基于深度学习的盾构隧道渗漏水病害图像识别

doi:10.13722/j.cnki.jrme.2017.0552

Abstract
Figure/Table
References (0)
Related Citation (15)

Download: PDF (1800 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract With the sharp increasing in the requirements for tunnel maintenance of urban metro，the structural defects of the metro shield tunnels，especially the water leakage，need be inspected fast and accurately. Using the computer vision to inspect the structural defects of shield tunnel is a thriving trend home and abroad during recent years. However，the traditional methods of image recognition on water leakage cannot meet the need in engineering practice. In this paper，a novel method employing the fully convolution network(FCN) based on the deep learning(DL) is proposed to improve the image recognition on water leakage in shield tunnel. The water leakage images are divided into six categories according to the lining surface of shield tunnel and some interference on image recognition. The recognition results，the error rates and the running time from FCN are compared with those from the traditional image recognition methods of Otsu algorithm(OA)，region growing algorithm(RGA) and watershed algorithm(WA). The results show that DL-based image recognition on water leakage effectively avoided the interference from the segment joints，bolt holes，cables，brackets etc.，and has excellent robustness in overcoming the defects shelter from cables.

Key words： tunnelling engineering shield tunnel water leakage deep learning image recognition

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	HUANG Hongwei1
	2
	LI Qingtong1

Cite this article:

HUANG Hongwei1,2,LI Qingtong1. Image recognition for water leakage in shield tunnel based on deep learning[J]. , 2017, 36(12): 2861-2871.

URL:

https://rockmech.whrsm.ac.cn/EN/10.13722/j.cnki.jrme.2017.0552 OR https://rockmech.whrsm.ac.cn/EN/Y2017/V36/I12/2861

[1] 蓝兰. 2020年全国轨道交通运营里程将超8 000公里[J]. 交通建设与管理月刊，2016，(5)：64–73.(LAN Lan. In 2020 national rail transit operation mileage will exceed 8 000 kilometers[J]. Transportation Construction and Management，2016，(5)：64–73.(in Chinese))
[2] 樊佳慧，张琛，卢恺，等. 2015年中国城市轨道交通运营线路统计与分析[J]. 都市快轨交通，2016，29(1)：1–3.(FAN Jiahui，ZHANG Chen，LU Kai，et al. Statistics and analysis of China?s urban rail transit operation in 2015[J]. Urban Rapid Rail Transit，2016，29(1)：1–3.(in Chinese))
[3] 王如路. 上海轨道交通隧道结构安全性分析[J]. 地下工程与隧道，2011，(4)：37–43.(WANG Rulu. Structural safety analysis of Shanghai rail transit tunnel[J]. Underground Engineering and Tunnel，2011，(4)：37–43.(in Chinese))
[4] 胡向东，白楠，李鸿博. 圣彼得堡地铁1号线区间隧道事故分析[J].隧道建设，2008，28(4)：418–422.(HU Xiangdong，BAI Nan，LI Hongbo. Analysis on tunnel accident on Line 1 of Saint Petersburg metro[J]. Tunnel Construction，2008，28(4)：418–422.(in Chinese))
[5] 邵华，黄宏伟，张东明，等. 突发堆载引起软土地铁盾构隧道大变形整治研究[J]. 岩土工程学报，2016，38(6)：1 036–1 043.(SHAO Hua，HUANG Hongwei，ZHANG Dongming，et al. Case study on repair work for excessively deformed shield tunnel under accidental surface surcharge in soft clay[J]. Chinese Journal of Geotechnical Engineering，2016，38(6)：1 036–1 043.(in Chinese))
[6] ASAKURA T，KOJIMA Y. Tunnel maintenance in Japan[J]. Tunnelling and Underground Space Technology，2003，18(2/3)：161–169.
[7] YUAN Y，JIANG X，LIU X. Predictive maintenance of shield tunnels[J]. Tunnelling and Underground Space Technology，2013，38： 69–86.
[8] LEE S Y，LEE S H，SHIN D I，et al. Development of an inspection system for cracks in a concrete tunnel lining[J]. Canadian Journal of Civil Engineering，2007，34(34)：966–975.
[9] MONTERO R，VICTORES J G，MARTINEZ S，et al. Past，present and future of robotic tunnel inspection[J]. Automation in Construction，2015，59：99–112.
[10] 刘学增，叶康. 隧道衬砌裂缝的远距离图像测量技术[J]. 同济大学学报：自然科学版，2012，40(6)：829–836.(LIU Xuezeng，YE Kang. A long-distance image measuring technique for crack on tunnel lining[J]. Journal of Tongji University：Natural Science，2012，40(6)：829–836.(in Chinese))
[11] 王平让，黄宏伟，薛亚东. 基于图像局部网格特征的隧道衬砌裂缝自动识别[J]. 岩石力学与工程学报，2012，31(5)：991–999.(WANG Pingrang，HUANG Hongwei，XUE Yadong. Automatic recognition of cracks in tunnel lining based on characteristics of local grids in images[J]. Chinese Journal of Rock Mechanics and Engineering，2012，31(5)：991–999.(in Chinese))
[12] ZHANG W，ZHANG Z，QI D，et al. Automatic crack detection and classification method for subway tunnel safety monitoring[J]. Sensors，2014，14(10)：19 307–19 328.
[13] AI Q，YUAN Y，BI X. Acquiring sectional profile of metro tunnels using charge-coupled device cameras[J]. Structure and Infrastructure Engineering，2015，12(9)：1 065–1 075.
[14] 王睿，漆泰岳，雷波，等. 隧道衬砌裂缝特征提取方法研究[J]. 岩石力学与工程学报，2015，34(6)：1 211–1 217.(WANG Rui，QI Taiyue，LEI Bo，et al. Characteristic extraction of cracks of tunnel lining[J]. Chinese Journal of Rock Mechanics and Engineering，2015，34(6)：1 211–1 217.(in Chinese))
[15] SUN Y，XUE Y D，HUANG H W. Inspection equipment study on subway tunnel defects[C]// Proceedings of the 2016 World Tunnel Congress. San Francisco，USA：International Tunneling and Underground Space Association，2016：1–9.
[16] HUANG H，SUN Y，XUE Y，et al. Inspection equipment study for subway tunnel defects by grey-scale image processing[J]. Advanced Engineering Informatics，2017，32：188–201.
[17] LECUN Y，BENGIO Y，HINTON G. Deep learning[J]. Nature，2015，521(7553)：436–444.
[18] HOF R D. MIT technology review：10 breakthrough technologies-deep learning[EB/OL]. (2013-4-23)[2017-1-3]. https：//www.technologyrevite. com/s/513696/deep-learning/.
[19] MAKANTASIS K，PROTOPAPADAKIS E，DOULAMIS A，et al. Deep convolutional neural networks for efficient vision based tunnel inspection[C]// Proceedings of the 11th International Conference on Intelligent Computer Communication and Processing. Cluj-Napoca，Romania：IEEE，2015：335–342.
[20] PROTOPAPADAKIS E，DOULAMIS N. Image based approaches for tunnels? defects recognition via robotic inspectors[C]// Proceedings of the 11th International Symposium on Visual Computing. Las Vegas，Nevada，USA：Springer International Publishing，2015：706–716.
[21] ZHANG L，YANG F，ZHANG Y D，et al. Road crack detection using deep Convolutional neural network[C]// Proceedings of the 23rd International Conference on Image Processing. Phoenix，Arizona，USA：IEEE，2016：3 708–3 712.
[22] CHA Y J，CHOI W，BUYUKOZTURK O. Deep learning-based crack damage detection using convolutional neural networks[J]. Computer-Aided Civil and Infrastructure Engineering，2017，32(5)：361–378.
[23] LONG J，SHELHAMER E，DARRELL T. Fully convolutional networks for semantic segmentation[C]// Proceedings of the 28thInternationalConference on Computer Vision and Pattern Recognition. Boston，MA，USA：IEEE，2015：3 431–3 440.
[24] 中华人民共和国国家标准编写组. GB 50208—2011地下防水工程质量验收规范[S]. 北京：中国建筑工业出版社，2011.(The National Standards Compilation Group of People?s Republic of China. GB 50208—2011 Code for acceptance of construction quality of underground waterproof[S]. Beijing：China Building Industry Press，2011.(in Chinese))
[25] JIA Y，SHELHAMER E，DONAHUE J，et al. Caffe：convolutional architecture for fast feature embedding[J]. Eprint Arxiv，2014：675–678.
[26] OTSU N. A threshold selection method from gray-Level histograms[J]. Systems Man and Cybernetics IEEE Transactions on，1979，9(1)：62–66.
[27] 豆海涛，黄宏伟，薛亚东. 隧道渗漏水红外辐射特征模型试验及图像处理[J]. 岩石力学与工程学报，2011，30(增2)：3 386– 3 391.(DOU Haitao，HUANG Hongwei，XUE Yadong. Model test on infrared radiation feature of tunnel seepage and image processing[J]. Chinese Journal of Rock Mechanics and Engineering，2011，30(Supp.2)：3 386–3 391.(in Chinese))
[28] KAMDI S，KRISHNA R K. Image segmentation and region growing algorithm[J]. International Journal of Computer Technology and Electronics Engineering，2012，1(2)：103–107.
[29] VINCENT L，SOILLE P. Watersheds in digital spaces：an efficient algorithm based on immersion simulations[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence，1991，13(6)：583–598.