Show simple item record

dc.contributor.authorLópez-Quintero, Manuel I.
dc.contributor.authorMarín-Jiménez, M.J.
dc.contributor.authorMuñoz-Salinas, Rafael
dc.contributor.authorMadrid-Cuevas, F.J.
dc.contributor.authorMedina-Carnicer, R.
dc.date.accessioned2018-10-17T09:14:22Z
dc.date.available2018-10-17T09:14:22Z
dc.date.issued2015
dc.identifier.urihttp://hdl.handle.net/10396/17301
dc.description.abstractIn this paper, we consider the problem of 2D human pose estimation on stereo image pairs. In particular, we aim at estimating the location, orientation and scale of upper-body parts of people detected in stereo image pairs from realistic stereo videos that can be found in the Internet. To address this task, we propose a novel pictorial structure model to exploit the stereo information included in such stereo image pairs: the Stereo Pictorial Structure (SPS). To validate our proposed model, we contribute a new annotated dataset of stereo image pairs, the Stereo Human Pose Estimation Dataset (SHPED), obtained from YouTube stereoscopic video sequences, depicting people in challenging poses and diverse indoor and outdoor scenarios. The experimental results on SHPED indicates that SPS improves on state-ofthe- art monocular models thanks to the appropriate use of the stereo informationes_ES
dc.format.mimetypeapplication/pdfes_ES
dc.language.isoenges_ES
dc.rightshttps://creativecommons.org/licenses/by-nc-nd/4.0/es_ES
dc.sourceMachine Vision and Applications (manuscript) (2015)es_ES
dc.subjectStereo pictorial structurees_ES
dc.subject2D human posees_ES
dc.subjectSHPEDes_ES
dc.titleStereo Pictorial Structure for 2D Articulated Human Pose Estimationes_ES
dc.typeinfo:eu-repo/semantics/preprintes_ES
dc.relation.publisherversionhttp://dx.doi.org/10.1007/s00138-015-0742-6es_ES
dc.relation.projectIDGobierno de España. TIN2012-32952 (BROCA)es_ES
dc.rights.accessRightsinfo:eu-repo/semantics/openAccesses_ES


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record