Relative Dense Tracklets for Human Action Recognition

Abstract : This paper addresses the problem of recognizing human actions in video sequences for home care applications. Recent studies have shown that approaches which use a bag-of-words representation reach high action recognition accuracy. Unfortunately, these approaches have problems to discriminate similar actions, ignoring spatial information of features. As we focus on recognizing subtle differences in behaviour of patients, we propose a novel method which significantly enhances the discriminative properties of the bag-of-words technique. Our approach is based on a dynamic coordinate system, which introduces spatial information to the bag-of-words model, by computing relative tracklets. We perform an extensive evaluation of our approach on three datasets: popular KTH dataset, challenging ADL dataset and our collected Hospital dataset. Experiments show that our representation enhances the discriminative power of features and bag-of-words model, bringing significant improvements in action recognition performance.
Type de document :
Communication dans un congrès
10th IEEE International Conference on Automatic Face and Gesture Recognition, Apr 2013, Shanghai, China. IEEE, pp.1-7, 2013, 〈10.1109/FG.2013.6553699〉
Liste complète des métadonnées

Littérature citée [37 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00806321
Contributeur : Piotr Bilinski <>
Soumis le : vendredi 22 novembre 2013 - 14:28:32
Dernière modification le : mardi 24 juillet 2018 - 15:48:03
Document(s) archivé(s) le : dimanche 23 février 2014 - 02:30:18

Fichier

Relative_Dense_Tracklets_for_H...
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Piotr Bilinski, Etienne Corvee, Slawomir Bak, Francois Bremond. Relative Dense Tracklets for Human Action Recognition. 10th IEEE International Conference on Automatic Face and Gesture Recognition, Apr 2013, Shanghai, China. IEEE, pp.1-7, 2013, 〈10.1109/FG.2013.6553699〉. 〈hal-00806321〉

Partager

Métriques

Consultations de la notice

548

Téléchargements de fichiers

269