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

arXiv: https://arxiv.org/abs/2203.05612 · HTML: https://mlsanity.com/paper/2203.05612/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 10 Mar 2022.

## Builds on (most cited first, 8 of 8)

- [VIGOR: Cross-View Image Geo-localization beyond One-to-one Retrieval](https://mlsanity.com/paper/2011.12172/) (2020)
- [Wide-Area Image Geolocalization with Aerial Reference Imagery](https://mlsanity.com/paper/1510.03743/) (2015)
- [Lending Orientation to Neural Networks for Cross-view Geo-localization](https://mlsanity.com/paper/1903.12351/) (2019)
- [Localizing and Orienting Street Views Using Overhead Imagery](https://mlsanity.com/paper/1608.00161/) (2016)
- [Cross-View Image Matching for Geo-localization in Urban Environments](https://mlsanity.com/paper/1703.07815/) (2017)
- [Revisiting Street-to-Aerial View Image Geo-localization and Orientation Estimation](https://mlsanity.com/paper/2005.11592/) (2020)
- [Image-Based Geo-Localization Using Satellite Imagery](https://mlsanity.com/paper/1903.00159/) (2019)
- [Satellite Image-based Localization via Learned Embeddings](https://mlsanity.com/paper/1704.01133/) (2017)

## Built on by (most cited first, 13 of 13)

- [Convolutional Cross-View Pose Estimation](https://mlsanity.com/paper/2303.05915/) (2023)
- [GOMAA-Geo: GOal Modality Agnostic Active Geo-localization](https://mlsanity.com/paper/2406.01917/) (2024)
- [Wide-Area Geolocalization with a Limited Field of View Camera](https://mlsanity.com/paper/2209.11854/) (2022)
- [Aerial View Localization with Reinforcement Learning: Towards Emulating Search-and-Rescue](https://mlsanity.com/paper/2209.03694/) (2022)
- [Energy-Based Models for Cross-Modal Localization using Convolutional Transformers](https://mlsanity.com/paper/2306.04021/) (2023)
- [Robust Self-Tuning Data Association for Geo-Referencing Using Lane Markings](https://mlsanity.com/paper/2207.14042/) (2022)
- [View-Invariant Localization using Semantic Objects in Changing Environments](https://mlsanity.com/paper/2209.14426/) (2022)
- [AGL-NET: Aerial-Ground Cross-Modal Global Localization with Varying Scales](https://mlsanity.com/paper/2404.03187/) (2024)
- [Learning autonomous driving from aerial imagery](https://mlsanity.com/paper/2410.14177/) (2024)
- [Evaluating Global Geo-alignment for Precision Learned Autonomous Vehicle Localization using Aerial Data](https://mlsanity.com/paper/2503.13896/) (2025)
- [Geo-Localization Based on Dynamically Weighted Factor-Graph](https://mlsanity.com/paper/2311.07301/) (2023)
- [GeoISF: Instance Semantic Forest Inspired Large-Scale Cross-View Geo-Localization via Ground LiDAR-to-Satellite Image](https://mlsanity.com/paper/2606.28371/) (2026)
- [Leveraging Semantic Maps for City-Scale Cross-View Localization](https://mlsanity.com/paper/2607.25215/) (2026)

## Abstract (arXiv)

Cross-view image geolocalization provides an estimate of an agent's global position by matching a local ground image to an overhead satellite image without the need for GPS. It is challenging to reliably match a ground image to the correct satellite image since the images have significant viewpoint differences. Existing works have demonstrated localization in constrained scenarios over small areas but have not demonstrated wider-scale localization. Our approach, called Wide-Area Geolocalization (WAG), combines a neural network with a particle filter to achieve global position estimates for agents moving in GPS-denied environments, scaling efficiently to city-scale regions. WAG introduces a trinomial loss function for a Siamese network to robustly match non-centered image pairs and thus enables the generation of a smaller satellite image database by coarsely discretizing the search area. A modified particle filter weighting scheme is also presented to improve localization accuracy and convergence. Taken together, WAG's network training and particle filter weighting approach achieves city-scale position estimation accuracies on the order of 20 meters, a 98% reduction compared to a baseline training and weighting approach. Applied to a smaller-scale testing area, WAG reduces the final position estimation error by 64% compared to a state-of-the-art baseline from the literature. WAG's search space discretization additionally significantly reduces storage and processing requirements.