一种基于关键信息监督的隧道雷达数据衬线识别算法

doi:10.11871/jfdc.issn.2096-742X.2023.05.013

数据与计算发展前沿 ›› 2023, Vol. 5 ›› Issue (5): 154-163.

CSTR: 32002.14.jfdc.CN10-1649/TP.2023.05.013

doi: 10.11871/jfdc.issn.2096-742X.2023.05.013

一种基于关键信息监督的隧道雷达数据衬线识别算法

宋恒(),耿天宝,王东杰,张宜声^*()

中国中铁四局集团有限公司，管理与技术研究院，安徽合肥 230000

收稿日期:2022-11-30 出版日期:2023-10-20 发布日期:2023-10-31
通讯作者: *张宜声（E-mail: ethonzhang@163.com）
作者简介:宋恒，中铁四局研究院一级专家兼人工智能研究中心主任，研究方向为智能信号处理。兼任中国科学技术大学企业硕博导师。牵头和主责过10余项国家级、省部级重大装备研制项目，获得军队科技进步二等奖2项（排名前两位），发明专利多项。
本文中负责论文初稿撰写。
SONG Heng is a first-class expert and director of the Artificial Intelligence Research Centre of the Management and Technology Institute of China Railway No.4 Engineering Group Co., Ltd, with research interests in intelligent signal processing. He is also a mentor of the Master of Enterprise at the University of Science and Technology of China. He has led and been in charge of more than ten major equipment development projects at national and provincial levels, and has won two Second Prize of the Army Science and Technology Progress Award (ranked in the top two) and many invention patents.
In this paper, he is responsible for writing the first draft.
E-mail: songhengyang@163.com|张宜声，中铁四局研究院人工智能研究中心，工程师，硕士，研究兴趣为计算机视觉、大数据等。
本文中参与撰写“3 实验结果”部分与论文修改。
ZHANG Yisheng is an engineer at the Artificial Intelligence Research Centre of the Management and Technology Institute of China Railway No.4 Engineering Group Co., Ltd, and a graduate of the University of Science and Technology of China.
In this paper, he is responsible for writing “3 Experimental results” and paper revision.
E-mail: ethonzhang@163.com
基金资助:
中国中铁股份有限公司2021年度揭榜挂帅重大项目(2021-重大-14)

An Algorithm for Liner Identification of Tunnel Radar Data Based on Critical Information Supervision

SONG Heng(),GENG Tianbao,WANG Dongjie,ZHANG Yisheng^*()

Management and Technology Institute, China Railway No.4 Engineering Group Co., Ltd, Hefei, Anhui 230000, China

Received:2022-11-30 Online:2023-10-20 Published:2023-10-31

摘要/Abstract

摘要：

【目的】 探索探地雷达数据解析和基建病理检测新的处理方法。探地雷达作为桥梁和隧道缺陷检测中常用无损技术手段，一直面临数据解析困难问题，提高解析结果的准确性，对交通基础设施的缺陷检测具有重大应用价值。【方法】 将衬砌结构作为识别对象，分解为关键点和曲线来表示。关键点检测基于双热图方法，借助 “软标注”来加快模型收敛。曲线拟合模块通过神经网络回归拟合，加入对抗扰动机制，抗图像噪声干扰。【结果】 结果表明，该算法识别的衬砌线较真实偏移量为2.23个像素点，较CenterNet网络提升1.24个像素点，较CornerNet网络提升0.71个像素点。【结论】 解析识别效果提升显著，具有较高应用价值。

关键词: 探地雷达, 热图, 衬砌线检测, 对抗扰动, 曲线拟合

Abstract:

[Objective] This paper mainly explores new processing methods for ground-penetrating radar data parsing and infrastructure pathology detection. The current ground-penetrating radar, as a common non-destructive technical tool in bridge and tunnel defect detection, is facing the problem of difficult data parsing. Improving the accuracy of the parsing results has significant application value to the defect detection of transportation infrastructure. [Methods] The lining structure is represented as an identification object, decomposed into key points and curves. Key point detection is based on a bipartite heat map approach, with the help of "soft annotation" to speed up model convergence. The curve fitting module is implemented by neural network regression, incorporating a counteracting perturbation mechanism to resist image noise interference. [Results] The results show that the algorithm identifies a liner offset of 2.23-pixel points from the true one, a 1.24-pixel point improvement over the CenterNet network and a 0.71-pixel point improvement over the CornerNet network. [Conclusions] The proposed method has significantly improved resolution recognition results and has obvious application value.

Key words: ground penetrating radar, heatmap, lining line detection, anti-disturbance, curve fitting

宋恒, 耿天宝, 王东杰, 张宜声. 一种基于关键信息监督的隧道雷达数据衬线识别算法[J]. 数据与计算发展前沿, 2023, 5(5): 154-163.

SONG Heng, GENG Tianbao, WANG Dongjie, ZHANG Yisheng. An Algorithm for Liner Identification of Tunnel Radar Data Based on Critical Information Supervision[J]. Frontiers of Data and Computing, 2023, 5(5): 154-163, https://cstr.cn/32002.14.jfdc.CN10-1649/TP.2023.05.013.

图/表 14

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

图11

表1

图12

表2

参考文献 42

[1]	郝志虎. 高速公路特长隧道群安全综合评价研究[D]. 西安: 长安大学, 2008.
[2]	巩江峰, 唐国荣, 王伟, 范磊. 截至2021年底中国铁路隧道情况统计及高黎贡山隧道设计施工概况[J]. 隧道建设(中英文), 2022, 42(3): 508-517.
[3]	冯爱军. 中国城市轨道交通2021年数据统计与发展分析[J]. 隧道建设(中英文), 2022, 42(2): 336-341.
[4]	王梦恕. 中国铁路, 隧道与地下空间发展概况[J]. 隧道建设, 2010, 30(4): 351-364.
[5]	严金秀. 中国隧道工程技术发展 40 年[J]. 隧道建设(中英文), 2019, 39(4):537-54.
[6]	ILLINGWORTH J, KITTLER J. A survey of the Hough transform[J]. Computer vision, graphics, and image processing, 1988, 44(1): 87-116. doi: 10.1016/S0734-189X(88)80033-1
[7]	VON GIOI R G, JAKUBOWICZ J, MOREL J M, et al. LSD: A fast line segment detector with a false detection control[J]. IEEE transactions on pattern analysis and machine intelligence, 2008, 32(4): 722-732. doi: 10.1109/TPAMI.2008.300
[8]	ZHOU Y T, VENKATESWAR V, CHELLAPPA R. Edge detection and linear feature extraction using a 2-D random field model[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989, 11(1): 84-95. doi: 10.1109/34.23115
[9]	GALAMHOS C, MATAS J, KITTLER J. Progressive probabilistic Hough transform for line detection[C]// Proceedings. 1999 IEEE computer society conference on computer vision and pattern recognition (Cat. No PR00149), IEEE, 1999, 1: 554-560.
[10]	韩秋蕾, 朱明, 姚志军. 基于改进 Hough 变换的图像线段特征提取[J]. 仪器仪表学报, 2004 (z3): 436-439.
[11]	林玉池, 谢妤婵, 刘启海. 基于Hough变换的线段提取新方法[J]. 纳米技术与精密工程, 2009, 7(5):433-438.
[12]	张培宣, 陈晓东, 孔帅, 等. 基于Hough变换原理的海冰厚度识别方法[J]. 海洋学报, 2022, 44(07):161-169.
[13]	曹家乐, 李亚利, 孙汉卿, 等. 基于深度学习的视觉目标检测技术综述[J]. 中国图象图形学报, 2022, 27(6):1697-1722.
[14]	LAW H, DENG J. Cornernet: Detecting objects as paired keypoints[C]// Proceedings of the European conference on computer vision (ECCV), 2018: 734-750.
[15]	NEWELL A, YANG K, DENG J. Stacked hourglass networks for human pose estimation[C]// European conference on computer vision, Springer, Cham, 2016: 483-499.
[16]	ZHOU X, ZHUO J, KRAHENBUHL P. Bottom-up object detection by grouping extreme and center points[C]// Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 2019: 850-859.
[17]	DUAN K, BAI S, XIE L, et al. Centernet: Keypoint triplets for object detection[C]// Proceedings of the IEEE/CVF international conference on computer vision, 2019: 6569-6578.
[18]	LAW H, TENG Y, RUSSAKOVSKY O, et al. Cornernet-lite: Efficient keypoint based object detection[J]. arXiv preprint arXiv:1904.08900, 2019. https://doi.org/10.48550/arXiv.1904.08900.
[19]	林林, 王延杰, 孙海超. 基于改进热图损失函数的目标6D姿态估计算法[J]. 液晶与显示, 2022, 37(7):913-923.
[20]	KITTLER J. On the accuracy of the Sobel edge detector[J]. Image and Vision Computing, 1983, 1(1): 37-42. doi: 10.1016/0262-8856(83)90006-9
[21]	ROBERTS L G. Machine perception of three dimensional solids[D]. Massachusetts Institute of Technology, 1963.
[22]	LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE, 1998, 86(11): 2278-2324. doi: 10.1109/5.726791
[23]	CANNY J. A computational approach to edge detection[J]. IEEE Transactions on pattern analysis and machine intelligence, 1986(6): 679-698. pmid: 21869365
[24]	KONISHI S, YUILLE A L, COUGHLAN J M, etal. Statistical edge detection: Learning and evaluating edge cues[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(1): 57-74. doi: 10.1109/TPAMI.2003.1159946
[25]	MARTIN D R, FOWLKES C C, MALIK J. Learning to detect natural image boundaries using local brightness, color, and texture cues[J]. IEEE transactions on pattern analysis and machine intelligence, 2004, 26(5): 530-549. pmid: 15460277
[26]	DOLLAR P, ZITNICK C L. Fast edge detection using structured forests[J]. IEEE transactions on pattern analysis and machine intelligence, 2014, 37(8): 1558-1570. doi: 10.1109/TPAMI.2014.2377715
[27]	XIE S, TU Z. Holistically-nested edge detection[C]// Proceedings of the IEEE international conference on computer vision, 2015: 1395-1403.
[28]	LIU Y, LEW M S. Learning relaxed deep supervision for better edge detection[C]// Proceedings of the IEEE conference on computer vision and pattern recognition, 2016: 231-240.
[29]	WANG Y, ZHAO X, LI Y, et al. Deep crisp boundaries: From boundaries to higher-level tasks[J]. IEEE Transactions on Image Processing, 2018, 28(3): 1285-1298. doi: 10.1109/TIP.2018.2874279
[30]	DENG R, LIU S. Deep structural contour detection[C]// Proceedings of the 28th ACM international conference on multimedia, 2020: 304-312.
[31]	THOMPSON J, JAIN A, LECUN Y, et al. Joint training of a convolutional network and a graphical model for human pose estimation[J]. Advances in Neural Information Processing Systems, 2014, 2(January):1799-1807.
[32]	WEI S E, RAMAKRISHNA V, KANADE T, et al. Convolutional pose machines[C]// Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, 2016: 4724-4732.
[33]	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6):84-90. doi: 10.1145/3065386
[34]	DANG Q, YIN J Q, WANG B, et al. Deep learning based 2D human pose estimation: A survey[J]. Tsinghua Science and Technology, 2019, 24(6): 663-676. doi: 10.26599/TST.2018.9010100
[35]	雷冬冬, 王俊英, 董方敏, 等. 基于混合域注意力机制的服装关键点定位及属性预测算法[J]. 东华大学学报(自然科学版), 2022, 48(4):28-35.
[36]	WANG Y, TEOH E K, SHEN D. Lane detection and tracking using B-Snake[J]. Image and Vision computing, 2004, 22(4): 269-280. doi: 10.1016/j.imavis.2003.10.003
[37]	SHI X, KONG B, ZHENG F. A new lane detection method based on feature pattern[C]. IEEE Image and Signal Processing, 2009:1-5.
[38]	WANG S. A method of traffic lane detection and tracking[J]. Jisuanji Gongcheng yu Yingyong(Computer Engineering and Applications), 2011, 47(3): 244-248.
[39]	KO Y, LEE Y, AZAM S, et al. Key points estimation and point instance segmentation approach for lane detection[J]. IEEE Transactions on Intelligent Transportation Systems, 2021, 23(7): 8949-8958. doi: 10.1109/TITS.2021.3088488
[40]	翁佳昊, 秦永法, 鹿晓峰, 等. 基于路径搜索的车道线检测算法[J]. 扬州大学学报(自然科学版), 2022, 25(2):69-73.
[41]	LI C, LI M J, ZHAO Y G, et al. Layer recognition and thickness evaluation of tunnel lining based on ground penetrating radar measurements[J]. Journal of Applied Geophysics, 2011, 73(1): 45-48. doi: 10.1016/j.jappgeo.2010.11.004
[42]	WANG J, ZHANG J, COHN A G, et al. Arbitrarily-oriented tunnel lining defects detection from Ground Penetrating Radar images using deep Convolutional Neural networks[J]. Automation in Construction, 2022, 133: 104044. doi: 10.1016/j.autcon.2021.104044

	CenterNet	CornerNet	本文方法
欧式距离	6.33	5.72	3.76
曼哈顿距离	8.48	7.82	5.27
切比雪夫距离	5.67	4.95	3.01

一种基于关键信息监督的隧道雷达数据衬线识别算法

An Algorithm for Liner Identification of Tunnel Radar Data Based on Critical Information Supervision

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

图/表 14

参考文献 42

相关文章 0

编辑推荐

Metrics

本文评价