Adaptive Appearance Models for 2D Tracking
Research Overview
Allan Jepson, Thomas El-Maraghi (University of Toronto) and I have
developed an approach to learning 2D models of image appearance for
stable, accurate 2D tracking. The approach works with an online version
of the EM algorithm to identify stable image structure during tracking.
In this way the most stable regions can play the most significant role
in the tracking, to facilitate tracking over long image sequences with
precise image alignment. This work was awarded Runner-Up for the Best
Paper at the IEEE Conference on Compuer Vision and Pattern Recognition
in 2001.
Related Publications
- Jepson, A.D., Fleet, D.J. and El-Maraghi, T. (2001) Robust,
on-line appearance models for vision tracking.
IEEE Conference on Computer Vision and Pattern Recognition,
Kauai, Vol. I, pp. 415--422
[Runner-Up for best paper]
(pdf)
© IEEE
- Jepson, A.D., Fleet, D.J. and El-Maraghi, T. (2002) Robust,
online appearance models for visual tracking.
IEEE Transactions on Pattern Analysis and Machine Intelligence
25(10):1296-1311, 2003.
(abstract)
(pdf)
© IEEE
Return to David Fleet's home page.