EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

DAE-YOLO: Remote Sensing Small Object Detection Method Integrating YOLO and State Space Models

Bing Li, Yongtao Kang, Yao Ding, Shaopeng Li, Zhili Zhang, Decao Ma

Remote Sensing · 28.12.2025 · 18 (1) · 109

DOI: 10.3390/rs18010109 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Remote Sensing, online erschienen am 28.12.2025. Verfasst von Bing Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 11-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, China Postdoctoral Science Foundation, Young Talent Fund of the University Association for Science and Technology in Shannxi.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small object detection in remote sensing images provides significant value for urban monitoring, aerospace reconnaissance, and other fields. However, detection accuracy still faces multiple challenges including limited target information, weak feature representation, and complex backgrounds. This research aims to improve the performance of the YOLO11 model for small object detection in remote sensing imagery by addressing key issues in long-distance spatial dependency modeling, multi-scale feature adaptive fusion, and computational efficiency. We constructed a specialized Remote Sensing Airport-Plane Detection (RS-APD) dataset and used the public VisDrone2019 dataset for generalization verification. Based on the YOLO11 architecture, we proposed the DAE-YOLO model with three innovative modules: Dynamic Spatial Sequence Module (DSSM) for enhanced long-distance spatial dependency capture; Adaptive Multi-scale Feature Enhancement (AMFE) for multi-scale feature adaptive receptive field adjustment; and Efficient Dual-level Attention Mechanism (EDAM) to reduce computational complexity while maintaining feature expression capability. Experimental results demonstrate that compared to the baseline YOLO11, our proposed model improved mAP50 and mAP50:95 on the RS-APD dataset by 2.1% and 2.5%, respectively, with APs increasing by 2.8%. This research provides an efficient and reliable small object detection solution for remote sensing applications.

Förderung

  • National Natural Science Foundation of China
  • China Postdoctoral Science Foundation
  • Young Talent Fund of the University Association for Science and Technology in Shannxi

Zitieren

APA

Li, B., Kang, Y., Ding, Y., Li, S., Zhang, Z., & Ma, D. (2025). DAE-YOLO: Remote Sensing Small Object Detection Method Integrating YOLO and State Space Models. Remote Sensing, 18(1), 109. https://doi.org/10.3390/rs18010109

Vancouver

Li B, Kang Y, Ding Y, Li S, Zhang Z, Ma D. DAE-YOLO: Remote Sensing Small Object Detection Method Integrating YOLO and State Space Models. Remote Sensing. 2025;18(1):109. doi:10.3390/rs18010109

BibTeX
@article{Li2025,
  author = {Li, Bing and Kang, Yongtao and Ding, Yao and Li, Shaopeng and Zhang, Zhili and Ma, Decao},
  title = {DAE-YOLO: Remote Sensing Small Object Detection Method Integrating YOLO and State Space Models},
  journal = {Remote Sensing},
  year = {2025},
  volume = {18},
  number = {1},
  pages = {109},
  doi = {10.3390/rs18010109}
}
Kostenlos starten →