Online updating appearance generative mixture model for meanshift tracking

  • Authors:

  • Jilin Tu;Hai Tao;Thomas Huang

  • Affiliations:

  • University of Illinois at Urbana and Champaign, Electrical and Computer Engineering Department, 61801, Urbana, IL, USA;University of California, Department of Computer Engineering, 95064, Santa Cruz, CA, USA;University of Illinois at Urbana and Champaign, Electrical and Computer Engineering Department, 61801, Urbana, IL, USA

  • Venue:
  • Machine Vision and Applications
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper proposes an appearance generative mixture model based on key frames for meanshift tracking. Meanshift tracking algorithm tracks an object by maximizing the similarity between the histogram in tracking window and a static histogram acquired at the beginning of tracking. The tracking therefore could fail if the appearance of the object varies substantially. In this paper, we assume the key appearances of the object can be acquired before tracking and the manifold of the object appearance can be approximated by piece-wise linear combination of these key appearances in histogram space. The generative process is described by a Bayesian graphical model. An Online EM algorithm is proposed to estimate the model parameters from the observed histogram in the tracking window and to update the appearance histogram. We applied this approach to track human head motion and to infer the head pose simultaneously in videos. Experiments verify that our online histogram generative model constrained by key appearance histograms alleviates the drifting problem often encountered in tracking with online updating, that the enhanced meanshift algorithm is capable of tracking object of varying appearances more robustly and accurately, and that our tracking algorithm can infer additional information such as the object poses.