TY - CONF
T1 - Context and observation driven latent variable model for human pose estimation
T2 - Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
Y1 - 2008
A1 - Gupta,A.
A1 - Chen,T.
A1 - Chen,F.
A1 - Kimber,D.
A1 - Davis, Larry S.
KW - estimation;
KW - estimation;image
KW - Gaussian
KW - gestures;pose
KW - latent
KW - learning;parameterized
KW - model;human
KW - observations;integrated
KW - pose
KW - process
KW - processes;gesture
KW - processing;pose
KW - recognition;image
KW - tracking;Gaussian
KW - variable
AB - Current approaches to pose estimation and tracking can be classified into two categories: generative and discriminative. While generative approaches can accurately determine human pose from image observations, they are computationally expensive due to search in the high dimensional human pose space. On the other hand, discriminative approaches do not generalize well, but are computationally efficient. We present a hybrid model that combines the strengths of the two in an integrated learning and inference framework. We extend the Gaussian process latent variable model (GPLVM) to include an embedding from observation space (the space of image features) to the latent space. GPLVM is a generative model, but the inclusion of this mapping provides a discriminative component, making the model observation driven. Observation Driven GPLVM (OD-GPLVM) not only provides a faster inference approach, but also more accurate estimates (compared to GPLVM) in cases where dynamics are not sufficient for the initialization of search in the latent space. We also extend OD-GPLVM to learn and estimate poses from parameterized actions/gestures. Parameterized gestures are actions which exhibit large systematic variation in joint angle space for different instances due to difference in contextual variables. For example, the joint angles in a forehand tennis shot are function of the height of the ball (Figure 2). We learn these systematic variations as a function of the contextual variables. We then present an approach to use information from scene/objects to provide context for human pose estimation for such parameterized actions.
JA - Computer Vision and Pattern Recognition, 2008. CVPR 2008. IEEE Conference on
M3 - 10.1109/CVPR.2008.4587511
ER -