Predicting good features for image geo-localization using per-bundle VLAD

Hyo Jin Kim, Enrique Dunn, Jan Michael Frahm

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

44 Scopus citations

Abstract

We address the problem of recognizing a place depicted in a query image by using a large database of geo-tagged images at a city-scale. In particular, we discover features that are useful for recognizing a place in a data-driven manner, and use this knowledge to predict useful features in a query image prior to the geo-localization process. This allows us to achieve better performance while reducing the number of features. Also, for both learning to predict features and retrieving geo-tagged images from the database, we propose per-bundle vector of locally aggregated descriptors (PBVLAD), where each maximally stable region is described by a vector of locally aggregated descriptors (VLAD) on multiple scale-invariant features detected within the region. Experimental results show the proposed approach achieves a significant improvement over other baseline methods.

Original languageEnglish
Title of host publication2015 International Conference on Computer Vision, ICCV 2015
Pages1170-1178
Number of pages9
ISBN (Electronic)9781467383912
DOIs
StatePublished - 17 Feb 2015
Event15th IEEE International Conference on Computer Vision, ICCV 2015 - Santiago, Chile
Duration: 11 Dec 201518 Dec 2015

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2015 International Conference on Computer Vision, ICCV 2015
ISSN (Print)1550-5499

Conference

Conference15th IEEE International Conference on Computer Vision, ICCV 2015
Country/TerritoryChile
CitySantiago
Period11/12/1518/12/15

Fingerprint

Dive into the research topics of 'Predicting good features for image geo-localization using per-bundle VLAD'. Together they form a unique fingerprint.

Cite this