基于深度学习的GPR B-SCAN图像双曲线检测方法

doi:10.12263/DZXB.20200635

电子学报 ›› 2021, Vol. 49 ›› Issue (5): 953-963.DOI: 10.12263/DZXB.20200635

基于深度学习的GPR B-SCAN图像双曲线检测方法

王辉^1,2, 欧阳缮¹, 廖可非¹, 晋良念¹

1. 桂林电子科技大学信息与通信学院, 广西桂林 541004;
2. 贺州学院人工智能学院, 广西贺州 542899

收稿日期:2020-06-29 修回日期:2020-08-07 出版日期:2021-05-25 发布日期:2021-05-25
通讯作者: 欧阳缮(通信作者) 男,1960年9月生,江西安福人,桂林电子科技大学教授,博士生导师.主要研究方向:探地雷达信号处理、智能信息处理. E-mail:hmoysh@guet.edu.cn
作者简介:王辉男,1982年10月生,湖北仙桃人,贺州学院副教授,现为桂林电子科技大学博士研究生.主要研究方向:探地雷达信号处理、深度学习. E-mail:syswangxueleng@163.com
基金资助:
国家自然科学基金（No.61871425）；广西自然科学基金（No.2017GXNSFBA198032，No.2017GXNSFAA198050，No.2018JJA170185）

GPR B-SCAN Image Hyperbola Detection Method Based on Deep Learning

WANG Hui^1,2, OUYANG Shan¹, LIAO Ke-fei¹, JIN Liang-nian¹

1. School of Information and Communication, Guilin University of Electronic Technology, Guilin, Guangxi 541004, China;
2. School of Artificial Intelligence Hezhou University, Hezhou, Guangxi 542899, China

Received:2020-06-29 Revised:2020-08-07 Online:2021-05-25 Published:2021-05-25

摘要/Abstract

摘要： 利用深度学习方法来处理探地雷达(Ground Penetrating Radar,GPR)数据以提高GPR B-SCAN双曲线检测准确率.为了解决数据集样本不够的问题采用循环生成对抗网络(Cycle Generative Adversarial Networks,CycleGAN)算法对GPR B-SCAN图像数据进行增强.采用Faster R-CNN算子来定位双曲线图像区域,充分利用双曲线结构对称性及其方向差异性特征,设计与之对应的卷积核模板,通过卷积运算实现对B-SCAN图像中双曲线目标的有效分割.对双曲线目标采用最小二乘法进行二次曲线拟合得到精确的双曲线图像.与基于迁移学习的方法、HOG算法以及基于Hough变换的B-SCAN检测算法等相比,本文方法得到的结果在综合指标度量F上是最优的.

关键词: 深度学习, 探地雷达, 循环对抗生成网络, 卷积运算

Abstract: In order to improve the accuracy of GPR(ground penetrating radar) B-SCAN hyperbola detection,the deep learning method is applied to the processing of GPR data.In order to solve the problem of insufficient samples in the data set,the GPR B-SCAN image data is augmented by using cycle generative adversarial networks algorithm (CycleGAN).The Faster R-CNN operator is used to locate the hyperbolic image area,making full use of the symmetry of the hyperbolic structure and its directional difference characteristics,designing the corresponding convolution kernel template,and realize effective segmentation of hyperbolic targets in B-SCAN images through convolution operation.The least square method is used to perform quadratic curve fitting on the hyperbolic target to obtain an accurate hyperbolic image.Compared with B-SCAN image detection algorithms such as transfer learning-based methods,HOG(histogram of oriented gradients) algorithm and Hough transform algorithm,the results obtained by the method in this paper are optimal on the comprehensive measurement index F.

Key words: deep learning, ground penetrating radar, cycle generative adversarial networks, convolution operation

中图分类号:

TP391.41

王辉, 欧阳缮, 廖可非, 晋良念. 基于深度学习的GPR B-SCAN图像双曲线检测方法[J]. 电子学报, 2021, 49(5): 953-963.

WANG Hui, OUYANG Shan, LIAO Ke-fei, JIN Liang-nian. GPR B-SCAN Image Hyperbola Detection Method Based on Deep Learning[J]. Acta Electronica Sinica, 2021, 49(5): 953-963.

参考文献

[1] Ebrahim S M,Medhat N I,Mansour K K,et al.Examination of soil effect upon GPR detectability of landmine with different orientations[J].NRIAG Journal of Astronomy and Geophysics,2018,7(1):90-98.
[2] Pablo B,Bonomo N,Patricia M.Automatic detection of pipe-flange reflections in GPR data sections using supervised learning[J].Journal of Applied Geophysics,2019,170:103856.
[3] 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 T,Zhao J.A brief review of the hyperbola signature recognition techniques for ground penetrating radar[J].Acta Electronica Sinica,2019,47(6):1366-1372.(in Chinese).
[4] 侯斐斐,施荣华,雷文太,等.面向探地雷达 B-scan图像的目标检测算法综述[J].电子与信息学报,2020,42(1): 191-200. Hou F F,Shi R H,Lei W T,et al.A review of target detection algorithm for GPR B-scan processing[J].Journal of Electronics and Information Technology,2020,42(1): 191-200.(in Chinese).
[5] 陈德莉,黄春琳,粟毅.用统计方法和Hough变换进行GPR目标检测与定位[J].电子学报,2004,32(9):1468-1471. Chen D L,Huang C L,Su Y.An integrated method of statistical method and Hough transform for GPR targets detection and location[J].Acta Electronica Sinica,2004,32(9):1468-1471.(in Chinese).
[6] Liu Y Y,Wang M Q,Cai Q R.The target detection for GPR images based on curve fitting[A].International Congress on Image and Signal Processing[C].Yantai,China:IEEE,2010.2876-2879.
[7] Torrione P A,Morton K D,Sakaguchi R,et al.Histograms of oriented gradients for landmine detection in ground-penetrating radar data[J].IEEE Transactions on Geoence and Remote Sensing,2014,52(3):1539-1550.
[8] Maas C,Schmalzl J.Using pattern recognition to automatically localize reflection hyperbolas in data from ground penetrating radar[J].Computers & Geosciences,2013,58(8):116-125.
[9] Kang M S,Kim N,Im S B,et al.3D GPR image-based UcNet for enhancing underground cavity detectability[J].Remote Sensing,2019,11(21):2545.
[10] Zhou X,Chen H,Li J.An automatic GPR B-Scan image interpreting model[J].IEEE Transactions on Geoscience & Remote Sensing,2018,56(99):3398-3412.
[11] Alvarez J K,Kodagoda S.Application of deep learning image-to-image transformation networks to GPR radargrams for sub-surface imaging in infrastructure monitoring[A].The 13th IEEE Conference on Industrial Electronics and Applications[C].Wuhan,China:IEEE,2018.611-616.
[12] Zhang J,Yang X,Li W G,et al.Automatic detection of moisture damages in asphalt pavements from GPR data with deep CNN and IRS method[J].Automation in Construction,2020,113:103119.
[13] Besaw L E,Stimac P J.Deep convolutional neural networks for classifying GPR B-Scans[J].Proceedings of SPIE the International Society for Optical Engineering,2015,9454:945413.
[14] Ren S Q,He K M,Girshick R,et al.Faster R-CNN: Towards real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2015,39(6): 1137-1149.
[15] Li J Y,Zhang J,Chang D D,et al.Computer-assisted detection of colonic polyps using improved Faster R-CNN[J].Chinese Journal of Electronics,2019,28(4):718-724.
[16] Zhao Z B,Zhen Z,Zhang L,et al.Insulator detection method in inspection image based on improved Faster R-CNN[J].Energies,2019,12(7): 1204-1213.
[17] 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.
[18] Lei W T,Hou F F,Xi J C,et al.Automatic hyperbola detection and fitting in GPR B-scan image[J].Automation in Construction,2019,106:102839.
[19] Goodfellow I J,Pouget-Abadie J,Mirza M,et al.Generative adversarial networks[J].Advances in Neural Information Processing Systems,2014,3:2672-2680.
[20] Huang S W,Lin C T,Chen S P,et al.AugGAN:Cross domain adaptation with gan-based data augmentation[A].ECCV 2018: European Conference on Computer Vision[C].Munich Germany:Springer,2018.718-731.
[21] Wu Y,Yang F,Huang J,et al.Super-resolution construction of intravascular ultrasound images using generative adversarial networks[J].Journal of Southern Medical University,2019,39(1):82-87.
[22] Micha P,Isabel F,Maria R,et al.Generating large labeled data sets for laparoscopic image processing tasks using unpaired image-to-image translation[A].Medical Image Computing and Computer Assisted Intervention[C].Shenzhen,China:Springer,2019.119-127.
[23] Zhu J Y,Park T,Isola P,et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[A].The IEEE International Conference on Computer Vision[C].Venice,Italy:IEEE,2017.2223-2232.
[24] Chen X Y.Proof of concept project for detecting and classifying hyperbolas in ground penetrating radar(GPR) data[DB/OL].https://github.com/irenexy-chen/gpr-data-classifier,2018-08-24.
[25] 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.
[26] Tacoma,Everett.Ground penetrating radar detection in seattle[DB/OL].https://www.cnilocates.com/ground-penetrating-radar-gpr-detection,2020-04-22.
[27] Zhou X R,Chen H H,Hao T.Efficient detection of buried plastic pipes by combining gpr and electric field methods[J].IEEE Transactions on Geoscience and Remote Sensing.2019,57(6):3967-3979.
[28] Sun W,Xu Q,Zhang H,et al.Research on detection and visualization of underground pipelines[A].International Conference on Remote Sensing[C].Nanjing,China:IEEE,2012.1-4.

基于深度学习的GPR B-SCAN图像双曲线检测方法

GPR B-SCAN Image Hyperbola Detection Method Based on Deep Learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	廖勇, 李玉杰. 一种轻量化低复杂度的FDD大规模MIMO系统CSI反馈方法[J]. 电子学报, 2022, 50(5): 1211-1217.
[2]	冀振燕, 韩梦豪, 宋晓军, 冯其波. 面向激光光条图像修复的循环相似度映射网络[J]. 电子学报, 2022, 50(5): 1234-1242.
[3]	潘敏婷, 王韫博, 朱祥明, 高思宇, 龙明盛, 杨小康. 基于无标签视频数据的深度预测学习方法综述[J]. 电子学报, 2022, 50(4): 869-886.
[4]	杨曦, 张鑫, 郭浩远, 王楠楠, 高新波. 基于不变特征的多源遥感图像舰船目标检测算法[J]. 电子学报, 2022, 50(4): 887-899.
[5]	张浩, 胡昌华, 杜党波, 裴洪, 张建勋. 多状态影响下基于Bi‑LSTM网络的锂电池剩余寿命预测方法[J]. 电子学报, 2022, 50(3): 619-624.
[6]	崔亚奇, 何友, 唐田田, 熊伟. 一种深度学习航迹关联方法[J]. 电子学报, 2022, 50(3): 759-763.
[7]	骈纬国, 吴映波, 陈蒙, 蔡俊鹏. 一种基于时空动态图注意力网络的共享出行需求预测方法[J]. 电子学报, 2022, 50(2): 432-439.
[8]	李居朋, 王颖慧, 李刚. 医学图像关键点检测深度学习方法研究与挑战[J]. 电子学报, 2022, 50(1): 226-237.
[9]	张聿远, 张立民, 闫文君. 基于深度多级残差网络的低信噪比下空频分组码识别方法[J]. 电子学报, 2022, 50(1): 79-88.
[10]	席亮, 刘涵, 樊好义, 张凤斌. 基于深度对抗学习潜在表示分布的异常检测模型[J]. 电子学报, 2021, 49(7): 1257-1265.
[11]	谢佳龙, 张波涛, 吕强. 一种基于双流融合3D卷积神经网络的动态头势识别方法[J]. 电子学报, 2021, 49(7): 1363-1369.
[12]	罗会兰, 袁璞, 童康. 基于深度学习的显著性目标检测方法综述[J]. 电子学报, 2021, 49(7): 1417-1427.
[13]	程旭, 宋晨, 史金钢, 周琳, 张毅锋, 郑钰辉. 基于深度学习的通用目标检测研究综述[J]. 电子学报, 2021, 49(7): 1428-1438.
[14]	廖勇, 田肖懿, 蔡志镕, 花远肖, 韩庆文. 面向C-V2I的基于边缘计算的智能信道估计[J]. 电子学报, 2021, 49(5): 833-842.
[15]	周勇, 陈思霖, 赵佳琦, 张迪, 王瀚正. 基于弱语义注意力的遥感图像可解释目标检测[J]. 电子学报, 2021, 49(4): 679-689.