Abstract
Of different learning-based methods in human tracking, many state-of-the-art approaches have been dedicated to reduce the dimensionality of the pose state space in order to avoid complex searching in a high dimensional state space. Seldom research on human tracking refers shared latent model. In this paper, We propose a method of shared latent dynamical model (SLDM) for human tracking from monocular images. The shared latent variables can be determined easily if state vectors and observation vectors are statistically independent.With a SLDM prior over state space and observation space, our approach can be integrated into a Bayesian tracking framework of Condensation, and further a scheme of variance feedback is designed to avoid mis-tracking. Experiments using simulations and real images demonstrate this human tracking method is very efficient and promising.
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
CMU Human Motion Capture DataBase, Available online at http://mocap.cs.cmu.edu
CASIA Gait Database, Available online at http://www.sinobiometrics.com/Gait%20Database.htm
Deutscher, J., Blake, A., Reid, I.: Articulated body motion capture by annealed particle filtering. In: proc. CVPR, vol. 2, pp. 126–133, Hilton Head Island (2000)
Sminchisescu, C., Triggs, B.: Kinematic jump processes for monocular 3d human tracking. In: Proc. CVPR (June 2003)
Sminchisescu, C., Jepson, A.: Generative modeling for continuous non-linearly embedded visual inference. In: Proc. ICML (2004)
Sminchisescu, C., Kanaujia, A., Metaxas, D.: Learning Joint Top-Down and Bottom-up Processes for 3D Visual Inference. In: Proc. CVPR (2006)
Agarwal, A., Triggs, B.: Recovering 3D Human Pose from Monocular Images. IEEE Trans. PAMI (January 2006)
Elgammal, A., Lee, C.: Inferring 3D Body Pose from Silhouettes using Activity Manifold Learning. In: Proc. CVPR (2004)
MacKay, D.J.C.: Information Theory, Inference, and Learning Algorithms. Cambridge University Press, Cambridge (2003)
Sidenbladh, H., Black, M.J., Sigal, L.: Learning the Statistics of People in Images and Video. In: IJCV (2003)
Lawrence, N.D.: Gaussian process latent variable models for visulisation of high dimensional data. Proc. NIPS 16. MIT Press, Cambridge (2004)
Wang, J., Fleet, D.J., Hertzmann, A.: Gaussian Process dynamical models. Proc. NIPS 18. MIT Press, Cambridge (2005)
Urtasun, R., Fleet, D.J., Hertzmann, A., Fua, P.: Priors for People Tracking from Small Training Sets. In: Proc. ICCV (2005)
Urtasun, R., Fleet, D.J., Fua, P.: 3D People Tracking with Gaussian Process Dynamical Models. In: Proc. CVPR (2006)
Tenenbaum, J.B., De Silva, V., Langford, J.C.: A global geometric framework for nonlinear dimensionality reduction. Science 290(5500), 2319–2323 (2000)
Roweis, S., Saul, L.: Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500), 2323–2326 (2000)
Isard, M., Blake, A.: Condensatioon-Conditional density propagation for visual tracking. In: IJCV (1998)
Sigal, L., Bhatia, S., Roth, S., Black, M., Isard, M.: Tracking Loose-limbed People. In: Proc. CVPR (2004)
Mori, G., Malik, J.: Estimating human body configurations using shape context matching. In: Proc. ECCV (2002)
Tong, M., Liu, Y., Huang, T.S.: Recover human pose from monocular image under weak perspective projection. In: Workshop ICCV-HCI (2005)
Rahimi, A., Recht, B., Darrell, T.: Learing appearance manifolds from video. In: Proc. CVPR (2005)
Bregler, C., Malik, J.: Tracking people with twists and exponential maps. In: Proc. CVPR (1998)
Li, R., Yang, M., Sclaroff, S., Tian, T.: Monocular Tracking of 3D Human Motion with a Coordinated Mixture of Factor Analyzers. In: Proc. ECCV (2006)
Tangkuampien, T., Suter, D.: Real-Time Human Pose Inference using Kernel Principal Component Pre-image Approximations. In: Proc. BMVC (2006)
Shon, A.P., Grochow, K., Hertzmann, A., Rao, R.P.N.: Learning Shared Latent Structure for Image Synthesis and Robotic Imitation. In: NIPS (2005)
Ham, J., Lee, D., Saul, L.: Learning High Dimensional Correspondence from Low Dimensional Manifolds,in / it Workshop on The Continuum from Labeled to Unlabeled Data in Machine Learning and Data Mining, ICML03
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Tong, M., Liu, Y. (2007). Shared Latent Dynamical Model for Human Tracking from Videos. In: Sebe, N., Liu, Y., Zhuang, Y., Huang, T.S. (eds) Multimedia Content Analysis and Mining. MCAM 2007. Lecture Notes in Computer Science, vol 4577. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73417-8_17
Download citation
DOI: https://doi.org/10.1007/978-3-540-73417-8_17
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73416-1
Online ISBN: 978-3-540-73417-8
eBook Packages: Computer ScienceComputer Science (R0)