Wide-Area Image Geolocalization with Aerial Reference Imagery

Abstract

We propose to use deep convolutional neural networks to address the problem of cross-view image geolocalization, in which the geolocation of a ground-level query image is estimated by matching to georeferenced aerial images. We use state-of-the-art feature representations for ground-level images and introduce a cross-view training approach for learning a joint semantic feature representation for aerial images. We also propose a network architecture that fuses features extracted from aerial images at multiple spatial scales. To support training these networks, we introduce a massive database that contains pairs of aerial and ground-level images from across the United States. Our methods significantly out-perform the state of the art on two benchmark datasets. We also show, qualitatively, that the proposed feature representations are discriminative at both local and continental spatial scales.

International Conference on Computer Vision (ICCV) 2015

Cited by in corpus (9)

• PlaNet - Photo Geolocation with Convolutional Neural Networks
• Towards seamless multi-view scene analysis from satellite to street-level
• Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scale
• Localizing and Orienting Street Views Using Overhead Imagery
• Lending Orientation to Neural Networks for Cross-view Geo-localization
• Semantics for UGV Registration in GPS-denied Environments
• Satellite Image-based Localization via Learned Embeddings
• Cross-View Image Synthesis with Deformable Convolution and Attention Mechanism
• Predicting Ground-Level Scene Layout from Aerial Imagery