EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Direction-Robust UAV–Satellite Cross-View Geo-Localization via Spatial Adaptive Alignment and Circular Adjacent-Direction Gated Interaction

Yonghao Yang, Kaiji Hou, Siyu Zhu, Qiang Tong, Xiulei Liu, Xuhong Liu

Drones · 11.11.2026 · 10 (11) · 846

DOI: 10.3390/drones10110846 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 11.11.2026. Verfasst von Yonghao Yang und 5 weiteren Autor:innen. Die Arbeit nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Young Elite Scientists Sponsorship Program of the Beijing High Innovation Plan, Science and Technology Commission of Changping District.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Cross-view geo-localization (CVGL) matches unmanned aerial vehicle (UAV) images with geotagged satellite imagery to support visual localization in Global Navigation Satellite System (GNSS)-challenged environments. However, substantial cross-view discrepancies between UAV and satellite images, together with variations in UAV viewing direction, induce pronounced shifts in feature distributions, thereby undermining the stability of cross-view matching. To address these issues, we propose a progressive spatial-to-directional framework. The Spatial Adaptive Alignment Module first adaptively balances height–channel and width–channel responses and applies a fine-grained consistency constraint to reduce cross-view feature discrepancies. On the spatially adapted features, the Direction-Aware Module performs radial directional decomposition and organizes the resulting directional features into a circularly ordered sequence. A channel-wise gated interaction mechanism then selectively transfers information between each direction and its circularly adjacent neighbors after semantic-space projection. This local interaction captures gradual structural transitions between neighboring directions while preserving direction-specific discriminability and avoiding indiscriminate global mixing. Across three independent training runs on University-1652, our method achieves mean R@1 and AP values of 94.63% and 95.46% for UAV-to-satellite retrieval. The corresponding means for satellite-to-UAV retrieval are 96.86% and 93.97%. These results demonstrate that our method effectively improves UAV–satellite cross-view retrieval performance and maintains stable retrieval performance under different UAV viewing directions.

Förderung

  • Young Elite Scientists Sponsorship Program of the Beijing High Innovation Plan
  • Science and Technology Commission of Changping District

Zitieren

APA

Yang, Y., Hou, K., Zhu, S., Tong, Q., Liu, X., & Liu, X. (2026). Direction-Robust UAV–Satellite Cross-View Geo-Localization via Spatial Adaptive Alignment and Circular Adjacent-Direction Gated Interaction. Drones, 10(11), 846. https://doi.org/10.3390/drones10110846

Vancouver

Yang Y, Hou K, Zhu S, Tong Q, Liu X, Liu X. Direction-Robust UAV–Satellite Cross-View Geo-Localization via Spatial Adaptive Alignment and Circular Adjacent-Direction Gated Interaction. Drones. 2026;10(11):846. doi:10.3390/drones10110846

BibTeX
@article{Yang2026,
  author = {Yang, Yonghao and Hou, Kaiji and Zhu, Siyu and Tong, Qiang and Liu, Xiulei and Liu, Xuhong},
  title = {Direction-Robust UAV–Satellite Cross-View Geo-Localization via Spatial Adaptive Alignment and Circular Adjacent-Direction Gated Interaction},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {11},
  pages = {846},
  doi = {10.3390/drones10110846}
}
Kostenlos starten →