Localizing and Orienting Street Views Using Overhead Imagery

07/30/2016
by   Nam Vo, et al.
0

In this paper we aim to determine the location and orientation of a ground-level query image by matching to a reference database of overhead (e.g. satellite) images. For this task we collect a new dataset with one million pairs of street view and overhead images sampled from eleven U.S. cities. We explore several deep CNN architectures for cross-domain matching -- Classification, Hybrid, Siamese, and Triplet networks. Classification and Hybrid architectures are accurate but slow since they allow only partial feature precomputation. We propose a new loss function which significantly improves the accuracy of Siamese and Triplet embedding networks while maintaining their applicability to large-scale retrieval tasks like image geolocalization. This image matching task is challenging not just because of the dramatic viewpoint difference between ground-level and overhead imagery but because the orientation (i.e. azimuth) of the street views is unknown making correspondence even more difficult. We examine several mechanisms to match in spite of this -- training for rotation invariance, sampling possible rotations at query time, and explicitly predicting relative rotation of ground and overhead images with our deep networks. It turns out that explicit orientation supervision also improves location prediction accuracy. Our best performing architectures are roughly 2.5 times as accurate as the commonly used Siamese network baseline.

READ FULL TEXT

page 3

page 11

page 18

page 19

page 20

page 22

page 23

page 24

research
03/29/2019

Lending Orientation to Neural Networks for Cross-view Geo-localization

This paper studies image-based geo-localization (IBL) problem using grou...
research
03/11/2021

Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization

The goal of cross-view image based geo-localization is to determine the ...
research
05/08/2020

Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching

Cross-view geo-localization is the problem of estimating the position an...
research
05/23/2017

Towards seamless multi-view scene analysis from satellite to street-level

In this paper, we discuss and review how combined multi-view imagery fro...
research
03/26/2022

Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching

We address the problem of ground-to-satellite image geo-localization, th...
research
03/10/2022

City-wide Street-to-Satellite Image Geolocalization of a Mobile Ground Agent

Cross-view image geolocalization provides an estimate of an agent's glob...
research
05/13/2017

Revisiting IM2GPS in the Deep Learning Era

Image geolocalization, inferring the geographic location of an image, is...

Please sign up or login with your details

Forgot password? Click here to reset