Fast and reliable object pose estimation from line correspondences

Stéphane Christy 1 Radu Horaud 1
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : In this paper, we describe a fast object pose estimation method from 3-D to 2-D line correspondences using a perspective camera model. The principle consists in iteratively improving the pose computed with an affine camera model (either weak perspective or paraperspective) to converge, at the limit, to a pose estimation computed with a perspective camera model. Thus, the advantage of the method is to reduce the problem to solving a linear system at each iteration step. The iterative algorithms that we describe in detail in this paper can deal with non coplanar or coplanar object models and have interesting properties both in terms of speed and rate of convergence.
Type de document :
Communication dans un congrès
Gerald Sommer and Konstantinos Daniilidis and Josef Pauli. 7th International Conference on Computer Analysis of Images and Patterns (CAIP '97), Sep 1997, Kiel, Germany. Springer-Verlag, 1296, pp.432--439, 1997, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-63460-6_147〉
Liste complète des métadonnées
https://hal.inria.fr/inria-00590076
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:14:55
Dernière modification le : mercredi 11 avril 2018 - 01:53:14
Document(s) archivé(s) le : jeudi 4 août 2011 - 02:49:23

Fichiers

Stephane-caip97.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Stéphane Christy, Radu Horaud. Fast and reliable object pose estimation from line correspondences. Gerald Sommer and Konstantinos Daniilidis and Josef Pauli. 7th International Conference on Computer Analysis of Images and Patterns (CAIP '97), Sep 1997, Kiel, Germany. Springer-Verlag, 1296, pp.432--439, 1997, Lecture Notes in Computer Science (LNCS). 〈10.1007/3-540-63460-6_147〉. 〈inria-00590076〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

677

Téléchargements de fichiers

1000

Contact


archive-ouverte@inria.fr