Please use this identifier to cite or link to this item:
http://hdl.handle.net/10553/11276
Title: | Optical flow estimation with consistent spatio-temporal coherence models | Authors: | Sánchez, Javier Salgado de la Nuez, Agustín Javier Monzón, Nelson |
UNESCO Clasification: | 220990 Tratamiento digital. Imágenes | Keywords: | Optical flow Variational methods PDE Temporal coherence |
Issue Date: | 2013 | Conference: | 8th International Conference on Computer Vision Theory and Applications, VISAPP 2013 | Abstract: | In this work we propose a new variational model for the consistent estimation of motion fields. The aim of this work is to develop appropriate spatio-temporal coherence models. In this sense, we propose two main contributions: a nonlinear flow constancy assumption, similar in spirit to the nonlinear brightness constancy assumption, which conveniently relates flow fields at different time instants; and a nonlinear temporal regularization scheme, which complements the spatial regularization and can cope with piecewise continuous motion fields. These contributions pose a congruent variational model since all the energy terms, except the spatial regularization, are based on nonlinear warpings of the flow field. This model is more general than its spatial counterpart, provides more accurate solutions and preserves the continuity of optical flows in time. In the experimental results, we show that the method attains better results and, in particular, it considerably improves the accuracy in the presence of large displacements. | URI: | http://hdl.handle.net/10553/11276 | ISBN: | 9789898565471 | Source: | VISAPP 2013 - Proceedings of the International Conference on Computer Vision Theory and Applications,v. 2, p. 366-369 | Rights: | by-nc-nd |
Appears in Collections: | Actas de congresos |
SCOPUSTM
Citations
4
checked on Nov 17, 2024
Page view(s)
97
checked on Apr 13, 2024
Download(s)
263
checked on Apr 13, 2024
Google ScholarTM
Check
Altmetric
Share
Export metadata
Items in accedaCRIS are protected by copyright, with all rights reserved, unless otherwise indicated.