Proposal Maps driven MCMC for Estimating Human Body Pose in Static Images (CVPR 2004)
Abstract
This paper addresses the problem of estimating human body pose in static
images. This problem is challenging due to the high dimensional state
space of body poses, the presence of pose ambiguity, and the need to
segment the human body in an image. We use an image generative approach by
modeling the human kinematics, the shape and the clothing
probabilistically. These models are used for deriving a good likelihood
measure to evaluate samples in the solution space. We adopt a data-driven
MCMC framework for searching the solution space efficiently. Our
observation data include the face, head-shoulders contour, skin color
blobs, and ridges; and they provide evidences on the positions of the
head, shoulders and limbs. To translate these inferences into pose
hypotheses, we introduce the use of "proposal maps", which is an efficient
way of consolidating the evidence and generating 3D pose candidates during
the MCMC search. As experimental results show, the proposed technique
estimates the human 3D pose accurately on various test images.