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

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

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

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

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

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

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

google. no matter how urgent or important they might be to you. and you will be suitably acknowledged. You might instead like to communicate with other users via the Google Group called “Robotics Toolbox” http://groups. I can guarantee that I will not respond to any requests for help with assignments or homework.com. You need to signup in order to post.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.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. I need you to write a Machine Vision Toolbox for MATLAB R 10 Copyright c Peter Corke 2011 .Chapter 1 Introduction 1. 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.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. and the signup process is moderated by me so allow a few days for this to happen. lecturers and professors are paid to do. tutors. That’s what you your teachers.

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

7 Acknowledgements Last. Corke. but not least.R. VLFeat http://www. 1. IEEE Robotics and Automation Magazine. pose estimation by Francesco Moreno-Noguer.mathworks. 1994 University of British Columbia.org is a great collection of advanced computer vision algorithms for MATLAB. which is also given in electronic form in the CITATION ﬁle.7. Pascal Fua at the CVLab-EPFL. and there are hundreds of modules available. graph-based segmentation and pose estimation are based on great code Some of the MEX ﬁle use some really neat macros that were part of the package VISTA Copyright 1993. pp 16–25.com/matlabcentral is a great resource for user contributed MATLAB code.the graph-based image segmentation software by Pedro Felzenszwalb. color space conversions by Pascal Getreuer. INTRODUCTION Pages = {16-25} } or “Machine Vision Toolbox”. P.I. November 2005. The Camera Calibration Toolbox by Jean-Yves Bouguet is used unmodiﬁed. Machine Vision Toolbox for MATLAB R 12 Copyright c Peter Corke 2011 . See the ﬁle CONTRIB for details. contributed by Nuno Alexandre Cid Martins of I. and the SURF feature detector by Dirk-Jan Kroon at U. RANSAC code by Peter Kovesi.vlfeat. 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. this release includes functions for computing image plane homographies and the fundamental matrix. the k-means and MSER algorithms by Andrea Vedaldi and Brian Fulkerson. 1. MSER.1. 12(4). Vincent Lepetit. ACKNOWLEDGEMENTS CHAPTER 1.1 Other toolboxes Matlab Central http://www. Twente. Coimbra..Functions such as SURF.6.S.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

• SiftCornerFeature objects can be used in vectors and arrays • The SIFT algorithm is patented and not distributed with this toolbox. Notes • SiftCornerFeature is a reference object. PointFeature. SurfPointFeature Machine Vision Toolbox for MATLAB R 30 Copyright c Peter Corke 2011 . 2004.Lowe. See README.91-110. 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. If F is a vector (N ×1) of SiftCornerFeature objects then F. See also isift. vol. References “Distinctive image features from scale-invariant keypoints”. D.SIFT. Journal on Computer Vision.CHAPTER 2. You can download a SIFT implementation which this class can utilize. Nov. ScalePointFeature.u is a 2×N matrix with each column the corresponding u coordinate.60. Int. pp.

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

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

CHAPTER 2. • 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.

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

Two windows are shown and animated: 1. error norm.camera intrinsic structure (camparam) . The params structure can be used to override simulation defaults by providing elements.the side length of the target in world units (0. params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. The camera/robot is initially at pose T and is driven to the orgin.2) niter eterm lambda ci depth . defaults in parentheses: target size . Two windows are shown and animated: 1. The external view.CHAPTER 2. showing the target points and the camera The results structure contains time-history information about the image plane.depth of points to use for Jacobian. showing the desired view (*) and the current view (o) 2. The camera view. can be scalar or diagonal 6 × 6 matrix (0. FUNCTIONS AND CLASSES SphericalCamera.sph Implement spherical IBVS for point features results = sph(T) results = sph(T. image plane size and desired feature locations.gain.sph2 Implement spherical IBVS for point features results = sph(T) results = sph(T.5) target center .the number of iterations to run the simulation (500) . 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.a stopping criteria on feature error norm (0) . from simulation ([]) SEE ALSO: ibvsplot SphericalCamera. of 4-vector. The camera/robot is initially at pose T and is driven to the orgin.0.center of the target in world coords (0.01) . camera pose. Jacobian condition number. The camera view. error. scalar for If null take actual value all points.

Robotics and Automation.the number of iterations to run the simulation (500) . The depth of the points from the camera is given by z which is a scalar. I. The params structure can be used to override simulation defaults by providing elements. pp. image plane size and desired feature locations.visjac p(pt.visjac l.CHAPTER 2. error.camera intrinsic structure (camparam) .visjac p polar.visjac p Visual motion Jacobian for point feature J = C.visjac e Machine Vision Toolbox for MATLAB R 36 Copyright c Peter Corke 2011 .gain. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera. IEEE Int. May 3-7 2010.3) niter eterm lambda ci depth . defaults in parentheses: target size . or a vector (N × 1) for each point. Reference “Spherical image-based visual servo and structure estimation”. CentralCamera. camera pose. of 4-vector. error norm.the side length of the target in world units (0. (Anchorage). z) is the image Jacobian (2N × 6) for the image plane points pt (2 × N ) described by phi (longitude) and theta (colatitude).a stopping criteria on feature error norm (0) . CentralCamera.5) target center . for all points. can be scalar or diagonal 6 × 6 matrix (0. FUNCTIONS AND CLASSES 2.0. scalar for If null take actual value all points.depth of points to use for Jacobian. Conf. The Jacobian gives the image-plane velocity in terms of camera spatial velocity. 5550-5555. The external view. See also CentralCamera. Corke.01) . P.center of the target in world coords (0. in Proc. showing the target points and the camera The results structure contains time-history information about the image plane. Jacobian condition number.

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

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

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

G ‘scale’. Obtain an image of size S=[W H]. 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. Options ‘uint8’ ‘ﬂoat’ ‘double’ ‘grey’ ‘gamma’. • The speciﬁed ‘resolution’ must match one that the camera is capable of. otherwise the result is not predictable. Machine Vision Toolbox for MATLAB R 40 Copyright c Peter Corke 2011 . Video AxisWebCamera.CHAPTER 2. S ‘resolution’. Methods grab size close char Aquire and return the next image Size of image Close the image source Convert the object parameters to human readable string See also ImageSource.axis.com). 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.axis. options) is an AxisWebCamera object that acquires images from an Axis Communications (www.com) web camera.AxisWebCamera Axis web camera constructor a = AxisWebCamera(url.

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

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

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

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

CHAPTER 2. subclass of Camera. FUNCTIONS AND CLASSES BagOfWords. 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 .wordvector(J) is the word frequency vector for the J’th image in the bag. The vector is K × 1 and the angle between any two WFVs is an indication of image similarity.wordvector Word frequency vector wf = B. Notes • The word vector is expensive to compute so a lazy evaluation is performed on the ﬁrst call to this function CatadioptricCamera Catadioptric camera class A concrete class for a catadioptric camera.

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

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

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

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

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

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

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

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

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

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

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

W ‘nbins’.char Convert to string s = HT.5) Set ht. The threshold is determined from the maximum edge strength value x ht. Options ‘equal’ ‘interpwidth’. else N = [Ntheta. Set ht. 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. Default 400 × 401.char() is a compact string representation of the Hough transform parameters. if N is scalar set Nrho=Ntheta=N.houghThresh (default 0.display Display value HT. Hough. W ‘houghthresh’.1). See also Hough. FUNCTIONS AND CLASSES the edge strength but votes can be made equal with the option ‘equal’. Nrho].suppress (default 0) Set number of bins.edgeThresh. T ‘edgethresh’. N All edge pixels have equal weight.display() displays a compact human-readable string representation of the Hough transform parameters. otherwise the edge pixel value is the vote strength Interpolation width (default 3) Set ht.char Machine Vision Toolbox for MATLAB R 57 Copyright c Peter Corke 2011 .edgeThresh (default 0. Hough.CHAPTER 2. T ‘suppress’.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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 . deﬁned by a point on the ray and a direction unit-vector.Ray3D Ray constructor R = Ray3D(p0. Ray3D Ray in 3D space This object represents a ray in 3D space.clockwise “outer boundary” and one or more clock-wise “inner boundaries” around “holes”. d) is a new Ray3D object deﬁned by a point on the ray p0 and a direction vector d. unit vector (3 × 1) Notes • Ray3D objects can be used in vectors and arrays Ray3D. 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.

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

FUNCTIONS AND CLASSES x = R.CHAPTER 2. minimum horizontal coordinate bounding box. maximum horizontal coordinate bounding box. minimum vertical coordinate bounding box. If R is a vector then x has multiple columns.c. corresponding to the intersection of R(i) with p. less for other shapes a structure containing moments of order 0 to 2 Machine Vision Toolbox for MATLAB R 80 Copyright c Peter Corke 2011 . 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. RegionFeature Region feature class This class represents a region feature.d) where aX + bY + cZ + d = 0. vertical coordinate bounding box.0) 1 for a circle.intersect(p) returns the point of intersection between the ray R and the plane p=(a. 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.b. horizontal coordinate centroid.

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

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

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

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

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

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

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

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

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

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

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

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

while Table I(5. E) is the CIE color matching (1×3) function for an illumination spectrum deﬁned by intensity E (N × 1) and wavelength lambda (N × 1) [m].d1. If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda. and 22500 (444. rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m]. FUNCTIONS AND CLASSES [k.16).44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 .d2] = closest(a.CHAPTER 2.3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps. rgb = cmfrgb(lambda.32). Notes • Is a MEX ﬁle. Notes • Data from http://cvrl.3) of Wyszecki & Stiles (1982). 19000 (526.5.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. The data are referred to as pilot data.) • These CMFs differ slightly from those of Stiles & Burch (1955).5.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers. but probably represent the best estimate of the 2 deg CMFs. See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation.ucl. the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645.ioo. unlike the CIE 2 deg functions (which were reconstructed from chromaticity data). As noted in footnote a on p.5. (Table 1(5. b) as above but also returns the distance to the second closest point. 335 of Table 1(5.3) of Wyszecki & Stiles (1982). they were measured directly. • From Table I(5.ac. since.5.

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

Perceptually uniform spaces such as Lab remedy this problem. See also colorspace Machine Vision Toolbox for MATLAB R 95 Copyright c Peter Corke 2011 .g] to every pixel in the color image im. Notes • The output image could be thresholded to determine color similarity. 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. • Note that Euclidean distance in the rg-chromaticity space does not correspond well with human perception of color differences. 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. colordistance Colorspace distance d = colordistance(im.

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

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

FUNCTIONS AND CLASSES • Based on the standard X11 color database rgb. As MATLAB’s native datatype. im) as above but speciﬁes separate output channels or planes. 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. • Tristimulus values are in the range 0 to 1 colorspace Color space conversion of image out = colorspace(s. double data is the natural choice. colorspace(s.i2. i1.601) + 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. im) converts the image im to a different color space according to the string s which speciﬁes the source and destination color spaces. Input and output images have 3 planes. [o1. s = ‘src->dest’. • When R’G’B’ is the source or destination. • Color space names are case insensitive.txt.709 gamma-corrected) Luma (ITU-R BT. it can be omitted. or alternatively. 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. and R Machine Vision Toolbox for MATLAB 98 Copyright c Peter Corke 2011 .i3) as above but speciﬁes separate input channels.o3] = colorspace(s. s = ‘dest<-src’. For example ‘yuv<’ is short for ‘yuv<-rgb’.CHAPTER 2.o2.

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

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

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

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

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

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

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

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

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

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

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

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

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.CHAPTER 2. 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. FUNCTIONS AND CLASSES Notes • Works for color or greyscale images • Direction can be abbreviated to ﬁrst character. options) convolves im1 with im2. See also conv2 Machine Vision Toolbox for MATLAB 111 R Copyright c Peter Corke 2011 . If the larger image is color (has multiple planes) the kernel is applied to each plane. ‘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. The smaller image is taken as the kernel and convolved with the larger image. im2.

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

Computer Vision and Pattern Recognition. Shi and C. pp.Noble. T ‘maxiter’.6.. Proc. J. • “Finding corners”. • “Good features to track”. • The descriptor is a vector of ﬂoat types to save space References • “A combined corner and edge detector”. Image and Vision Computing. Options ‘dplot’. IEEE Computer Society. limit the change in rotation at each step to T (default 0. Manchester. Proc. [T.CHAPTER 2. 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. N ‘mindelta’. vol. • The default descriptor is a vector [Ix* Iy* Ixy*] which are the unique elements of the structure tensor. p2.J. Machine Vision Toolbox for MATLAB 113 R Copyright c Peter Corke 2011 .05 rad) stop after N iterations (default 100) stop when the relative change in error norm is less than T (default 0. See also PointFeature. options) as above but also returns the norm of the error between the transformed point set p2 and p1. T ‘distthresh’. isurf icp Point cloud alignment T = icp(p1.121-128. Tomasi. pp. with a delay of d [sec]. Harris and M. pp 147-151. options) is the homogeneous transformation that best transforms the set of points p2 to p1 using the iterative closest point algorithm. J.5 [sec]. 1994.001) eliminate correspondences more than T x the median distance at each iteration. Stephens. p2. where * denotes squared and smoothed.d] = icp(p1. show the points p1 and p2 at each iteration. d ‘plot’ ‘maxtheta’. C. Fourth Alvey Vision Conf.G. May 1988. with a delay of 0. T show the points p1 and p2 at each iteration. 593-593. 1988.

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

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

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

See also itriplepoint. All pixels are raised to the power gamma.2. ‘sRGB’) is a gamma decoded version of im using the sRGB decoding function (JPEG images sRGB encoded). Notes • Gamma encoding is typically performed in a camera with gamma=0. out = igamma(im.CHAPTER 2. • Gamma decoding is typically performed in the display with gamma=2. 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.45. • For images of type double the pixels are assumed to be in the range 0 to 1. ithin. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1. • For images with multiple planes the gamma correction is applied to all planes. gamma) is a gamma corrected version of im. hitormiss igamma correction out = igamma(im. Computed using the hit-or-miss morphological operator. • For images of type int the pixels are assumed in the range 0 to max integer value. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 .

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

x] = ihist(im. For an image with multiple planes H is a matrix with one column per image plane. 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. 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. options) displays the image histogram.h). For an image with multiple planes the histogram of each plane is given in a separate subplot. ’normcdf’).x] = ihist(im). • 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 .x] = ihist(im. FUNCTIONS AND CLASSES ihist Image histogram ihist(im. options) as above but also returns the bin coordinates as a column vectors. [H.CHAPTER 2. plot(x. H = ihist(im.h). options) is the image histogram as a column vector. [h. bar(x.

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

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

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

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

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

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

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.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. 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. FUNCTIONS AND CLASSES See also ithresh. Machine Vision Toolbox for MATLAB 126 R Copyright c Peter Corke 2011 .

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

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

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

1. order. FUNCTIONS AND CLASSES dimensions half that of the previous image. op. The pyramid is computed down to a nonhalvable image size.3). im > irank(im. Machine Vision Toolbox for MATLAB 130 R Copyright c Peter Corke 2011 .2) = 0. sigma. n) as above but only n levels of the pyramid are computed. nbins. se) is a rank ﬁltered version of im. the maximum. nbins) as above but the number of histogram bins can be speciﬁed. out = ipyramid(im. edge) as above but the processing of edge pixels can be controlled. op. ismooth irank Rank ﬁlter out = irank(im. se). out = imorph(image. se(2. out = ipyramid(im. 12. ones(5. idecimate. See also iscalespace. se. 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 image is assumed to wrap around Examples 5 × 5 median ﬁlter: irank(im.CHAPTER 2. sigma) as above but the Gaussian standard deviation is sigma. hence output image had reduced dimensions. 3 × 3 non-local maximum: se = ones(3.5)). 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. Notes • Works for greyscale images only. out = imorph(image. se. The highest rank. is order=1.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

H) as above but the half-width H is speciﬁed. H) as above but the kernel half-width is speciﬁed. 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. k = kdog(sigma1. klog. where sigma1 > SIGMA2. sigma2.CHAPTER 2. See also kdgauss. By default SIGMA2 = 1. The kernel is centred within the matrix k whose half-width H = 3 × SIGM A and W=2 × H+1.6*sigma1. sigma2) as above but sigma2 is speciﬁed directly. kdog. FUNCTIONS AND CLASSES kdog Difference of Gaussian kernel k = kdog(sigma1) is a 2-dimensional difference of Gaussian kernel equal to KGAUSS(sigma1) . klog. iconv Machine Vision Toolbox for MATLAB 148 R Copyright c Peter Corke 2011 . iconv kgauss Gaussian kernel k = kgauss(sigma) is a 2-dimensional unit-volume Gaussian kernel of width (standard deviation) sigma.KGAUSS(SIGMA2). kdgauss. See also kgauss. k = kdog(sigma1. k = kgauss(sigma.

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

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

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

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

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

• The ncc similarity measure is invariant to scale changes in image intensity. The threshold at each pixel is a function of the mean and standard deviation computed over a W × W window.2 Reference An Introduction to Digital Image Processing. w2) as above but returns the per-pixel mean m and standard deviation s. See also zncc. ssd. k. T has the same dimensions as im.CHAPTER 2. [T. sad. FUNCTIONS AND CLASSES Notes • A value of 1 indicates identical pixel patterns. k. 20). Prentice-Hall. isimilarity niblack Adaptive thresholding T = niblack(im. w2) is the per-pixel (local) threshold to apply to image im. 1986. W. -0.s] = niblack(im. • w2 should be chosen to be half the “size” of the features to be segmented. the height of a character. in text segmentation. Machine Vision Toolbox for MATLAB 157 R Copyright c Peter Corke 2011 . • A common choice of k=-0.2. Notes • This is an efﬁcient algorithm very well suited for binarizing text. Example t = niblack(im. niblack. idisp(im >= t). where W=2*w2+1.m. for example.

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

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

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

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

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

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

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

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

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

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

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

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

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

then p is a vector whose elements are the relative luminosity at the corresponding elements of lambda.edu.uwa. See also xycolourspace rluminos Relative photopic luminosity function p = ruminos(lambda) is the relative photopic luminosity function for the wavelengths in lambda. If lambda is a vector.csse. 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 .au/ pk See also fmatrix. Relative luminosity lies in the interval 0 to 1 which indicate the intensity with which wavelengths are perceived by the light-adapted human eye.CHAPTER 2. homography rg addticks Label spectral locus RG ADDTICKS() adds wavelength ticks to the spectral locus.

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

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

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

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

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

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

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

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

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

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

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

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

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

FUNCTIONS AND CLASSES zssd Sum of squared differences m = zssd(i1. sad. i2) is the zero-mean sum of squared 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.CHAPTER 2. See also sdd. The result m is a scalar that indicates image similarity. ncc. Notes • The zssd similarity measure is invariant to changes in image brightness offset. isimilarity Machine Vision Toolbox for MATLAB 189 R Copyright c Peter Corke 2011 .

Sign up to vote on this title

UsefulNot useful- Machine Vision Toolbox for Matlab
- Introduction to MATLAB
- A Proposal Study for Designing and Introducing Automated Tools and Procedures Incorporating MATLAB Package for Undergraduate Basic Discipline Studies
- Getting Started With MATLAB
- Matlab Crash Course
- Matlab Short 152
- Mathcad_Matlab_Manual
- Introduction to Matlab1
- MATLAB Environment
- 1. MATLAB Environment
- Introduction to Image Processing in Matlab 1
- 4413-lecture-09
- Appendix
- INVERT.M
- matlab
- Sigmon_MATLABPrimer-3rdEd_2003
- Matlab
- Neuro Explorer Manual
- matlab tutorial
- MATLab1.docx
- Java Builder
- cs701Lec08Eng
- Numerical Methods with MATLAB_Recktenwald.pdf
- Hitachi HDC 571E
- faceAPI-techspecs
- fifii.docx
- D80 Quick Guide
- SI-2K User Manual
- LPC10E.M
- xg-8000lineal-131013151920-phpapp01
- Machine Vision Toolbox for MATLABr3