Location and rapid detection method of water leakage in subway tunnels based on mobile laser scanning

doi:10.11947/j.AGCS.2024.20230438

Abstract

Abstract:

Water leakage is one of the most important diseases in subway tunnels and can also cause other structural diseases. It is of great significance to carry out research on detection methods of water leakage diseases in subway tunnels. This paper focuses on the problem of water leakage in subway tunnels and proposes a water leakage location and detection method based on mobile laser scanning point cloud data. First, combined with the mobile laser scanning detection method, research on the precise positioning method of tunnels was carried out. Then, the YOLOv7 model was improved, and the ConvNeXt network and CBAM module were introduced to enable the model to better capture multi-scale, multi-abstraction level features and enhance attention to the key features of seepage water. The GIoU Loss function was used to make the model can better handle incomplete leaky water boxes. It uses the Soft-NMS weighted average method when predicting to retain more bounding boxes, thereby improving detection accuracy. The efficiency and robustness of the method in this paper are verified by combining the shield method and mine method tunnel leakage data sets constructed with laser scanning data obtained in Chongqing metro. The ablation test shows that compared with the baseline model, the method in this paper has achieved significant performance improvements on different data sets. In the shield method data set, the precision rate P is increased by 8.1%, and the recall rate R is increased by 4%. In the mining law data set, the precision rate P increased by 8.6%, and the recall rate R increased by 6.8%. At the same time, compared with the mainstream target detection algorithms faster RCNN (Swin), faster RCNN (ConvNeXt), and YOLOv8, this method shows advantages in both accuracy and speed. Finally, this paper shows the location and detection results of water leakage in some tunnels to verify the practicability of this method.

Key words: laser point cloud, tunnel localization, shield method, mine method, leakage detection, attention mechanism

CLC Number:

P258

Changqi JI, Zhaojie GUO, Haili SUN, Ruofei ZHONG. Location and rapid detection method of water leakage in subway tunnels based on mobile laser scanning[J]. Acta Geodaetica et Cartographica Sinica, 2024, 53(6): 1236-1250.

Figures/Tables 18

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Tab.1

Fig.7

Fig.8

Tab.2

Tab.3

Tab.4

Tab.5

Fig.9

Tab.6

Fig.10

Tab.7

Tab.8

References 45

[1]	韩宝明, 余怡然, 习喆, 等. 城市轨道交通2023年度统计和分析报告[R].北京: 中国城市轨道交通协会, 2024.
	HAN Baoming, YU Yiran, XI Zhe, et al. Urban rail transit 2023 annual statistics and analysis report [R].Beijing: China Association of Metros, 2024.
[2]	邓普. 铁路车载探地雷达检测隧道渗漏水的研究[D]. 成都: 西南交通大学, 2015.
	DENG Pu. Research on detection of railway tunnel seepage with train-mounted GPR[D]. Chengdu: Southwest Jiaotong University, 2015.
[3]	陈军, 刘万增, 武昊, 等. 智能化测绘的基本问题与发展方向[J]. 测绘学报, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
	CHEN Jun, LIU Wanzeng, WU Hao, et al. Smart surveying and mapping: fundamental issues and research agenda[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):995-1005.DOI:10.11947/j.AGCS.2021.20210235.
[4]	郑晔, 郭仁忠, 马丁, 等. 面向地理路网的交通信号智能协同控制方法[J]. 测绘学报, 2021, 50(9):1203-1210. DOI:10.11947/j.AGCS.2021.20210191.
	ZHENG Ye, GUO Renzhong, MA Ding, et al. Multi-agent cooperative control for traffic signal on geographic road network[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(9):1203-1210. DOI:10.11947/j.AGCS.2021.20210191.
[5]	杨必胜, 韩旭, 董震. 适用于城市场景大规模点云语义标识的深度学习网络[J]. 测绘学报, 2021, 50(8):1059-1067.DOI:10.11947/j.AGCS.2021.20210093.
	YANG Bisheng, HAN Xu, DONG Zhen. A deep learning network for semantic labeling of large-scale urban point clouds[J]. Acta Geodaetica et Cartographica Sinica, 2021, 50(8):1059-1067.DOI:10.11947/j.AGCS.2021.20210093.
[6]	李俊良. 地铁盾构隧道渗漏水病害点云自动识别研究[D]. 北京: 北京交通大学, 2021.
	LI Junliang. Automatic recognition of point cloud of water leakage in subway shield tunnel[D]. Beijing: Beijing Jiaotong University, 2021.
[7]	DU Liming, ZHONG Ruofei, SUN Haili, et al. Dislocation detection of shield tunnel based on dense cross-sectional point clouds[J]. IEEE Transactions on Intelligent Transportation Systems, 2022, 23(11):22227-22243.
[8]	阮东旭, 姚连璧, 许正文, 等. 基于轨道移动激光扫描的圆形隧道正射影像纠正算法[J]. 工程勘察, 2021, 49(1):41-46.
	RUAN Dongxu, YAO Lianbi, XU Zhengwen, et al. An orthoimage correction algorithm for circular tunnel based on track moving laser scanning[J]. Geotechnical Investigation & Surveying, 2021, 49(1):41-46.
[9]	UKAI M, NAGAMINE N. A high-performance inspection system of tunnel wall deformation using continuous scan image[EB/OL]. [2023-10-02]. https://documents.pub/document/a-high-performance-inspection-system-of-tunnel-wall-high-performance-inspection.html?page=1.
[10]	刘学增, 桑运龙, 苏云帆. 基于数字图像处理的隧道渗漏水病害检测技术[J]. 岩石力学与工程学报, 2012, 31(S2):3779-3786.
	LIU Xuezeng, SANG Yunlong, SU Yunfan. Detection technology of tunnel leakage disaster based on digital image processing[J]. Chinese Journal of Rock Mechanics and Engineering, 2012, 31(S2):3779-3786.
[11]	杨国田, 王云龙, 宋森平. 基于PSO的最佳熵阈值红外图像隧道渗漏水提取[J]. 计算机仿真, 2022, 39(7):233-237.
	YANG Guotian, WANG Yunlong, SONG Senping. Tunnel leakage water extraction from infrared image with optimal entropic thresholding based on particle swarm[J]. Computer Simulation, 2022, 39(7):233-237.
[12]	吴杭彬, 于鹏飞, 刘春, 等. 基于红外热成像的地铁隧道渗漏水提取[J]. 工程勘察, 2019, 47(2):44-49, 61.
	WU Hangbin, YU Pengfei, LIU Chun, et al. Extraction of metro tunnel seepage based on infrared thermal imaging[J]. Geotechnical Investigation & Surveying, 2019, 47(2):44-49, 61.
[13]	HUANG Hongwei, SUN Yan, XUE Yadong, et al. Inspection equipment study for subway tunnel defects by grey-scale image processing[J]. Advanced Engineering Informatics, 2017, 32:188-201.
[14]	OTSU N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1):62-66.
[15]	XU Teng, XU Lijun, LI Xiaolu, et al. Detection of water leakage in underground tunnels using corrected intensity data and 3D point cloud of terrestrial laser scanning[J]. IEEE Access, 2018, 6:32471-32480.
[16]	吴昌睿, 黄宏伟. 地铁隧道渗漏水的激光扫描检测方法及应用[J]. 自然灾害学报, 2018, 27(4):59-66.
	WU Changrui, HUANG Hongwei. Laser scanning inspection method and application for metro tunnel leakage[J]. Journal of Natural Disasters, 2018, 27(4):59-66.
[17]	HUANG Hongwei, LI Qingtong, ZHANG Dongming. Deep learning based image recognition for crack and leakage defects of metro shield tunnel[J]. Tunnelling and Underground Space Technology, 2018, 77:166-176.
[18]	LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]//Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston: IEEE, 2015: 3431-3440.
[19]	ZHAO Shuai, ZHANG Dongming, HUANG Hongwei. Deep learning-based image instance segmentation for moisture marks of shield tunnel lining[J]. Tunnelling and Underground Space Technology, 2020, 95:103156.
[20]	HE Kaiming, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//Proceedings of 2017 IEEE International Conference on Computer Vision. Venic: IEEE, 2017: 2980-2988.
[21]	XUE Yadong, CAI Xinyuan, SHADABFAR M, et al. Deep learning-based automatic recognition of water leakage area in shield tunnel lining[J]. Tunnelling and Underground Space Technology, 2020, 104:103524.
[22]	CAI Zhaowei, VASCONCELOS N. Cascade R-CNN: high quality object detection and instance segmentation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 43(5):1483-1498.
[23]	LIU Shuang, SUN Haili, ZHANG Zhenxin, et al. A multiscale deep feature for the instance segmentation of water leakages in tunnel using MLS point cloud intensity images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60:1-16.
[24]	MAN Ke, LIU Ruilin, LIU Xiaoli, et al. Water leakage and crack identification in tunnels based on transfer-learning and convolutional neural networks[J]. Water, 2022, 14(9):1462.
[25]	GENG Peng, JIA Mengye, REN Xiaoxia. Tunnel lining water leakage image Segmentation based on improved BlendMask[J]. Structural Health Monitoring, 2023, 22(2):865-878.
[26]	LI Mengjiao, WANG Hao, ZHANG Shumei, et al. Subway water leakage detection based on improved deeplabV3+[C]//Proceedings of 2022 International Conference on Computer Systems. Qingdao: IEEE, 2022.
[27]	HAN Lei, CHEN Jiangfan, LI Haobo, et al. Multispectral water leakage detection based on a one-stage anchor-free modality fusion network for metro tunnels[J]. Automation in Construction, 2022, 140:104345.
[28]	CHEN Qian, XIONG Chuanguo, LÜ Weishan, et al. Convolutional neural network with attention module for identification of tunnel seepage[J]. Transportation Research Record: Journal of the Transportation Research Board, 2022, 2676(11):112-123.
[29]	GENG Peng, TAN Ziye, LUO Jun, et al. ACPA-Net: atrous channel pyramid attention network for segmentation of leakage in rail tunnel linings[J]. Electronics, 2023, 12(2):255.
[30]	周宝定, 谢沛瑶, 郭文浩, 等. 基于激光点云灰度图像的隧道渗水病害检测[J]. 测绘通报, 2023 (8):34-39.
	ZHOU Baoding, XIE Peiyao, GUO Wenhao, et al. Detection of tunnel leakage based on gray scale image of laser point cloud[J]. Bulletin of Surveying and Mapping, 2023 (8):34-39.
[31]	FENG Shijin, FENG Yong, ZHANG Xiaolei, et al. Deep learning with visual explanations for leakage defect segmentation of metro shield tunnel[J]. Tunnelling and Underground Space Technology, 2023, 136:105107.
[32]	GUO Zhaojie, WEI Jifan, SUN Haili, et al. Enhanced water leakage detection in shield tunnels based on laser scanning intensity images using RDES-Net[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17:5680-5690.
[33]	WANG Chenyao, BOCHKOVSKIY A, LIAO Hongyuan. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[EB/OL]. [2023-10-02]. https://arxiv.org/pdf/2207.02696.
[34]	JI Changqi, SUN Haili, ZHONG Ruofei, et al. Precise positioning method of moving laser point cloud in shield tunnel based on bolt hole extraction[J]. Remote Sensing, 2022, 14(19):4791.
[35]	ZHANG Wuming, QI Jianbo, WAN Peng, et al. An easy-to-use airborne LiDAR data filtering method based on cloth simulation[J]. Remote Sensing, 2016, 8(6):501.
[36]	高智梅, 王竞雪, 沈昭宇. 机载LiDAR建筑物点云渐进提取算法[J]. 测绘通报, 2021 (8):7-13.
	GAO Zhimei, WANG Jingxue, SHEN Zhaoyu. Aerial LiDAR building point-cloud progressive extraction algorithm[J]. Bulletin of Surveying and Mapping, 2021 (8):7-13.
[37]	JI Changqi, SUN Haili, ZHONG Ruofei, et al. Deformation detection of mining tunnel based on automatic target recognition[J]. Remote Sensing, 2023, 15(2):307.
[38]	LIU Zhuang, MAO Hanzi, WU Chaoyuan, et al. A ConvNet for the 2020s[C]//Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orleans: IEEE, 2022: 11966-11976.
[39]	WOO S, PARK J, LEE J Y, et al. CBAM: convolutional block attention module[C]//Proceedings of 2018 European Conference on Computer Vision. Munich: IEEE, 2018: 3-19.
[40]	REZATOFIGHI H, TSOI N, GWAK J, et al. Generalized intersection over union: a metric and a loss for bounding box regression[C]//Proceedings of 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach: IEEE, 2019: 658-666.
[41]	ZHENG Zhaohui, WANG Ping, LIU Wei, et al. Distance-IoU loss: faster and better learning for bounding box regression[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7):12993-13000.
[42]	BODLA N, SINGH B, CHELLAPPA R, et al. Soft-NMS: improving object detection with one line of code[C]//Proceedings of 2017 IEEE International Conference on Computer Visionand Pattern Recognition. Venice: IEEE, 2017: 5562-5570.
[43]	SUN Haili, XU Zhengwen, YAO Lianbi, et al. Tunnel monitoring and measuring system using mobile laser scanning: design and deployment[J]. Remote Sensing, 2020, 12(4):730.
[44]	SUN Haili, LIU Shuang, ZHONG Ruofei, et al. Cross-section deformation analysis and visualization of shield tunnel based on mobile tunnel monitoring system[J]. Sensors, 2020, 20(4):1006.
[45]	YUE Zeyu, SUN Haili, ZHONG Ruofei, et al. Measurement of tunnel clearance convergence using mobile laser detection technology[J]. Canadian Journal of Remote Sensing, 2021, 47(1):100-118.

数据集名称	训练集	测试集	总数
盾构隧道数据集	258	64	322
盾构隧道扩充数据集	1290	320	1610
矿山法隧道数据集	255	63	318
矿山法隧道扩充数据集	1275	315	1580

数据集	损失函数	总标记	TP	FP	FN	P	R	m AP0.5	F₁值
盾构法	CIoU	375	303	80	72	0.791	0.808	0.807	0.799
	DIoU	375	283	49	92	0.852	0.755	0.802	0.801
	GIoU	375	312	83	63	0.790	0.832	0.825	0.810
矿山法	CIoU	398	302	74	96	0.803	0.759	0.815	0.780
	DIoU	398	300	97	98	0.756	0.754	0.802	0.755
	GIoU	398	323	71	75	0.820	0.812	0.848	0.816

试验组	CNEB	CBAM	GIoU	soft NMS
G1	×	×	×	×
G2	√	×	×	×
G3	×	√	×	×
G4	×	×	√	×
G5	×	×	×	√
G6	√	√	×	×
G7	√	√	√	×
G8	√	√	√	√

试验组	总标记	TP	FP	FN	P	R	m AP0.5	F₁值
G1	375	303	80	72	0.791	0.808	0.807	0.799
G2	375	316	103	59	0.753	0.843	0.82	0.795
G3	375	293	56	82	0.84	0.781	0.837	0.809
G4	375	312	83	63	0.790	0.832	0.825	0.810
G5	375	304	63	71	0.828	0.811	0.799	0.819
G6	375	319	73	56	0.814	0.851	0.852	0.832
G7	375	318	53	57	0.857	0.848	0.868	0.853
G8	375	320	47	55	0.872	0.853	0.865	0.862

试验组	总标记	TP	FP	FN	P	R	m AP0.5	F₁值
G1	398	302	74	96	0.803	0.759	0.815	0.78
G2	398	329	91	69	0.783	0.827	0.831	0.804
G3	398	316	67	82	0.825	0.794	0.886	0.809
G4	398	323	71	75	0.820	0.812	0.848	0.816
G5	398	323	62	75	0.839	0.812	0.867	0.825
G6	398	326	46	72	0.876	0.819	0.879	0.847
G7	398	328	55	70	0.856	0.824	0.878	0.840
G8	398	329	41	69	0.889	0.827	0.871	0.857