<title> KLT:  Kanade-Lucas-Tomasi Feature Tracker </title>
<IMG SRC="http://www-cs.stanford.edu/gifs/line.blue3.gif" ALT="-----" width="500" height="6">
<h1> KLT:  An Implementation of the <br>
Kanade-Lucas-Tomasi Feature Tracker </h1>
<IMG SRC="http://www-cs.stanford.edu/gifs/line.blue3.gif" ALT="-----" width="500" height="6"><p>

KLT is an implementation, in the C programming language, of a feature 
tracker for the computer vision community.
The tracker is based on the early work of Lucas and Kanade [1], was developed fully by
Tomasi
and Kanade [2], and was explained clearly in the paper by
Shi
and Tomasi [3].  
Later, Tomasi proposed a slight modification which
makes the computation symmetric with respect to the two images -- the
resulting equation is  derived
in the unpublished note by myself 
[4].<p>

Briefly, good features are located by examining the minimum
eigenvalue of each 2 by 2 gradient matrix, and features are
tracked using a Newton-Raphson method of minimizing the difference
between the two windows.  
Multiresolution tracking allows for relatively large displacements between images. <p>

The affine computation that evaluates the consistency of features between 
non-consecutive frames [3] was implemented by Thorsten Thormaehlen several years 
after the original code and documentation were written.&nbsp; To use this 
feature, please see the comments and declarations in the source code.<p>

<ul>
<li> <a href="installation.html"> Obtaining and Installing the Code </a>
<li> <a href="user/index.html"> Tutorial / User's Manual </a>
<li> <a href="ref/index.html"> Reference Manual </a>
<li> <a href="log.html"> Log of Changes </a>

</ul>

<p><i>Note:&nbsp; KLT is now in the public domain.&nbsp;  Stanford's 
Office of Technology Licensing has removed the non-commercial restriction.</i></p>

<hr>
<h1> References </h1>
<dl>
<dt> [1] Bruce D. Lucas and Takeo Kanade.
	<b> <a href="lucas_bruce_d_1981_1.pdf">An Iterative Image Registration Technique with an
              Application to Stereo Vision.</a> </b>
	International Joint Conference on Artificial Intelligence,
	pages 674-679, 1981.<p>

<dt> [2] Carlo Tomasi and Takeo Kanade.  
	<b> <a href="tomasi-kanade-techreport-1991.pdf">Detection and Tracking of Point Features.</a> </b>
	Carnegie Mellon University Technical Report CMU-CS-91-132,
	April 1991.<p>

<dt> [3] Jianbo Shi and Carlo Tomasi.
<a href="shi-tomasi-good-features-cvpr1994.pdf">
     <b> Good Features to Track</b></a>.
	IEEE Conference on Computer Vision and Pattern Recognition,
	pages 593-600, 1994.<p>

<dt> [4] Stan Birchfield.
     <b> <a href="birchfield-klt-derivation.pdf">Derivation of Kanade-Lucas-Tomasi 
Tracking Equation</a>. </b> Unpublished, May 1996.
</dl>
<P>
<HR>
<a href="http://www.ces.clemson.edu/~stb">Stan Birchfield</a></p>