DABP: A Deep Learning Based Auto Focusing Back Projection Imaging Method for Ground Penetrating Radar

LEI Wen-tai; SUI Hao; JIANG He-jun; LÜ Rong-qi

doi:10.12263/DZXB.20231144

您当前的位置：

首页 >

文章列表页 >

DABP: A Deep Learning Based Auto Focusing Back Projection Imaging Method for Ground Penetrating Radar

PAPERS | 更新时间：2025-12-11

- DABP: A Deep Learning Based Auto Focusing Back Projection Imaging Method for Ground Penetrating Radar
- ACTA ELECTRONICA SINICA Vol. 52, Issue 12, Pages: 4023-4036(2024)
- 作者机构：
  
  1.中南大学电子信息学院，湖南长沙 410083
  2.近地面探测技术重点实验室，江苏无锡 214035
- 作者简介：
- 基金信息：
  
  Foundation Project of Science and Technology on Near-Surface Detection Laboratory(6142414221605)
- DOI：10.12263/DZXB.20231144
  CLC： TN957.52;
- Received：08 December 2023，
  
  Revised：2024-06-26，
  
  Published：25 December 2024
- 稿件说明：
移动端阅览
雷文太, 隋浩, 姜和俊, 等. DABP：一种基于深度学习的探地雷达自聚焦后向投影成像方法[J]. 电子学报, 2024, 52(12): 4023-4036.

LEI Wen-tai, SUI Hao, JIANG He-jun, et al. DABP: A Deep Learning Based Auto Focusing Back Projection Imaging Method for Ground Penetrating Radar[J]. Acta Electronica Sinica, 2024, 52(12): 4023-4036.
雷文太, 隋浩, 姜和俊, 等. DABP：一种基于深度学习的探地雷达自聚焦后向投影成像方法[J]. 电子学报, 2024, 52(12): 4023-4036. DOI：10.12263/DZXB.20231144

LEI Wen-tai, SUI Hao, JIANG He-jun, et al. DABP: A Deep Learning Based Auto Focusing Back Projection Imaging Method for Ground Penetrating Radar[J]. Acta Electronica Sinica, 2024, 52(12): 4023-4036. DOI：10.12263/DZXB.20231144

摘要

探地雷达（Ground Penetrating Radar， GPR）作为一种非破坏性的电磁探测技术，已广泛应用于市政工程、交通、军事等领域的探测.复杂的地下环境中，电磁波传播规律变得复杂，背景介质的介电常数难以准确获得.后向投影（Back Projection，BP）成像算法需要预知背景介质的相对介电常数，且需逐个计算各成像网格的散射强度值，计算效率低.本文提出一种基于深度学习的探地雷达自聚焦后向投影（Deep learning based Auto focusing BP，DABP）成像方法，设计了目标感兴趣区域（Region Of Interest，ROI）的检测模块，基于地下目标的空间稀疏特征，将YOLOX网络和BP成像机理相结合，快速检测出目标潜在区域，仅对该区域中的成像网格进行成像处理，避免全域的后向投影计算，大幅降低运算量.其次，针对介电常数未知情况下BP成像难以聚焦的问题，设计了一个自聚焦后向投影（Auto Focusing BP，AF-BP）成像模块，构建了BS-YOLOv5网络和相应的数据集，实现基于改进二分法的地下介质介电常数估计和自聚焦成像.然后，设计了一个基于双阈值和积分聚焦的伪影抑制（artifact suppression based on Double Threshold and Integral Focusing，DTIF）模块，进一步提高成像结果的聚焦度.开展了仿真和实测数据的成像处理和对比分析，与BP成像方法相比，仿真数据成像结果的ISLR指标下降了250%、SCR指标提升了131%；实测数据成像结果的ISLR指标下降了322%、SCR指标提升了72%，仿真实验和实测实验的成像速度均提升了300%，验证了所提方法在提高GPR成像效率和成像质量方面的有效性.

Abstract

As a non-destructive electromagnetic detection technology

ground penetrating radar (GPR) has been widely used in municipal engineering

transportation

military and other fields. In the complex underground environment

the propagation law of electromagnetic wave becomes complicated

and the dielectric constant of background medium is difficult to be accurately obtained. Back projection (BP) imaging algorithm needs to predict the relative dielectric constant of the background media and calculate the scattering intensity of each imaging grid one by one

so the calculation efficiency is low. This paper puts forward the imaging method of deep learning based auto focusing BP (DABP). Firstly

a region of interest (ROI) detection module is designed. Based on the sparse space characteristics of underground targets

by combining YOLOX network and BP imaging mechanism

the potential target region is quickly detected

and only the imaging grid in the region is processed

which avoids the global back projection calculation and greatly reduces the amount of computation. Secondly

aiming at the problem that BP imaging is difficult to focus when the dielectric constant is unknown

an auto focusing BP (AF-BP) imaging module is designed

BS-YOLOv5 network and corresponding data set are constructed

and dielectric constant estimation and auto focusing imaging of underground media based on improved dichotomy are realized. Then

an artifact suppression based on double threshold and integral focusing (DTIF) module is designed to further improve the focusing degree of imaging results. Compared with BP imaging method

ISLR index of simulation data decreased by 250% and SCR index increased by 131%. ISLR index of measured data imaging results decreased by 322%

SCR index increased by 72%

and imaging speed of simulation experiment and measured experiment increased by 300%

which verified the effectiveness of the proposed method in improving GPR imaging efficiency and imaging quality.

关键词

Keywords

references

JOL H M . 探地雷达理论与应用 [M ] . 雷文太, 童孝忠, 周旸, 译. 北京 : 电子工业出版社 , 2011 .

JOL H M . Ground Penetrating Radar: Theory and Applications [M ] . LEI W T, TONG X Z, ZHOU Y, Trans. Beijing : Publishing House of Electronics Industry , 2011 . (in Chinese)

HU J H , VENNAPUSA P K R , WHITE D J , et al . Pavement thickness and stabilised foundation layer assessment using ground-coupled GPR [J ] . Nondestructive Testing and Evaluation , 2016 , 31 ( 3 ): 267 - 287 .

TEŠIĆ K , BARIČEVIĆ A , SERDAR M . Non-destructive corrosion inspection of reinforced concrete using ground-penetrating radar: A review [J ] . Materials , 2021 , 14 ( 4 ): 975 .

YANG H W , YANG Z K , PEI Y K . Ground-penetrating radar for soil and underground pipelines using the forward modeling simulation method [J ] . Optik , 2014 , 125 ( 23 ): 7075 - 7079 .

ZHANG J , LU Y M , YANG Z , et al . Recognition of void defects in airport runways using ground-penetrating radar and shallow CNN [J ] . Automation in Construction , 2022 , 138 : 104260 .

KANIEWSKI P , KRASZEWSKI T . Estimation of handheld ground-penetrating radar antenna position with pendulum-model-based extended Kalman filter [J ] . Remote Sensing , 2023 , 15 ( 3 ): 741 .

CHAMYAL L S , JOSHI P , VASAIKAR S , et al . Neotectonic characterization of the Narmada-Son Fault (NSF) using field and GPR data, Gujarat, western India [J ] . Journal of the Palaeontological Society of India , 2022 , 67 ( 1 ): 72 - 84 .

LIU L , CHEN Q Q , HAN Y P , et al . Improved clutter removal by robust principal component analysis for chaos through-wall imaging radar [J ] . Electronics , 2019 , 9 ( 1 ): 25 .

CARIN L , GENG N , MCCLURE M , et al . Ultra-wide-band synthetic-aperture radar for mine-field detection [J ] . IEEE Antennas and Propagation Magazine , 1999 , 41 ( 1 ): 18 - 33 .

LV Y Z , WANG H H , GONG J B . Application of GPR reverse time migration in tunnel lining cavity imaging [J ] . Applied Geophysics , 2020 , 17 ( 2 ): 277 - 284 .

ZHOU L , SU Y . GPR imaging with RM algorithm in layered mediums [J ] . IEEE Geoscience and Remote Sensing Letters , 2011 , 8 ( 5 ): 934 - 938 .

QU L L , YIN Y Q , SUN Y P , et al . Diffraction tomographic ground-penetrating radar multibistatic imaging algorithm with compressive frequency measurements [J ] . IEEE Geoscience and Remote Sensing Letters , 2015 , 12 ( 10 ): 2011 - 2015 .

雷文太 , 毛凌青 , 庞泽邦 , 等 . DR-GAN: 一种无监督学习的探地雷达杂波抑制方法 [J ] . 电子与信息学报 , 2023 , 45 ( 10 ): 3776 - 3785 .

LEI W T , MAO L Q , PANG Z B , et al . DR-GAN: An unsupervised learning approach to clutter suppression for ground penetrating radar [J ] . Journal of Electronics & Information Technology , 2023 , 45 ( 10 ): 3776 - 3785 . (in Chinese)

LUO J B , LEI W T , HOU F F , et al . GPR B-scan image denoising via multi-scale convolutional autoencoder with data augmentation [J ] . Electronics , 2021 , 10 ( 11 ): 1269 .

LEI W T , LUO J B , HOU F F , et al . Underground cylindrical objects detection and diameter identification in GPR B-scans via the CNN-LSTM framework [J ] . Electronics , 2020 , 9 ( 11 ): 1804 .

MA Y L , LEI W T , PANG Z B , et al . Rebar clutter suppression and road defects localization in GPR B-scan images based on SuppRebar-GAN and EC-Yolov7 networks [J ] . IEEE Transactions on Geoscience and Remote Sensing , 2024 , 62 : 1 - 14 .

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 . Overview of image recognition technology of ground penetrating radar for hyperbolic shape [J ] . Acta Electronica Sinica , 2019 , 47 ( 6 ): 1366 - 1372 . (in Chinese)

杨忠委 , 郭聪隆 , 孙浩然 , 等 . 基于波场互相关的探地雷达快速自聚焦成像 [J ] . 信号处理 , 2021 , 37 ( 9 ): 1663 - 1668 .

YANG Z W , GUO C L , SUN H R , et al . A fast-autofocusing approach for ground penetrating radar imaging based on correlation of wavefield [J ] . Journal of Signal Processing , 2021 , 37 ( 9 ): 1663 - 1668 . (in Chinese)

FENG D S , LI T , LI G C , et al . Reverse time migration of GPR data based on accurate velocity estimation and artifacts removal using total variation de-noising [J ] . Journal of Applied Geophysics , 2022 , 198 : 104563 .

LI B X , MA Y H , CHU L N , et al . A backprojection-based autofocus imaging method for circular synthetic aperture radar [J ] . Electronics , 2023 , 12 ( 12 ): 2561 .

雷文太 , 隋浩 , 辛常乐 , 等 . 一种探地雷达自聚焦后向投影成像方法及装置 : 202311255661.4 [P ] . 2023-12-29 .

LEI W T , SUI H , XIN C L , et al . A Ground Penetrating Radar Self-Focusing Back-Projection Imaging Method and Device : 202311255661.4 [P ] . 2023-12-29 .

LEI W T , ZENG S , ZHAO J , et al . An improved back projection imaging algorithm for subsurface target detection [J ] . Turkish Journal of Electrical Engineering & Computer Sciences , 2013 , 21 : 1820 - 1826 .

雷文太 , 隋浩 , 毛凌青 , 等 . 一种探地雷达后向投影成像方法及系统 : CN114966560A [P ] . 2022-08-30 .

LEI W T , SUI H , MAO L Q , et al . A Ground Penetrating Radar Back-Projection Imaging Method and System : CN114966560A [P ] . 2022-08-30 .

ZHOU L , SU Y . A GPR imaging algorithm with artifacts suppression [C ] // Proceedings of the XIII Internarional Conference on Ground Penetrating Radar . Piscataway : IEEE , 2010 : 1 - 7 .

BURKHOLDER R J , BROWNE K E . Coherence factor enhancement of through-wall radar images [J ] . IEEE Antennas and Wireless Propagation Letters , 2010 , 9 : 842 - 845 .

GE Z , LIU S T , WANG F , et al . Yolox: Exceeding yolo series in 2021 [EB/OL ] .( 2021-08-06 )[ 2023-12-07 ] . http://arxiv.org/abs/2107.08430v2 http://arxiv.org/abs/2107.08430v2 .

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 .

LI J X , CHEN X P , XU H , et al . Artifacts suppression using correlation-weighted back projection imaging algorithm for chaotic GPR [J ] . IEEE Geoscience and Remote Sensing Letters , 2022 , 19 : 3507305 .

ESMAEILI NAJAFABADI H , ATAEI M , SABAHI M F . Chebyshev chaotic polynomials for MIMO radar waveform generation [J ] . IET Radar , Sonar & Navigation, 2017 , 11 ( 2 ): 330 - 340 .

：作者简介：

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

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

Variable Horizon Multi-Directional Scanning Method for Time Series Anomaly Detection

Differentially Private with Sparse and Smooth Self-Distillation

Operator Fusion Method and Hardware Architecture Design Based on Non-Standard Operators

Related Author

LEI Wen-tai

WANG Hui

OUYANG Shan

LIAO Ke-fei

JIN Liang-nian

HUANG Yu-zhe

GUAN Yong-yuan

WEI Song-jie

Related Institution

School of Information and Communication, Guilin University of Electronic Technology

School of Artificial Intelligence Hezhou University

School of Information and Communication Guilin University of Electronic Technology Guilin Guangxi China

School of Artificial Intelligence Hezhou University Hezhou Guangxi China

School of Computer Science and Engineering, School of Cyber Science and Engineering, Nanjing University of Science and Technology

⁰