Algorithms of leakage disease images recognition in subway tunnel
FANG Enquan1, WANG Yaodong2,3*, LI Xingyan2, MA Nongjie2
1.National Engineering Research Center of Guangzhou Metro Group Co., Ltd., Guangzhou 510355, Guangdong, China; 2. School of Mechanical and Electronic Control Engineering, Beijing Jiaotong University, Beijing 100044, China; 3. Frontiers Science Center for Smart High-speed Railway System, Beijing Jiaotong University, Beijing 100044, China
Abstract: Aiming at low accuracy of recognition in complex leakage images of subway tunnels, this paper studied the application of image recognition algorithms in tunnel water-leakage disease, was using two kinds of neural networks: U-Net and PSP-Net. Based on the subway tunnel images, tunnel leakage disease sample data set was constructed, where 5000 subway tunnel disease image data and 4000 labeled images were included. This data set could be used for deep neural convolution network training. U-Net and PSP-Net deep learning frameworks were established, and the neural networks were trained by self-made data set. The accuracy of the prediction results from U-Net and PSP-Net was evaluated, and the performance of the two networks in the application of leakage disease identification was compared. U-Net had stronger coverage for the disease and quick detection, while PSP-net had higher accuracy fit to fine detection.
方恩权, 王耀东, 李星言, 马农杰. 地铁盾构隧道渗漏水病害图像识别算法[J]. 隧道与地下工程灾害防治, 2022, 4(4): 28-33.
FANG Enquan, WANG Yaodong, LI Xingyan, MA Nongjie. Algorithms of leakage disease images recognition in subway tunnel. Hazard Control in Tunnelling and Underground Engineering, 2022, 4(4): 28-33.
[1] 李翔宇,李新源,李明宇, 等.地铁盾构隧道渗漏水的产生原因及分布规律[J].建筑科学,2020,36(增刊1): 233-238. LI Xiangyu, LI Xinyuan, LI Mingyu, et al. The cause and distribution of water leakage in metro shield tunnel[J]. Building Science, 2020, 36(Suppl.1): 233-238. [2] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. Imagenet classification with deep convolutional neural networks[J].Communications of the ACM,2017, 60(6): 84-90. [3] HUANG H W, LI Q T, ZHANG D M. Deep learning based image recognition for crack and leakage defects of metro shield tunnel[J]. Tunnelling and Underground Space Technology, 2018, 77: 166-176. [4] 姚旭朋.地铁隧道渗漏水病害快速检测及图像处理技术[J]. 城市轨道交通研究, 2017, 20(12): 46-49. YAO Xupeng. Rapid inspection of water leakage defect in metro tunnel and image treatment technology[J]. Urban Mass Transit, 2017, 20(12): 46-49. [5] 汤一平,胡克钢,袁公萍.基于全景图像CNN的隧道病害自动识别方法[J].计算机科学, 2017, 44(增刊2): 207-211. TANG Yiping, HU Kegang, YUAN Gongping. Automatic recognition method of tunnel disease based on convolutional neural network for panoramic images[J]. Computer Science, 2017, 44(Suppl.2): 207-211. [6] KAKANTASIS K, PROTOPAPADAKIS E, DOULAMIS A, et al. Deep convolutional neural networks for efficient vision based tunnel inspection[C] //2015 IEEE International Conference on Intelligent Computer Communication and Processing. Cluj-Napoca, Romania:IEEE, 2015:335-342. [7] RONNEBERGER O, FISCHER P, BROX T. U-Net: convolutional networks for biomedical image segmentation[C] //Proceedings of the 18th International Conference on Medical Image Computing and Computer-Assisted Intervention. Munich, Germany:Springer Verlag, 2015:234-241. [8] SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition[J]. Computer Science, 2014:334-341. [9] ZHAO H S, SHI J P, QI X J, et al. Pyramid scene parsing network[C] //Proceedings of the Conference on Computer Vision and Pattern Recognition. Honolulu, USA:Institute of Electrical and Electronics Engineers Incorporated, 2017: 6230-6239. [10] SANDLER M, HOWARD A, ZHU M L, et al. MobileNetV2: inverted residuals and linear bottlenecks[C] //2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City, USA:IEEE, 2018: 4510-4520.
2022, Vol. 4 
