EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

EFC-YOLO: An Efficient Surface-Defect-Detection Algorithm for Steel Strips

Yanshun Li, Shuobo Xu, Zhenfang Zhu iD, Peng Wang iD, Kefeng Li, Qiang He, Quanfeng Zheng

Sensors · 02.09.2023 · 23 (17) · 7619

DOI: 10.3390/s23177619 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 02.09.2023. Verfasst von Yanshun Li und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan 250357, China. Die Arbeit wurde bisher 35-mal zitiert (Crossref) und nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The pursuit of higher recognition accuracy and speed with smaller model sizes has been a major research topic in the detection of surface defects in steel. In this paper, we propose an improved high-speed and high-precision Efficient Fusion Coordination network (EFC-YOLO) without increasing the model’s size. Since modifications to enhance feature extraction in shallow networks tend to affect the speed of model inference, in order to simultaneously ensure the accuracy and speed of detection, we add the improved Fusion-Faster module to the backbone network of YOLOv7. Partial Convolution (PConv) serves as the basic operator of the module, which strengthens the feature-extraction ability of shallow networks while maintaining speed. Additionally, we incorporate the Shortcut Coordinate Attention (SCA) mechanism to better capture the location information dependency, considering both lightweight design and accuracy. The de-weighted Bi-directional Feature Pyramid Network (BiFPN) structure used in the neck part of the network improves the original Path Aggregation Network (PANet)-like structure by adding step branches and reducing computations, achieving better feature fusion. In the experiments conducted on the NEU-DET dataset, the final model achieved an 85.9% mAP and decreased the GFLOPs by 60%, effectively balancing the model’s size with the accuracy and speed of detection.

Schlagwörter

Stichwörter der Autor:innen

YOLOv7deep learningfeature extractionsurface defect detection

Autor:innen und Institutionen

  • School of Information Science and Electrical Engineering, Shandong Jiaotong University, Jinan 250357, China.

ORCID-Profile: Zhenfang Zhu, Peng Wang

Zitieren

APA

Li, Y., Xu, S., Zhu, Z., Wang, P., Li, K., He, Q., & Zheng, Q. (2023). EFC-YOLO: An Efficient Surface-Defect-Detection Algorithm for Steel Strips. Sensors, 23(17), 7619. https://doi.org/10.3390/s23177619

Vancouver

Li Y, Xu S, Zhu Z, Wang P, Li K, He Q, et al. EFC-YOLO: An Efficient Surface-Defect-Detection Algorithm for Steel Strips. Sensors. 2023;23(17):7619. doi:10.3390/s23177619

BibTeX
@article{Li2023,
  author = {Li, Yanshun and Xu, Shuobo and Zhu, Zhenfang and Wang, Peng and Li, Kefeng and He, Qiang and Zheng, Quanfeng},
  title = {EFC-YOLO: An Efficient Surface-Defect-Detection Algorithm for Steel Strips},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {17},
  pages = {7619},
  doi = {10.3390/s23177619}
}
Kostenlos starten →