Multi-Valued Motion Fields Estimation for Transparent Sequences with a Variational Approach - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2006

Multi-Valued Motion Fields Estimation for Transparent Sequences with a Variational Approach

Résumé

Most optical flow algorithms provide flow fields as single valued functions of the image sequence domains. Only a very few of them attempt to recover multiple motion vectors at given location, which is necessary when some transparent layers are moving independently. In this report we introduce a novel framework for modeling multivalued motion fields, and propose an energy minimization formulation with smoothing terms and terms implementing velocity model competition. We illustrate the capabilities of this approach on synthetic and real sequences.
Fichier principal
Vignette du fichier
report.pdf (4.57 Mo) Télécharger le fichier

Dates et versions

inria-00077285 , version 1 (30-05-2006)
inria-00077285 , version 2 (06-06-2006)

Identifiants

  • HAL Id : inria-00077285 , version 1

Citer

Alonso Ramirez-Manzanares, Mariano Rivera, Pierre Kornprobst, François Lauze. Multi-Valued Motion Fields Estimation for Transparent Sequences with a Variational Approach. [Research Report] 2006, pp.25. ⟨inria-00077285v1⟩
218 Consultations
126 Téléchargements

Partager

Gmail Facebook X LinkedIn More