EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

FasterNet-YOLO for real-time detection of steel surface defects algorithm

Shiwei Yu iD, Zelin Liu, Liang Zhang, Xiaoqiang Zhang, Jikui Wang

PLOS One · 2025

DOI: 10.1371/journal.pone.0323248 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Shiwei Yu und 4 weiteren Autor:innen. Beteiligte Einrichtung: CGN Digital Technology Co., Ltd., Shanghai, China. Hauptthemen laut MEDLINE: Steel, Algorithms, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 17-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yangjiang Nuclear Power Domestic Intelligent Security System Construction Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Steel surface defect detection is an important application of object detection in industry. Achieving object detection in industry while balancing detection accuracy and real-time performance is a challenge. Therefore, this paper proposes an improved FasterNet-YOLO model based on the one-stage detector. Introduce the FasterNet network to reconstruct the YOLOv5 backbone network. Achievement of model lightweighting and significant improvement in detection speed, but with a slight reduction in accuracy. The YOLOv5 neck network’s ordinary convolution is improved by depthwise separable convolution. Continuing to improve detection speed while further reducing redundant parameters in the neck network. To improve model accuracy, the Swin-Transformer is integrated into the C3 module in the neck network. Solve the problem of cluttered backgrounds in defect photographs and easy confusion between defect types. Meanwhile, BiFPN is used for feature fusion. By retaining more informative features, the detector’s ability to adapt to targets at different scales is improved. The results indicated that when comparing FasterNet-YOLO with the original model, the parameters were reduced by 49.4%, GFLOPs were reduced by 57.0%, mAP increased by 6.2%, and FPS increased by 54.1%. The improved model not only increases the detection accuracy, but also significantly improves the speed of hot-rolled strip surface defect detection to meet the requirements of real-time detection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SteelAlgorithmsImage Processing, Computer-AssistedSurface PropertiesNeural Networks, Computer

Substanzen

Steel

Autor:innen und Institutionen

  • CGN Digital Technology Co., Ltd., Shanghai, China.

ORCID-Profile: Shiwei Yu

Förderung

  • Yangjiang Nuclear Power Domestic Intelligent Security System Construction Project

Zitieren

APA

Yu, S., Liu, Z., Zhang, L., Zhang, X., & Wang, J. (2025). FasterNet-YOLO for real-time detection of steel surface defects algorithm. PLOS One. https://doi.org/10.1371/journal.pone.0323248

Vancouver

Yu S, Liu Z, Zhang L, Zhang X, Wang J. FasterNet-YOLO for real-time detection of steel surface defects algorithm. PLOS One. 2025. doi:10.1371/journal.pone.0323248

BibTeX
@article{Yu2025,
  author = {Yu, Shiwei and Liu, Zelin and Zhang, Liang and Zhang, Xiaoqiang and Wang, Jikui},
  title = {FasterNet-YOLO for real-time detection of steel surface defects algorithm},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0323248}
}
Kostenlos starten →