Sciweavers

Share
CVPR
2005
IEEE

Learning to Estimate Human Pose with Data Driven Belief Propagation

11 years 11 days ago
Learning to Estimate Human Pose with Data Driven Belief Propagation
We propose a statistical formulation for 2-D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to infer pose parameters from image cues such as appearance, shape, edge, and color. From a set of hand labeled images, we accumulate prior knowledge of 2-D body shapes by learning their low-dimensional representations for inference of pose parameters. A data driven belief propagation Monte Carlo algorithm, utilizing importance sampling functions built from bottom-up visual cues, is proposed for efficient probabilistic inference. Contrasted to the few sequential statistical formulations in the literature, our algorithm integrates both top-down as well as bottom-up reasoning mechanisms, and can carry out the inference tasks in parallel. Experimental results demonstrate the potency and effectiveness of the proposed algorithm in estimating 2-D human pose from single images.
Gang Hua, Ming-Hsuan Yang, Ying Wu
Added 12 Oct 2009
Updated 29 Oct 2009
Type Conference
Year 2005
Where CVPR
Authors Gang Hua, Ming-Hsuan Yang, Ying Wu
Comments (0)
books