Please wait a minute...
浙江大学学报(工学版)
浙江大学学报(工学版)  2022, Vol. 56 Issue (7): 1404-1415    DOI: 10.3785/j.issn.1008-973X.2022.07.016
土木工程、水利工程、交通工程     
基于图像补偿的隧道衬砌裂缝检测方法
王建锋1,2(),邱雨1,刘水宙1
1. 长安大学 汽车学院，陕西 西安 710064
2. 陕西省道路交通智能检测与装备工程技术研究中心，陕西 西安 710064
Tunnel lining crack detection method based on image compensation
Jian-feng WANG1,2(),Yu QIU1,Shui-zhou LIU1
1. School of Automobile, Chang’an University, Xi’an 710064, China
2. Shaanxi Road Traffic Intelligent Detection and Equipment Engineering Technology Research Centre, Xi’an 710064, China
 全文: PDF(2348 KB)   HTML
摘要：

针对检测平台振动导致隧道衬砌裂缝图像识别准确率低、检测数据可靠性差的问题，提出基于图像补偿的隧道衬砌裂缝检测方法.开发车载式隧道衬砌裂缝检测系统，提出图像帧间自适应运动估计的方法. 对采用环境光增强处理得到的图像进行基于特征点匹配的自适应运动估计，建立图像帧间的运动关系，用卡尔曼滤波算法对运动参数进行滤波，去除采集平台的无规则振动，经过双三次插值实现图像补偿. 提出基于自适应分块综合滤波和形态学方法的衬砌图像裂缝分割方法，有效地完成裂缝提取和裂缝参数计算. 实验结果表明，利用提出的方法能够较好地补偿采集平台的振动误差，准确地提取裂缝信息，实现隧道衬砌裂缝的高精度检测.
关键词： 隧道衬砌裂缝;  图像补偿;  裂缝检测;  运动估计;  形态学处理    
Abstract:

A tunnel lining crack detection method based on image compensation was proposed aiming at the problems of low accuracy for tunnel lining crack image recognition and poor reliability of detection data caused by the vibration of detection platform. A vehicle mounted tunnel lining crack detection system was developed, and a method for adaptive motion estimation between image frames was proposed. Adaptive motion estimation based on feature point matching was conducted on the image obtained by ambient light enhancement processing in order to establish the motion relationship between image frames. The Kalman filter algorithm was utilized to filter the motion parameters in order to remove the random vibration of the acquisition platform. Then the image compensation was realized through bicubic interpolation. A method for lining image crack segmentation based on adaptive block comprehensive filtering and morphological methods was proposed to effectively complete crack extraction and crack parameter measurement. The experimental results show that the proposed method can better compensate the vibration error of the acquisition platform, accurately extract the crack information, and realize the high-precision detection of the tunnel lining crack.
Key words: tunnel lining crack    image compensation    crack detection    motion estimation    morphological processing
收稿日期: 2021-08-13 出版日期: 2022-07-26
CLC:  U 456  
基金资助: 国家重点研发计划资助项目（2020YFB1713303）；陕西省重点研发计划资助项目（2020ZDLGY16-05）
作者简介: 王建锋（1984—），男，副教授，博士，从事智能检测与装备技术的研究. orcid.org/0000-0002-7323-7143. E-mail： wjfchd@chd.edu.cn
服务　　
把本文推荐给朋友
加入引用管理器
E-mail Alert
作者相关文章　　
王建锋
邱雨
刘水宙

引用本文:

王建锋,邱雨,刘水宙. 基于图像补偿的隧道衬砌裂缝检测方法[J]. 浙江大学学报(工学版), 2022, 56(7): 1404-1415.

Jian-feng WANG,Yu QIU,Shui-zhou LIU. Tunnel lining crack detection method based on image compensation. Journal of ZheJiang University (Engineering Science), 2022, 56(7): 1404-1415.

链接本文:

https://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2022.07.016    或    https://www.zjujournals.com/eng/CN/Y2022/V56/I7/1404

图 1  隧道衬砌裂缝的检测系统
图 2  隧道衬砌检测系统的视野
图 3  裂缝检测方法的流程
图 4  增强后的图像
图 5  初匹配后的图像
图 6  2种匹配方法的对比
图 7  卡尔曼滤波器的运动滤波结果
图 8  三次插值法
图 9  自适应分块方法
图 10  边缘检测算法的对比
图 11  阈值分割算法的对比
图 12  Canny和Otsu双阈值综合方法的处理结果
图 13  区域形状特征去噪和形态学处理结果
图 14  裂缝宽度的计算流程
图 15  裂缝宽度的计算方法
图 16  补偿前、后的图像对比
图 17  补偿方法的PSNR结果
图 18  3种算法运行效率的结果
隧道桩号 真实结果 补偿后结果 不补偿结果
XZ11+024~XZ11+034 斜向裂缝 是 否
XZ11+084~XZ11+094 斜向裂缝 是 是
XZ11+134~XZ11+144 纵向裂缝 是 是
XZ11+194~XZ11+204 纵向裂缝 是 是
XZ11+284~XZ11+294 横向裂缝 是 是
XZ11+314~XZ11+324 斜向裂缝 是 是
XZ11+374~XZ11+384 斜向裂缝 是 否
XZ11+414~XZ11+424 斜向裂缝 是 是
XZ11+464~XZ11+474 斜向裂缝 是 是
XZ11+514~XZ11+524 斜向裂缝 是 否
表 1  裂缝类别的对比结果
隧道桩号 D/mm
真实值 补偿后值 未补偿值
XZ11+024~XZ11+034 271.0 278.4 261.2
XZ11+084~XZ11+094 150.0 152.3 170.6
XZ11+134~XZ11+144 610.5 617.6 538.9
XZ11+194~XZ11+204 578.5 580.2 493.2
XZ11+284~XZ11+294 321.0 323.6 372.4
XZ11+314~XZ11+324 301.5 306.6 320.7
XZ11+374~XZ11+384 402.5 408.7 380.9
XZ11+414~XZ11+424 380.0 384.6 372.6
XZ11+464~XZ11+474 260.7 264.1 256.8
XZ11+514~XZ11+524 320.5 327.8 339.1
表 2  裂缝长度的对比结果
隧道桩号 W/mm
真实值 补偿后值 未补偿值
XZ11+024~XZ11+034 1.20 1.38 1.53
XZ11+084~XZ11+094 1.07 1.23 0.98
XZ11+134~XZ11+144 2.24 2.45 2.56
XZ11+194~XZ11+204 1.79 1.94 2.13
XZ11+284~XZ11+294 1.38 1.51 1.26
XZ11+314~XZ11+324 0.61 0.71 0.81
XZ11+374~XZ11+384 1.34 1.52 1.46
XZ11+414~XZ11+424 1.50 1.67 1.37
XZ11+464~XZ11+474 1.18 1.30 1.62
XZ11+514~XZ11+524 1.45 1.60 1.78
表 3  裂缝宽度的对比结果
图 19  裂缝长度与宽度的计算误差
1 冷彪, 崔兆东, 杨辉, 等 基于线阵相机的运营隧道衬砌裂缝图像采集方法试验研究[J]. 现代隧道技术, 2020, 57 (1): 156- 161
LENG Biao, CUI Zhao-dong, YANG Hui, et al Experimental research on image acquisition method of tunnel lining cracks based on line-scanning digital camera[J]. Modern Tunneling Technology, 2020, 57 (1): 156- 161
2 李庆桐, 黄宏伟 基于数字图像的盾构隧道衬砌裂缝病害诊断[J]. 岩石力学与工程学报, 2020, 39 (8): 1658- 1670
LI Qing-tong, HUANG Hong-wei Diagnosis of structural cracks of shield tunnel lining based on digital images[J]. Chinese Journal of Rock Mechanics and Engineering, 2020, 39 (8): 1658- 1670
3 蒋宇静, 张学朋 隧道衬砌自动化检测及健康评价技术研究[J]. 隧道建设, 2021, 41 (3): 341- 348
JIANG Yu-jing, ZHANG Xue-peng Research on automatic detection and health assessment of tunnel lining[J]. Tunnel Construction, 2021, 41 (3): 341- 348
4 冯德山, 杨子龙 基于深度学习的隧道衬砌结构物探地雷达图像自动识别[J]. 地球物理学进展, 2020, 35 (4): 1552- 1556
FENG De-shan, YANG Zi-long Automatic recognition of ground penetrating radar image of tunnel lining structure based on deep learning[J]. Progress in Geophysics, 2020, 35 (4): 1552- 1556
doi: 10.6038/pg2020DD0325
5 黄震, 张陈龙, 傅鹤林, 等 隧道检测设备的发展及未来展望[J]. 公路交通科技, 2021, 38 (2): 98- 109
HUANG Zhen, ZHANG Chen-long, FU He-lin, et al Development and future prospect of tunnel machine detection equipment[J]. Journal of Highway and Transportation Research and Development, 2021, 38 (2): 98- 109
doi: 10.3969/j.issn.1002-0268.2021.02.013
6 ZHAO S, ZHANG D, HUANG H Deep learning based image instance segmentation for moisture marks of shield tunnel lining[J]. Tunneling and Underground Space Technology, 2020, 95 (1): 103156
7 林海山, 张彦龙 公路隧道病害快速检测技术发展和应用现状[J]. 中外公路, 2020, 40 (1): 176- 179
LIN Hai-shan, ZHANG Yan-long Development and application status of rapid detection technology of highway tunnel diseases[J]. Journal of China and Foreign Highway, 2020, 40 (1): 176- 179
8 FARAHANI B, BARROS F, SOUSA P A coupled 3D laser scanning and digital image correlation system for geometry acquisition and deformation monitoring of a railway tunnel[J]. Tunneling and Underground Space Technology, 2019, 91 (9): 102995
9 ATTARD L, DEBONO C J, VALENTINO G, et al Vision-based change detection for inspection of tunnel liners[J]. Automation in Construction, 2018, 91: 142- 154
doi: 10.1016/j.autcon.2018.03.020
10 GAO Z, LI F, LIU Y, et al Tunnel contour detection during construction based on digital image correlation[J]. Optics and Lasers in Engineering, 2020, 126 (5): 105879
11 YU S, JANG J, HAN C Auto inspection system using a mobile robot for detecting concrete cracks in a tunnel[J]. Automation in Construction, 2007, 16 (3): 255- 261
doi: 10.1016/j.autcon.2006.05.003
12 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 Ping-rang, HUANG Hong-wei, XUE Ya-dong 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
doi: 10.3969/j.issn.1000-6915.2012.05.016
13 STENT S, GHERA R, STENGE R, et al Visual change detection on tunnel linings[J]. Machine Vision and Applications, 2016, 27 (3): 319- 330
doi: 10.1007/s00138-014-0648-8
14 薛亚东, 李宜城 基于深度学习的盾构隧道衬砌病害识别方法[J]. 湖南大学学报: 自然科学版, 2018, 45 (3): 100- 109
XUE Ya-dong, LI Yi-cheng A method of disease recognition for shield tunnel lining based on deep learning[J]. Journal of Hunan University: Natural Science, 2018, 45 (3): 100- 109
15 江桁, 刘学增, 朱合华 基于隧道快速检测车数据的公路隧道衬砌开裂识别模型研究[J]. 现代隧道技术, 2020, 57 (5): 61- 65
JIANG Heng, LIU Xue-zeng, ZHU He-hua Research on crack identification of highway tunnel linings based on data obtained from the testing vehicle[J]. Modern Tunneling Technology, 2020, 57 (5): 61- 65
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 (4): 188- 201
17 JIANG Y, ZHANG X, TANIGUCHI T Quantitative condition inspection and assessment of tunnel lining[J]. Automation in Construction, 2019, 102 (6): 258- 269
18 唐钱龙, 谭园, 彭立敏, 等 基于数字图像技术的隧道衬砌裂缝识别方法研究[J]. 铁道科学与工程学报, 2019, 16 (12): 3041- 3049
TANG Qian-long, TAN Yuan, PENG Li-min, et al Crack identification method for tunnel linings based on digital image technology[J]. Journal of Railway Science and Engineering, 2019, 16 (12): 3041- 3049
19 石钰锋, 彭斌, 祝志恒, 等 隧道衬砌裂缝精细化识别及其评价[J]. 公路交通科技, 2020, 37 (2): 99- 106
SHI Yu-feng, PENG Bin, ZHU Zhi-heng, et al Refined identification of tunnel lining cracks and its evaluation[J]. Journal of Highway and Transportation Research and Development, 2020, 37 (2): 99- 106
20 代成刚, 林明星, 王震, 等 基于亮通道色彩补偿与融合的水下图像增强[J]. 光学学报, 2018, 38 (11): 86- 95
DAI Cheng-gang, LIN Ming-xing, WANH Zhen, et al Color compensation based on bright channel and fusion for underwater image enhancement[J]. Acta Optica Sinica, 2018, 38 (11): 86- 95
21 马文涛, 樊春玲 基于计算机视觉路面裂缝的识别与测量[J]. 电子测量技术, 2020, 43 (19): 85- 88
MA Wen-tao, FAN Chun-ling Recognition and measurement of pavement cracks based on computer vision[J]. Electronic Measurement Technology, 2020, 43 (19): 85- 88
22 高尚兵, 颉正, 潘志庚, 等 一种新的路面裂缝自动检测算法[J]. 系统仿真学报, 2017, 29 (9): 2009- 2015
GAO Shang-bing, XIE Zheng, PAN Zhi-geng, et al Novel automatic pavement crack detection algorithm[J]. Journal of System Simulation, 2017, 29 (9): 2009- 2015
23 杨杰文, 章光, 陈西江, 等 融合深度学习聚类分割和 形态学的混凝土表面裂缝量化识别[J]. 激光与光电子学进展, 2020, 57 (22): 242- 252
YANG Jie-wen, ZHANG Guang, CHEN Xi-jiang, et al Quantitative identification of concrete surface cracks based on deep learning clustering segmentation and morphology[J]. Laser and Optoelectronics Progress, 2020, 57 (22): 242- 252
24 姜吉荣, 陈小惠 基于多特征的路面裂缝目标提取方法[J]. 计算机技术与发展, 2016, 26 (5): 173- 178
JIANG Ji-rong, CHEN Xiao-hui Pavement crack object extraction method based on multi-features[J]. Computer Technology and Development, 2016, 26 (5): 173- 178
25 孙亮, 邢建春, 谢立强, 等 基于自适应阈值Canny算法的裂缝检测方法研究[J]. 微型机与应用, 2017, 36 (5): 35- 37
SUN Liang, XING Jian-chun, XIE Li-qiang, et al An adaptive threshold-based Canny algorithm for crack detection[J]. Microcomputer and Applications, 2017, 36 (5): 35- 37
26 赵芳, 周旺辉, 陈岳涛, 等 改进的Canny算子在裂缝检测中的应用[J]. 电子测量技术, 2018, 41 (20): 107- 111
ZHAO Fang, ZHOU Wang-hui, CHEN Yue-tao, et al Application of improved canny operator in crack detection[J]. Electronic Measurement Technology, 2018, 41 (20): 107- 111
27 徐欢, 李振璧, 姜媛媛, 等 基于OpenCV和改进Canny算子的路面裂缝检测[J]. 计算机工程与设计, 2014, 35 (12): 4254- 4258
XU Huan, LI Zhen-bi, JIANG Yuan-yuan, et al Pavement crack detection based on OpenCV and improveed Canny operator[J]. Computer Engineering and Design, 2014, 35 (12): 4254- 4258
doi: 10.3969/j.issn.1000-7024.2014.12.038
28 朱鑫, 漆泰岳, 王睿, 等 一种改进的用于裂缝图像分割的Otsu方法[J]. 地下空间与工程学报, 2017, 13 (Supple.1): 80- 84
ZHU Xin, QI Tai-yue, WANG Rui, et al An improved Otsu method for image segmentation of cracks[J]. Chinese Journal of Underground Space and Engineering, 2017, 13 (Supple.1): 80- 84
29 娄联堂, 何慧玲 基于图像灰度变换的OTSU阈值优化算法[J]. 中南民族大学学报: 自然科学版, 2021, 40 (3): 325- 330
LOU Lian-tang, HE Hui-ling OTSU threshold optimization algorithm based on image gray level transformation[J]. Journal of South-Central University for Nationalities: Natural Science Edition, 2021, 40 (3): 325- 330
30 梁义涛, 孟亚敏, 朱玲艳, 等 二维Otsu拟合线阈值图像分割方法[J]. 科学技术与工程, 2021, 21 (9): 3689- 3697
LIANG Yi-tao, MENG Ya-min, ZHU Ling-yan, et al Image segmentation with two-dimensional Otsu fitting line threshold method[J]. Science Technology and Engineering, 2021, 21 (9): 3689- 3697
doi: 10.3969/j.issn.1671-1815.2021.09.038
31 曾诚, 宋燕 改进的OTSU和最大熵结合的迭代图像分割算法[J]. 智能计算机与应用, 2020, 10 (12): 121- 125
ZENG Cheng, SONG Yan An improved image segmentation algorithm based on Otsu and maximum entropy[J]. Intelligent Computer and Applications, 2020, 10 (12): 121- 125
doi: 10.3969/j.issn.2095-2163.2020.12.027
32 宋浒, 张利, 许梦晗, 等 基于形态学和小波变换的图像边 缘检测方法[J]. 西南大学学报: 自然科学版, 2020, 42 (4): 105- 111
SONG Hu, ZAHNG Li, XU Meng-han, et al An image edge detection method based on morphology and wavelet transform[J]. Journal of Southwest University: Natural Science Edition, 2020, 42 (4): 105- 111
33 余小庆, 陈仁文, 唐杰, 等 融合小波变换和新形态学的含噪图像边缘检测[J]. 计算机科学, 2018, 45 (Supple.2): 194- 197
XU Xiao-qing, CHEN Ren-wen, TANG Jie, et al Edge detection for noisy image based on transform and new mathematical morphology[J]. Computer Science, 2018, 45 (Supple.2): 194- 197
34 李东兴, 高倩倩, 张起, 等 融合数学形态学滤波技术的边缘检测算法[J]. 山东理工大学学报: 自然科学版, 2018, 32 (6): 1- 5
LI Dong-xing, GAO Qian-qian, ZHANG Qi, et al Edge detection algorithm fused with mathematical morphology technology[J]. Journal of Shandong University of Technology: Natural Science Edition, 2018, 32 (6): 1- 5
[1] 蒋炜, 田翔, 陈耀武. H.264到HEVC的低复杂度视频转码算法[J]. 浙江大学学报(工学版), 2014, 48(6): 994-003.
[2] 康轶非,宋永端,宋宇,闫德立. 不依赖里程计的机器人定位与地图构建[J]. J4, 2014, 48(3): 414-422.
[3] 於俊,汪增福. 基于经验模式分解和多种评价准则的电子稳像[J]. J4, 2014, 48(3): 423-429.
[4] 欧阳柳,徐进,龚小谨,刘济林. 基于不确定性分析的视觉里程计优化[J]. J4, 2012, 46(9): 1572-1579.
[5] 张申,王维东,赵亚飞,吴祖成,王曰海,张明. 基于三维离散余弦变换的体三维视频数据压缩[J]. J4, 2012, 46(1): 112-117.
[6] 徐进,沈敏一,杨力,王炜强,刘济林. 基于双目光束法平差的机器人定位与地形拼接[J]. J4, 2011, 45(7): 1141-1146.
[7] 郑雅羽, 田翔, 陈耀武. 基于随机采样的两阶段全局运动估计[J]. J4, 2010, 44(1): 131-135.
[8] 杜歆 周围 朱云芳 刘济林. 基于单目视觉的障碍物检测[J]. J4, 2008, 42(6): 913-917.
[9] 莫林剑 卜佳俊 陈纯 杨智. H.264中基于预测的快速模式决策算法[J]. J4, 2008, 42(4): 612-617.
[10] 范佑 刘鹏. H.264中整像素和分数像素快速搜索算法[J]. J4, 2008, 42(2): 332-336.
[11] 杨智 莫林剑 卜佳俊 陈纯. MPEG-4到H.264转码中多帧参考运动估计快速算法[J]. J4, 2008, 42(12): 2055-2061.
[12] 李智 周文晖 刘济林. 动态场景下基于视差空间的立体视觉里程计[J]. J4, 2008, 42(10): 1661-1665.
[13] 李东晓 郑伟 张明. 访存带宽最小化的H.264整像素运动估计VLSI结构[J]. J4, 2007, 41(8): 1341-1347.
[14] 方健 郑伟 王匡. ATETS: 针对H.264的自适应提前终止搜索算法[J]. J4, 2007, 41(4): 607-611.
[15] 孙小叶 刘济林 陈建乐. 一种低码率下简单有效的环路滤波方法[J]. J4, 2005, 39(7): 931-934.