|
|
|
| A technique for automatically extracting regions of interest from ground penetrating radar data of roads based on the row-column variance method |
XU Li1,2( ), FENG Wen-Ya3, JIANG Yan-Nan1,2(), WANG Jiao1,2, ZHU Si-Xin4, QIN Zi-Xin1,2, LI Qin-Lin1,2, ZHANG Shi-Tian3 |
1. School of Information and Communication,Guilin University of Electronic Technology,Guilin 541004,China
2. Guangxi Key Laboratory of Wireless Wideband Communication & Signal Processing,Guilin 541000,China
3. China Research Institute of Radio Propagation,Qingdao 266107,China
4. College of Geosciences and Engineering,North China University of Water Resources and Electric Power,Zhengzhou 450011,China |
|
|
|
|
Abstract With the rapid development of the economy and society,traffic loads have increased sharply,gradually causing a series of pavement diseases.Ground penetrating radar (GPR),which is a non-destructive testing technique,can present the echo information of subsurface targets on the GPR profile.The echo information of diseases,such as voids,cavities underneath the pavement,and loosely infilled voids,constitutes a region of interest(ROI) on the GPR profile.The traditional manual ROI extraction method features high technical requirements and high laborious intensity due to massive data.Therefore,this study proposed an automatic ROI extraction method that combines the threshold segmentation data and the row-column variance.The experimental results show that the method proposed in this study can effectively extract the location information of multi-type and multi-target ROIs.This method has great potential for improving road detection efficiency based on GPR.
|
|
Received: 13 April 2022
Published: 05 July 2023
|
|
|
|
|
|
|
Radar profile and row-column variance distribution
a—original radar B-scan image;b—column variance and unit step;c—target 1 line variance and unit step;d—target 2 row variance and unit step
|
|
Row-column variance ROI extraction and labeling
a—ROI labeling;b—ROI of target No.1;c—ROI of target No.2
|
|
Flow chart of algorithm
|
|
ROI extraction with multiple targets
a—radar B-scan original image;b—ROI extraction effect
|
| 目标类型 | 目标编号 | 目标位置 | | 空洞 | 1 | (108,71;219,418) | | 管线 | 2 | (750,124;794,337) | | 钢筋网 | 3 | (1077,91;1142,341) | | 雨污井 | 4 | (1741,67;1865,511) | | 疏松体 | 5 | (2147,78;2640,487) |
|
Multi-types,multi-targets and their location information
|
| 数据量/采样点×道号 | T0 | T | η/% | | 512×20000 | 24 | 23 | 95.8 |
|
ROI detection rate
|
| 目标类型 | 目标编号 | | 空洞、脱空 | 12, 23, 25, 28, 36, 37, 39, 40, 46 | | 疏松体 | 3, 17, 29, 31, 35, 38, 43 | | 钢筋网 | 15, 22 | | 雨污井 | 2, 18, 42 | | 管线 | 30, 41 |
|
Target types corresponding to ROI and their automatic extraction numbers
|
|
B-scan diagram of Jiangxi road in Qingdao and the extracted ROI
a—B-scan diagram of Jiangxi road,Qingdao(illustration is automatic extraction of missing ROI);b—automatically extracting ROI
|
| [1] |
Griffiths H, Knott P, Koch W. Christian Hulsmeyer:Invention and demonstration of radar,1904[J]. IEEE Aerospace and Electronic Systems Magazine, 2019, 34(9):56-60.
|
| [2] |
白冰, 周健. 探地雷达测试技术发展概况及其应用现状[J]. 岩石力学与工程学报, 2001, 20(4):527-531.
|
| [2] |
Bai B, Zhou J. Development and application of ground penetrating radar[J]. Journal of Rock Mechanics and Engineering, 2001, 20(4):527-531.
|
| [3] |
曾昭发, 刘四新, 冯晅. 探地雷达原理与应用[M]. 北京: 电子工业出版社, 2010.
|
| [3] |
Zeng Z F, Liu S X, Feng Y. Principle and application of ground penetrating radar[M]. Beijing: Electronic Industry Press, 2010.
|
| [4] |
Baek J, Yoon J S, Lee C M, et al. A case study on detection of subsurface cavities of urban roads using ground-coupled GPR[C]// 2018 17th International Conference on Ground Penetrating Radar (GPR),2018.
|
| [5] |
Shi X, Cheng D, Song Z, et al. A real-time method for landmine detection using vehicle array GPR[C] // 2018 17th International Conference on Ground Penetrating Radar (GPR),2018.
|
| [6] |
Ciampoli L B, Benedetto A, Tosti F. The archaeo track project:Use of ground-penetrating radar for preventive conservation of buried archaeology towards the development of a virtual museum[C]// 2018 Metrology for Archaeology and Cultural Heritage(MetroArchaeo),2018.
|
| [7] |
中华人民共和国住房和城乡建设部. JGJ/T 437-2018 城市地下病害体综合探测与风险评估技术标准[S]. 北京:中国建筑工业出版社, 2018.
|
| [7] |
Ministry of Housing and Urban-Rural Development of the People's Republic of China. JGJ/T 437-2018 Technical Standard for Comprehensive Detection and Risk Assessment of Urban Underground Diseases [S].Beijing:China Construction Industry Press, 2018.
|
| [8] |
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.
|
| [8] |
Feng D S, Yang Z L. Automatic recognition of GPR image of tunnel lining structure based on deep learning[J]. Progress in Geophysics, 2020, 35(4):1552-1556.
|
| [9] |
刘普, 焦良葆, 曹雪虹. 基于行方差的GPR图像感兴趣区域提取定位方法[J]. 软件导刊, 2020, 19(6):218-222.
|
| [9] |
Liu P, Jiao L B, Cao X H. A method of extracting and locating regions of interest in GPR images based on row variance[J]. Software Guide, 2020, 19(6):218-222.
|
| [10] |
张旭, 龚钢军, 郝建红. 探地雷达目标回波信号双曲线提取算法研究[J]. 计算机测量与控制, 2016, 24(10):247-250.
|
| [10] |
Zhang X, Gong G J, Hao J H. Research on hyperbolic extraction algorithm of ground penetrating radar target echo signal[J]. Computer Measurement and Control, 2016, 24(10):247-250
|
| [11] |
Mertens L, Persico R, Matera L, et al. Automated detection of reflection Hyperbolas in complex GPR images with no a priori knowledge on the medium[J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54:580-596.
|
| [12] |
Ma X, Liu H, Wang M L, et al. Automatic detection of steel rebar in bridge decks from ground penetrating radar data[J]. Journal of Applied Geophysics, 2018, 158:93-102.
|
| [13] |
林春旭. 基于探地雷达和深度学习的地下目标智能探测与定位方法[D]. 广州: 广州大学, 2020.
|
| [13] |
Lin C X. Intelligent detection and location method of underground target based on ground penetrating radar and deep learning[D]. Guangzhou: Guangzhou University, 2020.
|
| [14] |
张军伟, 刘秉峰, 李雪, 等. 基于GPRMax2D的地下管线精细化探测方法[J]. 物探与化探, 2019, 43(2):435-440.
|
| [14] |
Zhang J W, Liu B F, Li X, et al. Refined detection method of underground pipeline based on GPRMax2D[J]. Geophysical and Geochemical Exploration, 2019, 43(2):435-440.
|
| [15] |
李靖翔, 赵明, 赖皓, 等. 地下电缆的探地雷达图像特征与识别技术[J]. 物探与化探, 2020, 44(6):1482-1489.
|
| [15] |
Li J X, Zhao M, Lai H, et al. Imaging detection and recognition technology of underground cable based on ground penetrating radar[J]. Geophysical and Geochemical Exploration, 2020, 44(6):1482-1489.
|
| [16] |
吴正平, 马占稳, 颜华, 等. 基于图像的多方向灰度波动局部阈值分割方法[J]. 激光与光电子学进展, 2020, 57(6):189-194
|
| [16] |
Wu Z P, Ma Z W, Yan H, et al. Image-based local threshold segmentation method for multi-directional gray fluctuation[J]. Advances in Laser and Optoelectronics, 2020, 57(6):189-194
|
| [1] |
WU Song, NING Xiao-Bin, YANG Ting-Wei, JIANG Hong-Liang, LU Chao-Bo, SU Yu-Di. Neural network-based denoising for ground-penetrating radar data[J]. Geophysical and Geochemical Exploration, 2023, 47(5): 1298-1306. |
| [2] |
ZENG Bo, LIU Shuo, YANG Jun, FENG De-Shan, YUAN Zhong-Ming, LIU Jie, WANG Xun. Influence of surface undulations on GPR-based underground pipeline detection[J]. Geophysical and Geochemical Exploration, 2023, 47(4): 1064-1070. |
|
|
|
|
