A Novel Approach for Fast Action Recognition using Simple Features

Abstract : We propose a new method for human action recognition from video streams that is fast and robust to random noise, partial occlusions and large changes in camera views. We extract features in the Fourier domain using the bounding boxes containing the silhouettes of a human for a number of frames representing an action. After preprocessing, we divide each space-time volume into space-time sub-volumes and compute their corresponding mean-power spectra as our feature vectors. Our features result in high classification performance using a weighted variant of the Euclidean distance. We require no camera calibration or synchronization and make use of multiple cameras to enrich the training data towards view-invariance. We test the robustness of our method using a variety of experiments including synthetic data generated in a virtual environment and real-world data used by other researchers. We also provide an experimental comparison, using the same data, between our method and two recent alternatives.
Type de document :
Communication dans un congrès
The Eighth International Workshop on Visual Surveillance - VS2008, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [11 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00325610
Contributeur : Peter Sturm <>
Soumis le : lundi 29 septembre 2008 - 17:26:46
Dernière modification le : lundi 29 septembre 2008 - 17:29:06
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:41:03

Fichier

VS2008-Oral-4a.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00325610, version 1

Collections

Citation

Hossein Ragheb, Sergio Velastin, Paolo Remagnino, Tim Ellis. A Novel Approach for Fast Action Recognition using Simple Features. The Eighth International Workshop on Visual Surveillance - VS2008, Oct 2008, Marseille, France. 2008. 〈inria-00325610〉

Partager

Métriques

Consultations de la notice

96

Téléchargements de fichiers

71