This work will appear at CVPR 2010. More results can be found on my channel page. Please give me some feedback and rate or comment on these videos.
A copy of my paper can be obtained from my website:
D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. Visual Object Tracking using Adaptive Correlation Filters (includes supplemental material). Computer Vision and Pattern Recognition. June 2010.
Although not commonly used, correlation filters can track complex objects through rotations, occlusions and other distractions at over 20 times the rate of current state-of- the-art techniques. The oldest and simplest correlation filters use simple templates and generally fail when applied to tracking. More modern approaches such as ASEF and UMACE perform better, but their training needs are poorly suited to tracking. Visual tracking requires robust filters to be trained from a single frame and dynamically adapted as the appearance of the target object changes. The original data can be obtained through David Ross's websight: http://www.cs.toronto.edu/~dross/ivt/
This is a simple realtime person detector described in:
D. S. Bolme, Y. M. Lui, B. A. Draper, and J. R. Beveridge. Simple Real-Time Human Detection Using a Single Correlation Filter. Twelfth International Workshop on Performance Evaluation of Tracking and Surveillance. 2009.