EXEMPLAR BASED METRIC LEARNING FOR ROBUST VISUAL LOCALIZATION

Abstract : This paper presents an exemplar based metric learning framework dedicated to robust visual localization in complex scenes, e.g. street images. The proposed framework learns off-line a specific (local) metric for each image of the database, so that the distance between a database image and a query image representing the same scene is smaller than the distance between the current image and other images of the database. To achieve this goal, we generate geometric and photometric transformations as proxies for query images. From the generated constraints, the learning problem is cast as a convex optimization problem over the cone of positive semi-definite matrices, which is efficiently solved using a projected gradient descent scheme. Successful experiments , conducted using a freely available geo-referenced image database, reveal that the proposed method significantly improves results over the metric in the input space, while being as efficient at test time. In addition, we show that the model learns discriminating features for the localization task, and is able to gain invariance to meaningful transformations.
Document type :
Poster communications
Liste complète des métadonnées

Cited literature [22 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-01198662
Contributor : Cédric Le Barz <>
Submitted on : Monday, September 14, 2015 - 10:49:49 AM
Last modification on : Tuesday, March 26, 2019 - 2:24:42 PM
Document(s) archivé(s) le : Tuesday, December 29, 2015 - 1:27:47 AM

File

ICIP_2015.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01198662, version 1

Citation

Cédric Le Barz, Nicolas Thome, Matthieu Cord, Stéphane Herbin, Martial Sanfourche. EXEMPLAR BASED METRIC LEARNING FOR ROBUST VISUAL LOCALIZATION. IEEE International Conference on Image Processing, ICIP 2015, Sep 2015, Québec, Canada. pp.388-w6mP-151, 2015. ⟨hal-01198662⟩

Share

Metrics

Record views

327

Files downloads

95