EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Structural damage detection and safety assessment method based on machine vision and machine learning

Shengmin Wang iD, Moxiao Li, Di Le iD

PLOS One · 2026

DOI: 10.1371/journal.pone.0341653 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2026. Verfasst von Shengmin Wang und 2 weiteren Autor:innen. Beteiligte Einrichtung: School of Management, Wuhan Textile University, Wuhan, China. Hauptthemen laut MEDLINE: Machine Learning, Image Processing, Computer-Assisted, Safety. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 77 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: the National Natural Science Foundation of China Youth Project, Hubei Key Laboratory of Intelligent Geo-Information Processing.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Structural damage detection and health assessment are crucial for maintaining infrastructure safety and durability. This study presents a novel multi-scale vision-based framework that combines deep learning and machine learning for accurate and interpretable structural safety evaluation. Specifically, we integrate ResNet-50 and SegFormer models to jointly achieve coarse-level damage classification and fine-grained pixel-level segmentation. Seven key damage parameters are quantitatively extracted from high-resolution images—such as crack length, spalling area, and rebar exposure—and serve as interpretable features for safety assessment. A Random Forest (RF) model is developed to establish a nonlinear mapping from these visual features to structural safety levels. Experimental results demonstrate that the RF-based safety assessment model outperforms other traditional machine learning approaches, achieving an accuracy of 87.0%, F1-score of 0.76, and AUC of 0.83, highlighting its strong generalization and classification capabilities. This work offers a comprehensive and generalizable solution for automated structural damage detection and safety evaluation.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningImage Processing, Computer-AssistedSafetyRandom ForestHumansConvolutional Neural NetworksClassification Algorithms

Autor:innen und Institutionen

  • School of Management, Wuhan Textile University, Wuhan, China.
  • School of Safety Science and Emergency Management, Wuhan University of Technology, Wuhan, China.
  • Hubei Longzhong Laboratory, Xiangyang, China.
  • Wuhan University of Technology, Department of Security, Wuhan, China.

ORCID-Profile: Shengmin Wang, Di Le

Förderung

  • the National Natural Science Foundation of China Youth Project
  • Hubei Key Laboratory of Intelligent Geo-Information Processing

Zitieren

APA

Wang, S., Li, M., & Le, D. (2026). Structural damage detection and safety assessment method based on machine vision and machine learning. PLOS One. https://doi.org/10.1371/journal.pone.0341653

Vancouver

Wang S, Li M, Le D. Structural damage detection and safety assessment method based on machine vision and machine learning. PLOS One. 2026. doi:10.1371/journal.pone.0341653

BibTeX
@article{Wang2026,
  author = {Wang, Shengmin and Li, Moxiao and Le, Di},
  title = {Structural damage detection and safety assessment method based on machine vision and machine learning},
  journal = {PLOS One},
  year = {2026},
  doi = {10.1371/journal.pone.0341653}
}
Kostenlos starten →