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.
Chapter PDF
Similar content being viewed by others
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.
References
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)
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)
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)
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)
Sullivan, J., Rittscher, J.: Guiding random particles by deterministic search. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 323–330 (2001)
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)
Sullivan, J., Blake, A., Isard, M., MacCormick, J.: Bayesian object localization in images. International Journal of Computer Vision (IJCV) 44, 111–135 (2001)
Roweis, R., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290, 2323–2326 (2000)
Tenenbaum, J., Silva, V., Langford, J.: A global geometric framework for nonlinear dimensionality reduction. Science 290, 2319–2323 (2000)
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)
Brand, M.: Charting a manifold. In: Advances in Neural Information Processing Systems (NIPS), pp. 961–968 (2002)
Teh, W.Y., Roweis, S.: Automatic alignment of local representations. In: Advances in Neural Information Processing Systems (NIPS), pp. 841–848 (2002)
Lawrence, N.D.: Gaussian process models for visualization of high dimensional data. In: Advances in Neural Information Processing Systems, NIPS (2003)
Wang, L., Hu, W.M., Tan, T.N.: Recent development in human motion analysis. Pattern Recognition 36, 585–601 (2003)
Isard, M., Blake, A.: CONDENSATION: conditional density propagation for visual tracking. International Journal of Computer Vision (IJCV) 29, 5–28 (1998)
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)
Toyama, K., Blake, A.: Probabilistic tracking in a metric space. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 50–57 (2001)
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)
Sidenbladh, H., Black, M.J.: Learning image statistics for Bayesian tracking. In: Proc. IEEE International Conf. on Computer Vision (ICCV), pp. 709–716 (2001)
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)
Grochow, K., Martin, S.L., Hertzmann, A., Popovic, Z.: Style-based inverse kinematics. In: ACM Computer Graphics (SIGGRAPH), pp. 522–531 (2004)
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)
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)
Tian, T.P., Li, R., Sclaroff, S.: Tracking human body pose on a learned smooth space. Technical Report 2005-029, Boston University (2005)
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)
Roweis, R., Saul, L., Hinton, G.E.: Global coordination of local linear models. Advances in Neural Information Processing Systems (NIPS), pp. 889–896 (2001)
Ghahramani, Z., Hinton, G.E.: The EM algorithm for mixtures of factor analyzers. Technical Report CRG-TR-96-1, University of Toronto (1996)
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)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Li, R., Yang, MH., Sclaroff, S., Tian, TP. (2006). Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers. In: Leonardis, A., Bischof, H., Pinz, A. (eds) Computer Vision – ECCV 2006. ECCV 2006. Lecture Notes in Computer Science, vol 3952. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11744047_11
Download citation
DOI: https://doi.org/10.1007/11744047_11
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-33834-5
Online ISBN: 978-3-540-33835-2
eBook Packages: Computer ScienceComputer Science (R0)