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

Licence Toolbox home page Discussion group

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

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

Preface

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

Peter C0rke

Robotics,

Vision and Control

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

Corke

Robotics,

Vision and Control

Peter Corke

1

Robotics, Vision and Control

isbn 978-3-642-20143-1

9 783642 201431

›

springer.com

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

Machine Vision Toolbox for MATLAB

R

3

Copyright c Peter Corke 2011

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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 .

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

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

2003.H Homography matrix H = C.H(T. from two viewpoints. The ﬁrst view is from the current camera pose C.T and the second is after a relative motion represented by the homogeneous transformation T. J.F(T) is the fundamental matrix relating two camera views. F = C. n. The ﬁrst view is from the current camera pose C. Machine Vision Toolbox for MATLAB R 23 Copyright c Peter Corke 2011 . “An invitation to 3D”.E CentralCamera.Soatto.F(C2) is the fundamental matrix relating two camera views described by camera objects C (ﬁrst view) and C2 (second view).F Fundamental matrix F = C.Sastry.K() is the 3 × 3 intrinsic parameter matrix.Kosecka.Ma. See also CentralCamera. p.H CentralCamera. S. Reference Y.T and the second is a relative motion represented by the homogeneous transformation T. FUNCTIONS AND CLASSES CentralCamera.K Intrinsic parameter matrix K = C. Springer. S.CHAPTER 2.177 See also CentralCamera. d) is a 3 × 3 homography matrix for the camera observing the plane with normal n and at distance d.

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

J. p120122 Notes • The transformation is from view 1 to view 2. 259 Y. s. 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. 2003.Sastry.CHAPTER 2. p116. In practice there are multiple solutions and s is a vector of structures with elements: • T. Reference Hartley & Zisserman. See also CentralCamera. FUNCTIONS AND CLASSES s = C. p.Sastry. Chap 9.3 Machine Vision Toolbox for MATLAB R 25 Copyright c Peter Corke 2011 . “An invitation to 3D”.Kosecka. “An invitation to 3D”.invE(E. J.Ma.Soatto. Springer. camera motion as a homogeneous transform matrix (4 × 4). Reference Y. p) as above but only solutions in which the world point p is visible are returned. s.Ma.E CentralCamera. s.invH Decompose homography matrix s = C. Springer.Kosecka. section 5. 2003. s.Soatto. “Multiview Geometry”.invH(H) decomposes the homography H (3 × 3) into the camera motion and the normal to the plane. translation not to scale • n.

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

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

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

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

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

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

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

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

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

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

gain. The Jacobian gives the image-plane velocity in terms of camera spatial velocity. defaults in parentheses: target size .01) . The params structure can be used to override simulation defaults by providing elements.visjac p Visual motion Jacobian for point feature J = C. I. P. or a vector (N × 1) for each point. CentralCamera. FUNCTIONS AND CLASSES 2. Reference “Spherical image-based visual servo and structure estimation”. IEEE Int. camera pose. May 3-7 2010. Corke. in Proc. error norm.the side length of the target in world units (0. See also CentralCamera. from simulation ([]) SEE ALSO: ibvsplot SphericalCamera.5) target center .visjac l.the number of iterations to run the simulation (500) . can be scalar or diagonal 6 × 6 matrix (0.3) niter eterm lambda ci depth . The depth of the points from the camera is given by z which is a scalar.visjac p polar. z) is the image Jacobian (2N × 6) for the image plane points pt (2 × N ) described by phi (longitude) and theta (colatitude). (Anchorage). CentralCamera. image plane size and desired feature locations. for all points.visjac e Machine Vision Toolbox for MATLAB R 36 Copyright c Peter Corke 2011 . Conf.center of the target in world coords (0. scalar for If null take actual value all points.camera intrinsic structure (camparam) . 5550-5555. The external view. Jacobian condition number. error. showing the target points and the camera The results structure contains time-history information about the image plane.CHAPTER 2. pp.0.a stopping criteria on feature error norm (0) .depth of points to use for Jacobian. of 4-vector.visjac p(pt. Robotics and Automation.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

T ‘Tcam’.project(p.CHAPTER 2. Temporarily overrides the current camera pose C. Options ‘Tobj’. SphericalCamera FishEyeCamera. The columns of p (3 × N ) are the world points and the columns of uv (2 × N ) are the corresponding image plane points. 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 . For every edge pixel in the input image a set of cells in the Hough accumulator (voting array) are incremented. 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. options) are the image plane coordinates for the world points p. T Transform all points by the homogeneous transformation T before projecting them to the camera image plane.T. See also FishEyeCamera.plot Hough Hough transform class The Hough transform is a technique for ﬁnding lines in an image using a voting scheme. See also Camera. CatadioptricCamera.project Project world points to image plane uv = C. Set the camera pose to the homogeneous transformation T before projecting points to the camera image plane.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

16). 335 of Table 1(5. As noted in footnote a on p. FUNCTIONS AND CLASSES [k. unlike the CIE 2 deg functions (which were reconstructed from chromaticity data). they were measured directly. • From Table I(5. See also distance cmfrgb Color matching function Tthe color matching function is the tristimulus required to match a particular wavelength excitation. while Table I(5. rgb = cmfrgb(lambda) is the CIE color matching function (N × 3) for illumination at wavelength lambda (N × 1) [m].5.3) of Wyszecki & Stiles (1982). Notes • Data from http://cvrl. but probably represent the best estimate of the 2 deg CMFs. the CMFs have been ”corrected in accordance with instructions given by Stiles & Burch (1959)” and renormalized to primaries at 15500 (645.ioo.5. and 22500 (444.d2] = closest(a.uk • The Stiles & Burch 2-deg CMFs are based on measurements made on 10 observers. rgb = cmfrgb(lambda. (Table 1(5.3) of Wyszecki & Stiles (1982) is gives them in interpolated 1 nm steps. 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].ac.) • These CMFs differ slightly from those of Stiles & Burch (1955).32).3) of Wyszecki & Stiles (1982) gives the Stiles & Burch functions in 250 cm-1 steps.ucl.d1. Notes • Is a MEX ﬁle.5. b) as above but also returns the distance to the second closest point.5.3) of Wyszecki & Stiles (1982). If lambda is a vector then each row of rgb is the color matching function of the corresponding element of lambda. 19000 (526.CHAPTER 2. The data are referred to as pilot data.44) cm-1 Machine Vision Toolbox for MATLAB R 93 Copyright c Peter Corke 2011 . since.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Create an aqua tinted version of the greyscale image c = icolor(im. [0 1 1]). D ‘bgval’. B direction of concatenation: ‘horizontal’ (default) or ‘vertical’. and smaller images are surrounded by background pixels which can be speciﬁed. 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. ipixswitch iconcat Concatenate images C = iconcat(im.CHAPTER 2. FUNCTIONS AND CLASSES icolor Colorize a greyscale image C = icolor(im) is a color image C (HxWx3)where each color plane is equal to im (H × W ). color) as above but each output pixel is color (3 × 1) times the corresponding element of im. iconcat(im.options) concatenates images from the cell array im.options) as above but also returns the vector u whose elements are the coordinates of the left (or top in vertical mode) edge of the corresponding image. Options ‘dir’. C = icolor(im. colorize.options) as above but displays the concatenated images using idisp. value of unset background pixels Machine Vision Toolbox for MATLAB 110 R Copyright c Peter Corke 2011 . See also imono. [C.u] = iconcat(im.

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

D ‘k’. P ‘color’ minimum corner strength minimum corner strength as a fraction of maximum corner strength don’t return features closer than E to the edge of image (default 2) don’t return a feature closer than R pixels to an earlier feature (default 0) return the N strongest corners (default Inf) choose the detector where D is one of ‘harris’ (default). The PointFeature object has many properties including: u v strength descriptor horizontal coordinate vertical coordinate corner strength corner descriptor (vector) Options ‘cmin’. N ‘detector’. K ‘patch’. options) is a vector of PointFeature objects describing detected corner features. D ‘sigma’. specify that im is a color image not a sequence Notes • Corners are processed in order from strongest to weakest. CM ‘cminthresh’. FUNCTIONS AND CLASSES icorner Corner detector f = icorner(im. E ‘suppress’. • 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. If im is an image sequence a cell array of PointFeature vectors is returned. The vector has zero mean and unit norm. CT ‘edgegap’. ‘noble’ or ‘klt’ kernel width for smoothing (default 2) kernel for gradient (default kdgauss(2)) set the value of k for Harris detector use a P × P patch of surrounding pixel values as the feature vector.CHAPTER 2. S ‘deriv’. • 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 . This is a non-scale space detector and by default the Harris method is used. R ‘nfeat’.

isurf icp Point cloud alignment T = icp(p1. See also PointFeature.05 rad) stop after N iterations (default 100) stop when the relative change in error norm is less than T (default 0. where * denotes squared and smoothed.d] = icp(p1. 593-593. limit the change in rotation at each step to T (default 0.001) eliminate correspondences more than T x the median distance at each iteration. with a delay of 0. Proc. pp. Proc. Tomasi. 1994.CHAPTER 2. • The descriptor is a vector of ﬂoat types to save space References • “A combined corner and edge detector”. pp 147-151. Image and Vision Computing. 1988. • The default descriptor is a vector [Ix* Iy* Ixy*] which are the unique elements of the structure tensor.G. J. [T. Manchester. C. Fourth Alvey Vision Conf. N ‘mindelta’. T ‘distthresh’. • “Finding corners”. 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. T ‘maxiter’. options) as above but also returns the norm of the error between the transformed point set p2 and p1. pp.Noble.6. Stephens. options) is the homogeneous transformation that best transforms the set of points p2 to p1 using the iterative closest point algorithm. d ‘plot’ ‘maxtheta’. p2.. Harris and M. Options ‘dplot’. Computer Vision and Pattern Recognition. • “Good features to track”. with a delay of d [sec]. Shi and C.121-128. T show the points p1 and p2 at each iteration. p2. vol. show the points p1 and p2 at each iteration.J. IEEE Computer Society.5 [sec]. May 1988. J. Machine Vision Toolbox for MATLAB 113 R Copyright c Peter Corke 2011 .

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

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

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

• For images of type double the pixels are assumed to be in the range 0 to 1. gamma) is a gamma corrected version of im. Notes • Gamma encoding is typically performed in a camera with gamma=0. • For images with multiple planes the gamma correction is applied to all planes.CHAPTER 2.45. All pixels are raised to the power gamma. Computed using the hit-or-miss morphological operator. hitormiss igamma correction out = igamma(im. 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. Machine Vision Toolbox for MATLAB 117 R Copyright c Peter Corke 2011 . ‘sRGB’) is a gamma decoded version of im using the sRGB decoding function (JPEG images sRGB encoded). See also itriplepoint. Gamma encoding can be performed with gamma > 1 and decoding with gamma < 1. • Gamma decoding is typically performed in the display with gamma=2. • For images of type int the pixels are assumed in the range 0 to max integer value. out = igamma(im. ithin.2.

jpg’).CHAPTER 2. Sept. 2006. sigma) as above and sigma is the width of a Gaussian which is used to initially smooth the image (default 0. See also ithresh. sigma) as above but m is the number of regions found. pp. min is the minimum region size (pixels). k.m] = igraphseg(im. P. 100. [l.5). 0. vol. min) is a graph-based segmentation of the greyscale or color image im. [L. Felzenszwalb and D. Int. Notes • Is a MEX ﬁle Author Pedro Felzenszwalb. idisp(im) Reference “Efﬁcient graph-based image segmentation”. 1500. Example im = iread(’58060. Huttenlocher. k is the scale parameter. L = igraphseg(im. 59. min. L is an image of the same size as im where each element is the label assigned to the corresponding pixel in im. FUNCTIONS AND CLASSES igraphseg Graph-based segmentation L = igraphseg(im. 2004. k.m] = igraphseg(im. k. Journal on Computer Vision. and a larger value indicates a preference for larger regions. 167181.5). min. imser Machine Vision Toolbox for MATLAB 118 R Copyright c Peter Corke 2011 .

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

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

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

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

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

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

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

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

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

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

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

Notes • Works for greyscale images only. op. ones(5. The pyramid is computed down to a nonhalvable image size. See also iscalespace. Only pixels corresponding to non-zero elements of the structuring element se are ranked and the order’th value in rank becomes the corresponding output pixel value. se.3). sigma. im > irank(im. nbins) as above but the number of histogram bins can be speciﬁed. ismooth irank Rank ﬁlter out = irank(im. FUNCTIONS AND CLASSES dimensions half that of the previous image. order. out = imorph(image. out = ipyramid(im. se(2. edge) as above but the processing of edge pixels can be controlled. 1.2) = 0. 3 × 3 non-local maximum: se = ones(3. hence output image had reduced dimensions. The highest rank. se). idecimate. se. sigma) as above but the Gaussian standard deviation is sigma. is order=1. Machine Vision Toolbox for MATLAB 130 R Copyright c Peter Corke 2011 . 12. out = ipyramid(im. n) as above but only n levels of the pyramid are computed.CHAPTER 2. the image is assumed to wrap around Examples 5 × 5 median ﬁlter: irank(im. se) is a rank ﬁltered version of im. the maximum. out = imorph(image.5)). op. nbins. 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.

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

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

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

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

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

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

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

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

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

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

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

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

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

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

that is where three single-pixel wide line intersect. ithin. 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. the image is assumed to wrap around Notes • Is a MEX ﬁle. hence output image had reduced dimensions. 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. edge) as above but performance at edge pixels can be controlled.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. op. Computed using the hit-or-miss morphological operator. The value of edge is: ‘border’ ‘none’ ‘trim’ ‘wrap’ the border value is replicated (default) pixels beyond the border are not included in the window output is not computed for pixels whose window crosses the border. See also iendpoint. Machine Vision Toolbox for MATLAB 145 R Copyright c Peter Corke 2011 . These are the Voronoi points in an image skeleton. op) is an image where each output pixel is the speciﬁed statistic over the pixel neighbourhood indicated by the structuring element se which should have odd side lengths. hitormiss ivar Pixel window statistics out = ivar(im. se. se.

The return value becomes the corresponding pixel value in out.CHAPTER 2. 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 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. se. The neighbourhood is deﬁned by the size of the structuring element se which should have odd side lengths. out = iwindow(image. se. ones(3.3). @std). func. @max). edge) as above but performance of edge pixels can be controlled. Compute the standard deviation over a 3 × 3 window: 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. • Is slow since the function func must be invoked once for every output pixel. irank Machine Vision Toolbox for MATLAB 146 R Copyright c Peter Corke 2011 . See also ivar. the image is assumed to wrap around Example Compute the maximum value over a 5 × 5 window: iwindow(im. ones(5. FUNCTIONS AND CLASSES See also irank. Notes • Is a MEX ﬁle.5). hence output image had reduced dimensions. iwindow iwindow Generalized spatial operator out = iwindow(im.

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

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

and W=2 × H+1. iconv.CHAPTER 2. zcross Machine Vision Toolbox for MATLAB 149 R Copyright c Peter Corke 2011 . iconv klog Laplacian of Gaussian kernel k = klog(sigma) is a 2-dimensional Laplacian of Gaussian kernel of width (standard deviation) sigma and centred within the matrix k whose half-width is H=3 × sigma. 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. H) as above but the half-width H is speciﬁed. See also kgauss. k = klog(sigma. See also ilaplace. kdog. kdgauss.

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

CHAPTER 2. FUNCTIONS AND CLASSES

See also

isobel

ktriangle

Triangular kernel

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

Examples

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

See also

kcircle

lambda2rg

RGB chromaticity coordinates

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

Machine Vision Toolbox for MATLAB 151

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

See also

cmfrgb, lambda2xy

lambda2xy

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

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

See also

cmfxyz, lambda2rg

loadspectrum

Load spectrum data

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

Notes

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

Machine Vision Toolbox for MATLAB 152

R

Copyright c Peter Corke 2011

CHAPTER 2. FUNCTIONS AND CLASSES

luminos

Photopic luminosity function

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

See also

rluminos

maxﬁlt

maximum ﬁlter

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

medﬁlt1

Median ﬁlter

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

Notes

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

Machine Vision Toolbox for MATLAB 153

R

Copyright c Peter Corke 2011

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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