EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

LGM-YOLO: A Context-Aware Multi-Scale YOLO-Based Network for Automated Structural Defect Detection

Chuanqi Liu, Yi Huang, Zaiyou Zhao, Wenjing Geng, Tianhong Luo

Processes · 29.07.2025 · 13 (8) · 2411

DOI: 10.3390/pr13082411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 29.07.2025. Verfasst von Chuanqi Liu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Special Project for Performance Incentive and Guidance of Research Institutions in Chongqing, National Natural Science Foundation of China, Innovation and Development Joint Fund Projects of Chongqing Natural Science Foundation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring the structural safety of steel trusses in escalators is critical for the reliable operation of vertical transportation systems. While manual inspection remains widely used, its dependence on human judgment leads to extended cycle times and variable defect-recognition rates, making it less reliable for identifying subtle surface imperfections. To address these limitations, a novel context-aware, multi-scale deep learning framework based on the YOLOv5 architecture is proposed, which is specifically designed for automated structural defect detection in escalator steel trusses. Firstly, a method called GIES is proposed to synthesize pseudo-multi-channel representations from single-channel grayscale images, which enhances the network’s channel-wise representation and mitigates issues arising from image noise and defocused blur. To further improve detection performance, a context enhancement pipeline is developed, consisting of a local feature module (LFM) for capturing fine-grained surface details and a global context module (GCM) for modeling large-scale structural deformations. In addition, a multi-scale feature fusion module (MSFM) is employed to effectively integrate spatial features across various resolutions, enabling the detection of defects with diverse sizes and complexities. Comprehensive testing on the NEU-DET and GC10-DET datasets reveals that the proposed method achieves 79.8% mAP on NEU-DET and 68.1% mAP on GC10-DET, outperforming the baseline YOLOv5s by 8.0% and 2.7%, respectively. Although challenges remain in identifying extremely fine defects such as crazing, the proposed approach offers improved accuracy while maintaining real-time inference speed. These results indicate the potential of the method for intelligent visual inspection in structural health monitoring and industrial safety applications.

Förderung

  • Special Project for Performance Incentive and Guidance of Research Institutions in Chongqing
  • National Natural Science Foundation of China
  • Innovation and Development Joint Fund Projects of Chongqing Natural Science Foundation
  • General Projects of Chongqing Natural Science Foundation

Zitieren

APA

Liu, C., Huang, Y., Zhao, Z., Geng, W., & Luo, T. (2025). LGM-YOLO: A Context-Aware Multi-Scale YOLO-Based Network for Automated Structural Defect Detection. Processes, 13(8), 2411. https://doi.org/10.3390/pr13082411

Vancouver

Liu C, Huang Y, Zhao Z, Geng W, Luo T. LGM-YOLO: A Context-Aware Multi-Scale YOLO-Based Network for Automated Structural Defect Detection. Processes. 2025;13(8):2411. doi:10.3390/pr13082411

BibTeX
@article{Liu2025,
  author = {Liu, Chuanqi and Huang, Yi and Zhao, Zaiyou and Geng, Wenjing and Luo, Tianhong},
  title = {LGM-YOLO: A Context-Aware Multi-Scale YOLO-Based Network for Automated Structural Defect Detection},
  journal = {Processes},
  year = {2025},
  volume = {13},
  number = {8},
  pages = {2411},
  doi = {10.3390/pr13082411}
}
Kostenlos starten →