EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EFSL-YOLO: An Improved Model for Small Object Detection in UAV Vision

Meng Zhou, Shuke He, Chang Wang, Jing Wang

Drones · 27.03.2026 · 10 (4) · 243

DOI: 10.3390/drones10040243 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Drones, online erschienen am 27.03.2026. Verfasst von Meng Zhou und 3 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Research and Development Program of China, Outstanding Talent Development Program in Yanqing District, R&D Program of Beijing Municipal Education Commission.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

To address the challenges in UAV remote sensing imagery, such as small object size, dense occlusion and complex background interference, this paper proposes an enhanced small object detection algorithm based on an improved YOLOv13 model for drone applications in complex weather environments. First, an enhanced feature fusion attention network (EFFA-Net) is designed in the preprocessing stage to reduce image degradation and suppress the interference caused by smoke and haze. Then, in the backbone, a swish-gated convolution (SwiGLUConv) module is designed to adaptively expand the receptive field and enhance multi-scale feature extraction, which strengthens the representation of small targets while maintaining efficient computation. Furthermore, a locally enhanced multi-scale context fusion (LF-MSCF) module is integrated into the feature fusion neck of YOLO, combining multi-head self-attention, channel attention, and spatial attention to suppress background noise and redundant responses, thereby improving detection accuracy. Extensive experiments on the VisDrone-DET2019 dataset, UAVDT dataset, and HazyDet dataset demonstrate that the proposed algorithm outperforms other mainstream methods, showcasing excellent detection accuracy and robustness in complex UAV aerial scenarios.

Förderung

  • National Key Research and Development Program of China
  • Outstanding Talent Development Program in Yanqing District
  • R&D Program of Beijing Municipal Education Commission
  • Yuxiu Innovation Project of NCUT
  • North China Institute of Science and Technology

Zitieren

APA

Zhou, M., He, S., Wang, C., & Wang, J. (2026). EFSL-YOLO: An Improved Model for Small Object Detection in UAV Vision. Drones, 10(4), 243. https://doi.org/10.3390/drones10040243

Vancouver

Zhou M, He S, Wang C, Wang J. EFSL-YOLO: An Improved Model for Small Object Detection in UAV Vision. Drones. 2026;10(4):243. doi:10.3390/drones10040243

BibTeX
@article{Zhou2026,
  author = {Zhou, Meng and He, Shuke and Wang, Chang and Wang, Jing},
  title = {EFSL-YOLO: An Improved Model for Small Object Detection in UAV Vision},
  journal = {Drones},
  year = {2026},
  volume = {10},
  number = {4},
  pages = {243},
  doi = {10.3390/drones10040243}
}
Kostenlos starten →