Fundamental matrix estimation without prior match

Nicolas Noury 1 Frédéric Sur 1 Marie-Odile Berger 1
1 MAGRIT - Visual Augmentation of Complex Environments
INRIA Lorraine, LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : This paper presents a probabilistic framework for computing correspondences and fundamental matrix in the structure from motion problem. Inspired by Moisan and Stival, we suggest using an a contrario model, which is a good answer to threshold problems in the robust filtering context. Contrary to most existing algorithms where perceptual correspondence setting and geometry evaluation are independent steps, the proposed algorithm is an all-in-one approach. We show that it is robust to repeated patterns which are usually difficult to unambiguously match and thus raise many problems in the fundamental matrix estimation.
Type de document :
Communication dans un congrès
14th IEEE International Conference on Image Processing - ICIP 2007, Sep 2007, San Antonio, Texas, United States. IEEE, pp.I - 513 - I - 516, 2007, 2007 IEEE International Conference on Image Processing - ICIP 2007 - Proceedings. 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4379004〉. 〈10.1109/ICIP.2007.4379004〉
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00164807
Contributeur : Frédéric Sur <>
Soumis le : lundi 20 septembre 2010 - 10:32:37
Dernière modification le : jeudi 11 janvier 2018 - 06:20:14
Document(s) archivé(s) le : mardi 23 octobre 2012 - 16:21:13

Fichier

icip07_noury_final.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Nicolas Noury, Frédéric Sur, Marie-Odile Berger. Fundamental matrix estimation without prior match. 14th IEEE International Conference on Image Processing - ICIP 2007, Sep 2007, San Antonio, Texas, United States. IEEE, pp.I - 513 - I - 516, 2007, 2007 IEEE International Conference on Image Processing - ICIP 2007 - Proceedings. 〈http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4379004〉. 〈10.1109/ICIP.2007.4379004〉. 〈inria-00164807〉

Partager

Métriques

Consultations de la notice

322

Téléchargements de fichiers

124