Image-Based Geo-Localization Using Satellite Imagery

  title={Image-Based Geo-Localization Using Satellite Imagery},
  author={Sixing Hu and Gim Hee Lee},
  journal={International Journal of Computer Vision},
  • Sixing Hu, Gim Hee Lee
  • Published 1 March 2019
  • Computer Science
  • International Journal of Computer Vision
The problem of localization on a geo-referenced satellite map given a query ground view image is useful yet remains challenging due to the drastic change in viewpoint. To this end, in this paper we work on the extension of our earlier work on the Cross-View Matching Network (CVM-Net) (Hu et al. in IEEE conference on computer vision and pattern recognition (CVPR), 2018 ) for the ground-to-aerial image matching task since the traditional image descriptors fail due to the drastic viewpoint change… 
Cross-View Matching for Vehicle Localization by Learning Geographically Local Representations
It is argued that the availability of coarse location estimates at test time should already be considered during training, and an image representation that is more discriminative within the geographically local neighborhood is adopted, without any modifications to a baseline deep neural network.
Lattice-Point Mutually Guided Ground-to-Aerial Feature Matching for Urban Scene Images
This article proposes a novel lattice-point mutually guided matching (LPMG) method that can obtain a considerable number of nearly pure correct matches from urban ground and aerial images, significantly outperforming those existing methods.
Real-time Geo-localization Using Satellite Imagery and Topography for Unmanned Aerial Vehicles
This work proposes a framework that is reliable in changing scenes, flexible about computing resource allocation and adaptable to common camera placements, and makes image-based geo-localization online and pragmatic for lightweight embedded systems on UAVs.
Video Geo-Localization Employing Geo-Temporal Feature Learning and GPS Trajectory Smoothing
In this paper, we address the problem of video geolocalization by proposing a Geo-Temporal Feature Learning (GTFL) Network to simultaneously learn the discriminative features for the query video
Deep Hybrid Network for Land Cover Semantic Segmentation in High-Spatial Resolution Satellite Images
A hybrid deep learning model that combines the benefits of two deep models, i.e., DenseNet and U-Net is developed and demonstrates that the proposed hybrid network exhibits a state-of-the-art performance and beats other existing models by a considerable margin.
Project AutoVision: Localization and 3D Scene Perception for an Autonomous Vehicle with a Multi-Camera System
An overview of the Project AutoVision is presented, and the sensor suite and current progress in the areas of calibration, localization, and perception are described.
Efficient Localisation Using Images and OpenStreetMaps
The ability to localise is key for robot navigation. We describe an efficient method for vision-based localisation, which combines sequential Monte Carlo tracking with matching ground-level images to
Evaluation of Cross-View Matching to Improve Ground Vehicle Localization with Aerial Perception
This paper evaluates cross-view matching for the task of localizing a ground vehicle over a longer trajectory using a city-wide dataset collected in a photorealistic simulation by varying four parameters: height of aerial images, the pitch of the aerial camera mount, FOV of the ground camera, and the methodology of fusing cross-View measurements in the particle filter.


Cross-View Image Matching for Geo-Localization in Urban Environments
A new framework for cross-view image geo-localization is presented by taking advantage of the tremendous success of deep convolutional neural networks (CNNs) in image classification and object detection and is able to generalize to images at unseen locations.
Satellite image-based localization via learned embeddings
A vision-based method that localizes a ground vehicle using publicly available satellite imagery as the only prior knowledge of the environment and overcome the significant viewpoint and appearance variations between the images through a neural multi-view model that learns location-discriminative embeddings.
CVM-Net: Cross-View Matching Network for Image-Based Ground-to-Aerial Geo-Localization
This work leverages on the recent success of deep learning to propose the CVM-Net for the cross-view image-based ground-to-aerial geo-localization task, based on the Siamese architecture to do metric learning for the matching task.
Cross-View Image Geolocalization
A cross-view feature translation approach to greatly extend the reach of image geolocalization methods by learning the relationship between ground level appearance and overhead appearance and land cover attributes from sparsely available geotagged ground-level images.
Wide-Area Image Geolocalization with Aerial Reference Imagery
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
Learning deep representations for ground-to-aerial geolocalization
This work localizes a ground-level query image by matching it to a reference database of aerial imagery and shows the effectiveness of Where-CNN in finding matches between street view and aerial view imagery and the ability of the learned features to generalize to novel locations.
Geo-localization of street views with aerial image databases
We study the feasibility of solving the challenging problem of geolocalizing ground level images in urban areas with respect to a database of images captured from the air such as satellite and
Localizing and Orienting Street Views Using Overhead Imagery
A new loss function is proposed which significantly improves the accuracy of Siamese and Triplet embedding networks while maintaining their applicability to large-scale retrieval tasks like image geolocalization.
Vision based robot localization by ground to satellite matching in GPS-denied situations
This paper proposes a two-step approach to matching images captured from an unmanned ground vehicle (UGV) to those from a satellite or high-flying vehicle, and shows that vision-based UGV localization from satellite maps is not only possible, but often provides better position estimates than GPS estimates, enabling the location estimates of Google Street View.
Accurate Geo-Registration by Ground-to-Aerial Image Matching
This work proposes a fully automated geo-registration pipeline with a novel viewpoint-dependent matching method that handles ground to aerial viewpoint variation, and demonstrates a high success rate for the task, and dramatically outperforms state-of-the-art techniques.