EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Strip Surface Defect Detection Algorithm Based on YOLOv5

Han Wang iD, Xiuding Yang, Bei Zhou iD, Zhuohao Shi, Daohua Zhan, Renbin Huang, Jian Lin, Zhiheng Wu, Danfeng Long

Materials · 31.03.2023 · 16 (7) · 2811

DOI: 10.3390/ma16072811 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Materials, online erschienen am 31.03.2023. Verfasst von Han Wang und 8 weiteren Autor:innen. Beteiligte Einrichtung: School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China. Die Arbeit wurde bisher 25-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Guangdong Academy of Sciences, Guangdong University of Technology, Jihua Laboratory Foundation of the Guangdong Province Laboratory of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

Schlagwörter

Stichwörter der Autor:innen

YOLOv5attention mechanismdeep learninghot rolled strip steelsurface defect detection

Autor:innen und Institutionen

  • School of Mechanical and Electrical Engineering, Guangdong University of Technology, Guangzhou 510006, China.
  • Institute of Intelligent Manufacturing, Guangdong Academy of Sciences, Guangzhou 510070, China.
  • Guangdong Provincial Key Laboratory of Modern Control Technology, Guangzhou 510070, China.

ORCID-Profile: Han Wang, Bei Zhou

Förderung

  • Guangdong Academy of Sciences
  • Guangdong University of Technology
  • Jihua Laboratory Foundation of the Guangdong Province Laboratory of China
  • National Natural Science Foundation of China
  • Natural Science Foundation of Guangdong Province
  • Guangdong Province Key Areas R&D Program
  • Guangzhou Key R&D Program
  • International Science and Technology Cooperation Project of Huangpu

Zitieren

APA

Wang, H., Yang, X., Zhou, B., Shi, Z., Zhan, D., Huang, R., Lin, J., Wu, Z., & Long, D. (2023). Strip Surface Defect Detection Algorithm Based on YOLOv5. Materials, 16(7), 2811. https://doi.org/10.3390/ma16072811

Vancouver

Wang H, Yang X, Zhou B, Shi Z, Zhan D, Huang R, et al. Strip Surface Defect Detection Algorithm Based on YOLOv5. Materials. 2023;16(7):2811. doi:10.3390/ma16072811

BibTeX
@article{Wang2023,
  author = {Wang, Han and Yang, Xiuding and Zhou, Bei and Shi, Zhuohao and Zhan, Daohua and Huang, Renbin and Lin, Jian and Wu, Zhiheng and Long, Danfeng},
  title = {Strip Surface Defect Detection Algorithm Based on YOLOv5},
  journal = {Materials},
  year = {2023},
  volume = {16},
  number = {7},
  pages = {2811},
  doi = {10.3390/ma16072811}
}
Kostenlos starten →