探地雷达杂波抑制技术研究综述：机理、方法与挑战

雷文太; 王以明; 钟继卫; 徐齐国; 姜玉印; 李成

doi:10.11999/JEIT250524

探地雷达杂波抑制技术研究综述：机理、方法与挑战

doi: 10.11999/JEIT250524 cstr: 32379.14.JEIT250524

雷文太^{1, 2, ,},
王以明²,
钟继卫^{1, 5},
徐齐国³,
姜玉印^{1, 4},
李成^{1, 4}

1.
桥梁智能与绿色建造全国重点实验室武汉 430050
2.
中南大学电子信息学院长沙 410000
3.
中南大学计算机学院长沙 410000
4.
中铁大桥科学研究院有限公司武汉 430050
5.
中铁大桥局集团有限公司武汉 430050

基金项目: 桥梁智能与绿色建造全国重点实验室开放研究基金项目(BIGCSKL24-09-GF)，西藏自治区科技计划项目(XZ202501ZY0005)，中国中铁股份有限公司科技研究开发计划重大专项(2023-专项-02)

详细信息

作者简介:
雷文太：男，教授，博士生导师，研究方向为探地雷达系统集成和信号处理

王以明：男，硕士生，研究方向为探地雷达，深度学习

钟继卫：男，教授级高工，研究方向为桥梁结构健康监测

徐齐国：男，博士生，研究方向为探地雷达，深度学习，图像处理

姜玉印：男，助理工程师，研究方向为桥梁结构健康监测

李成：男，高级工程师，研究方向为桥梁安全监测、智慧运维与防灾减灾

通讯作者:
雷文太　leiwentai@csu.edu.cn

中图分类号: TN957.51
计量
- 文章访问数: 14
- HTML全文浏览量: 7
- PDF下载量: 1
- 被引次数: 0
出版历程
- 收稿日期: 2025-06-09
- 修回日期: 2025-09-29
- 网络出版日期: 2025-10-11

A Review of Clutter Suppression Techniques in Ground Penetrating Radar: Mechanisms, Methods, and Challenges

LEI Wentai^{1, 2
, ,},
WANG Yiming²,
ZHONG Jiwei^{1, 5},
XU Qiguo³,
JIANG Yuyin^{1, 4},
LI Cheng^{1, 4}

1.
State Key Laboratory of Bridge Intelligent and Green Construction, Wuhan 430050, China
2.
Department of Electronic Information, Central South University, Changsha 410000, China
3.
Department of Computer Science and Engineering, Central South University, Changsha 410000, China
4.
China Railway Bridge Science Research Institute, Ltd., Wuhan 430050, China
5.
China Railway Construction Bridge Engineering Bureau Group Co., Ltd., Wuhan 430050, China

Funds: The Open Research Fund Project of State Key Laboratory of Bridge Intelligent and Green Construction(BIGCSKL24-09-GF) , The Science and Technology projects of Xizang Autonomous Region, China(XZ202501ZY0005) ,The Major Special Project of Science and Technology Research and Development of China Railway Group limited (2023-Special Project-02)

摘要

摘要: 探地雷达因其无损、快速、高分辨的检测能力广泛应用于城市地下空间、公路铁路轨道交通、地球物理探测和军事等领域。然而，由于收发天线的宽频带和宽波束特性，以及复杂探测场景中的感兴趣目标受到的非均匀背景媒质和临近目标的影响，探地雷达回波中无可避免地包含了相当多成分的杂波信号。杂波信号与感兴趣目标的回波信号在时频域部分重叠，对其产生干扰，严重影响了后续的目标定位、成像、参数估计、结构反演和分类识别等任务。在探地雷达数据处理中，通常需要先进行杂波抑制工作。该文是对冲激脉冲体制探地雷达杂波抑制方法的综述，分析了冲激脉冲体制探地雷达的各典型杂波的成因和杂波抑制效果评估的定量指标，对基于信号模型的杂波抑制和基于神经网络模型的杂波抑制这两大类方法进行了系统的分析和阐述。最后，讨论了将深度学习技术应用于探地雷达杂波抑制时面临的挑战和未来的发展方向。
- 探地雷达 /
- 杂波抑制 /
- 深度学习 /
- 性能指标 /
- 综述
Abstract: Significance Ground Penetrating Radar (GPR) is a widely adopted non-destructive subsurface detection technology, extensively applied in urban subsurface exploration, transportation infrastructure monitoring, geophysical surveys, and military operations. It is employed to detect underground pipelines, structural foundations, road voids, and concealed defects in roadbeds, railway tracks, and tunnels, as well as shallow geological formations and military targets such as unexploded ordnance. However, the presence of clutter—unwanted signals including direct coupling waves, ground reflections, and non-target echoes—severely degrades GPR data quality and complicates target detection, localization, imaging, and parameter estimation. Effective clutter suppression is therefore essential to enhance the accuracy and reliability of GPR data interpretation, making it a central research focus in improving GPR performance across diverse application domains. Progress Significant progress has been achieved in GPR clutter suppression, largely through two main approaches: signal model-based and neural network-based methods. Signal model-based techniques, such as time–frequency analysis, subspace decomposition, and dictionary learning, rely on physical modeling to distinguish clutter from target signals. These methods provide clear interpretability but are limited in addressing complex and non-linear clutter patterns. Neural network-based methods, employing architectures such as Convolutional Neural Networks, U-Net, and Generative Adversarial Networks, are more effective in capturing non-linear features through data-driven learning. Recent advances, including multi-scale convolutional autoencoders, attention mechanisms, and hybrid models, have further enhanced clutter suppression under challenging conditions. Quantitative metrics such as Mean Squared Error, Peak Signal-to-Noise Ratio, and Structural Similarity Index are commonly used for performance evaluation, often complemented by qualitative visual assessment. Conclusion The complexity and diversity of GPR clutter, originating from direct coupling, ground reflections, equipment imperfections, non-uniform media, and non-target scatterers, demand robust suppression strategies. Signal model-based methods provide strong theoretical foundations but are constrained by simplified assumptions, whereas neural network-based approaches offer greater adaptability at the expense of large data requirements and high computational cost. Hybrid approaches that integrate the strengths of both paradigms show considerable potential in addressing complex clutter scenarios. The selection of evaluation metrics plays a pivotal role in algorithm design, with quantitative measures offering objective assessment and qualitative analyses providing intuitive validation. Despite recent advances, significant challenges remain in suppressing non-linear clutter, enabling real-time processing, and reducing reliance on labeled data. Prospect Future research in GPR clutter suppression is likely to emphasize integrating the strengths of signal model-based and neural network-based methods to develop robust and adaptive solutions. Real-time processing and online learning will be prioritized to meet the requirements of dynamic applications. Self-supervised and unsupervised learning approaches are expected to reduce dependence on costly labeled datasets and improve model adaptability. Cross-task learning and multi-modal fusion, combining data from multiple sensors or frequencies, are expected to enhance robustness and precision. Furthermore, deeper integration of physical principles, including electromagnetic wave propagation and media properties, into algorithm design is expected to improve suppression accuracy and computational efficiency, advancing the development of more intelligent and effective GPR systems.
- Ground Penetrating Radar (GPR) /
- Clutter suppression /
- Deep learning /
- Performance metrics /
- Review

HTML全文

图 1 GPR对地探测原理示意图

下载: 全尺寸图片幻灯片

图 2 GPR典型杂波

下载: 全尺寸图片幻灯片

图 3 原始数据到图像数据的转换示例图

下载: 全尺寸图片幻灯片

图 4 CB-Net子空间投影

下载: 全尺寸图片幻灯片

图 5 SuppRebar-GAN网络结构

下载: 全尺寸图片幻灯片

表 1 基于编码-解码结构神经网络算法的对比一览表

分类	方法	时间	技术路线及评价
AE	MCAE	2021	设计了多尺度卷积核和WGAN网络，与CAE方法相比提高了PSNR。
	RAE	2022	结合l₁正则化捕捉稀疏分量和自编码器的非线性表示能力，优于RPCA的处理性能。
	DAE	2024	将粗糙表面杂波抑制问题转化为异常检测问题，仅需要少量GPR数据，但需要人工选择粗糙表面区域。
	DCAE	2022	采用了更深层次的卷积，在异构土壤背景模拟数据上表现出良好的性能。
U-Net	CR-Net	2022	将RDBs集成在U-Net中，采用MAE结合MS-SSIM的混合损失函数，获得了更好的杂波抑制能力性能。
	CI-Net	2023	在U²-Net中集成了残差模块、注意力机制和自适应权值学习模块，在地下管道探测场景中有更好的处理性能。
	CB-Net	2024	采用随机骨料模型构建了异质混凝土数据集，将SPA与数据驱动方法相结合，解决了传统子空间方法在目标分量选择上的困难。
	MIS-SE-Net	2024	将空间注意力机制引入到U-Net中，采用MAE感知损失，具有较好的抑制互扰波和信号增强的能力。
	U-Net- SAM-CAM	2024	将CAM和SAM引入到U-Net中，采用域自适应技术对已训练模型进行微调，提高对开放数据集的泛化能力。
	多阶段级联U-Net	2024	采取级联架构和联合训练的策略，引入指数加权移动平均方法来平滑历史损失，实现了从C-scan中重建墙体内弱目标。

下载: 导出CSV

表 2 基于生成-判别结构神经网络算法的对比一览表

分类	方法	时间	技术路线及评价
GAN	Declutter-GAN	2022	将cGAN应用于GPR杂波抑制，需要配对的无杂波目标数据和含杂波目标数据，将采集的背景数据与仿真计算的目标数据进行相加来制作数据集。
	DR-GAN	2023	不需要成对的匹配数据，利用解纠缠表示的思想来提取GPR图像的目标特征和杂波特征。
	Wavelet-GAN	2024	利用离散小波变换将GPR数据分为低频、中频和高频分量，设计了3个生成器对各频段数据进行重构，加快了训练速度并增强了泛化能力。
CycleGAN	RCE-GAN	2022	设计了两对生成器和判别器，在生成器中引入了注意力机制和膨胀中心模块，有效提高了对浅层钢筋网杂波的抑制性能。
	SuppRebar-GAN	2024	在CycleGAN中集成了CBAM，设计了RE模块和EC-Yolov7，表现出良好的钢筋网回波抑制能力和较好的泛化能力。
	REN-GAN	2024	采用感知一致性损失增强了损失函数，通过两种特征编码器来保证钢筋杂波抑制前后异常目标回波信号的一致性，提高钢筋网下空洞缺陷的识别精度。
	2C-GAN	2025	设计了R5模块，采用铰链损失来增强网络训练的稳定性，增强了对实测数据中杂波的抑制能力。
	UMDA-net	2025	生成器中融合了通道注意力、空间注意力和多头自注意力机制，可以同时关注局部特征和全局语义信息。

下载: 导出CSV

表 3 基于其他结构神经网络算法的对比一览表

方法	时间	网络原型来源	技术路线及评价
灵活残差BiSeNetV2	2023	IJCV	设计了灵活残差模块，根据不同任务所需的通道数和参数自适应选择卷积核大小，设计了一个高效通道注意力机制来提取通道间依赖关系。
RefineNet	2024	CVPR	设计了RefintNet杂波抑制网络，采用基于全变分正则化的逆时偏移成像来对杂波抑制性能进行分析验证。
VAE-RefineNet	2024	ICLR CVPR	采用VAE算法来抑制地下分层结构对目标回波的影响，采用RefineNet抑制杂波，通过成像处理验证上述算法的有效性。
VAE-ResNet	2024	ICLR CVPR	利用VAE初级网络进行初步杂波抑制，集成残差特征蒸馏块来增强网络特征提取能力，性能优于ResNet。
受约束Diffusion	2024	NeurIPS	通过低频B-scan作为约束条件来限制高分辨率图像的分布，克服了经典扩散模型在数据生成过程中易受到当前噪声样本迭代的影响问题。
DC-ViTs	2024	ICLR	设计了更善于捕捉局部上下文的卷积来替代经典ViT中的多层感知机，杂波抑制性能优于DCAE和CR-Net。
RCAN	2024	ECCV	采用了RCAN网络，构建了双层钢筋网场景下典型病害的数据集，开展了模拟仿真和实测数据的分析验证。

下载: 导出CSV

参考文献(73)

[1]	JOL H M, 雷文太, 童孝忠, 周旸, 等译. 探地雷达理论与应用[M]. 北京: 电子工业出版社, 2011. (查阅网上资料, 未找到本条文献页码信息, 请补充). JOL H M, LEI Wentai, TONG Xiaozhong, ZHOU Yang, et al. translation. Ground Penetrating Radar: Theory and Application[M]. Beijing: Publishing House of Electronics Industry, 2011.
[2]	XU Qiguo, GAO Hang, PANG Zebang, et al. GPR Bscan change detection network for structural defect evolution[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5110815. doi: 10.1109/Tgrs.2024.3480122.
[3]	SHI Xinghua, ZHANG Anxue, HAN Guoqing, et al. The design of 3-D ground-penetrating radar system for bridge inspection[J]. IEEE Sensors Journal, 2024, 24(13): 21276–21285. doi: 10.1109/Jsen.2024.3396467.
[4]	ZHOU Haoqiu, FENG Xuan, DONG Zejun, et al. Predictive rotation fusion: A physical model-based fusion method for full-polarimetric GPR data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 5103120. doi: 10.1109/Tgrs.2025.3550887.
[5]	ARENDT B, SCHNEIDER M, MAYER W, et al. Environmental influences on the detection of buried objects with a ground-penetrating radar[J]. Remote Sensing, 2024, 16(6): 1011. doi: 10.3390/rs16061011.
[6]	刘海, 黄肇刚, 岳云鹏, 等. 地下管线渗漏环境下探地雷达信号特征分析[J]. 电子与信息学报, 2022, 44(4): 1257–1264. doi: 10.11999/JEIT211213. LIU Hai, HUANG Zhaogang, YUE Yunpeng, et al. Characteristics analysis of ground penetrating radar signals for groundwater pipe leakage environment[J]. Journal of Electronics & Information Technology, 2022, 44(4): 1257–1264. doi: 10.11999/JEIT211213.
[7]	LIU Hai, YUE Yunpeng, LIAN Yunlong, et al. Reverse-time migration of GPR data for imaging cavities behind a reinforced shield tunnel[J]. Tunnelling and Underground Space Technology, 2024, 146: 105649. doi: 10.1016/j.tust.2024.105649.
[8]	倪志康, 叶盛波, 史城, 等. 一种深度学习辅助的探地雷达定位方法[J]. 电子与信息学报, 2022, 44(4): 1265–1273. doi: 10.11999/JEIT211072. NI Zhikang, YE Shengbo, SHI Cheng, et al. A deep learning assisted ground penetrating radar localization method[J]. Journal of Electronics & Information Technology, 2022, 44(4): 1265–1273. doi: 10.11999/JEIT211072.
[9]	QIAO Hanqing, ZHANG Minghe, and BANO M. Harris hawks optimization for soil water content estimation in ground-penetrating radar waveform inversion[J]. Remote Sensing, 2025, 17(8): 1436. doi: 10.3390/rs17081436.
[10]	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 Wentai, SUI Hao, JIANG Hejun, 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.
[11]	WEI Chuyang, ZHOU Xiren, LIU Shikang, et al. Enhanced anomaly detection in GPR data by combining spatial and dynamic information[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5112010. doi: 10.1109/Tgrs.2024.3504715.
[12]	WARREN C, GIANNOPOULOS A, and GIANNAKIS I. gprMax: Open source software to simulate electromagnetic wave propagation for ground penetrating radar[J]. Computer Physics Communications, 2016, 209: 163–170. doi: 10.1016/j.cpc.2016.08.020.
[13]	曾波, 刘硕, 杨军, 等. 地表起伏对地下管线GPR探测的影响[J]. 物探与化探, 2023, 47(4): 1064–1070. doi: 10.11720/wtyht.2023.1516. ZENG Bo, LIU Shuo, YANG Jun, et al. Influence of surface undulations on GPR-based underground pipeline detection[J]. Geophysical and Geochemical Exploration, 2023, 47(4): 1064–1070. doi: 10.11720/wtyht.2023.1516.
[14]	王磊. 探地雷达抑制射频干扰技术研究[D]. [硕士论文], 国防科学技术大学, 2009. WANG Lei. Radio frequency interference suppressing of ground penetrating radar[D]. [Master dissertation], National University of Defense Technology, 2009.
[15]	WANG Zhou, BOVIK A C, SHEIKH H R, et al. Image quality assessment: From error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4): 600–612. doi: 10.1109/Tip.2003.819861.
[16]	WANG Z, SIMONCELLI E P, and BOVIK A C. Multiscale structural similarity for image quality assessment[C]. The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, Pacific Grove, USA, 2003. doi: 10.1109/ACSSC.2003.1292216.
[17]	KIM H S, SEOL J, LEE J Y, et al. Style harmonization of panoramic radiography using deep learning[J]. Oral Radiology, 2025, 41(1): 111–119. doi: 10.1007/s11282-024-00782-2.
[18]	ZHANG Lin, ZHANG Lei, MOU Xuanqin, et al. FSIM: A feature similarity index for image quality assessment[J]. IEEE Transactions on Image Processing, 2011, 20(8): 2378–2386. doi: 10.1109/Tip.2011.2109730.
[19]	ZHANG Hua, DAI Qianwei, FENG Deshan, et al. ROI-binarized hyperbolic region segmentation and characterization by using deep residual convolutional neural network with skip connection for GPR imaging[J]. Applied Sciences, 2024, 14(11): 4689. doi: 10.3390/app14114689.
[20]	SALIMANS T, GOODFELLOW I, ZAREMBA W, et al. Improved techniques for training GANs[C]. Proceedings of the 30th International Conference on Neural Information Processing Systems, Barcelona, Spain, 2016.
[21]	HEUSEL M, RAMSAUER H, UNTERTHINER T, et al. GANs trained by a two time-scale update rule converge to a local Nash equilibrium[C]. Proceedings of the 31st International Conference on Neural Information Processing Systems, Long Beach, USA, 2017.
[22]	ZOUBIR A M, CHANT I J, BROWN C L, et al. Signal processing techniques for landmine detection using impulse ground penetrating radar[J]. IEEE Sensors Journal, 2002, 2(1): 41–51. doi: 10.1109/7361.987060.
[23]	RASHED M and HARBI H. Background matrix subtraction (BMS): A novel background removal algorithm for GPR data[J]. Journal of Applied Geophysics, 2014, 106: 154–163. doi: 10.1016/j.jappgeo.2014.04.022.
[24]	BAI Hao and SINFIELD J V. Improved background and clutter reduction for pipe detection under pavement using ground penetrating radar (GPR)[J]. Journal of Applied Geophysics, 2020, 172: 103918. doi: 10.1016/j.jappgeo.2019.103918.
[25]	WU Shuxian, WANG Longxiang, ZENG Xiaozhen, et al. UAV-mounted GPR for object detection based on cross-correlation background subtraction method[J]. Remote Sensing, 2022, 14(20): 5132. doi: 10.3390/rs14205132.
[26]	HAYASHI N and SATO M. F–k filter designs to suppress direct waves for bistatic ground penetrating radar[J]. IEEE Transactions on Geoscience and Remote Sensing, 2010, 48(3): 1433–1444. doi: 10.1109/TGRS.2009.2032536.
[27]	KANG M S and AN Y K. Frequency-wavenumber analysis of deep learning-based super resolution 3D GPR images[J]. Remote Sensing, 2020, 12(18): 3056. doi: 10.3390/rs12183056.
[28]	卢丹平, 沈绍祥, 李玉喜, 等. 一种基于改进f-k滤波的编码雷达信号去噪方法[J]. 电波科学学报, 2023, 38(5): 861–869. doi: 10.12265/j.cjors.2022183. LU Danping, SHEN Shaoxiang, LI Yuxi, et al. A denoising method for coded radar signals based on improved f-k filtering[J]. Chinese Journal of Radio Science, 2023, 38(5): 861–869. doi: 10.12265/j.cjors.2022183.
[29]	KONG Qingyang, YE Shengbo, LIANG Xiao, et al. A clutter removal method based on the F-K domain for ground-penetrating radar in complex scenarios[J]. Remote Sensing, 2024, 16(6): 935. doi: 10.3390/rs16060935.
[30]	GE Junkai, SUN Huaifeng, LIU Rui, et al. Removing rebar clutter through iterative F-k migration in GPR data[J]. IEEE Geoscience and Remote Sensing Letters, 2025, 22: 3500805. doi: 10.1109/Lgrs.2024.3515956.
[31]	SHI Xianxin and YANG Qiufen. Suppressing the direct wave noise in GPR data via the 2-D physical wavelet frame[C]. 2011 International Conference on Transportation, Mechanical, and Electrical Engineering (TMEE), Changchun, China, 2011: 1161–1164. doi: 10.1109/TMEE.2011.6199411.
[32]	WANG Xiannan and LIU Sixin. Noise suppressing and direct wave arrivals removal in GPR data based on Shearlet transform[J]. Signal Processing, 2017, 132: 227–242. doi: 10.1016/j.sigpro.2016.05.007.
[33]	HE Xingkun, LI Yujin, WANG Can, et al. Separate removal of random noise and clutter in GPR images based on Self2Self and NSST[J]. International Journal of Remote Sensing, 2022, 43(9): 3490–3508. doi: 10.1080/01431161.2022.2096420.
[34]	TANG Xiaosong, YANG Feng, QIAO Xu, et al. A ground-penetrating radar clutter suppression algorithm integrating signal processing and image fusion[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5936618. doi: 10.1109/Tgrs.2024.3508813.
[35]	CHEN Gaoxiang, FU Liyun, CHEN Kanfu, et al. Adaptive ground clutter reduction in ground-penetrating radar data based on principal component analysis[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(6): 3271–3282. doi: 10.1109/tgrs.2018.2882912.
[36]	雷文太, 梁琼, 谭倩颖. 基于自动反相校正和峰度值比较的探地雷达回波信号去噪方法[J]. 雷达学报, 2018, 7(3): 294–302. doi: 10.12000/JR17113. LEI Wentai, LIANG Qiong, and TAN Qianying. A new ground penetrating radar signal denoising algorithm based on automatic reversed-phase correction and kurtosis value comparison[J]. Journal of Radars, 2018, 7(3): 294–302. doi: 10.12000/JR17113.
[37]	CANDÈS E J, LI X D, MA Y, et al. Robust principal component analysis?[J]. Journal of the ACM, 2011, 58(3): 11. doi: 10.1145/1970392.1970395.
[38]	SONG Xiaoji, XIANG Deliang, ZHOU Kai, et al. Improving RPCA-based clutter suppression in GPR detection of antipersonnel mines[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(8): 1338–1342. doi: 10.1109/lgrs.2017.2711251.
[39]	SONG Xiaoji, XIANG Deliang, ZHOU Kai, et al. Fast prescreening for GPR antipersonnel mine detection via go decomposition[J]. IEEE Geoscience and Remote Sensing Letters, 2019, 16(1): 15–19. doi: 10.1109/lgrs.2018.2866331.
[40]	KUMLU D and ERER I. Improved clutter removal in GPR by robust nonnegative matrix factorization[J]. IEEE Geoscience and Remote Sensing Letters, 2020, 17(6): 958–962. doi: 10.1109/lgrs.2019.2937749.
[41]	LIU Li, WU Zezhou, XU Hang, et al. GPR clutter removal based on factor group-sparse regularization[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 3509305. doi: 10.1109/Lgrs.2021.3122262.
[42]	LIU Li, SONG Chenyan, WU Zezhou, et al. GPR clutter removal based on weighted nuclear norm minimization for nonparallel cases[J]. Sensors, 2023, 23(11): 5078. doi: 10.3390/s23115078.
[43]	ZHAO Yi, YANG Xiaopeng, QU Xiaodong, et al. Clutter removal method for GPR based on low-rank and sparse decomposition with total variation regularization[J]. IEEE Geoscience and Remote Sensing Letters, 2023, 20: 3502605. doi: 10.1109/lgrs.2023.3250717.
[44]	TEMLIOGLU E and ERER I. Clutter removal in ground-penetrating radar images using morphological component analysis[J]. IEEE Geoscience and Remote Sensing Letters, 2016, 13(12): 1802–1806. doi: 10.1109/Lgrs.2016.2612582.
[45]	ZHOU Yanhui and CHEN Wenchao. MCA-based clutter reduction from migrated GPR data of shallowly buried point target[J]. IEEE Transactions on Geoscience and Remote Sensing, 2019, 57(1): 432–448. doi: 10.1109/Tgrs.2018.2855728.
[46]	NI Zhikang, PAN Jun, SHI Cheng, et al. DL-based clutter removal in migrated GPR data for detection of buried target[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 3507205. doi: 10.1109/Lgrs.2021.3089246.
[47]	FENG Deshan, LIU Shuo, YANG Jun, et al. The noise attenuation and stochastic clutter removal of ground penetrating radar based on the K-SVD dictionary learning[J]. IEEE Access, 2021, 9: 74879–74890. doi: 10.1109/Access.2021.3081349.
[48]	FENG Deshan, HE Li, WANG Xun, et al. Efficient denoising of multidimensional GPR data based on fast dictionary learning[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 5221–5233. doi: 10.1109/Jstars.2024.3366397.
[49]	LUO Jiabin, LEI Wentai, HOU Feifei, et al. GPR B-scan image denoising via multi-scale convolutional autoencoder with data augmentation[J]. Electronics, 2021, 10(11): 1269. doi: 10.3390/electronics10111269.
[50]	NI Zhikang, YE Shengbo, SHI Cheng, et al. Clutter suppression in GPR B-scan images using robust autoencoder[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 3500705. doi: 10.1109/Lgrs.2020.3026007.
[51]	ZHANG Yan, DIAO Enmao, HUSTON D, et al. A data-efficient deep learning method for rough surface clutter reduction in GPR images[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5104610. doi: 10.1109/tgrs.2024.3382545.
[52]	TEMLIOGLU E and ERER I. A novel convolutional autoencoder-based clutter removal method for buried threat detection in ground-penetrating radar[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5103313. doi: 10.1109/tgrs.2021.3098122.
[53]	SUN Haihan, CHENG Weixia, and FAN Zheng. Learning to remove clutter in real-world GPR images using hybrid data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2022, 60: 5113714. doi: 10.1109/Tgrs.2022.3176029.
[54]	YANG Gexing, YUAN Da, XU Tianjia, et al. An adaptive clutter-immune method for pipeline detection with GPR[J]. IEEE Sensors Journal, 2023, 23(19): 22984–22997. doi: 10.1109/Jsen.2023.3305681.
[55]	CAO Yanjie, YANG Xiaopeng, GUO Conglong, et al. Subspace projection attention network for GPR heterogeneous clutter removal[J]. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2024, 17: 3917–3926. doi: 10.1109/jstars.2024.3355213.
[56]	LEI Wentai, TAN Xin, LUO Chaopeng, et al. Mutual interference suppression and signal enhancement method for ground-penetrating radar based on deep learning[J]. Electronics, 2024, 13(23): 4722. doi: 10.3390/electronics13234722.
[57]	PANDA S L, SAHOO U K, MAITI S, et al. An attention U-Net-based improved clutter suppression in GPR images[J]. IEEE Transactions on Instrumentation and Measurement, 2024, 73: 8502511. doi: 10.1109/tim.2024.3378267.
[58]	兰天, 盛世文, 孙熙韬, 等. 探地雷达多阶段级联U-Net墙内小目标三维重建方法[J]. 雷达学报(中英文), 2024, 13(6): 1184–1201. doi: 10.12000/JR24163. LAN Tian, SHENG Shiwen, SUN Xitao, et al. Three-dimensional reconstruction method for detecting small targets within walls based on a multistage cascade U-Net approach using ground penetrating radars[J]. Journal of Radars, 2024, 13(6): 1184–1201. doi: 10.12000/JR24163.
[59]	NI Zhikang, SHI Cheng, PAN Jun, et al. Declutter-GAN: GPR B-scan data clutter removal using conditional generative adversarial nets[J]. IEEE Geoscience and Remote Sensing Letters, 2022, 19: 4023105. doi: 10.1109/lgrs.2022.3159788.
[60]	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. doi: 10.11999/JEIT221072. LEI Wentai, MAO Lingqing, PANG Zebang, 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. doi: 10.11999/JEIT221072.
[61]	GE Junkai, SUN Huaifeng, SHAO Wei, et al. Wavelet-GAN: A GPR noise and clutter removal method based on small real datasets[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5918214. doi: 10.1109/Tgrs.2024.3410277.
[62]	WANG Yuanzheng, QIN Hui, TANG Yu, et al. RCE-GAN: A rebar clutter elimination network to improve tunnel lining void detection from GPR images[J]. Remote Sensing, 2022, 14(2): 251. doi: 10.3390/rs14020251.
[63]	MA Yalou, LEI Wentai, PANG Zebang, 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. doi: 10.1109/tgrs.2024.3373025.
[64]	REN Qiuyang, WANG Yanhui, XU Jie, et al. REN-GAN: Generative adversarial network-driven rebar clutter elimination network in GPR image for tunnel defect identification[J]. Expert Systems with Applications, 2024, 255: 124395. doi: 10.1016/j.eswa.2024.124395.
[65]	XIONG Hongqiang, LI Jing, LIU Tieyu, et al. Catenary clutter elimination network for railway tunnel ground penetrating radar data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2025, 63: 5905614. doi: 10.1109/Tgrs.2025.3533609.
[66]	GUO Zhishun, GAO Yesheng, SHI Mengyang, et al. Unsupervised multiattention domain adaptive decluttering model for metal pipe targets in GPR images[J]. IEEE Sensors Journal, 2025, 25(10): 17503–17513. doi: 10.1109/Jsen.2025.3553381.
[67]	LI Boyang, YUAN Da, YANG Gexing, et al. Flexibility-residual BiSeNetV2 for GPR image decluttering[J]. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61: 5106812. doi: 10.1109/Tgrs.2023.3296722.
[68]	LEI Jianwei, FANG Hongyuan, ZHU Yining, et al. GPR detection localization of underground structures based on deep learning and reverse time migration[J]. Ndt & E International, 2024, 143: 103043. doi: 10.1016/j.ndteint.2024.103043.
[69]	戴前伟, 熊泽平, 丁浩, 等. 基于VAE-RefineNet算法流程的GPR杂波抑制和目标成像[J]. 地球物理学进展, 2023, 38(5): 2250–2262. doi: 10.6038/pg2023GG0645. DAI Qianwei, XIONG Zeping, DING Hao, et al. Clutter suppression of GPR B-scan and target imaging based on VAE-RefineNet algorithm process[J]. Progress in Geophysics, 2023, 38(5): 2250–2262. doi: 10.6038/pg2023GG0645.
[70]	WANG Xiangyu and LIU Hai. VAE-ResNet cascade network: An advanced algorithm for stochastic clutter suppression in ground penetrating radar data[J]. IEEE Transactions on Geoscience and Remote Sensing, 2024, 62: 5913212. doi: 10.1109/Tgrs.2024.3394750.
[71]	LAN Tian, LUO Xi, YANG Xiaopeng, et al. A constrained diffusion model for deep GPR image enhancement[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 3003505. doi: 10.1109/Lgrs.2024.3433481.
[72]	KAYACAN Y E and ERER I. A vision-transformer-based approach to clutter removal in GPR: DC-ViT[J]. IEEE Geoscience and Remote Sensing Letters, 2024, 21: 3505105. doi: 10.1109/Lgrs.2024.3385694.
[73]	WANG Xiangyu, LIU Hai, MENG Xu, et al. Enhanced imaging of concealed defects behind concrete linings using residual channel attention network for rebar clutter suppression[J]. Automation in Construction, 2024, 166: 105574. doi: 10.1016/j.autcon.2024.105574.