Extraction of layers of similar motion through combinatorial techniques

Romain Dupont 1 Nikos Paragios 2, 3 Renaud Keriven 4 Philippe Fuchs 5
1 LIST - Laboratoire d'Intégration des Systèmes et des Technologies
2 UPEM - Université Paris-Est Marne-la-Vallée
3 ENPC - École des Ponts ParisTech
4 CERTIS - Centre d'Enseignement et de Recherche en Technologies de l'Information et Systèmes
5 équipe RV&RA
CAOR - Centre de Robotique
Abstract : In this paper we present a new technique to extract layers in a video sequence. To this end, we assume that the observed scene is composed of several transparent layers, that their motion in the 2D plane can be approximated with an affine model. The objective of our approach is the estimation of these motion models as well as the estimation of their support in the image domain. Our technique is based on an iterative process that integrates robust motion estimation, MRF-based formulation, combinatorial optimization and the use of visual as well as motion features to recover the parameters of the motion models as well as their support layers. Special handling of occlusions as well as adaptive techniques to detect new objects in the scene are also considered. Promising results demonstrate the potentials of our approach.
Type de document :
Communication dans un congrès
Liste complète des métadonnées
https://hal-mines-paristech.archives-ouvertes.fr/hal-00784751
Contributeur : Philippe Fuchs <>
Soumis le : lundi 4 février 2013 - 15:45:12
Dernière modification le : mercredi 23 janvier 2019 - 14:38:28

Lien texte intégral

istex

Identifiants

Collections

UPEC | UPEC-UPEM | IMAGINE | ENPC | ENSMP_CAOR | ENSMP | PARISTECH | INSTITUT-TELECOM | CEA | DRT | PSL | LIST

Citation

Romain Dupont, Nikos Paragios, Renaud Keriven, Philippe Fuchs. Extraction of layers of similar motion through combinatorial techniques. International Workshop On Energy Minimization Methods, Nov 2005, St. Augustine, United States. pp 220-234, ⟨10.1007/11585978_15⟩. ⟨hal-00784751⟩

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

297

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD