Licence Toolbox home page Discussion group

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

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

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

Peter C0rke

Robotics,
Vision and Control

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

Corke

Robotics,
Vision and Control

Peter Corke

1
Robotics, Vision and Control

isbn 978-3-642-20143-1

9 783642 201431

springer.com

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

Machine Vision Toolbox for MATLAB

R

3

Copyright c Peter Corke 2011

This toolbox considers images generally as arrays of double precision numbers. 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. Some particularly compute intensive functions are provided as mex-files and may need to be compiled for the particular platform. nearly 400 figures and 1000 code examples) of how to use the Toolbox functions to solve many types of problems in robotics. is open-source. and I commend it to you. 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. This is extravagant on storage.MATLAB compiler available then this can be used to compile bottleneck functions. However the book “Robotics. R R Machine Vision Toolbox for MATLAB R 4 Copyright c Peter Corke 2011 . contains many functions that are useful for image feature extraction and control. It was developed under Unix and Linux systems and some functions rely on tools and utilities that exist only in that environment. This toolbox predates IPT by many years. Vision & Control” provides a detailed discussion (over 600 pages.

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

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

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

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

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

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

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

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

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 .

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

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

v + c = 0. Machine Vision Toolbox for MATLAB R 16 Copyright c Peter Corke 2011 . Camera.line Plot homogeneous lines on image plane C. C.hold Control hold on image plane graphics C.line(L) plots lines on the camera image plane which are defined by columns of L (3 × N ) considered as lines in homogeneous form: a.char Camera.hold(H) hold mode is set on if H is true (or > 0). Camera.ishold() returns true (1) if the camera’s image plane is in hold mode. otherwise false (0).figure() is the handle of the figure that contains the camera’s image plane graphics.u + b. 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. See also Camera. and off if H is false (or 0).CHAPTER 2. Camera.ishold Return image plane hold status H = C.hold() sets “hold on” for the camera’s image plane.figure Return figure handle H = C.

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

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

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

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 .

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

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

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

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

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

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

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

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

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

Int. pp. SurfPointFeature Machine Vision Toolbox for MATLAB R 30 Copyright c Peter Corke 2011 .CHAPTER 2. ScalePointFeature. You can download a SIFT implementation which this class can utilize.91-110. FUNCTIONS AND CLASSES Methods plot plot scale distance match ncc uv display char Plot feature position Plot feature scale Descriptor distance Match features Descriptor similarity Return feature coordinate Display value Convert value to string Properties u horizontal coordinate v vertical coordinate strength feature strength theta feature orientation [rad] scale feature scale descriptor feature descriptor (vector) index of image containing feature image id Properties of a vector of SiftCornerFeature objects are returned as a vector. vol. If F is a vector (N ×1) of SiftCornerFeature objects then F. 2004. Journal on Computer Vision.Lowe. • SiftCornerFeature objects can be used in vectors and arrays • The SIFT algorithm is patented and not distributed with this toolbox. D. See README. PointFeature.u is a 2×N matrix with each column the corresponding u coordinate. Notes • SiftCornerFeature is a reference object.60. See also isift. References “Distinctive image features from scale-invariant keypoints”.SIFT. Nov.

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

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

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

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

the number of iterations to run the simulation (500) . showing the target points and the camera The results structure contains time-history information about the image plane. showing the desired view (*) and the current view (o) Machine Vision Toolbox for MATLAB R 35 Copyright c Peter Corke 2011 . The camera view.2) niter eterm lambda ci depth .the side length of the target in world units (0. of 4-vector. showing the desired view (*) and the current view (o) 2. The camera view.gain. error norm.camera intrinsic structure (camparam) . The external view. error.a stopping criteria on feature error norm (0) . Jacobian condition number. camera pose.sph Implement spherical IBVS for point features results = sph(T) results = sph(T. defaults in parentheses: target size . from simulation ([]) SEE ALSO: ibvsplot SphericalCamera.depth of points to use for Jacobian. Two windows are shown and animated: 1. FUNCTIONS AND CLASSES SphericalCamera. can be scalar or diagonal 6 × 6 matrix (0. The params structure can be used to override simulation defaults by providing elements.CHAPTER 2.center of the target in world coords (0.0. The camera/robot is initially at pose T and is driven to the orgin.5) target center . params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. params) Simulate IBVS with for a square target comprising 4 points is placed in the world XY plane. Two windows are shown and animated: 1.sph2 Implement spherical IBVS for point features results = sph(T) results = sph(T. The camera/robot is initially at pose T and is driven to the orgin. scalar for If null take actual value all points. image plane size and desired feature locations.01) .

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

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

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

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

axis.com).CHAPTER 2. • The specified ‘resolution’ must match one that the camera is capable of.axis. Video AxisWebCamera. 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.AxisWebCamera Axis web camera constructor a = AxisWebCamera(url. Options ‘uint8’ ‘float’ ‘double’ ‘grey’ ‘gamma’. G ‘scale’. options) is an AxisWebCamera object that acquires images from an Axis Communications (www. Obtain an image of size S=[W H]. S Notes: Return image with uint8 pixels (default) Return image with float pixels Return image with double precision pixels Return greyscale image Apply gamma correction with gamma=G Subsample the image by S in both directions. 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 ‘resolution’.com) web camera. otherwise the result is not predictable. Machine Vision Toolbox for MATLAB R 40 Copyright c Peter Corke 2011 .

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

F. SiftPointFeature ScalePointFeature. A Indicate scale by a circle (default) Indicate scale by a translucent disk Color of circle or disk (default green) Transparency of disk.plot scale(options. SurfPointFeature. Options ‘circle’ ‘disk’ ‘color’. strength. ls) as above but the optional line style arguments ls are passed to plot. 0=transparent (default 0. See also PointFeature.CHAPTER 2.2) Machine Vision Toolbox for MATLAB R 84 Copyright c Peter Corke 2011 . scale) as above but with specified feature scale.plot scale(options) overlay a marker at the feature position. If F is a vector (N × 1) of ScalePointFeature objects then F. FUNCTIONS AND CLASSES Properties u horizontal coordinate v vertical coordinate strength feature strength scale feature scale descriptor feature descriptor (vector) Properties of a vector of ScalePointFeature objects are returned as a vector. ScalePointFeature. 1=opaque. v) is a point feature object with specified coordinates. f = ScalePointFeature(u. f = ScalePointFeature(u. strength) as above but with specified strength.ScalePointFeature Create a scale point feature object f = ScalePointFeature() is a point feature object with null parameters. C ‘alpha’. v. f = ScalePointFeature(u. v.plot scale Plot feature scale F. If F is a vector then each element is plotted.u is a 2 × N matrix with each column the corresponding point coordinate.

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. options) is a new tracker object. The elements of the cell array are the point features for the corresponding element of the image sequence. A vector of track history structures with elements id and uv which is the path of the feature.Tracker Create new Tracker object T = Tracker(im. M Search radius for feature in next frame (default 20) Maximum number of tracks (default 800) Similarity threshold (default 0.8) Write the frames as images into the folder M as with sequential filenames. A complete history of all tracks is maintained. N ‘thresh’. Options ‘radius’. im (HxWxS) is an image sequence and C (S × 1) is a cell array of vectors of PointFeature subclass objects. R ‘nslots’. Machine Vision Toolbox for MATLAB R 85 Copyright c Peter Corke 2011 . C.CHAPTER 2. See also PointFeature Tracker. T ‘movie’. 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. Methods plot tracklengths Plot all tracks Length of all tracks Properties track history A vector of structures.

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

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

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

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

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

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

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

and 22500 (444. since.) • These CMFs differ slightly from those of Stiles & Burch (1955). while Table I(5.3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps. FUNCTIONS AND CLASSES [k. Notes • Data from http://cvrl.5. See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation.5.3) of Wyszecki & Stiles (1982). • From Table I(5.CHAPTER 2.d1. rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m]. 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. As noted in footnote a on p. Notes • Is a MEX file.44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 . unlike the CIE 2 deg functions (which were reconstructed from chromaticity data).32). 19000 (526.16).3) of Wyszecki & Stiles (1982). (Table 1(5.5.ac.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. The data are referred to as pilot data.5.ioo.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers. rgb = cmfrgb(lambda.d2] = closest(a. the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645.ucl. they were measured directly. If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda. but probably represent the best estimate of the 2 deg CMFs. 335 of Table 1(5.

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

CHAPTER 2. Perceptually uniform spaces such as Lab remedy this problem. • Note that Euclidean distance in the rg-chromaticity space does not correspond well with human perception of color differences. d is an image with the same dimensions as im and the value of each pixel is the color space distance of the corresponding pixel in im.g] to every pixel in the color image im. 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 . colordistance Colorspace distance d = colordistance(im. FUNCTIONS AND CLASSES See also im2col colnorm Column-wise norm of a matrix cn = colnorm(a) returns an M × 1 vector of the normals of each column of the matrix a which is N × M .

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

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

s = ‘src->dest’. s = ‘dest<-src’. FUNCTIONS AND CLASSES • Based on the standard X11 color database rgb. • Tristimulus values are in the range 0 to 1 colorspace Color space conversion of image out = colorspace(s. colorspace(s. Input and output images have 3 planes. As MATLAB’s native datatype.i3) as above but specifies separate input channels.i2. [o1. and uint8 data with integer-valued intensities from 0 to 255.709 gamma-corrected) Luma (ITU-R BT.CHAPTER 2. • Color space names are case insensitive.o3] = colorspace(s. im) converts the image im to a different color space according to the string s which specifies the source and destination color spaces. or alternatively. • MATLAB uses two standard data formats for R’G’B’: double data with intensities in the range 0 to 1. it can be omitted. double data is the natural choice. and R Machine Vision Toolbox for MATLAB 98 Copyright c Peter Corke 2011 . • When R’G’B’ is the source or destination.txt. i1.601) + Chroma Luma + Chroma (“digitized” version of Y’PbPr) NTSC PAL Y’UV Luma + Chroma NTSC Y’IQ Luma + Chroma SECAM Y’DbDr Luma + Chroma JPEG-Y’CbCr Luma + Chroma Hue Saturation Value/Brightness Hue Saturation Luminance/Intensity CIE XYZ CIE L*a*b* (CIELAB) CIE L*u*v* (CIELUV) CIE L*ch (CIELCH) Notes • RGB input is assumed to be gamma encoded • RGB output is gamma encoded • All conversions assume 2 degree observer and D65 illuminant. Supported color spaces are: ‘RGB’ ‘YPbPr’ ‘YCbCr’/’YCC’ ‘YUV’ ‘YIQ’ ‘YDbDr’ ‘JPEGYCbCr’ ‘HSV’/’HSB’ ‘HSL’/’HLS’/’HSI’ ‘XYZ’ ‘Lab’ ‘Luv’ ‘Lch’ R’G’B’ Red Green Blue (ITU-R BT. For example ‘yuv<’ is short for ‘yuv<-rgb’.o2. im) as above but specifies separate output channels or planes.

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

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

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

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

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

invhomog. p) applies homogeneous transformation T to the points stored columnwise in p.csse. p2) is the homography (3 × 3) that relates two sets of corresponding points p1 (2×N ) and p2 (2×N ) from two different camera views of a planar object. http://www.edu. Notes • The points must be corresponding.CHAPTER 2. See also ransac. • 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 . FUNCTIONS AND CLASSES homography Estimate homography H = homography(p1.au/. Author Based on homography code by Peter Kovesi. The University of Western Australia.uwa. School of Computer Science & Software Engineering. fmatrix homtrans Apply a homogeneous transformation p2 = homtrans(T. no outlier rejection is performed. • The points must be projections of points lying on a world plane • Contains a RANSAC driver. which means it can be passed to ransac().

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

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

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

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

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

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

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

CHAPTER 2. The PointFeature object has many properties including: u v strength descriptor horizontal coordinate vertical coordinate corner strength corner descriptor (vector) Options ‘cmin’. D ‘k’. specify that im is a color image not a sequence Notes • Corners are processed in order from strongest to weakest. If im is an image sequence a cell array of PointFeature vectors is returned. • 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. E ‘suppress’. ‘noble’ or ‘klt’ kernel width for smoothing (default 2) kernel for gradient (default kdgauss(2)) set the value of k for Harris detector use a P × P patch of surrounding pixel values as the feature vector. The vector has zero mean and unit norm. CM ‘cminthresh’. options) is a vector of PointFeature objects describing detected corner features. 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). S ‘deriv’. D ‘sigma’. CT ‘edgegap’. R ‘nfeat’. N ‘detector’. FUNCTIONS AND CLASSES icorner Corner detector f = icorner(im. This is a non-scale space detector and by default the Harris method is used. • If im is NxMx3 it is taken as a sequence unless the option ‘color’ is given Machine Vision Toolbox for MATLAB 112 R Copyright c Peter Corke 2011 . K ‘patch’.

• The descriptor is a vector of float types to save space References • “A combined corner and edge detector”. May 1988. vol. Fourth Alvey Vision Conf. Tomasi. 593-593.Noble.G. p2. show the points p1 and p2 at each iteration. • “Good features to track”. where * denotes squared and smoothed. Proc. pp.05 rad) stop after N iterations (default 100) stop when the relative change in error norm is less than T (default 0. 1988. Options ‘dplot’. J. J. isurf icp Point cloud alignment T = icp(p1. Image and Vision Computing. T ‘maxiter’. d ‘plot’ ‘maxtheta’. 1994.001) eliminate correspondences more than T x the median distance at each iteration. limit the change in rotation at each step to T (default 0. T show the points p1 and p2 at each iteration. pp 147-151. Computer Vision and Pattern Recognition.5 [sec].. Proc.J. pp. • “Finding corners”. Harris and M. [T. Manchester. See also PointFeature. options) as above but also returns the norm of the error between the transformed point set p2 and p1. T ‘distthresh’. with a delay of d [sec].6.121-128. Machine Vision Toolbox for MATLAB 113 R Copyright c Peter Corke 2011 . Shi and C. • The default descriptor is a vector [Ix* Iy* Ixy*] which are the unique elements of the structure tensor. C. N ‘mindelta’. p2. options) is the homogeneous transformation that best transforms the set of points p2 to p1 using the iterative closest point algorithm.d] = icp(p1. IEEE Computer Society. Stephens. FUNCTIONS AND CLASSES • If im is NxMx3xP it is taken as a sequence of color images and f is a cell array whose elements are feature vectors for the corresponding color image in the sequence.CHAPTER 2. with a delay of 0.

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

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

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

All pixels are raised to the power gamma. gamma) is a gamma corrected version of im.45. • Gamma decoding is typically performed in the display with gamma=2. FUNCTIONS AND CLASSES iendpoint Find end points in a binary skeleton image out = iendpoint(im) is a binary image where pixels are set if the corresponding pixel in the binary image im is the end point of a single-pixel wide line such as found in an image skeleton. • For images with multiple planes the gamma correction is applied to all planes. See also itriplepoint. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 . • For images of type double the pixels are assumed to be in the range 0 to 1. ithin. Notes • Gamma encoding is typically performed in a camera with gamma=0.2. hitormiss igamma correction out = igamma(im. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1. • For images of type int the pixels are assumed in the range 0 to max integer value.CHAPTER 2. ‘sRGB’) is a gamma decoded version of im using the sRGB decoding function (JPEG images sRGB encoded). Computed using the hit-or-miss morphological operator. out = igamma(im.

idisp(im) Reference “Efficient graph-based image segmentation”. Huttenlocher. k is the scale parameter. L is an image of the same size as im where each element is the label assigned to the corresponding pixel in im. Int. See also ithresh. min.m] = igraphseg(im.m] = igraphseg(im. k. sigma) as above but m is the number of regions found. 2006. 59. [L. L = igraphseg(im. FUNCTIONS AND CLASSES igraphseg Graph-based segmentation L = igraphseg(im. 1500. Sept. and a larger value indicates a preference for larger regions.jpg’).5). 0.5). Notes • Is a MEX file Author Pedro Felzenszwalb. P. sigma) as above and sigma is the width of a Gaussian which is used to initially smooth the image (default 0. k. imser Machine Vision Toolbox for MATLAB 118 R Copyright c Peter Corke 2011 . min) is a graph-based segmentation of the greyscale or color image im. pp. 167181. 100. Journal on Computer Vision. min is the minimum region size (pixels). Felzenszwalb and D. vol. [l. Example im = iread(’58060.CHAPTER 2. min. k. 2004.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

• For a floating point class image the slider range is 0 to 1. • For a uint8 class image the slider range is 0 to 255.0 See also idisp itrim Trim images [out1. a higher value will include fewer NaN value in the result. FUNCTIONS AND CLASSES ithresh Interactive image threshold ithresh(im) displays the image im in a window with a slider which adjusts the binary threshold. See also homwarp. a lower value will include more. ithresh(im.CHAPTER 2. T) as above but the initial threshold is set to T. [out1.5.out2] = itrim(im1. It assumes that the undefined pixels in im1 and im2 have values of NaN. This function crops out the central rectangular region of each. The default is 0. When images are rectified or warped the shapes can become quite distorted and are embedded in rectangular images surrounded by black of NaN values.im2. Notes • Greyscale image only.im2) returns the central parts of images im1 and im2 as out1 and out2 respectively.out2] = itrim(im1. The same cropping is applied to each input image. irectify Machine Vision Toolbox for MATLAB 144 R Copyright c Peter Corke 2011 .T) as above but the threshold T in the range 0 to 1 is used to adjust the level of cropping.

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

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

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

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

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

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. C) is similar to above but the clustering step is not performed.CHAPTER 2. k. k. 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. it is assumed to have been completed previously. Pattern Recognition Principles. c0) as above but the initial clusters c0 (D × k) is given and column I is the initial estimate of the centre of cluster I. L = kmeans(x.C] = kmeans(x. [L. C (D × k) contains the cluster centroids and L (N × 1) indicates which cluster the corresponding element of x is closest to. The data is organized into k clusters based on Euclidean distance from cluster centres C (D × k). and D is the dimension. FUNCTIONS AND CLASSES kmeans K-means clustering [L. options) is k-means clustering of multi-dimensional data points x (D × N ) where N is the number of points. L is a vector (N ×1) whose elements indicates which cluster the corresponding element of x belongs to.C] = kmeans(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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

resid] = ransac(func. T. T. N ‘maxDataTrials’. T. x typically contains corresponding point data. ransac classifies Points that support the model as inliers and those that do not as outliers. one column per point pair.in] = ransac(func. x. Options ‘maxTrials’. See also linspace ransac Random sample and consensus m = ransac(func. [m. if the fit residual is aboe the the threshold the point is considered an outlier. ransac determines the subset of points (inliers) that best fit the model described by the function func and the parameter m.in. options) is the ransac algorithm that robustly fits data x to the model represented by the function func. options) as above but returns the final residual of applying func to the inlier set. options) as above but returns the vector in of column indices of x that describe the inlier point set. d) as above but elements increment by d. FUNCTIONS AND CLASSES ramp create a ramp vector ramp(n) output a vector of length n that ramps linearly from 0 to 1 ramp(v) as above but vector is same length as v ramp(v. [m. 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 . x. T is a threshold on how well a point fits the estimated.CHAPTER 2. x.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

CHAPTER 2. FUNCTIONS AND CLASSES

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

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

See also
upq, mpq poly, npq poly

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

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

Machine Vision Toolbox for MATLAB 185

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

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

See also
skew

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

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

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

Machine Vision Toolbox for MATLAB 186

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

See also
rg addticks

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

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

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

See also
ilog

Machine Vision Toolbox for MATLAB 187

R

Copyright c Peter Corke 2011

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

isimilarity Machine Vision Toolbox for MATLAB 189 R Copyright c Peter Corke 2011 . 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. The result m is a scalar that indicates image similarity. See also sdd. sad. a value of 0 indicates identical pixel patterns and is increasingly positive as image dissimilarity increases.CHAPTER 2. Notes • The zssd similarity measure is invariant to changes in image brightness offset.