EUVIMEDObjevte EUVIMED
Open access · CC BY 4.0

AGEN: Adaptive Error Control-Driven Cross-View Geo-Localization Under Extreme Weather Conditions

Mengmeng Xu iD, Hongxiang Lv, Hai Zhu iD, Enlai Dong, Fei Wu

Sensors · 2025-06-15 · 25 (12) · 3749

DOI: 10.3390/s25123749 ↗

At a glance

Journal article in Sensors, published online on 2025-06-15. Written by Mengmeng Xu and 4 co-authors. Institution: Faculty of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China. Cited 8 times so far (Crossref); 74 references. The full text is freely available (open access, CC BY 4.0). Funded by: the Young Scientists Fund of the National Natural Science Foundation of China, the Key Project of Science and Technology Commission of Shanghai Municipality, Young Scientists Fund of the National Natural Science Foundation of China.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Cross-view geo-localization is a task of matching the same geographic image from different views, e.g., drone and satellite. Due to its GPS-free advantage, cross-view geo-localization is gaining increasing research interest, especially in drone-based localization and navigation applications. In order to guarantee system accuracy, existing methods mainly focused on image augmentation and denoising while still facing performance degradation when extreme weather conditions are considered. In this paper, we propose a robust end-to-end image retrieval framework, AGEN, serving for cross-view geo-localization under extreme weather conditions. Inspired by the strengths of the DINOv2 network, particularly its strong performance in global feature extraction, while acknowledging its limitations in capturing fine-grained details, we integrate the DINOv2 network with the Local Pattern Network (LPN) algorithm module to extract valuable classification features more efficiently. Additionally, to further enhance model robustness, we innovatively introduce an Adaptive Error Control (AEC) module based on fuzzy control to optimize the loss function dynamically. Specifically, by adjusting loss weights adaptively, the AEC module allows the model to better handle complex and challenging scenarios. Experimental results demonstrate that AGEN achieves a Recall@1 accuracy of 91.71% on the University160k-WX dataset under extreme weather conditions. Through extensive experiments on two well-known public datasets, i.e., University-1652 and SUES-200, AGEN achieves state-of-the-art Recall@1 accuracy in both drone-view target localization tasks and drone navigation tasks, outperforming existing models. In particular, on the University-1652 dataset, AGEN reaches 95.43% Recall@1 in the drone-view target localization task, showcasing its superior capability in handling challenging scenarios.

Subjects

Author keywords

DINOv2Siamese networkfuzzy PIDgeo-localization

Authors and institutions

  • Faculty of Electrical and Electronic Engineering, Shanghai University of Engineering Science, Shanghai 201620, China.

ORCID profiles: Mengmeng Xu, Hai Zhu

Funding

  • the Young Scientists Fund of the National Natural Science Foundation of China
  • the Key Project of Science and Technology Commission of Shanghai Municipality
  • Young Scientists Fund of the National Natural Science Foundation of China
  • Key Project of Science and Technology Commission of Shanghai Municipality

Cite

APA

Xu, M., Lv, H., Zhu, H., Dong, E., & Wu, F. (2025). AGEN: Adaptive Error Control-Driven Cross-View Geo-Localization Under Extreme Weather Conditions. Sensors, 25(12), 3749. https://doi.org/10.3390/s25123749

Vancouver

Xu M, Lv H, Zhu H, Dong E, Wu F. AGEN: Adaptive Error Control-Driven Cross-View Geo-Localization Under Extreme Weather Conditions. Sensors. 2025;25(12):3749. doi:10.3390/s25123749

BibTeX
@article{Xu2025,
  author = {Xu, Mengmeng and Lv, Hongxiang and Zhu, Hai and Dong, Enlai and Wu, Fei},
  title = {AGEN: Adaptive Error Control-Driven Cross-View Geo-Localization Under Extreme Weather Conditions},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {12},
  pages = {3749},
  doi = {10.3390/s25123749}
}
Start for free →