Learning and calibrating per-location classifiers for visual place recognition

Petr Gronat 1 Guillaume Obozinski 2, 3 Josef Sivic 2, 3, 1 Tomas Pajdla 4
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
2 LIENS - Laboratoire d'informatique de l'école normale supérieure
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
4 Department of Cybernetics [Prague]
Abstract : The aim of this work is to localize a query photograph by finding other images depicting the same place in a large geotagged image database. This is a challenging task due to changes in viewpoint, imaging conditions and the large size of the image database. The contribution of this work is two-fold. First, we cast the place recognition problem as a classification task and use the available geotags to train a classifier for each location in the database in a similar manner to per-exemplar SVMs in object recognition. Second, as only few positive training examples are available for each location, we propose a new approach to calibrate all the per-location SVM classifiers using only the negative examples. The calibration we propose relies on a significance measure essentially equivalent to the p-values classically used in statistical hypothesis testing. Experiments are per-formed on a database of 25,000 geotagged street view images of Pittsburgh and demonstrate improved place recognition accuracy of the proposed approach over the previous work.
Type de document :
Communication dans un congrès
CVPR 2013 - 26th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. 2013
Liste complète des métadonnées

Littérature citée [32 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-00934332
Contributeur : Petr Gronat <>
Soumis le : mardi 21 janvier 2014 - 19:44:32
Dernière modification le : mardi 17 avril 2018 - 11:26:25
Document(s) archivé(s) le : mardi 22 avril 2014 - 10:11:13

Fichier

cvpr13-gronat_opt.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00934332, version 1

Collections

INRIA | PSL

Citation

Petr Gronat, Guillaume Obozinski, Josef Sivic, Tomas Pajdla. Learning and calibrating per-location classifiers for visual place recognition. CVPR 2013 - 26th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2013, Portland, United States. 2013. 〈hal-00934332〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

248

Téléchargements de fichiers

226

Contact


archive-ouverte@inria.fr