|Table of Contents|

[1] WANG Meng, YANG Yanze, LIU Cheng, XU Huitong, et al. An automatic system for detecting and analyzing tunnel lining cracks based on deep learning [J]. Journal of Southeast University (English Edition), 2026, 42 (3): 337-350. [doi:10.3969/j.issn.1003-7985.2026.03.007]
Copy

An automatic system for detecting and analyzing tunnel lining cracks based on deep learning()
基于深度学习的隧道衬砌裂缝智能检测分析系统

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
42
Issue:
2026 3
Page:
337-350
Research Field:
Traffic and Transportation Engineering
Publishing date:
2026-09-06

Info

Title:
An automatic system for detecting and analyzing tunnel lining cracks based on deep learning
基于深度学习的隧道衬砌裂缝智能检测分析系统
Author(s):
WANG Meng1, YANG Yanze1,2, LIU Cheng3, XU Huitong1, ZHANG Xiaoyue1
1.School of Civil Engineering, Beijing Jiaotong University, Beijing 100044, China
2.China Energy Engineering Group Yunnan Electric Power Design Institute Co., Ltd., Kunming 650051, China
3.China-Road Transportation Verification and Inspection Hi-Tech Co., Ltd., Beijing 100088, China
王萌1, 杨燕泽1,2, 刘诚3, 徐慧通1, 张小月1
1.北京交通大学土木建筑工程学院, 北京 100044
2.中国能源建设集团云南省电力设计院有限公司, 昆明 650051
3.中路高科交通检测检验认证有限公司, 北京 100088
Keywords:
tunnel crack detection;  tunnel crack dataset;  semantic segmentation;  system development;  crack quantification
隧道裂缝检测;  隧道裂缝数据集;  语义分割;  系统开发;  裂缝量化
PACS:
U456.1
DOI:
10.3969/j.issn.1003-7985.2026.03.007
Abstract:
To address the low detection efficiency and difficult identification of microcracks in tunnel lining cracks, a closed-loop automatic detection system for tunnel lining cracks was proposed. Lining data were collected from 21 tunnels across five provinces of China, and an optimized annotation method was adopted to construct a dedicated tunnel crack dataset (T_Crack). The semantic segmentation network was improved by introducing a multichannel parallel mixed attention mechanism (MPMA) to enhance microcrack recognition accuracy. A tunnel crack detection application was developed to enable crack identification, quantification, localization, and panoramic image generation. The results show that the improved network achieves a mean Dice coefficient of 84.06%, a mean accuracy of 82.94%, and a mean intersection over union of 75.68% on T_Crack. Compared with the traditional annotation method, the optimized annotation method improves the labeling efficiency by 90.23% on average. The mean absolute error of the system is 0.076 mm, which is lower than the engineering detection accuracy requirement. The application of this system to long-term tunnel operation and maintenance can significantly improve the efficiency of tunnel inspection.
针对隧道衬砌裂缝检测效率低、微裂缝识别困难等问题,构建了一套闭环隧道衬砌裂缝自动检测系统。采集国内5省份21条隧道衬砌数据,利用优化标注方法,建立了隧道裂缝专用数据集T_crack。对语义分割网络进行改进,提出多通道并行混合注意力机制(MPMA),以提高微裂纹的识别精度。开发了裂缝检测应用,以实现裂缝识别、量化、定位及全景图像生成功能。试验结果表明,改进网络在T_crack数据集上的平均Dice系数为84.06%,平均准确率为82.94%,平均交并比为75.68%。相比传统标注方法,优化标注方法使标注效率平均提升90.23%。系统检测平均绝对误差为0.076 mm,低于工程检测精度要求,将其应用于隧道长期运维中,可以显著提升检测工作效率。

References:

[1]GAO W, YUAN S, GE S, et al. Inversion identification of cracks for underground shield tunnel structure based on HHO-XFEM[J]. Journal of Computing in Civil Engineering, 2025, 39: 04025015.
[2]JIANG Y, WANG L, ZHANG B, et al. Tunnel lining detection and retrofitting[J]. Automation in Construction, 2023, 152: 104881.
[3]KOCH C, GEORGIEVA K, KASIREDDY V, et al. A review on computer vision based defect detection and condition assessment of concrete and asphalt civil infrastructure[J]. Advanced Engineering Informatics, 2015, 29: 196-210.
[4]ATTARD L, DEBONO C J, VALENTINO G, et al. Tunnel inspection using photogrammetric techniques and image processing: A review[J]. ISPRS Journal of Photogrammetry and Remote Sensing, 2018, 144: 180-188.
[5]XUE Y, SHI P, JIA F, et al. 3D reconstruction and automatic leakage defect quantification of metro tunnel based on SfM-deep learning method[J]. Underground Space, 2022, 7: 311-323.
[6]FENG C, ZHANG H, LI Y, et al. Efficient real-time defect detection for spillway tunnel using deep learning[J]. Journal of Real-Time Image Processing, 2021, 18: 2377-2387.
[7]FLAH M, NUNEZ I, CHAABENE W BEN, et al. Machine learning algorithms in civil structural health monitoring: A systematic review[J]. Archives of Computational Methods in Engineering, 2021, 28: 2621-2643.
[8]MONTERO R, VICTORES J G, MARTÍNEZ S, et al. Past, present and future of robotic tunnel inspection[J]. Automation in Construction, 2015, 59: 99-112.
[9]WANG S, CAI B, WANG W, et al. Automated detection of pavement distress based on enhanced YOLOv8 and synthetic data with textured background modeling[J]. Transportation Geotechnics, 2024, 48: 101304.
[10]YU H, DENG Y, GUO F. Real-time pavement surface crack detection based on lightweight semantic segmentation model[J]. Transportation Geotechnics, 2024, 48: 101335.
[11]YOUNG T, HAZARIKA D, PORIA S, et al. Recent trends in deep learning based natural language processing[J]. IEEE Computational Intelligence Magazine, 2018, 13: 55-75.
[12]XU Z, SUN Z, HUYAN J, et al. Pixel-level pavement crack detection using enhanced high-resolution semantic network[J]. International Journal of Pavement Engineering, 2022, 23: 4943-4957.
[13]YU L, ZENG Z, LIU A, et al. A lightweight complex-valued DeepLabv3+ for semantic segmentation of PolSAR image[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2022, 15: 930-943.
[14]KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Advances in Neural Information Processing Systems, 2012, 25: 1097-1105.
[15]LIU F, DING W, QIAO Y, et al. Transfer learning-based encoder-decoder model with visual explanations for infrastructure crack segmentation: New open database and comprehensive evaluation[J]. Underground Space, 2024, 17: 60-81.
[16]HUANG H, LI Q, ZHANG D. Deep learning based image recognition for crack and leakage defects of metro shield tunnel[J]. Tunnelling and Underground Space Technology, 2018, 77: 166-176.
[17]JI A, XUE X, WANG Y, et al. An integrated approach to automatic pixel-level crack detection and quantification of asphalt pavement[J]. Automation in Construction, 2020, 114: 103176.
[18]WANG H, WANG Q, ZHAI J, et al. Design of fast acquisition system and analysis of geometric feature for highway tunnel lining cracks based on machine vision[J]. Applied Sciences, 2022, 12: 2516.
[19]CHEN W, HE Z, ZHANG J. Online monitoring of crack dynamic development using attention-based deep networks[J]. Automation in Construction, 2023, 154: 105022.
[20]JANG K, JUNG H, AN Y K. Automated bridge crack evaluation through deep super resolution network-based hybrid image matching[J]. Automation in Construction, 2022, 137: 104229.
[21]ZHOU Z, ZHANG J, GONG C, et al. Automatic tunnel lining crack detection via deep learning with generative adversarial network-based data augmentation[J]. Underground Space, 2023, 9: 140-154.
[22]ALIPOUR M, HARRIS D K, MILLER G R. Robust pixel-level crack detection using deep fully convolutional neural networks[J]. Journal of Computing in Civil Engineering, 2019, 33: 04019040.
[23]WANG C, LIU H, AN X, et al. DCNCrack: Pavement crack segmentation based on large-scaled deformable convolutional network[J]. Journal of Computing in Civil Engineering, 2025, 39: 04025009.
[24]LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, MA, USA, 2015: 3431-3440.
[25]RONNEBERGER O, FISCHER P, BROX T. U-Net: Convolutional networks for biomedical image segmentation[C]//18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany, 2015: 234-241.
[26]CHEN L C, PAPANDREOU G, KOKKINOS I, et al. Semantic image segmentation with deep convolutional nets and fully connected CRFs[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 40(4): 834-848.
[27]CHEN L C, PAPANDREOU G, SCHROFF F, et al. Rethinking atrous convolution for semantic image segmentation[EB/OL]. (2017-12-05)[2025-07-01]. https: //arxiv. org/pdf/1706. 05587.
[28]CHEN L C, ZHU Y, PAPANDREOU G, et al. Encoder-decoder with atrous separable convolution for semantic segmentation[C]//15th European Conference on Computer Vision. Munich, Germany, 2018: 833-851.
[29]ZHAO H, SHI J, QI X, et al. Pyramid scene parsing network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017: 2881-2890.
[30]XIE E, WANG W, YU Z, et al. SegFormer: Simple and efficient design for semantic segmentation with transformers[EB/OL]. (2021-10-28)[2025-07-01]. https: //arxiv. org/pdf/2105. 15203.
[31]ZHANG A, WANG K C P, FEI Y, et al. Deep learning-based fully automated pavement crack detection on 3D asphalt surfaces with an improved CrackNet[J]. Journal of Computing in Civil Engineering, 2018, 32: 04018041.
[32]REN Y, HUANG J, HONG Z, et al. Image-based concrete crack detection in tunnels using deep fully convolutional networks[J]. Construction and Building Materials, 2020, 234: 117367.
[33]O’BRIEN D O, OSBORNE J A, PEREZ-DUENAS E, et al. Automated crack classification for the CERN underground tunnel infrastructure using deep learning[J]. Tunnelling and Underground Space Technology, 2023, 131: 104668.
[34]LI G, MA B, HE S, et al. Automatic tunnel crack detection based on U-Net and a convolutional neural network with alternately updated clique[J]. Sensors, 2020, 20: 717.
[35]DANG L M, WANG H, LI Y, et al. Automatic tunnel lining crack evaluation and measurement using deep learning[J]. Tunnelling and Underground Space Technology, 2022, 124: 104472.
[36]ZHANG S L. Research on health diagnosis and technical condition evaluation of tunnel lining structures[D]. Beijing: Beijing Jiaotong University, 2012.
[37]ZHAO S, ZHANG D, XUE Y, et al. A deep learning-based approach for refined crack evaluation from shield tunnel lining images[J]. Automation in Construction, 2021, 132: 103934.
[38]OUYANG A, DI MURRO V, CULL M, et al. Automated pixel-level crack monitoring system for large-scale underground infrastructure: A case study at CERN[J]. Tunnelling and Underground Space Technology, 2023, 140: 105310.
[39]JIN Y, HAN D, KO H. TrSeg: Transformer for semantic segmentation[J]. Pattern Recognition Letters, 2021, 148: 29-35.
[40]LUO C, ZHANG J, CHEN X, et al. UCATR: Based on CNN and transformer encoding and cross-attention decoding for lesion segmentation of acute ischemic stroke in non-contrast computed tomography images[C]//2021 43rd Annual International Conference of the IEEE Engineering in Medicine & Biology Society. Mexico City, Mexico, 2021: 3565-3568.
[41]SUN C, SHRIVASTAVA A, SINGH S, et al. Revisiting unreasonable effectiveness of data in deep learning era[C]//2017 IEEE International Conference on Computer Vision. Venice, Italy, 2017: 843-852.
[42]LIU Y F, FAN J S, NIE J G, et al. Review and prospect of digital image method for identifying structural surface cracks[J]. China Civil Engineering Journal, 2021, 54: 79-98. (in Chinese)
[43]HSIEH Y A, TSAI Y J. Machine learning for crack detection: Review and model performance comparison[J]. Journal of Computing in Civil Engineering, 2020, 34: 04020038.
[44]KANG D, BENIPAL S S, GOPAL D L, et al. Hybrid pixel-level concrete crack segmentation and quantification across complex backgrounds using deep learning[J]. Automation in Construction, 2020, 118: 103291.
[45]CUI M D, WANG C, CHEN J Q, et al. Real-time detection system for concrete bridge cracks based on ROS and YOLOv3[J]. Journal of Southeast University (Natural Science Edition), 2023, 53: 61-66. (in Chinese)
[46]KIRILLOV A, MINTUN E, RAVI N, et al. Segment anything [C]//2023 IEEE International Conference on Computer Vision (ICCV). Paris, France, 2023: 371.
[47]WANG L L, MENG L, BU B Y, et al. Method for extracting apparent crack features of concrete dams using an improved DeepLabv3+ model[J]. Journal of Southeast University (Natural Science Edition), 2024, 54: 929-936. (in Chinese)
[48]FU H, MENG D, LI W, et al. Bridge crack semantic segmentation based on improved DeepLabv3+[J]. Journal of Marine Science and Engineering, 2021, 9: 671.
[49]TREISMAN A M, GELADE G. A feature-integration theory of attention[J]. Cognitive Psychology, 1980, 12: 97-136.
[50]BAHDANAU D, CHO K, BENGIO Y. Neural machine translation by jointly learning to align and translate[EB/OL]. (2016-05-19)[2025-07-01]. https: //arxiv. org/pdf/1409. 0473.
[51]GUO M H, XU T X, LIU J J, et al. Attention mechanisms in computer vision: A survey[J]. Computational Visual Media, 2022, 8: 331-368.
[52]HU J, SHEN L, ALBANIE S, et al. Squeeze-and-excitation networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42: 2011-2023.
[53]WANG Q, WU B, ZHU P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Seattle, WA, USA, 2020: 11534-11545.
[54]WOO S, PARK J, LEE J Y, et al. CBAM: Convolutional block attention module[C]//15th European Conference on Computer Vision. Munich, Germany, 2018: 3-19.
[55]YANG Q L, LI Z Y, ZHANG B. SA-Net: Shuffle attention for deep convolutional neural networks[C]//2021 IEEE International Conference on Acoustics, Speech and Signal Processing. Toronto, ON, Canada, 2021: 1185-1189.
[56]LI X, WANG W, HU X, et al. Selective kernel networks[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA, 2019: 510-519.
[57]SHU J P, LI S H, YANG H, et al. Ultrasonic full-focus imaging method for internal crack arrays in reinforced concrete beams based on deep learning[J]. Journal of Southeast University (English Edition), 2025, 41(4): 412-421.
[58]ZHOU Q, QU Z, LI Y X, et al. Tunnel crack detection with linear seam based on mixed attention and multiscale feature fusion[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 1-11.
[59]MIAO X, WANG J, WANG Z, et al. Automatic recognition of highway tunnel defects based on an improved U-Net model[J]. IEEE Sensors Journal, 2019, 19: 11413-11423.
[60]HUANG G, LIU Z, VAN DER MAATEN L, et al. Densely connected convolutional networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017: 4700-4708.
[61]CHOLLET F. Xception: Deep learning with depthwise separable convolutions[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA, 2017: 1251-1258.
[62]HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA, 2016: 770-778.
[63]CHEN G, LI C, WEI W, et al. Fully convolutional neural network with augmented atrous spatial pyramid pool and fully connected fusion path for high resolution remote sensing image segmentation[J]. Applied Sciences, 2019, 9: 1816.
[64]ZHANG H, WU C, ZHANG Z, et al. ResNeSt: Split-attention networks[C]//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops. New Orleans, LA, USA, 2022: 2735-2745.
[65]Ministry of Transport of the People’s Republic of China. Technical specifications for maintenance of highway tunnels: JTG H12—2015[S]. Beijing: China Communications Press, 2015. (in Chinese)
[66]ZHANG T Y, SUEN C Y. A fast parallel algorithm for thinning digital patterns[J]. Communications of the ACM, 1984, 27: 236-239.
[67]LI B L, NI H Q, SUI G Y. Design of an axial dimension measurement system for corrugated compensators based on HALCON[J]. Pipeline Technology and Equipment, 2023: 48-51. (in Chinese)
[68]LIU Y F. Multi-scale structural damage identification based on model updating and image processing[D]. Beijing: Tsinghua University, 2016. (in Chinese)
[69]SOKOLOVA M, LAPALME G. A systematic analysis of performance measures for classification tasks[J]. Information Processing & Management, 2009, 45: 427-437.
[70]GARCIA-GARCIA A, ORTS-ESCALANO S, OPREA S, et al. A review on deep learning techniques applied to semantic segmentation[EB/OL]. (2017-04-22)[2025-07-01]. https: //arxiv. org/pdf/1704. 06857.
[71]SHI Y, CUI L, QI Z, et al. Automatic road crack detection using random structured forests[J]. IEEE Transactions on Intelligent Transportation Systems, 2016, 17: 3434-3445.
[72]ZHANG Z. Flexible camera calibration by viewing a plane from unknown orientations[C]//1999 Seventh IEEE International Conference on Computer Vision. Kerkyra, Greece, 1999: 666-673.
[73]JIA J W, NI Y H, MAO J X, et al. Recognition of geometric parameters of prefabricated box girder sections of bridges based on deep learning and computer vision[J]. Journal of Southeast University (English Edition), 2025, 41(3): 278-285.

Memo

Memo:
Received: 2025-07-10; Revised: 2026-04-20.
Biography: WANG Meng (1985—), female, doctor, professor, wangmeng@bjtu.edu.cn.
Foundation items: Beijing Natural Science Foundation(No.26JL009), the National Natural Science Foundation of China(No.52478491).
Citation: WANG Meng, YANG Yanze, LIU Cheng, et al. An automatic system for detecting and analyzing tunnel lining cracks based on deep learning[J]. Journal of Southeast University (English Edition), 2026, 42(3): 337-350. DOI: 10. 3969/j. issn. 1003-7985. 2026. 03. 007.
Last Update: 2026-09-20