UAVs locate themselves on satellite maps from a single angled image
SatFix: Absolute Visual Localization of UAVs in Satellite Maps from a Single Oblique Image
Computer Vision and Pattern Recognition
Summary
Locating a drone precisely on a map using just one angled photo is a challenge because existing methods only find similar map tiles without giving exact positions or viewing directions. The authors present SatFix, a model that estimates a drone’s continuous position and heading on satellite maps from a single or a few images, without extra sensors or map data. They also introduce a larger evaluation dataset with continuous location labels and show that SatFix improves accuracy in positioning and heading compared to previous methods. The approach runs quickly, making it useful for real-time drone applications.
What this means in practice
- •For drone operations teams: Enable drones to determine their exact location and heading on satellite maps from a single onboard camera image without extra sensors.
- •For disaster response coordinators: Use single-view drone images to quickly localize UAVs over large areas for fast situational awareness in emergency zones lacking GPS.
Authors
Jiarui Zeng, Kun Shi, Chiman Vong, Zhedong Zheng
Abstract
We study absolute metric UAV localization within a provided geo-referenced satellite region, recovering continuous map position and viewing heading from a single oblique image or a short multi-view clip. Existing cross-view geo-localization methods retrieve the most similar satellite tile from a gallery and report Recall@K, but retrieval depends on gallery sampling, provides no heading estimate, and returns a tile index rather than a continuous coordinate. We propose SatFix, a feed-forward UAV--satellite localization framework built on VGGT-$Ω$. Satellite-grid features act as queries that aggregate UAV visual evidence, and two lightweight heads regress a 3-DoF pose in the satellite-map frame: continuous 2D position and heading. SatFix requires no explicit 3D map, rendered bird's-eye image, auxiliary sensor, or test-time pose alignment. A single model supports both single- and multi-view inputs, with trajectory constraints used during multi-view training. For metric evaluation, we introduce University-Metric, where satellite imagery is re-collected over a region up to 10.7$\times$ longer on a side (about 114$\times$ the ground area) than the original University-1652 tiles, with continuous position and heading labels for the original UAV tours. With one UAV view, SatFix localizes 52.08% of test frames within 50 m and 17.34% within 10 m, with median position and heading errors of 45.66 m and $20.81^\circ$, respectively. Inference takes under 0.1 s per single-view query on an NVIDIA RTX 4090. With nine UAV views, the median position error falls to 21.96 m and the median heading error to $8.73^\circ$. Compared with a fine-tuned VGGT-$Ω$ baseline, SatFix reduces median position error by 34.0% and nine-view median heading error from $25.43^\circ$ to $8.73^\circ$.