Detecting end-effectors on 2.5D data using geometric deformable models: application to human pose estimation

Suau Cuadros, Xavier; Ruiz Hidalgo, Javier; Casas Pla, Josep Ramon

doi:10.1016/j.cviu.2012.11.006

dc.contributor.author	Suau Cuadros, Xavier
dc.contributor.author	Ruiz Hidalgo, Javier
dc.contributor.author	Casas Pla, Josep Ramon
dc.contributor.other	Universitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned	2014-10-08T17:06:07Z
dc.date.created	2013-03
dc.date.issued	2013-03
dc.identifier.citation	Suau, X.; Ruiz, J.; Casas, J. Detecting end-effectors on 2.5D data using geometric deformable models: application to human pose estimation. "Computer vision and image understanding", Març 2013, vol. 117, núm. 3, p. 281-288.
dc.identifier.issn	1077-3142
dc.identifier.uri	http://hdl.handle.net/2117/24311
dc.description.abstract	End-effectors are usually related to the location of limbs, and their reliable detection enables robust body tracking as well as accurate pose estimation. Recent innovation in depth cameras has re-stated the pose estimation problem. We focus on the information provided by these sensors, for which we borrow the name 2.5D data from the Graphics community. In this paper we propose a human pose estimation algorithm based on topological propagation. Geometric Deformable Models are used to carry out such propagation, implemented according to the Narrow Band Level Set approach. A variant of the latter method is proposed, including a density restriction which helps preserving the topological properties of the object under analysis. Principal end-effectors are extracted from a directed graph weighted with geodesic distances, also providing a skeletal-like structure describing human pose. An evaluation against reference methods is performed with promising results. The proposed solution allows a frame-wise end-effector detection, with no temporal tracking involved, which may be generalized to the tracking of other objects beyond human body.
dc.format.extent	8 p.
dc.language.iso	eng
dc.rights	Attribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.uri	http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject	Àrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la imatge i del senyal vídeo
dc.subject.lcsh	Computer vision
dc.subject.other	Depth image
dc.subject.other	End-effector
dc.subject.other	Extremities
dc.subject.other	Human pose estimation
dc.subject.other	Range camera
dc.title	Detecting end-effectors on 2.5D data using geometric deformable models: application to human pose estimation
dc.type	Article
dc.subject.lemac	Visió per ordinador
dc.contributor.group	Universitat Politècnica de Catalunya. GPI - Grup de Processament d'Imatge i Vídeo
dc.identifier.doi	10.1016/j.cviu.2012.11.006
dc.description.peerreviewed	Peer Reviewed
dc.relation.publisherversion	http://www.sciencedirect.com/science/article/pii/S1077314212001907
dc.rights.access	Restricted access - publisher's policy
drac.iddocument	11179701
dc.description.version	Postprint (published version)
dc.relation.projectid	info:eu-repo/grantAgreement/EC/FP7/248138/EU/Format-Agnostic SCript-based INterAcTive Experience/FASCINATE
dc.date.lift	10000-01-01
upcommons.citation.author	Suau, X.; Ruiz, J.; Casas, J.
upcommons.citation.published	true
upcommons.citation.publicationName	Computer vision and image understanding
upcommons.citation.volume	117
upcommons.citation.number	3
upcommons.citation.startingPage	281
upcommons.citation.endingPage	288