An affine invariant interest point detector

Krystian Mikolajczyk 1 Cordelia Schmid 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 presents a novel approach for detecting affine invariant interest points. Our method can deal with significant affine transformations including large scale changes. Such transformations introduce significant changes in the point location as well as in the scale and the shape of the neighbourhood of an interest point. Our approach allows to solve for these problems simultaneously. It is based on three key ideas: 1) The second moment matrix computed in a point can be used to normalize a region in an affine invariant way (skew and stretch). 2) The scale of the local structure is indicated by local extrema of normalized derivatives over scale. 3) An affine-adapted Harris detector determines the location of interest points. A multi-scale version of this detector is used for initialization. An iterative algorithm then modifies location, scale and neighbourhood of each point and converges to affine invariant points. For matching and recognition, the image is characterized by a set of affine invariant points; the affine transformation associated with each point allows the computation of an affine invariant descriptor which is also invariant to affine illumination changes. A quantitative comparison of our detector with existing ones shows a significant improvement in the presence of large affine deformations. Experimental results for wide baseline matching show an excellent performance in the presence of large perspective transformations including significant scale changes. Results for recognition are very good for a database with more than 5000 images.
Type de document :
Communication dans un congrès
Anders Heyden and Gunnar Sparr and Mads Nielsen and Peter Johansen. 7th European Conference on Computer Vision (ECCV '02), May 2002, Copenhagen, Denmark. Springer-Verlag, 2350, pp.128--142, 2002, Lecture Notes in Computer Science (LNCS). 〈http://springerlink.metapress.com/content/d946wrklrq1fnpjh/〉. 〈10.1007/3-540-47969-4_9〉
Liste complète des métadonnées

Littérature citée [16 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00548252
Contributeur : Thoth Team <>
Soumis le : mardi 21 décembre 2010 - 08:53:17
Dernière modification le : mercredi 11 avril 2018 - 01:56:16
Document(s) archivé(s) le : mardi 22 mars 2011 - 02:30:29

Fichier

mikolajc_ECCV2002.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

IMAG | INRIA | UGA

Citation

Krystian Mikolajczyk, Cordelia Schmid. An affine invariant interest point detector. Anders Heyden and Gunnar Sparr and Mads Nielsen and Peter Johansen. 7th European Conference on Computer Vision (ECCV '02), May 2002, Copenhagen, Denmark. Springer-Verlag, 2350, pp.128--142, 2002, Lecture Notes in Computer Science (LNCS). 〈http://springerlink.metapress.com/content/d946wrklrq1fnpjh/〉. 〈10.1007/3-540-47969-4_9〉. 〈inria-00548252〉

Partager

Métriques

Consultations de la notice

1078

Téléchargements de fichiers

4100