Accession Number : AD1039801

Title :   Predicting Good Features for Image Geo-Localization Using Per-Bundle VLAD (Open Access)

Descriptive Note : Journal Article

Corporate Author : University of North Carolina at Chapel Hill Chapel Hill United States

Personal Author(s) : Kim, Hyo Jin ; Dunn,Enrique ; Frahm,Jan-Michael

Full Text :

Report Date : 18 Feb 2016

Pagination or Media Count : 9

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.

Descriptors :   supervised machine learning , dimensionality reduction , geographic regions , photo sharing websites , feature extraction , classification , clustering , algorithms , internet , databases , training , image processing , information retrieval , DATA VISUALIZATION

Subject Categories : Information Science

Distribution Statement : APPROVED FOR PUBLIC RELEASE