Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/54429
DC FieldValueLanguage
dc.contributor.authorAlvarez, Luisen_US
dc.contributor.authorDeriche, Rachiden_US
dc.contributor.authorPapadopoulo, Théoen_US
dc.contributor.authorSánchez, Javieren_US
dc.date.accessioned2019-02-18T10:45:49Z-
dc.date.available2019-02-18T10:45:49Z-
dc.date.issued2007en_US
dc.identifier.issn0920-5691en_US
dc.identifier.urihttp://hdl.handle.net/10553/54429-
dc.description.abstractTraditional techniques of dense optical flow estimation do not generally yield symmetrical solutions: the results will differ if they are applied between images I 1 and I 2 or between images I 2 and I 1. In this work, we present a method to recover a dense optical flow field map from two images, while explicitely taking into account the symmetry across the images as well as possible occlusions in the flow field. The idea is to consider both displacements vectors from I 1 to I 2 and I 2 to I 1 and to minimise an energy functional that explicitely encodes all those properties. This variational problem is then solved using the gradient flow defined by the Euler-Lagrange equations associated to the energy. To prove the importance of the concepts of symmetry and occlusions for optical flow computation, we have extended a classical approach to handle those. Experiments clearly show the added value of these properties to improve the accuracy of the computed flows. Figures appear in color in the online version of this paper. © 2007 Springer Science+Business Media, LLC.
dc.languageengen_US
dc.publisher0920-5691-
dc.relation.ispartofInternational Journal of Computer Visionen_US
dc.sourceInternational Journal of Computer Vision[ISSN 0920-5691],v. 75, p. 371-385en_US
dc.subject120601 Construcción de algoritmosen_US
dc.subject120602 Ecuaciones diferencialesen_US
dc.subject120326 Simulaciónen_US
dc.subject220990 Tratamiento digital. Imágenesen_US
dc.subject120304 Inteligencia artificialen_US
dc.titleSymmetrical dense optical flow estimation with occlusions detectionen_US
dc.typeinfo:eu-repo/semantics/Articleen_US
dc.typeArticleen_US
dc.identifier.doi10.1007/s11263-007-0041-4
dc.identifier.scopus34548539425-
dc.identifier.isi000249539000004-
dc.contributor.authorscopusid55640159000-
dc.contributor.authorscopusid7003952036-
dc.contributor.authorscopusid6602252094-
dc.contributor.authorscopusid22735426600-
dc.description.lastpage385-
dc.description.firstpage371-
dc.relation.volume75-
dc.type2Artículoen_US
dc.identifier.externalWOS:000249539000004-
dc.identifier.externalWOS:000249539000004-
dc.date.coverdateDiciembre 2007
dc.identifier.ulpgces
dc.description.jcr3,381
dc.description.jcrqQ1
dc.description.scieSCIE
item.grantfulltextnone-
item.fulltextSin texto completo-
crisitem.author.deptGIR Modelos Matemáticos-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.deptGIR IUCES: Centro de Tecnologías de la Imagen-
crisitem.author.deptIU de Cibernética, Empresa y Sociedad (IUCES)-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.orcid0000-0002-6953-9587-
crisitem.author.orcid0000-0001-8514-4350-
crisitem.author.parentorgDepartamento de Informática y Sistemas-
crisitem.author.parentorgIU de Cibernética, Empresa y Sociedad (IUCES)-
crisitem.author.fullNameÁlvarez León, Luis Miguel-
crisitem.author.fullNameSánchez Pérez, Javier-
Appears in Collections:Artículos
Show simple item record

Google ScholarTM

Check

Altmetric


Share



Export metadata



Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.