KLT: An Implementation of the Kanade-Lucas-Tomasi Feature Tracker

Note: You are looking at a local copy. There is also an official, updated version.

KLT is an implementation, in the C programming language, of a feature tracker that will hopefully be of interest to the computer vision community. The tracker is based on the early work of Lucas and Kanade [1] and was developed fully by Tomasi and Kanade [2], but the only published, readily accessible description is contained in the paper by Shi and Tomasi [3]. Recently, Tomasi proposed a slight modification which makes the computation symmetric with respect to the two images; the resulting equation is fully derived in the unpublished note by Birchfield [4].

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 even large displacements between images. Currently, the affine computation that evaluates the consistency of features between non-consecutive frames [3] is not implemented.

References

[1] Bruce D. Lucas and Takeo Kanade. An Iterative Image Registration Technique with an Application to Stereo Vision. International Joint Conference on Artificial Intelligence, pages 674-679, 1981.
[2] Carlo Tomasi and Takeo Kanade. Detection and Tracking of Point Features. Carnegie Mellon University Technical Report CMU-CS-91-132, April 1991.
[3] Jianbo Shi and Carlo Tomasi. Good Features to Track. IEEE Conference on Computer Vision and Pattern Recognition, pages 593-600, 1994.
[4] Stan Birchfield. Derivation of Kanade-Lucas-Tomasi Tracking Equation. Unpublished, May 1996.

Last updated by Stan Birchfield on March 11, A. D. 1998
birchfield@cs.stanford.edu