AeroMap3D: Anchoring Monocular UAV 6-DoF Localization to Visual-Geometric-Semantic Map Priors
2026-07-15 • Robotics
Robotics
AI summaryⓘ
The authors developed AeroMap3D, a system that helps drones find their exact 3D location using just one camera, even when GPS is unavailable. They solved tricky problems like differences between images taken from the drone and satellite maps, and mismatches between flat elevation maps and real city structures. Their system smartly matches drone images to maps using scale and angle corrections, and uses map details to ignore confusing features before calculating the drone's position. Finally, they combine these map-based fixes with drone movement data to keep tracking its flight smoothly, achieving accurate localization over long distances without extra training.
6-DoF localizationmonocular visionGNSS-denied navigationdigital elevation model (DEM)OpenStreetMapdense correspondenceRANSAC-PnPEKF (Extended Kalman Filter)aerial localizationcross-view registration
Authors
Zhiyun Deng, Luis Sentis
Abstract
We present AeroMap3D, a monocular 6-DoF UAV localization system that anchors onboard imagery to visual, geometric, and semantic map priors for GNSS-denied navigation. AeroMap3D addresses two fundamental challenges in map-referenced aerial localization: the cross-view discrepancy between UAV imagery and satellite maps, and the structural inconsistency between bare-earth digital elevation models (DEMs) and urban scenes. First, we introduce a lightweight adapter that enables a dense matcher pretrained on internet-scale generic data to perform reliable UAV-to-map registration without finetuning. By estimating the scale ratio and yaw offset between the UAV image and map tile, the adapter removes the dominant geometric misalignment induced by altitude, camera field of view, and heading before dense correspondence estimation. Second, AeroMap3D lifts 2D UAV-map correspondences onto DEM terrain while using OpenStreetMap annotations to reject semantically unreliable matches before RANSAC-PnP pose estimation, thereby reducing errors caused by unmodeled building heights and off-nadir structures. Delayed map-based pose measurements are further fused with relative-motion priors using a delayed-state EKF for continuous trajectory estimation. Without UAV-Terra3D retraining or tuning, AeroMap3D localizes all trajectories across eight Austin sites within 50 m and achieves 5.88 m mean 3D error over 55 km of flight.