Gaussian Process Models for Human Pose and Motion
Research Overview
The inference of human shape and motion in 3D has become a topic of great
interest in the vision community. The problem is difficult because
people move in complex ways, having with many degrees of freedom. Their
appearance is similarly hard to model due to variations in lighting,
to deformations of clothing, and to occlusions.
One effective way to constrain tracking is with a prior model
of human pose and motion learned from motion capture data.
Given the high-dimensionality of motion capture data, and the relative
sparsity of data, it is natural to learn a latent probabilistic model.
The Gaussian Process Latent Variable Model of Lawrence (2004) is a
natural mechanism for this.
We have extended this Gaussian Process model to incorporate latent
time series prediction, and to multifactor variants of the GPLVm
which yield a form of style-content separation when learning multiple
types of model from multiple people.
We have also used this framework for monocular people tracking.
For more details see Jack Wang's
GPDM page
and his
GPSC page.
Related Publications
-
Gaussian process dynamical models.
(abstract)
(pdf)
© IEEE
Wang, J., Fleet, D.J. and Hertzmann, A.
IEEE Transactions on Pattern Analysis and Machine Intelligence
30(2):283--298, 2008.
-
Topologically constrained latent variable models.
(pdf)
Urtasun, R., Fleet, D.J., Geiger, A., Popovic, J., Darrell, T. and Lawrence, N.
International Conference on Machine Learning (ICML),
Helsinki, 2008.
-
Modeling Human Locomotion with Topologically Constrained Latent Variable Models.
Urtasun, R., Fleet, D.J., and Lawrence, N.
Workshop on Human Motion: Understanding, Modeling, Capture and Animation,
Rio de Janeiro, October 2007, pp. 104-118
-
Multifactor Gaussian Process models for style-content separation.
(pdf)
Wang, J., Fleet, D.J., and Hertzmann, A.
International Conference on Machine Learning (ICML),
Oregon, pp. 975-982, 2007.
-
3D people tracking with Gaussian process dynamical models.
(pdf)
© IEEE
Urtasun, R., Fleet, D.J., and Fua, P.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
New York, Vol. II, pp. 238-245, 2006.
-
Priors for people tracking from small training sets.
(pdf)
© IEEE
Urtasun, R., Fleet, D.J., Hertzmann, A. and Fua, P.
IEEE International Conference on Computer Vision (ICCV),
Beijing, Vol.I, pp. 403-410, October 2005.
Return to David Fleet's home page.