Visual data fusion for objects localization by active vision

Grégory Flandin 1 François Chaumette 1
1 VISTA - Vision spatio-temporelle et active
IRISA - Institut de Recherche en Informatique et Systèmes Aléatoires, Inria Rennes – Bretagne Atlantique
Abstract : Visual sensors provide exclusively uncertain and partial knowledge of a scene. In this article, we present a suitable scene knowl- edge representation that makes integration and fusion of new, uncertain and partial sensor measures possible. It is based on a mixture of stochas- tic and set membership models. We consider that, for a large class of ap- plications, an approximated representation is sufficient to build a prelim- inary map of the scene. Our approximation mainly results in ellipsoidal calculus by means of a normal assumption for stochastic laws and ellip- soidal over or inner bounding for uniform laws. These approximations allow us to build an efficient estimation process integrating visual data on line. Based on this estimation scheme, optimal exploratory motions of the camera can be automatically determined. Real time experimental results validating our approach are finally given.
Type de document :
Communication dans un congrès
Eur. Conf. on Computer Vision, ECCV'02, LNCS 2353, 2002, Copenhagen, Denmark, Denmark. pp.312-326, 2002
Liste complète des métadonnées

https://hal.inria.fr/inria-00352090
Contributeur : Eric Marchand <>
Soumis le : lundi 12 janvier 2009 - 14:23:51
Dernière modification le : mercredi 16 mai 2018 - 11:23:06
Document(s) archivé(s) le : mardi 8 juin 2010 - 19:36:48

Fichier

2002_eccv_flandin.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00352090, version 1

Collections

Citation

Grégory Flandin, François Chaumette. Visual data fusion for objects localization by active vision. Eur. Conf. on Computer Vision, ECCV'02, LNCS 2353, 2002, Copenhagen, Denmark, Denmark. pp.312-326, 2002. 〈inria-00352090〉

Partager

Métriques

Consultations de la notice

212

Téléchargements de fichiers

105