Multiple Hypothesis Tracking for Automatic Optical Motion Capture

We present a technique for performing the tracking stage of optical motion capture which retains, at each time frame, multiple marker association hypotheses and estimates of the subject's position. Central to this technique are the equations for calculating the likelihood of a sequence of association hypotheses, which we develop using a Bayesian approach. The system is able to perform motion capture using fewer cameras and a lower frame rate than has been used previously, and does not require the assistance of a human operator. We conclude by demonstrating the tracker on real data and provide an example in which our technique is able to correctly determine all marker associations and standard tracking techniques fail.

[1]  Ingemar J. Cox,et al.  An Efficient Implementation of Reid's Multiple Hypothesis Tracking Algorithm and Its Evaluation for the Purpose of Visual Tracking , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Pascal Fua,et al.  Skeleton-based motion capture for robust reconstruction of human motion , 2000, Proceedings Computer Animation 2000.

[3]  Takeo Kanade,et al.  Visual Tracking of Self-Occluding Articulated Objects , 1994 .

[4]  Yang Song,et al.  Monocuolar Perception of Biological Motion - Clutter and Partial Occlusion , 2000, ECCV.

[5]  R. Danchick,et al.  A fast method for finding the exact N-best hypotheses for multitarget tracking , 1993 .

[6]  Gregory D. Hager,et al.  Joint probabilistic techniques for tracking multi-part objects , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[7]  A. Doucet,et al.  Maximum a Posteriori Sequence Estimation Using Monte Carlo Particle Filters , 2001, Annals of the Institute of Statistical Mathematics.

[8]  Paolo Toth,et al.  Algorithm 548: Solution of the Assignment Problem [H] , 1980, TOMS.

[9]  Simon J. Godsill,et al.  Improvement Strategies for Monte Carlo Particle Filters , 2001, Sequential Monte Carlo Methods in Practice.

[10]  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.

[11]  Donald Reid.  An algorithm for tracking multiple targets , 1978 .

[12]  Alberto Menache,et al.  Understanding Motion Capture for Computer Animation and Video Games , 1999 .

[13]  Yang Song,et al.  Monocular perception of biological motion-detection and labeling , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[14]  Joan Lasenby,et al.  Using occlusions to aid position estimation for visual motion capture , 2001, Proceedings of the 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. CVPR 2001.

[15]  Takeo Kanade,et al.  Model-based tracking of self-occluding articulated objects , 1995, Proceedings of IEEE International Conference on Computer Vision.

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

[17]  Joan Lasenby,et al.  Modelling and Tracking Articulated Motion from Multiple Camera Views , 2000, BMVC.

[18]  Samuel S. Blackman,et al.  Design and Analysis of Modern Tracking Systems , 1999 .

[19]  James M. Rehg,et al.  A multiple hypothesis approach to figure tracking , 1999, Proceedings. 1999 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No PR00149).

[20]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .