Spike to Spike Model and Applications: A biological plausible approach for the motion processing

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 V1 and MT functional models for biological motion recognition. Our V1 model transforms a video stream into spike trains through local motion detectors. The spike trains are the inputs of a spiking MT network. Each entity in the MT network corresponds to a simplified model of an MT cell. From the spike trains of MT cells a motion map of velocity distribution is built representing a sequence. Biological plausibility of both models is discused in detail in the paper. In order to show the efficiency of these models, the motion maps here obtained are used in the biological motion recognition task. We ran the experiments using two databases Giese and Weizmann, containing two (march, walk) and ten (e.g., march, jump, run) different classes, respectively. The results revealed that the motion map here proposed could be used as a reliable motion representation.
Type de document :
Rapport
[Research Report] RR-6280, INRIA. 2007, pp.37
Liste complète des métadonnées

https://hal.inria.fr/inria-00170153
Contributeur : Maria-Jose Escobar <>
Soumis le : mardi 29 janvier 2008 - 12:18:48
Dernière modification le : jeudi 18 janvier 2018 - 02:10:40
Document(s) archivé(s) le : vendredi 25 novembre 2016 - 20:38:56

Fichier

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

Identifiants

  • HAL Id : inria-00170153, version 3

Citation

Maria-Jose Escobar, Guillaume Masson, Thierry Viéville, Pierre Kornprobst. Spike to Spike Model and Applications: A biological plausible approach for the motion processing. [Research Report] RR-6280, INRIA. 2007, pp.37. 〈inria-00170153v3〉

Partager

Métriques

Consultations de la notice

378

Téléchargements de fichiers

192