Skip to Main content Skip to Navigation
Conference papers

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, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download

https://hal.inria.fr/hal-00934332
Contributor : Petr Gronat <>
Submitted on : Tuesday, January 21, 2014 - 7:44:32 PM
Last modification on : Thursday, July 1, 2021 - 5:58:07 PM
Long-term archiving on: : Tuesday, April 22, 2014 - 10:11:13 AM

File

cvpr13-gronat_opt.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00934332, version 1

Collections

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. ⟨hal-00934332⟩

Share

Metrics

Record views

403

Files downloads

693