Efficient Dense Matching for Textured Scenes Using Region Growing

Maxime Lhuillier 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 : We present a simple and efficient dense matching method based on region growing techniques, which can be applied to a wide range of globally textured images like many outdoor scenes. Our method can deal with non-rigid scenes and large camera motions. First a few highly distinctive features like points or areas are extracted and matched. These initial matches are then used in a correlation-based region growing step which propagates the matches in textured and more ambiguous regions of the images. The implementation of the algorithm is also given and is demonstrated on real image pairs.
Type de document :
Communication dans un congrès
John N. Carter and Mark S. Nixon. 9th British Machine Vision Conference (BMVC '98), 1998, Southampton, United Kingdom. The British Machine Vision Association (BMVA), pp.700--709, 1998, 〈http://www.bmva.org/bmvc/1998/papers/d052/h052.htm〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00590096
Contributeur : Team Perception <>
Soumis le : jeudi 5 mai 2011 - 14:35:41
Dernière modification le : mercredi 11 avril 2018 - 01:53:08
Document(s) archivé(s) le : samedi 6 août 2011 - 02:33:40

Fichier

Bmvc98.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00590096, version 1

Collections

IMAG | INRIA | UGA

Citation

Maxime Lhuillier. Efficient Dense Matching for Textured Scenes Using Region Growing. John N. Carter and Mark S. Nixon. 9th British Machine Vision Conference (BMVC '98), 1998, Southampton, United Kingdom. The British Machine Vision Association (BMVA), pp.700--709, 1998, 〈http://www.bmva.org/bmvc/1998/papers/d052/h052.htm〉. 〈inria-00590096〉

Partager

Métriques

Consultations de la notice

107

Téléchargements de fichiers

134