EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Semantic segmentation and quantitative analysis of tunnel cracks and water leakage using a TransUNet framework

Xinjian Li, Qiaofeng Liu, Gang Yan, Qifeng Yu iD

PLOS One · 11.08.2026 · 21 (8) · e0349175

DOI: 10.1371/journal.pone.0349175 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 11.08.2026. Verfasst von Xinjian Li und 3 weiteren Autor:innen. Beteiligte Einrichtung: Business School, Guilin University of Electronic Technology, Guilin, China. Hauptthemen laut MEDLINE: Water, Semantics, Image Processing, Computer-Assisted. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Program of Guangxi.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As a vital component of structural health monitoring, the detection of cracks and water leakage in tunnel linings is essential for ensuring structural durability and operational safety. However, due to complex site conditions, such as non-uniform illumination, surface texture interference, and the slender, blurred nature of defects, traditional manual inspections and threshold-based algorithms often fail to provide reliable damage identification. To address these challenges, this study proposes an end-to-end semantic segmentation framework based on TransUNet. By integrating the local feature extraction of convolutional neural networks (CNNs) with the global dependency modeling of Transformers, the framework significantly enhances the characterization of multi-scale defects and boundary features. A comprehensive dataset comprising public benchmarks and real-world engineering images was developed using a standardized preprocessing and validation pipeline. The proposed method was systematically evaluated against state-of-the-art models like U-Net and DeepLabv3 + . Experimental results demonstrate that the TransUNet framework achieves an IoU of 71.57% for crack segmentation and a Precision of 91.51% for water leakage. Crucially for engineering applications, the geometric error for length and area measurements is maintained within 5%, while the inference latency remains under 200 ms. In terms of precision, boundary preservation, and geometric consistency, the proposed method shows clear advantages over the comparison models, while U‑Net exhibits stronger region overlap for water leakage detection. Overall, the method meets the requirements of offline inspection and near-real-time applications. This data-driven approach provides a robust technical foundation for tunnel defect detection and subsequent maintenance decision-making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

WaterSemanticsImage Processing, Computer-AssistedConvolutional Neural NetworksAlgorithms

Substanzen

Water

Autor:innen und Institutionen

  • Business School, Guilin University of Electronic Technology, Guilin, China.
  • Guangxi Institute of Industrial Technology for Space-Time Information Co., Ltd, Nanning, China.
  • Guangxi Transport Vocational and Technical College, Nanning, China.
  • College of Transport and Communications, Shanghai Maritime University, Shanghai, China.

ORCID-Profile: Qifeng Yu

Förderung

  • Science and Technology Program of Guangxi

Zitieren

APA

Li, X., Liu, Q., Yan, G., & Yu, Q. (2026). Semantic segmentation and quantitative analysis of tunnel cracks and water leakage using a TransUNet framework. PLOS One, 21(8), e0349175. https://doi.org/10.1371/journal.pone.0349175

Vancouver

Li X, Liu Q, Yan G, Yu Q. Semantic segmentation and quantitative analysis of tunnel cracks and water leakage using a TransUNet framework. PLOS One. 2026;21(8):e0349175. doi:10.1371/journal.pone.0349175

BibTeX
@article{Li2026,
  author = {Li, Xinjian and Liu, Qiaofeng and Yan, Gang and Yu, Qifeng},
  title = {Semantic segmentation and quantitative analysis of tunnel cracks and water leakage using a TransUNet framework},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0349175},
  doi = {10.1371/journal.pone.0349175}
}
Kostenlos starten →