Abstract
We present a novel approach to modelling the non-linear and time-varying dynamics of human motion, using statistical methods to capture the characteristic motion patterns that exist in typical human activities. Our method is based on automatically clustering the body pose space into connected regions exhibiting similar dynamical characteristics, modelling the dynamics in each region as a Gaussian autoregressive process. Activities that would require large numbers of exemplars in example based methods are covered by comparatively few motion models. Different regions correspond roughly to different action-fragments and our class inference scheme allows for smooth transitions between these, thus making it useful for activity recognition tasks. The method is used to track activities including walking, running, etc., using a planar 2D body model. Its effectiveness is demonstrated by its success in tracking complicated motions like turns, without any key frames or 3D information.
Chapter PDF
Similar content being viewed by others
Keywords
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
Brand, M., Hertzmann, A.: Style Machines. In: Proceedings Siggraph 2000, Computer Graphics, pp. 183–192 (2000)
Bregler, C., Malik, J.: Tracking People with Twists and Exponential Maps. In: International Conference on Computer Vision and Pattern Recognition, pp. 8–15 (1998)
Cham, T., Rehg, J.: A Multiple Hypothesis Approach to Figure Tracking. In: International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 239–245 (1999)
Efros, A., Berg, G.: Mori, and J. Malik. Recognizing Action at a Distance. In: International Conference on Computer Vision (2003) (to appear)
Ghahramani, Z., Hinton, G.: Switching State-Space Models. Technical report, Department of Computer Science, University of Toronto, Canada (1998)
Heap, T., Hogg, D.: Nonlinear Manifold Learning for Visual Speech Recognition. In: International Conference on Computer Vision, pp. 494–499 (1995)
Heap, T., Hogg, D.: Wormholes in Shape Space: Tracking Through Discontinuous Changes in Shape. In: International Conference on Computer Vision, pp. 344–349 (1998)
Howe, N., Leventon, M., Freeman, W.: Bayesian Reconstruction of 3D Human Motion from Single-Camera Video. Neural Information Processing Systems (1999)
Ju, S., Black, M., Yacoob, Y.: Cardboard People: A Parameterized Model of Articulated Motion. In: Int. Conf. on Automatic Face and Gesture Recognition, pp. 38–44 (1996)
Lütkepohl, H.: Introduction to Multiple Time Series Analysis, 2nd edn. Springer, Berlin (1993)
Mori, G., Malik, J.: Estimating Human Body Configurations Using Shape Context Matching. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 666–680. Springer, Heidelberg (2002)
Morris, D., Rehg, J.: Singularity Analysis for Articulated Object Tracking. In: International Conference on Computer Vision and Pattern Recognition, pp. 289–296 (1998)
North, B., Blake, A., Isard, M., Rittscher, J.: Learning and Classification of Complex Dynamics. Pattern Analysis and Machine Intelligence 22(9), 1016–1034 (2000)
Pavlovic, V., Rehg, J., MacCormick, J.: Learning Switching Linear Models of Human Motion. In: Neural Information Processing Systems, pp. 981–987 (2000)
Ramanan, D., Forsyth, D.: Finding and Tracking People from the Bottom Up. In: International Conference on Computer Vision and Pattern Recognition (2003)
Sidenbladh, H., Black, M.: Learning Image Statistics for Bayesian Tracking. In: International Conference on Computer Vision, vol. 2, pp. 709–716 (2001)
Sidenbladh, H., Black, M., Sigal, L.: Implicit Probabilistic Models of Human Motion for Synthesis and Tracking. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 784–800. Springer, Heidelberg (2002)
Sminchisescu, C., Triggs, B.: Covariance Scaled Sampling for Monocular 3D Body Tracking. In: International Conference on Computer Vision and Pattern Recognition (2001)
Sullivan, J., Carlsson, S.: Recognizing and Tracking Human Action. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2350, pp. 629–644. Springer, Heidelberg (2002)
Thayananthan, A., Stenger, B., Torr, P., Cipolla, R.: Learning a kinematic prior for tree-based filtering. In: Proc. British Machine Vision Conference, vol. 2, pp. 589–598 (2003)
Toyama, K., Blake, A.: Probabilistic Tracking in a Metric Space. In: International Conference on Computer Vision, pp. 50–59 (2001)
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
Agarwal, A., Triggs, B. (2004). Tracking Articulated Motion Using a Mixture of Autoregressive Models. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3023. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24672-5_5
Download citation
DOI: https://doi.org/10.1007/978-3-540-24672-5_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21982-8
Online ISBN: 978-3-540-24672-5
eBook Packages: Springer Book Archive