Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/12385
DC FieldValueLanguage
dc.contributor.authorMonzón López, Nelson Manuelen_US
dc.contributor.authorSalgado de la Nuez, Agustín Javieren_US
dc.contributor.authorSánchez, Javieren_US
dc.date.accessioned2014-11-05T10:29:40Z-
dc.date.accessioned2018-06-06T08:57:15Z-
dc.date.available2014-11-05T10:29:40Z-
dc.date.available2018-06-06T08:57:15Z-
dc.date.issued2014en_US
dc.identifier.issn2254-2353en_US
dc.identifier.urihttp://hdl.handle.net/10553/12385-
dc.description.abstractWe analyze the discontinuity preserving problem in TV-L1 optical flow methods. This type of methods typically creates rounded effects at flow boundaries, which usually do not coincide with object contours. A simple strategy to overcome this problem consists in inhibiting the diffusion at high image gradients. In this work, we first introduce a general framework for TV regularizers in optical flow and relate it with some standard approaches. Our survey takes into account several methods that use decreasing functions for mitigating the diffusion at image contours. Consequently, this kind of strategies may produce instabilities in the estimation of the optical flows. Hence, we study the problem of instabilities and show that it actually arises from an ill-posed formulation. From this study, it is possible to come across with different schemes to solve this problem. One of these consists in separating the pure TV process from the mitigating strategy. This has been used in another work and we demonstrate here that it has a good performance. Furthermore, we propose two alternatives to avoid the instability problems: (i) we study a fully automatic approach that solves the problem based on the information of the whole image; (ii) we derive a semi-automatic approach that takes into account the image gradients in a close neighborhood adapting the parameter in each position. In the experimental results, we present a detailed study and comparison between the different alternatives. These methods provide very good results, especially for sequences with a few dominant gradients. Additionally, a surprising effect of these approaches is that they can cope with occlusions. This can be easily achieved by using strong regularizations and high penalizations at image contours.en_US
dc.languageengen_US
dc.relation.ispartofCTIM Technical Reporten_US
dc.sourceCTIM: Technical report. Las Palmas de Gran Canaria: Centro de Tecnologías de la Imágen, 2014. Nº 5. 42 p. ISSN 2254-2353en_US
dc.subject220990 Tratamiento digital. Imágenesen_US
dc.subject.otherOptical flowen_US
dc.subject.otherTotal variationen_US
dc.subject.otherTV-L1en_US
dc.subject.otherVariational methoden_US
dc.subject.otherDiffusion process.en_US
dc.titleDiscontinuity preserving in TV-L1 optical flow methodsen_US
dc.typeinfo:eu-repo/semantics/reporten_US
dc.typeArticlees
dc.investigacionIngeniería y Arquitecturaen_US
dc.rights.accessrightsinfo:eu-repo/semantics/openAccesses
dc.type2Informe técnicoen_US
dc.utils.revisionen_US
dc.identifier.ulpgces
item.fulltextCon texto completo-
item.grantfulltextopen-
crisitem.author.deptAnálisis de Imagen e Ingeniería de Software-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.deptAnálisis de Imagen e Ingeniería de Software-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.deptAnálisis de Imagen e Ingeniería de Software-
crisitem.author.deptDepartamento de Informática y Sistemas-
crisitem.author.orcid0000-0003-0571-9068-
crisitem.author.orcid0000-0001-8514-4350-
crisitem.author.parentorgDepartamento de Informática y Sistemas-
crisitem.author.parentorgDepartamento de Informática y Sistemas-
crisitem.author.parentorgDepartamento de Informática y Sistemas-
crisitem.author.fullNameMonzón López, Nelson Manuel-
crisitem.author.fullNameSalgado De La Nuez, Agustín-
crisitem.author.fullNameSánchez Pérez, Javier-
Appears in Collections:Informe técnico
Thumbnail
CTIM Technical Report
Adobe PDF (10,19 MB)
Show simple item record

Google ScholarTM

Check


Share



Export metadata



This item is licensed under a Creative Commons License Creative Commons