Multiple-Target Tracking by Spatiotemporal Monte Carlo Markov Chain Data Association

We propose a framework for tracking multiple targets, where the input is a set of candidate regions in each frame, as obtained from a state-of-the-art background segmentation module, and the goal is to recover trajectories of targets over time. Due to occlusions by targets and static objects, as also by noisy segmentation and false alarms, one foreground region may not correspond to one target faithfully. Therefore, the one-to-one assumption used in most data association algorithms is not always satisfied. Our method overcomes the one-to-one assumption by formulating the visual tracking problem in terms of finding the best spatial and temporal association of observations, which maximizes the consistency of both motion and appearance of trajectories. To avoid enumerating all possible solutions, we take a data-driven Markov Chain Monte Carlo (DD-MCMC) approach to sample the solution space efficiently. The sampling is driven by an informed proposal scheme controlled by a joint probability model combining motion and appearance. Comparative experiments with quantitative evaluations are provided.

[1]  Frank Dellaert,et al.  MCMC-based particle filtering for tracking a variable number of interacting targets , 2005, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  P. Green,et al.  Trans-dimensional Markov chain Monte Carlo , 2000 .

[3]  Ingemar J. Cox,et al.  An efficient implementation and evaluation of Reid's multiple hypothesis tracking algorithm for visual tracking , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[4]  Ying Wu,et al.  Collaborative tracking of multiple targets , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[5]  Jean-Marc Odobez,et al.  Using particles to track varying numbers of interacting people , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[6]  P. Green.  Reversible jump Markov chain Monte Carlo computation and Bayesian model determination , 1995 .

[7]  Songhwai Oh,et al.  Markov chain Monte Carlo data association for general multiple-target tracking problems , 2004, 2004 43rd IEEE Conference on Decision and Control (CDC) (IEEE Cat. No.04CH37601).

[8]  Frank Dellaert,et al.  An MCMC-Based Particle Filter for Tracking Multiple Interacting Targets , 2004, ECCV.

[9]  C. Morefield.  Application of 0-1 integer programming to multitarget tracking problems , 1977 .

[10]  Pascal Fua,et al.  Robust People Tracking with Global Trajectory Optimization , 2006, 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06).

[11]  L. Davis,et al.  M2Tracker: A Multi-View Approach to Segmenting and Tracking People in a Cluttered Scene , 2003, International Journal of Computer Vision.

[12]  Frank Dellaert,et al.  Structure from motion without correspondence , 2000, Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662).

[13]  Robert T. Collins,et al.  Mean-shift blob tracking through scale space , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[14]  Harry Shum,et al.  Image segmentation by data driven Markov chain Monte Carlo , 2001, Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001.

[15]  Aubrey B. Poore,et al.  Multidimensional assignment formulation of data association problems arising from multitarget and multisensor tracking , 1994, Comput. Optim. Appl..

[16]  Ramakant Nevatia,et al.  Tracking multiple humans in crowded environment , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[17]  Frank Dellaert,et al.  Multitarget tracking with split and merged measurements , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[18]  W. Ames.  Mathematics in Science and Engineering , 1999 .

[19]  L. Hong,et al.  Markov-chain Monte-Carlo approach for association probability evaluation , 2004 .

[20]  Yaakov Bar-Shalom,et al.  Sonar tracking of multiple targets using joint probabilistic data association , 1983 .

[21]  Gérard G. Medioni,et al.  Continuous tracking within and across camera streams , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..