Machine vision inspection system of subway tunnel structure and its application analysis

doi:10.13474/j.cnki.11-2246.2020.0277

Abstract

Abstract: This paper presents a rapid machine vision detection system for subway tunnel. The system uses deep learning algorithm to effectively identify the disease features in the collected images. The software platform can facilitate tunnel managers to view and track tunnel disease information in real time. The detection system has been applied to the detection of Nanning metro, and has achieved good detection results. It can accurately identify the tunnel defects such as cracks, spalling and leakage. It also compares with the manual detection method in terms of image effect, positioning accuracy, detection efficiency, recognition rate and detection accuracy. The results show that the image acquisition effect of the system is significantly better than that of the manual method; the detection speed can reach 30 km/h; the recognition accuracy of crack, spalling and leakage can reach 89%, 100% and 94% respectively; the surface defects with an area of 100 mm² and cracks with a width of more than 0.2 mm can be identified.

Key words: subway tunnel, machine vision, image processing, rapid detection, application analysis

CLC Number:

P258

LI Jun, ZHU Guoqi, FAN Xiaodong, YANG Wei, HUANG Zhen. Machine vision inspection system of subway tunnel structure and its application analysis[J]. Bulletin of Surveying and Mapping, 2020, 0(9): 27-32,37.

References

[1] 傅鹤林,黄震, 黄宏伟,等. 基于云理论的隧道结构健康诊断方法[J]. 工程科学学报,2017,39(5):794-801.
[2] 宋云记,王智. 利用三维激光扫描技术进行地铁隧道施工质量管控及病害检测[J]. 测绘通报,2020(5):150-154.
[3] 傅鹤林,黄震,王慧,等. 地铁安全事故分析及安全管理[J]. 隧道与地下工程灾害防治,2019,1(2):59-66.
[4] HUANG Z, FU H L, ZHANG J B, et al. Structural damage evaluation method for metro shield tunnel[J]. Journal of Performance of Constructed Facilities, 2019, 33(1):04018097.
[5] HUANG H W, SUN Y, XUE Y D, et al. Inspection equipment study for subway tunnel defects by grey-scale image processing[J].Advanced Engineering Informatics, 2017, 32:188-201.
[6] 高洪,李凯,马全明,等. 移动三维激光测量系统在地铁运营隧道病害监测中的应用研究[J]. 测绘通报,2019(8):96-101,161.
[7] SASAMA H, UKAI M, OHTA M, et al. Inspection system for railway facilities using a continuously scanned image[J]. Electrical Engineering in Japan, 1998,125 (2):52-64.[8] NISHIYAMA S, MINAKATA N, KIKUCHI T, et al. Improved digital photogrammetry technique for crack monitoring[J]. Advanced Engineering Informatics, 2015,29(4):851-858.[9] MENENDEZ E, VICTORES J G, MONTERO R, et al. Tunnel structural inspection and assessment using an autonomous robotic system[J]. Automation in Construction, 2018, 87:117-126.[10] 杨俊,刘笑娣,刘新根,等. 公路隧道结构快速检测车综述[J]. 华东交通大学学报,2018,35(4):30-38.[11] 王平让. 隧道病害快速检测技术现状及分析比较[J]. 公路与汽运,2016(3):241-245.[12] CAI Z, VASCONCELOS N. Cascade R-CNN:delving into high quality object detection[C]//IEEE Conference on Computer Vision and Pattern Recognition. Salt Lake City, UT:IEEE, 2018:6154-6162.[13] LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521(7553):436-444.[14] XIE S, GIRSHICK R, DOLLAR P, et al. Aggregated Residual Transformations for Deep Neural Networks[C]//IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI:IEEE, 2017:5987-5995.[15] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal loss for dense object detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020, 42(2):318-327.[16] CHENG Chuanqi, HAO Xiangyang, LI Jiansheng,et al. A robust Gaussian mixture model for mobile robots' vision-based pose estimation[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(3):79-90.[17] SHANG Yang,X SUN iaoliang, ZHANG Yueqiang,et al. Research on 3D target pose tracking and modeling[J]. Journal of Geodesy and Geoinformation Science, 2019, 2(2):60-69.