Advertisement

Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers

  • Rui Li
  • Ming-Hsuan Yang
  • Stan Sclaroff
  • Tai-Peng Tian
Part of the Lecture Notes in Computer Science book series (LNCS, volume 3952)

Abstract

Filtering based algorithms have become popular in tracking human body pose. Such algorithms can suffer the curse of dimensionality due to the high dimensionality of the pose state space; therefore, efforts have been dedicated to either smart sampling or reducing the dimensionality of the original pose state space. In this paper, a novel formulation that employs a dimensionality reduced state space for multi-hypothesis tracking is proposed. During off-line training, a mixture of factor analyzers is learned. Each factor analyzer can be thought of as a “local dimensionality reducer” that locally approximates the pose manifold. Global coordination between local factor analyzers is achieved by learning a set of linear mixture functions that enforces agreement between local factor analyzers. The formulation allows easy bidirectional mapping between the original body pose space and the low-dimensional space. During online tracking, the clusters of factor analyzers are utilized in a multiple hypothesis tracking algorithm. Experiments demonstrate that the proposed algorithm tracks 3D body pose efficiently and accurately , even when self-occlusion, motion blur and large limb movements occur. Quantitative comparisons show that the formulation produces more accurate 3D pose estimates over time than those that can be obtained via a number of previously-proposed particle filtering based tracking algorithms.

Keywords

Tracking Algorithm Neural Information Processing System Locally Linear Embedding Motion Capture Data Nonlinear Dimensionality Reduction 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    King, O., Forsyth, D.: How does CONDENSATION behave with a finite number of samples? In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1842, pp. 695–709. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  2. 2.
    Isard, M., Blake, A.: ICONDENSATION: Unifying low-level and high-level tracking in a stochastic framework. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 893–908. Springer, Heidelberg (1998)Google Scholar
  3. 3.
    MacCormick, J., Blake, A.: A probabilistic exclusion principle for tracking multiple objects. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 572–578 (1999)Google Scholar
  4. 4.
    Sminchisescu, C., Triggs, B.: Covariance scaled sampling for monocular 3D body tracking. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 447–454 (2001)Google Scholar
  5. 5.
    Sullivan, J., Rittscher, J.: Guiding random particles by deterministic search. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 323–330 (2001)Google Scholar
  6. 6.
    Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 126–133 (2000)Google Scholar
  7. 7.
    Sullivan, J., Blake, A., Isard, M., MacCormick, J.: Bayesian object localization in images. International Journal of Computer Vision (IJCV) 44, 111–135 (2001)CrossRefMATHGoogle Scholar
  8. 8.
    Roweis, R., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)CrossRefGoogle Scholar
  9. 9.
    Tenenbaum, J., Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)CrossRefGoogle Scholar
  10. 10.
    Belkin, M., Niyogi, P.: Laplacian eigenmaps and spectral techniques for embedding and clustering. In: Advances in Neural Information Processing Systems (NIPS), pp. 585–591 (2001)Google Scholar
  11. 11.
    Brand, M.: Charting a manifold. In: Advances in Neural Information Processing Systems (NIPS), pp. 961–968 (2002)Google Scholar
  12. 12.
    Teh, W.Y., Roweis, S.: Automatic alignment of local representations. In: Advances in Neural Information Processing Systems (NIPS), pp. 841–848 (2002)Google Scholar
  13. 13.
    Lawrence, N.D.: Gaussian process models for visualization of high dimensional data. In: Advances in Neural Information Processing Systems, NIPS (2003)Google Scholar
  14. 14.
    Wang, L., Hu, W.M., Tan, T.N.: Recent development in human motion analysis. Pattern Recognition 36, 585–601 (2003)CrossRefGoogle Scholar
  15. 15.
    Isard, M., Blake, A.: CONDENSATION: conditional density propagation for visual tracking. International Journal of Computer Vision (IJCV) 29, 5–28 (1998)CrossRefGoogle Scholar
  16. 16.
    Cham, T.J., Rehg, J.M.: A multiple hypothesis approach to figure tracking. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 239–245 (1999)Google Scholar
  17. 17.
    Toyama, K., Blake, A.: Probabilistic tracking in a metric space. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 50–57 (2001)Google Scholar
  18. 18.
    Sidenbladh, H., Black, M.J., Fleet, D.J.: Stochastic tracking of 3D human figures using 2D image motion. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 702–718. Springer, Heidelberg (2000)CrossRefGoogle Scholar
  19. 19.
    Sidenbladh, H., Black, M.J.: Learning image statistics for Bayesian tracking. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 709–716 (2001)Google Scholar
  20. 20.
    Elgammal, A., Lee, C.S.: Inferring 3D body pose from silhouettes using activity manifold learning. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 681–688 (2004)Google Scholar
  21. 21.
    Grochow, K., Martin, S.L., Hertzmann, A., Popovic, Z.: Style-based inverse kinematics. In: ACM Computer Graphics (SIGGRAPH), pp. 522–531 (2004)Google Scholar
  22. 22.
    Safonova, A., Hodgins, J.K., Pollard, N.S.: Synthesizing physically realistic human motion in low dimensional, behavior-specific spaces. In: ACM Computer Graphics (SIGGRAPH), pp. 514–521 (2004)Google Scholar
  23. 23.
    Sminchisescu, C., Jepson, A.: Generative modelling for continuous non-linearly embedded visual inference. In: Proc. IEEE International Conf. on Machine Learning (ICML), pp. 140–147 (2004)Google Scholar
  24. 24.
    Tian, T.P., Li, R., Sclaroff, S.: Tracking human body pose on a learned smooth space. Technical Report 2005-029, Boston University (2005)Google Scholar
  25. 25.
    Urtasun, R., Fleet, D.J., Hertzmann, A., Fua, P.: Priors for people tracking from small training sets. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 403–410 (2005)Google Scholar
  26. 26.
    Roweis, R., Saul, L., Hinton, G.E.: Global coordination of local linear models. Advances in Neural Information Processing Systems (NIPS), pp. 889–896 (2001)Google Scholar
  27. 27.
    Ghahramani, Z., Hinton, G.E.: The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1, University of Toronto (1996)Google Scholar
  28. 28.
    Sigal, L., Bhatia, S., Roth, S., Black, M.J., Isard, M.: Tracking loose-limbed people. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp. 421–428 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rui Li
    • 1
  • Ming-Hsuan Yang
    • 2
  • Stan Sclaroff
    • 1
  • Tai-Peng Tian
    • 1
  1. 1.Boston UniversityBostonUSA
  2. 2.Honda Research InstituteMountain ViewUSA

Personalised recommendations