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

This toolbox considers images generally as arrays of double precision numbers. This toolbox predates IPT by many years. is open-source. Vision & Control” provides a detailed discussion (over 600 pages. This is extravagant on storage. and I commend it to you. However the book “Robotics. though this is much less signiﬁcant today than it was in the past. nearly 400 ﬁgures and 1000 code examples) of how to use the Toolbox functions to solve many types of problems in 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. This toolbox is not a clone of the Mathwork’s own Image Processing Toolbox (IPT) although there are many functions in common. contains many functions that are useful for image feature extraction and control.MATLAB compiler available then this can be used to compile bottleneck functions. It was developed under Unix and Linux systems and some functions rely on tools and utilities that exist only in that environment. Some particularly compute intensive functions are provided as mex-ﬁles and may need to be compiled for the particular platform. R R Machine Vision Toolbox for MATLAB R 4 Copyright c Peter Corke 2011 .

. . . . . . . . . . . . 1. . . . Machine Vision Toolbox for MATLAB R 5 Copyright c Peter Corke 2011 . . . . . .6 Use in research . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 What’s new . . . . . . . . . . . . . FeatureMatch . . . . SiftPointFeature . . . . . . . . . LineFeature . . . . . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . PGraph . . . . . . . . . . . . . .3 How to obtain the Toolbox 1. . . . anaglyph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Video . . . . . . . . . . . . . . . . . . . . 1. . . . . . AxisWebCamera . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Tracker . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . SphericalCamera . . . . . . . . . . . . . . . .2 Support . Movie . . . . . . . . . . . . . . . . . . . . . . . . . . Hough . . . . . . . . . . . . . . . . . . . . ScalePointFeature . . . .4 MATLAB version issues . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . PointFeature . . Ray3D . RegionFeature . . . . . . . . . . . . . . . . . . . . . . . . . . . . .6. . . . . . . . . . . . . . . . . . . . . . . . . . . . 1. . . CentralCamera . . . . . . . 2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . angdiff . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .1 Other toolboxes . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . Polygon . . . . . . . SurfPointFeature . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . . . . . . . BagOfWords . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .Contents Introduction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .7 Acknowledgements . . . . . . 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 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 1 Introduction 1. . . . . . . . . . . . . . . . . . . . . . 1. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . CatadioptricCamera . . . . . . . . . . . Functions and classes Camera . . . . . . . . . about . . FishEyeCamera . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .5 Use in teaching . . . blackbody . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . colordistance colorize . . . iconv . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . epiline . . . . . . . . . . . . . iendpoint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iclose . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ibbox . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idisplabel . . . . . . . . . . . diff2 . . ccdresponse . . . . . . . . . . . . . . . . . . cmfxyz . . . . . . . . . . . . . . . . . . . . . . . 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 . . . . . . . . . . .CONTENTS CONTENTS boundmatch . iconcat . . . . . . . . . . . . colorname . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . idecimate . . . . . . . . h2e . . . . . . . . . . . homwarp . . . . . . . . . . . . . . . . . . . . idisp . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . igamma . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iblobs . . . . . . . . . . . . . . . . . R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . icp . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ihist . . . . . . . . . . igraphseg . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . fmatrix . . . . . . . . . . . . . . icorner . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . col2im . . . ianimate . . . . . . . . . . . . . . . gauss2d . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . colorspace . . . hitormiss . . . . icolor . homtrans . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . edgelist . distance . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . e2h . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . closest . . . . . . . . . . . . . . . . . . . . . . homline . . . . . . . . . . . . . . . . . . . . bresenham . . . . . . . . . . . . . . . . . . cmfrgb . . . . . . . . . . . . . . icanny . . . . . . . . idouble . . . . . . . . . . . . . . . . . . . . . . . . . . . . . colorkmeans . . . . . . . . . . . . . . . . . . . . . . homography . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . cie primaries circle . . . . . . . . . . . . . . 6 . . . . . . . . . . . . . . . . . . . colnorm . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . humoments . . . . . . . . . . . . . . . . . . . . . . . . . . . epidist . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . camcald . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . imatch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . itriplepoint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isurf . . . . . . . . . . . . . . . . . . . imser . . . . . . . . . . . . . . . . . . . . . . isobel . . . . . . . . . . . . . iroi . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . irank . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . kgauss . . . . im2col . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isift . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iproﬁle . . . . . . . . . . . . . . . irectify . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . irotate . . . . . . . . . . . . . . ipixswitch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .CONTENTS CONTENTS iisum . ipaste . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . isrot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . istereo . . . . . . . . . . . ithresh . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . itrim . . . . . . . . . . . . . . . . . . . . . . ishomog . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iscalespace . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iscolor . . . . . . . . . isvec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 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 . . . . . . . . . . . . . . . . . . . . . . . . . . inormhist . . . . . . . . . . . . . . . . . . . . . . . . . . isimilarity . . . . . ipyramid . imeshgrid . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imoments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . iread . . . . . ipad . . . . . . . . . . . . . . . . . . . . . . . . . ismooth . . . . . . . . kdgauss . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7 . . . . . . . . . . . . . isamesize . . . . . . . istretch . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imorph . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . imono . . ilabel . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . kdog . . . . . . . . . . iline . . . . . . . . . . . . isize . . . . iscale . . . . . . . . . . . . . . . . . . iwindow . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . intgimage . . . . . . . . . . . . iscalemax . . . . . . . . . . . . . . iopen . . . . . . . . . ithin . . . . . . . . . . . . . . . kcircle . . . . . . . . . . . . . . . . . . . . . . . . . R . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ivar . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ireplicate . . . . . . . . . . .

. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mkgrid . . . . . . . . . . plot poly . . . . . . . . plot2 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . numcols . . . plotp . . . . . kmeans . . . . . . . . . . . . . . . . . . . . . . . . . . . R . . . . . .CONTENTS CONTENTS klaplace . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . rotz . . . . . . plot homline . . . . . . . . . . . . . . . mkcube . . . . . . . . . . . . . . . . . . . . . . . . . . mlabel . . . . pnmﬁlt . . . . . . . . . . . . r2t . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . otsu . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 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 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . pgmﬁlt . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . rotx . . . . . . . . . . . . . . . . . . . . . . . . roty . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . niblack . . . . . . peak . . . . . . . . . . lambda2rg . . . . . . . norm2 . . . . . . . . . . plot circle . . . . . . . . . . . . . . . . . npq poly . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mpq . . . . . . . . . . . . ksobel . . . . . . . . rluminos . . . . . . . . . . . . . . . . . . . . . . . . . . maxﬁlt . . . . . . . . . . . . . . . . . . . . . . mplot . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . radgrad . . . . . . . . . . . . . . . . . . . . . . . . plot ellipse . . . . . . . . npq . ktriangle . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mtools . . . . . . . . . . . . . . . . . . . . . 8 . . . . . . . . . . . . . . . . . . medﬁlt1 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . lambda2xy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . mpq poly . . . . . . . . . . . . . . . . . . plot sphere . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . rg addticks . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . plot ellipse inv plot frame . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . numrows . . . . . . . . . . . . . . . . . . . . . . . . . . ramp . . . plot point . klog . . . . . . . . . . . . . . . . . ncc . . . . . . . . . . . . . . loadspectrum . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . ransac . . . . . . . . . . . . . . . . . . . . . . . . . . luminos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . peak2 . . . plot box . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .

. . . . . . . . . . . . se2 . . . . . . . . . . . . tr2angvec . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . stdisp . . . . . . . . . . . . . . . . . . . . . zssd . . . . . . . upq poly . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tr2rpy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . unit . transl . . . . . . . . xaxis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . vex . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 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 . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . trotz . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . skew . . . . . . . . . . . upq . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tb optparse . . . . . . trprint . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . zsad . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . trnorm . . . . . . . . . . . . . . . . . . . . ssd . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .CONTENTS CONTENTS rpy2tr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . tr2rt . . . . . troty . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . t2r . . . . . . . . . . . . . . . testpattern . . . . . . . . . . . . . . sad . . . . . . . . . . . . zncc . . . . . . . . . xycolorspace yaxis . . . . . . . . . . trotx . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . useﬁg . . . . . . . tpoly . . . . . . . . . . . . . . . . . . . . . . . tristim2cc . . . . . rt2tr . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . zcross . . . . .

tutors. lecturers and professors are paid to do. I can guarantee that I will not respond to any requests for help with assignments or homework. and you will be suitably acknowledged. That’s what you your teachers.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. and the signup process is moderated by me so allow a few days for this to happen. You need to signup in order to post. no matter how urgent or important they might be to you. You might instead like to communicate with other users via the Google Group called “Robotics Toolbox” http://groups.Chapter 1 Introduction 1.google. 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.au/group/robotics-tool-box which is a forum for discussion. I am very happy to accept contributions for inclusion in future versions of the toolbox.com.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 .

The ﬁle robot. INTRODUCTION few words about why you want to join the list so I can distinguish you from a spammer or a web-bot. HOW TO OBTAIN THE TOOLBOX CHAPTER 1. This is just a means for me to gauge interest and to help convince my bosses (and myself) that this is a worthwhile activity. Journal = {IEEE Robotics and Automation Magazine}.3.5 Use in teaching This is deﬁnitely encouraged! You are free to put the PDF manual (vision.1. Corke}. The web page requests some information from you regarding such as your country.I. type of organization and application. If you plan to distribute paper copies of the PDF manual then every copy must include the ﬁrst two pages (cover and licence). It is R auto-generated from the comments in the MATLAB code and is fully hyperlinked: to external web sites.3 How to obtain the Toolbox The Machine Vision Toolbox is freely available from the Toolbox home page at http://www.html on a server for class use. and the “See also” functions to each other.pdf is a manual that describes all functions in the Toolbox.zip). A menu-driven demonstration can be invoked by the function rtdemo. The details are @article{Corke05f. 1. Title = {Machine Vision Toolbox}.com The ﬁles are available in either gzipped tar format (.gz) or zip format (.6 Use in research If the Toolbox helps you in your endeavours then I’d appreciate you citing the Toolbox when you publish. Year = {2005}. Machine Vision Toolbox for MATLAB R 11 Copyright c Peter Corke 2011 . Month = nov. Number = {4}. Author = {P. 1. 1.pdf or the web-based documentation html/*. 1. Volume = {12}.4 MATLAB version issues The Toolbox has been tested under R2011a.petercorke. the table of content to functions.

See the ﬁle CONTRIB for details. Vincent Lepetit. The Camera Calibration Toolbox by Jean-Yves Bouguet is used unmodiﬁed.vlfeat. this release includes functions for computing image plane homographies and the fundamental matrix.the graph-based image segmentation software by Pedro Felzenszwalb. MSER..S. 12(4).6. IEEE Robotics and Automation Magazine.R. and the SURF feature detector by Dirk-Jan Kroon at U. 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.I. and there are hundreds of modules available. pp 16–25.7. Coimbra. P. November 2005. ACKNOWLEDGEMENTS CHAPTER 1. 1. Pascal Fua at the CVLab-EPFL.org is a great collection of advanced computer vision algorithms for MATLAB. 1. 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 1993.1. Corke.com/matlabcentral is a great resource for user contributed MATLAB code. RANSAC code by Peter Kovesi. Twente. which is also given in electronic form in the CITATION ﬁle.7 Acknowledgements Last. VLFeat http://www.1 Other toolboxes Matlab Central http://www. color space conversions by Pascal Getreuer. contributed by Nuno Alexandre Cid Martins of I. Machine Vision Toolbox for MATLAB R 12 Copyright c Peter Corke 2011 . the k-means and MSER algorithms by Andrea Vedaldi and Brian Fulkerson. 1994 University of British Columbia. INTRODUCTION Pages = {16-25} } or “Machine Vision Toolbox”.Functions such as SURF.mathworks. pose estimation by Francesco Moreno-Noguer. but not least.

Chapter 2 Functions and classes Camera Camera superclass An abstract superclass for Toolbox camera classes. 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 .

used by all subclasses. Machine Vision Toolbox for MATLAB R 14 Copyright c Peter Corke 2011 . The ‘image’ option paints the speciﬁed image onto the image plane and allows points and lines to be overlaid. IM ‘resolution’. N ‘sensor’. N ‘image’. 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. Camera.CHAPTER 2. • The object can create a window to display the Camera image plane. T ‘color’. C = Camera(options) creates a default (abstract) camera with null parameters. this window is protected and can only be accessed by the plot methods of this object.Camera Create camera object Constructor for abstact Camera class. • Camera objects can be used in vectors and arrays • This is an abstract class and must be subclassed and a project() method deﬁned.8]) Notes • Normally the class plots points and lines into a set of axes that represent the image plane. P ‘pixel’. 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. Options ‘name’. S ‘noise’. S ‘centre’. SIGMA ‘pose’.

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

C. Camera.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.CHAPTER 2. Camera.ishold Return image plane hold status H = C.line Plot homogeneous lines on image plane C.ﬁgure Return ﬁgure handle H = C.u + b. See also Camera. 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.ﬁgure() is the handle of the ﬁgure that contains the camera’s image plane graphics.hold(H) hold mode is set on if H is true (or > 0).hold() sets “hold on” for the camera’s image plane.hold Control hold on image plane graphics C. and off if H is false (or 0).char Camera. Machine Vision Toolbox for MATLAB R 16 Copyright c Peter Corke 2011 .ishold() returns true (1) if the camera’s image plane is in hold mode. otherwise false (0).v + c = 0. Camera.

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

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

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

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.C() is the 3×4 camera matrix. CentralCamera.CHAPTER 2.C Camera matrix C = C. also known as the camera calibration or projection matrix. Machine Vision Toolbox for MATLAB R 21 Copyright c Peter Corke 2011 . • Camera objects can be used in vectors and arrays See also Camera 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.CentralCamera Create central projection camera object C = CentralCamera() creates a central projection camera with canonic parameters: f=1 and name=’canonic’.

S. FUNCTIONS AND CLASSES Options ‘name’.8]) See also Camera.Kosecka.Soatto.E Essential matrix E = C.and v-axes parallel to x. CatadioptricCamera. Springer. S. D ‘default’ ‘image’. D ‘distortion-bouguet’. N ‘sensor’.and y-axes respectively. The ﬁrst view is from the current camera pose C. P ‘pixel’. E = C. 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. ﬁsheyecamera. 10um pixels. N ‘focal’.invE Machine Vision Toolbox for MATLAB R 22 Copyright c Peter Corke 2011 .Ma. E = C. p.F(F) is the essential matrix based on the fundamental matrix F (3 × 3) and the intrinsic parameters of camera C.F. optical axis is z-axis. IM ‘resolution’. 2003. S ‘noise’.E(T) is the essential matrix relating two camera views. J. SphericalCamera CentralCamera. S ‘centre’. camera at origin.177 See also CentralCamera. f=8mm.CHAPTER 2. T ‘color’. CentralCamera. “An invitation to 3D”.Sastry.T and the second is a relative motion represented by the homogeneous transformation T. 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.F(C2) is the essential matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view). SIGMA ‘pose’. F ‘distortion’. u. Reference Y.

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

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

“Multiview Geometry”. p116. “An invitation to 3D”. Chap 9. J.Soatto. 259 Y.E CentralCamera. camera motion as a homogeneous transform matrix (4 × 4). 2003. 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 2.3 Machine Vision Toolbox for MATLAB R 25 Copyright c Peter Corke 2011 . Springer. section 5. In practice there are multiple solutions and s is a vector of structures with elements: • T. s. p120122 Notes • The transformation is from view 1 to view 2.Ma.Ma. s.invE(E. translation not to scale • n. 2003. Springer. p) as above but only solutions in which the world point p is visible are returned.Soatto.invH(H) decomposes the homography H (3 × 3) into the camera motion and the normal to the plane.Sastry. See also CentralCamera. s. FUNCTIONS AND CLASSES s = C. Reference Hartley & Zisserman. s.invH Decompose homography matrix s = C. J.Sastry.Kosecka. “An invitation to 3D”. Reference Y. p.Kosecka.CHAPTER 2.

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

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

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

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

Int. Journal on Computer Vision. SurfPointFeature Machine Vision Toolbox for MATLAB R 30 Copyright c Peter Corke 2011 . You can download a SIFT implementation which this class can utilize. See README.Lowe. PointFeature. vol. Notes • SiftCornerFeature is a reference object. ScalePointFeature. pp. References “Distinctive image features from scale-invariant keypoints”.u is a 2×N matrix with each column the corresponding u coordinate. • SiftCornerFeature objects can be used in vectors and arrays • The SIFT algorithm is patented and not distributed with this toolbox.91-110.60.SIFT. 2004. 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. Nov. See also isift. If F is a vector (N ×1) of SiftCornerFeature objects then F. D.CHAPTER 2.

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

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

• SphericalCamera objects can be used in vectors and arrays See also Camera Machine Vision Toolbox for MATLAB R 33 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.CHAPTER 2.

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

Two windows are shown and animated: 1.sph2 Implement spherical IBVS for point features results = sph(T) results = sph(T. image plane size and desired feature locations.CHAPTER 2. showing the target points and the camera The results structure contains time-history information about the image plane. FUNCTIONS AND CLASSES SphericalCamera. showing the desired view (*) and the current view (o) Machine Vision Toolbox for MATLAB R 35 Copyright c Peter Corke 2011 . params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. defaults in parentheses: target size . can be scalar or diagonal 6 × 6 matrix (0.center of the target in world coords (0.2) niter eterm lambda ci depth .01) .camera intrinsic structure (camparam) .sph Implement spherical IBVS for point features results = sph(T) results = sph(T.5) target center . params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera.gain. of 4-vector. Two windows are shown and animated: 1. scalar for If null take actual value all points. camera pose. The camera/robot is initially at pose T and is driven to the orgin. The params structure can be used to override simulation defaults by providing elements. The camera/robot is initially at pose T and is driven to the orgin. error norm. showing the desired view (*) and the current view (o) 2. Jacobian condition number.depth of points to use for Jacobian. The external view. The camera view.the side length of the target in world units (0.a stopping criteria on feature error norm (0) .the number of iterations to run the simulation (500) . The camera view. error.0.

visjac l.01) . See also CentralCamera.depth of points to use for Jacobian. May 3-7 2010. (Anchorage).gain. z) is the image Jacobian (2N × 6) for the image plane points pt (2 × N ) described by phi (longitude) and theta (colatitude). defaults in parentheses: target size .visjac e Machine Vision Toolbox for MATLAB R 36 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES 2. can be scalar or diagonal 6 × 6 matrix (0. I. The params structure can be used to override simulation defaults by providing elements. showing the target points and the camera The results structure contains time-history information about the image plane. of 4-vector. error.a stopping criteria on feature error norm (0) . Robotics and Automation. for all points. P. The external view.3) niter eterm lambda ci depth . Reference “Spherical image-based visual servo and structure estimation”. pp.CHAPTER 2.camera intrinsic structure (camparam) .0. 5550-5555.5) target center . CentralCamera. IEEE Int. or a vector (N × 1) for each point.center of the target in world coords (0. image plane size and desired feature locations. Conf. The depth of the points from the camera is given by z which is a scalar. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera. CentralCamera.visjac p(pt. camera pose. scalar for If null take actual value all points. Corke.visjac p polar.visjac p Visual motion Jacobian for point feature J = C.the number of iterations to run the simulation (500) . error norm. The Jacobian gives the image-plane velocity in terms of camera spatial velocity. Jacobian condition number.the side length of the target in world units (0. in Proc.

Tinne Tuytelaars. If F is a vector (N × 1) of SurfCornerFeature objects then F. Luc Van Gool. No. Notes • SurfCornerFeature is a reference object. “SURF: Speeded Up Robust Features”. Computer Vision and Image Understanding (CVIU). pp. • SurfCornerFeature objects can be used in vectors and arrays Reference Herbert Bay. FUNCTIONS AND CLASSES SurfPointFeature SURF point corner feature object A subclass of PointFeature for SURF features. Vol. 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. 110. 2008 Machine Vision Toolbox for MATLAB R 37 Copyright c Peter Corke 2011 . 346–359. 3.CHAPTER 2.u is a 2 × N matrix with each column the corresponding u coordinate. Andreas Ess.

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

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

Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’.com) web camera.axis. 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.com). Video AxisWebCamera. G ‘scale’. otherwise the result is not predictable.axis.AxisWebCamera Axis web camera constructor a = AxisWebCamera(url. 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. • The speciﬁed ‘resolution’ must match one that the camera is capable of.CHAPTER 2. 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. options) is an AxisWebCamera object that acquires images from an Axis Communications (www. Machine Vision Toolbox for MATLAB R 40 Copyright c Peter Corke 2011 . S ‘resolution’.

AxisWebCamera.display AxisWebCamera.close() closes the connection to the web camera.grab() is an image acquired from the web camera. and this function will return the most recently captured image held in the camera.char Convert to string 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’. Notes • Some web cameras have a ﬁxed picture taking interval.CHAPTER 2. FUNCTIONS AND CLASSES AxisWebCamera. See also AxisWebCamera.close Close the image source A.char() is a string representing the state of the camera object in human readable form. Machine Vision Toolbox for MATLAB R 41 Copyright c Peter Corke 2011 .grab Acquire image from the camera im = A.

Oct.BagOfWords Create a BagOfWords object b = BagOfWords(f. pp.CHAPTER 2. The features are sorted into k clusters and each cluster is termed a visual word. on Computer Vision.Sivic and A. “Video Google: a text retrieval approach to object matching in videos”.1470-1477. Notes • Uses the MEX function vl kmeans to perform clustering (vlfeat. 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.Zisserman. 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. in Proc. Machine Vision Toolbox for MATLAB R 42 Copyright c Peter Corke 2011 .org). f can also be a cell array. 2003. Ninth IEEE Int. b = BagOfWords(f. k) is a new bag of words created from the feature vector f and with k words. See also PointFeature BagOfWords. Conf. as produced by ISURF() for an image sequence.

isurf BagOfWords. BagOfWords. BagOfWords.contains Find images containing word k = B.exemplars display exemplars of words B.contains(w) is a vector of the indices of images in the sequence that contain one or more instances of the word w.char() is a compact string representation of a bag of words. See also 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.display() displays the parameters of the bag in a compact human readable form.char Convert to string s = B.char BagOfWords. options) displays examples of the support regions of the words speciﬁed by the vector w.CHAPTER 2. images. FUNCTIONS AND CLASSES See also PointFeature.display Display value B.exemplars(w. The examples are displayed as a table of thumbR Machine Vision Toolbox for MATLAB 43 Copyright c Peter Corke 2011 .

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

subclass of Camera. 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. 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.wordvector(J) is the word frequency vector for the J’th image in the bag.CHAPTER 2. FUNCTIONS AND CLASSES BagOfWords.wordvector Word frequency vector wf = B.

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. • Camera objects can be used in vectors and arrays See also CentralCamera.CHAPTER 2. Machine Vision Toolbox for MATLAB R 46 Copyright c Peter Corke 2011 . Camera CatadioptricCamera.CatadioptricCamera Create central projection camera object C = CatadioptricCamera() creates a central projection camera with canonic parameters: f=1 and name=’canonic’. C = CatadioptricCamera(options) as above but with speciﬁed parameters.

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

SiftPointFeature Machine Vision Toolbox for MATLAB R 48 Copyright c Peter Corke 2011 . Note • FeatureMatch is a reference object. SurfPointFeature and SiftPointFeature. SurfPointFeature.p1 is a 2 × N matrix with each column the corresponding view 1 point coordinate.CHAPTER 2. See also PointFeature. If F is a vector (N × 1) of FeatureMatch objects then F. FUNCTIONS AND CLASSES FeatureMatch Feature correspondence object This class represents the correspondence between two PointFeature objects. such as ScalePointFeature. 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. A vector of FeatureMatch objects can represent the correspondence between sets of points. • FeatureMatch objects can be used in vectors and arrays • Operates with all objects derived from PointFeature.

Notes • Only the coordinates of the PointFeature are kept. 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.char() is a compact string representation of the match object. SiftPointFeature FeatureMatch. m = FeatureMatch(f1.CHAPTER 2. FUNCTIONS AND CLASSES FeatureMatch.display() displays a compact human-readable representation of the feature pair. If M is a vector then the elements are printed one per line.FeatureMatch Create a new FeatureMatch object m = FeatureMatch(f1. FeatureMatch. f2) as above but the strength is set to NaN.char Machine Vision Toolbox for MATLAB R 49 Copyright c Peter Corke 2011 . See also PointFeature. s) is a new FeatureMatch object describing a correspondence between point features f1 and f2 with a strength of s. one per element. See also FeatureMatch.display Display value M.char Convert to string s = M. f2. If M is a vector then the string has multiple lines. SurfPointFeature.

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

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

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

subset Subset of matches m2 = M. The image is not inverted. FishEyeCamera Fish eye camera class A concrete class a ﬁsheye lense projection camera. 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 . that is.CHAPTER 2. v. The camera coordinate system is: 0------------> u. X | | | + (principal point) | | Z-axis is into the page. FUNCTIONS AND CLASSES FeatureMatch. the focal point is at z=0 and the image plane is at z=f.subset(n) is a FeatureMatch vector with no more than n elements sampled uniformly from M. Y This camera model assumes central projection.

N ‘sensor’. T Name of camera Default camera parameters: 1024 × 1024. 10um pixels. Fisheye model: ‘equiangular’ (default). 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 . K ‘resolution’.and y. S ‘noise’. M ‘k’. ‘stereographic’ Parameter for the projection model Image plane resolution: N × N or N=[W H].and v-axes are parallel to x. S ‘centre’. Image sensor size [metres] (2 × 1) Principal point (2 × 1) Pixel size: S × S or S=[W H]. P ‘pixel’. f=8mm. SIGMA ‘pose’. • Camera objects can be used in vectors and arrays See also Camera FishEyeCamera.FishEyeCamera Create ﬁsheyecamera object C = FishEyeCamera() creates a ﬁsheye camera with canonic parameters: f=1 and name=’canonic’.CHAPTER 2. camera at origin. Options ‘name’. 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. ‘equisolid’. ‘sine’. optical axis is z-axis. N ‘default’ ‘projection’.axes respectively. u. C = FishEyeCamera(options) as above but with speciﬁed parameters.

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

Hough Create Hough transform object ht = Hough(E. Offset is in the range -rho max to rho max where rho max=max(W. A horizontal line has theta = 0.0) and the line. By default the vote is incremented by Machine Vision Toolbox for MATLAB R 56 Copyright c Peter Corke 2011 . Theta spans the range -pi/2 to pi/2 in Ntheta steps.CHAPTER 2. For every pixel in the edge image E (H ×W ) greater than a threshold the corresponding elements of the accumulator are incremented. with columns corresponding to theta and rows corresponding to offset (d). and d is the perpendicular distance between (0. a vertical line has theta = pi/2 or -pi/2. FUNCTIONS AND CLASSES where theta is the angle the line makes to horizontal axis. The voting array is 2-dimensional. 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.H). See also LineFeature Hough. options) is the Hough transform of the edge image E.

Nrho].display() displays a compact human-readable string representation of the Hough transform parameters. if N is scalar set Nrho=Ntheta=N. Set ht.1). Options ‘equal’ ‘interpwidth’. N All edge pixels have equal weight.edgeThresh. W ‘houghthresh’.houghThresh (default 0.5) Set ht.edgeThresh (default 0. else N = [Ntheta. The threshold is determined from the maximum edge strength value x ht. W ‘nbins’. T ‘edgethresh’. Hough.CHAPTER 2.char() is a compact string representation of the Hough transform parameters.char Machine Vision Toolbox for MATLAB R 57 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES the edge strength but votes can be made equal with the option ‘equal’. 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. See also Hough.suppress (default 0) Set number of bins.char Convert to string s = HT. Default 400 × 401. Hough.display Display value HT. otherwise the edge pixel value is the vote strength Interpolation width (default 3) Set ht. T ‘suppress’.

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

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.CHAPTER 2.rho is an N × 1 vector of the rho element of each feature. FUNCTIONS AND CLASSES See also colormap. RegionFeature. • LineFeature objects can be used in vectors and arrays See also Hough. hot LineFeature Line feature class This class represents a line feature. Note • LineFeature is a reference object.

LineFeature Create a line feature object L = LineFeature() is a line feature object with null parameters. L = LineFeature(l2) is a deep copy of the line feature l2. LENGTH is undeﬁned. L = LineFeature(rho.char Convert to string s = L. one per element. If L is a vector then the string has multiple lines.char Machine Vision Toolbox for MATLAB R 60 Copyright c Peter Corke 2011 .display Display value L. 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. strength) is a line feature object with the speciﬁed properties. LineFeature. If L is a vector then the elements are printed one per line. L = LineFeature(rho. theta. theta. See also LineFeature. length) is a line feature object with the speciﬁed properties. LineFeature.display() displays a compact human-readable representation of the feature.char() is a compact string representation of the line feature.CHAPTER 2. strength. FUNCTIONS AND CLASSES LineFeature.

seglength(edge.seglength(edge) as above but the maximum allowable gap is 5 pixels. gap) is a copy of the line feature object with the property length updated to the length of the line (pixels). This method examines the edge pixels in the original image and determines the longest stretch of non-zero pixels along the line. Notes • If L is a vector then each element is plotted. LineFeature. less than gap pixels are tolerated. FUNCTIONS AND CLASSES LineFeature.plot() overlay the line on current plot.points Return points on line segments p = L. 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. See also icanny LineFeature.CHAPTER 2. l2 = L.plot Plot line L. Small gaps.plot(ls) as above but the optional line style arguments ls are passed to plot.points(edge) is the set of points that lie along the line in the edge image edge are determined. l2 = L. L.

Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’.axis.Movie Image source constructor m = Movie(ﬁle. options) is an Movie object that returns frames from the movie ﬁle ﬁle.close() closes the connection to the movie.char() is a string representing the state of the movie object in human readable form. Machine Vision Toolbox for MATLAB R 62 Copyright c Peter Corke 2011 . G ‘scale’.close Close the image source M.char Convert to string M. Movie. 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.CHAPTER 2.com). Movie. S ‘skip’. 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.

vid • edges are represented by integer ids. S ‘frame’. FUNCTIONS AND CLASSES Movie. 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. undirected graph create an n-d. planar.grab(options) as above but allows the next frame to be speciﬁed. Options ‘skip’. 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 . F Skip frames.grab() acquires the next image from the movie im = M. eid Graph connectivity is maintained by a labeling algorithm and this is updated every time an edge is added. PGraph Simple graph class g = PGraph() g = PGraph(n) create a 2D.CHAPTER 2.grab Acquire next frame from movie im = M.

next(v) g.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.component(v) g.connectivity() 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. v2) distance between v1 and v2 as the crow ﬂies g.add node(coord) g. v2) g.closest(coord) return vertex closest to coord g.path(v) set goal vertex.clear() add vertex.coord(v) g.plot() g. 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(). FUNCTIONS AND CLASSES Methods Constructing the graph g.distance(v1.add edge(v1.add node(coord. return eid remove all nodes and edges from the graph Information from graph g.CHAPTER 2. return vid add vertex and edge to v.edges(e) g.neighbours(v) g. return vid add edge from v1 to v2.n number of nodes Machine Vision Toolbox for MATLAB R 64 Copyright c Peter Corke 2011 . Object properties (read/write) g.goal(v) g.cost(e) g.

FUNCTIONS AND CLASSES PGraph. Machine Vision Toolbox for MATLAB R 65 Copyright c Peter Corke 2011 .add node(x. and returns the edge id E. C) add an edge between nodes with id v1 and v2 with cost C.add edge Add an edge to the graph E = G. C) adds a node with coordinate x and connected to node v by an edge with cost C. PGraph. and returns the node id v.add edge(v1.PGraph Graph class constructor g = PGraph(d. E = G.add edge(v1.CHAPTER 2. v2) add an edge between nodes with id v1 and v2. v = G. v = G.add node Add a node to the graph v = G. 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.add node(x) adds a node with coordinate x. v. PGraph.add node(x. where x is D × 1. v) adds a node with coordinate x and connected to node v by an edge. Options ‘distance’. v2. options) returns a graph object embedded in d dimensions.

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

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

PointFeature.display Display value F.u is a 2 × N matrix with each column the corresponding point coordinate. If F is a vector (N × 1) of PointFeature objects then F.PointFeature Create a point feature object f = PointFeature() is a point feature object with null parameters. 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.char() is a compact string representation of the point feature.display() displays a compact human-readable representation of the feature. v. SurfPointFeature. If F is a vector then the string has multiple lines. Machine Vision Toolbox for MATLAB R 71 Copyright c Peter Corke 2011 .char Convert to string s = F.CHAPTER 2. SiftPointFeature PointFeature. See also ScalePointFeature. v) is a point feature object with speciﬁed coordinates. f = PointFeature(u. PointFeature. f = PointFeature(u. strength) as above but with speciﬁed strength. one per element. If F is a vector then the elements are printed one per line. 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.

ncc Feature descriptor similarity s = F.match(f2.distance Distance between feature descriptors d = F.ncc(f1) is the similarty between feature descriptors which is a scalar in the interval -1 to 1. [m.match(f2.char PointFeature. the norm of the Euclidean distance. options) as above but returns a correspodence matrix where each row contains the indices of corresponding features in F and f2 respectively. PointFeature. If F is a vector then d is a vector whose elements are the distance between the corresponding element of F and f1.match Match point features m = F. options) is a vector of FeatureMatch objects that describe candidate matches between the two vectors of point features F and f2. FUNCTIONS AND CLASSES See also PointFeature.CHAPTER 2. where 1 is perfect match. Machine Vision Toolbox for MATLAB R 72 Copyright c Peter Corke 2011 . T ‘median’ match threshold (default 0.05) Threshold at the median distance See also FeatureMatch PointFeature.distance(f1) is the distance between feature descriptors. If F is a vector then D is a vector whose elements are the distance between the corresponding element of F and f1.C] = F. Options ‘thresh’.

one per column Bounding box [minx maxx.CHAPTER 2.plot Plot feature F.plot() overlay a marker at the feature position. 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 . 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.General polygon class p = Polygon(vertices). Polygon .plot(ls) as above but the optional line style arguments ls are passed to plot. FUNCTIONS AND CLASSES PointFeature. F. If F is a vector then each element is plotted.

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

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

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

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

clockwise “outer boundary” and one or more clock-wise “inner boundaries” around “holes”. deﬁned by a point on the ray and a direction unit-vector. 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.Ray3D Ray constructor R = Ray3D(p0. d) is a new Ray3D object deﬁned by a point on the ray p0 and a direction vector d. FUNCTIONS AND CLASSES • If the result P is not simply connected (such as a polygon with a “hole”) the resulting contour consist of counter.CHAPTER 2. 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. Ray3D Ray in 3D space This object represents a ray in 3D space.

closest(p) as above but also returns the distance E between x and p. If R is a vector then then x has multiple columns.display() displays a compact human-readable representation of the Ray3D’s value. [x.intersect Intersetion of ray with line or plane x = R.closest(p) is the point on the ray R closest to the point p. 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. Machine Vision Toolbox for MATLAB R 79 Copyright c Peter Corke 2011 . one per element.char Convert to string s = R. If R is a vector then the string has multiple lines. Ray3D.intersect(r2) is the point on R that is closest to the ray r2.char() is a compact string representation of the Ray3D’s value. FUNCTIONS AND CLASSES Ray3D.E] = R.display Display value R.E] = R.CHAPTER 2.intersect(r2) as above but also returns the closest distance between the rays.char Ray3D. If R is a vector then the elements are printed one per line. See also Ray3D. [x. Ray3D. corresponding to the intersection of R(i) with r2.closest Closest distance between point and ray x = R.

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. FUNCTIONS AND CLASSES x = R.intersect(p) returns the point of intersection between the ray R and the plane p=(a. vertical coordinate bounding box.0) 1 for a circle. RegionFeature Region feature class This class represents a region feature. If R is a vector then x has multiple columns. 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 . minimum vertical coordinate bounding box.b. maximum horizontal coordinate bounding box.c. 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. corresponding to the intersection of R(i) with p. horizontal coordinate centroid. minimum horizontal coordinate bounding box.CHAPTER 2.d) where aX + bY + cZ + d = 0.

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

plot(ls) as above but the optional line style arguments ls are passed to plot.display Display value R. If R is a vector then the elements are printed one per line. Notes • If R is a vector then each element is plotted. If R is a vector then each element is plotted. RegionFeature.and xmarkers. R. R. See also RegionFeature. Machine Vision Toolbox for MATLAB R 82 Copyright c Peter Corke 2011 .plot boundary plot boundary R.plot() overlay the centroid on current plot. FUNCTIONS AND CLASSES RegionFeature.plot boundary(ls) as above but the optional line style arguments ls are passed to plot. It is indicated with overlaid o.CHAPTER 2.display() is a compact string representation of the region feature.plot boundary() overlay perimeter points on current plot. 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.char RegionFeature.plot Plot centroid R.

R.plot ellipse() overlay the the equivalent ellipse of the region on current plot. RegionFeature. FUNCTIONS AND CLASSES See also boundmatch RegionFeature.plot box() overlay the the bounding box of the region on current 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 .plot ellipse Plot equivalent ellipse R. 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. R. ScalePointFeature ScalePointCorner feature object A subclass of PointFeature for features with scale.plot box Plot bounding box R.plot ellipse(ls) as above but the optional line style arguments ls are passed to plot.CHAPTER 2.

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

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

tracklengths Length of all tracks T.char Convert to string s = T. FUNCTIONS AND CLASSES See also PointFeature Tracker.display Display value T. Tracker.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.char Tracker. Tracker. Machine Vision Toolbox for MATLAB R 86 Copyright c Peter Corke 2011 .char() is a compact string representation of the Tracker parameters and status.plot Show feature trajectories T.CHAPTER 2.plot() overlays the tracks of all features on the current plot.tracklengths() is a vector containing the length of every track. See also Tracker.

Video Video camera constructor v = Video(camera. AxisWebCamera. otherwise the result is not predictable. options) is a Video object that acquires images from the local video camera speciﬁed by the string camera. G ‘scale’. Machine Vision Toolbox for MATLAB R 87 Copyright c Peter Corke 2011 . Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’. 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. and their characteristics is displayed. 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. If camera is ‘?’ a list of available cameras. Movie Video.CHAPTER 2. • The speciﬁed ‘resolution’ must match one that the camera is capable of. S ‘resolution’. FUNCTIONS AND CLASSES Video Class to read from local video camera A concrete subclass of ImageSource that acquires images from a local camera. Obtain an image of size S=[W H].

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 .close Close the image source V. Video. FUNCTIONS AND CLASSES Video.char Convert to string V.close() closes the connection to the camera.CHAPTER 2. about Compact display of variable type about(x) displays a compact line that describes the class and dimensions of x.grab() acquires an image from the camera.grab Acquire image from the camera im = V. Video. Notes • the function will block until the next frame is acquired.char() is a string representing the state of the camera object in human readable form.

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

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

CHAPTER 2.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.E] = camcald(d) as above but E is the maximum residual error after back substitution [pixels]. See also CentralCamera ccdresponse CCD spectral response R = ccdresponse(lambda) is the spectral response of a typical silicon imaging sensor at the wavelength lambda. Reference An ancient Fairchild data book for a sensor with no IR ﬁlter ﬁtted. Notes: • This method cannot handle lense distortion.V] is the corresponding image plane coordinate. Machine Vision Toolbox for MATLAB R 91 Copyright c Peter Corke 2011 . 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. 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. The response is normalized in the range 0 to 1.Y.

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

rgb = cmfrgb(lambda.d2] = closest(a. If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda.16).3) of Wyszecki & Stiles (1982). 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]. while Table I(5. unlike the CIE 2 deg functions (which were reconstructed from chromaticity data). Notes • Data from http://cvrl.5. The data are referred to as pilot data.5. Notes • Is a MEX ﬁle. 335 of Table 1(5. but probably represent the best estimate of the 2 deg CMFs.3) of Wyszecki & Stiles (1982). See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. since.) • These CMFs differ slightly from those of Stiles & Burch (1955).32). the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645. rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m].ioo.5. FUNCTIONS AND CLASSES [k.ac.CHAPTER 2. (Table 1(5.44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 . As noted in footnote a on p. b) as above but also returns the distance to the second closest point.5. they were measured directly.ucl.d1.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers.3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps. 19000 (526. • From Table I(5. and 22500 (444.

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

Notes • The output image could be thresholded to determine color similarity. • Note that Euclidean distance in the rg-chromaticity space does not correspond well with human perception of color differences. colordistance Colorspace distance d = colordistance(im.g] to every pixel in the color image 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 .CHAPTER 2. rg) is the Euclidean distance on the rg-chromaticity plane from coordinate rg=[r. 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. See also colorspace Machine Vision Toolbox for MATLAB R 95 Copyright c Peter Corke 2011 .

See also imono. FUNCTIONS AND CLASSES colorize Colorize a greyscale image out = colorize(im. out = colorize(im. and returns a per-pixel logical result. [0 0 1]) Display image with NaN values shown in red out = colorize(im. k. eg. icolor. ipixswitch colorkmeans Color image segmentation by clustering L = colorkmeans(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. @isnan.C] = colorkmeans(im. 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. func.B). Examples Display image with values < 100 in blue out = colorize(im. A k-means clustering of the chromaticity of all input pixels is performed. mask.G. [1 0 0]) Notes • With no output arguments the image is displayed. The color is speciﬁed as a 3-vector (R. options) is a segmentation of the color image im into k classes.CHAPTER 2. im<100. @isnan. R Machine Vision Toolbox for MATLAB 96 Copyright c Peter Corke 2011 . 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. A k-means clustering of the chromaticity of all input pixels is performed. color) as above but a the mask is the return value of the function handle func applied to the image im. [L.

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

and R Machine Vision Toolbox for MATLAB 98 Copyright c Peter Corke 2011 . [o1. As MATLAB’s native datatype. Input and output images have 3 planes. im) converts the image im to a different color space according to the string s which speciﬁes the source and destination color spaces. FUNCTIONS AND CLASSES • Based on the standard X11 color database rgb. • Color space names are case insensitive. • Tristimulus values are in the range 0 to 1 colorspace Color space conversion of image out = colorspace(s. colorspace(s. double data is the natural choice.CHAPTER 2. it can be omitted.o2. s = ‘src->dest’. s = ‘dest<-src’. im) as above but speciﬁes separate output channels or planes.o3] = colorspace(s.i3) as above but speciﬁes separate input channels. 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. For example ‘yuv<’ is short for ‘yuv<-rgb’.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. i1. • When R’G’B’ is the source or destination. or alternatively.txt.i2. and uint8 data with integer-valued intensities from 0 to 255. • MATLAB uses two standard data formats for R’G’B’: double data with intensities in the range 0 to 1.709 gamma-corrected) Luma (ITU-R BT.

out will also have size M × 3.100). Notes • This fully vectorized (VERY FAST!) • It computes the Euclidean distance between two vectors by: ||A-B|| = sqrt ( ||A||ˆ2 + ||B||ˆ2 . Example A = rand(400.B). FUNCTIONS AND CLASSES the R’G’B’ format used by colorspace. like a colormap. • If im is an M × 3 array.b) is the Euclidean distances between L-dimensional points described by the matrices a (L × M ) and b (L × N ) respectively. some functions also operate with uint8 R’G’B’. 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 . However.200). for memory and computational performance. Given uint8 R’G’B’ color data.2*A. distance Euclidean distances between sets of points d = distance(a.J) is the distance between points a(I) and d(J). Author Pascal Getreuer 2005-2006 diff2 diff3(v) compute 2-point difference for each point in the vector v.CHAPTER 2. B = rand(400. d = distance(A. The distance d is M × N and element d(I.

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

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

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

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

au/. 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. • 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 .CHAPTER 2. Notes • The points must be corresponding. invhomog. http://www. The University of Western Australia. School of Computer Science & Software Engineering. no outlier rejection is performed. FUNCTIONS AND CLASSES homography Estimate homography H = homography(p1. • The points must be projections of points lying on a world plane • Contains a RANSAC driver.edu. which means it can be passed to ransac(). fmatrix homtrans Apply a homogeneous transformation p2 = homtrans(T.uwa.csse. Author Based on homography code by Peter Kovesi. See also ransac. p) applies homogeneous transformation T to the points stored columnwise in p.

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

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

YMIN YMAX]. iharris.CHAPTER 2. N ‘only’. 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 ). M ‘npoints’. box = ibbox(im) is the minimal bounding box that contains the non-zero pixels in the image im. FUNCTIONS AND CLASSES Options ‘fps’. Machine Vision Toolbox for MATLAB 107 R Copyright c Peter Corke 2011 . F ‘loop’ ‘movie’. The bounding box is a 2 × 2 matrix [XMIN XMAX. isurf. 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. options) is a vector of RegionFeature objects that describe each connected region in the image im. iblobs features f = iblobs(im.

default 1.CHAPTER 2. C set connectivity.S2] accept only blobs with shape in interval S1 to S2 ‘touch’ ignore blobs that touch the edge (default accept) ‘class’. [S1. 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. The edges within im are marked by non-zero values in E.0 ‘connect’. less for other shapes a structure containing moments of order 0 to 2 See also RegionFeature. 4 (default) or 8 ‘greyscale’ compute greyscale moments 0 (default) or 1 ‘boundary’ compute boundary (default off) ‘area’. FUNCTIONS AND CLASSES Options ‘aspect’. options) returns an edge image using the Canny edge detector. and larger values correspond to stronger edges. maximum horizontal coordinate bounding box. horizontal coordinate centroid. minimum horizontal coordinate bounding box. Machine Vision Toolbox for MATLAB 108 R Copyright c Peter Corke 2011 . ilabel. minimum vertical coordinate bounding box. [A1. imoments icanny edge detection E = icanny(im.0) 1 for a circle.A2] accept only blobs with area in interval A1 to A2 ‘shape’. 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. vertical coordinate bounding box. A set pixel aspect ratio.

out = iclose(im. n) as above but the structuring element se is applied n times. 1996-7. Tel Aviv University. S ‘th0’. See also iopen. FUNCTIONS AND CLASSES Options ‘sd’.1 x strongest edge) set the upper hysteresis threshold (default 0.5 x strongest edge) Author Oded Comay. T set the standard deviation for smoothing (default 1) set the lower hysteresis threshold (default 0. se) is the image im after morphological closing with the structuring element se. kdgauss iclose closing out = iclose(im. See also isobel. the effective structuing element is the Minkowski sum of the structuring element with itself n times. Notes • Cheaper to apply a smaller structuring element multiple times than one large one. T ‘th1’.CHAPTER 2. se. imorph Machine Vision Toolbox for MATLAB 109 R Copyright c Peter Corke 2011 . This is an dilation followed by erosion. that is n dilations followed by n erosions.

D ‘bgval’. Options ‘dir’. colorize.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. ipixswitch iconcat Concatenate images C = iconcat(im. The images do not have to be of the same size. [C.CHAPTER 2. [0 1 1]). and smaller images are surrounded by background pixels which can be speciﬁed. 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. C = icolor(im. Create an aqua tinted version of the greyscale image c = icolor(im. value of unset background pixels Machine Vision Toolbox for MATLAB 110 R Copyright c Peter Corke 2011 . See also imono.u] = iconcat(im.options) as above but displays the concatenated images using idisp.options) concatenates images from the cell array im. iconcat(im. B direction of concatenation: ‘horizontal’ (default) or ‘vertical’. Examples Create a color image that looks the same as the greyscale image c = icolor(im).

If the larger image is color (has multiple planes) the kernel is applied to each plane. and contains only valid pixels Notes • This function is a convenience wrapper for the builtin function CONV2. resulting in an output image with the same number of planes. ‘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 ‘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.CHAPTER 2. See also conv2 Machine Vision Toolbox for MATLAB 111 R Copyright c Peter Corke 2011 . The smaller image is taken as the kernel and convolved with the larger image. options) convolves im1 with im2. FUNCTIONS AND CLASSES Notes • Works for color or greyscale images • Direction can be abbreviated to ﬁrst character. im2.

If im is an image sequence a cell array of PointFeature vectors is returned. D ‘k’. D ‘sigma’. specify that im is a color image not a sequence Notes • Corners are processed in order from strongest to weakest. CT ‘edgegap’. ‘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. The PointFeature object has many properties including: u v strength descriptor horizontal coordinate vertical coordinate corner strength corner descriptor (vector) Options ‘cmin’. • 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. R ‘nfeat’. 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). The vector has zero mean and unit norm. FUNCTIONS AND CLASSES icorner Corner detector f = icorner(im. This is a non-scale space detector and by default the Harris method is used.CHAPTER 2. S ‘deriv’. options) is a vector of PointFeature objects describing detected corner features. E ‘suppress’. CM ‘cminthresh’. N ‘detector’. • 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 . K ‘patch’.

p2. J. where * denotes squared and smoothed.G. Machine Vision Toolbox for MATLAB 113 R Copyright c Peter Corke 2011 . Options ‘dplot’. pp. May 1988. [T. show the points p1 and p2 at each iteration. Image and Vision Computing. Computer Vision and Pattern Recognition. T ‘maxiter’.001) eliminate correspondences more than T x the median distance at each iteration. with a delay of 0. limit the change in rotation at each step to T (default 0. vol. Harris and M. 593-593. • The descriptor is a vector of ﬂoat types to save space References • “A combined corner and edge detector”.121-128.d] = icp(p1. Shi and C. C. options) is the homogeneous transformation that best transforms the set of points p2 to p1 using the iterative closest point algorithm. options) as above but also returns the norm of the error between the transformed point set p2 and p1. • “Good features to track”.05 rad) stop after N iterations (default 100) stop when the relative change in error norm is less than T (default 0.J. 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.6..CHAPTER 2. 1994.Noble. Stephens. • The default descriptor is a vector [Ix* Iy* Ixy*] which are the unique elements of the structure tensor. d ‘plot’ ‘maxtheta’. Tomasi. 1988. • “Finding corners”. IEEE Computer Society. Fourth Alvey Vision Conf. N ‘mindelta’.5 [sec]. pp 147-151. p2. isurf icp Point cloud alignment T = icp(p1. See also PointFeature. Proc. pp. Manchester. T ‘distthresh’. Proc. with a delay of d [sec]. T show the points p1 and p2 at each iteration. J.

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

and y-axes respectively. highlights ﬁne structure color map: greyscale unsigned. negative is red. If the image is zoomed. F ‘square’ ‘wide’ ‘ﬂatten’ ‘ynormal’ ‘cscale’. Machine Vision Toolbox for MATLAB 115 R Copyright c Peter Corke 2011 . XY ‘colormap’. XY is a cell array whose elements are vectors that span the x. – The “zoom” button requires a left-click and drag to specify a box which deﬁnes the zoomed view. 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. darker than ‘grey’. Set colormap C (N × 3) color map: greyscale unsigned. zero is white. C ‘xydata’. Options ‘ncolors’. linear proﬁle. zero is black. image is inverted C is a 2-vector that speciﬁes the grey value range that spans the colormap. positive is blue. zero is black color map: greyscale signed. • The “histo” button displays a histogram of the pixel values in a new ﬁgure. they are ﬁrst concatenated (horizontally). FUNCTIONS AND CLASSES idisp image display tool idisp(im. N ‘nogui’ ‘noaxes’ ‘noframe’ ‘plain’ ‘bar’ ‘print’. the histogram is computed over only those pixels in view. positive is blue. 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. options) displays an image and allows interactive investigation of pixel value. The image is displayed in a ﬁgure with a toolbar across the top. histogram and zooming. zero is white color map: random values. If im is a cell array of images. 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. User interface: • Left clicking on a pixel will display its value in a box at the top.CHAPTER 2. useful for displaying stereo pair display image planes (colors or sequence) as horizontally adjacent images y-axis increases upward. • The “line” button allows two points to be speciﬁed and a new ﬁgure displays intensity along a line between those points. maximum value is black color map: greyscale signed. negative is red.

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

ithin.CHAPTER 2. • For images of type int the pixels are assumed in the range 0 to max integer value. 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.2. • Gamma decoding is typically performed in the display with gamma=2. • For images with multiple planes the gamma correction is applied to all planes. Computed using the hit-or-miss morphological operator. • For images of type double the pixels are assumed to be in the range 0 to 1. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 . out = igamma(im. gamma) is a gamma corrected version of im. Notes • Gamma encoding is typically performed in a camera with gamma=0. hitormiss igamma correction out = igamma(im. See also itriplepoint. ‘sRGB’) is a gamma decoded version of im using the sRGB decoding function (JPEG images sRGB encoded). All pixels are raised to the power gamma. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1.45.

k. FUNCTIONS AND CLASSES igraphseg Graph-based segmentation L = igraphseg(im. and a larger value indicates a preference for larger regions.5). P. pp. vol. imser Machine Vision Toolbox for MATLAB 118 R Copyright c Peter Corke 2011 . Example im = iread(’58060. 2004. Journal on Computer Vision. Huttenlocher. min. 1500. 100. L = igraphseg(im. Sept. idisp(im) Reference “Efﬁcient graph-based image segmentation”. min. 59. [l. Notes • Is a MEX ﬁle Author Pedro Felzenszwalb. k. [L. 0. 167181. k.CHAPTER 2. See also ithresh.5). 2006. sigma) as above and sigma is the width of a Gaussian which is used to initially smooth the image (default 0. Felzenszwalb and D.m] = igraphseg(im. min is the minimum region size (pixels).jpg’). k is the scale parameter. Int. L is an image of the same size as im where each element is the label assigned to the corresponding pixel in im.m] = igraphseg(im. sigma) as above but m is the number of regions found. min) is a graph-based segmentation of the greyscale or color image 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. [h. options) displays the image histogram. • 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 . ’normcdf’). options) as above but also returns the bin coordinates as a column vectors.x] = ihist(im). bar(x. [H.h).CHAPTER 2. For an image with multiple planes the histogram of each plane is given in a separate subplot. FUNCTIONS AND CLASSES ihist Image histogram ihist(im.h). 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.x] = ihist(im. plot(x. For an image with multiple planes H is a matrix with one column per image plane. H = ihist(im. options) is the image histogram as a column vector.x] = ihist(im.

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

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

w2. Notes • Useful for tracking a template in an image sequence.and y-offsets relative to (x.CC] where (DX. -s. s) is the matching subimage of im1 (template) within the image im2. y.DY) are the x.score] = imatch(im1. If s is a scalar the search region is [-s. ymin.y) and its half-width is H. More generally s is a 4-vector s=[xmin.y) and of size s. • ZNCC matching is used. ymax] relative to (x. s. The return value is xm=[DX. [xm. a perfect match score is 1. s) works as above but also returns a matrix of matching score values for each template position tested. 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 ). • Is a MEX ﬁle.0 Machine Vision Toolbox for MATLAB 122 R Copyright c Peter Corke 2011 . The pixels are in image column order and there are N=W × H rows. s] % relative to (x.y). im2. im2.y) and CC is the similarity score (zero-mean normalized cross correlation) for the best match in the search region.DY.CHAPTER 2. x. The template in im1 is centred at (x. H. • im1 and im2 must be the same size. and columns the vertical position. The template is searched for within im2 inside a rectangular region. y. The rows correspond to horizontal positions of the template. See also col2im imatch Template matching xm = imatch(im1. xmax. x. centred at (x.y).

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

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

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

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

CHAPTER 2. that is n erosions followed by n dilations. n) as above but the structuring element se is applied n times. Notes • Cheaper to apply a smaller structuring element multiple times than one large one. FUNCTIONS AND CLASSES See also iisum iopen Morphological opening out = iopen(im. sides. v) as above but pads with pixels of value v. 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. out = iopen(im. the effective structuing element is the Minkowski sum of the structuring element with itself n times. Machine Vision Toolbox for MATLAB 127 R Copyright c Peter Corke 2011 . n. imorph ipad Pad an image with constants out = ipad(im. sides. se) is the image im after morphological opening with the structuring element se. se. This is an erosion followed by dilation. See also iclose.

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

Notes • The Bresenham algorithm is used to ﬁnd points along the line. p1. p2) as above but also returns the coordinates of the pixels for each point along the line.v) for the corresponding row of p.CHAPTER 2. p2) is a vector of pixel values extracted from the image im (HxWxP) between the points p1 (2 × 1) and p2 (2 × 1). p1. 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. Each row of uv is the pixel coordinate (u. 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. See also bresenham.uv] = iproﬁle(im. 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. [p.

3).5)). edge) as above but the processing of edge pixels can be controlled. se(2. ismooth irank Rank ﬁlter out = irank(im. op. nbins. se. op. out = ipyramid(im.2) = 0. 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. out = ipyramid(im. FUNCTIONS AND CLASSES dimensions half that of the previous image. nbins) as above but the number of histogram bins can be speciﬁed. See also iscalespace. hence output image had reduced dimensions. the maximum. n) as above but only n levels of the pyramid are computed. 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). 12. ones(5. idecimate. is order=1. sigma. The highest rank. sigma) as above but the Gaussian standard deviation is sigma. the image is assumed to wrap around Examples 5 × 5 median ﬁlter: irank(im. out = imorph(image. 1. The pyramid is computed down to a nonhalvable image size. 3 × 3 non-local maximum: se = ones(3. Machine Vision Toolbox for MATLAB 130 R Copyright c Peter Corke 2011 . order. Notes • Works for greyscale images only. se) is a rank ﬁltered version of im. se. im > irank(im.CHAPTER 2. out = imorph(image.

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’. If the path is relative it is searched for on Matlab search path. See also imorph. vmin vmax]. return an image with double precision ﬂoating point pixels in the range 0 to 1. ivar. • A histogram method is used with nbins (default 256). If multiple ﬁles match a 3D or 4D image is returned where the last dimension is the number of images in the sequence. 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. 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. where R=[umin umax. On subsequent calls the initial folder is as set on the last call. Options ‘uint8’ ‘single’ ‘double’ ‘grey’ ‘grey 709’ ‘gamma’. Wildcards are allowed in ﬁle names. either numeric or ‘sRGB’ decimate image by R in both dimensions apply the region of interest R to each image. G ‘reduce’. options) reads the speciﬁed ﬁle and returns a matrix. FUNCTIONS AND CLASSES Notes • Is a MEX ﬁle. im = iread(ﬁle.CHAPTER 2. 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 .

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

iline irotate Rotate image out = irotate(im. vmin.vmin vmax].vmax].H] return central part of image. 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. S ‘crop’ ‘scale’.R) is a subimage of the image im described by the rectangle R=[umin.umax. 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 .CHAPTER 2. S ‘extrapval’. options) is a version of the image im that has been rotated about its centre. V ‘smooth’. angle. See also idisp. FUNCTIONS AND CLASSES See also idecimate. iscale iroi Extract region of interest out = iroi(im. [out.R] = iroi(im) as above but returns the selected region of interest R=[umin umax. S set size of out to H × W where S=[W. Options ‘outsize’.

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

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

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

pp. 2 (2004). Reference David G. “Distinctive image features from scale-invariant keypoints”. isurf. N ‘suppress’. Lowe.org • Corners are processed in order from strongest to weakest. • Wraps a MEX ﬁle from www.vlfeat. 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’.CHAPTER 2. • The SIFT algorithm is patented by Univerity of British Columbia. See also SiftPointFeature. 91-110. • ISURF is a functional equivalent. International Journal of Computer Vision. • 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. 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 . each of which is the feature vectors for the corresponding image in the sequence. icorner isimilarity Locate template in image s = isimilarity(T. 60. R set the number of features to return (default Inf) set the suppression radius (default 0) Notes • Greyscale images only.

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

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

range. That is. the disparity d=d(v.u) means that imr(v. isrot(R. isvec istereo Stereo matching d = istereo(iml. See also ishomog. which can be a scalar for N × N or a 2-vector [N. See also ksobel. imr.M] for an N × M window. range. range is the disparity search range. 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 ). H. w. iconv isrot Test if argument is a rotation matrix isrot(R) is true (1) if the argument is of dimension 3 × 3. • The resulting image is the same size as the input image.u-d) is the same world point as iml(v. else false (0). 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. which can be a scalar for disparities in the range 0 to range.sim] = istereo(iml. ‘valid’) as above. [d.CHAPTER 2. or a 2-vector [DMIN DMAX] for searches in the range DMIN to DMAX. icanny. 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 . imr.u). but also checks the validity of the rotation matrix. H is the half size of the matching window. FUNCTIONS AND CLASSES Notes • Tends to produce quite thick edges.

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

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

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

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

Machine Vision Toolbox for MATLAB 145 R Copyright c Peter Corke 2011 .CHAPTER 2. the image is assumed to wrap around Notes • Is a MEX ﬁle. 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. ithin. 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. These are the Voronoi points in an image skeleton. Computed using the hit-or-miss morphological operator. hence output image had reduced dimensions. 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. The elements in the neighbourhood corresponding to non-zero elements in se are packed into a vector on which the required statistic is computed. se. hitormiss ivar Pixel window statistics out = ivar(im. 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. op. See also iendpoint. that is where three single-pixel wide line intersect. edge) as above but performance at edge pixels can be controlled.

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. @max). se. @std). ones(5.3). the image is assumed to wrap around Example Compute the maximum value over a 5 × 5 window: iwindow(im. 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. FUNCTIONS AND CLASSES See also irank. • Is slow since the function func must be invoked once for every output pixel. The return value becomes the corresponding pixel value in out. Notes • Is a MEX ﬁle. irank Machine Vision Toolbox for MATLAB 146 R Copyright c Peter Corke 2011 . hence output image had reduced dimensions. se. edge) as above but performance of edge pixels can be controlled. func. out = iwindow(image. iwindow iwindow Generalized spatial operator out = iwindow(im.CHAPTER 2. ones(3. Compute the standard deviation over a 3 × 3 window: iwindow(im.5). 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 neighbourhood is deﬁned by the size of the structuring element se which should have odd side lengths. See also ivar.

See also ones. • The vertical derivative.CHAPTER 2. • This kernel is an effective edge detector. Notes • This kernel is the horizontal derivative of the Gaussian. ktriangle. H) as above but the half-width is explictly speciﬁed. kdog. klog. 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. and the two numbers are interpretted as inner and outer radii. k = kdgauss(sigma. dG/dx. k = kcircle(R. iconv Machine Vision Toolbox for MATLAB 147 R Copyright c Peter Corke 2011 .s) as above but s is explicitly speciﬁed. See also kgauss. Notes • If R is a 2-element vector the result is an annulus of ones. is k’. dG/dy. 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.

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

H) as above but the half-width H is speciﬁed. and W=2 × H+1. See also kgauss. zcross Machine Vision Toolbox for MATLAB 149 R Copyright c Peter Corke 2011 . kdgauss. k = klog(sigma. 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.CHAPTER 2. 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. kdog. See also ilaplace. iconv.

[L. 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. L = kmeans(x. and D is the dimension. Reference Tou and Gonzalez. C (D × k) contains the cluster centroids and L (N × 1) indicates which cluster the corresponding element of x is closest to.CHAPTER 2.C] = kmeans(x. it is assumed to have been completed previously. C) is similar to above but the clustering step is not performed.C] = kmeans(x. The data is organized into k clusters based on Euclidean distance from cluster centres C (D × k). FUNCTIONS AND CLASSES kmeans K-means clustering [L. options) is k-means clustering of multi-dimensional data points x (D × N ) where N is the number of points. Pattern Recognition Principles. 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. k. k. 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 . L is a vector (N ×1) whose elements indicates which cluster the corresponding element of x belongs to.

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

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

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

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

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

mpq. p. p. See also npq poly. That is UPQ(im.p. ithresh norm2 columnwise norm n = norm2(m) n = norm2(a. q) is the PQ’th normalized central moment of the polygon with vertices described by the columns of v. b) npq Normalized central image moments m = npq(im.CHAPTER 2.0. Notes • The normalized central moments are invariant to translation and scale. FUNCTIONS AND CLASSES See also otsu. q) is the PQ’th normalized central moment of the image im.0).q)/MPQ(im. upq npq poly Normalized central polygon moments m = NPQ POLY(v. Machine Vision Toolbox for MATLAB 158 R Copyright c Peter Corke 2011 .

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

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

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

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

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

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

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

R. R is the radius and color is a Matlab color spec. Polygon plot sphere Plot spheres PLOT SPHERE(C. R. alpha) as above but alpha speciﬁes the opacity of the sphere were 0 is transparant and 1 is opaque. R. See also plot. text plot poly Plot a polygon plotpoly(p. FUNCTIONS AND CLASSES See also plot. 1=solid.CHAPTER 2. H = PLOT SPHERE(C. color) as above but returns the handle(s) for the spheres. color) add spheres to the current ﬁgure. The default is 1. Matlab color spec transparency of the ﬁlled circle: 0=transparent. Machine Vision Toolbox for MATLAB 166 R Copyright c Peter Corke 2011 . patch. 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. either a letter or 3-vector. H = PLOT SPHERE(C. NOTES • The sphere is always added. 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. • The number of vertices to draw the sphere is hardwired. color. irrespective of ﬁgure hold state.

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

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

options) as above but returns the vector in of column indices of x that describe the inlier point set. N ‘maxDataTrials’. x. if the ﬁt residual is aboe the the threshold the point is considered an outlier. See also linspace ransac Random sample and consensus m = ransac(func. x.in. ransac classiﬁes Points that support the model as inliers and those that do not as outliers. 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 . one column per point pair. options) as above but returns the ﬁnal residual of applying func to the inlier set. T is a threshold on how well a point ﬁts the estimated. [m.in] = ransac(func. 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. [m.resid] = ransac(func. x. ransac determines the subset of points (inliers) that best ﬁt the model described by the function func and the parameter m. options) is the ransac algorithm that robustly ﬁts data x to the model represented by the function func. T. T. T. Options ‘maxTrials’.CHAPTER 2. d) as above but elements increment by d. x typically contains corresponding point data.

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

then p is a vector whose elements are the relative luminosity at the corresponding elements of lambda. See also xycolourspace rluminos Relative photopic luminosity function p = ruminos(lambda) is the relative photopic luminosity function for the wavelengths in lambda. 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. See also luminos Machine Vision Toolbox for MATLAB 171 R Copyright c Peter Corke 2011 .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.csse.edu. If lambda is a vector.au/ pk See also fmatrix. homography rg addticks Label spectral locus RG ADDTICKS() adds wavelength ticks to the spectral locus.CHAPTER 2.

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

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

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

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

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

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

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

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

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

An historical anomaly. Machine Vision Toolbox for MATLAB 181 R Copyright c Peter Corke 2011 . [o1. if tri is XYZ then cc is xy. 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. 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).C2] = tristim2cc(tri) as above but the chromaticity coordinates are returned in separate vectors. [c1. If tri is RGB then cc is rg. 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. each N × 1.o2] = tristim2cc(im) as above but the chromaticity is returned as separate images (H × W ).CHAPTER 2. out (HxWx2) has planes corresponding to r and g. out = tristim2cc(im) is the chromaticity coordinates corresponding to every pixel in the tristimulus image im (HxWx3). Notes • somewhat unusually this function performs a function and its inverse. See also ctraj tristim2cc Tristimulus to chromaticity coordinates cc = tristim2cc(tri) is the chromaticity coordinate (1 × 2) corresponding to the tristimulus tri (1 × 3). or x and y. The O and A vectors are normalized and the normal vector is formed from O x A.

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

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

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

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

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

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