Hybrid-Supervised-Learning-Based Automatic Image Segmentation for Water Leakage in Subway Tunnels

Quickly and accurately identifying water leakage is one of the important components of the health monitoring of subway tunnels. A mobile vision measurement system consisting of several high-resolution, industrial, charge-coupled device (CCD) cameras is placed on trains to implement structural health monitoring in tunnels. Through the image processing technology proposed in this paper, water leakage areas in subway tunnels can be found and repaired in real time. A lightweight automatic segmentation approach to water leakage using hybrid-supervised-deep-learning technology is proposed. This approach consists of the weakly supervised learning Water Leakage-CAM and fully supervised learning WRDeepLabV3+. The Water Leakage-CAM is used for the automatic labeling of data. The WRDeepLabV3+ is used for the accurate identification of water leakage areas in subway tunnels. Compared with other end-to-end semantic segmentation networks, the hybrid-supervised learning approach can more completely segment the water leakage region when dealing with water leakage in complex environments. The hybrid-supervised-deep-learning approach proposed in this paper achieves the highest MIoU of 82.8% on the experimental dataset, which is 6.4% higher than the second. The efficiency is also 25% higher than the second and significantly outperforms other end-to-end deep learning approaches.

[1]  Yan Liu,et al.  Prediction of tunnelling induced ground movement in clay using principle of minimum total potential energy , 2023, Tunnelling and Underground Space Technology.

[2]  Han Zhang,et al.  OTSU Multi-Threshold Image Segmentation Based on Improved Particle Swarm Algorithm , 2022, Applied Sciences.

[3]  Yanyan Wu,et al.  The Algorithm of Watershed Color Image Segmentation Based on Morphological Gradient , 2022, Sensors.

[4]  Katherine van Lopik,et al.  A Survey of Indoor Location Technologies, Techniques and Applications in Industry , 2022, Internet Things.

[5]  B. Leng,et al.  Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels , 2022, Automation in Construction.

[6]  Qianbing Zhang,et al.  Experimental investigation of mechanical characteristics for linings of twins tunnels with asymmetric cross-section , 2022, Tunnelling and Underground Space Technology.

[7]  Hyeonjoon Moon,et al.  Pixel-level tunnel crack segmentation using a weakly supervised annotation approach , 2021, Comput. Ind..

[8]  Hyeonjoon Moon,et al.  Deep learning-based sewer defect classification for highly imbalanced dataset , 2021, Comput. Ind. Eng..

[9]  Licheng Jiao,et al.  Adaptive Affinity Loss and Erroneous Pseudo-Label Refinement for Weakly Supervised Semantic Segmentation , 2021, ACM Multimedia.

[10]  Danijel Skocaj,et al.  Mixed supervision for surface-defect detection: from weakly to fully supervised learning , 2021, Comput. Ind..

[11]  Xing Wang,et al.  Experimental Study on Mesoscopic Shear Behavior of Calcareous Sand Material with Digital Imaging Approach , 2020 .

[12]  Xiaoling Wang,et al.  Patch-based weakly supervised semantic segmentation network for crack detection , 2020 .

[13]  Sen Zhang,et al.  Deep learning-based automatic recognition of water leakage area in shield tunnel lining , 2020 .

[14]  Xing Wang,et al.  Shape Characteristics of Coral Sand from the South China Sea , 2020 .

[15]  Leijin Xiong,et al.  Water leakage image recognition of shield tunnel via learning deep feature representation , 2020, J. Vis. Commun. Image Represent..

[16]  Qiaosong Wang,et al.  Weakly-Supervised Semantic Segmentation via Sub-Category Exploration , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[17]  Stefan Roth,et al.  Single-Stage Semantic Segmentation From Image Labels , 2020, 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Jinbo Song,et al.  Weakly supervised network based intelligent identification of cracks in asphalt concrete bridge deck , 2020, Alexandria Engineering Journal.

[19]  Hao Xu,et al.  A high-precision calibration approach for Camera-IMU pose parameters with adaptive constraints of multiple error equations , 2020 .

[20]  Wei Lu,et al.  Image-based concrete crack detection in tunnels using deep fully convolutional networks , 2020 .

[21]  Wei Wang,et al.  Computer vision-based concrete crack detection using U-net fully convolutional networks , 2019, Automation in Construction.

[22]  Pengfei Chen,et al.  Rethinking the Usage of Batch Normalization and Dropout in the Training of Deep Neural Networks , 2019, ArXiv.

[23]  Min Yang,et al.  Real-Time Tunnel Crack Analysis System via Deep Learning , 2019, IEEE Access.

[24]  Cao Vu Dung,et al.  Autonomous concrete crack detection using deep fully convolutional neural network , 2019, Automation in Construction.

[25]  Ting Zhao,et al.  Pyramid Feature Attention Network for Saliency Detection , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Hyoungkwan Kim,et al.  Encoder–decoder network for pixel‐level road crack detection in black‐box images , 2019, Comput. Aided Civ. Infrastructure Eng..

[27]  Dong Liu,et al.  Deep High-Resolution Representation Learning for Human Pose Estimation , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[28]  Hui-jie Zhou,et al.  Screening of Fungi for Potential Application of Self-Healing Concrete , 2019, Scientific Reports.

[29]  Xuefeng Zhao,et al.  Automatic pixel‐level multiple damage detection of concrete structure using fully convolutional network , 2019, Comput. Aided Civ. Infrastructure Eng..

[30]  Xiaochun Luo,et al.  Automatic Pixel‐Level Crack Detection and Measurement Using Fully Convolutional Network , 2018, Comput. Aided Civ. Infrastructure Eng..

[31]  Yang Liu,et al.  Automated Pixel‐Level Pavement Crack Detection on 3D Asphalt Surfaces with a Recurrent Neural Network , 2018, Comput. Aided Civ. Infrastructure Eng..

[32]  Yicheng Li,et al.  A Fast Detection Method via Region‐Based Fully Convolutional Neural Networks for Shield Tunnel Lining Defects , 2018, Comput. Aided Civ. Infrastructure Eng..

[33]  Dongming Zhang,et al.  Deep learning based image recognition for crack and leakage defects of metro shield tunnel , 2018, Tunnelling and Underground Space Technology.

[34]  Tarek Zayed,et al.  Computer Vision-Based Model for Moisture Marks Detection and Recognition in Subway Networks , 2018, J. Comput. Civ. Eng..

[35]  George Papandreou,et al.  Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation , 2018, ECCV.

[36]  Kaiming He,et al.  Focal Loss for Dense Object Detection , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[37]  Sinisa Todorovic,et al.  Combining Bottom-Up, Top-Down, and Smoothness Cues for Weakly Supervised Image Segmentation , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[38]  José García Rodríguez,et al.  A Review on Deep Learning Techniques Applied to Semantic Segmentation , 2017, ArXiv.

[39]  Xiangyu Zhang,et al.  Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[40]  Xiaogang Wang,et al.  Pyramid Scene Parsing Network , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[41]  Yi Li,et al.  R-FCN: Object Detection via Region-based Fully Convolutional Networks , 2016, NIPS.

[42]  Thomas Brox,et al.  U-Net: Convolutional Networks for Biomedical Image Segmentation , 2015, MICCAI.

[43]  George Papandreou,et al.  Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[44]  Branko Glisic,et al.  Crack detection and characterization techniques—An overview , 2014 .

[45]  Hongwei Huang,et al.  Deep learning–based image instance segmentation for moisture marks of shield tunnel lining , 2020 .

[46]  Diganta Misra.  Mish: A Self Regularized Non-Monotonic Activation Function , 2020, BMVC.

[47]  D. Vermeij.  Flood risk reduction interventions for the New York City subway system: A research on the impact of storm surge and sea level rise on the safety against flooding in urban delta's , 2016 .