Trajectory based Primitive Events for learning and recognizing Activity

Abstract : This paper proposes a framework to recognize and classify loosely constrained activities with minimal supervision. The framework use basic trajectory information as input and goes up to video interpretation. The work reduces the gap between low-level information and semantic interpretation, building an intermediate layer composed Primitive Events. The proposed representation for primitive events aims at capturing small meaningful motions over the scene with the advantage of been learnt in an unsupervised manner. We propose the modelling of an activity using Primitive Events as the main descriptors. The activity model is built in a semi-supervised way using only real tracking data. Finally we validate the descriptors by recognizing and labelling modelled activities in a home-care application dataset.
Type de document :
Communication dans un congrès
Second IEEE International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS2009), Sep 2009, Kyoto, Japan. 2009
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00503209
Contributeur : Guido Pusiol <>
Soumis le : vendredi 16 juillet 2010 - 19:48:58
Dernière modification le : vendredi 16 juillet 2010 - 21:12:31
Document(s) archivé(s) le : vendredi 22 octobre 2010 - 15:24:24

Fichier

PID967691.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00503209, version 1

Collections

Citation

Guido Pusiol, François Bremond, Monique Thonnat. Trajectory based Primitive Events for learning and recognizing Activity. Second IEEE International Workshop on Tracking Humans for the Evaluation of their Motion in Image Sequences (THEMIS2009), Sep 2009, Kyoto, Japan. 2009. 〈inria-00503209〉

Partager

Métriques

Consultations de
la notice

288

Téléchargements du document

145