EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SEB-YOLO: An Improved YOLOv5 Model for Remote Sensing Small Target Detection

Yan Hui, Shijie You iD, Xiuhua Hu, Panpan Yang iD, Jing Zhao

Sensors · 29.03.2024 · 24 (7) · 2193

DOI: 10.3390/s24072193 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 29.03.2024. Verfasst von Yan Hui und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Engineering, Xi'an Technological University, Xi'an 710021, China. Die Arbeit wurde bisher 40-mal zitiert (Crossref) und nennt 50 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Natural Science Basic Research Project of Shaanxi Provincial Department of Science and Technology.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Due to the limited semantic information extraction with small objects and difficulty in distinguishing similar targets, it brings great challenges to target detection in remote sensing scenarios, which results in poor detection performance. This paper proposes an improved YOLOv5 remote sensing image target detection algorithm, SEB-YOLO (SPD-Conv + ECSPP + Bi-FPN + YOLOv5). Firstly, the space-to-depth (SPD) layer followed by a non-strided convolution (Conv) layer module (SPD-Conv) was used to reconstruct the backbone network, which retained the global features and reduced the feature loss. Meanwhile, the pooling module with the attention mechanism of the final layer of the backbone network was designed to help the network better identify and locate the target. Furthermore, a bidirectional feature pyramid network (Bi-FPN) with bilinear interpolation upsampling was added to improve bidirectional cross-scale connection and weighted feature fusion. Finally, the decoupled head is introduced to enhance the model convergence and solve the contradiction between the classification task and the regression task. Experimental results on NWPU VHR-10 and RSOD datasets show that the mAP of the proposed algorithm reaches 93.5% and 93.9%respectively, which is 4.0% and 5.3% higher than that of the original YOLOv5l algorithm. The proposed algorithm achieves better detection results for complex remote sensing images.

Schlagwörter

Stichwörter der Autor:innen

YOLOv5attention mechanismfeature fusionsmall target detection

Autor:innen und Institutionen

  • School of Computer Science and Engineering, Xi'an Technological University, Xi'an 710021, China.
  • State and Provincial Joint Engineering Laboratory of Advanced Network, Monitoring and Control, Xi'an 710021, China.

ORCID-Profile: Shijie You, Panpan Yang

Förderung

  • Natural Science Basic Research Project of Shaanxi Provincial Department of Science and Technology

Zitieren

APA

Hui, Y., You, S., Hu, X., Yang, P., & Zhao, J. (2024). SEB-YOLO: An Improved YOLOv5 Model for Remote Sensing Small Target Detection. Sensors, 24(7), 2193. https://doi.org/10.3390/s24072193

Vancouver

Hui Y, You S, Hu X, Yang P, Zhao J. SEB-YOLO: An Improved YOLOv5 Model for Remote Sensing Small Target Detection. Sensors. 2024;24(7):2193. doi:10.3390/s24072193

BibTeX
@article{Hui2024,
  author = {Hui, Yan and You, Shijie and Hu, Xiuhua and Yang, Panpan and Zhao, Jing},
  title = {SEB-YOLO: An Improved YOLOv5 Model for Remote Sensing Small Target Detection},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {7},
  pages = {2193},
  doi = {10.3390/s24072193}
}
Kostenlos starten →