OrthoTrack: Continuous 6-DoF UAV Trajectory Estimation Anchored in Public Orthophotos

2026-06-23

AI Summary

This work addresses the limitations of existing visual odometry and SLAM methods, which suffer from drift accumulation and yield only relative trajectories, as well as single-frame geolocalization approaches that lack temporal continuity and real-time performance. The paper proposes a novel, training-free, GPS-free method for real-time absolute pose estimation by leveraging publicly available orthophotos and digital surface models as map priors. Through keyframe matching, 3D lifting, and optical flow propagation, the approach achieves continuous, metric-scale, six-degree-of-freedom trajectory estimation for drones. It enables zero-shot deployment in unseen environments and significantly outperforms current baselines on both the MovingDrone benchmark and real-world datasets. Additionally, the authors release the first large-scale MovingDrone dataset with ground-truth trajectories.

Abstract

Continuous 6-DoF pose estimation is essential for autonomous UAV operations. Yet, existing visual odometry and SLAM methods accumulate drift and yield only relative, up-to-scale trajectories. Single-frame geo-localization, in turn, discards temporal continuity and remains too slow for real-time use. We present OrthoTrack, a training-free system that estimates continuous 6-DoF UAV trajectories using only publicly available orthophotos and surface models as a map prior. OrthoTrack matches keyframes against the orthophoto and lifts correspondences to metric 3D via the surface model. It then propagates these map-anchored correspondences to intermediate frames with optical flow, producing absolute, metrically scaled poses at every frame without GPS or post-hoc alignment. We also introduce the MovingDrone Dataset, a large-scale benchmark pairing photorealistic UAV sequences with dense 6-DoF ground truth and co-registered multi-modal geodata including multi-temporal orthophotos. On MovingDrone and real-world benchmarks, OrthoTrack runs in real time on a single GPU. It outperforms all baselines by a large margin, even those receiving oracle scale and alignment. By relying on publicly available geodata, OrthoTrack enables deployment to new regions without site-specific adaptation.

Problem

• 6-DoF pose estimation
• UAV trajectory
• visual odometry
• geo-localization
• drift

Innovation

• 6-DoF pose estimation
• orthophoto-based localization
• training-free visual odometry
• metric-scale trajectory
• public geospatial data