3D Projective Invariants from Two Images

Patrick Gros 1, 2 Long Quan 1, 2
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 : We are interested in the applications of invariant theory to computer vision problems. A survey and clarification of the different invariant calculation methods are detailed in our extended technical report. In this paper, we concentrate on 3-D invariants from pairs of images instead of invariants related to the planar projective transformations from monocular image that have been already largely studied by many people. Especially invariants of different configurations coming from different combinations of 3-D points, 3-D lines and conics are under consideration, and the stabilities of the invariants computed differently are compared. We conclude by showing to what extent these invariant measures can be used for recognition and indexing.
Type de document :
Communication dans un congrès
Baba C. Vemuri. Proceedings of the SPIE Conference on Geometric Methods in Computer Vision II, Jun 1993, San Diego, United States. SPIE, 2031, pp.75--86, 1993, 〈10.1117/12.146647〉
Liste complète des métadonnées

https://hal.inria.fr/inria-00590017
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:07:33
Dernière modification le : mercredi 11 avril 2018 - 01:53:35

Identifiants

Collections

Citation

Patrick Gros, Long Quan. 3D Projective Invariants from Two Images. Baba C. Vemuri. Proceedings of the SPIE Conference on Geometric Methods in Computer Vision II, Jun 1993, San Diego, United States. SPIE, 2031, pp.75--86, 1993, 〈10.1117/12.146647〉. 〈inria-00590017〉

Partager

Métriques

Consultations de la notice

89