Sparse Multi-View Consistency for Object Segmentation

Abdelaziz Djelouah 1, 2 Jean-Sébastien Franco 1 Edmond Boyer 1 François Le Clerc 2 Patrick Perez 2
1 MORPHEO - Capture and Analysis of Shapes in Motion
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Multiple view segmentation consists in segmenting objects simultaneously in several views. A key issue in that respect and compared to monocular settings is to ensure propagation of segmentation information between views while minimizing complexity and computational cost. In this work, we first investigate the idea that examining measurements at the projections of a sparse set of 3D points is sufficient to achieve this goal. The proposed algorithm softly assigns each of these 3D samples to the scene background if it projects on the background region in at least one view, or to the foreground if it projects on foreground region in all views. Second, we show how other modalities such as depth may be seamlessly integrated in the model and benefit the segmentation. The paper exposes a detailed set of experiments used to validate the algorithm, showing results comparable with the state of art, with reduced computational complexity. We also discuss the use of different modalities for specific situations, such as dealing with a low number of viewpoints or a scene with color ambiguities between foreground and background.
Type de document :
Article dans une revue
IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2015, 37 (9), pp.1890-1903. 〈10.1109/TPAMI.2014.2385704〉
Liste complète des métadonnées

Littérature citée [36 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01115557
Contributeur : Jean-Sébastien Franco <>
Soumis le : mercredi 11 février 2015 - 12:03:23
Dernière modification le : lundi 9 octobre 2017 - 13:36:08
Document(s) archivé(s) le : jeudi 28 mai 2015 - 09:56:49

Fichier

paper_V3.pdf
Fichiers produits par l'(les) auteur(s)

Licence


Copyright (Tous droits réservés)

Identifiants

Collections

Citation

Abdelaziz Djelouah, Jean-Sébastien Franco, Edmond Boyer, François Le Clerc, Patrick Perez. Sparse Multi-View Consistency for Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, Institute of Electrical and Electronics Engineers, 2015, 37 (9), pp.1890-1903. 〈10.1109/TPAMI.2014.2385704〉. 〈hal-01115557〉

Partager

Métriques

Consultations de la notice

644

Téléchargements de fichiers

637