Gaze control of an active vision system in dynamic scenes

Yann Ducrocq 1 Shahram Bahrami 1 Luc Duvieubourg 2 François Cabestaing 2
2 LAGIS-SI
LAGIS - Laboratoire d'Automatique, Génie Informatique et Signal
Abstract : In this paper, we present an active vision system that imitates the human viewing strategy. We know that gaze control is a major activity in scene observation. In fact, a person instinctively directs his visual fixation point toward regions of interest containing salient information. This information is then acquired by the region of the retina near the center of the field of view, i.e. the fovea. In this region, the acuity and the color sensitivity are higher. In order to mimic this human behavior, we have developed a novel active vision system based on a particular stereovision rig. It is composed with one camera, one prism and a set of mirrors. To direct the fixation point, the prism is rotated about its axis by a motorized stage. The system is designed for accurate dynamical adjustments of gaze and for operating at video rate. To validate our approach to active perception, we have developed a simple observation strategy for a real scene with dynamic objects. We present an experiment on real videos, which show its efficiency.
Type de document :
Communication dans un congrès
Workshop on Vision in Action: Efficient strategies for cognitive agents in complex environments, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées


https://hal.inria.fr/inria-00325803
Contributeur : Peter Sturm <>
Soumis le : mardi 30 septembre 2008 - 13:35:23
Dernière modification le : lundi 13 octobre 2014 - 15:43:25
Document(s) archivé(s) le : vendredi 4 juin 2010 - 12:01:09

Fichier

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

Identifiants

  • HAL Id : inria-00325803, version 1

Collections

Citation

Yann Ducrocq, Shahram Bahrami, Luc Duvieubourg, François Cabestaing. Gaze control of an active vision system in dynamic scenes. Workshop on Vision in Action: Efficient strategies for cognitive agents in complex environments, Oct 2008, Marseille, France. 2008. <inria-00325803>

Partager

Métriques

Consultations de
la notice

279

Téléchargements du document

149