Action Recognition with a Bio--Inspired Feedforward Motion Processing Model: The Richness of Center-Surround Interactions

Maria-Jose Escobar 1 Pierre Kornprobst 1
1 ODYSSEE - Computer and biological vision
DI-ENS - Département d'informatique de l'École normale supérieure, CRISAM - Inria Sophia Antipolis - Méditerranée , ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, ENPC - École des Ponts ParisTech
Abstract : Here we show that reproducing the functional properties of MT cells with various center--surround interactions enriches motion representation and improves the action recognition performance. To do so, we propose a simplified bio--inspired model of the motion pathway in primates: It is a feedforward model restricted to V1-MT cortical layers, cortical cells cover the visual space with a foveated structure, and more importantly, we reproduce some of the richness of center-surround interactions of MT cells. Interestingly, as observed in neurophysiology, our MT cells not only behave like simple velocity detectors, but also respond to several kinds of motion contrasts. Results show that this diversity of motion representation at the MT level is a major advantage for an action recognition task. Defining motion maps as our feature vectors, we used a standard classification method on the Weizmann database: We obtained an average recognition rate of 98.9%, which is superior to the recent results by Jhuang et al. (2007). These promising results encourage us to further develop bio--inspired models incorporating other brain mechanisms and cortical layers in order to deal with more complex videos.
Type de document :
Communication dans un congrès
European Conference on Computer Vision 2008, Oct 2008, Marseille, France. Springer, 5305, pp.186--199, 2008, Lecture Notes in Computer Science. 〈10.1007/978-3-540-88693-8_14〉
Liste complète des métadonnées

Littérature citée [38 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00423322
Contributeur : Alain Monteil <>
Soumis le : vendredi 9 octobre 2009 - 14:45:29
Dernière modification le : jeudi 11 janvier 2018 - 16:21:47
Document(s) archivé(s) le : mardi 16 octobre 2012 - 12:05:43

Fichier

escobar-kornprobst_08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Maria-Jose Escobar, Pierre Kornprobst. Action Recognition with a Bio--Inspired Feedforward Motion Processing Model: The Richness of Center-Surround Interactions. European Conference on Computer Vision 2008, Oct 2008, Marseille, France. Springer, 5305, pp.186--199, 2008, Lecture Notes in Computer Science. 〈10.1007/978-3-540-88693-8_14〉. 〈inria-00423322〉

Partager

Métriques

Consultations de la notice

180

Téléchargements de fichiers

274