Affordable Access

ORGM: Occlusion Relational Graphical Model for Human Pose Estimation.

Authors
  • Fu, Lianrui
  • Zhang, Junge
  • Huang, Kaiqi
Type
Published Article
Journal
IEEE Transactions on Image Processing
Publisher
Institute of Electrical and Electronics Engineers
Publication Date
Dec 14, 2016
Identifiers
PMID: 27992338
Source
Medline
License
Unknown

Abstract

Articulated human pose estimation from monocular image is a challenging problem in computer vision. Occlusion is a main challenge for human pose estimation, which is largely ignored in popular tree structured models. The tree structured model is simple and convenient for exact inference, but short in modeling the occlusion coherence especially in the case of selfocclusion. We propose an occlusion relational graphical model which is able to model both self-occlusion and occlusion by the other objects simultaneously. The proposed model can encode the interactions between human body parts and objects, and enables it to learn occlusion coherence from data discriminatively. We evaluate our model on several public benchmarks for human pose estimation including challenging subsets featuring significant occlusion. The experimental results show that our method is superior to the previous state-of-the-arts, and is robust to occlusion for 2D human pose estimation.

Report this publication

Statistics

Seen <100 times