MAC-RANSAC: a robust algorithm for the recognition of multiple objects

Julien Rabin 1 Julie Delon 1 Yann Gousseau 1 Lionel Moisan 2
1 LTCI - Laboratoire Traitement et Communication de l'Information
2 MAP5 - MAP5 - Mathématiques Appliquées à Paris 5
Abstract : This paper addresses the problem of recognizing multiple rigid objects that are common to two images. We propose a generic algorithm that allows to simultaneously decide if one or several objects are common to the two images and to estimate the corresponding geometric transformations. The considered transformations include similarities, homographies and epipolar geometry. We first propose a generalization of an "a contrario" formulation of the RANSAC algorithm proposed in [Moisan and Stival 04]. We then introduce an algorithm for the detection of multiple transformations between images and show its efficiency on various experiments.
Keywords : Object recognition object pose estimation a contrario method RANSAC SIFT local descriptors planar transformation epipolar geometry
Type de document :
Communication dans un congrès
Fifth International Symposium on 3D Data Processing, Visualization and Transmission (3DPTV 2010), 2010, Paris, France. pp.051, 2010
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00466487
Contributeur : Julien Rabin <>
Soumis le : jeudi 25 mars 2010 - 17:18:40
Dernière modification le : jeudi 9 février 2017 - 15:19:44
Document(s) archivé(s) le : mercredi 30 novembre 2016 - 16:03:58

Fichier

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

Identifiants

  • HAL Id : hal-00466487, version 2

Collections

UNIV-PARIS5 | PARISTECH | TELECOM-PARISTECH | MAP5 | USPC

Citation

Julien Rabin, Julie Delon, Yann Gousseau, Lionel Moisan. MAC-RANSAC: a robust algorithm for the recognition of multiple objects. Fifth International Symposium on 3D Data Processing, Visualization and Transmission (3DPTV 2010), 2010, Paris, France. pp.051, 2010. <hal-00466487v2>

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de
la notice

734

Téléchargements du document

1032

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD