EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Shield Tunnel Crack Detection Based on Improved Unet

Gang Ming, Xiao-Wei Ye iD, Da Hang, Jian-She Qin, Jie Li

Sensors · 26.05.2026 · 26 (11) · 3360

DOI: 10.3390/s26113360 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 26.05.2026. Verfasst von Gang Ming und 4 weiteren Autor:innen. Beteiligte Einrichtung: Polytechnic Institute, Zhejiang University, Hangzhou 310015, China. Die Arbeit nennt 35 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Unet, a deep learning architecture, has become one of the most widely used models for crack detection in the tunneling field. Although it performs well in overall crack image segmentation, it still has issues of limited feature expression capability and inaccurate segmentation. To address these problems, DTA-Unet was proposed based on dynamic convolution decomposition (DCD) and triple attention (TA). Firstly, the model used Unet as the baseline network and replaced traditional convolutions in the encoding-decoding process with DCD to enhance its feature extraction ability. Secondly, TA was combined with attention gate (AG) in the skip connections of the network, eliminating redundant information in spatial and channel dimensions to highlight the crack area. Finally, the proposed model was tested on crack datasets and compared with the conventional Unet model, image processing algorithms, and other deep neural network models in terms of detection performance on the datasets. The results show that it outperforms other advanced methods in crack detection performance. The proposed method is of significance to the maintenance of shield tunnel cracks.

Schlagwörter

Stichwörter der Autor:innen

DTA-Unetcrack detectiondynamic convolution decompositionshield tunneltriple attention

Autor:innen und Institutionen

  • Polytechnic Institute, Zhejiang University, Hangzhou 310015, China.
  • Department of Civil Engineering, Zhejiang University, Hangzhou 310058, China.
  • Hangzhou Metro Group Co., Ltd., Hangzhou 310017, China.

ORCID-Profile: Xiao-Wei Ye

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Ming, G., Ye, X. W., Hang, D., Qin, J. S., & Li, J. (2026). Shield Tunnel Crack Detection Based on Improved Unet. Sensors, 26(11), 3360. https://doi.org/10.3390/s26113360

Vancouver

Ming G, Ye XW, Hang D, Qin JS, Li J. Shield Tunnel Crack Detection Based on Improved Unet. Sensors. 2026;26(11):3360. doi:10.3390/s26113360

BibTeX
@article{Ming2026,
  author = {Ming, Gang and Ye, Xiao-Wei and Hang, Da and Qin, Jian-She and Li, Jie},
  title = {Shield Tunnel Crack Detection Based on Improved Unet},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {11},
  pages = {3360},
  doi = {10.3390/s26113360}
}
Kostenlos starten →