An online motion-based particle filter for head tracking applications

The particle filtering framework has revolutionized probabilistic tracking of objects in a video sequence. In this framework, the proposal density can be any density as long as its support includes that of the posterior. However, in practice, the number of samples is finite and consequently the choice of the proposal is crucial to the effectiveness of the tracking. The CONDENSATION filter uses the transition prior as the proposal density. We propose in this paper a motion-based proposal. We use adaptive block matching (ABM) as the motion estimation technique. The benefits of this model are two fold. It increases the sampling efficiency and handles abrupt motion changes. Analytically, we derive a Kullback-Leibler (KL)-based performance measure and show that the motion proposal is superior to the proposal of the CONDENSATION filter. Our experiments are applied to head tracking. Finally, we report promising tracking results in complex environments.

[1]  B. Anderson,et al.  Optimal Filtering , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[2]  M. Tanner.  Tools for statistical inference: methods for the exploration of posterior distributions and likeliho , 1994 .

[3]  N. Gordon,et al.  Novel approach to nonlinear/non-Gaussian Bayesian state estimation , 1993 .

[4]  Jun S. Liu,et al.  Sequential Monte Carlo methods for dynamic systems , 1997 .

[5]  Simon J. Godsill,et al.  On sequential simulation-based methods for Bayesian filtering , 1998 .

[6]  Stanley T. Birchfield,et al.  Elliptical head tracking using intensity gradients and color histograms , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[7]  Larry S. Davis,et al.  W4: Real-Time Surveillance of People and Their Activities , 2000, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Simon J. Godsill,et al.  On sequential Monte Carlo sampling methods for Bayesian filtering , 2000, Stat. Comput..

[9]  Luc Van Gool,et al.  Object Tracking with an Adaptive Color-Based Particle Filter , 2002, DAGM-Symposium.

[10]  Éric Marchand,et al.  Virtual Visual Servoing: a framework for real‐time augmented reality , 2002, Comput. Graph. Forum.

[11]  Dan Schonfeld,et al.  Object tracking using adaptive block matching , 2003, 2003 International Conference on Multimedia and Expo. ICME '03. Proceedings (Cat. No.03TH8698).

[12]  Michael Isard,et al.  CONDENSATION—Conditional Density Propagation for Visual Tracking , 1998, International Journal of Computer Vision.

[13]  Dan Schonfeld,et al.  Fast object tracking using adaptive block matching , 2005, IEEE Transactions on Multimedia.

[14]  Volker Graefe,et al.  Applications of dynamic monocular machine vision , 1988, Machine Vision and Applications.

[15]  Éric Marchand,et al.  Real-time markerless tracking for augmented reality: the virtual visual servoing framework , 2006, IEEE Transactions on Visualization and Computer Graphics.