Progressive search space reduction for human pose estimation

The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely challenging. We propose an approach that progressively reduces the search space for body parts, to greatly improve the chances that pose estimation will succeed. This involves two contributions: (i) a generic detector using a weak model of pose to substantially reduce the full pose search space; and (ii) employing `grabcut' initialized on detected regions proposed by the weak model, to further prune the search space. Moreover, we also propose (iii) an integrated spatiotemporal model covering multiple frames to refine pose estimates from individual frames, with inference using belief propagation. The method is fully automatic and self-initializing, and explains the spatio-temporal volume covered by a person moving in a shot, by soft-labeling every pixel as belonging to a particular body part or to the backg...

• Type: Conference
• Year: 2008
• Where: CVPR
• Authors: Andrew Zisserman, Manuel J. Marín-Jiménez, Vittorio Ferrari
• Keywords: Computer Vision, CVPR 2008, Human Pose, Pose Estimates, Pose Search Space, Upper-body Pose Estimation, Weak Model