Sparse Multi-View Consistency for Object Segmentation - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Pattern Analysis and Machine Intelligence Année : 2015

Sparse Multi-View Consistency for Object Segmentation

Résumé

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.
Fichier principal
Vignette du fichier
paper_V3.pdf (17.88 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01115557 , version 1 (11-02-2015)

Licence

Copyright (Tous droits réservés)

Identifiants

Citer

Abdelaziz Djelouah, Jean-Sébastien Franco, Edmond Boyer, François Le Clerc, Patrick Pérez. Sparse Multi-View Consistency for Object Segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2015, 37 (9), pp.1890-1903. ⟨10.1109/TPAMI.2014.2385704⟩. ⟨hal-01115557⟩
380 Consultations
661 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More