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

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Feb 18, 2016
Accession Number
AD1039801

Entities

People

  • Enrique Dunn
  • Hyo Jin Kim
  • Jan-michael Frahm

Organizations

  • University of North Carolina at Chapel Hill

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Accuracy
  • Classification
  • Clustering
  • Computer Science
  • Databases
  • Dimensionality Reduction
  • Feature Extraction
  • Feature Selection
  • Geographic Regions
  • Global Positioning Systems
  • Images
  • Internet
  • Machine Learning
  • Photo Sharing Websites
  • Supervised Machine Learning
  • Training

Fields of Study

  • Computer science

Readers

  • Computer Vision.
  • Educational Psychology