Abstract
Usually a uniform observation strategy will result in frustrated tracking processes. To address this problem, we construct a flexible model with Hierarchical Dynamic Bayesian Network by introducing hidden variables to infer the intrinsic properties of the state and observation spaces. With this model, a dynamic-mapping is built between target state space and the observation space. Based on a decoupling based inference strategy, a tractable solution for this algorithm is proposed. Experiments of human face tracking under various poses and occlusions show promising results.
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
Comaniciu, D., Ramesh, V., Meer, P.: Real-time Tracking of Non-rigid Objects using Mean Shift. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, vol. II, pp. 142–149 (2000)
Dempster, A.P., Laird, N.M., Rubin, D.B.: Maximum likelihood from incomplete data via the EM algorithm. J. Royal Statistical Society Series B 39, 1–38 (1997)
Doucet, A., Godsill, J., Andrieu, C.: On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and Computing 10(3), 197–208 (2000)
Isard, M., Blake, A.: Contour Tracking by Stochastic Propagation of Conditional Density. In: Buxton, B.F., Cipolla, R. (eds.) ECCV 1996. LNCS, vol. 1064, pp. 343–356. Springer, Heidelberg (1996)
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. 767–781. Springer, Heidelberg (1998)
Isard, M., Blake, A.: Condensation-Conditional Density Propagation for Visual Tracking. Int. J. Computer Vision 29(1), 5–28 (1998)
Krishnamurthy, V., Evans, J.: Finite-dimensional filters for passive tracking of markov jump linear systems. Automatica 34(6), 765–770 (1998)
Palvovic, V., Rehg, J.M., Cham, T.-J.: A Dynamic Bayesian Network Approach to Figure Tracking using Learned Switching Dynamic Models. In: Proc. IEEE Int’l Conf. on Computer Vision, Corfu, Greece, September 1999, vol. I, pp. 94–101 (1999)
Raja, Y., McKenna, S., Gong, S.: Colour Model Selection and Adaptation in Dynamic Scenes. In: Burkhardt, H.-J., Neumann, B. (eds.) ECCV 1998. LNCS, vol. 1406, pp. 460–475. Springer, Heidelberg (1998)
Wu, Y., Gang, H., Wu, T.: Switching Observation Models for Contour Tracking in Clutter. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Madison, WI, vol. I, pp. 295–302.
Wu, Y., Huang, T.S.: A Co-inference Approach to Robust Visual Tracking. In: Proc. of IEEE Int’l Conf. on Computer Vision, Vancouver, Canada, vol. II, pp. 26–33 (2001)
Wu, Y., Huang, T.S.: Color Tracking by Transductive Learning. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition, Hilton Head Island, South Carolina, USA, vol. II, pp. 133–138 (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
Li, H., Xiao, R., Zhang, HJ., Peng, LZ. (2004). A Hierarchical Dynamic Bayesian Network Approach to Visual Tracking. In: Aizawa, K., Nakamura, Y., Satoh, S. (eds) Advances in Multimedia Information Processing - PCM 2004. PCM 2004. Lecture Notes in Computer Science, vol 3332. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-30542-2_76
Download citation
DOI: https://doi.org/10.1007/978-3-540-30542-2_76
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-23977-2
Online ISBN: 978-3-540-30542-2
eBook Packages: Computer ScienceComputer Science (R0)