Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/54429
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Alvarez, Luis | en_US |
dc.contributor.author | Deriche, Rachid | en_US |
dc.contributor.author | Papadopoulo, Théo | en_US |
dc.contributor.author | Sánchez, Javier | en_US |
dc.date.accessioned | 2019-02-18T10:45:49Z | - |
dc.date.available | 2019-02-18T10:45:49Z | - |
dc.date.issued | 2007 | en_US |
dc.identifier.issn | 0920-5691 | en_US |
dc.identifier.uri | http://hdl.handle.net/10553/54429 | - |
dc.description.abstract | Traditional 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.language | eng | en_US |
dc.publisher | 0920-5691 | - |
dc.relation.ispartof | International Journal of Computer Vision | en_US |
dc.source | International Journal of Computer Vision[ISSN 0920-5691],v. 75, p. 371-385 | en_US |
dc.subject | 120601 Construcción de algoritmos | en_US |
dc.subject | 120602 Ecuaciones diferenciales | en_US |
dc.subject | 120326 Simulación | en_US |
dc.subject | 220990 Tratamiento digital. Imágenes | en_US |
dc.subject | 120304 Inteligencia artificial | en_US |
dc.title | Symmetrical dense optical flow estimation with occlusions detection | en_US |
dc.type | info:eu-repo/semantics/Article | en_US |
dc.type | Article | en_US |
dc.identifier.doi | 10.1007/s11263-007-0041-4 | |
dc.identifier.scopus | 34548539425 | - |
dc.identifier.isi | 000249539000004 | - |
dc.contributor.authorscopusid | 55640159000 | - |
dc.contributor.authorscopusid | 7003952036 | - |
dc.contributor.authorscopusid | 6602252094 | - |
dc.contributor.authorscopusid | 22735426600 | - |
dc.description.lastpage | 385 | - |
dc.description.firstpage | 371 | - |
dc.relation.volume | 75 | - |
dc.type2 | Artículo | en_US |
dc.identifier.external | WOS:000249539000004 | - |
dc.identifier.external | WOS:000249539000004 | - |
dc.date.coverdate | Diciembre 2007 | |
dc.identifier.ulpgc | Sí | es |
dc.description.jcr | 3,381 | |
dc.description.jcrq | Q1 | |
dc.description.scie | SCIE | |
item.grantfulltext | none | - |
item.fulltext | Sin texto completo | - |
crisitem.author.dept | GIR Modelos Matemáticos | - |
crisitem.author.dept | Departamento de Informática y Sistemas | - |
crisitem.author.dept | GIR IUCES: Centro de Tecnologías de la Imagen | - |
crisitem.author.dept | IU de Cibernética, Empresa y Sociedad (IUCES) | - |
crisitem.author.dept | Departamento de Informática y Sistemas | - |
crisitem.author.orcid | 0000-0002-6953-9587 | - |
crisitem.author.orcid | 0000-0001-8514-4350 | - |
crisitem.author.parentorg | Departamento de Informática y Sistemas | - |
crisitem.author.parentorg | IU de Cibernética, Empresa y Sociedad (IUCES) | - |
crisitem.author.fullName | Álvarez León, Luis Miguel | - |
crisitem.author.fullName | Sánchez Pérez, Javier | - |
Appears in Collections: | Artículos |
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.