Jointly optical flow and occlusion estimation for images with large displacements

Mostra el registre complet Registre parcial de l'ítem

• 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.description Comunicació presentada a: VISIGRAPP 2018, celebrat del 27 al 29 de gemer de 2018 a Funchal, Madeira, Portugal.
• 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.en
• dc.format.mimetype application/pdf*
• 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.doi http://dx.doi.org/10.5220/0006716305880595
• dc.identifier.isbn 978-989-758-290-5
• dc.identifier.uri http://hdl.handle.net/10230/37097
• dc.language.iso eng
• 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.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Optical flowen
• dc.subject.keyword Exhaustive searchen
• dc.subject.keyword Large displacementsen
• dc.subject.keyword Illumination changesen
• dc.title Jointly optical flow and occlusion estimation for images with large displacements
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/publishedVersion