EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Research on a Metal Surface Defect Detection Algorithm Based on DSL-YOLO

Zhiwen Wang, Lei Zhao, Heng Li, Xiaojun Xue, Hui Liu

Sensors · 27.09.2024 · 24 (19) · 6268

DOI: 10.3390/s24196268 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 27.09.2024. Verfasst von Zhiwen Wang und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650032, China. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Science and Technology Department Basic Research Project - General Project, Yunnan Provincial Science and Technology Department Basic Research Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

In industrial manufacturing, metal surface defect detection often suffers from low detection accuracy, high leakage rates, and false detection rates. To address these issues, this paper proposes a novel model named DSL-YOLO for metal surface defect detection. First, we introduce the C2f_DWRB structure by integrating the DWRB module with C2f, enhancing the model’s ability to detect small and occluded targets and effectively extract sparse spatial features. Second, we design the SADown module to improve feature extraction in challenging tasks involving blurred images or very small objects. Finally, to further enhance the model’s capacity to extract multi-scale features and capture critical image information (such as edges, textures, and shapes) without significantly increasing memory usage and computational cost, we propose the LASPPF structure. Experimental results demonstrate that the improved model achieves significant performance gains on both the GC10-DET and NEU-DET datasets, with a mAP@0.5 increase of 4.2% and 2.6%, respectively. The improvements in detection accuracy highlight the model’s ability to address common challenges while maintaining efficiency and feasibility in metal surface defect detection, providing a valuable solution for industrial applications.

Schlagwörter

Stichwörter der Autor:innen

DWRB moduleLASPPF moduleSADown modulesurface defect detection

Autor:innen und Institutionen

  • Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming 650032, China.

Förderung

  • Yunnan Provincial Science and Technology Department Basic Research Project - General Project
  • Yunnan Provincial Science and Technology Department Basic Research Project

Zitieren

APA

Wang, Z., Zhao, L., Li, H., Xue, X., & Liu, H. (2024). Research on a Metal Surface Defect Detection Algorithm Based on DSL-YOLO. Sensors, 24(19), 6268. https://doi.org/10.3390/s24196268

Vancouver

Wang Z, Zhao L, Li H, Xue X, Liu H. Research on a Metal Surface Defect Detection Algorithm Based on DSL-YOLO. Sensors. 2024;24(19):6268. doi:10.3390/s24196268

BibTeX
@article{Wang2024,
  author = {Wang, Zhiwen and Zhao, Lei and Li, Heng and Xue, Xiaojun and Liu, Hui},
  title = {Research on a Metal Surface Defect Detection Algorithm Based on DSL-YOLO},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {19},
  pages = {6268},
  doi = {10.3390/s24196268}
}
Kostenlos starten →