JWAJournal of World Architecture2208-34802208-3499Bio-Byword Scientific Publishing Pty. Ltd.10.26689/jwa.v8i1.6203ArticleAutomatic Sensing and Detection for Subway Tunnel Pathologieshttps://artdesignp.com/journal/JWA/8/1/10.26689/jwa.v8i1.6203WangXingyu,ZhuZhengkun2024812024-02-26Subway tunnels often suffer from surface pathologies such as cracks, corrosion, fractures, peeling, water and sand infiltration, and sudden hazards caused by foreign object intrusions. Installing a mobile visual pathology sensing system at the front end of operating trains is a critical measure to ensure subway safety. Taking leakage as the typical pathology, a tunnel pathology automatic visual detection method based on Deeplabv3+ (ASTPDS) was proposed to achieve automatic and high-precision detection and pixel-level morphology extraction of pathologies. Compared with similar methods, this approach showed significant advantages and achieved a detection accuracy of 93.12%, surpassing FCN and U-Net. Moreover, it also exceeded the recall rates for detecting leaks of FCN and U-Net by 8.33% and 8.19%, respectively.

Hong J, 2023, Overview of the Application of Visual Inspection Technology for Surface Defects of Subway Tunnel. Railway Survey, 49(01): 18–22 + 32. https://www.doi.org/10.19630/j.cnki.tdkc.202201140001

Tian Y, Fan T, Tang C, 2022, Rapid Detection Technology for Surface Leakage of Subway Tunnels. Bulletin of Surveying and Mapping, 2022(09): 29–33. https://www.doi.org/10.13474/j.cnki.11-2246.2022.0259.

Xue Y, Li Y, 2018, A Method of Disease Recognition for Shield Tunnel Lining Based on Deep Learning. Journal of Hunan University. 45(3): 100–109.

Wang X, Wu Y, Cui J, et al., 2020, Shape Characteristics of Coral Sand from the South China Sea. J. Mar. Sci. Eng., 8(10): 803

Shen JH, Wang X, Liu WB, et al., 2020, Experimental Study on Mesoscopic Shear Behavior of Calcareous Sand Material with Digital Imaging Approach. Adv. Civ. Eng., 2020: 8881264.

Ren YP, Huang JS, Hong ZY, et al., 2020, Image-Based Concrete Crack Detection in Tunnels Using Deep Fully Convolutional Networks. Constr. Build. Mater., 234: 117367–117379.

Huang HW, Li QT, Zhang DM, 2018, Deep Learning-Based Image Recognition for Crack and Leakage Defects of Metro Shield Tunnel. Tunn. Undergr. Sp. Tech., 77: 166–176.

Garcia-Garcia A, Orts-Escolano S, Oprea S, et al., Review on Deep Learning Techniques Applied to Semantic Segmentation.

Hu M, 2021, Design and Implementation of Crack Detection System for Subway Tunnel Lining based on OpenCV, dissertation, Yangzhou University. https://www.doi.org/10.27441/d.cnki.gyzdu.2021.001467

Tian Y, Fan T, Tang C, 2022, Rapid Detection Technology for Surface Leakage of Subway Tunnel. Surveying and Mapping Bulletin, 546(9): 29–33. https://www.doi.org/10.13474/j.cnki.11-2246.2022.0259

Jiang S, 2022, Image Detection of Crack Disease in Subway Tunnel based on Deep Learning, dissertation, East China Normal University. https://www.doi.org/10.27149/d.cnki.ghdsu.2022.004606

Bai B, 2019, Research on Image Recognition Algorithm of Complex Crack Disease in Subway Tunnel, dissertation, Beijing Jiaotong University.

Zhao S, Zhang D, Huang H, 2020, Deep Learning-Based Image Instance Segmentation for Moisture Marks of Shield Tunnel Lining. Tunnelling and Underground Space Technology, 95: 103–109.

Zhu J, Zheng A, Lei Z, et al., 2023, Detection Method for Apparent Defects of Subway Tunnel Ancillary Facilities and Lining Based on Improved YOLOv5. Journal of Railway Science and Engineering, 20(03): 1008–1019. https://www.doi.org/10.19713/j.cnki.43-1423/u.t20220712