EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

MSA-YOLO: A Remote Sensing Object Detection Model Based on Multi-Scale Strip Attention

Zihang Su, Jiong Yu, Haotian Tan, Xueqiang Wan, Kaiyang Qi

Sensors · 30.07.2023 · 23 (15) · 6811

DOI: 10.3390/s23156811 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 30.07.2023. Verfasst von Zihang Su und 4 weiteren Autor:innen. Beteiligte Einrichtung: School of Software, Xinjiang University, Urumqi 830091, China. Die Arbeit wurde bisher 56-mal zitiert (Crossref) und nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China Project under Grant, Key R&D projects in Xinjiang Uygur Autonomous Region, Natural Science Foundation of Xinjiang Uygur Autonomous Region of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Remote sensing image object detection holds significant research value in resources and the environment. Nevertheless, complex background information and considerable size differences between objects in remote sensing images make it challenging. This paper proposes an efficient remote sensing image object detection model (MSA-YOLO) to improve detection performance. First, we propose a Multi-Scale Strip Convolution Attention Mechanism (MSCAM), which can reduce the introduction of background noise and fuse multi-scale features to enhance the focus of the model on foreground objects of various sizes. Second, we introduce the lightweight convolution module GSConv and propose an improved feature fusion layer, which makes the model more lightweight while improving detection accuracy. Finally, we propose the Wise-Focal CIoU loss function, which can reweight different samples to balance the contribution of different samples to the loss function, thereby improving the regression effect. Experimental results show that on the remote sensing image public datasets DIOR and HRRSD, the performance of our proposed MSA-YOLO model is significantly better than other existing methods.

Schlagwörter

Stichwörter der Autor:innen

YOLO networkattention mechanismobject detectionremote sensing images

Autor:innen und Institutionen

  • School of Software, Xinjiang University, Urumqi 830091, China.
  • College of Information Science and Engineering, Xinjiang University, Urumqi 830046, China.

Förderung

  • National Natural Science Foundation of China Project under Grant
  • Key R&D projects in Xinjiang Uygur Autonomous Region
  • Natural Science Foundation of Xinjiang Uygur Autonomous Region of China
  • National Natural Science Foundation of China Project
  • Key R&D projects in Xinjiang Uygur Autonomous Region

Zitieren

APA

Su, Z., Yu, J., Tan, H., Wan, X., & Qi, K. (2023). MSA-YOLO: A Remote Sensing Object Detection Model Based on Multi-Scale Strip Attention. Sensors, 23(15), 6811. https://doi.org/10.3390/s23156811

Vancouver

Su Z, Yu J, Tan H, Wan X, Qi K. MSA-YOLO: A Remote Sensing Object Detection Model Based on Multi-Scale Strip Attention. Sensors. 2023;23(15):6811. doi:10.3390/s23156811

BibTeX
@article{Su2023,
  author = {Su, Zihang and Yu, Jiong and Tan, Haotian and Wan, Xueqiang and Qi, Kaiyang},
  title = {MSA-YOLO: A Remote Sensing Object Detection Model Based on Multi-Scale Strip Attention},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {15},
  pages = {6811},
  doi = {10.3390/s23156811}
}
Kostenlos starten →