EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

CSSA-YOLO: A Clutter-Suppressed and Scale-Aware Framework for Robust Object Detection in UAV Imagery

Xiao Yang, Yongjia Wang, Yong Wang, Wangyuan Li, Beiyuan Liu, Ganchao Liu

Remote Sensing · 12.05.2026 · 18 (10) · 1533

DOI: 10.3390/rs18101533 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 12.05.2026. Verfasst von Xiao Yang und 5 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Suzhou Leading Talent Program for Innovation and Entrepreneurship, Basic Research Programs of Taicang.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The widespread deployment of unmanned aerial vehicles (UAVs) in remote sensing has highlighted the necessity for robust object detection methods in UAV imagery. However, high-altitude UAV imagery suffers from severe background clutter that obscures target discriminability and extreme scale variations that degrade fine-grained features. To address these challenges, we propose CSSA-YOLO, a clutter-suppressed and scale-aware detection framework built upon YOLOv9. Specifically, we project dense spatial features into a low-rank token space via a Semantic Bottleneck Module (SBM). This projection acts as an information bottleneck, suppressing the background clutter while robustly retaining critical target semantic and structural priors. Furthermore, we develop a Scale-Aware Complete-IoU (SA-CIoU) loss to tackle gradient attenuation for small objects. By analytically integrating a scale-aware modulation factor with a dynamic alignment mechanism into localization optimization, SA-CIoU shifts the optimization priority to the precise localization of small and hard-to-detect instances. Extensive experiments on the VisDrone2019 benchmark demonstrate the superiority of our approach, with CSSA-YOLO achieving an mAP@0.5 of 46.0% and an mAP@0.5:0.95 of 28.4%, yielding an absolute 1.4% improvement over the YOLOv9 baseline. Furthermore, when integrated with a P2-enhanced YOLOv9 architecture, our method achieves a remarkable mAP@0.5 of 49.5%. Notably, evaluations across diverse scenarios, including the infrared (IR) thermal HIT-UAV benchmark and PCB defect detection datasets, further demonstrate the generalizability and robustness of our framework.

Förderung

  • National Natural Science Foundation of China
  • Suzhou Leading Talent Program for Innovation and Entrepreneurship
  • Basic Research Programs of Taicang

Zitieren

APA

Yang, X., Wang, Y., Wang, Y., Li, W., Liu, B., & Liu, G. (2026). CSSA-YOLO: A Clutter-Suppressed and Scale-Aware Framework for Robust Object Detection in UAV Imagery. Remote Sensing, 18(10), 1533. https://doi.org/10.3390/rs18101533

Vancouver

Yang X, Wang Y, Wang Y, Li W, Liu B, Liu G. CSSA-YOLO: A Clutter-Suppressed and Scale-Aware Framework for Robust Object Detection in UAV Imagery. Remote Sensing. 2026;18(10):1533. doi:10.3390/rs18101533

BibTeX
@article{Yang2026,
  author = {Yang, Xiao and Wang, Yongjia and Wang, Yong and Li, Wangyuan and Liu, Beiyuan and Liu, Ganchao},
  title = {CSSA-YOLO: A Clutter-Suppressed and Scale-Aware Framework for Robust Object Detection in UAV Imagery},
  journal = {Remote Sensing},
  year = {2026},
  volume = {18},
  number = {10},
  pages = {1533},
  doi = {10.3390/rs18101533}
}
Kostenlos starten →