Search papers, labs, and topics across Lattice.
This paper introduces a semantic reprojection framework for UAV localization in GNSS-denied nighttime environments using thermal imagery and daytime RGB-based semantic 3D maps. The method aligns segmented thermal observations with the semantic map by formulating localization as a symmetric bidirectional reprojection problem, incorporating confusion-aware weighting to handle segmentation uncertainties. Evaluated on 6.5 km of real-world nighttime UAV flights, the system achieves a bias-corrected RMSE2D of 2.18 m, demonstrating the potential of semantic reprojection for robust nighttime UAV localization.
Nighttime UAVs can navigate using only thermal cameras and semantic maps, achieving meter-level accuracy without GPS.
Reliable backup localization for unmanned aerial vehicles (UAVs) operating in GNSS-denied nighttime conditions remains an open challenge due to the severe modality gap between daytime RGB maps and nighttime thermal imagery. This work presents a semantic reprojection framework for map-relative nighttime UAV localization by aligning segmented thermal observations with a globally referenced, semantically labeled 3D map constructed from daytime RGB data. Rather than relying on appearance-based correspondence, localization is formulated in a shared semantic domain and solved via a symmetric bidirectional reprojection objective with confusion-aware weighting to improve robustness under segmentation uncertainty. The approach is evaluated offline across 6.5 km of nighttime, real-world UAV flight trajectories in urban and semi-structured environments. Relative to RTK GNSS ground truth, the system achieves a bias-corrected RMSE2D of 2.18 m and a median RMSE2D of 1.52 m. Results show that localization performance is strongly correlated with the availability of semantic edge evidence and that large-error events are spatially localized to semantically ambiguous areas rather than uniformly distributed. These findings indicate that semantic reprojection offers a promising pathway toward globally referenced nighttime UAV localization using thermal imagery alone.
