Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues

Jose Lezama 1 Karteek Alahari 2, 3 Josef Sivic 2, 3 Ivan Laptev 2, 3
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : Video provides not only rich visual cues such as motion and appearance, but also much less explored long-range temporal interactions among objects. We aim to capture such interactions and to construct a powerful intermediate-level video representation for subsequent recognition. Motivated by this goal, we seek to obtain spatio-temporal oversegmentation of a video into regions that respect object boundaries and, at the same time, associate object pixels over many video frames. The contributions of this paper are two-fold. First, we develop an efficient spatiotemporal video segmentation algorithm, which naturally incorporates long-range motion cues from the past and future frames in the form of clusters of point tracks with coherent motion. Second, we devise a new track clustering cost function that includes occlusion reasoning, in the form of depth ordering constraints, as well as motion similarity along the tracks. We evaluate the proposed approach on a challenging set of video sequences of office scenes from feature length movies.
Type de document :
Communication dans un congrès
CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3369 - 3376, 2011, 〈http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6044588〉. 〈10.1109/CVPR.2011.6044588〉
Liste complète des métadonnées

Littérature citée [39 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00817961
Contributeur : Karteek Alahari <>
Soumis le : jeudi 17 octobre 2013 - 19:02:25
Dernière modification le : lundi 28 mai 2018 - 15:10:02
Document(s) archivé(s) le : samedi 18 janvier 2014 - 02:40:18

Fichier

lezama11.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Jose Lezama, Karteek Alahari, Josef Sivic, Ivan Laptev. Track to the Future: Spatio-temporal Video Segmentation with Long-range Motion Cues. CVPR - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3369 - 3376, 2011, 〈http://ieeexplore.ieee.org/xpl/articleDetails.jsp?arnumber=6044588〉. 〈10.1109/CVPR.2011.6044588〉. 〈hal-00817961〉

Partager

Métriques

Consultations de la notice

837

Téléchargements de fichiers

680