Tracking by parts: a Bayesian approach with component collaboration

  • Authors:

  • Wen-Yan Chang;Chu-Song Chen;Yi-Ping Hung

  • Affiliations:

  • Institute of Information Science, Academia Sinica, Taipei, Taiwan and Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan;Institute of Information Science, Academia Sinica, Taipei, Taiwan and Graduate Institute of Networking and Multimedia, National Taiwan University, Taipei, Taiwan;Dept. of Comp. Sci. and Inf. Eng., National Taiwan Univ., Taipei, Taiwan and the Graduate Ins. of Networking and Multimedia, National Taiwan Univ., Taipei, Taiwan and Inst. of Inf. Science, Academ ...

  • Venue:
  • IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

Instead of using global-appearance information for visual tracking, as adopted by many methods, we propose a tracking-by-parts (TBP) approach that uses partial appearance information for the task. The proposed method considers the collaborations between parts and derives a probability propagation framework by encoding the spatial coherence in a Bayesian formulation. To resolve this formulation, a TBP particle-filtering method is introduced. Unlike existing methods that only use the spatial-coherence relationship for particle-weight estimation, our method further applies this relationship for state prediction based on system dynamics. Thus, the part-based information can be utilized efficiently, and the tracking performance can be improved. Experimental results show that our approach outperforms the factored-likelihood and particle reweight methods, which only use spatial coherence for weight estimation.