Multi-View Object Segmentation in Space and Time - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2013

Multi-View Object Segmentation in Space and Time

Abstract

In this paper, we address the problem of object segmentation in multiple views or videos when two or more viewpoints of the same scene are available. We propose a new approach that propagates segmentation coherence information in both space and time, hence allowing evidences in one image to be shared over the complete set. To this aim the segmentation is cast as a single efficient labeling problem over space and time with graph cuts. In contrast to most existing multi-view segmentation methods that rely on some form of dense reconstruction, ours only requires a sparse 3D sampling to propagate information between viewpoints. The approach is thoroughly evaluated on standard multi-view datasets, as well as on videos. With static views, results compete with state of the art methods but they are achieved with significantly fewer viewpoints. With multiple videos, we report results that demonstrate the benefit of segmentation propagation through temporal cues.
Fichier principal
Vignette du fichier
paper_final.pdf (3.27 Mo) Télécharger le fichier
HalfPipe.wmv (16.27 Mo) Télécharger le fichier
seg_dancers.avi (10.41 Mo) Télécharger le fichier
teaser.pdf (2.5 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
Format : Video
Origin : Files produced by the author(s)
Format : Video
Origin : Files produced by the author(s)
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00873544 , version 1 (26-07-2016)

Licence

Attribution

Identifiers

Cite

Abdelaziz Djelouah, Jean-Sébastien Franco, Edmond Boyer, Francois Le Clerc, Patrick Pérez. Multi-View Object Segmentation in Space and Time. ICCV 2013 - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. pp.2640-2647, ⟨10.1109/ICCV.2013.328⟩. ⟨hal-00873544⟩
1076 View
352 Download

Altmetric

Share

Gmail Facebook X LinkedIn More