Lucas-Kanade tracker
(Difference between revisions)
m |
m |
||
Line 4: | Line 4: | ||
<embed style="width:320px; height:236px;" id="VideoPlayback" type="application/x-shockwave-flash" src="http://vision.eng.shu.ac.uk/jan/foodautomation/flvplayer.swf" width="320" height="236" flashvars="file=http://vision.eng.shu.ac.uk/jan/flv/lucaskanade.flv&image=http://vision.eng.shu.ac.uk/jan/flv/lucaskanade.jpg&displayheight=236" pluginspage="http://www.macromedia.com/go/getflashplayer"/> | <embed style="width:320px; height:236px;" id="VideoPlayback" type="application/x-shockwave-flash" src="http://vision.eng.shu.ac.uk/jan/foodautomation/flvplayer.swf" width="320" height="236" flashvars="file=http://vision.eng.shu.ac.uk/jan/flv/lucaskanade.flv&image=http://vision.eng.shu.ac.uk/jan/flv/lucaskanade.jpg&displayheight=236" pluginspage="http://www.macromedia.com/go/getflashplayer"/> | ||
<div class="thumbcaption">Tracking 2-D affine transforms of a texture patch using Lucas-Kanade</div></div></div></html> | <div class="thumbcaption">Tracking 2-D affine transforms of a texture patch using Lucas-Kanade</div></div></div></html> | ||
+ | |- | ||
+ | |<html><div class="thumb tright"><div style="width:320px;"> | ||
+ | <embed style="width:320px; height:240px;" id="VideoPlayback" type="application/x-shockwave-flash" src="http://vision.eng.shu.ac.uk/jan/foodautomation/flvplayer.swf" width="320" height="240" flashvars="file=http://vision.eng.shu.ac.uk/jan/flv/tip10lk.flv&image=http://vision.eng.shu.ac.uk/jan/flv/tip10lk.jpg&displayheight=240" pluginspage="http://www.macromedia.com/go/getflashplayer"/> | ||
+ | <div class="thumbcaption">Tracking of a nano-indenter in a TEM-video</div></div></div></html> | ||
|- | |- | ||
|} | |} |
Revision as of 22:55, 18 January 2008
The Lucas-Kanade algorithm iteratively tries to minimise the difference between the image and a warped template. The technique can be used for image alignment, tracking, optic flow analysis, and motion estimation. In this example a texture patch in a Space Shuttle video is tracked over 324 frames. A 2-D affine transform was used as a model.
For the documentation of the mathematics have a look at the web-page of the CMU-project "Lucas-Kanade 20 years on" and at the publication by Baker and Matthews.
The implementation is available as an example application with HornetsEye. There also is a web-page with the source code of the Lucas-Kanade tracker.
See Also
External Links
- Hornetseye implementation
- CMU project: "Lucas-Kanade 20 years on"
- S. Baker, I. Matthews: Lucas-Kanade 20 Years On: A Unifying Framework, International Journal of Computer Vision, Vol. 56, No. 3, March, 2004, pp. 221-255.
- NASA high definition videos