基于非负矩阵分解的GPR高频杂波抑制

doi:10.3778/j.issn.1002-8331.2008-0285

摘要/Abstract

摘要： 针对探地雷达（ground penetrating radar，GPR）采集数据时会产生高频杂波影响地下目标自动识别的问题。提出了一种基于变分贝叶斯的GPR图像非负矩阵分解方法（probability nonnegative matrix factorization，PNMF）。该方法使用变分贝叶斯模型对非负矩阵分解的基矩阵和系数矩阵进行近似推理，得到杂波成分的低秩矩阵表示，进而将杂波从图像中分离出来。实验过程采用模拟和实测数据进行对比分析，通过信噪比和视觉质量结果验证了PNMF对杂波有较好的抑制作用，具有较好的鲁棒性。

关键词: 探地雷达, 高频杂波, 变分贝叶斯, 非负矩阵分解

Abstract: Aiming at the problem of ground penetrating radar（ground penetrating radar, GPR） collecting data, high-frequency clutter will interfere with the automatic identification of underground targets. A nonnegative matrix decomposition method（probability nonnegative matrix factorization, PNMF） for GPR images based on variational bayes is proposed. This method uses a variational bayes model to decompose the base matrix and coefficient matrix of the nonnegative matrix. It performs approximate reasoning to obtain the low-rank matrix component representation of the clutter, and then separates the clutter from the image. In the experimental process, simulation and measured data are used for comparative analysis. The signal-to-noise ratio and visual quality results verify that PNMF has a good suppression effect on clutter and has good robustness.

Key words: ground penetrating radar（GPR）, high-frequency clutter, variational Bayes, nonnegative matrix factorization

苗翠, 原达, 王冬雨, 李文生. 基于非负矩阵分解的GPR高频杂波抑制[J]. 计算机工程与应用, 2022, 58(1): 241-247.

MIAO Cui, YUAN Da, WANG Dongyu, LI Wensheng. GPR High-Frequency Clutter Suppression Based on Nonnegative Matrix Factorization[J]. Computer Engineering and Applications, 2022, 58(1): 241-247.

参考文献

[1] BARONE P M，FERRARA C.The past beneath the present：GPR as a remote sensor in archaeology and cultural heritage management（Conference Presentation）[C]//Proceedings of Earth Resources and Environmental Remote Sensing/GIS Applications VII，2018.
[2] MINET J，BOGAERT P，VANCLOOSTER M，et al.Validation of ground penetrating radar full-waveform inversion for field scale soil moisture mapping[J].Journal of Hydro-logy，2012，424：112-123.
[3] LAI W W L，DEROBERT X，ANNAN P.A review of ground penetrating radar application in civil engineering：A 30-year journey from locating and testing to imaging and diagnosis[J].Ndt & E International，2018，96：58-78.
[4] SHEBALKOVA L V，MARKOV M A，ROMODIN V B.Broadband antenna for ground penetratingradar application in soil[C]//Proceedings of IOP Conference Series：Earth and Environmental Science，2018.
[5] TEBCHRANY E.Apports de l’ultra large bande et de la diversité de polarisation du radar desol pour l’auscultation des ouvrages du géniecivil[D].Paris Est，2015.
[6] CHEN G，FU L，CHEN K，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.
[7] SONG X，XIANG D，ZHOU K，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.
[8] LIU C，SONG C，LU Q.Random noise de-noising and direct wave eliminating based on SVD method for ground penetrating radar signals[J].Journal of Applied Geophysics，2017，144：125-133.
[9] ZHOU Y，CHEN W.MCA-based clutter reduction from migrated GPR data of shallowly buried point target[J].IEEE Transactions on Geoscience and Remote Sensing，2018，57（1）：432-448.
[10] KUMLU D，ERER I.Multiscale directional bilateral filter based clutter removal in GPR image analysis[C]//Proceedings of IEEE International Geoscience and Remote Sensing Symposium（IGARSS），2017：2345-2348.
[11] XUE W，DAI X，ZHU J，et al.A noise suppression method of ground penetrating radar based on EEMD and permutation entropy[J].IEEE Geoscience and Remote Sensing Letters，2019，16（10）：1625-1629.
[12] ZHANG J W，YE S B，LIU H，et al.Filtering out antenna effects from GPR data by an RBF neural network[J].IEEE Geoscience and Remote Sensing Letters，2019，16（9）：1378-1382.
[13] LEE D D，SEUNG H S.Learning the parts of objects by non-negative matrix factorization[J].Nature，1999，401：788-791.
[14] BERRY M W，BROWNE M，LANGVILLE A N，et al.Algorithms and applications for approximate nonnegative matrix factorization[J].Computational Statistics & Data Analysis，2007，52（1）：155-173.
[15] WANG Y X，ZHANG Y J.Nonnegative matrix factorization：A comprehensive review[J].IEEE Transactions on Knowledge and Data Engineering，2012，25（6）：1336-1353.
[16] 蔡菲，张鑫，牟晓慧，等.深度非负矩阵分解的链路预测方法研究[J].计算机工程与应用，2020，56（15）：153-161.
CAI F，ZHANG X，MOU X H，et al.Research on link prediction method based on deep non-negative matrix factorization[J].Computer Engineering and Applications，2020，56（15）：153-161.
[17] 徐霜，余琍.利用正则化矩阵分解技术的多视图聚类方法[J].计算机工程与应用，2019，55（14）：142-147.
XU S，YU L.Regularized matrix factorization algorithm for multi-view data clustering[J].Computer Engineering and Applications，2019，55（14）：142-147.
[18] KUMLU D，ERER I.Clutter removal in GPR images using non-negative matrix factorization[J].Journal of Electromagnetic Waves，2018，32（16）：2055-2066.
[19] KUMLU D，ERER I.Improved clutter removal in gpr by robust nonnegative matrix factorization[J].IEEE Geoscience and Remote Sensing Letters，2020，17（6）：958-962.
[20] BROUWER T，FRELLSEN J，LIó P.Comparative study of inference methods for bayesian nonnegative matrix factorisation[C]//Proceedings of Joint European Conference on Machine Learning and Knowledge Discovery in Databases，2017：513-529.
[21] 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.
[22] BOSTANUDIN N.Computational methods for processing ground penetrating radar data[D].Postsmouth：University of Portsmouth，2013.