GPR Clutter Reduction by Robust Orthonormal Subspace Learning

Kumlu, Deniz; Erer, İşın

doi:10.1109/access.2020.2988333

Cited by 17 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The original image is decomposed into two parts: clutter and target by ROSL. It performs better than robust principal component analysis (RPCA), go decomposition (GoDec), and other algorithms [45]. In 2022, Fok Hing Chi Tivive and others proposed the multilevel projective dictionary learning with low-rank prior (MPDL-LR) model [46], which uses a multilevel projective dictionary method to estimate radar trace signals.…”

Section: Dictionary Learning (Dl)mentioning

confidence: 99%

A Comprehensive Review of Conventional and Deep Learning Approaches for Ground-Penetrating Radar Detection of Raw Data

Bai

Chen

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

Ground-penetrating radar (GPR) is a nondestructive testing technology that is widely applied in infrastructure maintenance, archaeological research, military operations, and other geological studies. A crucial step in GPR data processing is the detection and classification of underground structures and buried objects, including reinforcement bars, landmines, pipelines, bedrock, and underground cavities. With the development of machine learning algorithms, traditional methods such as SVM, K-NN, ANN, and HMM, as well as deep learning algorithms, have gradually been incorporated into A-scan, B-scan, and C-scan GPR image processing. This paper provides a summary of the typical machine learning and deep learning algorithms employed in the field of GPR and categorizes them based on the feature extraction method or classifier used. Additionally, this work discusses the sources and forms of data utilized in these studies. Finally, potential future development directions are presented.

show abstract

Section: Dictionary Learning (Dl)mentioning

confidence: 99%

A Comprehensive Review of Conventional and Deep Learning Approaches for Ground-Penetrating Radar Detection of Raw Data

Bai

Chen

et al. 2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Robust principal component analysis (RPCA) [21], which decomposes the GPR image into a low-rank clutter matrix and a sparse target matrix, has demonstrated its superiority to the conventional subspace-based methods in GPR clutter removal [22,23]. Motivated by its success, various low-rank and sparse decomposition (LRSD) methods are successively proposed [24][25][26][27][28][29][30][31]. Song et al [24] presented an improved RPCA method that focuses on the target response by migration imaging, followed by suppressing the clutter using the RPCA.…”

Section: Introductionmentioning

confidence: 99%

“…They also presented a two-step GoDec approach for cases with missing data [28]. Moreover, they exploited a robust orthonormal subspace learning (ROSL) method for GPR clutter reduction [29]. This method has a faster implementation and comparable performance to GoDec and RNMF without presetting the parameters.…”

Section: Introductionmentioning

confidence: 99%

GPR Clutter Removal Based on Weighted Nuclear Norm Minimization for Nonparallel Cases

Liu

Song

et al. 2023

Sensors

View full text Add to dashboard Cite

Ground-penetrating radar (GPR) is an effective geophysical electromagnetic method for underground target detection. However, the target response is usually overwhelmed by strong clutter, thus damaging the detection performance. To account for the nonparallel case of the antennas and the ground surface, a novel GPR clutter-removal method based on weighted nuclear norm minimization (WNNM) is proposed, which decomposes the B-scan image into a low-rank clutter matrix and a sparse target matrix by using a non-convex weighted nuclear norm and assigning different weights to different singular values. The WNNM method’s performance is evaluated using both numerical simulations and experiments with real GPR systems. Comparative analysis with the commonly used state-of-the-art clutter removal methods is also conducted in terms of the peak signal-to-noise ratio (PSNR) and the improvement factor (IF). The visualization and quantitative results demonstrate that the proposed method outperforms the others in the nonparallel case. Moreover, it is about five times faster than the RPCA, which is beneficial for practical applications.

show abstract

“…It can be seen that although these methods can suppress noise to a certain extent, they all have some shortcomings. In terms of removing clutter, principal component analysis (PCA) [28], independent component analysis (ICA) [29], morphological component analysis (MCA) [30], non-negative matrix factorization (NMF) [31], go decomposition (GoDec) [32], robust matrix factorization (RMF) [33], robust orthonormal subspace learning (ROSL) [34], robust PCA (RPCA) [35], [36], and tensor RPCA (TRPCA) [37], [38] are all good methods. They divide GPR data into two categories through different methods, one corresponding to the clutter and the other corresponding to the target signal, thus achieving the purpose of clutter removal.…”

Section: Introductionmentioning

confidence: 99%

The Noise Attenuation and Stochastic Clutter Removal of Ground Penetrating Radar Based on the K-SVD Dictionary Learning

et al. 2021

View full text Add to dashboard Cite

The ground penetrating radar (GPR) data in the complex detection environment is nonstationary, non-Gaussian, and non-uniform, so the traditional noise attenuation methods are difficult to meet the requirements of denoising. Therefore, we introduced the K-singular value decomposition (K-SVD) dictionary learning into the denoising of GPR signals. It uses the orthogonal matching pursuit (OMP) algorithm to sparse decompose different radar data and trains the overcomplete dictionary with sample characteristics. K-SVD makes full use of the prior information and can extract features according to the sample data adaptively, which means it has strong sparse representation competence. Because radar signals can be sparsely represented in the dictionary, whereas the random noise does not have a sparse representation, the K-SVD dictionary can be used to distinguish effective signals from noise in the GPR data. We used the discrete cosine transform (DCT) and K-SVD dictionaries to process the Gaussian noise and stochastic clutter in the GPR profile. The results show that both K-SVD and DCT can effectively suppress the Gaussian noise. But for the clutter generated by the random medium, the DCT dictionary also causes damage to the effective signals while removing the noise; whereas the K-SVD dictionary learning algorithm uses the DCT dictionary as the initial dictionary and carries out adaptive learning on the noisy data, considering the information in the block and the global observation to complete the denoising, with good denoising effect and high fidelity. We finally verified the effectiveness and practicability of the K-SVD method for measured data.

show abstract

GPR Clutter Reduction by Robust Orthonormal Subspace Learning

Cited by 17 publications

References 24 publications

A Comprehensive Review of Conventional and Deep Learning Approaches for Ground-Penetrating Radar Detection of Raw Data

A Comprehensive Review of Conventional and Deep Learning Approaches for Ground-Penetrating Radar Detection of Raw Data

GPR Clutter Removal Based on Weighted Nuclear Norm Minimization for Nonparallel Cases

The Noise Attenuation and Stochastic Clutter Removal of Ground Penetrating Radar Based on the K-SVD Dictionary Learning

Contact Info

Product

Resources

About