articleIEEE Transactions on Pattern Analysis and Machine IntelligenceSep 30, 2003Closed access

Robust online appearance models for visual tracking

ADAllan D. JepsonDJDavid J. FleetTEThomas El-Maraghi

University of Toronto · Palo Alto Research Center

Indexed incrossref

Abstract

We propose a framework for learning robust, adaptive, appearance models to be used for motion-based tracking of natural objects. The model adapts to slowly changing appearance, and it maintains a natural measure of the stability of the observed image structure during tracking. By identifying stable properties of appearance, we can weight them more heavily for motion estimation, while less stable properties can be proportionately downweighted. The appearance model involves a mixture of stable image structure, learned over long time courses, along with two-frame motion information and an outlier process. An online EM-algorithm is used to adapt the appearance model parameters over time. An implementation of this…

Citation impact

926
total citations
FWCI
30.69
Percentile
100%
References
32
Citations per year

Authors

3

Topics & keywords

Topics
Keywords
  • Artificial intelligence
  • Computer vision
  • Active appearance model
  • Computer science
  • Robustness (evolution)
  • Outlier
  • Motion estimation
  • Pattern recognition (psychology)
No related works found for this paper.

Funding