Abstract
Stochastic tracking of structured models in monolithic state spaces often requires modeling complex distributions that are difficult to represent with either parametric or sample-based approaches. We show that if redundant representations are available, the individual state estimates may be improved by combining simpler dynamical systems, each of which captures some aspect of the complex behavior. For example, human body parts may be robustly tracked individually, but the resulting pose combinations may not satisfy articulation constraints. Conversely, the results produced by full-body trackers satisfy such constraints, but such trackers are usually fragile due to the presence of clutter. We combine constituent dynamical systems in a manner similar to a Product of HMMs model. Hidden variables are introduced to represent system appearance. While the resulting model contains loops, making the inference hard in general, we present an approximate non-loopy filtering algorithm based on sequential application of Belief Propagation to acyclic subgraphs of the model.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Brown, A., Hinton, G.E.: Products of Hidden Markov Models. In: Proceedings of Artificial Intelligence and Statistics, pp. 3–11 (2001)
Choo, K., Fleet, D.J.: People tracking using hybrid monte carlo filtering. In: Proc. ICCV (2001)
Fei, H., Reid, I.: Joint bayes filter: A hybrid tracker for non-rigid hand motion recognition. In: Pajdla, T., Matas, J(G.) (eds.) ECCV 2004. LNCS, vol. 3023, pp. 497–508. Springer, Heidelberg (2004)
Hinton, G.E.: Products of Experts. In: Proc. of the Ninth International Conference on Artificial Neural Networks, pp. 1–6 (1999)
Jojic, N., Turk, M., Huang, T.S.: Tracking self-occluding articulated objects in dense disparity maps. In: Proc. of International Conference on Computer Vision (1999)
MacCormick, J., Isard, M.: Partitioned sampling, articulated objects, and interface-quality hand tracking. In: Vernon, D. (ed.) ECCV 2000. LNCS, vol. 1843, pp. 3–19. Springer, Heidelberg (2000)
Morasso, P.: Spatial control of arm movements. Experimental Brain Research 42, 223–227 (1981)
Pavlović, V., Rehg, J.M., Cham, T.-J., Murphy, K.P.: A dynamic bayesian network approach to figure tracking using learned dynamic models. In: Proc. ICCV (1999)
Rohr, K.: Towards models-based recognition of human movements in image sequences. CVGIP 59(1), 94–115 (1994)
Sidenbladh, H.: Probabilistic Tracking and Reconstruction of 3D Human Motion in Monocular Video Sequences. PhD thesis, Royal Institute of Technology, Stockholm (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)
Sminchiesescu, C., Triggs, B.: Covariance Scaled Sampling For Monocular 3D Human Tracking. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (2001)
Stenger, B., Mendonca, P.R.S., Cipolla, R.: Model-Based Hand Tracking Using an Unscented Kalman Filter. In: Proc. British Machine Vision Conference (2001)
Sullivan, J., Blake, A., Isard, M., MacCormick, J.: Object Localization by Bayesian Correlation. In: ICCV 1999, vol. 2, pp. 1068–1075 (1999)
Taycher, L., Darrell, T.: Bayesian articulated tracking using single frame pose sampling. In: Proc. 3rd Int’l. Workshop on Statistical and Computational Theories of Vision (October 2003)
Toyama, K., Horvitz, E.: Bayesian modality fusion: Probabilistic integration of multiple vision algorithms for head tracking. In: ACCV 2000 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Taycher, L., Fisher, J.W., Darrell, T. (2004). Combining Simple Models to Approximate Complex Dynamics. In: Comaniciu, D., Mester, R., Kanatani, K., Suter, D. (eds) Statistical Methods in Video Processing. SMVP 2004. Lecture Notes in Computer Science, vol 3247. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30212-4_9
Download citation
DOI: https://doi.org/10.1007/978-3-540-30212-4_9
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23989-5
Online ISBN: 978-3-540-30212-4
eBook Packages: Springer Book Archive