EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EMFE-YOLO: A Lightweight Small Object Detection Model for UAVs

Chengjun Yang iD, Yan Shen iD, Lutao Wang

Sensors · 21.08.2025 · 25 (16) · 5200

DOI: 10.3390/s25165200 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 21.08.2025. Verfasst von Chengjun Yang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Science and Technology Project of Sichuan Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Small object detection in Unmanned Aerial Vehicles’ (UAVs) aerial images faces challenges such as low detection accuracy and complex backgrounds. Meanwhile, it is difficult to deploy the object detection models with large parameters on resource-constrained UAVs. Therefore, a lightweight small object detection model EMFE-YOLO is proposed based on efficient multi-scale feature enhancement by improving YOLOv8s. Firstly, the Enhanced Attention to Large-scale Features (EALF) structure is applied in EMFE-YOLO to focus on large-scale features, improve the detection ability to small objects, and decrease the parameters. Secondly, the efficient multi-scale feature enhancement (EMFE) module is integrated into the backbone of EALF for feature extraction and enhancement. The EMFE module reduces the computational cost, obtains richer contextual information, and mitigates the interference from complex backgrounds. Finally, DySample is employed in the neck of EALF to optimize the upsampling process of features. The EMFE-YOLO is validated on the VisDrone2019-val dataset. Experimental results show that it improves mAP50 and mAP50:95 by 8.5% and 6.3%, respectively, and reduces the parameters by 73% compared to YOLOv8s. These results demonstrate that EMFE-YOLO achieves a good balance between accuracy and efficiency, making it suitable for deployment on UAVs with limited computational resources.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8enhanced attention to large-scale featureslightweight small object detection modelmulti-scale feature enhancementunmanned aerial vehicles

Autor:innen und Institutionen

  • School of Computer Science, Chengdu University of Information Technology, Chengdu 610225, China.

ORCID-Profile: Chengjun Yang, Yan Shen

Förderung

  • National Natural Science Foundation of China
  • Science and Technology Project of Sichuan Province

Zitieren

APA

Yang, C., Shen, Y., & Wang, L. (2025). EMFE-YOLO: A Lightweight Small Object Detection Model for UAVs. Sensors, 25(16), 5200. https://doi.org/10.3390/s25165200

Vancouver

Yang C, Shen Y, Wang L. EMFE-YOLO: A Lightweight Small Object Detection Model for UAVs. Sensors. 2025;25(16):5200. doi:10.3390/s25165200

BibTeX
@article{Yang2025,
  author = {Yang, Chengjun and Shen, Yan and Wang, Lutao},
  title = {EMFE-YOLO: A Lightweight Small Object Detection Model for UAVs},
  journal = {Sensors},
  year = {2025},
  volume = {25},
  number = {16},
  pages = {5200},
  doi = {10.3390/s25165200}
}
Kostenlos starten →