Action Recognition Using a Bio-Inspired Feedforward Spiking Network

Maria-Jose Escobar 1 Guillaume Masson 2 Thierry Viéville 3 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
3 CORTEX - Neuromimetic intelligence
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : We propose a bio-inspired feedforward spiking network modeling two brain areas dedicated to motion (V1 and MT), and we show how the spiking output can be exploited in a computer vision application: action recognition. In order to analyze spike trains, we consider two characteristics of the neural code: mean firing rate of each neuron and synchrony between neurons. Interestingly, we show that they carry some relevant information for the action recognition application. We compare our results to Jhuang et al. (Proceedings of the 11th international conference on computer vision, pp. 1–8, 2007) on the Weizmann database. As a conclusion, we are convinced that spiking networks represent a powerful alternative framework for real vision applications that will benefit from recent advances in computational neuroscience.
Type de document :
Article dans une revue
International Journal of Computer Vision, Springer Verlag, 2009, 82 (3), pp.284-301
Liste complète des métadonnées

https://hal.inria.fr/inria-00407903
Contributeur : Thierry Viéville <>
Soumis le : lundi 27 juillet 2009 - 19:11:42
Dernière modification le : vendredi 25 mai 2018 - 12:02:04

Identifiants

  • HAL Id : inria-00407903, version 1

Citation

Maria-Jose Escobar, Guillaume Masson, Thierry Viéville, Pierre Kornprobst. Action Recognition Using a Bio-Inspired Feedforward Spiking Network. International Journal of Computer Vision, Springer Verlag, 2009, 82 (3), pp.284-301. 〈inria-00407903〉

Partager

Métriques

Consultations de la notice

487