Learning to estimate human pose with data driven belief propagation

Gang Hua, Ming Hsuan Yang, Ying Wu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

89 Citations (Scopus)

Abstract

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.

Original languageEnglish
Title of host publicationProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
PublisherIEEE Computer Society
Pages747-754
Number of pages8
ISBN (Print)0769523722, 9780769523729
DOIs
Publication statusPublished - 2005
Event2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005 - San Diego, CA, United States
Duration: 2005 Jun 202005 Jun 25

Publication series

NameProceedings - 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
VolumeII

Conference

Conference2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2005
Country/TerritoryUnited States
CitySan Diego, CA
Period05/6/2005/6/25

All Science Journal Classification (ASJC) codes

  • Engineering(all)

Fingerprint

Dive into the research topics of 'Learning to estimate human pose with data driven belief propagation'. Together they form a unique fingerprint.

Cite this