Welcome to the UPF Digital Repository

Jointly optical flow and occlusion estimation for images with large displacements

Show simple item record

dc.contributor.author Lazcano, Vanel
dc.contributor.author Garrido Ostermann, Luis
dc.contributor.author Ballester, Coloma
dc.date.accessioned 2019-04-11T13:24:36Z
dc.date.available 2019-04-11T13:24:36Z
dc.date.issued 2018
dc.identifier.citation Lazcano V, Garrido L, Ballester C. Jointly optical flow and occlusion estimation for images with large displacements. In: Bechmann D, Cláudio AP, Braz J. Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP. 2018 Jan 27-29; Funchal, Madeira, Portugal. Setúbal: Scitepress; 2018. p. 588-95. DOI: 10.5220/0006716305880595
dc.identifier.isbn 978-989-758-290-5
dc.identifier.uri http://hdl.handle.net/10230/37097
dc.description.abstract This paper deals with motion estimation of objects in a video sequence. This problem is known as optical flow estimation. Traditional models to estimate it fail in presence of occlusions and non-uniform illumination. To tackle these problems we propose a variational model to jointly estimate optical flow and occlusions. The proposed model is able to deal with the usual drawback of variational methods in dealing with large displacements of objects in the scene which are larger than the object itself. The addition of a term that balances gradient and intensities increases the robustness to illumination changes of the proposed model. The inclusion of a supplementary matching obtained by exhaustive search in specific locations helps to follow large displacements.
dc.description.abstract Comunicació presentada a: VISIGRAPP 2018, celebrat del 27 al 29 de gemer de 2018 a Funchal, Madeira, Portugal.
dc.format.mimetype application/pdf
dc.language.iso eng
dc.publisher SCITEPRESS
dc.publisher SCITEPRESS
dc.relation.ispartof Bechmann D, Cláudio AP, Braz J. Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2018) - Volume 5: VISAPP. 2018 Jan 27-29; Funchal, Madeira, Portugal. Setúbal: Scitepress; 2018. p. 588-95.
dc.rights © 2018 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved
dc.title Jointly optical flow and occlusion estimation for images with large displacements
dc.type info:eu-repo/semantics/conferenceObject
dc.identifier.doi http://dx.doi.org/10.5220/0006716305880595
dc.subject.keyword Optical flow
dc.subject.keyword Exhaustive search
dc.subject.keyword Large displacements
dc.subject.keyword Illumination changes
dc.rights.accessRights info:eu-repo/semantics/openAccess
dc.type.version info:eu-repo/semantics/publishedVersion


This item appears in the following Collection(s)

Show simple item record

Search DSpace


Advanced Search

Browse

My Account

Statistics

Compliant to Partaking