面向双曲线形态的探地雷达图像识别技术综述

doi:10.3969/j.issn.0372-2112.2019.06.025

摘要/Abstract

摘要： 探地雷达作为一种重要的无损探测技术，可以准确快速对浅层地表进行成像，以获取埋设目标的空间与几何信息.该文在分析探地雷达成像模型与目标识别基本思路的基础上，简述和归纳了七类探地雷达图像双曲线特征的检测方法，分别为基于双曲线性质、时域信号分析、数字图像分析、机器学习、数学模型、综合性方法以及深度学习方法，最后展望了深度学习在双曲线形态识别中的应用前景.

关键词: 物探技术, 无损探测, 探地雷达, 目标识别, 双曲线特征, 深度学习

Abstract: Ground penetrating radar (GPR),as an important non-destructive detection technology,can image the shallow subsurface accurately and quickly to obtain the spatial and geometric information of the buried targets.This paper describes and summarizes seven detection methods of hyperbolic signatures in GPR images,i.e.,based on hyperbolic properties,based on the time domain signal analysis,based on the digital image analysis,based on the machine learning,based on the mathematical model,based on the comprehensive and deep learning methods.Finally,we discuss the application potential of the deep learning method for the recognition of hyperbolic signatures.

Key words: geophysical technology, non-destructive detection, GPR, object recognition, hyperbola signature, deep learning

中图分类号:

TP391.4

郝彤, 赵杰. 面向双曲线形态的探地雷达图像识别技术综述[J]. 电子学报, 2019, 47(6): 1366-1372.

HAO Tong, ZHAO Jie. A Brief Review of the Hyperbola Signature Recognition Techniques for Ground Penetrating Radar[J]. Acta Electronica Sinica, 2019, 47(6): 1366-1372.

参考文献

[1] 李嘉,郭成超,王复明,等.探地雷达应用概述[J].地球物理学进展,2007,22(2):629-637. LI Jia,GUO Cheng-chao,WANG Fu-ming,et al.The summary of the surface ground penetrating radar applied in subsurface investigation[J].Progress in Geophysics,200722(2):629-637.(in Chinese)
[2] DANIELS D J.Ground Penetrating Radar[M].USA.:John Wiley & Sons,Inc,2005.
[3] 许献磊,赵艳玲,王方,等.GPR探测地埋管径研究综述[J].地球物理学进展,2012,27(5):2206-2215. XU Xian-lei,ZHAO Yan-lin,WANG Fang,et al.Review on diameter detection of underground pipe with GPR[J].Progress in Geophysics,2012,27(5):2206-2215.(in Chinese)
[4] WARREN C,GIANNOPOULOS A,GIANNAKIS I.gprMax:Open source software to simulate electromagnetic wave propagation for Ground Penetrating Radar[J].Computer Physics Communications,2016,209:163-170.
[5] 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(1):580-596.
[6] SANDMEIER K J.Reflexw Version 6.0[Z].Karlsruhe,Germany:Sandmeier Scientific Software,2011.
[7] TZANIS A.MATGPR:A freeware MATLAB package for the analysis of common-offset GPR data[A].Geophysical Research Abstracts[C].Vienna,Austria:Copernicus,2006.
[8] HUBER E,HANS G.RGPR-An open-source package to process and visualize GPR data[A].International Conference on Ground Penetrating Radar[C].Rapperswil,Switzerland:IEEE,2018.1-4.
[9] LI Ting-jun,ZHOU Zheng-ou.Fast extraction of hyperbolic signatures in GPR[A].International Conference on Microwave and Millimeter Wave Technology[C].Guilin,China:IEEE,2007.1-3.
[10] LIU Yayu,WANG Meiqing,CAI Qiurong.The target detection for GPR images based on curve fitting[A].International Congress on Image and Signal Processing[C].USA:IEEE,2010.
[11] XU Xiaoyin,MILLER E,RAPPAPORT C,et al.Statistical method to detect subsurface objects using array ground-penetrating radar data[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(4):963-976.
[12] 胡进峰,周正欧.基于核方法的探地雷达目标特征提取方法[J].电波科学学报,2005,20(5):671-674. HU Jin-feng,ZHOU Zheng-ou.GPR target feature extraction based on kernel method[J].Chinese Journal of Radio Science,2005,20(5):671-674.(in Chinese)
[13] 高翔,姬光荣,姬婷婷,等.基于探测过程建模的探地雷达多目标识别[J].电波科学学报,2011(3):574-580. GAO Xiang,JI Guang-rong,JI Ting-ting,et al.GPR multi-target recognition using texture features of time-frequency analysis and HMM[J].Chinese Journal of Radio Science,2011(3):574-580.(in Chinese)
[14] 杨莘,陈淑珍,唐中柱.探地雷达管道目标图像的识别[J].计算机应用,2005,25(5):1209-1211. YANG Xin,CHEN Shu-zhen,TANG Zhong-zhu.Recognition for pipe image of ground penetrating radar[J].Journal of Computer Applications,2005,25(5):1209-1211.(in Chinese)
[15] 王建,袁宵,李禹,等.利用互相关和Hough变换快速检测探地雷达目标[J].电子与信息学报,2013,35(5):1156-1162. WANG Jian,YUAN Xiao,LI Yu,et al.Fast detection of ground penetrating radar objects based on cross correlation and hough transform[J].Journal of Electronics and Information Technology,2013,35(5):1156-1162.(in Chinese)
[16] 孔祥维,石浩.形状约束的Snake算法在探地雷达图像目标自动提取中的应用[J].物探化探计算技术,2001,23(4):333-337. KONG Xiang-wei,SHI Hao.The automatic target detection on ground penetrating radar images using shape-bounded active contour model[J].Computing Techniques for Geophysical and Geochemical Exploration,2001,23(4):333-337.(in Chinese)
[17] SAGNARD F,TAREL J.Template-matching based detection of hyperbolas in ground-penetrating radargrams for buried utilities[J].Journal of Geophysics and Engineering,2016,13(4):491-504.
[18] PASOLLI E,MELGANI F,DONELLI M.Automatic analysis of GPR images:A pattern-recognition approach[J].IEEE Transactions on Geoscience and Remote Sensing,2009,47(7):2206-2217.
[19] DELBO S,GAMBA P,ROCCATO D.A fuzzy shell clustering approach to recognize hyperbolic signatures in subsurface radar images[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(3):1447-1451.
[20] KOBAYASHI M,NAKANO K.Dirichlet process crescent-signal mixture model for ground-penetrating radar signals[A].Annual Conference of the IEEE Industrial Electronics Society[C].Dallas,Texas,USA:IEEE,2014.3431-3437.
[21] CHEN Huanhuan,COHN A.Probabilistic robust hyperbola mixture model for interpreting ground penetrating radar data[A].International Joint Conference on Neural Networks[C].Barcelona,Spain:IEEE,2010.1-8.
[22] ZHOU Xiren,CHEN Huanhuan,LI Jinlong.An automatic GPR B-Scan image interpreting model[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(6):3398-3412.
[23] SAKAGUCHI R,MORTON K,COLLINS L,et al.A comparison of feature representations for explosive threat detection in ground penetrating radar data[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(12):6736-6745.
[24] REICHMAN D,COLLINS L,MALOF J.On choosing training and testing data for supervised algorithms in ground-penetrating radar data for buried threat detection[J].IEEE Transactions on Geoscience and Remote Sensing,2018,56(1):497-507.
[25] GAMBA P,LOSSANI S.Neural detection of pipe signatures in ground penetrating radar images[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(2):790-797.
[26] MAAS C,SCHMALZL J.Using pattern recognition to automatically localize reflection hyperbolas in data from ground penetrating radar[J].Computers and Geosciences,2013,58:116-125.
[27] TORRIONE P,MORTON K,SAKAGUCHI R,et al.Histograms of oriented gradients for landmine detection in ground-penetrating radar data[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(3):1539-1550.
[28] FRIGUI H,GADER P.Detection and discrimination of land mines in ground-penetrating radar based on edge histogram descriptors and a possibilistic k-nearest neighbor classifier[J].IEEE Transactions on Fuzzy Systems,2009,17(1):185-199.
[29] QING Xudou,LI Junwei,DEREK R,et al.Real-time hyperbola recognition and fitting in GPR data[J].IEEE Transactions on Geoscience and Remote Sensing,2017,55(1):51-62.
[30] BESAW L,STIMAC P.Deep convolutional neural networks for classifying GPR B-scans[A].Detection and Sensing of Mines,Explosive Objects,and Obscured Targets[C].Baltimore,Maryland,USA:SPIE,2015.
[31] BRALICH J,REICHMAN D,COLLINS L,et al.Improving convolutional neural networks for buried target detection in ground penetrating radar using transfer learning via pretraining[A].Detection and Sensing of Mines,Explosive Objects,and Obscured Targets[C].Anaheim,California,USA:SPIE,2017.
[32] PHAM M T,LEFÈVRE S.Buried object detection from B-scan ground penetrating radar data using Faster-RCNN[A].IEEE International Geoscience and Remote Sensing Symposium[C].Valencia,Spain:IEEE,2018.6804-6807.
[33] ALVAREZ J,KODAGODA S.Application of deep learning image-to-image transformation networks to GPR radargrams for sub-surface imaging in infrastructure monitoring[A].IEEE Conference on Industrial Electronics and Applications[C].Singapore:IEEE,2018.611-616.
[34] CHEN Xiang-yi.Proof-of-concept project for detecting and classifying hyperbolas in ground penetrating radar (GPR) data[DB/OL].https://github.com/irenexychen/gpr-data-classifier,2018-08-24.