Mostra el registre d'ítem simple
A joint model for 2D and 3D pose estimation from a single image
dc.contributor.author | Simó Serra, Edgar |
dc.contributor.author | Quattoni, Ariadna Julieta |
dc.contributor.author | Torras, Carme |
dc.contributor.author | Moreno-Noguer, Francesc |
dc.contributor.other | Universitat Politècnica de Catalunya. Departament de Llenguatges i Sistemes Informàtics |
dc.contributor.other | Institut de Robòtica i Informàtica Industrial |
dc.date.accessioned | 2013-12-10T10:35:59Z |
dc.date.created | 2013 |
dc.date.issued | 2013 |
dc.identifier.citation | Simo, E. [et al.]. A joint model for 2D and 3D pose estimation from a single image. A: IEEE Conference on Computer Vision and Pattern Recognition. "Proceedings : 2013 IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2013". Portland, Oregon: Institute of Electrical and Electronics Engineers (IEEE), 2013, p. 3634-3641. |
dc.identifier.uri | http://hdl.handle.net/2117/20946 |
dc.description.abstract | We introduce a novel approach to automatically recover 3D human pose from a single image. Most previous work follows a pipelined approach: initially, a set of 2D features such as edges, joints or silhouettes are detected in the image, and then these observations are used to infer the 3D pose. Solving these two problems separately may lead to erroneous 3D poses when the feature detector has performed poorly. In this paper, we address this issue by jointly solving both the 2D detection and the 3D inference problems. For this purpose, we propose a Bayesian framework that integrates a generative model based on latent variables and discriminative 2D part detectors based on HOGs, and perform inference using evolutionary algorithms. Real experimentation demonstrates competitive results, and the ability of our methodology to provide accurate 2D and 3D pose estimations even when the 2D detectors are inaccurate. |
dc.format.extent | 8 p. |
dc.language.iso | eng |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Robòtica |
dc.subject | Àrees temàtiques de la UPC::Informàtica::Intel·ligència artificial |
dc.subject.lcsh | Computer vision -- Mathematical models |
dc.subject.other | Deformable models |
dc.subject.other | Detectors |
dc.subject.other | Estimation |
dc.subject.other | Joints |
dc.subject.other | Shape |
dc.subject.other | Solid modeling |
dc.subject.other | Three-dimensional displays |
dc.title | A joint model for 2D and 3D pose estimation from a single image |
dc.type | Conference report |
dc.subject.lemac | Visió per ordinador -- Models matemàtics |
dc.contributor.group | Universitat Politècnica de Catalunya. ROBiri - Grup de Robòtica de l'IRI |
dc.contributor.group | Universitat Politècnica de Catalunya. VIS - Visió Artificial i Sistemes Intel·ligents |
dc.contributor.group | Universitat Politècnica de Catalunya. LARCA - Laboratori d'Algorísmia Relacional, Complexitat i Aprenentatge |
dc.identifier.doi | 10.1109/CVPR.2013.466 |
dc.description.peerreviewed | Peer Reviewed |
dc.relation.publisherversion | http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6619310 |
dc.rights.access | Restricted access - publisher's policy |
local.identifier.drac | 12912706 |
dc.description.version | Postprint (published version) |
dc.relation.projectid | info:eu-repo/grantAgreement/MICINN//DPI2011-27510/ES/PERCEPCION Y ACCION EN PROBLEMAS DE ROBOTICA CON ESPACIOS DE ESTADOS GRANDES/ |
dc.relation.projectid | info:eu-repo/grantAgreement/EC/FP7/269959/EU/Intelligent observation and execution of Actions and manipulations/INTELLACT |
dc.date.lift | 10000-01-01 |
local.citation.author | Simo, E.; Quattoni, A.J.; Torras, C.; Moreno-Noguer, F. |
local.citation.contributor | IEEE Conference on Computer Vision and Pattern Recognition |
local.citation.pubplace | Portland, Oregon |
local.citation.publicationName | Proceedings : 2013 IEEE Conference on Computer Vision and Pattern Recognition : CVPR 2013 |
local.citation.startingPage | 3634 |
local.citation.endingPage | 3641 |