Body localization in still images using hierarchical models and hybrid search

Jiayong Zhang, Jiebo Luo, Robert Collins, Yanxi Liu

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

24 Scopus citations

Abstract

We present a 3-level hierarchical model for localizing human bodies in still images from arbitrary viewpoints. We first fit a simple tree-structured model defined on a small landmark set along the body contours by Dynamic Programming (DP). The output is a series of proposal maps that encode the probabilities of partial body configurations. Next, we fit a mixture of view-dependent models by Sequential Monte Carlo (SMC), which handles self-occlusion, anthropometric constraints, and large viewpoint changes. DP and SMC are designed to search in opposite directions such that the DP proposals are utilized effectively to initialize and guide the SMC inference. This hybrid strategy of combining deterministic and stochastic search ensures both the robustness and efficiency of DP, and the accuracy of SMC. Finally, we fit an expanded mixture model with increased landmark density through local optimization. The model hierarchy is trained on a large number of gait images. Extensive tests on cluttered images with varying poses including walking, dancing and various types of sports activities demonstrate the feasibility of the proposed approach.

Original languageEnglish (US)
Title of host publicationProceedings - 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
Pages1536-1543
Number of pages8
DOIs
StatePublished - Dec 22 2006
Event2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006 - New York, NY, United States
Duration: Jun 17 2006Jun 22 2006

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2
ISSN (Print)1063-6919

Other

Other2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, CVPR 2006
CountryUnited States
CityNew York, NY
Period6/17/066/22/06

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint Dive into the research topics of 'Body localization in still images using hierarchical models and hybrid search'. Together they form a unique fingerprint.

Cite this