Sparse Multi-View Consistency for Object Segmentation

Abdelaziz Djelouah 1, 2 Jean-Sébastien Franco 1 Edmond Boyer 1 François Le Clerc 2 Patrick Pérez 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.
Document type :
Journal articles
Liste complète des métadonnées

Cited literature [36 references]  Display  Hide  Download

https://hal.inria.fr/hal-01115557
Contributor : Jean-Sébastien Franco <>
Submitted on : Wednesday, February 11, 2015 - 12:03:23 PM
Last modification on : Wednesday, April 11, 2018 - 1:58:37 AM
Document(s) archivé(s) le : Thursday, May 28, 2015 - 9:56:49 AM

File

paper_V3.pdf
Files produced by the author(s)

Licence


Copyright

Identifiers

Collections

Citation

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, Institute of Electrical and Electronics Engineers, 2015, 37 (9), pp.1890-1903. ⟨10.1109/TPAMI.2014.2385704⟩. ⟨hal-01115557⟩

Share

Metrics

Record views

788

Files downloads

810