as I used to — the downside is that there are no worked examples and ﬁgures in the manual. and I commend it to you. Vision & Control” provides a detailed discussion (over 600 pages.

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 Other toolboxes . . . . . . . FeatureMatch . . . . . . . . . . . . . . . . . . AxisWebCamera . . . . . . . . . . . . . . 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 What’s new . . . . . . . . . . . . . . . . blackbody . . . . . . . Tracker . . . . . . . . . . . . .2 Support . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . SiftPointFeature . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . RegionFeature . . . . . . . . . . . . . . . . . . . . . . . . . . . . . FishEyeCamera . . . . . . . . . . . . . . . . . . . . . . . . . . . Machine Vision Toolbox for MATLAB R 5 Copyright c Peter Corke 2011 . . . . . . PGraph . . anaglyph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Video . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . PointFeature . . . . . . . . . . . .7 Acknowledgements .6 Use in research . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Ray3D . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ScalePointFeature . . . . . . . . . . . . Polygon . .6. . . . . . . . . . . . . . .3 How to obtain the Toolbox 1. . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . about . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 3 10 10 10 11 11 11 11 12 12 13 13 19 29 32 37 40 41 45 48 53 55 59 62 63 70 73 78 80 83 85 87 88 89 89 90 . . . . . . . . . . . . . . . . . . . Hough . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . LineFeature . . . . . . . . 1 Introduction 1. . CatadioptricCamera . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . .5 Use in teaching . . . . . . . . . . . . . CentralCamera . . . . . . . . . Functions and classes Camera . . . . . . . . . .Contents Introduction . . . . . . . . . . . . . . . . angdiff . . . . . . . . . . . . . . . . . . . . . . . . . . . . Movie . . . . . .4 MATLAB version issues . . . . . . . . . . . . . . SurfPointFeature . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . BagOfWords . . . . . . . . . . . . . . . . . . . . . . . . SphericalCamera . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . epidist . . . . . . . . . . . . . . . . . . . . . distance . . . . . . . . . . . . . . . . . . . . . . . . cmfrgb . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 90 90 91 91 92 92 92 93 94 94 95 95 96 96 97 98 99 99 100 100 101 101 102 102 103 103 103 104 104 105 106 106 107 107 108 109 110 110 111 112 113 114 115 116 116 117 117 118 119 120 Machine Vision Toolbox for MATLAB Copyright c Peter Corke 2011 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idisplabel . . . . . . R . . . . . . icp . . . diff2 . . . . . . . . . . . . . . . . . . . . . . . . icolor . . . . . .CONTENTS CONTENTS boundmatch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iendpoint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . edgelist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . homwarp . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . cmfxyz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . igraphseg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . cie primaries circle . . . . . . . . . . . . . . . . . . . . colnorm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iconv . . . . . . . . iint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ihist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . homography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . colorkmeans . . . . . . . . . . . . . . . . . . . . . . colorname . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ibbox . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . colorspace . . . . . . . . . . . . . . . . . . . . . . . . ccdresponse . . . . . . . . . . . . . . . . e2h . . . . . . . . . . . . . . . . . . . . . . 6 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . homtrans . . . . . . . . . . . . . . . . . . . hitormiss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ianimate . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . h2e . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . homline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idecimate . . . . . . . . . . . . . . . . . . . icorner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idouble . . colordistance colorize . . . . . . . . . . . . epiline . . . . . . . . . . . . . . . gauss2d . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . humoments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . bresenham . . . . . . . . . . . . . . . . . iclose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . camcald . . . . . . . . . . . . iblobs . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . igamma . . . . . icanny . . . . . . . . . . . . . . . . . . . . . . . fmatrix . . . . . . . . . . . . . . . . . . . . . . . . col2im . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idisp . . . . . . . . . . . . iconcat . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . closest . . .

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . itrim . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . irank . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isurf . . . . . . iscalespace . . . . . . iroi . . . . . . . . . . . . . . . . . . . inormhist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iline . . . . . . . . . . . . . . . . . . . . . . . . . . isrot . . . . . . . . intgimage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . kcircle . . . . . . . . . . . . . . . . . . . . . ipaste . . . . . iscale . 120 120 121 122 122 123 123 124 125 125 126 126 127 127 128 128 129 129 130 131 132 132 133 133 134 134 135 135 136 136 136 137 138 138 139 140 140 141 142 143 143 144 144 145 145 146 147 147 148 148 Machine Vision Toolbox for MATLAB Copyright c Peter Corke 2011 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . istretch . . . . . . . . . .CONTENTS CONTENTS iisum . . . . . . im2col . . . . . . . . . . . . . . . . . ishomog . . . . . . . . . irectify . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ivar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imeshgrid . . . . . . . . . . kdog . . . . . . . . . . . . . . . . . . . . . . . . . kgauss . . . . . . istereo . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ipyramid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ismooth . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imoments . . . . . . . . . . . . . . . . . . . . . . . . . . . imorph . . . . . . . . . . iread . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ireplicate . . . . . . . . . . . . . . . . . ithin . . . . iscalemax . . . . . . . . . . . . . . . . . . . . . ithresh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isamesize . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iscolor . . . . . . . . . . . . . . . . . . . . . . . iproﬁle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isift . . . . . . . . . . . . . . . . . . ipixswitch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isobel . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ilabel . . . . . . itriplepoint . . . . . . . . . . . . . . . . isvec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imono . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iwindow . . . . . . . . . . . . . . . . . . . . . . . . . . . . isimilarity . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imser . . . R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isize . . irotate . . . . . kdgauss . . . . . . . . . . . . . imatch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iopen . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ipad . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . otsu . . . . . . . . . . . peak2 . . . maxﬁlt . . mpq . . . . . . . . . . . . . . . . . . . . . mplot . . . rg addticks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 149 149 150 150 151 151 152 152 153 153 153 154 154 155 155 155 156 156 156 157 158 158 158 159 159 160 160 161 162 162 163 163 164 164 164 165 165 166 166 167 167 168 168 169 169 171 171 172 172 172 Machine Vision Toolbox for MATLAB Copyright c Peter Corke 2011 . . . . . . . . . . . . . . . . . numcols . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . lambda2rg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . roty . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ktriangle . . . . . . . . . . ransac . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . numrows . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . npq poly . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plotp . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . pgmﬁlt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot sphere . . . . . . . . . radgrad . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . npq . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot ellipse inv plot frame . . . . . 8 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot2 . . . . niblack . . . . . . . . . . . . . . plot box . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . luminos . . . . . . . . . . . . . . . . . . . rotx . . . . . . . . . kmeans . . . . pnmﬁlt . . . . . . . . . . . . . medﬁlt1 . . . . . . . . . . . klog . . . . . . . . . . . . . . . . . . . . . r2t . . . . . . . . . . . . . . . norm2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mpq poly . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . peak . . . . . . . . . plot ellipse . . . . . . . . . . . mlabel . . . . . . . . . . . . ksobel . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot homline . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . rluminos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ncc . . . . . . . . . . . . . . . . . ramp . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mkcube . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .CONTENTS CONTENTS klaplace . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mkgrid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot circle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot point . . . . . . . . . . . . . . . . . . . . . . . lambda2xy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mtools . . . . . . . . . . . . loadspectrum . plot poly . . . . . . . . . . . . . . . rotz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . zncc . . . . . . . . xaxis . . trotx . . . . . . . . . . . . . . . . . . . useﬁg . . . . se2 . . . . . . . . . . . . . . . . . . . . . . unit . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . trotz . . . . . . . . . . . . . tb optparse . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . troty . . . . . .CONTENTS CONTENTS rpy2tr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . t2r . . . . . . . . . . . . . . . . . . . tpoly . . . . . . . . . . . . . . xycolorspace yaxis . . . . . . . . . . . . . . . . . . . . upq poly . . . . . . . . . . . . . . . . . . . . . . . . stdisp . . . . . . . . . . . . 173 173 174 174 175 175 175 176 176 177 178 179 179 180 180 181 181 182 182 183 183 184 184 185 185 185 186 186 187 187 188 188 189 Machine Vision Toolbox for MATLAB R 9 Copyright c Peter Corke 2011 . . . . . . . . . . . . . transl . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vex . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tr2angvec . . . tr2rt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tristim2cc . . . . . . . ssd . . . . . . . . . . . . . . . . . . . . . . zssd . . . . . . . . . . . . . . . . . . . . . . . . . . . trprint . . . . . . . sad . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . upq . . . . . . . . . . . . . . . . . . . . . . . . zsad . . . testpattern . . . . . . . . . . . . . . . . . . . . . . . . . . skew . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tr2rpy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . zcross . . . . . . . . . . trnorm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . rt2tr . . . . . . . . . . . . . . . . . . . . .

I am happy to correspond with people who have found genuine bugs or deﬁciencies but my response time can be long and I can’t guarantee that I respond to your email.google. lecturers and professors are paid to do.com.au/group/robotics-tool-box which is a forum for discussion. That’s what you your teachers. and you will be suitably acknowledged. no matter how urgent or important they might be to you.Chapter 1 Introduction 1.2 Support There is no support! This software is made freely available in the hope that you ﬁnd it useful in solving whatever problems you have to hand. You might instead like to communicate with other users via the Google Group called “Robotics Toolbox” http://groups. I can guarantee that I will not respond to any requests for help with assignments or homework.1 • x New features: • x Bugﬁxes: • Improved error messages in many functions • Removed trailing commas from if and for statements What’s new Changes: 1. I need you to write a Machine Vision Toolbox for MATLAB R 10 Copyright c Peter Corke 2011 . You need to signup in order to post. and the signup process is moderated by me so allow a few days for this to happen. tutors. I am very happy to accept contributions for inclusion in future versions of the toolbox.

It is R auto-generated from the comments in the MATLAB code and is fully hyperlinked: to external web sites. Volume = {12}. Author = {P. the table of content to functions. If you plan to distribute paper copies of the PDF manual then every copy must include the ﬁrst two pages (cover and licence).6 Use in research If the Toolbox helps you in your endeavours then I’d appreciate you citing the Toolbox when you publish.pdf or the web-based documentation html/*.3. type of organization and application.html on a server for class use. Title = {Machine Vision Toolbox}. and the “See also” functions to each other. Corke}. Month = nov. Year = {2005}.gz) or zip format (. A menu-driven demonstration can be invoked by the function rtdemo. Number = {4}. 1. Journal = {IEEE Robotics and Automation Magazine}. 1. Machine Vision Toolbox for MATLAB R 11 Copyright c Peter Corke 2011 .1.5 Use in teaching This is deﬁnitely encouraged! You are free to put the PDF manual (vision. This is just a means for me to gauge interest and to help convince my bosses (and myself) that this is a worthwhile activity. 1.4 MATLAB version issues The Toolbox has been tested under R2011a.I. The details are @article{Corke05f. 1. The web page requests some information from you regarding such as your country. INTRODUCTION few words about why you want to join the list so I can distinguish you from a spammer or a web-bot.com The ﬁles are available in either gzipped tar format (. The ﬁle robot.zip).pdf is a manual that describes all functions in the Toolbox.petercorke.3 How to obtain the Toolbox The Machine Vision Toolbox is freely available from the Toolbox home page at http://www. HOW TO OBTAIN THE TOOLBOX CHAPTER 1.

The Camera Calibration Toolbox by Jean-Yves Bouguet is used unmodiﬁed. MSER. November 2005. 1994 University of British Columbia. RANSAC code by Peter Kovesi.com/matlabcentral is a great resource for user contributed MATLAB code. and there are hundreds of modules available. graph-based segmentation and pose estimation are based on great code Some of the MEX ﬁle use some really neat macros that were part of the package VISTA Copyright 1993.org is a great collection of advanced computer vision algorithms for MATLAB.. P.6.7. color space conversions by Pascal Getreuer. Corke. pp 16–25. numerical routines for geometric vision by various members of the Visual Geometry Group at Oxford (from the web site of the Hartley and Zisserman book. and the SURF feature detector by Dirk-Jan Kroon at U.7 Acknowledgements Last.mathworks. 12(4). Machine Vision Toolbox for MATLAB R 12 Copyright c Peter Corke 2011 .1 Other toolboxes Matlab Central http://www. IEEE Robotics and Automation Magazine. INTRODUCTION Pages = {16-25} } or “Machine Vision Toolbox”. Twente. but not least. Pascal Fua at the CVLab-EPFL. contributed by Nuno Alexandre Cid Martins of I.the graph-based image segmentation software by Pedro Felzenszwalb. this release includes functions for computing image plane homographies and the fundamental matrix. VLFeat http://www.S.Functions such as SURF.vlfeat. See the ﬁle CONTRIB for details. 1. which is also given in electronic form in the CITATION ﬁle. pose estimation by Francesco Moreno-Noguer. 1. Coimbra. the k-means and MSER algorithms by Andrea Vedaldi and Brian Fulkerson. ACKNOWLEDGEMENTS CHAPTER 1. Vincent Lepetit.R.1.I.

Methods plot hold ishold clf ﬁgure mesh point line plot camera rpy move centre delete char display plot projection of world point to image plane control ﬁgure hold for image plane window test ﬁgure hold for image plane clear image plane ﬁgure holding the image plane draw shape represented as a mesh draw homogeneous points on image plane draw homogeneous lines on image plane draw camera in world view set camera attitude clone Camera after motion get world coordinate of camera centre object destructor convert camera parameters to string display camera parameters Properties (read/write) npix pp rho T image dimensions (2 × 1) principal point (2 × 1) pixel dimensions (2 × 1) in metres camera pose as homogeneous transformation R Machine Vision Toolbox for MATLAB 13 Copyright c Peter Corke 2011 .Chapter 2 Functions and classes Camera Camera superclass An abstract superclass for Toolbox camera classes.

Machine Vision Toolbox for MATLAB R 14 Copyright c Peter Corke 2011 . S ‘noise’.8]) Notes • Normally the class plots points and lines into a set of axes that represent the image plane. used by all subclasses.Camera Create camera object Constructor for abstact Camera class. N ‘image’. S ‘centre’. T ‘color’. IM ‘resolution’. Camera. FUNCTIONS AND CLASSES Properties (read only) nu nv u0 v0 number of pixels in u-direction number of pixels in v-direction principal point u-coordinate principal point v-coordinate Notes • Camera is a reference object. • The object can create a window to display the Camera image plane.CHAPTER 2. P ‘pixel’. SIGMA ‘pose’. • Camera objects can be used in vectors and arrays • This is an abstract class and must be subclassed and a project() method deﬁned. C Name of camera Load image IM to image plane Image plane resolution: N × N or N=[W H] Image sensor size in metres (2 × 1) [metres] Principal point (2 × 1) Pixel size: S × S or S=[W H] Standard deviation of additive Gaussian noise added to returned image projections Pose of the camera as a homogeneous transformation Color of image plane background (default [1 1 0. Options ‘name’. The ‘image’ option paints the speciﬁed image onto the image plane and allows points and lines to be overlaid. C = Camera(options) creates a default (abstract) camera with null parameters. N ‘sensor’. this window is protected and can only be accessed by the plot methods of this object.

clf() removes all graphics from the camera’s image plane. Machine Vision Toolbox for MATLAB R 15 Copyright c Peter Corke 2011 .centre() is the 3-dimensional position of the camera centre (3 × 1). Camera. CatadioptricCamera. Camera.display() displays a compact human-readable representation of the camera parameters.display Display value C.centre Get camera position p = C. SphericalCamera Camera.clf Clear the image plane C. FUNCTIONS AND CLASSES See also CentralCamera.delete() destroys all ﬁgures associated with the Camera object and removes the object. Camera.delete Camera object destructor C. ﬁsheyecamera.CHAPTER 2.char() is a compact string representation of the camera parameters.char Convert to string s = C. Camera.

otherwise false (0).v + c = 0.u + b. Camera.ﬁgure() is the handle of the ﬁgure that contains the camera’s image plane graphics.ishold() returns true (1) if the camera’s image plane is in hold mode.CHAPTER 2.ishold Return image plane hold status H = C.line(L) plots lines on the camera image plane which are deﬁned by columns of L (3 × N ) considered as lines in homogeneous form: a. C. Camera.hold(H) hold mode is set on if H is true (or > 0). and off if H is false (or 0).ﬁgure Return ﬁgure handle H = C. Camera.char Camera. Machine Vision Toolbox for MATLAB R 16 Copyright c Peter Corke 2011 .line Plot homogeneous lines on image plane C. See also Camera.hold Control hold on image plane graphics C.hold() sets “hold on” for the camera’s image plane. FUNCTIONS AND CLASSES Notes • This method is invoked implicitly at the command line when the result of an expression is a Camera object and the command has no trailing semicolon.

plot Plot points on image plane C.T.move(T) is a new camera object that is a clone of C but its pose is displaced by the homogeneous transformation T with respect to the current pose of C. T ‘Tcam’.plot(p) as above but returns the image plane coordinates uv (2 × N ). Camera. T Transform all points by the homogeneous transformation T before projecting them to the camera image plane. cylinder. options) projects a 3D shape deﬁned by the matrices x.move Instantiate displaced camera C2 = C. Machine Vision Toolbox for MATLAB R 17 Copyright c Peter Corke 2011 . The matrices x. Temporarily overrides the current camera pose C. sphere. z.plot(p. See also mesh. If p is 2 × N the points are assumed to be image plane coordinates and are plotted directly.mesh(x. Options ‘Tobj’. FUNCTIONS AND CLASSES Camera. mkcube. Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane.mesh Plot mesh object on image plane C.clf Camera.CHAPTER 2. z to the image plane and plots them. z are of the same size and the corresponding elements of the matrices deﬁne 3D points. uv = C.hold. Camera. Camera.plot. y. y. options) projects world points p (3 × N ) to the image plane and plots them. If p has 3 dimensions (3xNxS) then it is considered a sequence of point sets and is displayed as an animation. Camera. y.

point Plot homogeneous points on image plane C. Overrides the current camera pose C. ‘Tcam’.2 x maximum axis dimension) Notes • The graphic handles are stored within the Camera object.T. C Text color for annotation (default black) ‘textsize’. FUNCTIONS AND CLASSES Options Transform all points by the homogeneous transformation T before projecting them to the camera image plane.clf Camera. S Text size for annotation (default 12) ‘drawnow’ Execute MATLAB drawnow function Additional options are considered MATLAB linestyle parameters and are passed directly to plot. Camera. ‘fps’.mesh. N Number of frames per second for point sequence display ‘sequence’ Annotate the points with their index ‘textcolor’. T ‘scale’. Options ‘Tcam’.plot camera Display camera icon in world view C. T Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane.CHAPTER 2. Camera. T See also Camera. S Camera displayed in pose T (homogeneous transformation 4 × 4) Overall scale factor (default 0. ‘Tobj’. Machine Vision Toolbox for MATLAB R 18 Copyright c Peter Corke 2011 . Camera.hold.plot camera(options) draw a camera as a simple 3D model in the current ﬁgure.point(p) plots points on the camera image plane which are deﬁned by columns of p (3 × N ) considered as points in homogeneous form.

C. the focal point is at z=0 and the image plane is at z=f.rpy Set camera attitude C. p. that is. y) sets the camera attitude to the speciﬁed roll-pitch-yaw angles. v Y This camera model assumes central projection. Machine Vision Toolbox for MATLAB R 19 Copyright c Peter Corke 2011 . CentralCamera Perspective camera class A concrete class for a central-projection perspective camera.p. FUNCTIONS AND CLASSES Camera. The camera coordinate system is: 0------------> u X | | | + (principal point) | | Z-axis is into the page. a subclass of Camera.CHAPTER 2.rpy(R. The image is not inverted.rpy(rpy) as above but rpy=[R.y].

FUNCTIONS AND CLASSES Methods project K C H invH F E invE fov ray plot hold ishold clf ﬁgure mesh point line plot camera plot line tr plot epiline ﬂowﬁeld visjac p visjac p polar visjac l visjac e rpy move centre estpose delete char display project world points camera intrinsic matrix camera matrix camera motion to homography decompose homography camera motion to fundamental matrix camera motion to essential matrix decompose essential matrix ﬁeld of view Ray3D corresponding to point plot projection of world point on image plane control hold for image plane test ﬁgure hold for image plane clear image plane ﬁgure holding the image plane draw shape represented as a mesh draw homogeneous points on image plane draw homogeneous lines on image plane draw camera in world view draw line in theta/rho format draw epipolar line compute optical ﬂow image Jacobian for point features image Jacobian for point features in polar coordinates image Jacobian for line features image Jacobian for ellipse features set camera attitude clone Camera after motion get world coordinate of camera centre estimate pose object destructor convert camera parameters to string display camera parameters Properties (read/write) npix pp rho f k p distortion T image dimensions in pixels (2 × 1) intrinsic: principal point (2 × 1) intrinsic: pixel dimensions (2 × 1) in metres intrinsic: focal length intrinsic: radial distortion vector intrinsic: tangential distortion parameters intrinsic: camera distortion [k1 k2 k3 p1 p2] extrinsic: camera pose as homogeneous transformation Machine Vision Toolbox for MATLAB R 20 Copyright c Peter Corke 2011 .CHAPTER 2.

C = CentralCamera(options) as above but with speciﬁed parameters. • Camera objects can be used in vectors and arrays See also Camera CentralCamera. Machine Vision Toolbox for MATLAB R 21 Copyright c Peter Corke 2011 .CHAPTER 2.C() is the 3×4 camera matrix. CentralCamera. FUNCTIONS AND CLASSES Properties (read only) nu nv u0 v0 number of pixels in u-direction number of pixels in v-direction principal point u-coordinate principal point v-coordinate Notes • Camera is a reference object. also known as the camera calibration or projection matrix.C Camera matrix C = C.CentralCamera Create central projection camera object C = CentralCamera() creates a central projection camera with canonic parameters: f=1 and name=’canonic’.

SphericalCamera CentralCamera. CatadioptricCamera.T and the second is a relative motion represented by the homogeneous transformation T. S ‘noise’. CentralCamera.and y-axes respectively.F(C2) is the essential matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view).Ma. D ‘distortion-bouguet’.and v-axes parallel to x. E = C. The ﬁrst view is from the current camera pose C.F(F) is the essential matrix based on the fundamental matrix F (3 × 3) and the intrinsic parameters of camera C.E Essential matrix E = C. FUNCTIONS AND CLASSES Options ‘name’. Display an image rather than points Image plane resolution: N × N or N=[W H] Image sensor size in metres (2 × 1) Principal point (2 × 1) Pixel size: S × S or S=[W H] Standard deviation of additive Gaussian noise added to returned image projections Pose of the camera as a homogeneous transformation Color of image plane background (default [1 1 0. Reference Y. camera at origin.Soatto. E = C. P ‘pixel’. optical axis is z-axis. p. D ‘default’ ‘image’.CHAPTER 2. S. SIGMA ‘pose’. S ‘centre’. F ‘distortion’.Kosecka.E(T) is the essential matrix relating two camera views. ﬁsheyecamera. u. N ‘focal’.invE Machine Vision Toolbox for MATLAB R 22 Copyright c Peter Corke 2011 .F. 2003. S. “An invitation to 3D”. f=8mm.177 See also CentralCamera.8]) See also Camera. J. C Name of camera Focal length [metres] Distortion vector [k1 k2 k3 p1 p2] Distortion vector [k1 k2 p1 p2 k3] Default camera parameters: 1024 × 1024. IM ‘resolution’. N ‘sensor’.Sastry. 10um pixels. Springer. T ‘color’.

K Intrinsic parameter matrix K = C.CHAPTER 2. S. “An invitation to 3D”.H CentralCamera.F(T) is the fundamental matrix relating two camera views.T and the second is a relative motion represented by the homogeneous transformation T. p.T and the second is after a relative motion represented by the homogeneous transformation T. n. Springer.H(T.Ma.Sastry.177 See also CentralCamera.F Fundamental matrix F = C.Soatto.F(C2) is the fundamental matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view). J. Reference Y. from two viewpoints. 2003.H Homography matrix H = C.E CentralCamera. The ﬁrst view is from the current camera pose C. Machine Vision Toolbox for MATLAB R 23 Copyright c Peter Corke 2011 . d) is a 3 × 3 homography matrix for the camera observing the plane with normal n and at distance d.Kosecka. The ﬁrst view is from the current camera pose C. See also CentralCamera.K() is the 3 × 3 intrinsic parameter matrix. F = C. FUNCTIONS AND CLASSES CentralCamera. S.

estpose(xyz. a = C. uv (2×N ) are the corresponding image plane coordinates. CentralCamera. In practice there are multiple solutions and s (4x4xN) is a set of homogeneous transformations representing possible camera motion.estpose Estimate pose from object model and camera view T = C. Journal on Computer Vision. Lepetit. Fua.ﬂowﬁeld Optical ﬂow C.ﬂowﬁeld(v) displays the optical ﬂow pattern for a sparse grid of points when the camera has a spatial velocity v (6 × 1). and P. 81. Int. FUNCTIONS AND CLASSES CentralCamera.fov Camera ﬁeld-of-view angles.CHAPTER 2. 155-166. Machine Vision Toolbox for MATLAB R 24 Copyright c Peter Corke 2011 . Feb. vol. V. CentralCamera. pp. Moreno-Noguer.invE Decompose essential matrix s = C. See also quiver CentralCamera. uv) is an estimate of the pose of the object deﬁned by coordinates xyz (3×N ) in its own coordinate frame.invE(E) decomposes the essential matrix E (3 × 3) into the camera motion.fov() are the ﬁeld of view angles (2 × 1) in radians for the camera x and y (horizontal and vertical) directions. Reference “EPnP: An accurate O(n) solution to the PnP problem”. 2009. F.

Springer. “Multiview Geometry”. camera motion as a homogeneous transform matrix (4 × 4). s.invE(E. Chap 9. In practice there are multiple solutions and s is a vector of structures with elements: • T. J. 2003. p120122 Notes • The transformation is from view 1 to view 2. translation not to scale • n. 259 Y. Reference Y. See also CentralCamera. “An invitation to 3D”.3 Machine Vision Toolbox for MATLAB R 25 Copyright c Peter Corke 2011 . p.E CentralCamera.Sastry. normal vector to the plane (3 × 3) Notes • There are up to 4 solutions • Only those solutions that obey the positive depth constraint are returned • The required camera intrinsics are taken from the camera object • The transformation is from view 1 to view 2. s. p116.Soatto. s. Reference Hartley & Zisserman. Springer.invH Decompose homography matrix s = C. 2003.Sastry.Kosecka.invH(H) decomposes the homography H (3 × 3) into the camera motion and the normal to the plane. p) as above but only solutions in which the world point p is visible are returned.Soatto.Ma.Ma. s.Kosecka. “An invitation to 3D”. section 5.CHAPTER 2. FUNCTIONS AND CLASSES s = C. J.

See also Hough CentralCamera. Options Transform all points by the homogeneous transformation T before projecting them to the camera image plane. FUNCTIONS AND CLASSES See also CentralCamera.T.plot epiline Plot epipolar line C. ‘Tcam’.plot epiline(f. one per line.plot epiline(f. If Tcam (4x4xS) is a transform sequence then uv (2xNxS) represents the sequence of projected points as the camera moves in the world. C. options) are the image plane coordinates (2 × N ) corresponding to the world points p (3 × N ). Temporarily overrides the current camera pose C. p. T Machine Vision Toolbox for MATLAB R 26 Copyright c Peter Corke 2011 .project Project world points to image plane uv = C.CHAPTER 2. p) plots the epipolar lines due to the fundamental matrix f and the image points p.plot line tr Plot line in theta-rho format CentralCamera. ls) as above but draw lines using the line style arguments ls.H CentralCamera.plot line tr(L) plots lines on the camera’s image plane that are described by columns of L with rows theta and rho respectively.plot epiline(f. p) as above but return a vector of graphic handles. T Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane. ‘Tobj’. H = C. CentralCamera.project(p.

pp. Reference B.CHAPTER 2. Chaumette.ray 3D ray for image point R = C. Reference Hartley & Zisserman. 8. F. Rives. pl) is the image Jacobian (5 × 6) for the ellipse E (5 × 1) described by u2 + E1v2 . one for each point deﬁned by the columns of p. June 1992. The Jacobian gives the rates of change of the ellipse parameters in terms of camera spatial velocity.ray(p) returns a vector of Ray3D objects.b. IEEE Transactions on Robotics and Automation. Espiau. “Multiview Geometry”.c.plot CentralCamera.2E2uv + 2E3u + 2E4v + E5 = 0. vol. See also Camera. and P. 313-326. p 162 See also Ray3D CentralCamera.d) such that aX + bY + cZ + d = 0. FUNCTIONS AND CLASSES If Tobj (4x4x) is a transform sequence then uv (2xNxS) represents the sequence of projected points as the object moves in the world. Machine Vision Toolbox for MATLAB R 27 Copyright c Peter Corke 2011 . The ellipse lies in the world plane pl = (a. “A New Approach to Visual Servoing in Robotics”.visjac e(E.visjac e Visual motion Jacobian for point feature J = C.

Reference B.CHAPTER 2. or a vector (N × 1) of depth for each point. “A New Approach to Visual Servoing in Robotics”. pp. The Jacobian gives the image-plane point velocity in terms of camera spatial velocity. See also CentralCamera. Machine Vision Toolbox for MATLAB R 28 Copyright c Peter Corke 2011 . CentralCamera. Reference “A tutorial on Visual Servo Control”.visjac l(L. June 1992. Rives.visjac p Visual motion Jacobian for point feature J = C. 8. CentralCamera.b. and P. 313-326. and the rows are theta and rho respectively.visjac p(uv. CentralCamera. IEEE Transactions on Robotics and Automation. Hutchinson.visjac p polar. CentralCamera. Hager & Corke. pp 651-670.d) such that aX + bY + cZ + d = 0. FUNCTIONS AND CLASSES See also CentralCamera. z) is the image Jacobian (2N × 6) for the image plane points uv (2 × N ). pl) is the image Jacobian (2N × 6) for the image plane lines L (2 × N ).visjac p polar. vol.visjac e CentralCamera. Vol 12(5).visjac p. Chaumette. IEEE Trans.visjac p. R&A. The lines all lie in the plane pl = (a.c. Espiau. F.visjac l Visual motion Jacobian for line feature J = C. The depth of the points from the camera is given by z which is a scalar for all points. The Jacobian gives the rates of change of the line parameters in terms of camera spatial velocity. Oct. Each column of L is a line in theta-rho format.visjac l CentralCamera. 1996.

Spindler. The Jacobian gives the image-plane polar point coordinate velocity in terms of camera spatial velocity. radius and theta.visjac p polar Visual motion Jacobian for point feature J = C. or a vector (N × 1) of depths for each point. Corke. z) is the image Jacobian (2N × 6) for the image plane points rt (2 × N ) described in polar form.visjac e SiftPointFeature SIFT point corner feature object A subclass of PointFeature for SIFT features.visjac l.visjac p polar(rt. CentralCamera. See also CentralCamera. (St. P. F. 2009. I. Oct. Louis). Int. FUNCTIONS AND CLASSES See also CentralCamera. and F. 5962-5967.visjac l. Reference “Combining Cartesian and polar coordinates in IBVS”.visjac e CentralCamera. in Proc. Machine Vision Toolbox for MATLAB R 29 Copyright c Peter Corke 2011 . pp. Chaumette. CentralCamera. CentralCamera.CHAPTER 2.visjac p. CentralCamera.visjac p polar. The depth of the points from the camera is given by z which is a scalar for all point. Conf on Intelligent Robots and Systems (IROS).

Journal on Computer Vision. If F is a vector (N ×1) of SiftCornerFeature objects then F. PointFeature. See also isift.SIFT. Nov. • SiftCornerFeature objects can be used in vectors and arrays • The SIFT algorithm is patented and not distributed with this toolbox.u is a 2×N matrix with each column the corresponding u coordinate. ScalePointFeature. See README. FUNCTIONS AND CLASSES Methods plot plot scale distance match ncc uv display char Plot feature position Plot feature scale Descriptor distance Match features Descriptor similarity Return feature coordinate Display value Convert value to string Properties u horizontal coordinate v vertical coordinate strength feature strength theta feature orientation [rad] scale feature scale descriptor feature descriptor (vector) index of image containing feature image id Properties of a vector of SiftCornerFeature objects are returned as a vector. vol. 2004. You can download a SIFT implementation which this class can utilize. References “Distinctive image features from scale-invariant keypoints”. Int. Notes • SiftCornerFeature is a reference object. D. pp. SurfPointFeature Machine Vision Toolbox for MATLAB R 30 Copyright c Peter Corke 2011 .91-110.Lowe.CHAPTER 2.60.

options) is a vector of FeatureMatch objects that describe candidate matches between the two vectors of SIFT features F and f2. 1=opaque. f = PointFeature(u. ls) as above but the optional line style arguments ls are passed to plot. C ‘alpha’.match Match SIFT point features m = F. A Indicate scale by a circle (default) Indicate scale by circle with one radial line for orientation Indicate scale and orientation by an arrow Indicate scale by a translucent disk Color of circle or disk (default green) Transparency of disk. strength) as above but with speciﬁed strength. f = PointFeature(u.SiftPointFeature Create a SIFT point feature object f = SiftPointFeature() is a point feature object with null parameters. See also isift SiftPointFeature.CHAPTER 2. SiftPointFeature. F. 0=transparent (default 0. If F is a vector then each element is plotted.plot scale(options. v. FUNCTIONS AND CLASSES SiftPointFeature.plot scale Plot feature scale F.2) Machine Vision Toolbox for MATLAB R 31 Copyright c Peter Corke 2011 . Correspondence is based on descriptor similarity.match(f2. Options ‘circle’ ‘clock’ ‘arrow’ ‘disk’ ‘color’.plot scale(options) overlay a marker to indicate feature point position and scale. v) is a point feature object with speciﬁed coordinates.

support(im. w) as above but the support region is displayed. See also SiftPointFeature SphericalCamera Spherical camera class A concrete class a spherical-projection camera.support(im.T] = F.support(images.support Support region of feature out = F.CHAPTER 2. w) as above but if the features were extracted from an image sequence images then the feature is extracted from the appropriate image in the same sequence. FUNCTIONS AND CLASSES SiftPointFeature. The support region is scaled to w × w and rotated so that the feature’s orientation axis is upward. F. w) as above but returns the pose of the feature as a 3 × 3 homogeneous transform in SE(2) that comprises the feature position and orientation.support(images. out = F. w) is an image of the support region of the feature F. extracted from the image im in which the feature appears. [out. Machine Vision Toolbox for MATLAB R 32 Copyright c Peter Corke 2011 .

FUNCTIONS AND CLASSES Methods project plot hold ishold clf ﬁgure mesh point line plot camera rpy move centre delete char display project world points plot/return world point on image plane control hold for image plane test ﬁgure hold for image plane clear image plane ﬁgure holding the image plane draw shape represented as a mesh draw homogeneous points on image plane draw homogeneous lines on image plane draw camera set camera attitude copy of Camera after motion get world coordinate of camera centre object destructor convert camera parameters to string display camera parameters Properties (read/write) npix pp rho T image dimensions in pixels (2 × 1) intrinsic: principal point (2 × 1) intrinsic: pixel dimensions (2 × 1) in metres extrinsic: camera pose as homogeneous transformation Properties (read only) nu nv number of pixels in u-direction number of pixels in v-direction Note • SphericalCamera is a reference object. • SphericalCamera objects can be used in vectors and arrays See also Camera Machine Vision Toolbox for MATLAB R 33 Copyright c Peter Corke 2011 .CHAPTER 2.

T Transform all points by the homogeneous transformation T before projecting them to the camera image plane. Options ‘Tobj’.CHAPTER 2. CatadioptricCamera SphericalCamera.project(p.plot Machine Vision Toolbox for MATLAB R 34 Copyright c Peter Corke 2011 . S ‘pose’. T Name of camera Pixel size: S × S or S(1)xS(2) Pose of the camera as a homogeneous transformation See also Camera. each column is phi (longitude) and theta (colatitude).project Project world points to image plane pt = C. N ‘pixel’. Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane. See also SphericalCamera. options) are the image plane coordinates for the world points p.T. T ‘Tcam’. ﬁsheyecamera. Overrides the current camera pose C. The columns of p (3 × N ) are the world points and the columns of pt (2 × N ) are the corresponding spherical projection points. CentralCamera. C = CentralCamera(options) as above but with speciﬁed parameters.SphericalCamera Create spherical projection camera object C = SphericalCamera() creates a spherical projection camera with canonic parameters: f=1 and name=’canonic’. FUNCTIONS AND CLASSES SphericalCamera. Options ‘name’.

sph Implement spherical IBVS for point features results = sph(T) results = sph(T. showing the target points and the camera The results structure contains time-history information about the image plane. error.0. showing the desired view (*) and the current view (o) Machine Vision Toolbox for MATLAB R 35 Copyright c Peter Corke 2011 .sph2 Implement spherical IBVS for point features results = sph(T) results = sph(T. camera pose.01) .camera intrinsic structure (camparam) . scalar for If null take actual value all points. Jacobian condition number. The camera/robot is initially at pose T and is driven to the orgin.depth of points to use for Jacobian.a stopping criteria on feature error norm (0) .5) target center . Two windows are shown and animated: 1.center of the target in world coords (0. params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. defaults in parentheses: target size . The camera view. of 4-vector. showing the desired view (*) and the current view (o) 2. FUNCTIONS AND CLASSES SphericalCamera.CHAPTER 2. can be scalar or diagonal 6 × 6 matrix (0. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera.2) niter eterm lambda ci depth . The camera view. error norm. The external view. The camera/robot is initially at pose T and is driven to the orgin.gain.the side length of the target in world units (0. Two windows are shown and animated: 1. The params structure can be used to override simulation defaults by providing elements.the number of iterations to run the simulation (500) . image plane size and desired feature locations.

See also CentralCamera.0. IEEE Int.visjac l.the side length of the target in world units (0. image plane size and desired feature locations. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera. FUNCTIONS AND CLASSES 2. of 4-vector. I. error. defaults in parentheses: target size . for all points. camera pose. CentralCamera.camera intrinsic structure (camparam) .center of the target in world coords (0.a stopping criteria on feature error norm (0) . (Anchorage). in Proc.depth of points to use for Jacobian.gain. Conf.CHAPTER 2.visjac p(pt. scalar for If null take actual value all points. The depth of the points from the camera is given by z which is a scalar.3) niter eterm lambda ci depth . The params structure can be used to override simulation defaults by providing elements. or a vector (N × 1) for each point. Jacobian condition number. Robotics and Automation.the number of iterations to run the simulation (500) .5) target center .01) . The external view. The Jacobian gives the image-plane velocity in terms of camera spatial velocity. P. pp. CentralCamera.visjac p polar. Corke. showing the target points and the camera The results structure contains time-history information about the image plane. Reference “Spherical image-based visual servo and structure estimation”. z) is the image Jacobian (2N × 6) for the image plane points pt (2 × N ) described by phi (longitude) and theta (colatitude). can be scalar or diagonal 6 × 6 matrix (0.visjac p Visual motion Jacobian for point feature J = C. 5550-5555. May 3-7 2010. error norm.visjac e Machine Vision Toolbox for MATLAB R 36 Copyright c Peter Corke 2011 .

110. Tinne Tuytelaars. 2008 Machine Vision Toolbox for MATLAB R 37 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES SurfPointFeature SURF point corner feature object A subclass of PointFeature for SURF features. 3. Computer Vision and Image Understanding (CVIU). “SURF: Speeded Up Robust Features”. No. pp. Andreas Ess. 346–359.CHAPTER 2. • SurfCornerFeature objects can be used in vectors and arrays Reference Herbert Bay. If F is a vector (N × 1) of SurfCornerFeature objects then F. Vol.u is a 2 × N matrix with each column the corresponding u coordinate. Notes • SurfCornerFeature is a reference object. Methods plot plot scale distance match ncc uv display char Plot feature position Plot feature scale Descriptor distance Match features Descriptor similarity Return feature coordinate Display value Convert value to string Properties u horizontal coordinate v vertical coordinate strength feature strength scale feature scale theta feature orientation [rad] descriptor feature descriptor (vector) index of image containing feature image id Properties of a vector of SurfCornerFeature objects are returned as a vector. Luc Van Gool.

[m. Options ‘thresh’. strength) as above but with speciﬁed strength. See also FeatureMatch Machine Vision Toolbox for MATLAB R 38 Copyright c Peter Corke 2011 .match Match SURF point features m = F. v) is a point feature object with speciﬁed coordinates.match(f2. FUNCTIONS AND CLASSES See also isurf.match(f2.SurfPointFeature Create a SURF point feature object f = SurfPointFeature() is a point feature object with null parameters. PointFeature. v. Correspondence is based on descriptor similarity. SiftPointFeature SurfPointFeature. See also isurf SurfPointFeature. options) is a vector of FeatureMatch objects that describe candidate matches between the two vectors of SURF features F and f2.05) Threshold at the median distance Notes • for no threshold set to [].CHAPTER 2. f = PointFeature(u. ScalePointFeature. T ‘median’ match threshold (default 0. f = PointFeature(u.C] = F. options) as above but returns a correspodence matrix where each row contains the indices of corresponding features in F and f2 respectively.

T] = F. See also SurfPointFeature Machine Vision Toolbox for MATLAB R 39 Copyright c Peter Corke 2011 . F.support(im. FUNCTIONS AND CLASSES SurfPointFeature. out = F.support(images. ls) as above but the optional line style arguments ls are passed to plot. w) as above but returns the pose of the feature as a 3 × 3 homogeneous transform in SE(2) that comprises the feature position and orientation. The support region is scaled to w × w and rotated so that the feature’s orientation axis is upward. If F is a vector then each element is plotted. 0=transparent (default 0.plot scale(options. C ‘alpha’.plot scale Plot feature scale F.support Support region of feature out = F. extracted from the image im in which the feature appears. Options ‘circle’ ‘clock’ ‘arrow’ ‘disk’ ‘color’.support(im.2) SurfPointFeature. w) as above but the support region is displayed.support(images.plot scale(options) overlay a marker to indicate feature point position and scale. F. w) as above but if the features were extracted from an image sequence images then the feature is extracted from the appropriate image in the same sequence. 1=opaque. A Indicate scale by a circle (default) Indicate scale by circle with one radial line for orientation Indicate scale and orientation by an arrow Indicate scale by a translucent disk Color of circle or disk (default green) Transparency of disk.CHAPTER 2. [out. w) is an image of the support region of the feature F.

Machine Vision Toolbox for MATLAB R 40 Copyright c Peter Corke 2011 . otherwise the result is not predictable.axis. Video AxisWebCamera.CHAPTER 2. S ‘resolution’. Methods grab size close char Aquire and return the next image Size of image Close the image source Convert the object parameters to human readable string See also ImageSource. Obtain an image of size S=[W H]. S Notes: Return image with uint8 pixels (default) Return image with ﬂoat pixels Return image with double precision pixels Return greyscale image Apply gamma correction with gamma=G Subsample the image by S in both directions.AxisWebCamera Axis web camera constructor a = AxisWebCamera(url.axis. • The speciﬁed ‘resolution’ must match one that the camera is capable of.com). Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’. options) is an AxisWebCamera object that acquires images from an Axis Communications (www.com) web camera. G ‘scale’. FUNCTIONS AND CLASSES AxisWebCamera Image from Axis webcam A concrete subclass of ImageSource that acquires images from a web camera built by Axis Communications (www.

close Close the image source A. BagOfWords Bag of words class The BagOfWords class holds sets of features for a number of images and supports image retrieval by comparing new images with those in the ‘bag’.display AxisWebCamera.grab Acquire image from the camera im = A.grab() is an image acquired from the web camera. FUNCTIONS AND CLASSES AxisWebCamera.close() closes the connection to the web camera.char Convert to string A.char() is a string representing the state of the camera object in human readable form. and this function will return the most recently captured image held in the camera. AxisWebCamera.CHAPTER 2. See also AxisWebCamera. Machine Vision Toolbox for MATLAB R 41 Copyright c Peter Corke 2011 . Notes • Some web cameras have a ﬁxed picture taking interval.

b2) is a new bag of words created from the feature vector f but clustered to the words (and stop words) from the existing bag b2. on Computer Vision.Sivic and A.BagOfWords Create a BagOfWords object b = BagOfWords(f. pp. Oct. Notes • Uses the MEX function vl kmeans to perform clustering (vlfeat. as produced by ISURF() for an image sequence. Conf. FUNCTIONS AND CLASSES Methods isword occurrences remove stop wordvector wordfreq similarity contains exemplars display char Return all features assigned to word Return number of occurrences of word Remove stop words Return word frequency vector Return words and their frequencies Compare two word bags List the images that contain a word Display examples of word support regions Display the parameters of the bag of words Convert the parameters of the bag of words to a string Properties K nstop nimages The number of clusters speciﬁed The number of stop words speciﬁed The number of images in the bag Reference J.org).1470-1477. Machine Vision Toolbox for MATLAB R 42 Copyright c Peter Corke 2011 . See also PointFeature BagOfWords.Zisserman. Ninth IEEE Int. f can also be a cell array. k) is a new bag of words created from the feature vector f and with k words. 2003. b = BagOfWords(f.CHAPTER 2. “Video Google: a text retrieval approach to object matching in videos”. in Proc. The features are sorted into k clusters and each cluster is termed a visual word.

options) displays examples of the support regions of the words speciﬁed by the vector w.exemplars(w.contains Find images containing word k = B.exemplars display exemplars of words B. The examples are displayed as a table of thumbR Machine Vision Toolbox for MATLAB 43 Copyright c Peter Corke 2011 . BagOfWords. Notes • This method is invoked implicitly at the command line when the result of an expression is a BagOfWords object and the command has no trailing semicolon. isurf BagOfWords. See also BagOfWords.char() is a compact string representation of a bag of words.contains(w) is a vector of the indices of images in the sequence that contain one or more instances of the word w. BagOfWords. images. FUNCTIONS AND CLASSES See also PointFeature.CHAPTER 2.char Convert to string s = B.display Display value B.char BagOfWords.display() displays the parameters of the bag in a compact human readable form.

All remaining words are renumbered so that the word labels are consecutive. BagOfWords.CHAPTER 2.wordfreq Word frequency statistics [w. BagOfWords. If w is a vector of words the result is a vector of features assigned to all the words in w.remove stop Remove stop words B.wordfreq() is a vector of word labels w and the corresponding elements of n are the number of occurrences of that word.isword(w) is a vector of feature objects that are assigned to any of the word w. Options ‘ncolumns’.isword Features from words f = B. BagOfWords. FUNCTIONS AND CLASSES nail images.remove stop(n) removes the n most frequent words (the stop words) from the bag.occurrence Word occurrence n = B.occurrence(w) is the number of occurrences of the word w across all features in the bag. The original sequence of images from which the features were extracted must be provided as images. Machine Vision Toolbox for MATLAB R 44 Copyright c Peter Corke 2011 . w Number of columns to display (default 10) Maximum number of exemplars to display from any one image (default 2) Width of each thumbnail [pixels] (default 50) BagOfWords. N ‘maxperimage’.n] = B. M ‘width’.

subclass of Camera.wordvector(J) is the word frequency vector for the J’th image in the bag. Methods project plot hold ishold clf ﬁgure mesh point line plot camera rpy move centre delete char display project world points to image plane plot/return world point on image plane control hold for image plane test ﬁgure hold for image plane clear image plane ﬁgure holding the image plane draw shape represented as a mesh draw homogeneous points on image plane draw homogeneous lines on image plane draw camera set camera attitude copy of Camera after motion get world coordinate of camera centre object destructor convert camera parameters to string display camera parameters Machine Vision Toolbox for MATLAB R 45 Copyright c Peter Corke 2011 . The vector is K × 1 and the angle between any two WFVs is an indication of image similarity. FUNCTIONS AND CLASSES BagOfWords.wordvector Word frequency vector wf = B. Notes • The word vector is expensive to compute so a lazy evaluation is performed on the ﬁrst call to this function CatadioptricCamera Catadioptric camera class A concrete class for a catadioptric camera.CHAPTER 2.

Camera CatadioptricCamera. • Camera objects can be used in vectors and arrays See also CentralCamera. FUNCTIONS AND CLASSES Properties (read/write) npix pp rho f p T image dimensions in pixels (2 × 1) intrinsic: principal point (2 × 1) intrinsic: pixel dimensions (2 × 1) [metres] intrinsic: focal length [metres] intrinsic: tangential distortion parameters extrinsic: camera pose as homogeneous transformation Properties (read only) nu nv u0 v0 number of pixels in u-direction number of pixels in v-direction principal point u-coordinate principal point v-coordinate Notes • Camera is a reference object. C = CatadioptricCamera(options) as above but with speciﬁed parameters.CatadioptricCamera Create central projection camera object C = CatadioptricCamera() creates a central projection camera with canonic parameters: f=1 and name=’canonic’.CHAPTER 2. Machine Vision Toolbox for MATLAB R 46 Copyright c Peter Corke 2011 .

Options ‘Tobj’.plot Machine Vision Toolbox for MATLAB R 47 Copyright c Peter Corke 2011 . P ‘pixel’. S ‘noise’. f=8mm.project Project world points to image plane uv = C. T Name of camera Focal length (metres) Default camera parameters: 1024 × 1024. F ‘default’ ‘projection’. ‘equisolid’. K ‘maxangle’. N ‘focal’. See also Camera. The columns of p (3 × N ) are the world points and the columns of uv (2 × N ) are the corresponding image plane points. N ‘sensor’. A ‘resolution’. Catadioptric model: ‘equiangular’ (default). 10um pixels. Image plane resolution: N × N or N=[W H]. SIGMA ‘pose’.T. FUNCTIONS AND CLASSES Options ‘name’.and v-axes parallel to x. T Transform all points by the homogeneous transformation T before projecting them to the camera image plane. ‘stereographic’ Parameter for the projection model The maximum viewing angle above the horizontal plane. S ‘centre’. optical axis is z-axis. Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane. ﬁsheyecamera. camera at origin. CatadioptricCamera.CHAPTER 2. u. Image sensor size in metres (2 × 1) Principal point (2 × 1) Pixel size: S × S or S=[W H]. Temporarily overrides the current camera pose C. SphericalCamera CatadioptricCamera.project(p. Standard deviation of additive Gaussian noise added to returned image projections Pose of the camera as a homogeneous transformation Notes • The elevation angle range is from -pi/2 (below the mirror) to maxangle above the horizontal plane. T ‘Tcam’. M ‘k’.and y-axes respectively. options) are the image plane coordinates for the world points p. ‘sine’. See also Camera.

Methods plot show ransac inlier outlier subset display char Plot corresponding points Show summary statistics of corresponding points Determine inliers and outliers Return inlier matches Return outlier matches Return a subset of matches Display value of match Convert value of match to string Properties p1 Point coordinates in view 1 (2 × 1) p2 Point coordinates in view 2 (2 × 1) p Point coordinates in view 1 and 2 (4 × 1) distance Match strength between the points Properties of a vector of FeatureMatch objects are returned as a vector. such as ScalePointFeature.CHAPTER 2. FUNCTIONS AND CLASSES FeatureMatch Feature correspondence object This class represents the correspondence between two PointFeature objects. SiftPointFeature Machine Vision Toolbox for MATLAB R 48 Copyright c Peter Corke 2011 . Note • FeatureMatch is a reference object. A vector of FeatureMatch objects can represent the correspondence between sets of points. SurfPointFeature.p1 is a 2 × N matrix with each column the corresponding view 1 point coordinate. If F is a vector (N × 1) of FeatureMatch objects then F. See also PointFeature. • FeatureMatch objects can be used in vectors and arrays • Operates with all objects derived from PointFeature. SurfPointFeature and SiftPointFeature.

char Convert to string s = M. See also PointFeature.display() displays a compact human-readable representation of the feature pair. one per element. f2) as above but the strength is set to NaN. SiftPointFeature FeatureMatch. s) is a new FeatureMatch object describing a correspondence between point features f1 and f2 with a strength of s. If M is a vector then the string has multiple lines.display Display value M. If M is a vector then the elements are printed one per line. f2. See also FeatureMatch. FUNCTIONS AND CLASSES FeatureMatch. FeatureMatch.CHAPTER 2. m = FeatureMatch(f1. Notes • Only the coordinates of the PointFeature are kept.char() is a compact string representation of the match object.char Machine Vision Toolbox for MATLAB R 49 Copyright c Peter Corke 2011 . SurfPointFeature.FeatureMatch Create a new FeatureMatch object m = FeatureMatch(f1. Notes • This method is invoked implicitly at the command line when the result of an expression is a FeatureMatch object and the command has no trailing semicolon.

p Feature point coordinate pairs p = M. Each column contains the coordinates of a pair of corresponding points [u1. Notes • Outliers are not determined until after RANSAC is run.v1. Machine Vision Toolbox for MATLAB R 50 Copyright c Peter Corke 2011 .outlier.u2. See also FeatureMatch.CHAPTER 2.inlier.outlier() is a subset of the FeatureMatch vector M that are considered to be outliers.outlier Outlier features m2 = M. FeatureMatch.inlier Inlier features m2 = M.p() is a 4 × N matrix containing the feature point coordinates. FUNCTIONS AND CLASSES FeatureMatch. See also FeatureMatch.ransac FeatureMatch. FeatureMatch.ransac FeatureMatch.inlier() is a subset of the FeatureMatch vector M that are considered to be inliers. Notes • Inliers are not determined until after RANSAC is run.v2].

FeatureMatch.CHAPTER 2.im2}) m. FeatureMatch. FeatureMatch.p FeatureMatch. See also FeatureMatch. FeatureMatch. FUNCTIONS AND CLASSES See also FeatureMatch. Machine Vision Toolbox for MATLAB R 51 Copyright c Peter Corke 2011 . See also FeatureMatch. FeatureMatch. The ﬁgure must comprise views 1 and 2 side by side.plot() M.p1 Feature point coordinates from view 1 p = M. FeatureMatch.p2.p2 Feature point coordinates from view 2 p = M.plot() overlays the correspondences in the FeatureMatch vector M on the current ﬁgure.p1.p FeatureMatch.v) properties of the feature F2 passed to the constructor. for example by: idisp({im1. These are the (u.plot(ls) as above but the optional line style arguments ls are passed to plot. These are the (u.p1() is a 2 × N matrix containing the feature points coordinates from view 1.p2() is a 2 × N matrix containing the feature points coordinates from view 1.plot Show corresponding points M.FeatureMatch.p1.p2 FeatureMatch.v) properties of the feature F1 passed to the constructor.

See also idisp FeatureMatch.ransac( @fmatrix. ransac FeatureMatch. Example f1 = isurf(im1). Elements of the FeatureMatch vector have their status updated in place to indicate whether they are inliers or outliers. See also fmatrix.show Display summary statistics of the FeatureMatch vector M. inliers and outliers (and their percentages). m = f1.show() is a compact summary of the FeatureMatch vector M that gives the number of matches. The options are passed to the RANSAC() function. Machine Vision Toolbox for MATLAB R 52 Copyright c Peter Corke 2011 . 1e-4). f2 = isurf(im2).CHAPTER 2.ransac Apply RANSAC M. m. options) applies the RANSAC algorithm to ﬁt the point correspondences to the model described by the function func. and an error is created if this UserData is not found.ransac(func. FUNCTIONS AND CLASSES Notes • Using IDISP as above adds UserData to the ﬁgure. homography.match(f2).

subset(n) is a FeatureMatch vector with no more than n elements sampled uniformly from M. The camera coordinate system is: 0------------> u.subset Subset of matches m2 = M. v. X | | | + (principal point) | | Z-axis is into the page. Y This camera model assumes central projection.CHAPTER 2. FishEyeCamera Fish eye camera class A concrete class a ﬁsheye lense projection camera. The image is not inverted. FUNCTIONS AND CLASSES FeatureMatch. that is. Methods project plot hold ishold clf ﬁgure mesh point line plot camera rpy move centre delete char display project world points to image plane plot/return world point on image plane control hold for image plane test ﬁgure hold for image plane clear image plane ﬁgure holding the image plane draw shape represented as a mesh draw homogeneous points on image plane draw homogeneous lines on image plane draw camera set camera attitude copy of Camera after motion get world coordinate of camera centre object destructor convert camera parameters to string display camera parameters Machine Vision Toolbox for MATLAB R 53 Copyright c Peter Corke 2011 . the focal point is at z=0 and the image plane is at z=f.

N ‘sensor’. ‘stereographic’ Parameter for the projection model Image plane resolution: N × N or N=[W H].axes respectively. P ‘pixel’. Image sensor size [metres] (2 × 1) Principal point (2 × 1) Pixel size: S × S or S=[W H]. Options ‘name’. S ‘centre’. SIGMA ‘pose’.CHAPTER 2. f=8mm. • Camera objects can be used in vectors and arrays See also Camera FishEyeCamera. Standard deviation of additive Gaussian noise added to returned image projections Pose of the camera as a homogeneous transformation R Machine Vision Toolbox for MATLAB 54 Copyright c Peter Corke 2011 . T Name of camera Default camera parameters: 1024 × 1024. ‘sine’. camera at origin. Fisheye model: ‘equiangular’ (default).and v-axes are parallel to x. 10um pixels. K ‘resolution’. N ‘default’ ‘projection’. u. C = FishEyeCamera(options) as above but with speciﬁed parameters.and y. S ‘noise’. FUNCTIONS AND CLASSES Properties (read/write) npix pp f rho T image dimensions in pixels (2 × 1) intrinsic: principal point (2 × 1) intrinsic: focal length [metres] intrinsic: pixel dimensions (2 × 1) [metres] extrinsic: camera pose as homogeneous transformation Properties (read only) nu nv number of pixels in u-direction number of pixels in v-direction Notes • Camera is a reference object. optical axis is z-axis. M ‘k’.FishEyeCamera Create ﬁsheyecamera object C = FishEyeCamera() creates a ﬁsheye camera with canonic parameters: f=1 and name=’canonic’. ‘equisolid’.

CHAPTER 2. SphericalCamera FishEyeCamera.project Project world points to image plane uv = C. The columns of p (3 × N ) are the world points and the columns of uv (2 × N ) are the corresponding image plane points. Options ‘Tobj’.plot Hough Hough transform class The Hough transform is a technique for ﬁnding lines in an image using a voting scheme. See also Camera. T Transform all points by the homogeneous transformation T before projecting them to the camera image plane. FUNCTIONS AND CLASSES Notes • If K is not speciﬁed it is computed such that the circular imaging region maximally ﬁlls the square image plane. CatadioptricCamera. T ‘Tcam’. For every edge pixel in the input image a set of cells in the Hough accumulator (voting array) are incremented. Temporarily overrides the current camera pose C.project(p. options) are the image plane coordinates for the world points p. See also FishEyeCamera. Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane. CentralCamera. In this version of the Hough transform lines are described by: d = y cos(theta) + x sin(theta) Machine Vision Toolbox for MATLAB R 55 Copyright c Peter Corke 2011 .T.

Offset is in the range -rho max to rho max where rho max=max(W. Methods plot show lines char display Overlay detected lines Display the Hough accumulator Return line features Convert Hough parameters to string Display Hough parameters Properties Nrho Ntheta A rho theta edgeThresh houghThresh suppress interpWidth Number of bins in rho direction Number of bins in theta direction The Hough accumulator (Nrho x Ntheta) rho values for the centre of each bin vertically Theta values for the centre of each bin horizontally Threshold on relative edge pixel strength Threshold on relative peak strength Radius of accumulator cells cleared around peak Width of region used for peak interpolation Notes • Hough is a reference object.CHAPTER 2. a vertical line has theta = pi/2 or -pi/2. By default the vote is incremented by Machine Vision Toolbox for MATLAB R 56 Copyright c Peter Corke 2011 . A horizontal line has theta = 0. FUNCTIONS AND CLASSES where theta is the angle the line makes to horizontal axis. The voting array is 2-dimensional. See also LineFeature Hough. Theta spans the range -pi/2 to pi/2 in Ntheta steps.0) and the line.Hough Create Hough transform object ht = Hough(E. with columns corresponding to theta and rows corresponding to offset (d). For every pixel in the edge image E (H ×W ) greater than a threshold the corresponding elements of the accumulator are incremented. and d is the perpendicular distance between (0. options) is the Hough transform of the edge image E.H).

char() is a compact string representation of the Hough transform parameters. Hough. if N is scalar set Nrho=Ntheta=N.CHAPTER 2. Set ht. T ‘edgethresh’.edgeThresh (default 0. T ‘suppress’. W ‘houghthresh’. See also Hough.display Display value HT.5) Set ht. Nrho].char Machine Vision Toolbox for MATLAB R 57 Copyright c Peter Corke 2011 . otherwise the edge pixel value is the vote strength Interpolation width (default 3) Set ht. Default 400 × 401. The threshold is determined from the maximum edge strength value x ht.suppress (default 0) Set number of bins. FUNCTIONS AND CLASSES the edge strength but votes can be made equal with the option ‘equal’.1). W ‘nbins’.char Convert to string s = HT.edgeThresh. N All edge pixels have equal weight.display() displays a compact human-readable string representation of the Hough transform parameters. else N = [Ntheta. Notes • This method is invoked implicitly at the command line when the result of an expression is a Hough object and the command has no trailing semicolon. Hough. Options ‘equal’ ‘interpwidth’.houghThresh (default 0.

plot.plot() overlays all detected lines on the current ﬁgure. LineFeature Hough.lines() is a vector of LineFeature objects that represent the dominant lines in the Hough accumulator. The peak detection loop breaks early if the remaining peak has a strength less than HT. ls) as above but the optional line style arguments ls are passed to plot. reﬁned to subpixel precision. See also Hough.show Display the Hough accumulator as image s = HT. HT.lines Find lines L = HT.plot() as above but returns a vector of graphics handles for each line. HT.lines(n) as above but returns no more than n LineFeature objects. Lines are the coordinates of peaks in the Hough accumulator. where ‘heat’ is proportional to the number of votes. See also Hough.show() displays the Hough vote accumulator as an image using the hot colormap. then all elements in an HT.lines Hough.suppress radius around are zeroed so as to eliminate multiple close minima.houghThresh times the maximum vote value. L = HT.CHAPTER 2.plot(n. H = HT. Machine Vision Toolbox for MATLAB R 58 Copyright c Peter Corke 2011 . The process is repeated for all peaks.plot(n) overlays a maximum of n strongest lines on the current ﬁgure. FUNCTIONS AND CLASSES Hough. The highest peak is found.plot Plot line features HT.

CHAPTER 2. • LineFeature objects can be used in vectors and arrays See also Hough. PointFeature Machine Vision Toolbox for MATLAB R 59 Copyright c Peter Corke 2011 . If L is a vector (N × 1) of LineFeature objects then L. Methods plot seglength display char Plot the line segment Determine length of line segment Display value Convert value to string Properties rho Offset of the line theta Orientation of the line strength Feature strength length Length of the line Properties of a vector of LineFeature objects are returned as a vector.rho is an N × 1 vector of the rho element of each feature. RegionFeature. hot LineFeature Line feature class This class represents a line feature. FUNCTIONS AND CLASSES See also colormap. Note • LineFeature is a reference object.

Notes • This method is invoked implicitly at the command line when the result of an expression is a LineFeature object and the command has no trailing semicolon.CHAPTER 2. strength. theta.char Machine Vision Toolbox for MATLAB R 60 Copyright c Peter Corke 2011 .char() is a compact string representation of the line feature. one per element.display() displays a compact human-readable representation of the feature. If L is a vector then the elements are printed one per line. If L is a vector then the string has multiple lines. LineFeature. length) is a line feature object with the speciﬁed properties.display Display value L. L = LineFeature(rho. FUNCTIONS AND CLASSES LineFeature.LineFeature Create a line feature object L = LineFeature() is a line feature object with null parameters. strength) is a line feature object with the speciﬁed properties. theta. LENGTH is undeﬁned. L = LineFeature(l2) is a deep copy of the line feature l2. L = LineFeature(rho. LineFeature.char Convert to string s = L. See also LineFeature.

See also icanny Machine Vision Toolbox for MATLAB R 61 Copyright c Peter Corke 2011 .seglength Compute length of line segments The Hough transform identiﬁes lines but cannot determine their length.points(edge) is the set of points that lie along the line in the edge image edge are determined. l2 = L.plot(ls) as above but the optional line style arguments ls are passed to plot.plot Plot line L. FUNCTIONS AND CLASSES LineFeature. LineFeature. L. Small gaps.CHAPTER 2.seglength(edge) as above but the maximum allowable gap is 5 pixels.seglength(edge. gap) is a copy of the line feature object with the property length updated to the length of the line (pixels). l2 = L. less than gap pixels are tolerated.points Return points on line segments p = L. This method examines the edge pixels in the original image and determines the longest stretch of non-zero pixels along the line.plot() overlay the line on current plot. Notes • If L is a vector then each element is plotted. See also icanny LineFeature.

char() is a string representing the state of the movie object in human readable form.close Close the image source M. Movie.close() closes the connection to the movie. G ‘scale’. S ‘skip’.char Convert to string M. Movie. options) is an Movie object that returns frames from the movie ﬁle ﬁle.com).Movie Image source constructor m = Movie(ﬁle.CHAPTER 2. S Return image with uint8 pixels (default) Return image with ﬂoat pixels Return image with double precision pixels Return greyscale image Apply gamma correction with gamma=G Subsample the image by S in both directions Read every S’th frame from the movie Movie. Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’. Machine Vision Toolbox for MATLAB R 62 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES Movie Class to read movie ﬁle A concrete subclass of ImageSource that acquires images from a web camera built by Axis Communications (www.axis.

S ‘frame’. Options ‘skip’. FUNCTIONS AND CLASSES Movie.CHAPTER 2. and return current+S frame Return frame F within the movie Notes • If no output argument given the image is displayed using IDISP. Machine Vision Toolbox for MATLAB R 63 Copyright c Peter Corke 2011 . PGraph Simple graph class g = PGraph() g = PGraph(n) create a 2D. planar. F Skip frames. eid Graph connectivity is maintained by a labeling algorithm and this is updated every time an edge is added. vid • edges are represented by integer ids.grab() acquires the next image from the movie im = M. undirected graph create an n-d.grab Acquire next frame from movie im = M.grab(options) as above but allows the next frame to be speciﬁed. undirected graph Graphs • are undirected • are symmetric cost edges (A to B is same cost as B to A) • are embedded in coordinate system • have no loops (edges from A to A) • vertices are represented by integer ids.

Object properties (read/write) g.plot() g.n number of nodes Machine Vision Toolbox for MATLAB R 64 Copyright c Peter Corke 2011 .connectivity() g.add node(coord) g.cost(e) g.clear() add vertex.coord(v) g.distances(coord) return sorted distances from coord and vertices To change the distance metric create a subclass of PGraph and override the method distance metric(). return vid add edge from v1 to v2.component(v) g.closest(coord) return vertex closest to coord g.add edge(v1.CHAPTER 2.distance(v1.pick() char(g) return vid for edge return cost for edge list return coordinate of node v return vid for edge return component id for vertex return number of edges for all nodes set goal vertex for path planning return vertex id closest to picked point display summary info about the graph Planning paths through the graph g.neighbours(v) g. FUNCTIONS AND CLASSES Methods Constructing the graph g.path(v) set goal vertex. v) g. v2) distance between v1 and v2 as the crow ﬂies g. and plan paths return d of neighbour of v closest to goal return list of nodes from v to goal Graph and world points g.edges(e) g. return eid remove all nodes and edges from the graph Information from graph g. return vid add vertex and edge to v.next(v) g.add node(coord. v2) g.goal(v) g.

v2) add an edge between nodes with id v1 and v2. PGraph.CHAPTER 2. Machine Vision Toolbox for MATLAB R 65 Copyright c Peter Corke 2011 .add node(x) adds a node with coordinate x.add node Add a node to the graph v = G. E = G. Options ‘distance’.add node(x.add node(x. PGraph. where x is D × 1. v. FUNCTIONS AND CLASSES PGraph. M ‘verbose’ Use the distance metric M for path planning Specify verbose operation Note • The distance metric is either ‘Euclidean’ or ‘SE2’ which is the sum of the squares of the difference in position and angle modulo 2pi. and returns the edge id E. options) returns a graph object embedded in d dimensions. C) add an edge between nodes with id v1 and v2 with cost C. v) adds a node with coordinate x and connected to node v by an edge.add edge Add an edge to the graph E = G. and returns the node id v. C) adds a node with coordinate x and connected to node v by an edge with cost C. v2. v = G.add edge(v1.PGraph Graph class constructor g = PGraph(d.add edge(v1. v = G.

PGraph. PGraph.char() returns a compact human readable representation of the state of the graph including the number of vertices.coord Coordinate of node x = G. D × 1. of node id v.CLEAR() removes all nodes and edges. PGraph.connectivity() returns the total number of edges in the graph. FUNCTIONS AND CLASSES PGraph. PGraph. Machine Vision Toolbox for MATLAB R 66 Copyright c Peter Corke 2011 .connectivity Graph connectivity C = G.closest Find closest node v = G.clear Clear the graph G. edges and components.closest(x) return id of node geometrically closest to coordinate x. [v.d] = G.char Convert graph to string s = G.CHAPTER 2.CLOSEST(x) return id of node geometrically closest to coordinate x.coord(v) return coordinate vector. and the distance d.

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.cost

Cost of edge

C = G.cost(E) return cost of edge id E.

PGraph.display

Display state of the graph

G.display() displays a compact human readable representation of the state of the graph including the number of vertices, edges and components.

See also

PGraph.char

PGraph.distance

Distance between nodes

d = G.distance(v1, v2) return the geometric distance between the nodes with id v1 and v2.

PGraph.distances

distance to all nodes

d = G.distances(v) returns vector of geometric distance from node id v to every other node (including v) sorted into increasing order by d. [d,w] = G.distances(v) returns vector of geometric distance from node id v to every other node (including v) sorted into increasing order by d where elements of w are the corresponding node id.

Machine Vision Toolbox for MATLAB

R

67

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.edges

Find edges given vertex

E = G.edges(v) return the id of all edges from node id v.

PGraph.goal

Set goal node

G.goal(vg) for least-cost path through graph set the goal node. The cost of reaching every node in the graph connected to vg is computed.

See also

PGraph.path cost is total distance from goal

PGraph.neighbours

Neighbours of a node

n = G.neighbours(v) return a vector of ids for all nodes which are directly connected neighbours of node id v. [n,C] = G.neighbours(v) return a vector n of ids for all nodes which are directly connected neighbours of node id v. The elements of C are the edge costs of the paths to the corresponding node ids in n.

PGraph.next

Find next node toward goal

v = G.next(vs) return the id of a node connected to node id vs that is closer to the goal.

See also

PGraph.goal, PGraph.path

Machine Vision Toolbox for MATLAB

R

68

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.path

Find path to goal node

p = G.path(vs) return a vector of node ids that form a path from the starting node vs to the previously speciﬁed goal. The path includes the start and goal node id.

See also

PGraph.goal

PGraph.pick

Graphically select a node

v = G.pick() returns the id of the node closest to the point clicked by user on a plot of the graph.

See also

PGraph.plot

PGraph.plot

Plot the graph

G.plot(opt) plot the graph in the current ﬁgure. Nodes are shown as colored circles.

Options

‘labels’ ‘edges’ ‘edgelabels’ ‘MarkerSize’, S ‘MarkerFaceColor’, C ‘MarkerEdgeColor’, C ‘componentcolor’ Display node id (default false) Display edges (default true) Display edge id (default false) Size of node circle Node circle color Node circle edge color Node color is a function of graph component

Machine Vision Toolbox for MATLAB

R

69

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.showComponent

t

G.showcomponent(C) plots the nodes that belong to graph component C.

PGraph.showVertex

Highlight a vertex

G.showVertex(v) highlights the vertex v with a yellow marker.

PGraph.vertices

Find vertices given edge

v = G.vertices(E) return the id of the nodes that deﬁne edge E.

PointFeature

PointCorner feature object

A superclass for image corner features.

Methods

plot distance ncc uv display char Plot feature position Descriptor distance Descriptor similarity Return feature coordinate Display value Convert value to string

Machine Vision Toolbox for MATLAB

R

70

Copyright c Peter Corke 2011

f = PointFeature(u. If F is a vector then the elements are printed one per line. SurfPointFeature.char Convert to string s = F. If F is a vector (N × 1) of PointFeature objects then F.char() is a compact string representation of the point feature. one per element. v.CHAPTER 2. Notes • This method is invoked implicitly at the command line when the result of an expression is a PointFeature object and the command has no trailing semicolon. strength) as above but with speciﬁed strength. Machine Vision Toolbox for MATLAB R 71 Copyright c Peter Corke 2011 . PointFeature. FUNCTIONS AND CLASSES Properties u horizontal coordinate v vertical coordinate strength feature strength descriptor feature descriptor (vector) Properties of a vector of PointFeature objects are returned as a vector.u is a 2 × N matrix with each column the corresponding point coordinate. SiftPointFeature PointFeature. If F is a vector then the string has multiple lines.display() displays a compact human-readable representation of the feature. v) is a point feature object with speciﬁed coordinates.PointFeature Create a point feature object f = PointFeature() is a point feature object with null parameters.display Display value F. f = PointFeature(u. PointFeature. See also ScalePointFeature.

PointFeature.distance(f1) is the distance between feature descriptors.match(f2. FUNCTIONS AND CLASSES See also PointFeature.match Match point features m = F.C] = F. T ‘median’ match threshold (default 0. where 1 is perfect match. the norm of the Euclidean distance. Machine Vision Toolbox for MATLAB R 72 Copyright c Peter Corke 2011 .05) Threshold at the median distance See also FeatureMatch PointFeature. Options ‘thresh’.match(f2. options) is a vector of FeatureMatch objects that describe candidate matches between the two vectors of point features F and f2.ncc Feature descriptor similarity s = F.char PointFeature.CHAPTER 2.ncc(f1) is the similarty between feature descriptors which is a scalar in the interval -1 to 1. If F is a vector then d is a vector whose elements are the distance between the corresponding element of F and f1.distance Distance between feature descriptors d = F. options) as above but returns a correspodence matrix where each row contains the indices of corresponding features in F and f2 respectively. If F is a vector then D is a vector whose elements are the distance between the corresponding element of F and f1. [m.

plot(ls) as above but the optional line style arguments ls are passed to plot. miny maxy] Number of vertices Notes • this is reference class object • Polygon objects can be used in vectors and arrays R Machine Vision Toolbox for MATLAB 73 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES PointFeature.plot Plot feature F. Methods plot area moments centroid perimeter transform inside intersection difference union xor display char Plot polygon Area of polygon Moments of polygon Centroid of polygon Perimter of polygon Transform polygon Test if points are inside polygon Intersection of two polygons Difference of two polygons Union of two polygons Exclusive or of two polygons print the polygon in human readable form convert the polgyon to human readable string Properties vertices extent n List of polygon vertices. F. one per column Bounding box [minx maxx.General polygon class p = Polygon(vertices). Polygon . If F is a vector then each element is plotted.CHAPTER 2.plot() overlay a marker at the feature position.

mit. Polygon.char String representation s = P. HEIGHT].html and require a licence.centroid() is the centroid of the polygon. kirill@plume.char() is a compact representation of the polgyon in human readable form. wh) is a rectangle centred at C with dimensions wh=[WIDTH.area Area of polygon a = P. Polygon.edu. Pankratov.area() is the area of the polygon.CHAPTER 2.mit. However the author does not respond to email regarding the licence. Polygon.edu/ glenn/kirill/saga. union. difference. one column per vertex. p = Polygon(C. http://puddle. FUNCTIONS AND CLASSES Acknowledgement The methods inside. Polygon. so use with care.Polygon Polygon class constructor p = Polygon(v) is a polygon with vertices given by v. intersection.centroid Centroid of polygon x = P. Machine Vision Toolbox for MATLAB R 74 Copyright c Peter Corke 2011 . and xor are based on code written by: Kirill K.

returns coordinates of P. Polygon. else 0. Notes • If polygons P and q are not intersecting.intersect Intersection of polygon with list of polygons i = P.char Polygon. See also Polygon. Polygon. FUNCTIONS AND CLASSES Polygon. Machine Vision Toolbox for MATLAB R 75 Copyright c Peter Corke 2011 .intersect(plist) indicates whether or not the Polygon P intersects with i(j) = 1 if p intersects polylist(j). The corresponding elements of in are either true or false.difference(q) is polygon P minus polygon q. resulting vertex list will contain NaNs.inside Test if points are inside polygon in = p.display() displays the polygon in a compact human readable form.difference Difference of polygons d = P.CHAPTER 2.display Display polygon P. • If the result d is not simply connected or consists of several polygons.inside(p) tests if points given by columns of p are inside the polygon.

FUNCTIONS AND CLASSES Polygon. each column is [x y]’. i is an N × 2 matrix with one column per intersection. • If intersection consist of several disjoint polygons (for non-convex P or q) then vertices of i is the concatenation of the vertices of these polygons.CHAPTER 2. q) is the pq’th moment of the polygon.perimeter Perimeter of polygon L = P. See also mpq poly Polygon. Notes • If these polygons are not intersecting.moments Moments of polygon a = P. Polygon. Machine Vision Toolbox for MATLAB R 76 Copyright c Peter Corke 2011 .intersect line(L) is the intersection points of a polygon P with the line segment L=[x1 x2.intersect line Intersection of polygon and line segment i = P. returns empty polygon. y1 y2].moments(p.perimeter() is the perimeter of the polygon. Polygon.intersection Intersection of polygons i = P.intersection(q) is a Polygon representing the intersection of polygons P and q.

Polygon.plot(ls) as above but pass the arguments ls to plot. Machine Vision Toolbox for MATLAB R 77 Copyright c Peter Corke 2011 . returns a polygon with vertices of both polygons separated by NaNs. Polygon.CHAPTER 2.transform(T) is a new Polygon object whose vertices have been transfored by the 3 × 3 homgoeneous transformation T.xor Exclusive or of polygons i = P. Notes • If these polygons are not intersecting.union(q) is a Polygon representing the union of polygons P and q. FUNCTIONS AND CLASSES Polygon.plot Plot polygon P.clockwise “outer boundary” and one or more clock-wise “inner boundaries” around “holes”. Polygon.union(q) is a Polygon representing the union of polygons P and q.union Union of polygons i = P.plot() plot the polygon. returns a polygon with vertices of both polygons separated by NaNs. • If the result P is not simply connected (such as a polygon with a “hole”) the resulting contour consist of counter. Notes • If these polygons are not intersecting.transform Transformation of polygon vertices p2 = P. P.

Ray3D Ray constructor R = Ray3D(p0. FUNCTIONS AND CLASSES • If the result P is not simply connected (such as a polygon with a “hole”) the resulting contour consist of counter. Ray3D Ray in 3D space This object represents a ray in 3D space. deﬁned by a point on the ray and a direction unit-vector.CHAPTER 2. Methods intersect closest char display Intersection of ray with plane or ray Closest distance between point and ray Ray parameters as human readable string Display ray parameters in human readable form Properties P0 d A point on the ray (3 × 1) Direction of the ray. Machine Vision Toolbox for MATLAB R 78 Copyright c Peter Corke 2011 . unit vector (3 × 1) Notes • Ray3D objects can be used in vectors and arrays Ray3D.clockwise “outer boundary” and one or more clock-wise “inner boundaries” around “holes”. d) is a new Ray3D object deﬁned by a point on the ray p0 and a direction vector d.

Machine Vision Toolbox for MATLAB R 79 Copyright c Peter Corke 2011 .intersect Intersetion of ray with line or plane x = R.CHAPTER 2. If R is a vector then then x has multiple columns. corresponding to the intersection of R(i) with r2. FUNCTIONS AND CLASSES Ray3D.char Convert to string s = R.intersect(r2) as above but also returns the closest distance between the rays.closest(p) as above but also returns the distance E between x and p.closest(p) is the point on the ray R closest to the point p.closest Closest distance between point and ray x = R.char Ray3D.intersect(r2) is the point on R that is closest to the ray r2. [x.E] = R. See also Ray3D. one per element. Ray3D.char() is a compact string representation of the Ray3D’s value.display() displays a compact human-readable representation of the Ray3D’s value.E] = R. If R is a vector then the elements are printed one per line. If R is a vector then the string has multiple lines. Notes • This method is invoked implicitly at the command line when the result of an expression is a Ray3D object and the command has no trailing semicolon.display Display value R. [x. Ray3D.

minimum horizontal coordinate bounding box.b.d) where aX + bY + cZ + d = 0. corresponding to the intersection of R(i) with p. less for other shapes a structure containing moments of order 0 to 2 Machine Vision Toolbox for MATLAB R 80 Copyright c Peter Corke 2011 . Methods boundary box plot plot boundary plot box plot ellipse display char Return the boundary as a list Return the bounding box Plot the centroid Plot the boundary Plot the bounding box Plot the equivalent ellipse Display value Convert value to string Properties uc vc umin umax vmin vmax area class label children edgepoint edge perimeter touch a b theta shape circularity moments centroid.c. horizontal coordinate centroid.intersect(p) returns the point of intersection between the ray R and the plane p=(a. FUNCTIONS AND CLASSES x = R. RegionFeature Region feature class This class represents a region feature. maximum vertical coordinate the number of pixels the value of the pixels forming this region the label assigned to this region a list of indices of features that are children of this feature coordinate of a point on the perimeter a list of edge points 2 × N matrix number of edge pixels true if region touches edge of the image major axis length of equivalent ellipse minor axis length of equivalent ellipse angle of major ellipse axis to horizontal axis aspect ratio b/a (always <= 1. If R is a vector then x has multiple columns. maximum horizontal coordinate bounding box.CHAPTER 2. minimum vertical coordinate bounding box.0) 1 for a circle. vertical coordinate bounding box.

These vectors have 400 elements irrespective of region size. RegionFeature.boundary Boundary in polar form [d.box Return bounding box b = R.RegionFeature Create a region feature object R = RegionFeature() is a region feature object with null parameters. RegionFeature. ymax]. imoments RegionFeature.char Convert to string s = R. RegionFeature. FUNCTIONS AND CLASSES Note • RegionFeature is a reference object.uc will be a list not a vector. d(i) and th(i) are the distance to the boundary point and the angle respectively.th] = R.char() is a compact string representation of the region feature.xmax.CHAPTER 2.boundary() is a polar representation of the boundary with respect to the centroid.box() is the bounding box in standard Toolbox form [xmin. If R is a vector then the string has multiple lines. ymin. • RegionFeature objects can be used in vectors and arrays • This class behaves differently to LineFeature and PointFeature when getting properties of a vector of RegionFeature objects. See also iblobs. one per element. For example R. Machine Vision Toolbox for MATLAB R 81 Copyright c Peter Corke 2011 .

plot boundary() overlay perimeter points on current plot. It is indicated with overlaid o. R.display Display value R.plot(ls) as above but the optional line style arguments ls are passed to plot.plot Plot centroid R. R. Machine Vision Toolbox for MATLAB R 82 Copyright c Peter Corke 2011 .and xmarkers. Notes • If R is a vector then each element is plotted. RegionFeature.display() is a compact string representation of the region feature.CHAPTER 2. If R is a vector then each element is plotted.char RegionFeature.plot boundary plot boundary R. If R is a vector then the elements are printed one per line. Notes • this method is invoked implicitly at the command line when the result of an expression is a RegionFeature object and the command has no trailing semicolon.plot() overlay the centroid on current plot.plot boundary(ls) as above but the optional line style arguments ls are passed to plot. See also RegionFeature. FUNCTIONS AND CLASSES RegionFeature.

CHAPTER 2.plot box() overlay the the bounding box of the region on current plot.plot box Plot bounding box R.plot ellipse(ls) as above but the optional line style arguments ls are passed to plot. If R is a vector then each element is plotted. Methods plot plot scale distance ncc uv display char Plot feature position Plot feature scale Descriptor distance Descriptor similarity Return feature coordinate Display value Convert value to string Machine Vision Toolbox for MATLAB R 83 Copyright c Peter Corke 2011 . R. R. RegionFeature.plot ellipse() overlay the the equivalent ellipse of the region on current plot. If R is a vector then each element is plotted.plot box(ls) as above but the optional line style arguments ls are passed to plot. FUNCTIONS AND CLASSES See also boundmatch RegionFeature.plot ellipse Plot equivalent ellipse R. ScalePointFeature ScalePointCorner feature object A subclass of PointFeature for features with scale.

plot scale(options) overlay a marker at the feature position. Options ‘circle’ ‘disk’ ‘color’. v) is a point feature object with speciﬁed coordinates.ScalePointFeature Create a scale point feature object f = ScalePointFeature() is a point feature object with null parameters. F. C ‘alpha’.u is a 2 × N matrix with each column the corresponding point coordinate. 0=transparent (default 0.plot scale(options. SiftPointFeature ScalePointFeature. See also PointFeature. strength) as above but with speciﬁed strength. 1=opaque. f = ScalePointFeature(u. A Indicate scale by a circle (default) Indicate scale by a translucent disk Color of circle or disk (default green) Transparency of disk. If F is a vector then each element is plotted. f = ScalePointFeature(u. v. strength. scale) as above but with speciﬁed feature scale. FUNCTIONS AND CLASSES Properties u horizontal coordinate v vertical coordinate strength feature strength scale feature scale descriptor feature descriptor (vector) Properties of a vector of ScalePointFeature objects are returned as a vector.CHAPTER 2. If F is a vector (N × 1) of ScalePointFeature objects then F.plot scale Plot feature scale F.2) Machine Vision Toolbox for MATLAB R 84 Copyright c Peter Corke 2011 . v. ScalePointFeature. ls) as above but the optional line style arguments ls are passed to plot. f = ScalePointFeature(u. SurfPointFeature.

C. N ‘thresh’. R ‘nslots’.CHAPTER 2. A complete history of all tracks is maintained. FUNCTIONS AND CLASSES Tracker Track points in image sequence This class assigns each new feature a unique identiﬁer and tracks it from frame to frame until it is lost. Machine Vision Toolbox for MATLAB R 85 Copyright c Peter Corke 2011 . During operation the image sequence is animated and the point features are overlaid along with annotation giving the unique identiﬁer of the track.8) Write the frames as images into the folder M as with sequential ﬁlenames.Tracker Create new Tracker object T = Tracker(im. The elements of the cell array are the point features for the corresponding element of the image sequence. options) is a new tracker object. T ‘movie’. Options ‘radius’. M Search radius for feature in next frame (default 20) Maximum number of tracks (default 800) Similarity threshold (default 0. im (HxWxS) is an image sequence and C (S × 1) is a cell array of vectors of PointFeature subclass objects. See also PointFeature Tracker. A vector of track history structures with elements id and uv which is the path of the feature. Methods plot tracklengths Plot all tracks Length of all tracks Properties track history A vector of structures. one per active track.

Tracker.CHAPTER 2.display() displays a compact human-readable string representation of the Tracker object Notes • This method is invoked implicitly at the command line when the result of an expression is a Tracker object and the command has no trailing semicolon. FUNCTIONS AND CLASSES See also PointFeature Tracker.char Convert to string s = T. Machine Vision Toolbox for MATLAB R 86 Copyright c Peter Corke 2011 . Tracker.char Tracker.plot() overlays the tracks of all features on the current plot.plot Show feature trajectories T.tracklengths Length of all tracks T.char() is a compact string representation of the Tracker parameters and status.display Display value T.tracklengths() is a vector containing the length of every track. See also Tracker.

AxisWebCamera. If camera is ‘?’ a list of available cameras.CHAPTER 2. FUNCTIONS AND CLASSES Video Class to read from local video camera A concrete subclass of ImageSource that acquires images from a local camera. Movie Video. and their characteristics is displayed. S ‘resolution’.Video Video camera constructor v = Video(camera. Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’. Obtain an image of size S=[W H]. Methods grab size close char Aquire and return the next image Size of image Close the image source Convert the object parameters to human readable string See also ImageSource. otherwise the result is not predictable. Machine Vision Toolbox for MATLAB R 87 Copyright c Peter Corke 2011 . G ‘scale’. S Notes: Return image with uint8 pixels (default) Return image with ﬂoat pixels Return image with double precision pixels Return greyscale image Apply gamma correction with gamma=G Subsample the image by S in both directions. • The speciﬁed ‘resolution’ must match one that the camera is capable of. options) is a Video object that acquires images from the local video camera speciﬁed by the string camera.

close() closes the connection to the camera.char() is a string representing the state of the camera object in human readable form.grab() acquires an image from the camera.char Convert to string V.close Close the image source V. Video. about x as above but this is the command rather than functional form See also whos Machine Vision Toolbox for MATLAB R 88 Copyright c Peter Corke 2011 .grab Acquire image from the camera im = V. about Compact display of variable type about(x) displays a compact line that describes the class and dimensions of x.CHAPTER 2. Video. Notes • the function will block until the next frame is acquired. FUNCTIONS AND CLASSES Video.

If th1 is a column vector. the second for right. right. color. a = anaglyph(left. The result is in the interval [-pi pi). Use this option to make the images more natural/comfortable to view. th2) returns the difference between angles th1 and th2 on the circle. Machine Vision Toolbox for MATLAB R 89 Copyright c Peter Corke 2011 . disp) as above but allows for disparity correction.CHAPTER 2. and th2 a scalar then return a column vector where th2 is modulo subtracted from the corresponding elements of th1. and each is one of: ‘r’ red ‘g’ green ‘b’ green ‘c’ cyan ‘m’ magenta a = anaglyph(left. and the right image is cyan. Return the equivalent angle in the interval [-pi pi). See also stdisp angdiff Difference of two angles d = angdiff(th1. By default the left image is red. color) as above but the string color describes the color coding as a string with 2 letters. d = angdiff(th) returns the equivalent angle to th in the interval [-pi pi). These adjustments are achieved by trimming the images. FUNCTIONS AND CLASSES anaglyph Convert stereo images to an anaglyph image a = anaglyph(left. useful if the images were captured with a non-human stereo baseline or ﬁeld of view. If disp is positive the disparity is increased. the ﬁrst for left. if negative it is reduced. right) is an anaglyph image where the two images of a stereo pair are combined into a single image by coding them in two different colors. right.

x is also N × 1 and is a correlation whose peak indicates the relative orientation of one proﬁle with respect to the other. x2.y1) to (x2. p = bresenham(p1.y2). % visible spectrum e = blackbody(l. See also RegionFeature. 6500). Machine Vision Toolbox for MATLAB R 90 Copyright c Peter Corke 2011 .y1] and p2=[x2. Endpoints must be integer. If lambda is a column vector. y1.boundary. T) is the blackbody radiation power density [W/m3 ] at the wavelength lambda [m] and temperature T [K]. e) boundmatch Match boundary proﬁles x = boundmatch(R1. xcorr bresenham Generate a line p = bresenham(x1. p2) as above but p1=[x1. [x. For example: l = [380:10:700]’*1e-9.CHAPTER 2.s] = boundmatch(R1. then E is a column vector whose elements correspond to to those in lambda. r2) is the correlation of the two boundary proﬁles R1 and r2.y2]. y2) is a list of integer coordinates for points lying on the line segement (x1. FUNCTIONS AND CLASSES blackbody Compute blackbody emission spectrum E = blackbody(lambda. r2) as above but also returns the relative scale s which is the size of object 2 with respect to object 1. % emission of sun plot(l. Each is an N × 1 vector of distances from the centroid of an object to points on its perimeter at equal angular increments.

CHAPTER 2.E] = camcald(d) as above but E is the maximum residual error after back substitution [pixels]. Machine Vision Toolbox for MATLAB R 91 Copyright c Peter Corke 2011 . See also CentralCamera ccdresponse CCD spectral response R = ccdresponse(lambda) is the spectral response of a typical silicon imaging sensor at the wavelength lambda. The response is normalized in the range 0 to 1. If lambda is a vector then R is a vector of the same length whose elements are the response at the corresponding element of lambda. [C. Notes: • This method cannot handle lense distortion. FUNCTIONS AND CLASSES See also icanvas camcald Camera calibration from data points C = camcald(d) is the camera matrix (3 × 4) determined by least squares from corresponding world and image-plane points. Reference An ancient Fairchild data book for a sensor with no IR ﬁlter ﬁtted.Y.V] is the corresponding image plane coordinate.Z) is the coordinate of a world point and [U. d is a table of points with rows of the form [X Y Z U V] where (X.

green and blue primaries respectively. Options ‘n’. R Machine Vision Toolbox for MATLAB 92 Copyright c Peter Corke 2011 . that the I’th column of a is closest to the Jth column of b. that is. circle Compute points on a circle circle(C. but the circle is always in the xy-plane with a z-coordinate of C(3). b) is the correspondence for N-dimensional point sets a (N × N A) and b (N × N B).d1] = closest(a. opt) return an N × 2 matrix whose rows deﬁne the coordinates [x. R. and x is N × 3. C is normally 2 × 1 but if 3 × 1 then the circle is embedded in 3D.CHAPTER 2. opt) plot a circle centred at C with radius R. FUNCTIONS AND CLASSES See also rluminos cie primaries Deﬁne CIE primary colors p = CIE PRIMARIES() is a 3-vector with the wavelengths [m] of the CIE 1976 red. b) as above and d1(I)=—a(I)-b(J)— is the distance of the closest point. x = circle(C. [k. R. k = closest(a. N Specify the number of points (default 50) closest Find closest points in N-dimensional space.y] of points around the circumferance of a circle centred at C and of radius R. k (1 x NA) is such that the element J = k(I).

The data are referred to as pilot data. Notes • Is a MEX ﬁle. 19000 (526.16).5.32).d2] = closest(a.CHAPTER 2. since. unlike the CIE 2 deg functions (which were reconstructed from chromaticity data). and 22500 (444. but probably represent the best estimate of the 2 deg CMFs. • From Table I(5.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645. See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation. Notes • Data from http://cvrl.ac.3) of Wyszecki & Stiles (1982). 335 of Table 1(5. while Table I(5.d1.5. E) is the CIE color matching (1×3) function for an illumination spectrum deﬁned by intensity E (N × 1) and wavelength lambda (N × 1) [m].3) of Wyszecki & Stiles (1982).44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 . rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m].3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps. they were measured directly.ioo. As noted in footnote a on p.5. FUNCTIONS AND CLASSES [k. rgb = cmfrgb(lambda.) • These CMFs differ slightly from those of Stiles & Burch (1955). If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda.5.ucl.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers. b) as above but also returns the distance to the second closest point. (Table 1(5.

R Machine Vision Toolbox for MATLAB 94 Copyright c Peter Corke 2011 .uk See also cmfrgb. E) is the CIE xyz color matching (1 × 3) function for an illumination spectrum deﬁned by intensity E (N × 1) and wavelength lambda (N × 1) [m]. If lambda is a vector then each row of xyz is the color matching function of the corresponding element of lambda. FUNCTIONS AND CLASSES See also ccxyz cmfxyz matching function The color matching function is the XYZ tristimulus required to match a particular wavelength excitation.M). Notes • The number of rows in pix must match the product of the elements of imsize. imsize is a 2-vector (N. imsize) is an image (HxWxP) comprising the pixel values in pix (N × P ) with one row per pixel where N=H × W .ioo. im) as above but the dimensions of out are the same as im.CHAPTER 2.ucl. out = col2im(pix. xyz = cmfxyz(lambda. Note • CIE 1931 2-deg xyz CMFs from cvrl.ac. ccxyz col2im Convert pixel vector to image out = col2im(pix. xyz = cmfxyz(lambda) is the CIE xyz color matching function (N ×3) for illumination at wavelength lambda (N × 1) [m].

g] to every pixel in the color image im. colordistance Colorspace distance d = colordistance(im. FUNCTIONS AND CLASSES See also im2col colnorm Column-wise norm of a matrix cn = colnorm(a) returns an M × 1 vector of the normals of each column of the matrix a which is N × M . • Note that Euclidean distance in the rg-chromaticity space does not correspond well with human perception of color differences. See also colorspace Machine Vision Toolbox for MATLAB R 95 Copyright c Peter Corke 2011 . Notes • The output image could be thresholded to determine color similarity. Perceptually uniform spaces such as Lab remedy this problem. d is an image with the same dimensions as im and the value of each pixel is the color space distance of the corresponding pixel in im. rg) is the Euclidean distance on the rg-chromaticity plane from coordinate rg=[r.CHAPTER 2.

C] = colorkmeans(im. color) as above but a the mask is the return value of the function handle func applied to the image im. A k-means clustering of the chromaticity of all input pixels is performed.CHAPTER 2. k) as above but also returns the cluster centres C (k × 2) where the I’th row is the rg-chromaticity of the I’th cluster and corresponds to the label I. options) is a segmentation of the color image im into k classes. im<100. The label image L has the same row and column dimension as im and each pixel has a value in the range 0 to k-1 which indicates which cluster the corresponding pixel belongs to. ipixswitch colorkmeans Color image segmentation by clustering L = colorkmeans(im. FUNCTIONS AND CLASSES colorize Colorize a greyscale image out = colorize(im. color) is a color image where each pixel in out is set to the corresponding element of the greyscale image im or a speciﬁed color according to whether the corresponding value of mask is true or false respectively.B). [0 0 1]) Display image with NaN values shown in red out = colorize(im. See also imono. out = colorize(im. A k-means clustering of the chromaticity of all input pixels is performed. @isnan. [1 0 0]) Notes • With no output arguments the image is displayed. eg. icolor. func. k. The color is speciﬁed as a 3-vector (R.G. [L. mask. @isnan. Examples Display image with values < 100 in blue out = colorize(im. R Machine Vision Toolbox for MATLAB 96 Copyright c Peter Corke 2011 . and returns a per-pixel logical result.

• Clustering is performed in rg-chromaticity space. the root mean square error of all pixel chromaticities with respect to their cluster centre. C) is a segmentation of the color image im into k classes which are deﬁned by the cluster centres C (k × 2) in chromaticity space. interactively pick cluster centres Notes • The k-means clustering algorithm used in the ﬁrst three forms is computationally expensive and time consuming. Pixels are assigned to the closest (Euclidean) centre. Options Various options are possible to choose the initial cluster centres for k-means: ‘random’ ‘spread’ ‘pick’ randomly choose k points from randomly choose k values within the rectangle spanned by the input chromaticities. “?burnt” Machine Vision Toolbox for MATLAB R 97 Copyright c Peter Corke 2011 . Notes • Color name may contain a wildcard. ‘xy’) is the XYZ-tristimulus value corresponding to the color speciﬁed by the string name. low is good.C. Since cluster centres are provided the k-means segmentation step is not required. name = colorname(rgb) is a string giving the name of the color that is closest (Euclidean) to the given rgb-tristimulus value. XYZ = colorname(name. ‘xy’) is a string giving the name of the color that is closest (Euclidean) to the given XYZ-tristimulus value. name = colorname(XYZ. See also colorname Map between color names and RGB values rgb = colorname(name) is the rgb-tristimulus value corresponding to the color speciﬁed by the string name. k) as above but also returns the residual R. L = colorkmeans(im.R] = colorkmeans(im.CHAPTER 2. • The residual is an indication of quality of ﬁt. eg. FUNCTIONS AND CLASSES [L.

• Tristimulus values are in the range 0 to 1 colorspace Color space conversion of image out = colorspace(s. • Color space names are case insensitive. As MATLAB’s native datatype. FUNCTIONS AND CLASSES • Based on the standard X11 color database rgb. and uint8 data with integer-valued intensities from 0 to 255. s = ‘dest<-src’.o3] = colorspace(s.CHAPTER 2. colorspace(s. [o1. or alternatively. • MATLAB uses two standard data formats for R’G’B’: double data with intensities in the range 0 to 1. Supported color spaces are: ‘RGB’ ‘YPbPr’ ‘YCbCr’/’YCC’ ‘YUV’ ‘YIQ’ ‘YDbDr’ ‘JPEGYCbCr’ ‘HSV’/’HSB’ ‘HSL’/’HLS’/’HSI’ ‘XYZ’ ‘Lab’ ‘Luv’ ‘Lch’ R’G’B’ Red Green Blue (ITU-R BT.txt.o2. • When R’G’B’ is the source or destination. and R Machine Vision Toolbox for MATLAB 98 Copyright c Peter Corke 2011 .709 gamma-corrected) Luma (ITU-R BT. s = ‘src->dest’. it can be omitted.601) + Chroma Luma + Chroma (“digitized” version of Y’PbPr) NTSC PAL Y’UV Luma + Chroma NTSC Y’IQ Luma + Chroma SECAM Y’DbDr Luma + Chroma JPEG-Y’CbCr Luma + Chroma Hue Saturation Value/Brightness Hue Saturation Luminance/Intensity CIE XYZ CIE L*a*b* (CIELAB) CIE L*u*v* (CIELUV) CIE L*ch (CIELCH) Notes • RGB input is assumed to be gamma encoded • RGB output is gamma encoded • All conversions assume 2 degree observer and D65 illuminant. Input and output images have 3 planes. i1. For example ‘yuv<’ is short for ‘yuv<-rgb’.i3) as above but speciﬁes separate input channels. im) converts the image im to a different color space according to the string s which speciﬁes the source and destination color spaces. double data is the natural choice. im) as above but speciﬁes separate output channels or planes.i2.

some functions also operate with uint8 R’G’B’. However. Example A = rand(400. colorspace will ﬁrst cast it to double R’G’B’ before processing.B ) R Machine Vision Toolbox for MATLAB 99 Copyright c Peter Corke 2011 . Given uint8 R’G’B’ color data.2*A.b) is the Euclidean distances between L-dimensional points described by the matrices a (L × M ) and b (L × N ) respectively. distance Euclidean distances between sets of points d = distance(a.B). d = distance(A. FUNCTIONS AND CLASSES the R’G’B’ format used by colorspace.200). Notes • This fully vectorized (VERY FAST!) • It computes the Euclidean distance between two vectors by: ||A-B|| = sqrt ( ||A||ˆ2 + ||B||ˆ2 .100). The distance d is M × N and element d(I.J) is the distance between points a(I) and d(J).CHAPTER 2. Author Pascal Getreuer 2005-2006 diff2 diff3(v) compute 2-point difference for each point in the vector v. • If im is an M × 3 array. out will also have size M × 3. like a colormap. for memory and computational performance. B = rand(400.

non-zero is an object. each row is one edge point coordinate (x. • seed must be a point on the edge of the region. tel. See also closest e2h Euclidean to homogeneous edgelist Return list of edge pixels for region E = edgelist(im.nl Last Rev: Oct 29 16:35:48 MET DST 1999. seed) return the list of edge pixels of a region in the image im starting at edge coordinate seed (i.(+31)20-5257524. Tested: PC Matlab v5. E = edgelist(im. Intelligent Autonomous Systems (IAS) group.2 and Solaris Matlab v5. Thanx: Nikos Vlassis. Notes • im is a binary image where 0 is assumed to be background.CHAPTER 2. but the direction of edge following is speciﬁed. Kruislaan 403 1098 SJ Amsterdam.j). Machine Vision Toolbox for MATLAB 100 R Copyright c Peter Corke 2011 . The result E is a matrix.uva. not image frame. Note that direction is with respect to y-axis upward. in matrix coordinate frame. University of Amsterdam. • The seed point is always the ﬁrst element of the returned edgelist. seed. bunschot@wins. FUNCTIONS AND CLASSES Author Roland Bunschoten.3. direction) returns the list of edge pixels as above.y). non zero is counter-clockwise. direction == 0 (default) means clockwise.

ls) as above but draw lines using the line style arguments ls. ls) as above but return a vector of graphic handles. FUNCTIONS AND CLASSES See also ilabel epidist Distance of point from epipolar line d = epidist(f. Nuno Alexandre Cid Martins. epiline(f. p. p. See also fmatrix. See also epiline. p2) is the distance of the points p2 (2 × M ) from the epipolar lines due to points p1 (2 × N ) where f (3 × 3) is a fundamental matrix relating the views containing image points p1 and p2. 1998. H = epiline(f. Oct 27. Author Based on fmatrix code by. d (N × M ) is the distance matrix where element d(i. p1.CHAPTER 2. I. Points are speciﬁed by the columns of p.S. epidist Machine Vision Toolbox for MATLAB 101 R Copyright c Peter Corke 2011 . one per line drawn. p) draws epipolar lines in current ﬁgure based on points p (2 × N ) and the fundamental matrix f (3 × 3).j) is the distance from the point p2(j) to the epipolar line due to point p1(i).R. Coimbra. fmatrix epiline Draw epipolar lines epiline(f.

sigma) Returns a unit volume Gaussian smoothing kernel. Reference Hartley and Zisserman. If w is not speciﬁed it defaults to 2*sigma.uwa. FUNCTIONS AND CLASSES fmatrix Estimate fundamental matrix f = fmatrix(p1. that is. Notes • The points must be corresponding. k is (2W+1) x (2W+1). See also ransac.CHAPTER 2. epiline. no outlier rejection is performed. c. and the convolution kernel has a half size of w. School of Computer Science & Software Engineering. The Gaussian has a standard deviation of sigma. options) is the fundamental matrix (3 × 3) that relates two sets of corresponding points p1 (2 × N ) and p2 (2 × N ) from two different camera views. ‘Multiple View Geometry in Computer Vision’.au/. it is singular. which means it can be passed to ransac(). The University of Western Australia. • Contains a RANSAC driver. epidist gauss2d kernel k = gauss2d(im. that is. p2.csse. Machine Vision Toolbox for MATLAB 102 R Copyright c Peter Corke 2011 . page 270. homography. Author Based on fundamental matrix code by Peter Kovesi. • f is a rank 2 matrix. http://www.edu.

se) is the hit-or-miss transform of the binary image im with the structuring element se. itriplepoint. Homogeneous points X (3 × 1) on the line must satisfy L’*X = 0. FUNCTIONS AND CLASSES h2e Homogeneous to Euclidean hitormiss Hit or miss transform H = hitormiss(im.y1) and (x2.y2). Unlike standard morphological operations S has three possible values: 0.CHAPTER 2. x2. See also plot homline Machine Vision Toolbox for MATLAB 103 R Copyright c Peter Corke 2011 . iendpoint homline Homogeneous line from two points L = homline(x1. ithin. See also imorph. y2) returns a 3 × 1 vectors which describes a line in homogeneous form that contains the two Euclidean points (x1. y1. 1 and don’t care (represented by NaN).

au/. which means it can be passed to ransac(). no outlier rejection is performed. invhomog. fmatrix homtrans Apply a homogeneous transformation p2 = homtrans(T. The University of Western Australia. • If T is in SE(2) (3 × 3) and – p is 2 × N (2D points) they are considered Euclidean (R2 ) – p is 3 × N (2D points) they are considered projective (p2 ) • If T is in SE(3) (4 × 4) and – p is 3 × N (3D points) they are considered Euclidean (R3 ) – p is 4 × N (3D points) they are considered projective (p3 ) Machine Vision Toolbox for MATLAB 104 R Copyright c Peter Corke 2011 .edu. Author Based on homography code by Peter Kovesi. p) applies homogeneous transformation T to the points stored columnwise in p. http://www. Notes • The points must be corresponding.CHAPTER 2. • The points must be projections of points lying on a world plane • Contains a RANSAC driver.uwa. See also ransac. School of Computer Science & Software Engineering.csse. FUNCTIONS AND CLASSES homography Estimate homography H = homography(p1. p2) is the homography (3 × 3) that relates two sets of corresponding points p1 (2×N ) and p2 (2×N ) from two different camera views of a planar object.

R ‘scale’. S ‘dimension’. S output image contains all the warped pixels. if T = N × N and T=NxNxP then the result is NxNxP. that is tp=T*T1. T1) applies homogeneous transformation T to the homogeneous transformation T1. D ‘size’. FUNCTIONS AND CLASSES tp = homtrans(T. [out. options) as above but offs is the offset of the warped tile out with respect to the origin of im. See also homography.CHAPTER 2. im. V ‘roi’. ie. Options ‘full’ ‘extrapval’. See also e2h.H] Notes • The edges of the resulting output image will in general not be be vertical and horizontal lines. interp2 Machine Vision Toolbox for MATLAB 105 R Copyright c Peter Corke 2011 . im. If T1 is a 3-dimensional transformation then T is applied to each plane as deﬁned by the ﬁrst two dimensions. but its position with respect to the input image is given by the second return value offs. set unmapped pixels to this value output image contains the speciﬁed ROI in the input image scale the output by this factor ensure output image is D × D size of output image S=[W. options) is a warp of the image im obtained by applying the homography H to the coordinates of every input pixel. itrim.offs] = homwarp(H. h2e homwarp Warp image by an homography out = homwarp(H.

IT-8:pp.CHAPTER 2. features. Hu. ianimate(im. options) displays a greyscale image sequence im (HxWxN) where N is the number of frames in the sequence. features. Notes • im is assumed to be a binary image of a single connected region Reference M-K. Examples Animate image sequence: ianimate(seq). on Information Theory. 200). Animate image sequence with overlaid corner features: c = icorner(im. % computer corners % features shown as green squares Machine Vision Toolbox for MATLAB 106 R Copyright c Peter Corke 2011 . options) displays a greyscale image sequence im with point features overlaid. 179-187. The feature is plotted using the object’s plot method and additional options are passed through to that method. ’nfeat’. ’gs’). Visual pattern recognition by moment invariants. See also npq ianimate Display an image sequence ianimate(im. IRE Trans. ianimate(seq. FUNCTIONS AND CLASSES humoments Hu moments phi = humoments(im) is the vector (7 × 1) of Hu moment invariants for the binary image im. features (N × 1) cell array whose elements are vectors of feature objects. 1962.

idisp ibbox Find bounding box box = ibbox(p) is the minimal bounding box that contains the points described by the columns of p (2 × N ). FUNCTIONS AND CLASSES Options ‘fps’. isurf. iharris. Machine Vision Toolbox for MATLAB 107 R Copyright c Peter Corke 2011 . iblobs features f = iblobs(im. N ‘only’. options) is a vector of RegionFeature objects that describe each connected region in the image im. F ‘loop’ ‘movie’. YMIN YMAX].CHAPTER 2. box = ibbox(im) is the minimal bounding box that contains the non-zero pixels in the image im. The bounding box is a 2 × 2 matrix [XMIN XMAX. M ‘npoints’. I set the frame rate (default 5 frames/sec) endlessly loop over the sequence save the animation as a series of PNG frames in the folder M plot no more than N features per frame (default 100) display only the I’th frame from the sequence See also PointFeature.

C set connectivity. [S1.A2] accept only blobs with area in interval A1 to A2 ‘shape’. less for other shapes a structure containing moments of order 0 to 2 See also RegionFeature. ilabel. minimum vertical coordinate bounding box. Machine Vision Toolbox for MATLAB 108 R Copyright c Peter Corke 2011 . imoments icanny edge detection E = icanny(im. maximum vertical coordinate the number of pixels the value of the pixels forming this region the label assigned to this region a list of indices of features that are children of this feature coordinate of a point on the perimeter a list of edge points 2 × N matrix number of edge pixels true if region touches edge of the image major axis length of equivalent ellipse minor axis length of equivalent ellipse angle of major ellipse axis to horizontal axis aspect ratio b/a (always <= 1.CHAPTER 2. A set pixel aspect ratio. FUNCTIONS AND CLASSES Options ‘aspect’. minimum horizontal coordinate bounding box. options) returns an edge image using the Canny edge detector.0) 1 for a circle. 4 (default) or 8 ‘greyscale’ compute greyscale moments 0 (default) or 1 ‘boundary’ compute boundary (default off) ‘area’. default 1. horizontal coordinate centroid. and larger values correspond to stronger edges. maximum horizontal coordinate bounding box. [A1. The edges within im are marked by non-zero values in E.S2] accept only blobs with shape in interval S1 to S2 ‘touch’ ignore blobs that touch the edge (default accept) ‘class’. vertical coordinate bounding box. C accept only blobs of pixel value C (default all) The RegionFeature object has many properties including: uc vc umin umax vmin vmax area class label children edgepoint edge perimeter touch a b theta shape circularity moments centroid.0 ‘connect’.

See also iopen. This is an dilation followed by erosion. See also isobel. out = iclose(im.CHAPTER 2. imorph Machine Vision Toolbox for MATLAB 109 R Copyright c Peter Corke 2011 . the effective structuing element is the Minkowski sum of the structuring element with itself n times. T set the standard deviation for smoothing (default 1) set the lower hysteresis threshold (default 0. that is n dilations followed by n erosions. Tel Aviv University. se) is the image im after morphological closing with the structuring element se.5 x strongest edge) Author Oded Comay. S ‘th0’. Notes • Cheaper to apply a smaller structuring element multiple times than one large one. n) as above but the structuring element se is applied n times. kdgauss iclose closing out = iclose(im. se. 1996-7. T ‘th1’.1 x strongest edge) set the upper hysteresis threshold (default 0. FUNCTIONS AND CLASSES Options ‘sd’.

The images do not have to be of the same size. FUNCTIONS AND CLASSES icolor Colorize a greyscale image C = icolor(im) is a color image C (HxWx3)where each color plane is equal to im (H × W ). color) as above but each output pixel is color (3 × 1) times the corresponding element of im. value of unset background pixels Machine Vision Toolbox for MATLAB 110 R Copyright c Peter Corke 2011 .options) concatenates images from the cell array im. Create an aqua tinted version of the greyscale image c = icolor(im.u] = iconcat(im.CHAPTER 2. colorize. iconcat(im. B direction of concatenation: ‘horizontal’ (default) or ‘vertical’. [C. [0 1 1]). ipixswitch iconcat Concatenate images C = iconcat(im. See also imono. C = icolor(im. Examples Create a color image that looks the same as the greyscale image c = icolor(im). Options ‘dir’.options) as above but also returns the vector u whose elements are the coordinates of the left (or top in vertical mode) edge of the corresponding image.options) as above but displays the concatenated images using idisp. D ‘bgval’. and smaller images are surrounded by background pixels which can be speciﬁed.

The smaller image is taken as the kernel and convolved with the larger image. See also conv2 Machine Vision Toolbox for MATLAB 111 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES Notes • Works for color or greyscale images • Direction can be abbreviated to ﬁrst character. resulting in an output image with the same number of planes. If the larger image is color (has multiple planes) the kernel is applied to each plane. im2. Options ‘same’ ‘full’ ‘valid’ output image is same size as largest input image (default) output image is larger than the input image output image is smaller than the input image. ‘h’ or ‘v’ • In vertical mode all images are right justiﬁed • In horizontal mode all images are top justiﬁed See also idisp iconv Image convolution C = iconv(im1. options) convolves im1 with im2.CHAPTER 2. and contains only valid pixels Notes • This function is a convenience wrapper for the builtin function CONV2.

P ‘color’ minimum corner strength minimum corner strength as a fraction of maximum corner strength don’t return features closer than E to the edge of image (default 2) don’t return a feature closer than R pixels to an earlier feature (default 0) return the N strongest corners (default Inf) choose the detector where D is one of ‘harris’ (default). D ‘k’. E ‘suppress’. K ‘patch’. ‘noble’ or ‘klt’ kernel width for smoothing (default 2) kernel for gradient (default kdgauss(2)) set the value of k for Harris detector use a P × P patch of surrounding pixel values as the feature vector. CM ‘cminthresh’. • If im is NxMx3 it is taken as a sequence unless the option ‘color’ is given Machine Vision Toolbox for MATLAB 112 R Copyright c Peter Corke 2011 . R ‘nfeat’. specify that im is a color image not a sequence Notes • Corners are processed in order from strongest to weakest. CT ‘edgegap’. • The function stops when: – the corner strength drops below cmin – the corner strenght drops below cMinThresh x strongest corner – the list of corners is exhausted • Features are returned in descending strength order • If im has more than 2 dimensions it is either a color image or a sequence • If im is NxMxP it is taken as an image sequence and f is a cell array whose elements are feature vectors for the corresponding image in the sequence. S ‘deriv’. This is a non-scale space detector and by default the Harris method is used. If im is an image sequence a cell array of PointFeature vectors is returned.CHAPTER 2. The vector has zero mean and unit norm. options) is a vector of PointFeature objects describing detected corner features. N ‘detector’. The PointFeature object has many properties including: u v strength descriptor horizontal coordinate vertical coordinate corner strength corner descriptor (vector) Options ‘cmin’. FUNCTIONS AND CLASSES icorner Corner detector f = icorner(im. D ‘sigma’.

N ‘mindelta’. with a delay of 0. See also PointFeature. pp 147-151. pp. show the points p1 and p2 at each iteration. 1994.d] = icp(p1. Harris and M. Proc. vol. • “Finding corners”. Shi and C.05 rad) stop after N iterations (default 100) stop when the relative change in error norm is less than T (default 0. options) is the homogeneous transformation that best transforms the set of points p2 to p1 using the iterative closest point algorithm.J.Noble. [T. Image and Vision Computing. d ‘plot’ ‘maxtheta’. 593-593.6. Fourth Alvey Vision Conf. T ‘maxiter’. • The default descriptor is a vector [Ix* Iy* Ixy*] which are the unique elements of the structure tensor. FUNCTIONS AND CLASSES • If im is NxMx3xP it is taken as a sequence of color images and f is a cell array whose elements are feature vectors for the corresponding color image in the sequence.CHAPTER 2. isurf icp Point cloud alignment T = icp(p1. J. 1988. J.121-128..G. Computer Vision and Pattern Recognition. Machine Vision Toolbox for MATLAB 113 R Copyright c Peter Corke 2011 . Options ‘dplot’. • The descriptor is a vector of ﬂoat types to save space References • “A combined corner and edge detector”. Stephens. IEEE Computer Society.5 [sec]. May 1988. T show the points p1 and p2 at each iteration. limit the change in rotation at each step to T (default 0. p2. • “Good features to track”.001) eliminate correspondences more than T x the median distance at each iteration. T ‘distthresh’. with a delay of d [sec]. p2. where * denotes squared and smoothed. C. pp. options) as above but also returns the norm of the error between the transformed point set p2 and p1. Tomasi. Manchester. Proc.

Intell. []) as above but no smoothing is applied prior to decimation. Mach. m. See also iscale. Pattern Anal. s = idecimate(im. Notes • If the image has multiple planes. s = idecimate(im. IEEETrans. • For noisy data setting distthresh and maxtheta can help to prevent the the solution from diverging. P. FUNCTIONS AND CLASSES Notes • Points can be 2. sd) as above but the standard deviation of the smoothing kernel is set to sd. vol..CHAPTER 2. m. 14. no. 1992. each plane is decimated. • Smoothing is used to eliminate aliasing artifacts and the standard deviation should be chosen as a function of the maximum spatial frequency in the image. Feb. 2. idecimate an image s = idecimate(im. 239-256. pp. The image is smoothed with a Gaussian kernel with standard deviation m/2 then subsampled.McKay.or 3-dimensional. ismooth Machine Vision Toolbox for MATLAB 114 R Copyright c Peter Corke 2011 .Besl and H. Reference “A method for registration of 3D shapes”. m) is a decimated version of the image im whose size is reduced by m (an integer) in both dimensions.

If the image is zoomed. XY ‘colormap’. User interface: • Left clicking on a pixel will display its value in a box at the top. options) displays an image and allows interactive investigation of pixel value. zero is white. darker than ‘grey’. • The “histo” button displays a histogram of the pixel values in a new ﬁgure. frame or GUI add a color bar to the image write the image to ﬁle F in EPS format display aspect ratio so that pixels are squate make ﬁgure very wide. the histogram is computed over only those pixels in view. they are ﬁrst concatenated (horizontally). zero is black.CHAPTER 2. linear proﬁle. Set colormap C (N × 3) color map: greyscale unsigned. maximum value is black color map: greyscale signed. XY is a cell array whose elements are vectors that span the x. F ‘square’ ‘wide’ ‘ﬂatten’ ‘ynormal’ ‘cscale’. FUNCTIONS AND CLASSES idisp image display tool idisp(im. The image is displayed in a ﬁgure with a toolbar across the top. positive is blue. • The “line” button allows two points to be speciﬁed and a new ﬁgure displays intensity along a line between those points.and y-axes respectively. histogram and zooming. image is inverted C is a 2-vector that speciﬁes the grey value range that spans the colormap. negative is red. – The “zoom” button requires a left-click and drag to specify a box which deﬁnes the zoomed view. Machine Vision Toolbox for MATLAB 115 R Copyright c Peter Corke 2011 . C ‘xydata’. positive is blue. N ‘nogui’ ‘noaxes’ ‘noframe’ ‘plain’ ‘bar’ ‘print’. useful for displaying stereo pair display image planes (colors or sequence) as horizontally adjacent images y-axis increases upward. C ‘grey’ ‘invert’ ‘signed’ ‘invsigned’ ‘random’ ‘dark’ number of colors in the color map (default 256) display the image without the GUI no axes on the image no axes or frame on the image no axes. maximum value is white color map: greyscale unsigned. negative is red. good for superimposed graphics Notes • Color images are displayed in true color mode: pixel triples map to display pixels • Grey scale images are displayed in indexed mode: the image pixel value is mapped through the color map to determine the display pixel value. zero is white color map: random values. highlights ﬁne structure color map: greyscale unsigned. zero is black color map: greyscale signed. Options ‘ncolors’. If im is a cell array of images.

iconcat idisplabel Display an image with mask idisplabel(im. bg) as above but the grey level of the non-selected pixels is speciﬁed by bg in the range 0 to 1. which by default (’greyscale’) is the range black to white. and labelimage is an N × M image containing integer pixel class labels for the corresponding pixels in im. colormap. Non-selected pixels are displayed as white. See also iint Machine Vision Toolbox for MATLAB 116 R Copyright c Peter Corke 2011 . caxis. labelimage. idisplabel(im. im is a greyscale N × M or color NxMx3 image. labels) displays only those image pixels which belong to a speciﬁc class. labelimage. The integer pixels are assumed to span the range 0 to the maximum value of their integer class. labels. See also iblobs. See also image. FUNCTIONS AND CLASSES • The minimum and maximum image values are mapped to the ﬁrst and last element of the color map. colorseg idouble Convert integer image to double imd = idouble(im) returns an image with double precision elements in the range 0 to 1. The pixel classes to be displayed are given by the elements of labels which is a scalar a vector of class labels. icolorize.CHAPTER 2.

Notes • Gamma encoding is typically performed in a camera with gamma=0. • For images with multiple planes the gamma correction is applied to all planes. All pixels are raised to the power gamma. FUNCTIONS AND CLASSES iendpoint Find end points in a binary skeleton image out = iendpoint(im) is a binary image where pixels are set if the corresponding pixel in the binary image im is the end point of a single-pixel wide line such as found in an image skeleton. • For images of type int the pixels are assumed in the range 0 to max integer value. ‘sRGB’) is a gamma decoded version of im using the sRGB decoding function (JPEG images sRGB encoded). out = igamma(im.CHAPTER 2.45. • For images of type double the pixels are assumed to be in the range 0 to 1. hitormiss igamma correction out = igamma(im. • Gamma decoding is typically performed in the display with gamma=2. gamma) is a gamma corrected version of im.2. ithin. See also itriplepoint. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1. Computed using the hit-or-miss morphological operator. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 .

vol. and a larger value indicates a preference for larger regions. min. L is an image of the same size as im where each element is the label assigned to the corresponding pixel in im. imser Machine Vision Toolbox for MATLAB 118 R Copyright c Peter Corke 2011 . min) is a graph-based segmentation of the greyscale or color image im. Felzenszwalb and D.5). [L. Huttenlocher. 1500. Int. L = igraphseg(im. See also ithresh. Sept. Notes • Is a MEX ﬁle Author Pedro Felzenszwalb. P. min is the minimum region size (pixels). k is the scale parameter. 0. [l. k. idisp(im) Reference “Efﬁcient graph-based image segmentation”. 2004. sigma) as above and sigma is the width of a Gaussian which is used to initially smooth the image (default 0. FUNCTIONS AND CLASSES igraphseg Graph-based segmentation L = igraphseg(im.CHAPTER 2.5). 2006. Example im = iread(’58060. k. pp. k. sigma) as above but m is the number of regions found. 167181. Journal on Computer Vision.jpg’). 59. 100. min.m] = igraphseg(im.m] = igraphseg(im.

Options ‘nbins’ ‘cdf’ ‘normcdf’ ‘sorted’ number of histogram bins (default 256) compute a cumulative histogram compute a normalized cumulative histogram histogram but with occurrence sorted in descending order Example [h.x] = ihist(im. options) displays the image histogram. options) as above but also returns the bin coordinates as a column vectors. bar(x. [H. For an image with multiple planes the histogram of each plane is given in a separate subplot. Notes • For a uint8 image the histogram spans the greylevel range 0-255 • For a ﬂoating point image the histogram spans the greylevel range 0-1 • For ﬂoating point images all NaN and Inf values are ﬁrst removed. ’normcdf’).h). [h.h). • For a uint8 image the MEX function fhist is used See also hist Machine Vision Toolbox for MATLAB 119 R Copyright c Peter Corke 2011 .CHAPTER 2.x] = ihist(im). H = ihist(im. For an image with multiple planes H is a matrix with one column per image plane.x] = ihist(im. options) is the image histogram as a column vector. FUNCTIONS AND CLASSES ihist Image histogram ihist(im. plot(x.

y1. for a multilevel image it means that it touches more than one other region. for a binary image this means the region touches the edge of the image. [L.y2).m] = ilabel(im) as above but returns the value of the maximum label value. A value of 0 indicates that the region has no single enclosing region.CHAPTER 2.y1) and bottom-right (x2. ii is a precomputed integral image.parents] = ilabel(im) as above but also returns region hierarchy information. same size as im. The value of parents(I) is the label of the parent or enclosing region of region I. The ﬂoating point pixels values in im are assumed to span the range 0 to 1. [L.m. Region labels are in the range 1 to M. where each pixel value represents the integer region label assigned to the corresponding pixel in im. y2. See also intgimage ilabel Label an image L = ilabel(im) performs connectivity analysis on the image im and returns a label image L. x2) is the sum of pixels in the rectangular image region deﬁned by its top-left (x1. x1. See also idouble iisum Sum of integral image s = iisum(ii. Machine Vision Toolbox for MATLAB 120 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES iint Convert image to integer class out = iint(im) is an image with 8-bit unsigned integer elements in the range 0 to 255.

• The image can be binary or multi-level • Connectivity is performed using 4 nearest neighbours by default.maxlabel. p1.parents. • This is a “low level” function. iproﬁle. Notes • Uses the Bresenham algorith • Only works for greyscale images • The line looks jagged since no anti-aliasing is performed See also bresenham. p2. If edge(I) is 1 then region I touches edge of the image. p1. v) as above but the pixel on the line are set to v.parents. Notes • Is a MEX ﬁle. The value of class(I) is the value of the pixels that comprise region I. See also iblobs. otherwise it does not. FUNCTIONS AND CLASSES [L.maxlabel. The pixels on the line are set to 1. [L. IBLOBS is a higher level interface. To use 8-way connectivity pass a second argument of 8.edge] = ilabel(im) as above but also returns the edge-touch status of each region.class.CHAPTER 2. eg. p2) is a copy of the image im with a line drawn between the points p1 and p2. ilabel(im. 8). out = iline(im. each a 2-vector [X. ipaste Machine Vision Toolbox for MATLAB 121 R Copyright c Peter Corke 2011 .Y]. imoments iline Draw a line in an image out = iline(im.class] = ilabel(im) as above but also returns the class of pixels within each region.

y.score] = imatch(im1. im2. See also col2im imatch Template matching xm = imatch(im1. FUNCTIONS AND CLASSES im2col Convert an image to pixel per row format out = im2col(im) returns the image (HxWxP) as a pixel vector (N ×P ) where each row is a pixel value (1 × P ). If s is a scalar the search region is [-s. centred at (x. x. • Is a MEX ﬁle. s) works as above but also returns a matrix of matching score values for each template position tested. a perfect match score is 1.CHAPTER 2.0 Machine Vision Toolbox for MATLAB 122 R Copyright c Peter Corke 2011 .DY) are the x. The return value is xm=[DX.y). The template is searched for within im2 inside a rectangular region. x. w2. The pixels are in image column order and there are N=W × H rows. s] % relative to (x. y. Notes • Useful for tracking a template in an image sequence.CC] where (DX. ymin. • ZNCC matching is used.y) and CC is the similarity score (zero-mean normalized cross correlation) for the best match in the search region. • im1 and im2 must be the same size. s. More generally s is a 4-vector s=[xmin. im2.y) and of size s. s) is the matching subimage of im1 (template) within the image im2. H.DY.y). xmax. The template in im1 is centred at (x. The rows correspond to horizontal positions of the template.and y-offsets relative to (x. [xm. -s. ymax] relative to (x. and columns the vertical position.y) and its half-width is H.

FUNCTIONS AND CLASSES See also isimilarity imeshgrid Domain matrices for image [u.u) = u and v(v. effectively a greyscale image. f = imoments(u. [u. v) as above but the moments are computed from the pixel coordinates given as vectors u and v. v. All pixels are equally weighted. [u. effectively a binary image.CHAPTER 2. w) as above but the pixels have weights given by the vector w. The RegionFeature object has many properties including: Machine Vision Toolbox for MATLAB 123 R Copyright c Peter Corke 2011 .v] = imeshgrid(im) return matrices that describe the domain of image im and can be used for the evaluation of functions over the image. f = imoments(u.v] = imeshgrid(size) as above but the domain is described size which is scalar size× size or a 2-vector [w H]. H) as above but the domain is w × H.v] = imeshgrid(w. See also meshgrid imoments Image moments f = imoments(im) is a RegionFeature object that describes the greyscale moments of the image im.u) = v. The element u(v.

the elements are m00. horizontal coordinate centroid. or its area. • This function does not perform connectivity. imoments imono Convert color image to monochrome out = imono(im.CHAPTER 2. m02. m11. vertical coordinate the number of pixels major axis length of equivalent ellipse minor axis length of equivalent ellipse angle of major ellipse axis to horizontal axis aspect ratio b/a (always <= 1. if connected blobs are required then the ILABEL function must be used ﬁrst. m10. See also RegionFeature. ilabel. colorspace Machine Vision Toolbox for MATLAB 124 R Copyright c Peter Corke 2011 . icolor. Options ‘r601’ ‘r709’ ITU recommendation 601 (default) ITU recommendation 709 See also colorize. options) is a greyscale equivalent to the color image im. Notes • For a binary image the zeroth moment is the number of non-zero pixels. m01. m20.0) a structure containing moments of order 0 to 2. Different conversion functions are supported. FUNCTIONS AND CLASSES uc vc area a b theta shape moments centroid.

options) is a greyscale segmentation of the image im based on maximally stable extremal regions. FUNCTIONS AND CLASSES imorph Morphological neighbourhood processing out = imorph(im.png’. Options ‘dark’ ‘light’ looking for dark features against a light background (default) looking for light features against a dark background Example im = iread(’castle_sign2.CHAPTER 2. 761767. Pajdla. 22. Sept. pp. options) as above but m is the number of regions found. L is an image of the same size as im where each element is the label assigned to the corresponding pixel in im. Notes • Is a wrapper for vl mser. 2004. O. J. by Andrea Vedaldi and Brian Fulkerson • vl mser is a MEX ﬁle Machine Vision Toolbox for MATLAB 125 R Copyright c Peter Corke 2011 . and T.m] = imser(im. imser Maximally stable extremal regions L = imser(im.org). Chum. op) is the image im after morphological processing with the operator op and structuring element se. idisp(im) Reference “Robust wide-baseline stereo from maximally stable extremal regions”. ’grey’. m. ’double’). ’light’). Urban. The labels [L. [label. se. part of VLFeat (vlfeat. Matas.m] = imser(im. vol. Image and Vision Computing.

See also ihist intgimage Compute integral image out = intimage(im) is an integral image corresponding to im. Create integral images for sum of pixel squared values over rectangular regions i = intimage(im.ˆ2). Examples Create integral images for sum of pixels over rectangular regions i = intimage(im). Machine Vision Toolbox for MATLAB 126 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES See also ithresh. • Highlights image detail in dark areas of an image.CHAPTER 2. igraphseg inormhist Histogram normalization out = inormhist(im) is a histogram normalized version of the image im. Notes • The histogram of the normalized image is approximately uniform. Integral images can be used for rapid computation of summations over rectangular regions.

se) is the image im after morphological opening with the structuring element se. This is an erosion followed by dilation. sides. the effective structuing element is the Minkowski sum of the structuring element with itself n times. se. n) is a padded version of the image im with a block of NaN values n pixels wide on the sides of im as speciﬁed by sides which is a string containing one or more of the characters: ‘t’ top ‘b’ bottom ‘l’ left ‘r’ right out = ipad(im. See also iclose.CHAPTER 2. out = iopen(im. imorph ipad Pad an image with constants out = ipad(im. n. Machine Vision Toolbox for MATLAB 127 R Copyright c Peter Corke 2011 . sides. v) as above but pads with pixels of value v. FUNCTIONS AND CLASSES See also iisum iopen Morphological opening out = iopen(im. that is n erosions followed by n dilations. Notes • Cheaper to apply a smaller structuring element multiple times than one large one. n) as above but the structuring element se is applied n times.

FUNCTIONS AND CLASSES Examples Add a band of zero pixels 20 pixels high across the top of the image: ipad(im. 0) Add a band of white pixels 10 pixels wide on all sides of the image: ipad(im.CHAPTER 2. Options ‘centre’ ‘zero’ ‘set’ ‘add’ ‘mean’ The pasted image is centred at p. im1. ipaste Paste an image into an image out = ipaste(im. 20.V]. ’t’. Machine Vision Toolbox for MATLAB 128 R Copyright c Peter Corke 2011 . im2. ’tblr’. by default 1 is assumed im2 overwrites the pixels in im (default) im2 is added to the pixels in im im2 is set to the mean of pixel values in im2 and im See also iline ipixswitch Pixelwise image merge out = ipixswitch(mask. otherwise p is the top-left corner (default) the coordinates of p start at zero. otherwise im2 is selected. p. If the element of mask is zero im1 is selected. 10. 255) Notes • Not a tablet computer. im2) is an image where each pixel is selected from the corresponding pixel in im1 or im2 according to the corresponding values of mask. options) is the image im with the image im2 pasted in at the position p=[U.

CHAPTER 2. Each row of uv is the pixel coordinate (u. FUNCTIONS AND CLASSES Notes • im1 and im2 must have the same number of rows and columns • if im1 and im2 are both greyscale then out is greyscale • if either of im1 and im2 are color then out is color See also colorize iproﬁle Extract pixels along a line v = iproﬁle(im. See also bresenham. out is a cell array of images each one having R Machine Vision Toolbox for MATLAB 129 Copyright c Peter Corke 2011 . iline ipyramid Pyramidal image decomposition out = ipyramid(im) is a pyramid decomposition of input image im using Gaussian smoothing with standard deviation of 1. p1. v (N × P ) has one row for each point along the line and the row is the pixel value which will be a vector for a multi-plane image. Notes • The Bresenham algorithm is used to ﬁnd points along the line. p2) is a vector of pixel values extracted from the image im (HxWxP) between the points p1 (2 × 1) and p2 (2 × 1). p1. [p.uv] = iproﬁle(im. p2) as above but also returns the coordinates of the pixels for each point along the line.v) for the corresponding row of p.

op. hence output image had reduced dimensions. 12. is order=1. edge) as above but the processing of edge pixels can be controlled. The highest rank. im > irank(im. the image is assumed to wrap around Examples 5 × 5 median ﬁlter: irank(im. out = ipyramid(im. sigma. nbins. idecimate. See also iscalespace. The pyramid is computed down to a nonhalvable image size. out = imorph(image. ones(5. the maximum. FUNCTIONS AND CLASSES dimensions half that of the previous image. se) is a rank ﬁltered version of im. se). Notes • Works for greyscale images only.3). out = imorph(image. se. Machine Vision Toolbox for MATLAB 130 R Copyright c Peter Corke 2011 . out = ipyramid(im.CHAPTER 2. nbins) as above but the number of histogram bins can be speciﬁed. op. n) as above but only n levels of the pyramid are computed. se(2. The value of edge is: ‘border’ ‘none’ ‘trim’ ‘wrap’ the border value is replicated (default) pixels beyond the border are not included in the window output is not computed for pixels whose window crosses the border. order. Only pixels corresponding to non-zero elements of the structuring element se are ranked and the order’th value in rank becomes the corresponding output pixel value. se. ismooth irank Rank ﬁlter out = irank(im.5)). 3 × 3 non-local maximum: se = ones(3. 1.2) = 0. sigma) as above but the Gaussian standard deviation is sigma.

im = iread(ﬁle. options) reads the speciﬁed ﬁle and returns a matrix. See also imorph. If the path is relative it is searched for on Matlab search path. either numeric or ‘sRGB’ decimate image by R in both dimensions apply the region of interest R to each image. Notes • A greyscale image is returned as an H × W matrix • A color image is returned as an HxWx3 matrix • A greyscale image sequence is returned as an HxWxN matrix where N is the sequence length Machine Vision Toolbox for MATLAB 131 R Copyright c Peter Corke 2011 . Options ‘uint8’ ‘single’ ‘double’ ‘grey’ ‘grey 709’ ‘gamma’. convert image to greyscale if it’s color using ITU rec 601 convert image to greyscale if it’s color using ITU rec 709 gamma value. If multiple ﬁles match a 3D or 4D image is returned where the last dimension is the number of images in the sequence. G ‘reduce’. iwindow iread Read image from ﬁle im = iread() presents a ﬁle selection GUI from which the user can select an image ﬁle which is returned as 2D or 3D matrix. On subsequent calls the initial folder is as set on the last call.CHAPTER 2. return an image with double precision ﬂoating point pixels in the range 0 to 1. vmin vmax]. Wildcards are allowed in ﬁle names. where R=[umin umax. FUNCTIONS AND CLASSES Notes • Is a MEX ﬁle. ivar. • A histogram method is used with nbins (default 256). R return an image with 8-bit unsigned integer pixels in the range 0 to 255 return an image with single precision ﬂoating point pixels in the range 0 to 1. R ‘roi’.

out2. im2) is a rectiﬁed pair of images corresponding to im1 and im2. im2) as above but also returns the homographies h1 and h2 that warp im1 to out1 and im2 to out2 respectively. k) is an image where each pixel is replicated into a k × k tile.h1. im1. Notes • Color images are not supported. imono. imwrite. path irectify Rectify stereo image pair [out1. im1. [out1. See also FeatureMatch.out2] = irectify(f. FUNCTIONS AND CLASSES • A color image sequence is returned as an HxWx3xN matrix where N is the sequence length See also idisp. f (3 × 3) is the fundamental matrix relating the two views and m is a FeatureMatch object containing point correspondences between the images. Machine Vision Toolbox for MATLAB 132 R Copyright c Peter Corke 2011 . CentralCamera ireplicate Expand image out = ireplicate(im. • The resulting images may have negative disparity. m. Notes • The resulting image pair are epipolar aligned.h2] = irectify(f. homwarp. istereo.CHAPTER 2. If im is H × W the result is (KH)x(KW). igamma. m.

V ‘smooth’. out = iroi(im) as above but the image is displayed and the user is prompted to adjust a rubber band box to select the region of interest.umax. options) is a version of the image im that has been rotated about its centre.CHAPTER 2.R) is a subimage of the image im described by the rectangle R=[umin. [out. vmin.H] return central part of image. S set size of out to H × W where S=[W. See also idisp. iscale iroi Extract region of interest out = iroi(im. S ‘crop’ ‘scale’. iline irotate Rotate image out = irotate(im. same size as im scale the image size by S (default 1) set background pixels to V (default 0) smooth image with Gaussian of standard deviation S Machine Vision Toolbox for MATLAB 133 R Copyright c Peter Corke 2011 . S ‘extrapval’. Options ‘outsize’. angle. FUNCTIONS AND CLASSES See also idecimate.vmax].vmin vmax].R] = iroi(im) as above but returns the selected region of interest R=[umin umax.

5 moves the crop window down or to the right. s ‘extrapval’. s) is a version of im scaled in both directions by s which is a real scalar.H] set background pixels to V (default 0) smooth image with Gaussian of standard deviation s.5 is symmetric cropping. • Counter-clockwise is a positive angle. s<1 makes it smaller. bias<0. s>1 makes the image larger. V ‘smooth’. while bias>0. bias=0. out = isamesize(im1. s=[] means no smoothing (default s=1) Machine Vision Toolbox for MATLAB 134 R Copyright c Peter Corke 2011 .5 moves the crop window up or to the left. FUNCTIONS AND CLASSES Notes • Rotation is deﬁned with respect to a z-axis into the image. See also iscale iscale Scale an image out = iscale(im. bias) as above but bias controls which part of the image is cropped. s set size of out to H × W where s=[W. See also iscale isamesize Automatic image trimming out = isamesize(im1. im2) is an image derived from im1 that has the same dimensions as im2 which is achieved by cropping and scaling.CHAPTER 2. im2. Options ‘outsize’.

in space and scale.L. [g. of the Laplacian of Gaussian (LoG) scale-space image sequence L (HxWxN).s] = iscalespace(im. At each scale step the variance of the Gaussian increases by sigma2 . See also iscalespace. Machine Vision Toolbox for MATLAB 135 R Copyright c Peter Corke 2011 . The standard deviation of the smoothing Gaussian is sigma. g (HxWxN) is the scale sequence. and s (n × 1) is the vector of scales. sigma) is a scale space image sequence of length n derived from im (H × W ). s (N × 1) is a vector of scale values corresponding to each plane of L. Notes • The Laplacian is computed from the difference of adjacent Gaussians. irotate iscalemax Scale space maxima f = iscalemax(L. idecimate.s] = iscalespace(im. The ﬁrst step in the sequence is the original image. n) as above but sigma=1.CHAPTER 2. ScalePointFeature iscalespace Scale-space image sequence [g. FUNCTIONS AND CLASSES See also ireplicate. Notes • Features are sorted into descending feature strength. n. L (HxWxN) is the absolute value of the Laplacian of Gaussian (LoG) of the scale sequence. corresponding to each step of the sequence.L. s) is a vector of ScalePointFeature objects which are the maxima.

but also checks the validity of the rotation matrix.CHAPTER 2. ‘valid’) as above. it its third dimension is equal to three. See also isrot. FUNCTIONS AND CLASSES See also iscalemax. klog iscolor Test for color image iscolor(im) is true (1) if im is a color image. ismooth. isvec isift SIFT feature extractor sf = isift(im. options) returns a vector of SiftPointFeature objects representing scale and rotationally invariant interest points in the image im. The SiftPointFeature object has many properties including: Machine Vision Toolbox for MATLAB 136 R Copyright c Peter Corke 2011 . else false (0). ishomog(T. that is. ishomog Test if argument is a homogeneous transformation ishomog(T) is true (1) if the argument T is of dimension 4 × 4 or 4x4xN. ilaplace.

• If im is HxWxN it is considered to be an image sequence and F is a cell array with N elements. each of which is the feature vectors for the corresponding image in the sequence. 2 (2004). Reference David G. FUNCTIONS AND CLASSES u v strength descriptor sigma theta horizontal coordinate vertical coordinate feature strength feature descriptor (128 × 1) feature scale feature orientation [rad] Options ‘nfeat’. im) is an image where each pixel is the ZNCC similarity of the template T (M × M ) to the M × M neighbourhood surrounding the corresonding Machine Vision Toolbox for MATLAB 137 R Copyright c Peter Corke 2011 . International Journal of Computer Vision. • Wraps a MEX ﬁle from www. • Features are returned in descending strength order. See also SiftPointFeature. “Distinctive image features from scale-invariant keypoints”. icorner isimilarity Locate template in image s = isimilarity(T.vlfeat. R set the number of features to return (default Inf) set the suppression radius (default 0) Notes • Greyscale images only. 91-110. 60. isurf.org • Corners are processed in order from strongest to weakest. N ‘suppress’. • ISURF is a functional equivalent. Lowe. • The SIFT algorithm is patented by Univerity of British Columbia.CHAPTER 2. pp.

zncc isize Size of image n = isize(im. FUNCTIONS AND CLASSES input pixel in im. im. ncc. R Machine Vision Toolbox for MATLAB 138 Copyright c Peter Corke 2011 . See also imatch. and these output pixels are set to NaN.d) is the size of the d’th dimension of im.H] = isize(im) is the image height H and width w. @ssd. sad. @ncc. See also size ismooth Gaussian smoothing out = ismooth(im.CHAPTER 2. [w. s is same size as im. s = isimilarity(T. zssd. the function accepts two regions and returns a scalar similarity score. [w. zsad. Even if the image has only two dimensions p will be one.p] = isize(im) is the image height H and width w and number of planes p. @zsad. @zssd. metric) as above but the similarity metric is speciﬁed by the function metric which can be any of @sad. • The ZNCC function is a MEX ﬁle and therefore the fastest • User provided similarity metrics can be provided. Notes • Similarity is not computed where the window crosses the image boundary. sigma) is the image im after convolution with a Gaussian kernel of standard deviation sigma. ssd.H.

then converted back to integer.dx) as above but applies the kernel dx and dx’ to compute the horizontal and vertical gradients respectively. Options ‘full’ ‘same’ ‘valid’ returns the full 2-D convolution (default) returns out the same size as im returns the valid pixels only. convolved. kgauss isobel Sobel edge detector out = isobel(im) is an edge image computed using the Sobel edge operator applied to the image im. Machine Vision Toolbox for MATLAB 139 R Copyright c Peter Corke 2011 . The Sobel kernel is: | -1 | -2 | -1 0 0 0 1| 2| 1| out = isobel(im. options) as above but the options are passed to CONV2. those where the kernel does not exceed the bounds of the image. FUNCTIONS AND CLASSES out = ismooth(im. [gx. [gx. This is the norm of the vertical and horizontal gradients at each pixel.CHAPTER 2.gy] = isobel(im. See also iconv. • Smooths all planes of the input image • The Gaussian kernel has a unit volume • If input image is integer it is converted to ﬂoat.gy] = isobel(im) as above but returns the gradient images.dx) as above but returns the gradient images. sigma. Notes • By default (option ‘full’) the returned image is larger than the passed image.

See also ishomog.u).M] for an N × M window. ‘valid’) as above. range is the disparity search range. range. or a 2-vector [DMIN DMAX] for searches in the range DMIN to DMAX.CHAPTER 2. which can be a scalar for N × N or a 2-vector [N. w. [d. isvec istereo Stereo matching d = istereo(iml.u-d) is the same world point as iml(v.u) means that imr(v. isrot(R. which can be a scalar for disparities in the range 0 to range. range. That is. imr.sim] = istereo(iml. the disparity d=d(v. but also checks the validity of the rotation matrix. H. options) as above but returns sim which is the same size as d and the elements are the peak matching score for the corresponding Machine Vision Toolbox for MATLAB 140 R Copyright c Peter Corke 2011 . icanny. imr. See also ksobel. H is the half size of the matching window. • The resulting image is the same size as the input image. iconv isrot Test if argument is a rotation matrix isrot(R) is true (1) if the argument is of dimension 3 × 3. else false (0). FUNCTIONS AND CLASSES Notes • Tends to produce quite thick edges. d (H × W ) is the disparity and the value at each pixel is the horizontal shift of the corresponding pixel in iml as observed in imr. options) is a disparity image computed from the epipolar aligned stereo pair: the left image iml (H × W ) and the right image imr (H × W ).

p. M ‘interp’ string that speciﬁes the similarity metric to use which is one of ‘zncc’ (default). w. options) if the ‘interp’ option is given then disparity is estimated to sub-pixel precision using quadratic interpolation. ‘ncc’.CHAPTER 2. • Disparity values pixels within a half-window dimension (H) of the edges will not be valid and are set to NaN. range. Options ‘metric’. imr. a linear mapping where the minimum value of im is mapped to 0 and the maximum value of im is mapped to 1. w.p] = istereo(iml. For the default matching metric ZNCC this varies between -1 (very bad) to +1 (perfect).5 to +0.5). dx.B are matrices the same size as d whose elements are the per pixel values of the interpolation polynomial coefﬁcients.dx is the peak of the polynomial with respect to the integer disparity at which s is maximum (in the range -0. stdisp istretch Image normalization out = istretch(im) is a normalized image in which all pixel values lie in the range 0 to 1.A and p. range.max) as above but pixel values lie in the range 0 to max. 3) See also irectify. Machine Vision Toolbox for MATLAB 141 R Copyright c Peter Corke 2011 .dsi] = istereo(iml. imr.sim.sim. In this case d is the interpolated disparity and p is a structure with elements A. That is. FUNCTIONS AND CLASSES elements of d. enable subpixel interpolation and d contains non-integer values (default false) Notes • Images must be greyscale. [d. The interpolation polynomial is s = Ad2 + Bd + C where s is the similarity score and d is disparity relative to the integer disparity at which s is maximum. options) as above but returns dsi which is the disparity space image (HxWxN) where N=DMAX-DMIN+1. out = istretch(im. • sim = max(dsi. ‘ssd’ or ‘sad’. B. The I’th plane is the similarity of iml to imr shifted by DMIN+I-1. p. [d.

The SurfPointFeature object has many properties including: u v strength descriptor sigma theta horizontal coordinate vertical coordinate feature strength feature descriptor (64 × 1 or 128 × 1) feature scale feature orientation [rad] Options ‘nfeat’. Twente) or a MEX-ﬁle OpenCV wrapper by Petter Strandmark. N ‘extended’ ‘upright’ ‘suppress’. Increasing the threshold reduces the number of features computed and reduces computation time. Features are not returned if they are within R [pixels] of an earlier (stronger) feature. each of which is the feature vectors for the corresponding image in the sequence. N ‘thresh’. FUNCTIONS AND CLASSES See also inormhist isurf SURF feature extractor sf = isurf(im. • Wraps an M-ﬁle implementation of OpenSurf by D. options) returns a vector of SurfPointFeature objects representing scale and rotationally invariant interest points in the image im. Kroon (U. R set the number of features to return (default Inf) set Hessian threshold. Notes • Color images. number of octaves to process (default 5) return 128-element descriptor (default 64) don’t compute rotation invariance set the suppression radius (default 0).CHAPTER 2. • The sign of the Laplacian is not retained. or sequences. • Features are returned in descending strength order • If im is HxWxN it is considered to be an image sequence and F is a cell array with N elements. are ﬁrst converted to greyscale. Machine Vision Toolbox for MATLAB 142 R Copyright c Peter Corke 2011 . T ‘octaves’.

2008 See also SurfPointFeature. “SURF: Speeded Up Robust Features”. Andreas Ess. icorner isvec Test if argument is a vector isvec(v) is true (1) if the argument v is a 3-vector.or columnvector. Otherwise false (0).delay) as above but graphically displays each iteration of the skeletonization algorithm with a pause of delay seconds between each iteration. isift. Tinne Tuytelaars. Computer Vision and Image Understanding (CVIU). pp. either a row. Luc Van Gool. out = ithin(im. L) is true (1) if the argument v is a vector of length L. See also hitormiss. else false (0). isrot ithin Morphological skeletonization out = ithin(im) is the binary skeleton of the binary image im.CHAPTER 2. Any non-zero region is replaced by a network of single-pixel wide lines. Vol. iendpoint Machine Vision Toolbox for MATLAB 143 R Copyright c Peter Corke 2011 . itriplepoint. No. isvec(v. See also ishomog. FUNCTIONS AND CLASSES Reference Herbert Bay. 3. 110. 346–359.

out2] = itrim(im1. FUNCTIONS AND CLASSES ithresh Interactive image threshold ithresh(im) displays the image im in a window with a slider which adjusts the binary threshold. a lower value will include more.CHAPTER 2.im2) returns the central parts of images im1 and im2 as out1 and out2 respectively. • For a uint8 class image the slider range is 0 to 255. irectify Machine Vision Toolbox for MATLAB 144 R Copyright c Peter Corke 2011 . • For a ﬂoating point class image the slider range is 0 to 1.out2] = itrim(im1.im2.5. [out1.0 See also idisp itrim Trim images [out1. ithresh(im. The same cropping is applied to each input image. It assumes that the undeﬁned pixels in im1 and im2 have values of NaN.T) as above but the threshold T in the range 0 to 1 is used to adjust the level of cropping. This function crops out the central rectangular region of each. See also homwarp. Notes • Greyscale image only. T) as above but the initial threshold is set to T. The default is 0. a higher value will include fewer NaN value in the result. When images are rectiﬁed or warped the shapes can become quite distorted and are embedded in rectangular images surrounded by black of NaN values.

se. se. The operation op is one of: ‘var’ variance ‘kurt’ Kurtosis or peakiness of the distribution ‘skew’ skew or asymmetry of the distribution out = ivar(im. that is where three single-pixel wide line intersect. FUNCTIONS AND CLASSES itriplepoint Find triple points out = itriplepoint(im) is a binary image where pixels are set if the corresponding pixel in the binary image im is a triple point. hence output image had reduced dimensions. The elements in the neighbourhood corresponding to non-zero elements in se are packed into a vector on which the required statistic is computed. These are the Voronoi points in an image skeleton. edge) as above but performance at edge pixels can be controlled. Machine Vision Toolbox for MATLAB 145 R Copyright c Peter Corke 2011 . the image is assumed to wrap around Notes • Is a MEX ﬁle. Computed using the hit-or-miss morphological operator. ithin.CHAPTER 2. op. op) is an image where each output pixel is the speciﬁed statistic over the pixel neighbourhood indicated by the structuring element se which should have odd side lengths. hitormiss ivar Pixel window statistics out = ivar(im. See also iendpoint. The value of edge is: ‘border’ ‘none’ ‘trim’ ‘wrap’ the border value is replicated (default) pixels beyond the border are not included in the window output is not computed for pixels whose window crosses the border.

3). func) is an image where each pixel is the result of applying the function func to a neighbourhood centred on the corresponding pixel in im. The value of edge is: ‘border’ ‘none’ ‘trim’ ‘wrap’ the border value is replicated (default) pixels beyond the border are not included in the window output is not computed for pixels whose window crosses the border.5). • Is slow since the function func must be invoked once for every output pixel. out = iwindow(image. iwindow iwindow Generalized spatial operator out = iwindow(im. func.CHAPTER 2. The neighbourhood is deﬁned by the size of the structuring element se which should have odd side lengths. hence output image had reduced dimensions. The return value becomes the corresponding pixel value in out. irank Machine Vision Toolbox for MATLAB 146 R Copyright c Peter Corke 2011 . ones(3. @std). the image is assumed to wrap around Example Compute the maximum value over a 5 × 5 window: iwindow(im. Compute the standard deviation over a 3 × 3 window: iwindow(im. edge) as above but performance of edge pixels can be controlled. FUNCTIONS AND CLASSES See also irank. se. se. See also ivar. ones(5. The elements in the neighbourhood corresponding to non-zero elements in se are packed into a vector (in column order from top left) and passed to the speciﬁed function handle func. Notes • Is a MEX ﬁle. @max).

FUNCTIONS AND CLASSES kcircle Circular structuring element k = kcircle(R) is a square matrix S × S where S=2R+1 of zeros with a maximal centered circular region of radius R pixels set to one.CHAPTER 2. H) as above but the half-width is explictly speciﬁed. See also kgauss. Notes • This kernel is the horizontal derivative of the Gaussian.s) as above but s is explicitly speciﬁed. k = kcircle(R. • The vertical derivative. dG/dx. • This kernel is an effective edge detector. Notes • If R is a 2-element vector the result is an annulus of ones. iconv Machine Vision Toolbox for MATLAB 147 R Copyright c Peter Corke 2011 . See also ones. and the two numbers are interpretted as inner and outer radii. imorph kdgauss Derivative of Gaussian kernel k = kdgauss(sigma) is a 2-dimensional derivative of Gaussian kernel (W × W ) of width (standard deviation) sigma and centred within the matrix k whose half-width H = 3 × sigma and W=2 × H+1. dG/dy. is k’. klog. kdog. k = kdgauss(sigma. ktriangle.

Notes • This kernel is similar to the Laplacian of Gaussian and is often used as an efﬁcient approximation. k = kgauss(sigma. and centred within the matrix k whose half-width is H=2 × sigma and W=2 × H+1. H) as above but the half-width H is speciﬁed. kdgauss. sigma2) as above but sigma2 is speciﬁed directly. sigma2. iconv Machine Vision Toolbox for MATLAB 148 R Copyright c Peter Corke 2011 . See also kdgauss. FUNCTIONS AND CLASSES kdog Difference of Gaussian kernel k = kdog(sigma1) is a 2-dimensional difference of Gaussian kernel equal to KGAUSS(sigma1) . k = kdog(sigma1. iconv kgauss Gaussian kernel k = kgauss(sigma) is a 2-dimensional unit-volume Gaussian kernel of width (standard deviation) sigma.CHAPTER 2. See also kgauss. By default SIGMA2 = 1. H) as above but the kernel half-width is speciﬁed. kdog. The kernel is centred within the matrix k whose half-width H = 3 × SIGM A and W=2 × H+1. k = kdog(sigma1. where sigma1 > SIGMA2.KGAUSS(SIGMA2). klog. klog.6*sigma1.

k = klog(sigma. See also kgauss. iconv klog Laplacian of Gaussian kernel k = klog(sigma) is a 2-dimensional Laplacian of Gaussian kernel of width (standard deviation) sigma and centred within the matrix k whose half-width is H=3 × sigma. See also ilaplace. iconv. zcross Machine Vision Toolbox for MATLAB 149 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES klaplace Laplacian kernel k = klaplace() is the Laplacian kernel: —0 |1 1 0— -4 1| —0 1 0— Notes • This kernel has an isotropic response to gradient.CHAPTER 2. kdgauss. and W=2 × H+1. kdog. H) as above but the half-width H is speciﬁed.

CHAPTER 2.C] = kmeans(x. c0) as above but the initial clusters c0 (D × k) is given and column I is the initial estimate of the centre of cluster I. k. k. [L. it is assumed to have been completed previously.C] = kmeans(x. C (D × k) contains the cluster centroids and L (N × 1) indicates which cluster the corresponding element of x is closest to. C) is similar to above but the clustering step is not performed. The data is organized into k clusters based on Euclidean distance from cluster centres C (D × k). L is a vector (N ×1) whose elements indicates which cluster the corresponding element of x belongs to. L = kmeans(x. pp 94 ksobel Sobel edge detector k = ksobel() is the Sobel x-derivative kernel: |-1 |-2 |-1 0 0 0 1| 2| 1| Notes • This kernel is an effective horizontal edge detector • The Sobel vertical derivative is k’ Machine Vision Toolbox for MATLAB 150 R Copyright c Peter Corke 2011 . Options ‘random’ ‘spread’ initial cluster centres are chosen randomly from the set of data points x initial cluster centres are chosen randomly from within the hypercube spanned by x. FUNCTIONS AND CLASSES kmeans K-means clustering [L. Pattern Recognition Principles. options) is k-means clustering of multi-dimensional data points x (D × N ) where N is the number of points. Reference Tou and Gonzalez. and D is the dimension.

CHAPTER 2. FUNCTIONS AND CLASSES

See also

isobel

ktriangle

Triangular kernel

k = ktriangle(w) is a triangular kernel within a rectangular matrix k. The dimensions k are w × w if w is scalar or w(1) wide and w(2) high. The triangle is isocles and is full width at the bottom row of the kernel and with its apex in the top row.

Examples

>> ktriangle(3) ans = |0 1 0| |0 1 0| |1 1 1|

See also

kcircle

lambda2rg

RGB chromaticity coordinates

rgb = lambda2rg(lambda) is the rg-chromaticity coordinate (1 × 2) for illumination at the speciﬁc wavelength lambda [metres]. If lambda is a vector (N × 1), then P (N × 2) is a vector whose elements are the luminosity at the corresponding elements of lambda. rgb = lambda2rg(lambda, E) is the rg-chromaticity coordinate (1 × 2) for an illumination spectrum E (N × 1) and lambda (N × 1).

Machine Vision Toolbox for MATLAB 151

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

See also

cmfrgb, lambda2xy

lambda2xy

= LAMBDA2XY(LAMBDA) is the xy-chromaticity coordinate (1 × 2) for

illumination at the speciﬁc wavelength LAMBDA [metres]. If LAMBDA is a vector (N × 1), then P (N × 2) is a vector whose elements are the luminosity at the corresponding elements of LAMBDA. xy = lambda2xy(lambda, E) is the rg-chromaticity coordinate (1 × 2) for an illumination spectrum E (N × 1) and lambda (N × 1).

See also

cmfxyz, lambda2rg

loadspectrum

Load spectrum data

s = loadspectrum(lambda, ﬁlename) is spectral data (N × D) from ﬁle ﬁlename interpolated to wavelengths [metres] speciﬁed in lambda (N × 1). The spectral data can be scalar (D=1) or vector (D>1) valued. [s,lambda] = loadspectrum(lambda, ﬁlename) as above but also returns the passed wavelength lambda.

Notes

• The ﬁle is assumed to have its ﬁrst column as wavelength in metres, the remainding columns are linearly interpolated and returned as columns of s.

Machine Vision Toolbox for MATLAB 152

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

luminos

Photopic luminosity function

p = luminos(lambda) is the photopic luminosity function for the wavelengths in lambda. If lambda is a vector (N × 1), then p (N × 2) is a vector whose elements are the luminosity at the corresponding elements of lambda. Luminosity has units of lumens which are the intensity with which wavelengths are perceived by the light-adapted human eye.

See also

rluminos

maxﬁlt

maximum ﬁlter

MAXFILT(s [,w]) minimum ﬁlter a signal with window of width w (default is 5) SEE ALSO: medﬁlt, minﬁlt pic 6/93

medﬁlt1

Median ﬁlter

y = medﬁlt1(x, w) is the one-dimensional median ﬁlter of the signal x computed over a sliding window of width w.

Notes

• A median ﬁlter performs smoothing but preserves sharp edges, unlike traditional smoothing ﬁlters.

Machine Vision Toolbox for MATLAB 153

R

Copyright c Peter Corke 2011

[x. Options ‘T’.z] = mkcube(s. s. C ‘T’. The points are the columns of p. If d is a 2-vector the grid is d(1)xD(2) points. Options ‘facepoint’ ‘centre’. FUNCTIONS AND CLASSES mkcube Create cube p = mkcube(s. By default the grid lies in the XY plane. [x.z] = mkcube(s.y. ‘edge’. options) is a mesh that deﬁnes the edges of a cube. T the homogeneous transform T is applied to all points.y. The cube is centred at C (3 × 1) not the origin The cube is arbitrarily transformed by the homogeneous transform T Return a set of cube edges in MATLAB mesh format rather than points.CHAPTER 2. options) is a set of points (3 × 8) that deﬁne the vertices of a cube of side length s and centred at the origin. options) as above but return the rows of p as three vectors. options) is a set of points (3 x d2 ) that deﬁne a d × d planar grid of points with side length s. If s is a 2-vector the side lengths are s(1)xS(2). in this case the returned value is 3 × 14 (8 vertices + 6 face centres). T ‘edge’ Add an extra point in the middle of each face. See also cylinder. sphere mkgrid Create grid of points p = mkgrid(d. symmetric about the origin. Machine Vision Toolbox for MATLAB 154 R Copyright c Peter Corke 2011 . allowing the plane to be translated or rotated.

n) MPLOT(t. n) MPLOT(y. p. MPLOT(y) MPLOT(y. Subplots are labelled as per the data ﬁelds.y). npq. the sum of I(x. n is a row vector specifying which variables to plot (1 is ﬁrst data column. n is a row vector specifying which variables to plot (1 is ﬁrst data column. See also mpq poly. {labels}) Where y is multicolumn data and ﬁrst column is time.yq . upq Machine Vision Toolbox for MATLAB 155 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES mlabel for mplot style graph mlabel(lab1 lab2 lab3) mplot multiple data Plot y versus t in multiple windows.CHAPTER 2. y. Plot all other vectors versus time in subplots.xp . q) is the PQ’th moment of the image im. y.2)). MPLOT(S) Where S is a structure and one element ‘t’ is assumed to be time. y) MPLOT(t. labels is a cell array of labels for the subplots. mpq Image moments m = mpq(im. {labels}) Where y is multicolumn data and t is time. n.2)). or y(:. MPLOT(t. or y(:. labels is a cell array of labels for the subplots. That is.

CHAPTER 2. q) is the PQ’th moment of the polygon with vertices described by the columns of v. Machine Vision Toolbox for MATLAB 156 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES mpq poly Polygon moments m = MPQ POLY(v. • If the points are clockwise the moments will all be negated. See also mpq. p. they are considered to be a single vertex. npq poly. so centroids will be still be correct. • If the ﬁrst and last point in the list are the same. Polygon mtools simple/useful tools to all windows in ﬁgure ncc Normalized cross correlation m = ncc(i1. Notes • The points must be sorted such that they follow the perimeter in sequence (counterclockwise). The result m is a scalar in the interval -1 (non match) to 1 (perfect match) that indicates similarity. upq poly. i2) is the normalized cross-correlation between the two equally sized image patches i1 and i2.

The threshold at each pixel is a function of the mean and standard deviation computed over a W × W window. where W=2*w2+1. isimilarity niblack Adaptive thresholding T = niblack(im. W. w2) is the per-pixel (local) threshold to apply to image im. • A common choice of k=-0. FUNCTIONS AND CLASSES Notes • A value of 1 indicates identical pixel patterns. k. in text segmentation. • w2 should be chosen to be half the “size” of the features to be segmented.2 Reference An Introduction to Digital Image Processing. sad. -0. 20).CHAPTER 2. the height of a character. idisp(im >= t). • The ncc similarity measure is invariant to scale changes in image intensity.2. ssd. See also zncc. Machine Vision Toolbox for MATLAB 157 R Copyright c Peter Corke 2011 . k. T has the same dimensions as im. 1986.s] = niblack(im. w2) as above but returns the per-pixel mean m and standard deviation s. [T. Prentice-Hall. Example t = niblack(im. Notes • This is an efﬁcient algorithm very well suited for binarizing text. for example.m. niblack.

That is UPQ(im. p. q) is the PQ’th normalized central moment of the image im. Notes • The normalized central moments are invariant to translation and scale.0).0. p. b) npq Normalized central image moments m = npq(im. q) is the PQ’th normalized central moment of the polygon with vertices described by the columns of v. ithresh norm2 columnwise norm n = norm2(m) n = norm2(a. mpq.p. FUNCTIONS AND CLASSES See also otsu. See also npq poly. upq npq poly Normalized central polygon moments m = NPQ POLY(v.CHAPTER 2.q)/MPQ(im. Machine Vision Toolbox for MATLAB 158 R Copyright c Peter Corke 2011 .

See also numcols Machine Vision Toolbox for MATLAB 159 R Copyright c Peter Corke 2011 . npq. upq. See also mpq poly. so centroids will be still be correct. mpq. • If the points are clockwise the moments will all be negated. See also numrows numrows Return number of rows in matrix nr = numrows(m) returns the number of rows in the matrix m. • If the ﬁrst and last point in the list are the same. • The normalized central moments are invariant to translation and scale. Polygon numcols Return number of columns in matrix nc = numcols(m) returns the number of columns in the matrix m. FUNCTIONS AND CLASSES Notes • The points must be sorted such that they follow the perimeter in sequence (counterclockwise).CHAPTER 2. they are considered as a single vertex.

CHAPTER 2. Example t = otsu(im). [yp. FUNCTIONS AND CLASSES otsu Threshold selection T = otsu(im) is an optimal threshold for binarizing an image with a bimodal intensity histogram. ithresh peak Find peaks in vector yp = peak(y. Man and Cybernetics Vol SMC-9(1). T is a scalar threshold that maximizes the variance between the classes of pixels below and above the thresold T. N. Machine Vision Toolbox for MATLAB 160 R Copyright c Peter Corke 2011 . x is the same length of y and contains the corresponding x-coordinates. Reference A Threshold Selection Method from Gray-Level Histograms. x. [yp. Jan 1979. options) as above but also returns the corresponding x-coordinates of the maxima in the vector y. options) as above but also returns the indices of the maxima in the vector y. pp 62-66 See also niblack.xp] = peak(y.i] = peak(y. idisp(im >= t). options) are the values of the maxima in the vector y. Systems. Notes • Performance for images with non-bimodal histograms can be quite poor. otsu IEEE Trans.

CHAPTER 2.S points. See also peak2 peak2 Find peaks in a matrix zp = peak2(z. use peak(-V). N ‘scale’. use peak2(-V). Machine Vision Toolbox for MATLAB 161 R Copyright c Peter Corke 2011 . options) are the peak values in the 2-dimensional signal z. • The interp options ﬁts points in the neighbourhood about the peak with a paraboloid and its peak position is returned. Order of interpolation polynomial (default no interpolation) Display the interpolation polynomial overlaid on the point data Notes • To ﬁnd minima.S points. • The interp options ﬁts points in the neighbourhood about the peak with an N’th order polynomial and its peak position is returned. S ‘interp’ ‘plot’ Number of peaks to return (default all) Only consider as peaks the largest value in the horizontal and vertical range +/. Use SUB2IND to convert these to row and column coordinates Options ‘npeaks’. Interpolate peak (default no interpolation) Display the interpolation polynomial overlaid on the point data Notes • To ﬁnd minima. S ‘interp’. N ‘scale’. options) as above but also returns the indices of the maxima in the matrix z. [zp. N ‘plot’ Number of peaks to return (default all) Only consider as peaks the largest value in the horizontal range +/. Typically choose N to be odd. FUNCTIONS AND CLASSES Options ‘npeaks’.ij] = peak2(z.

sub2ind pgmﬁlt Pipe image through PGM utility out = pgmﬁlt(im. pgmcmd) pipes the image im through a Unix ﬁlter program and returns its output as an image. See also plot Machine Vision Toolbox for MATLAB 162 R Copyright c Peter Corke 2011 . If p has three dimensions. iread plot2 Plot trajectories plot2(p) plots a line with coordinates taken from successive rows of p. ie. The program given by the string pgmcmd must accept and return images in PGM format. p can be N × 2 or N × 3. plot2(p. See also pnmﬁlt.CHAPTER 2. Nx2xM or Nx3xM then the M trajectories are overlaid in the one plot. FUNCTIONS AND CLASSES See also peak. Notes • Provides access to a large number of Unix command line utilities such as ImageMagick. ls) as above but the line style arguments ls are passed to plot.

y2. 5). or a set of name. value pairs that are passed to plot. ’fillcolor’. Matlab color spec the color of the circle’s interior. 1=solid.Y] and with dimensions W=[WIDTH HEIGHT].y1) and (x2. PLOT BOX(’centre’. ls) draws a box with center at P=[X. ‘size’. Machine Vision Toolbox for MATLAB 163 R Copyright c Peter Corke 2011 .CHAPTER 2.y1. R. ls) draws a box with top-left at P=[X. plot circle Draw a circle on the current plot PLOT CIRCLE(C. ’LineWidth’. PLOT BOX(’topleft’. PLOT BOX(x1. ls) draws a box deﬁned by b=[XL XR. ’b’). P. ‘size’. YL YR] with optional Matlab linestyle options ls. Notes • the option can be either a simple linespec (eg. ’g’. Examples plot_circle(c. r. x2. W. ‘r’. Matlab color spec transparency of the ﬁlled circle: 0=transparent. r. If C (2 × N or 3 × N ) and R (1 × N ) then a set of N circles are drawn with centre and radius taken from the columns of C and R. options) draws a circle on the current plot with centre C=[X Y] and radius R. ‘g:’) for a non-ﬁlled circle. and optional Matlab linestyle options ls. Options ‘edgecolor’ ‘ﬁllcolor’ ‘alpha’ the color of the circle’s edge. ’r’). r. plot_circle(c.y2). plot_circle(c. FUNCTIONS AND CLASSES plot box a box on the current plot PLOT BOX(b. P. If C=[X Y Z] the circle is drawn in the XY-plane at height Z.Y] and with dimensions W=[WIDTH HEIGHT]. ’edgecolor’. W. ls) draws a box with corners at (x1.

plot frame Plot a coordinate frame represented by a homogeneous transformation trplot(T. Options ‘color’. FUNCTIONS AND CLASSES See also plot plot ellipse Draw an ellipse on the current plot PLOT ELLIPSE(a. with Matlab line style ls. If C=[X. options) draws a coordinate frame corresponding to the homogeneous transformation T. xc. ls) as above but centred at C=[X. centred at the origin.Y]. current plot. PLOT ELLIPSE(a. C. ls) draws an ellipse deﬁned by X’AX = 0 on the current plot.Y.Z] the ellipse is parallel to the XY plane but at height Z. Matlab colorspec ‘axes’ ’axis’ Machine Vision Toolbox for MATLAB 164 R Copyright c Peter Corke 2011 . ls) ls is the standard line styles.CHAPTER 2. plot ellipse inv Plot an ellipse plot ellipse(a. c Specify color of the axes.

ls) draws a line in the current ﬁgure L. ’r’). ’r’. ’color’. See also homline plot point point features PLOT POINT(p. Matlab line speciﬁcation ls can be set. to ‘view’. l Specify length of the axes (default 1) Examples: trplot( T. fmt. Options ‘textcolor’. The return argument is a vector of graphics handles for the lines.X = 0. w ‘arrow’ ’length’. data Label points according to printf format string and corresponding element of data ‘sequence’ Label points sequentially Additional options are passed through to PLOT for creating the marker. v Specify the view angle for the Matlab axes ‘width’. colspec Specify color of text ‘textsize’. ’color’. Machine Vision Toolbox for MATLAB 165 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES ‘name’. n Specify the name of the coordinate frame. The current axis limits are used to determine the endpoints of the line.CHAPTER 2. trplot( T. where p is 2 × N and each column is the point coordinate. ‘framename’. n ‘text opts’. ‘printf’. options) adds point markers to a plot. ’name’. size Specify size of text ‘bold’ Text in bold font. ’B’) plot homline Draw a line in homogeneous form H = PLOT HOMLINE(L.

C is the centre of the sphere and if its a 3 × N matrix then N spheres are drawn with centres as per the columns. See also plot. patch. NOTES • The sphere is always added. FUNCTIONS AND CLASSES See also plot. Matlab color spec transparency of the ﬁlled circle: 0=transparent. H = PLOT SPHERE(C. R. alpha) as above but alpha speciﬁes the opacity of the sphere were 0 is transparant and 1 is opaque. R. The default is 1. options) plot a polygon deﬁned by columns of p which can be 2 × N or 3 × N. options ‘ﬁll’ ‘alpha’ the color of the circle’s interior. R is the radius and color is a Matlab color spec. text plot poly Plot a polygon plotpoly(p. either a letter or 3-vector. • The number of vertices to draw the sphere is hardwired. irrespective of ﬁgure hold state. Polygon plot sphere Plot spheres PLOT SPHERE(C. R. color. color) as above but returns the handle(s) for the spheres. H = PLOT SPHERE(C. color) add spheres to the current ﬁgure. Machine Vision Toolbox for MATLAB 166 R Copyright c Peter Corke 2011 . 1=solid.CHAPTER 2.

plotp(p. pnmcmd) pipes the image im through a Unix ﬁlter program and returns its output as an image. ls) as above but the line style arguments ls are passed to plot. By default a linestyle of ‘bx’ is used. The program given by the string pnmcmd must accept and return images in PNM format.CHAPTER 2. p can be N × 2 or N × 3. See also plot. FUNCTIONS AND CLASSES plotp Plot trajectories plotp(p) plots a set of points p. which by Toolbox convention are stored one per column. See also pgmﬁlt. iread Machine Vision Toolbox for MATLAB 167 R Copyright c Peter Corke 2011 . Notes • Provides access to a large number of Unix command line utilities such as ImageMagick. plot2 pnmﬁlt Pipe image through PNM utility out = pnmﬁlt(im.

• translational component is zero See also t2r radgrad Radial gradient [gr.gt] = radgrad(im.gt] = radgrad(im) is the radial and tangential gradient of the image im. or – if R is 3 × 3 then T is 4 × 4. centre) as above but the centre of the image is speciﬁed as centre=[X. At each pixel the image gradient vector is resolved into the radial and tangential directions.Y] rather than the centre pixel of im. [gr.CHAPTER 2. FUNCTIONS AND CLASSES r2t Convert rotation matrix to a homogeneous transform T = r2t(R) is a homogeneous transform equivalent to an orthonormal rotation matrix R with a zero translational component. Notes • functions for T in SE(2) or SE(3) – if R is 2 × 2 then T is 3 × 3. See also isobel Machine Vision Toolbox for MATLAB 168 R Copyright c Peter Corke 2011 . radgrad(im) as above but the result is displayed graphically.

one column per point pair. x. options) is the ransac algorithm that robustly ﬁts data x to the model represented by the function func.CHAPTER 2. ransac classiﬁes Points that support the model as inliers and those that do not as outliers. See also linspace ransac Random sample and consensus m = ransac(func. x typically contains corresponding point data. N maximum number of iterations (default 2000) maximum number of attempts to select a non-degenerate data set (default 100) Model function out = func(R) is the function passed to RANSAC and it must accept a single argument R which is a structure: Machine Vision Toolbox for MATLAB 169 R Copyright c Peter Corke 2011 . if the ﬁt residual is aboe the the threshold the point is considered an outlier. [m. T. [m.in] = ransac(func.resid] = ransac(func. T. ransac determines the subset of points (inliers) that best ﬁt the model described by the function func and the parameter m. FUNCTIONS AND CLASSES ramp create a ramp vector ramp(n) output a vector of length n that ramps linearly from 0 to 1 ramp(v) as above but vector is same length as v ramp(v. N ‘maxDataTrials’.in. options) as above but returns the vector in of column indices of x that describe the inlier point set. T. x. x. T is a threshold on how well a point ﬁts the estimated. Options ‘maxTrials’. options) as above but returns the ﬁnal residual of applying func to the inlier set. d) as above but elements increment by d.

CHAPTER 2.theta is a cell array.x data to work on.theta to the points R.T) evaluates the distance from the model(s) R. Comm. 2001 Machine Vision Toolbox for MATLAB 170 R Copyright c Peter Corke 2011 .inlier. pp 101-113. ‘error’ Notes • For some algorithms (eg. [out. Vol 24.inlier list of inliers (1 × m) out.resid model ﬁt residual (1 × 1) The values of R. N point pairs (6 × N ) R. that is they will produce a model. • The functions FMATRIX and HOMOG are written so as to be callable from RANSAC. Comp. This is used to discard random samples that do not result in useful models.A. Cambridge University Press.misc element.valid if data is valid for estimation (logical) out. Assoc. and the data transform parameters are kept in the . References • m.s is the minimum number of points required to compute an estimate to out.theta = [].x conditioned data (2D × N ) out.debug display what’s going on (logical) R. 1981 • Richard Hartley and Andrew Zisserman. FUNCTIONS AND CLASSES R.theta. For efﬁciency the data is conditioned once. that is.cmd are: ‘size’ ‘condition’ ‘decondition’ ‘valid’ ‘estimate’ out.x. The inverse conditioning operation is applied to the model to transform the estimate based on conditioned data to a model applicable to the original data.x) returns the best ﬁt model and residual for the subset of points R.out.s sample size (1 × 1) out.cmd the operation to perform which is either (string) R. they detect a structure argument. ”Multiple View Geometry in Computer Vision”.. Fishler and R. [out. pp 381-395.x and returns the best model out.theta and the subset of R.theta.theta) decondition the estimated model data out.misc private data (cell array) The function return value is also a structure: out. If multiple models are found out.x that best supports (most inliers) that model. ”Random sample concensus: A paradigm for model ﬁtting with applications to image analysis and automated cartography”.t threshold (1 × 1) R.C.s out.theta] = ERR(R.theta estimated quantity (3 × 3) out.theta estimated quantity to test (3 × 3) R.x = CONDITION(R.resid] = EST(R.theta = DECONDITION(R.R. Mach. If this function cannot ﬁt a model then out.x. fundamental matrix) it is necessary to condition the data to improve the accuracy of model estimation. No 6.misc private data (cell array) out.out.valid is true if a set of points is not degenerate. Boles.x) condition the point data out.

then p is a vector whose elements are the relative luminosity at the corresponding elements of lambda. See also luminos Machine Vision Toolbox for MATLAB 171 R Copyright c Peter Corke 2011 . homography rg addticks Label spectral locus RG ADDTICKS() adds wavelength ticks to the spectral locus.au/ pk See also fmatrix. If lambda is a vector.uwa. Relative luminosity lies in the interval 0 to 1 which indicate the intensity with which wavelengths are perceived by the light-adapted human eye.edu. FUNCTIONS AND CLASSES Author Peter Kovesi School of Computer Science & Software Engineering The University of Western Australia pk at csse uwa edu au http://www.CHAPTER 2. See also xycolourspace rluminos Relative photopic luminosity function p = ruminos(lambda) is the relative photopic luminosity function for the wavelengths in lambda.csse.

roty. angvec2r Machine Vision Toolbox for MATLAB 172 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES rotx Rotation about X axis R = rotx(theta) is a rotation matrix representing a rotation of theta about the x-axis. See also rotx.CHAPTER 2. rotz. rotz. See also roty. See also rotx. angvec2r rotz Rotation about Z axis R = rotz(theta) is a rotation matrix representing a rotation of theta about the z-axis. angvec2r roty Rotation about Y axis R = roty(theta) is a rotation matrix representing a rotation of theta about the y-axis.

where the last index corresponds to the rows of rpy. If rpy has multiple rows they are assumed to represent a trajectory and R is a three dimensional matrix. Spong) use the rotation order ZYX. Note • in previous releases (<8) the angles corresponded to rotations about ZYX. If roll. eul2tr rt2tr Convert rotation and translation to homogeneous transform TR = rt2tr(R. Z axes respectively. pitch. then TR is 3 × 3 – If R is 3 × 3 and t is 3 × 1. pitch. then TR is 4 × 4 • the validity of R is not checked Machine Vision Toolbox for MATLAB 173 R Copyright c Peter Corke 2011 . • many texts (Paul. FUNCTIONS AND CLASSES rpy2tr Roll-pitch-yaw angles to homogeneous transform T = rpy2tr(rpy) is an orthonormal rotation matrix equivalent to the speciﬁed roll. See also tr2rpy. yaw) as above but the roll-pitch-yaw angles are passed as separate arguments. yaw angles which correspond to rotations about the X. Y. where the last index corresponds to the rows of roll. T = rpy2tr(roll. Notes • functions for R in SO(2) or SO(3) – If R is 2 × 2 and t is 2 × 1. pitch and yaw are column vectors then they are assumed to represent a trajectory and R is a three dimensional matrix. t) is a homogeneous transformation matrix formed from an orthonormal rotation matrix R and a translation vector t. yaw.CHAPTER 2. pitch.

theta) is a 3 × 3 homogeneous transformation SE(2) representing translation x and y. See also zsad. ssd.theta] See also trplot2 Machine Vision Toolbox for MATLAB 174 R Copyright c Peter Corke 2011 .CHAPTER 2.y] T = se2(xyt) as above where xyt=[x.y. isimilarity se2 Create planar translation and rotation transformation T = se2(x. FUNCTIONS AND CLASSES See also t2r. The result m is a scalar that indicates image similarity.y] and rotation is zero T = se2(xy. theta) as above where xy=[x. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases. i2) is the sum of absolute differences between the two equally sized image patches i1 and i2. r2t. ncc. tr2rt sad Sum of absolute differences m = sad(i1. and rotation theta in the plane. T = se2(xy) as above where xy=[x. y.

See also zsdd. ncc. Clicking a point in the left image positions black cross hair at the same pixel coordinate in the right image.CHAPTER 2. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases. Two cross-hairs are created. R) displays the stereo image pair L and R in adjacent windows. sad. FUNCTIONS AND CLASSES skew Create skew-symmetric matrix s = skew(v) is a skew-symmetric matrix and v is a 3-vector. Clicking the corresponding world point in the right image sets the green crosshair and displays the disparity [pixels]. See also vex ssd Sum of squared differences m = ssd(i1. The result m is a scalar that indicates image similarity. i2) is the sum of squared differences between the two equally sized image patches i1 and i2. isimilarity stdisp Display stereo pair stdisp(L. Machine Vision Toolbox for MATLAB 175 R Copyright c Peter Corke 2011 .

• the validity of rotational part is not checked See also r2t.choose = {’this’. rt2tr tb optparse Standard option parser for Toolbox functions [optout. – If T is 3 × 3. boolean or enumeration types (string or int). The software pattern is: function(a. tr2rt.bar = false. opt.args] = TB OPTPARSE(opt. c.CHAPTER 2. ’other’}. then R is 2 × 2. varargin) opt. FUNCTIONS AND CLASSES See also idisp. It supports options that have an assigned value. b. Machine Vision Toolbox for MATLAB 176 R Copyright c Peter Corke 2011 . then R is 3 × 3. arglist) is a generalized option parser for Toolbox functions. ’that’. opt. istereo t2r Return rotational submatrix of a homogeneous transformation R = t2r(T) is the orthonormal rotation matrix component of homogeneous transformation matrix T: Notes • functions for T in SE(2) or SE(3) – If T is 4 × 4. opt.blah = [].foo = true.

3 ‘blah’.choose <.choose <. • that only one value can be assigned to a ﬁeld. Note: • that the enumerator names must be distinct from the ﬁeld names. N ‘setopt’.true sets opt.CHAPTER 2.‘this’. if multiple values are required they must be converted to a cell array. By default if an option is given that is not a ﬁeld of opt an error is declared.blah <.blah <.y sets opt.‘that’ ‘yes’ sets opt. Sometimes it is useful to collect the unassigned options and this can be achieved using a second output argument [opt. ’#yes’}. Optional arguments to the function behave as follows: ‘foo’ sets opt. If w is a scalar the image is w × w else w(2)xW(1). 3 sets opt.1.foo <.y ‘that’ sets opt. The following options are automatically parsed: ‘verbose’ ‘debug’. If neither of ‘this’. varargin). If neither of ‘no’ or ‘yes’ are speciﬁed then opt.2 (the second element) and can be given in any combination.true ‘nobar’ sets opt. x.N sets opt <. The allowable options are speciﬁed by the names of the ﬁelds in the structure opt. opt = tb_optparse(opt.select <. w.foo <. The image is speciﬁed by the string type and one or two (type speciﬁc) arguments: Machine Vision Toolbox for MATLAB 177 R Copyright c Peter Corke 2011 . varargin). FUNCTIONS AND CLASSES opt.select <. args) creates a test pattern image.false ‘blah’.verbose <.debug <.S displays opt and arglist testpattern Create test images im = testpattern(type.arglist] = tb_optparse(opt. ‘that’ or ‘other’ are speciﬁed then opt.x. which is a cell array of all unassigned arguments in the order given in varargin.select = {’#no’. S ‘showopt’ sets opt. The return structure is automatically populated with ﬁelds: verbose and debug.

25). Velocity and acceleration can be optionally returned as sd and sdd.sd. sinusoidal intensity pattern (from -1 to 1) in the y-direction.CHAPTER 2. Examples A 256 × 256 image with 2 cycles of a horizontal sawtooth intensity ramp: testpattern(’rampx’. Notes • With no output argument the testpattern in displayed using idisp. T) as above but speciﬁes the trajectory in terms of the length of the time vector T. binary dot pattern. 256. sf. 50. intercept. A 256 × 256 image with a grid of dots on 50 pixel centres and 20 pixels in diameter: testpattern(’dots’.sdd] = tpoly(s0. square side length. args is the number of cycles. sd and sdd are n-vectors. args are dot pitch (distance between centres). intensity ramp from 0 to 1 in the y-direction. 2). FUNCTIONS AND CLASSES ‘rampx’ ‘rampy’ ‘sinx’ ‘siny’ ‘dots’ ‘squares’ ‘line’ intensity ramp from 0 to 1 in the x-direction. See also idisp tpoly Generate scalar polynomial trajectory [s. Machine Vision Toolbox for MATLAB 178 R Copyright c Peter Corke 2011 . [s. n) is a trajectory of a scalar that varies smoothly from s0 to sf in n steps using a quintic (5th order) polynomial. args is the number of cycles. args is the number of cycles. 256. a line. The trajectory s.sd. args is the number of cycles. sf. sinusoidal intensity pattern (from -1 to 1) in the x-direction.sdd] = tpoly(s0. dot diameter. binary square pattern. args are theta (rad). args are pitch (distance between centres).

Y] correspond to sequential rotations about the X. Notes • If no output arguments are speciﬁed the result is displayed. then each row of rpy corresponds to a step of the trajectory. Options ‘deg’ ‘zyx’ Compute angles in degrees (radians default) Return solution for sequential rotations about Z. See also angvec2r. options) are the roll-pitch-yaw angles expressed as a row vector corresponding to the orthonormal rotation matrix R.v] = tr2angvec(T) is a rotation of theta about the vector v equivalent to the rotational component of the homogeneous transform T. Y and Z axes respectively.v] = tr2angvec(R) is a rotation of theta about the vector v equivalent to the orthonormal rotation matrix R.CHAPTER 2. FUNCTIONS AND CLASSES tr2angvec Convert rotation matrix to angle-vector form [theta. angvec2tr tr2rpy Convert a homogeneous transform to roll-pitch-yaw angles rpy = tr2rpy(T. rpy = tr2rpy(R. X axes (Paul book) Notes • There is a singularity for the case where THETA=0 in which case PHI is arbitrarily set to zero and PSI is the sum (PHI+PSI).P. options) are the roll-pitch-yaw angles expressed as a row vector corresponding to the rotation part of a homogeneous transform T. Machine Vision Toolbox for MATLAB 179 R Copyright c Peter Corke 2011 . The 3 angles rpy=[R. Y. If R or T represents a trajectory (has 3 dimensions). [theta.

t] = tr2rt(TR) split a homogeneous transformation matrix into an orthonormal rotation matrix R and a translation vector t.:. T = transl(p) is a homogeneous transform representing a translation or point p=[x. If p is an M × 3 matrix transl returns a 4x4xM matrix representing a sequence of homogenous transforms such that T(:.y. See also rt2tr. y. p = transl(T) is the translational part of a homogenous transform as a 3-element column vector. – If TR is 3 × 3. then R is 2 × 2 and T is 2 × 1. ie. t2r transl Create translational transform T = transl(x. 4x4xN then T is considered a homgoeneous Machine Vision Toolbox for MATLAB 180 R Copyright c Peter Corke 2011 . then R is 3 × 3 and T is 3 × 1. If T has three dimensions. FUNCTIONS AND CLASSES • Note that textbooks (Paul. Spong) use the rotation order ZYX.i) corresponds to the i’th row of p.CHAPTER 2. tr2eul tr2rt Convert homogeneous transform to rotation and translation [R.z]. z) is a homogeneous transform representing a pure translation. Notes • Functions for TR in SE(2) or SE(3) – If TR is 4 × 4. r2t. • The validity of R is not checked. See also rpy2tr.

The O and A vectors are normalized and the normal vector is formed from O x A. [c1.o2] = tristim2cc(im) as above but the chromaticity is returned as separate images (H × W ). An historical anomaly.C2] = tristim2cc(tri) as above but the chromaticity coordinates are returned in separate vectors. or x and y. out = tristim2cc(im) is the chromaticity coordinates corresponding to every pixel in the tristimulus image im (HxWx3). trnorm Normalize a homogeneous transform tn = trnorm(T) is a normalized homogeneous transformation matrix in which the rotation submatrix is guaranteed to be a proper orthogonal matrix.CHAPTER 2. Multiple tristimulus values can be given as rows of tri (N × 3) in which case the chromaticity coordinates are the corresponding rows of cc (N × 2). Notes • somewhat unusually this function performs a function and its inverse. if tri is XYZ then cc is xy. Machine Vision Toolbox for MATLAB 181 R Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES transform sequence and returns an N × 3 matrix where each row is the translational component of the corresponding transform in the sequence. If tri is RGB then cc is rg. out (HxWx2) has planes corresponding to r and g. See also ctraj tristim2cc Tristimulus to chromaticity coordinates cc = tristim2cc(tri) is the chromaticity coordinate (1 × 2) corresponding to the tristimulus tri (1 × 3). [o1. each N × 1.

trotz troty Rotation about Y axis T = troty(theta) is a homogeneous transformation representing a rotation of theta about the y-axis. FUNCTIONS AND CLASSES Notes • Used to prevent ﬁnite word length arithmetic causing transforms to become ‘unnormalized’.CHAPTER 2. troty. Notes • translational component is zero Machine Vision Toolbox for MATLAB 182 R Copyright c Peter Corke 2011 . See also oa2tr trotx Rotation about X axis T = trotx(theta) is a homogeneous transformation representing a rotation of theta about the x-axis. Notes • translational component is zero See also rotx.

trprint T is the command line form of above. trotx. Notes • translational component is zero See also rotz. trotx. trotz trotz Rotation about Z axis T = trotz(theta) is a homogeneous transformation representing a rotation of theta about the z-axis. FUNCTIONS AND CLASSES See also roty. l display with rotation in roll/pitch/yaw angles (default) display with rotation in ZYX Euler angles display with rotation in angle/vector format display angle in radians (default is degrees) use format string f for all numbers. options) displays the homogoneous transform in a compact single-line format. If T is a homogeneous transform sequence then print each element is printed on a separate line. Options ‘rpy’ ‘euler’ ‘angvec’ ‘radian’ ‘fmt’.CHAPTER 2. troty trprint Compact display of homogeneous transformation trprint(T. (default %g) display the text before the transform Machine Vision Toolbox for MATLAB 183 R Copyright c Peter Corke 2011 . and displays in RPY format. f ‘label’.

npq Machine Vision Toolbox for MATLAB 184 R Copyright c Peter Corke 2011 . p.y). upq Central image moments m = upq(im.CHAPTER 2. mpq.y0) is the centroid. the sum of I(x.(y-y0)q where (x0. tr2rpy. FUNCTIONS AND CLASSES See also tr2eul. tr2angvec unit Unitize a vector vn = unit(v) is a unit vector parallel to v. Note • fails for the case where norm(v) is zero. q) is the PQ’th central moment of the image im. That is. See also upq poly.(x-x0)p . Notes • The central moments are invariant to translation.

CHAPTER 2. FUNCTIONS AND CLASSES

upq poly

Central polygon moments

m = UPQ POLY(v, p, q) is the PQ’th central moment of the polygon with vertices described by the columns of v.

Notes

• The points must be sorted such that they follow the perimeter in sequence (counterclockwise). • If the points are clockwise the moments will all be negated, so centroids will be still be correct. • If the ﬁrst and last point in the list are the same, they are considered as a single vertex. • The central moments are invariant to translation.

See also

upq, mpq poly, npq poly

useﬁg

a named ﬁgure or create a new ﬁgure

useﬁg(’Foo’) make ﬁgure ‘Foo’ the current ﬁgure, if it doesn’t exist create it. h = useﬁg(’Foo’) as above, but returns the ﬁgure handle

vex

Convert skew-symmetric matrix to vector

v = vex(s) is the vector which has the skew-symmetric matrix s.

Machine Vision Toolbox for MATLAB 185

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

Notes

• No checking is done to ensure that the matrix is skew-symmetric. • The function takes the mean of the two elements that correspond to each unique element of the matrix, ie. vx = 0.5*(s(3,2)-s(2,3))

See also

skew

xaxis

X-axis scaling

xaxis(max) xaxis([min max]) xaxis(min, max) xaxis restore automatic scaling for this axis

xycolorspace

Display spectral locus

xycolorspace() display a fully colored spectral locus in terms of CIE x and y coordinates. xycolorspace(p) as above but plot the points whose xy-chromaticity is given by the columns of p. [im,ax,ay] = xycolorspace() as above returns the spectral locus as an image im, with corresponding x- and y-axis coordinates ax and ay respectively.

Notes

• The colors shown within the locus only approximate the true colors, due to the gamut of the display device.

Machine Vision Toolbox for MATLAB 186

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

See also

rg addticks

yaxis

Y-axis scaling

yayis(max) yayis(min, max) YAXIS restore automatic scaling for this axis

zcross

Zero-crossing detector

iz = zcross(im) is a binary image with pixels set where the corresponding pixels in the signed image im have a zero crossing, a positive pixel adjacent to a negative pixel.

Notes

• Can be used in association with a Lapalacian of Gaussian image to determine edges.

See also

ilog

Machine Vision Toolbox for MATLAB 187

R

Copyright c Peter Corke 2011

isimilarity Machine Vision Toolbox for MATLAB 188 R Copyright c Peter Corke 2011 . The result m is a scalar that indicates image similarity. isimilarity zsad Sum of absolute differences m = zsad(i1. i2) is the zero-mean normalized cross-correlation between the two equally sized image patches i1 and i2. FUNCTIONS AND CLASSES zncc Normalized cross correlation m = zncc(i1. Notes • The zncc similarity measure is invariant to afﬁne changes in image intensity (brightness offset and scale). ssd. sad. ssd. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases.CHAPTER 2. A value of 1 indicates identical pixel patterns. ncc. See also ncc. Notes • The zsad similarity measure is invariant to changes in image brightness offset. The result m is a scalar in the interval -1 to 1 that indicates similarity. See also sad. i2) is the zero-mean sum of absolute differences between the two equally sized image patches i1 and i2.

Notes • The zssd similarity measure is invariant to changes in image brightness offset. FUNCTIONS AND CLASSES zssd Sum of squared differences m = zssd(i1. isimilarity Machine Vision Toolbox for MATLAB 189 R Copyright c Peter Corke 2011 . ncc. See also sdd. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases. The result m is a scalar that indicates image similarity.CHAPTER 2. sad. i2) is the zero-mean sum of squared differences between the two equally sized image patches i1 and i2.

Sign up to vote on this title

UsefulNot useful- Machine Vision Toolbox for Matlab
- Vision
- lab02
- Matlab
- ANPR PowerPoint
- Robotics Toolbox for Matlab (Peter Corke)
- MATLAB Assignment Help myassignmenthelp.net
- Ch 1 Brief Overview of MATLAB
- INTRO TO MATLAB
- 10 Ea PIV Stereoscopic PIV Educational Slide Show
- Intro to Matlab
- Intro to Matlab
- A Para Perspective Factorization Method for Shape and Motion Recovery
- M893-IS_exUG_GLB_en
- KodakDigital-EasyShare-C340
- Gsizer Eng 2009
- Robotics Toolbox
- MATLAB Simulink Tutorial
- Quat
- Avtron IR Varifocal Dome Camera AM-W606-VMR1
- Log
- CDROM Appendix E
- Steadicam Merlin
- Canon A1
- 0-360guide_5700
- WFS_Ebook_01.pdf
- Canon U.S.a. _ Consumer & Home Office _ PowerShot A2300
- Information Display for digital dslr Camera
- Cubic QTVR Tutorial
- Interfacing MATLAB and ROS.pdf
- Machine Vision Toolbox for MATLABr3