24/7 place recognition by view synthesis

Akihiko Torii 1 Relja Arandjelović 2, 3 Josef Sivic 3, 2 Masatoshi Okutomi 1 Tomas Pajdla 4
3 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
Abstract : We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings built or destroyed. Such situations represent a major challenge for current large-scale place recognition methods. This work has the following three principal contributions. First, we demonstrate that matching across large changes in the scene appearance becomes much easier when both the query image and the database image depict the scene from approximately the same viewpoint. Second, based on this observation, we develop a new place recognition approach that combines (i) an efficient synthesis of novel views with (ii) a compact in-dexable image representation. Third, we introduce a new challenging dataset of 1,125 camera-phone query images of Tokyo that contain major changes in illumination (day, sunset, night) as well as structural changes in the scene. We demonstrate that the proposed approach significantly out-performs other large-scale place recognition techniques on this challenging data.
Type de document :
Communication dans un congrès
CVPR 2015 - 28th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition
Liste complète des métadonnées

https://hal.inria.fr/hal-01147212
Contributeur : Relja Arandjelović <>
Soumis le : jeudi 30 avril 2015 - 00:21:04
Dernière modification le : jeudi 11 janvier 2018 - 06:23:05
Document(s) archivé(s) le : lundi 14 septembre 2015 - 15:51:30

Fichier

Torii15_24-7.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01147212, version 1

Collections

Citation

Akihiko Torii, Relja Arandjelović, Josef Sivic, Masatoshi Okutomi, Tomas Pajdla. 24/7 place recognition by view synthesis. CVPR 2015 - 28th IEEE Conference on Computer Vision and Pattern Recognition, Jun 2015, Boston, United States. Proceedings IEEE Conference on Computer Vision & Pattern Recognition. 〈hal-01147212〉

Partager

Métriques

Consultations de la notice

484

Téléchargements de fichiers

350