Body-Part Templates for Recovery of 2D Human Poses under Occlusion


Detection of humans and estimation of their 2D poses from a single image are challenging tasks. This is especially true when part of the observation is occluded. However, given a limited class of movements, poses can be recovered given the visible body-parts. To this end, we propose a novel template representation where the body is divided into five body-parts. Given a match, we not only estimate the joints in the body-part, but all joints in the body. Quantitative evaluation on a HumanEva walking sequence shows mean 2D errors of approximately 27.5 pixels. For simulated occlusion of the head and arms, similar results are obtained while occlusion of the legs increases this error by 6 pixels.

DOI: 10.1007/978-3-540-70517-8_28

Extracted Key Phrases

5 Figures and Tables

Cite this paper

@inproceedings{Poppe2008BodyPartTF, title={Body-Part Templates for Recovery of 2D Human Poses under Occlusion}, author={Ronald Poppe and Mannes Poel}, booktitle={AMDO}, year={2008} }