The template update problem
Top Cited Papers
- 19 April 2004
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 26 (6) , 810-815
- https://doi.org/10.1109/tpami.2004.16
Abstract
Template tracking dates back to the 1981 Lucas-Kanade algorithm. One question that has received very little attention, however, is how to update the template so that it remains a good model of the tracked object. We propose a template update algorithm that avoids the "drifting" inherent in the naive algorithm.Keywords
This publication has 8 references indexed in Scilit:
- Equivalence and efficiency of image alignment algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Active Appearance Models RevisitedInternational Journal of Computer Vision, 2004
- Lucas-Kanade 20 Years On: A Unifying FrameworkInternational Journal of Computer Vision, 2004
- Robust full-motion recovery of head by dynamic templates and re-registration techniquesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Active appearance modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2001
- Efficient region tracking with parametric models of geometry and illuminationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1998
- EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based RepresentationInternational Journal of Computer Vision, 1998
- A bootstrapping algorithm for learning linear models of object classesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1997