Linear Projective Reconstruction from Matching Tensors

Bill Triggs 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 : This paper describes initial work on a family of projective reconstruction techniques that extract projection matrices directly and linearly from matching tensors estimated from image data. The simplest methods use fundamental matrices and epipoles, alternative ones use trilinear tensors. All of the data is treated uniformly, and there is no reliance on ‘privileged' images or tokens. The approach is based on ‘joint image closure relations' — bilinear constraints between the projection matrices and their matching tensors, that express the fact that the latter derive from the former. The performance of the new techniques is quantified and compared with that of several existing methods.
Type de document :
Communication dans un congrès
British Machine Vision Conference (BMVC '96), 1996, Edinburgh, United Kingdom. pp.665--674, 1996, 〈http://www.bmva.org/bmvc/1996/〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00548365
Contributeur : Thoth Team <>
Soumis le : lundi 20 décembre 2010 - 08:43:56
Dernière modification le : mercredi 11 avril 2018 - 01:54:22
Document(s) archivé(s) le : lundi 21 mars 2011 - 02:58:32

Identifiants

  • HAL Id : inria-00548365, version 1

Collections

IMAG | INRIA | UGA

Citation

Bill Triggs. Linear Projective Reconstruction from Matching Tensors. British Machine Vision Conference (BMVC '96), 1996, Edinburgh, United Kingdom. pp.665--674, 1996, 〈http://www.bmva.org/bmvc/1996/〉. 〈inria-00548365〉

Partager

Métriques

Consultations de la notice

115

Téléchargements de fichiers

159