EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

SLGA-YOLO: A Lightweight Castings Surface Defect Detection Method Based on Fusion-Enhanced Attention Mechanism and Self-Architecture

Chengjun Wang, Yifan Wang

Sensors · 24.06.2024 · 24 (13) · 4088

DOI: 10.3390/s24134088 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 24.06.2024. Verfasst von Chengjun Wang und 1 weiteren Autor:innen. Beteiligte Einrichtung: School of Artificial Intelligence, Anhui University of Science and Technology, Huainan 232001, China. Die Arbeit wurde bisher 16-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: The Natural Science Foundation of Anhui Province, Natural Science Foundation of Anhui Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Castings’ surface-defect detection is a crucial machine vision-based automation technology. This paper proposes a fusion-enhanced attention mechanism and efficient self-architecture lightweight YOLO (SLGA-YOLO) to overcome the existing target detection algorithms’ poor computational efficiency and low defect-detection accuracy. We used the SlimNeck module to improve the neck module and reduce redundant information interference. The integration of simplified attention module (SimAM) and Large Separable Kernel Attention (LSKA) fusion strengthens the attention mechanism, improving the detection performance, while significantly reducing computational complexity and memory usage. To enhance the generalization ability of the model’s feature extraction, we replaced part of the basic convolutional blocks with the self-designed GhostConvML (GCML) module, based on the addition of p2 detection. We also constructed the Alpha-EIoU loss function to accelerate model convergence. The experimental results demonstrate that the enhanced algorithm increases the average detection accuracy (mAP@0.5) by 3% and the average detection accuracy (mAP@0.5:0.95) by 1.6% in the castings’ surface defects dataset.

Schlagwörter

Stichwörter der Autor:innen

YOLOv8attention mechanismcastings’ surface-defect detection

Autor:innen und Institutionen

  • School of Artificial Intelligence, Anhui University of Science and Technology, Huainan 232001, China.

Förderung

  • The Natural Science Foundation of Anhui Province
  • Natural Science Foundation of Anhui Province

Zitieren

APA

Wang, C., & Wang, Y. (2024). SLGA-YOLO: A Lightweight Castings Surface Defect Detection Method Based on Fusion-Enhanced Attention Mechanism and Self-Architecture. Sensors, 24(13), 4088. https://doi.org/10.3390/s24134088

Vancouver

Wang C, Wang Y. SLGA-YOLO: A Lightweight Castings Surface Defect Detection Method Based on Fusion-Enhanced Attention Mechanism and Self-Architecture. Sensors. 2024;24(13):4088. doi:10.3390/s24134088

BibTeX
@article{Wang2024,
  author = {Wang, Chengjun and Wang, Yifan},
  title = {SLGA-YOLO: A Lightweight Castings Surface Defect Detection Method Based on Fusion-Enhanced Attention Mechanism and Self-Architecture},
  journal = {Sensors},
  year = {2024},
  volume = {24},
  number = {13},
  pages = {4088},
  doi = {10.3390/s24134088}
}
Kostenlos starten →