Body-part templates for recovery of 2D human poses under occlusion


Share/Save/Bookmark

Poppe, Ronald and Poel, Mannes (2008) Body-part templates for recovery of 2D human poses under occlusion. In: International Conference on Articulated Motion and Deformable Objects, AMDO, July 9-11, 2008, Port d’Andratx, Spain (pp. pp. 289-298).

open access
[img]
Preview
PDF
359kB
Abstract: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.
Item Type:Conference or Workshop Item
Copyright:© 2008 Springer
Faculty:
Electrical Engineering, Mathematics and Computer Science (EEMCS)
Research Group:
Link to this item:http://purl.utwente.nl/publications/64813
Official URL:http://dx.doi.org/10.1007/978-3-540-70517-8_28
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page

Metis ID: 251011