SF-DETR: A Scale-Frequency Detection Transformer for Drone-View Object Detection
Sensors · 30.03.2025 · 25 (7) · 2190
DOI: 10.3390/s25072190 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 30.03.2025. Verfasst von Haotong Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: The School of Automation Engineering, Qingdao University, Qingdao 266071, China. Die Arbeit wurde bisher 23-mal zitiert (Crossref) und nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Key Technology Research and Industrialization Demonstration Project of Qingdao, Shandong Provincial Natural Science Foundation, Key Technology Research and Industrialization Demonstration Project of Qingdao.
Abstract (Originalsprache)
Drone-based object detection faces critical challenges, including tiny objects, complex urban backgrounds, dramatic scale variations, and high-frequency detail loss during feature propagation. Current detection methods struggle to address these challenges while maintaining computational efficiency effectively. We propose Scale-Frequency Detection Transformer (SF-DETR), a novel end-to-end framework for drone-view scenarios. SF-DETR introduces a lightweight ScaleFormerNet backbone with Dual Scale Vision Transformer modules, a Bilateral Interactive Feature Enhancement Module, and a Multi-Scale Frequency-Fused Feature Enhancement Network. Extensive experiments on the VisDrone2019 dataset demonstrate SF-DETR’s superior performance, achieving 51.0% mAP50 and 31.8% mAP50:95, surpassing state-of-the-art methods like YOLOv9m and RTDETR-r18 by 6.2% and 4.0%, respectively. Further validation of the HIT-UAV dataset confirms the model’s generalization capability. Our work establishes a new benchmark for drone-view object detection and provides lightweight architecture suitable for embedded device deployment in real-world aerial surveillance applications.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- The School of Automation Engineering, Qingdao University, Qingdao 266071, China.
ORCID-Profile: Haotong Wang
Förderung
- The Key Technology Research and Industrialization Demonstration Project of Qingdao
- Shandong Provincial Natural Science Foundation
- Key Technology Research and Industrialization Demonstration Project of Qingdao
Zitieren
APA
Wang, H., & Gao, J. (2025). SF-DETR: A Scale-Frequency Detection Transformer for Drone-View Object Detection. Sensors, 25(7), 2190. https://doi.org/10.3390/s25072190
Vancouver
Wang H, Gao J. SF-DETR: A Scale-Frequency Detection Transformer for Drone-View Object Detection. Sensors. 2025;25(7):2190. doi:10.3390/s25072190
BibTeX
@article{Wang2025,
author = {Wang, Haotong and Gao, Junwei},
title = {SF-DETR: A Scale-Frequency Detection Transformer for Drone-View Object Detection},
journal = {Sensors},
year = {2025},
volume = {25},
number = {7},
pages = {2190},
doi = {10.3390/s25072190}
}
EUVIMED