EV-Pose: Event Camera-Enhanced High-Frequency Visual Positioning Service for Accurate Drone Landing
IEEE Transactions on Mobile Computing · 2026-12 · 25 (12) · 22679-22696
DOI: 10.1109/tmc.2026.3724581 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-12. Verfasst von Haoyang Wang und 11 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Gefördert von: NSFC, Shenzhen Science and Technology Program, Shenzhen Low-Altitude Airspace Strategic Program Portfolio.
Abstract (Originalsprache)
Real-time 6-DoF drone pose tracking enables precise flight control and accurate drone landing. With the widespread availability of urban 3D maps, the Visual Positioning Service (VPS) has been adapted for drone landing to overcome GPS unreliability, serving as a global localization system that yields absolute global coordinates by continuously aligning visual features with the prior 3D map. However, deploying conventional vision-based VPS on highly dynamic drones faces bottlenecks in both pose estimation accuracy and efficiency. In this work, we pioneer EV-Pose, an event camera-enhanced VPS designed to deliver drift-free, absolute global coordinates at ultra-high frequencies for drones. EV-Pose addresses the 2D-3D modality gap via a novel Spatio-Temporal Feature-instructed Pose Estimation module, which extracts a Temporal Distance Field (TDF) to enable continuous, differentiable matching with a prior 3D point map for pose estimation. To fully exploit this formulation, we propose a Motion-aware Hierarchical Fusion and Optimization scheme. This architecture utilizes onboard IMU motion information for fine-grained early-stage event filtering and seamlessly optimizes pose estimation in a later-stage factor graph. Evaluation shows that EV-Pose achieves a rotation accuracy of $1.76^{\circ }$ 1 . 76 ∘ and a translation accuracy of 7.5 mm with a latency of 10.08 ms, outperforming baselines by $> $ > 40% and enabling accurate drone landings.
Förderung
- NSFC
- Shenzhen Science and Technology Program
- Shenzhen Low-Altitude Airspace Strategic Program Portfolio
- Meituan Academy of Robotics Shenzhen
Zitieren
APA
Wang, H., Luo, X., Ding, W., Xu, J., Chen, X., Duan, R., Chen, J., Wang, C., Zhang, H., Zhou, Z., Liu, Y., & Chen, X. (2026). EV-Pose: Event Camera-Enhanced High-Frequency Visual Positioning Service for Accurate Drone Landing. IEEE Transactions on Mobile Computing, 25(12), 22679-22696. https://doi.org/10.1109/tmc.2026.3724581
Vancouver
Wang H, Luo X, Ding W, Xu J, Chen X, Duan R, et al. EV-Pose: Event Camera-Enhanced High-Frequency Visual Positioning Service for Accurate Drone Landing. IEEE Transactions on Mobile Computing. 2026;25(12):22679-22696. doi:10.1109/tmc.2026.3724581
BibTeX
@article{Wang2026,
author = {Wang, Haoyang and Luo, Xinyu and Ding, Wenhua and Xu, Jingao and Chen, Xuecheng and Duan, Ruiyang and Chen, Jialong and Wang, Chao and Zhang, Haitao and Zhou, Ziyi and Liu, Yunhao and Chen, Xinlei},
title = {EV-Pose: Event Camera-Enhanced High-Frequency Visual Positioning Service for Accurate Drone Landing},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {12},
pages = {22679--22696},
doi = {10.1109/tmc.2026.3724581}
}
EUVIMED