Correcting Pose Estimation with Implicit Occlusion Detection and Rectification

Ibrahim Hamed Ismail RADWAN, Abhinav Dhall, Roland Goecke

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

1 Downloads (Pure)


Recently, articulated pose estimation methods based on the pictorial structure framework have received much attention in computer vision. However, the performance of these approaches has been limited due to the presence of self-occlusion. This paper deals with the problem of handling self-occlusion in the pictorial structure framework. We propose an exemplar-based framework for implicit occlusion detection and rectification. Our framework can be applied as a general post-processing plug-in following any pose estimation approach to rectify errors due to self-occlusion and to improve the accuracy. The proposed framework outperforms a state-of-the-art pictorial structure approach for human pose estimation on the HumanEva dataset.
Original languageEnglish
Title of host publicationThe 2012 21th International Conference on Pattern Recognition (ICPR2012)
Place of PublicationTsukuba, Japan
PublisherIEEE, Institute of Electrical and Electronics Engineers
Number of pages4
ISBN (Electronic)9784990644109
ISBN (Print)9781467322164
Publication statusPublished - 2012
Event21st International Conference on Pattern Recognition (ICPR 2012) - Tsukuba, Tsukuba, Japan
Duration: 11 Nov 201215 Nov 2012

Publication series

NameInternational Conference on Pattern Recognition


Conference21st International Conference on Pattern Recognition (ICPR 2012)
Abbreviated titleICPR 2012


Dive into the research topics of 'Correcting Pose Estimation with Implicit Occlusion Detection and Rectification'. Together they form a unique fingerprint.

Cite this