This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Approximate Bayesian Multibody Tracking
September 2006 (vol. 28 no. 9)
pp. 1436-1449
Visual tracking of multiple targets is a challenging problem, especially when efficiency is an issue. Occlusions, if not properly handled, are a major source of failure. Solutions supporting principled occlusion reasoning have been proposed but are yet unpractical for online applications. This paper presents a new solution which effectively manages the trade-off between reliable modeling and computational efficiency. The Hybrid Joint-Separable (HJS) filter is derived from a joint Bayesian formulation of the problem, and shown to be efficient while optimal in terms of compact belief representation. Computational efficiency is achieved by employing a Markov random field approximation to joint dynamics and an incremental algorithm for posterior update with an appearance likelihood that implements a physically-based model of the occlusion process. A particle filter implementation is proposed which achieves accurate tracking during partial occlusions, while in cases of complete occlusion, tracking hypotheses are bound to estimated occlusion volumes. Experiments show that the proposed algorithm is efficient, robust, and able to resolve long-term occlusions between targets with identical appearance.

[1] O. Lanz and R. Manduchi, “Hybrid Joint-Separable Multibody Tracking,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2005.
[2] J. MacCormick and A. Blake, “Probabilistic Exclusion and Partitioned Sampling for Tracking Multiple Objects,” Int'l J. Computer Vision, vol. 39, no. 1, 2000.
[3] D. Tweed and A. Calway, “Tracking Many Objects Using Subordinated CONDENSATION,” Proc. British Machine Vision Conf., 2002.
[4] H. Tao, H.S. Sawhney, and R. Kumar, “A Sampling Algorithm for Detecting and Tracking Multiple Objects,” Proc. Vision Algorithms Workshop, 1999.
[5] K. Otsuka and N. Mukawa, “Multiview Occlusion Analysis for Tracking Densely Populated Objects Based on 2-D Visual Angles,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2004.
[6] B. Vo, S. Singh, and A. Doucet, “Sequential Monte Carlo Methods for Bayesian Multi-Target Filtering with Random Finite Sets,” IEEE Trans. Aerospace and Electronic Systems, vol. 41, no. 4, 2005.
[7] M. Isard and J. MacCormick, “BraMBle: A Bayesian Multiple-Blob Tracker,” Proc. Int'l Conf. Computer Vision, 2003.
[8] J. Sullivan, A. Blake, M. Isard, and J. MacCormick, “Bayesian Object Localisation in Images,” Int'l J. Computer Vision, vol. 44, no. 2, 2001.
[9] J. Vermaak, A. Doucet, and P. Perez, “Maintaining Multi-Modality through Mixture Tracking,” Proc. Int'l Conf. Computer Vision, 2001.
[10] Z. Khan, T. Balch, and F. Dellaert, “MCMC-Based Particle Filtering for Tracking a Variable Number of Interacting Targets,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 27, no. 11, Nov. 2005.
[11] T. Yu and Y. Wu, “Collaborative Tracking of Multiple Targets,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2005.
[12] J. Deutscher, A. Blake, and I. Reid, “Articulated Body Motion Capture by Annealed Particle Filtering,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2000.
[13] C. Sminchisescu and B. Triggs, “Fast Mixing Hyperdynamic Sampling,” J. Image and Vision Computing, vol. 24, no. 3, 2006.
[14] K. Choo and D. Fleet, “People Tracking with Hybrid Monte Carlo,” Proc. Int'l Conf. Computer Vision, 2001.
[15] J. Sullivan and J. Rittscher, “Guiding Random Particles by Deterministic Search,” Proc. Int'l Conf. Computer Vision, 2001.
[16] C. Sminchisescu and B. Triggs, “A Robust Multiple Hypothesis Approach to Monocular Human Motion Tracking,” Technical Report 4208, INRIA, 2001.
[17] M. Cover and J. Thomas, Elements of Information Theory. Wiley, 1991.
[18] J. Coughlan and S. Ferreira, “Finding Deformable Shapes Using Loopy Belief Propagation,” Proc. European Conf. Computer Vision, 2002.
[19] J. Sun, H. Shum, and N. Zheng, “Stereo Matching Using Belief Propagation,” Proc. European Conf. Computer Vision, 2002.
[20] L. Sigal, S. Bhatia, S. Roth, M. Black, and M. Isard, “Tracking Loose-Limbed People,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2004.
[21] E. Sudderth, M. Mandel, W. Freeman, and A. Willsky, “Distributed Occlusion Reasoning for Tracking with Nonparametric Belief Propagation,” Advances in Neural Information Processing Systems, MIT Press, 2005.
[22] J. Yedidia, W. Freeman, and Y. Weiss, “Understanding Belief Propagation and Its Generalizations,” Exploring Artificial Intelligence in the New Millennium, Morgan Kaufmann, 2003.
[23] M. Isard, “PAMPAS: Real-Valued Graphical Models for Computer Vision,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2003.
[24] E. Sudderth, A. Ihler, W. Freeman, and A. Willsky, “Nonparametric Belief Propagation,” Proc. Int'l Conf. Computer Vision and Pattern Recognition, 2003.
[25] K. Murphy, “Dynamic Bayesian Networks: Representation, Inference and Learning,” PhD dissertation, Univ. of California, Berkeley, 2002.
[26] Q. Diao, J. Lu, W. Hu, Y. Zhang, and G. Bradski, “DBN Models and a Prediction Method for Visual Tracking,” Proc. Bayesian Modeling Applications Workshop, 2003.
[27] M. Jordan, Z. Ghahramani, T. Jaakkola, and L. Saul, “An Introduction to Variational Methods for Graphical Models,” Machine Learning, 1999.
[28] M. Opper and D. Saad, Advanced Mean Field Methods. MIT Press, 2001.
[29] S. Li, Markov Random Field Modeling in Computer Vision. Springer, 1995.
[30] A. Santuari, O. Lanz, and R. Brunelli, “Synthetic Movies for Computer Vision Applications,” Proc. Int'l Conf. Visualization, Imaging, and Image Processing, 2003.
[31] H. Sidenbladh and M. Black, “Learning the Statistics of People in Images and Video,” Int'l J. Computer Vision, vol. 54, no. 1, 2003.
[32] A. Jepson, D. Fleet, and T. El-Maraghi, “Robust Online Appearance Models for Visual Tracking,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 10, Oct. 2003.
[33] D. Comaniciu, V. Ramesh, and P. Meer, “Kernel-Based Object Tracking,'” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 25, no. 5, May 2003.
[34] A. Doucet, N. DeFreitas, and N. Gordon, Sequential Monte Carlo Methods in Practice. Springer, 2001.
[35] M. Isard and A. Blake, “CONDENSATION–Conditional Density Propagation for Visual Tracking,” Int'l J. Computer Vision, vol. 29, no. 1, 1998.
[36] S. Arulampalam, A. Maskell, N. Gordon, and T. Clapp, “A Tutorial on Particle Filters for On-Line Non-Linear/Non-Gaussian Bayesian Tracking,” IEEE Trans. Signal Processing, vol. 50, no. 2, 2002.

Index Terms:
Computer vision, tracking, occlusion, approximate inference, Bayes filter, particle filter.
Citation:
Oswald Lanz, "Approximate Bayesian Multibody Tracking," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 9, pp. 1436-1449, Sept. 2006, doi:10.1109/TPAMI.2006.177
Usage of this product signifies your acceptance of the Terms of Use.