Communication Dans Un Congrès Année : 2005

Video classification based on low-level feature fusion model

Résumé

This article presents a new system for automatically extracting high-level video concepts. The novelty of the approach lies in the feature fusion method. The system architecture is divided into three steps. The first step consists in creating sensors from a low-level (color or texture) descriptor, and a Support Vector Machine (SVM) learning to recognize a given concept (for example, “beach” or “road”). The sensor fusion step is the combination of several sensors for each concept. Finally, as the concepts depend on context, the concept fusion step models interaction between concepts in order to modify their prediction. The fusion method is based on the Transferable Belief Model (TBM). It offers an appropriate framework for modeling source uncertainty and interaction between concepts. Results obtained on TREC video protocol demonstrate the improvement provided by such a combination, compared to mono-source information.

Fichier principal
Vignette du fichier
05_eusipco_guironnet_trec.pdf (270.83 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Licence
Loading...

Dates et versions

hal-00365259 , version 1 (02-03-2009)

Licence

Identifiants

  • HAL Id : hal-00365259 , version 1

Citer

Mickael Guironnet, Denis Pellerin, Michèle Rombaut. Video classification based on low-level feature fusion model. EUSIPCO 2005 - 13th European Signal Processing Conference (EUSIPCO'05), Sep 2005, Antalya, Turkey. pp.CD. ⟨hal-00365259⟩
360 Consultations
233 Téléchargements

Partager

  • More