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

Licence Toolbox home page Discussion group

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

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

Preface

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

Peter C0rke

Robotics,

Vision and Control

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

Corke

Robotics,

Vision and Control

Peter Corke

1

Robotics, Vision and Control

isbn 978-3-642-20143-1

9 783642 201431

›

springer.com

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

Machine Vision Toolbox for MATLAB

R

3

Copyright c Peter Corke 2011

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

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

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

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

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

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

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. I need you to write a Machine Vision Toolbox for MATLAB R 10 Copyright c Peter Corke 2011 . You need to signup in order to post.com.google.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.au/group/robotics-tool-box which is a forum for discussion. lecturers and professors are paid to do. tutors. 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. I am very happy to accept contributions for inclusion in future versions of the toolbox. no matter how urgent or important they might be to you. That’s what you your teachers. 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.Chapter 1 Introduction 1. and the signup process is moderated by me so allow a few days for this to happen. and you will be suitably acknowledged.

pdf or the web-based documentation html/*. 1. type of organization and application. Number = {4}.3. Author = {P. HOW TO OBTAIN THE TOOLBOX CHAPTER 1. Corke}. 1. the table of content to functions. Title = {Machine Vision Toolbox}.pdf is a manual that describes all functions in the Toolbox.3 How to obtain the Toolbox The Machine Vision Toolbox is freely available from the Toolbox home page at http://www. INTRODUCTION few words about why you want to join the list so I can distinguish you from a spammer or a web-bot.html on a server for class use. If you plan to distribute paper copies of the PDF manual then every copy must include the ﬁrst two pages (cover and licence). It is R auto-generated from the comments in the MATLAB code and is fully hyperlinked: to external web sites.4 MATLAB version issues The Toolbox has been tested under R2011a.gz) or zip format (. 1. 1.com The ﬁles are available in either gzipped tar format (.petercorke.I. The ﬁle robot.6 Use in research If the Toolbox helps you in your endeavours then I’d appreciate you citing the Toolbox when you publish. A menu-driven demonstration can be invoked by the function rtdemo. Volume = {12}.zip). Journal = {IEEE Robotics and Automation Magazine}. The details are @article{Corke05f. This is just a means for me to gauge interest and to help convince my bosses (and myself) that this is a worthwhile activity. Year = {2005}. Machine Vision Toolbox for MATLAB R 11 Copyright c Peter Corke 2011 .5 Use in teaching This is deﬁnitely encouraged! You are free to put the PDF manual (vision. and the “See also” functions to each other.1. The web page requests some information from you regarding such as your country. Month = nov.

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

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

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

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

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

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

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

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

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

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

F(C2) is the essential matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view). optical axis is z-axis. N ‘focal’. u. FUNCTIONS AND CLASSES Options ‘name’.F. CatadioptricCamera.invE Machine Vision Toolbox for MATLAB R 22 Copyright c Peter Corke 2011 . camera at origin. p. SIGMA ‘pose’. “An invitation to 3D”. N ‘sensor’. E = C. D ‘default’ ‘image’. CentralCamera.177 See also CentralCamera. P ‘pixel’. SphericalCamera CentralCamera. IM ‘resolution’.T and the second is a relative motion represented by the homogeneous transformation T.Ma.E Essential matrix E = C.CHAPTER 2. Reference Y.Kosecka.Soatto. E = C.Sastry. f=8mm. T ‘color’. J. S ‘noise’. S ‘centre’. Springer.and v-axes parallel to x. 10um pixels. 2003.8]) See also Camera. S.E(T) is the essential matrix relating two camera views.F(F) is the essential matrix based on the fundamental matrix F (3 × 3) and the intrinsic parameters of camera C. S. ﬁsheyecamera. The ﬁrst view is from the current camera pose C. C Name of camera Focal length [metres] Distortion vector [k1 k2 k3 p1 p2] Distortion vector [k1 k2 p1 p2 k3] Default camera parameters: 1024 × 1024. D ‘distortion-bouguet’. 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.and y-axes respectively. F ‘distortion’.

F Fundamental matrix F = C.Soatto.T and the second is a relative motion represented by the homogeneous transformation T.T and the second is after a relative motion represented by the homogeneous transformation T.F(C2) is the fundamental matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view).K() is the 3 × 3 intrinsic parameter matrix. “An invitation to 3D”.H Homography matrix H = C. S. S. F = C. Springer. Reference Y. The ﬁrst view is from the current camera pose C. d) is a 3 × 3 homography matrix for the camera observing the plane with normal n and at distance d.H(T.Kosecka. 2003.177 See also CentralCamera.Sastry.CHAPTER 2.K Intrinsic parameter matrix K = C.E CentralCamera. Machine Vision Toolbox for MATLAB R 23 Copyright c Peter Corke 2011 . FUNCTIONS AND CLASSES CentralCamera. J.Ma. See also CentralCamera.H CentralCamera.F(T) is the fundamental matrix relating two camera views. from two viewpoints. n. p. The ﬁrst view is from the current camera pose C.

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

FUNCTIONS AND CLASSES s = C. J. p120122 Notes • The transformation is from view 1 to view 2. p) as above but only solutions in which the world point p is visible are returned.invE(E.E CentralCamera.CHAPTER 2. section 5.3 Machine Vision Toolbox for MATLAB R 25 Copyright c Peter Corke 2011 . Reference Hartley & Zisserman.Soatto. See also CentralCamera. translation not to scale • n. In practice there are multiple solutions and s is a vector of structures with elements: • T. s. “An invitation to 3D”.Sastry. 2003. camera motion as a homogeneous transform matrix (4 × 4). “An invitation to 3D”. Springer.invH Decompose homography matrix s = C. J. p. s.Sastry. p116. Chap 9.Soatto. Springer. s.Ma. Reference Y.Kosecka. “Multiview Geometry”.Kosecka. s.invH(H) decomposes the homography H (3 × 3) into the camera motion and the normal to the plane. 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. 259 Y.Ma. 2003.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

in Proc. Conf. See also PointFeature BagOfWords. 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. Ninth IEEE Int. Notes • Uses the MEX function vl kmeans to perform clustering (vlfeat. on Computer Vision. “Video Google: a text retrieval approach to object matching in videos”.CHAPTER 2.1470-1477. f can also be a cell array. as produced by ISURF() for an image sequence. b = BagOfWords(f. pp.org). The features are sorted into k clusters and each cluster is termed a visual word. k) is a new bag of words created from the feature vector f and with k words. 2003.BagOfWords Create a BagOfWords object b = BagOfWords(f.Sivic and A. Machine Vision Toolbox for MATLAB R 42 Copyright c Peter Corke 2011 . Oct. FUNCTIONS AND CLASSES Methods isword occurrences remove stop wordvector wordfreq similarity contains exemplars display char Return all features assigned to word Return number of occurrences of word Remove stop words Return word frequency vector Return words and their frequencies Compare two word bags List the images that contain a word Display examples of word support regions Display the parameters of the bag of words Convert the parameters of the bag of words to a string Properties K nstop nimages The number of clusters speciﬁed The number of stop words speciﬁed The number of images in the bag Reference J.Zisserman.

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

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

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

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

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

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

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

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

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

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

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

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

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

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 . A horizontal line has theta = 0. and d is the perpendicular distance between (0.H). options) is the Hough transform of the edge image E. a vertical line has theta = pi/2 or -pi/2. Offset is in the range -rho max to rho max where rho max=max(W. See also LineFeature Hough. Theta spans the range -pi/2 to pi/2 in Ntheta steps.CHAPTER 2. FUNCTIONS AND CLASSES where theta is the angle the line makes to horizontal axis.Hough Create Hough transform object ht = Hough(E.0) and the line. 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. The voting array is 2-dimensional. For every pixel in the edge image E (H ×W ) greater than a threshold the corresponding elements of the accumulator are incremented.

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

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

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

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

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

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

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

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

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

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

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.cost

Cost of edge

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

PGraph.display

Display state of the graph

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

See also

PGraph.char

PGraph.distance

Distance between nodes

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

PGraph.distances

distance to all nodes

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

Machine Vision Toolbox for MATLAB

R

67

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.edges

Find edges given vertex

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

PGraph.goal

Set goal node

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

See also

PGraph.path cost is total distance from goal

PGraph.neighbours

Neighbours of a node

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

PGraph.next

Find next node toward goal

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

See also

PGraph.goal, PGraph.path

Machine Vision Toolbox for MATLAB

R

68

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.path

Find path to goal node

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

See also

PGraph.goal

PGraph.pick

Graphically select a node

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

See also

PGraph.plot

PGraph.plot

Plot the graph

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

Options

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

Machine Vision Toolbox for MATLAB

R

69

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

PGraph.showComponent

t

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

PGraph.showVertex

Highlight a vertex

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

PGraph.vertices

Find vertices given edge

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

PointFeature

PointCorner feature object

A superclass for image corner features.

Methods

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

Machine Vision Toolbox for MATLAB

R

70

Copyright c Peter Corke 2011

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

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

FUNCTIONS AND CLASSES PointFeature.plot() overlay a marker at the feature position. Polygon . If F is a vector then each element is plotted.plot(ls) as above but the optional line style arguments ls are passed to plot.plot Plot feature F.CHAPTER 2. Methods plot area moments centroid perimeter transform inside intersection difference union xor display char Plot polygon Area of polygon Moments of polygon Centroid of polygon Perimter of polygon Transform polygon Test if points are inside polygon Intersection of two polygons Difference of two polygons Union of two polygons Exclusive or of two polygons print the polygon in human readable form convert the polgyon to human readable string Properties vertices extent n List of polygon vertices.General polygon class p = Polygon(vertices). one per column Bounding box [minx maxx. 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 . F.

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

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

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

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

FUNCTIONS AND CLASSES • If the result P is not simply connected (such as a polygon with a “hole”) the resulting contour consist of counter.Ray3D Ray constructor R = Ray3D(p0. d) is a new Ray3D object deﬁned by a point on the ray p0 and a direction vector d.CHAPTER 2.clockwise “outer boundary” and one or more clock-wise “inner boundaries” around “holes”. Machine Vision Toolbox for MATLAB R 78 Copyright c Peter Corke 2011 . deﬁned by a point on the ray and a direction unit-vector. 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. Ray3D Ray in 3D space This object represents a ray in 3D space.

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

b.d) where aX + bY + cZ + d = 0. minimum vertical coordinate bounding box. minimum horizontal coordinate bounding box.c. Methods boundary box plot plot boundary plot box plot ellipse display char Return the boundary as a list Return the bounding box Plot the centroid Plot the boundary Plot the bounding box Plot the equivalent ellipse Display value Convert value to string Properties uc vc umin umax vmin vmax area class label children edgepoint edge perimeter touch a b theta shape circularity moments centroid. vertical coordinate bounding box. corresponding to the intersection of R(i) with p. If R is a vector then x has multiple columns. maximum horizontal coordinate bounding box.CHAPTER 2. RegionFeature Region feature class This class represents a region feature. 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 . FUNCTIONS AND CLASSES x = R. maximum vertical coordinate the number of pixels the value of the pixels forming this region the label assigned to this region a list of indices of features that are children of this feature coordinate of a point on the perimeter a list of edge points 2 × N matrix number of edge pixels true if region touches edge of the image major axis length of equivalent ellipse minor axis length of equivalent ellipse angle of major ellipse axis to horizontal axis aspect ratio b/a (always <= 1.0) 1 for a circle.intersect(p) returns the point of intersection between the ray R and the plane p=(a. horizontal coordinate centroid.

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

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

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

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

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

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

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

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

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

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

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

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

44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 . • From Table I(5. The data are referred to as pilot data. FUNCTIONS AND CLASSES [k.5. If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda.3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps.ac.3) of Wyszecki & Stiles (1982). See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. while Table I(5. As noted in footnote a on p.5. but probably represent the best estimate of the 2 deg CMFs. unlike the CIE 2 deg functions (which were reconstructed from chromaticity data). Notes • Is a MEX ﬁle.CHAPTER 2.5.32). since. Notes • Data from http://cvrl. the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645.ucl.ioo. (Table 1(5. 335 of Table 1(5. 19000 (526. rgb = cmfrgb(lambda.d2] = closest(a.3) of Wyszecki & Stiles (1982). E) is the CIE color matching (1×3) function for an illumination spectrum deﬁned by intensity E (N × 1) and wavelength lambda (N × 1) [m]. b) as above but also returns the distance to the second closest point.16). and 22500 (444. they were measured directly.) • These CMFs differ slightly from those of Stiles & Burch (1955).5.d1. rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m].

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

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

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

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

and uint8 data with integer-valued intensities from 0 to 255. im) as above but speciﬁes separate output channels or planes.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.o3] = colorspace(s. • MATLAB uses two standard data formats for R’G’B’: double data with intensities in the range 0 to 1. FUNCTIONS AND CLASSES • Based on the standard X11 color database rgb. im) converts the image im to a different color space according to the string s which speciﬁes the source and destination color spaces. it can be omitted.i2. s = ‘src->dest’.709 gamma-corrected) Luma (ITU-R BT.i3) as above but speciﬁes separate input channels. For example ‘yuv<’ is short for ‘yuv<-rgb’. • When R’G’B’ is the source or destination.CHAPTER 2. Input and output images have 3 planes. [o1.o2. As MATLAB’s native datatype. i1. • Color space names are case insensitive. • Tristimulus values are in the range 0 to 1 colorspace Color space conversion of image out = colorspace(s. colorspace(s. or alternatively. Supported color spaces are: ‘RGB’ ‘YPbPr’ ‘YCbCr’/’YCC’ ‘YUV’ ‘YIQ’ ‘YDbDr’ ‘JPEGYCbCr’ ‘HSV’/’HSB’ ‘HSL’/’HLS’/’HSI’ ‘XYZ’ ‘Lab’ ‘Luv’ ‘Lch’ R’G’B’ Red Green Blue (ITU-R BT.txt. double data is the natural choice. and R Machine Vision Toolbox for MATLAB 98 Copyright c Peter Corke 2011 . s = ‘dest<-src’.

However.b) is the Euclidean distances between L-dimensional points described by the matrices a (L × M ) and b (L × N ) respectively.CHAPTER 2. • If im is an M × 3 array. FUNCTIONS AND CLASSES the R’G’B’ format used by colorspace. B = rand(400. out will also have size M × 3.100).200). The distance d is M × N and element d(I. distance Euclidean distances between sets of points d = distance(a.B). for memory and computational performance. Example A = rand(400. Given uint8 R’G’B’ color data. d = distance(A. Author Pascal Getreuer 2005-2006 diff2 diff3(v) compute 2-point difference for each point in the vector v. like a colormap. colorspace will ﬁrst cast it to double R’G’B’ before processing.J) is the distance between points a(I) and d(J). some functions also operate with uint8 R’G’B’.2*A. Notes • This fully vectorized (VERY FAST!) • It computes the Euclidean distance between two vectors by: ||A-B|| = sqrt ( ||A||ˆ2 + ||B||ˆ2 .B ) R Machine Vision Toolbox for MATLAB 99 Copyright c Peter Corke 2011 .

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

out = igamma(im. • For images of type double the pixels are assumed to be in the range 0 to 1. hitormiss igamma correction out = igamma(im. • For images of type int the pixels are assumed in the range 0 to max integer value. FUNCTIONS AND CLASSES iendpoint Find end points in a binary skeleton image out = iendpoint(im) is a binary image where pixels are set if the corresponding pixel in the binary image im is the end point of a single-pixel wide line such as found in an image skeleton. ithin. Computed using the hit-or-miss morphological operator. All pixels are raised to the power gamma.2. • For images with multiple planes the gamma correction is applied to all planes. gamma) is a gamma corrected version of im. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 .45.CHAPTER 2. See also itriplepoint. ‘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. • Gamma decoding is typically performed in the display with gamma=2.

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

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

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

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

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

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

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

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

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

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

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

v) for the corresponding row of p. p2) as above but also returns the coordinates of the pixels for each point along the line. p2) is a vector of pixel values extracted from the image im (HxWxP) between the points p1 (2 × 1) and p2 (2 × 1). [p. p1. 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. p1. Each row of uv is the pixel coordinate (u. See also bresenham. Notes • The Bresenham algorithm is used to ﬁnd points along the line.uv] = iproﬁle(im. out is a cell array of images each one having R Machine Vision Toolbox for MATLAB 129 Copyright c Peter Corke 2011 . 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. 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.

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

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. im = iread(ﬁle. Wildcards are allowed in ﬁle names. where R=[umin umax. G ‘reduce’. See also imorph. If multiple ﬁles match a 3D or 4D image is returned where the last dimension is the number of images in the sequence. 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. 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. options) reads the speciﬁed ﬁle and returns a matrix. either numeric or ‘sRGB’ decimate image by R in both dimensions apply the region of interest R to each image. On subsequent calls the initial folder is as set on the last call. • A histogram method is used with nbins (default 256). vmin vmax]. If the path is relative it is searched for on Matlab search path. Options ‘uint8’ ‘single’ ‘double’ ‘grey’ ‘grey 709’ ‘gamma’. return an image with double precision ﬂoating point pixels in the range 0 to 1. R return an image with 8-bit unsigned integer pixels in the range 0 to 255 return an image with single precision ﬂoating point pixels in the range 0 to 1. R ‘roi’.CHAPTER 2. ivar.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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. out = iwindow(image. • Is slow since the function func must be invoked once for every output pixel.3). See also ivar. 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. func) is an image where each pixel is the result of applying the function func to a neighbourhood centred on the corresponding pixel in im. The return value becomes the corresponding pixel value in out. se. FUNCTIONS AND CLASSES See also irank. Compute the standard deviation over a 3 × 3 window: iwindow(im. the image is assumed to wrap around Example Compute the maximum value over a 5 × 5 window: iwindow(im.CHAPTER 2. Notes • Is a MEX ﬁle. @std). edge) as above but performance of edge pixels can be controlled. irank Machine Vision Toolbox for MATLAB 146 R Copyright c Peter Corke 2011 . iwindow iwindow Generalized spatial operator out = iwindow(im. se. ones(3.5). func. ones(5. The neighbourhood is deﬁned by the size of the structuring element se which should have odd side lengths. @max). hence output image had reduced dimensions.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

The result m is a scalar that indicates image similarity. sad. ncc. i2) is the zero-mean sum of squared differences between the two equally sized image patches i1 and i2. FUNCTIONS AND CLASSES zssd Sum of squared differences m = zssd(i1. See also sdd. 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 .CHAPTER 2. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases.