Action Recognition Robust to Background Clutter by Using Stereo Vision

Jordi Sanchez-Riera 1 Jan Cech 1 Radu Horaud 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : An action recognition algorithm which works with binocular videos is presented. The proposed method uses standard bag-of-words approach, where each action clip is represented as a histogram of visual words. However, instead of using classical monocular HoG/HoF features, we construct features from the scene-flow computed by a matching algorithm on the sequence of stereo images. The resulting algorithm has a comparable or slightly better recognition accuracy than standard monocular solution in controlled setup with a single actor present in the scene. However, we show its significantly improved performance in case of strong background clutter due to other people freely moving behind the actor.
Type de document :
Communication dans un congrès
Andrea Fusiello and Vittorio Murino and Rita Cucchiara. 4th International Workshop on Video Event Categorization, Tagging and Retrieval, Oct 2012, Firenze, Italy. Springer, 7583, pp.332-341, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-33863-2_33〉
Liste complète des métadonnées

Littérature citée [23 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00768670
Contributeur : Team Perception <>
Soumis le : samedi 22 décembre 2012 - 18:42:14
Dernière modification le : mercredi 11 avril 2018 - 01:58:25
Document(s) archivé(s) le : samedi 23 mars 2013 - 03:47:42

Fichier

ws106.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Jordi Sanchez-Riera, Jan Cech, Radu Horaud. Action Recognition Robust to Background Clutter by Using Stereo Vision. Andrea Fusiello and Vittorio Murino and Rita Cucchiara. 4th International Workshop on Video Event Categorization, Tagging and Retrieval, Oct 2012, Firenze, Italy. Springer, 7583, pp.332-341, 2012, Lecture Notes in Computer Science. 〈10.1007/978-3-642-33863-2_33〉. 〈hal-00768670〉

Partager

Métriques

Consultations de la notice

496

Téléchargements de fichiers

258