1. accedaCRIS
  2. Publicaciones
  3. Actas de congresos
Please use this identifier to cite or link to this item: http://hdl.handle.net/10553/72522
DC FieldValueLanguage
dc.contributor.authorZimmer, Henningen_US
dc.contributor.authorBruhn, Andresen_US
dc.contributor.authorWeickert, Joachimen_US
dc.contributor.authorValgaerts, Levien_US
dc.contributor.authorSalgado De la Nuez, Agustínen_US
dc.contributor.authorRosenhahn, Bodoen_US
dc.contributor.authorSeidel, Hans-Peteren_US
dc.date.accessioned2020-05-18T11:32:40Z-
dc.date.available2020-05-18T11:32:40Z-
dc.date.issued2009en_US
dc.identifier.isbn978-3-642-03640-8en_US
dc.identifier.issn0302-9743en_US
dc.identifier.otherWoS-
dc.identifier.urihttp://hdl.handle.net/10553/72522-
dc.description.abstractWe introduce the concept of complementarity between data and smoothness term in modern variational optic flow methods. First we design a sophisticated data term that incorporates HSV colour representation with higher order constancy assumptions, completely separate robust penalisation, and constraint normalisation. Our anisotropic smoothness term reduces smoothing in the data constraint direction instead of the image edge direction, while enforcing a strong filling-in effect orthogonal to it. This allows optimal complementarity between both terms and avoids undesirable interference. The high quality of our complementary optic flow (COF) approach is demonstrated by the current top ranking result at the Middlebury benchmark.en_US
dc.languageengen_US
dc.relation.ispartofLecture Notes in Computer Scienceen_US
dc.sourceCremers D., Boykov Y., Blake A., Schmidt F.R. (eds), Energy Minimization Methods In Computer Vision And Pattern Recognition, Proceedings [ISSN 0302-9743], v. 5681, p. 207-220, (2009)en_US
dc.subject120304 Inteligencia artificialen_US
dc.subject.otherComputationen_US
dc.subject.otherMotionen_US
dc.titleComplementary optic flowen_US
dc.typeinfo:eu-repo/semantics/conferenceObjecten_US
dc.typeConferenceObjecten_US
dc.relation.conference7th International Conference on Energy Minimization Methods in Computer Vision and Pattern Recognitionen_US
dc.identifier.doi10.1007/978-3-642-03641-5_16en_US
dc.identifier.scopus70350576737-
dc.identifier.isi000274187100016-
dc.contributor.authorscopusid26667379500-
dc.contributor.authorscopusid6603722894-
dc.contributor.authorscopusid7004916957-
dc.contributor.authorscopusid25522589600-
dc.contributor.authorscopusid56268272100-
dc.contributor.authorscopusid57203083760-
dc.contributor.authorscopusid7202927645-
dc.identifier.eissn1611-3349-
dc.description.lastpage220en_US
dc.description.firstpage207en_US
dc.relation.volume5681en_US
dc.investigacionIngeniería y Arquitecturaen_US
dc.type2Actas de congresosen_US
dc.contributor.daisngid2599648-
dc.contributor.daisngid823591-
dc.contributor.daisngid100055-
dc.contributor.daisngid3139596-
dc.contributor.daisngid1889991-
dc.contributor.daisngid144639-
dc.contributor.daisngid162650-
dc.identifier.eisbn978-3-642-03641-5-
dc.utils.revisionSíen_US
dc.contributor.wosstandardWOS:Zimmer, H-
dc.contributor.wosstandardWOS:Bruhn, A-
dc.contributor.wosstandardWOS:Weickert, J-
dc.contributor.wosstandardWOS:Valgaerts, L-
dc.contributor.wosstandardWOS:Salgado, A-
dc.contributor.wosstandardWOS:Rosenhahn, B-
dc.contributor.wosstandardWOS:Seidel, HP-
dc.date.coverdateNoviembre 2009en_US
dc.identifier.conferenceidevents120699-
dc.identifier.ulpgcSíes
item.grantfulltextnone-
item.fulltextSin texto completo-
crisitem.event.eventsstartdate24-08-2009-
crisitem.event.eventsenddate27-08-2009-
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.orcid0000-0002-6142-3432-
crisitem.author.parentorgIU de Cibernética, Empresa y Sociedad (IUCES)-
crisitem.author.fullNameSalgado De La Nuez, Agustín-
Appears in Collections:Actas de congresos
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.