N-Tuple Color Segmentation for Multi-View Silhouette Extraction

Abdelaziz Djelouah 1 Jean-Sébastien Franco 2 Edmond Boyer 2 François Leclerc 1 Patrick Pérez 1
1 Technicolor [Cesson Sévigné]
2 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We present a new method to extract multiple segmentations of an object viewed by multiple cameras, given only the camera calibration. We introduce the n-tuple color model to express inter-view consistency when inferring in each view the foreground and background color models permitting the final segmentation. A color n-tuple is a set of pixel colors associated to the n projections of a 3D point. The first goal is set as finding the MAP estimate of background/foreground color models based on an arbitrary sample set of such n-tuples, such that sam- ples are consistently classified, in a soft way, as "empty" if they project in the background of at least one view, or "occupied" if they project to foreground pixels in all views. An Expectation Maximization framework is then used to alternate between color models and soft classifications. In a final step, all views are segmented based on their attached color models. The approach is significantly simpler and faster than previous multi-view segmentation methods, while providing results of equivalent or better quality.
Type de document :
Communication dans un congrès
ECCV'12 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. Springer, 7576, pp.818-831, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-33715-4_59〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-00735718
Contributeur : Edmond Boyer <>
Soumis le : mercredi 26 septembre 2012 - 15:55:36
Dernière modification le : mercredi 11 avril 2018 - 01:59:36
Document(s) archivé(s) le : jeudi 27 décembre 2012 - 07:05:29

Fichier

Final_N-tuple_Multi-View_Silho...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | LJK_GI | LJK | LJK_GI_MORPHEO | UGA

Citation

Abdelaziz Djelouah, Jean-Sébastien Franco, Edmond Boyer, François Leclerc, Patrick Pérez. N-Tuple Color Segmentation for Multi-View Silhouette Extraction. ECCV'12 - 12th European Conference on Computer Vision, Oct 2012, Firenze, Italy. Springer, 7576, pp.818-831, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-33715-4_59〉. 〈hal-00735718〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

554

Téléchargements de fichiers

737

Contact


archive-ouverte@inria.fr