Ground penetrating radar data reconstruction combined with regularized K-SVD and Hampel filter

doi:10.13474/j.cnki.11-2246.2021.0234

Abstract

Abstract: To alleviate the energy difference between the GPR data caused by topographic relief, and ensure the accuracy of the GPR image interpretation and recognition, this paper proposes a GPR data reconstruction method combining regularized K-SVD dictionary learning and Hampel filtering algorithm. In the experiment, regularized K-SVD dictionary learning is used to carry out the energy balance of GPR signals, Hampel filtering algorithm is used to eliminate the outliers of the balanced signals, and two-dimensional visualization of the balanced signals is carried out, so as to complete the image reconstruction of the GPR. The comparison experiment shows that this method can not only balance the original GPR signal, but also the balanced signal is more in line with the GPR signal propagation law, which can guarantee the quality of the trace data signal, and the reconstructed image is better, which has a good practical value in the GPR image reconstruction.

Key words: energy balance, regularized K-SVD dictionary learning, Hampel filtering algorithm, registration method

CLC Number:

P237

YAN Kun, ZHANG Zhihua, YAN Luchun. Ground penetrating radar data reconstruction combined with regularized K-SVD and Hampel filter[J]. Bulletin of Surveying and Mapping, 2021, 0(8): 22-27.

References

[1] HARRY M. Ground penetrating radar:theory and applica-tions[M]. Netherlands:Elsevier, 2011.
[2] TORBAGHAN M E, LI W, METJE N, et al. Automated detection of cracks in roads using ground penetrating radar[J]. Journal of Applied Geophysics, 2020, 179:104-118.
[3] TONG Z, YUAN D, GAO J, et al. Pavement-distress detection using ground-penetrating radar and network in networks[J]. Construction and Building Materials, 2020, 233:117352-117363.
[4] AHARON M, ELAD M, BRUCKSTEIN A. K-SVD:an algorithm for designing overcomplete dictionaries for sparse representation[J]. IEEE Transactions on Signal Processing, 2006, 54(11):4311-4322.
[5] JAFARI M G, PLUMBLEY M D. Fast dictionary learning for sparse representations of speech signals[J]. IEEE Journal of Selected Topics in Signal Process, 2011, 5(5):1025-1031.
[6] KOKIOPOULOU E, FROSSARD P. Semantic coding by supervised dimensionality reduction[J]. IEEE Transactions on Multimedia, 2008, 10(5):806-818.
[7] PLUMBLEY M D, BLUMENSATH T, DAUDET L, et al. Sparse representations in audio and music:from coding to source separation[J]. Proceedings of the IEEE, 2010, 98(6):995-1005.
[8] LI W, LIANG J, WU Q, et al. An efficient face classifica-tion method based on shared and class-specific dictionary learning[C]//Proceedings of IEEE International Conference on Image Processing (ICIP).[S.l.]:IEEE, 2015:2596-2600.
[9] KE H, AVIYENTE S. Sparse representation for signal classification[C]//Proceedings of the 20th Conference on Advances in Neural Information Processing Systems. Vancouver:[s.n.], 2006:609-616.
[10] MAIRAL J, BACH F, Ponce J, et al. Discriminative learned dictionaries for local image analysis[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.[S.l.]:IEEE, 2008:1-8.
[11] ZHANG G, PORIKLI F, SUN H, et al. Cost-sensitive joint feature and dictionary learning for face recognition[J]. Neurocomputing, 2020, 391:177-188.
[12] WRIGHT J, YANG A Y, GANESH A, et al. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2):210-227.
[13] AWATE S P, DIBELLA E V R. Spatiotemporal dictionary learning for undersampled dynamic MRI reconstruction via joint frame-based and dictionary-based sparsity[C]//Proceedings of the 9th IEEE International Symposium on Biomedical Imaging (ISBI).[S.l.]:IEEE, 2012:318-321.
[14] WANG J, LIAO X, LI J, et al. Single image super-resolution based on incoherent dictionary learning[C]//Proceedings of the 9th International Conference on Software Engineering and Service Science (ICSESS).[S.l.]:IEEE, 2018:555-558.
[15] IROFTI P, Dumitrescu B. Regularized algorithms for dictionary learning[C]//Proceedings of International Conference on Communications (COMM).[S.l.]:IEEE, 2016:439-442.
[16] DAI W, XU T, WANG W. Simultaneous codeword optimiza-tion (SimCO) for dictionary update and learning[J]. IEEE Transactions on Signal Processing, 2012, 60(12):6340-6353.
[17] KUANG Y, ZHANG L, YI Z. An adaptive rank-sparsity K-SVD algorithm for image sequence denoising[J]. Pattern Recognition Letters, 2014, 45:46-54.
[18] ZHOU Y, ZHAO H, SHANG L, et al. Immune K-SVD algorithm for dictionary learning in speech denoising[J]. Neurocomputing, 2014, 137:223-233.
[19] YANG J, ZHANG X, PENG W, et al. A novel regularized K-SVD dictionary learning based medical image super-resolution algorithm[J]. Multimedia Tools and Applications, 2016, 75(21):13107-13120.
[20] DUMITRESCU B, IROFTI P. Regularized K-SVD[J]. IEEE Signal Processing Letters, 2017, 24(3):309-313.
[21] BHOWMIK S, JELFS B, ARJUNAN S P, et al. Outlier removal in facial surface electromyography through Hampel filtering technique[C]//Proceedings of IEEE Life Sciences Conference (LSC).[S.l.]:IEEE, 2017:258-261.