Image matching with scale adjustment

Yves Dufournaud 1 Cordelia Schmid 1, * Radu Horaud 2
* Auteur correspondant
1 LEAR - Learning and recognition in vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
2 PERCEPTION - Interpretation and Modelling of Images and Videos
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
Abstract : In this paper we address the problem of matching two images with two different resolutions: a high-resolution image and a low-resolution one. The difference in resolution between the two images is not known and without loss of generality one of the images is assumed to be the high-resolution one. On the premise that changes in resolution act as a smoothing equivalent to changes in scale, a scale-space representation of the high-resolution image is produced. Hence the one-toone classical image matching paradigm becomes one-to-many because the low-resolution image is compared with all the scale-space representations of the high-resolution one. Key to the success of such a process is the proper representation of the features to be matched in scale-space. We show how to represent and extract interest points at variable scales and we devise a method allowing the comparison of two images at two different resolutions. The method comprises the use of photometric- and rotation-invariant descriptors, a geometric model mapping the high-resolution image onto a low-resolution image region, and an image matching strategy based on local constraints and on the robust estimation of this geometric model. Extensive experiments show that our matching method can be used for scale changes up to a factor of 6.
Type de document :
Article dans une revue
Computer Vision and Image Understanding, Elsevier, 2004, 93 (2), pp.175-194. 〈10.1016/j.cviu.2003.07.003〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548555
Contributeur : Thoth Team <>
Soumis le : vendredi 17 janvier 2014 - 10:29:41
Dernière modification le : mercredi 11 avril 2018 - 01:50:53
Document(s) archivé(s) le : vendredi 18 avril 2014 - 11:21:51

Fichier

Horaud-CVIU30.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Yves Dufournaud, Cordelia Schmid, Radu Horaud. Image matching with scale adjustment. Computer Vision and Image Understanding, Elsevier, 2004, 93 (2), pp.175-194. 〈10.1016/j.cviu.2003.07.003〉. 〈inria-00548555〉

Partager

Métriques

Consultations de la notice

1097

Téléchargements de fichiers

474