Skip to Main content Skip to Navigation
Reports

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

Alonso Ramirez-Manzanares 1 Mariano Rivera 1 Pierre Kornprobst 2 François Lauze 3
2 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique de l'École normale supérieure, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
Abstract : 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.
Document type :
Reports
Complete list of metadata

Cited literature [1 references]  Display  Hide  Download

https://hal.inria.fr/inria-00077285
Contributor : Rapport de Recherche Inria <>
Submitted on : Tuesday, June 6, 2006 - 10:12:53 AM
Last modification on : Tuesday, September 22, 2020 - 3:58:34 AM
Long-term archiving on: : Monday, September 20, 2010 - 2:35:53 PM

Identifiers

  • HAL Id : inria-00077285, version 2

Collections

Citation

Alonso Ramirez-Manzanares, Mariano Rivera, Pierre Kornprobst, François Lauze. Multi-Valued Motion Fields Estimation for Transparent Sequences with a Variational Approach. [Research Report] RR-5920, INRIA. 2006, pp.25. ⟨inria-00077285v2⟩

Share

Metrics

Record views

424

Files downloads

571