A2G-SRNet: An Adaptive Attention-Guided Transformer and Super-Resolution Network for Enhanced Aircraft Detection in Satellite Imagery
Sensors · 22.10.2025 · 25 (21) · 6506
DOI: 10.3390/s25216506 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 22.10.2025. Verfasst von Nan Chen und 5 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science, Xihang University, Xi'an 710077, China. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 46 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China, Shaanxi Provincial Natural Science Basic Research Program, the Open Research Fund of Key Laboratory of Smart Earth.
Abstract (Originalsprache)
Accurate aircraft detection in remote sensing imagery is critical for aerospace surveillance, military reconnaissance, and aviation security but remains fundamentally challenged by extreme scale variations, arbitrary orientations, and dense spatial clustering in high-resolution scenes. This paper presents an adaptive attention-guided super-resolution network that integrates multi-scale feature learning with saliency-aware processing to address these challenges. Our architecture introduces three key innovations: (1) A hierarchical coarse-to-fine detection pipeline that first identifies potential regions in downsampled imagery before applying precision refinement, (2) A saliency-aware tile selection module employing learnable attention tokens to dynamically localize aircraft-dense regions without manual thresholds, and (3) A local tile refinement network combining transformer-based super-resolution for target regions with efficient upsampling for background areas. Extensive experiments on DIOR and FAIR1M benchmarks demonstrate state-of-the-art performance, achieving 93.1% AP50 (DIOR) and 83.2% AP50 (FAIR1M), significantly outperforming existing super-resolution-enhanced detectors. The proposed framework offers an adaptive sensing solution for satellite-based aircraft detection, effectively mitigating scale variations and background clutter in real-world operational environments.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- College of Computer Science, Xihang University, Xi'an 710077, China.
- Key Laboratory of Smart Earth, No. 8 Minzu Yuan Road, Beijing 100029, China.
- Aerial Photogrammetry and Remote Sensing Group Co., Ltd., Xi'an 710100, China.
- Department of Geography and Environmental Management, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
- Department of Systems Design Engineering, University of Waterloo, Waterloo, ON N2L 3G1, Canada.
- Xi'an Key Laboratory of Territorial Spatial Information, Chang'an University, Xi'an 710064, China.
ORCID-Profile: Nan Chen, Biao Zhang, Hongjie He, Kyle Gao, Zhouzhou Liu, Liangzhi Li
Förderung
- the National Natural Science Foundation of China
- Shaanxi Provincial Natural Science Basic Research Program
- the Open Research Fund of Key Laboratory of Smart Earth
- the Open Research Fund of Xi'an Key Laboratory of Territorial Spatial Information
- the Xianyang City Key Research and Development Program
- National Natural Science Foundation of China
- Open Research Fund of Key Laboratory of Smart Earth
- Open Research Fund of Xi’an Key Laboratory of Territorial Spatial Information
Zitieren
APA
Chen, N., Zhang, B., He, H., Gao, K., Liu, Z., & Li, L. (2025). A2G-SRNet: An Adaptive Attention-Guided Transformer and Super-Resolution Network for Enhanced Aircraft Detection in Satellite Imagery. Sensors, 25(21), 6506. https://doi.org/10.3390/s25216506
Vancouver
Chen N, Zhang B, He H, Gao K, Liu Z, Li L. A2G-SRNet: An Adaptive Attention-Guided Transformer and Super-Resolution Network for Enhanced Aircraft Detection in Satellite Imagery. Sensors. 2025;25(21):6506. doi:10.3390/s25216506
BibTeX
@article{Chen2025,
author = {Chen, Nan and Zhang, Biao and He, Hongjie and Gao, Kyle and Liu, Zhouzhou and Li, Liangzhi},
title = {A2G-SRNet: An Adaptive Attention-Guided Transformer and Super-Resolution Network for Enhanced Aircraft Detection in Satellite Imagery},
journal = {Sensors},
year = {2025},
volume = {25},
number = {21},
pages = {6506},
doi = {10.3390/s25216506}
}
EUVIMED