Multiple Hypothesis Tracking for Automatic Optical Motion Capture

  • Maurice Ringer
  • Joan Lasenby
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2350)


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.


Visual motion correspondence problem tracking optical motion capture 


  1. 1.
    S. Blackman and R. Popoli. Design and analysis of modern tracking systems. Artech House, 1999.Google Scholar
  2. 2.
    G. Carpaneto and P. Toth. Algorithm 548: Solution of the assignment problem [H]. A CM Transactions on Mathematical Software, 6(1):104–111, March 1980.Google Scholar
  3. 3.
    T.-J. Cham and J. Rehg. A multiple hypothesis approach to figure tracking. In Proc. 1999 Comp Vision and Pattern Recognition (CVPR 99), volume 2, pages 239–245, Fort Collins, USA, 1999.CrossRefGoogle Scholar
  4. 4.
    I. J. Cox and S. L. Hingorani. An efficient implementation and evaluation of Reid’s multiple hypothesis tracking algorithm for visual tracking. IEEE Trans. on PAMI, 18(2):138–150, February 1996.Google Scholar
  5. 5.
    R. Danchick and G. Newnam. A fast method for finding the exact N-best hypothesis for multitarget tracking. In IEEE trans on Aerospace and Elec Sys, volume 29, pages 555–560, Apr 1993.Google Scholar
  6. 6.
    D. G. Forney Jr. The Viterbi algorithm. Proceedings of the IEEE, 61(3):268–268, March 1973.Google Scholar
  7. 7.
    S. J. Godsill, A. Doucet, and M. West. Maximum a posteriori sequence estimation using Monte Carlo particle filters. Ann. Inst. Statist. Math, 52(1), March 2001.Google Scholar
  8. 8.
    N. Gordon, D. Salmond, and A. Smith. Novel approach to nonlinear/non-gaussian bayesian state estimation. In IEEE Proc F, No 140, pages 107–113, 1993.Google Scholar
  9. 9.
    L. Herda, P. Fua, R. Plänkers, R. Boulic, and D. Thalmann. Skelton-based motion capture for robust reconstruction of human motion. In Proc. Computer Animation, IEEE CS Press, 2000.Google Scholar
  10. 10.
    A. Menache. Understanding Motion Capture for Computer Animation and Video Games. Korgan Kaufmann Publishers, Academic Press, 2000.Google Scholar
  11. 11.
    C. Rasmussen and G. D. Hager. Joint porbabilistic techniques for tracking multipart objects. In Proc. Computer Vision and Pattern Recognition (CVPR), pages 16–21, 1998.Google Scholar
  12. 12.
    J. Rehg and T. Kanade. Visual tracking of self-occluding articulated objects. In Proc of the International Conf on Computer Vision (ICCV), Boston, USA, June 1995.Google Scholar
  13. 13.
    D. Reid. An algorithm for tracking multiple targets. In IEEE Trans on Automatic Control, volume AC-24, pages 843–854, Dec 1979.Google Scholar
  14. 14.
    M. Ringer, T. Drummond, and J. Lasenby. Using occlusions to aid pose estimation for visual motion capture. In Proc. Computer Vision and Pattern Recognition (CVPR), Kauai, USA, 2001.Google Scholar
  15. 15.
    M. Ringer and J. Lasenby. Modelling and tracking articulated motion from multiple camera views. In Proc. 11th British Machine Vision Conference (BMVC2000), volume 1, pages 172–181, Bristol, UK, September 2000.Google Scholar
  16. 16.
    L. Schiff. The future of motion-capture animation: Building the perfect digital human. Animation World Magazine, Issue 4.11, February 2000.Google Scholar
  17. 17.
    Y. Song, L. Goncalves, E. Di Bernardo, and P. Perona. Monocular perception of biological motion-detection and labeling. In Proc. 7th Int. Conf. on Computer Vision (ICCV99), pages 805–812, Corfu, Greece, 1999.Google Scholar
  18. 18.
    Y. Song, L. Goncalves, and P. Perona. Monocular perception of biological motion-clutter and partial occlusion. In Proc. 6th European Conf. on Computer Vision (ECCV00), volume 2, pages 719–733, Dublin, Ireland, 2000.Google Scholar
  19. 19.
    H. A. Taha. Operations Research, An Introduction. Prentice-Hall, 6th edition, 1997.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2002

Authors and Affiliations

  • Maurice Ringer
    • 1
  • Joan Lasenby
    • 1
  1. 1.Engineering DeptCambridge UniversityCambridgeUK

Personalised recommendations