Clutter Learning Based LS Method for Buried Target Detection in GPR Images

A regularized version of the least squares (LS) target detection method is combined with the subspace-based clutter learning for buried target detection in ground penetrating radar (GPR) images. The LS method is used to estimate the next A-scans from previously observed A-scans which are assumed to belong to the clutter component. Generally, A-scans used in the initial stage are accepted as target-free for the LS to work correctly. However, this is not guaranteed and if the first observed A-scan samples contain any target information, LS method will fail. In this paper, the clutter information is retrieved via robust principal component analysis (RPCA) as a preprocessing stage and used in the LS estimation of the actual A-scan. Thus, for A-scans containing target information, LS method will provide an increase in the estimation error indicating target presence at this location. Moreover, due to the regularization, the proposed method is more robust to noise caused by the irregularities of the soil.

YNR Görüntülerinde Gömülü Hedef Tespitini için Kargaşa Öğrenme Tabanlı LS Metodu

En küçük kareler (EKK) hedef tespit yönteminin düzenleştirilmiş versiyonu ile alt uzay tabanlı kargaşa giderme, yere nüfuz eden radar (YNR) görüntülerinde gömülü hedef tespiti için birleştirilmiştir. EKK yöntemi geçmişte gözlenmiş A-taramaları kullanarak, gelecek A-taramayı tahmin etmeye çalışır ve gözlemlenmiş A-taramanın kargaşa bileşenine ait olduğu varsayımı mevcuttur. Genellikle, EKK’nin doğru çalışabilmesi için, başlangıç aşamasında gözlemlenen A-taramalarda hedefe ait olmadığı kabul edilir. Fakat bu her zaman doğru bir varsayım değildir ve ilk gözlemlenen Ataramalarda hedef bileşeni mevcutsa, EKK yöntemi başarısız olacaktır. Bu çalışmada, ön adım olarak kargaşa bilgisi gürbüz temel bileşen analizi (GTBA) yöntemi ile çıkartılmıştır ve bu bilgi EKK’nin gelecek A-taramayı tahmini için kullanılmıştır. Böylece, hedef bilgisi içeren A-taramalarda EKK yönteminin tahmin hatası artacağından, bu A-taramalarda bölgesinde hedefin olduğunu gösterecektir. Ayrıca, düzenlileştirme işleminden dolayı, önerilen yöntem yüzey düzensizliklerinden dolayı meydana gelen gürültüye karşı daha gürbüz olacaktır.

PDF

___

[1] D. J. Daniels, Ground Penetrating Radar. IEE, London, U.K. (2004).

[2] A.B. Yoldemir, and M. Sezgin, “A least squares approach to buried object detection using ground penetrating radar.” IEEE Sensors Journal, Vol. 11, No. 6, pp. 1337-1341, 2011.

[3] E. Temlioglu, I. Erer and D. Kumlu, “A least mean square approach to buried object detection in ground penetrating radar,” In IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 4833-4836, July 2017.

[4] B.P.A. Rohman and M. Nishimoto, “GPR Target Signal Enhancement Using Least Square Fitting Background and Multiple Clustering of Singular Values,” Progress In Electromagnetics Research, Vol. 83, pp.123-132, 2019.

[5] X. Song.; D. Xiang; K. Zhou and Y. Su, “Improving RPCA-based clutter suppression in GPR detection of antipersonnel mines.” IEEE Geosci. Remote Sens. Letters, Vol. 14, No. 8, pp. 1338-1342, 2017.

[6] F. Abujarad, Ground Penetrating Radar Signal Processing for Landmine Detection, PhD Thesis, Otto- Von-Guericke University Magdeburg, Germany (2007).

[7] P.K. Verma, A. N. Gaikwad, D. Singh et al. “Analysis of clutter reduction techniques for through wall imaging in UWB range.” Progress In Electromagnics Res B., Vol. 17, pp. 29-48, 2009.

[8] D. Kumlu and I. Erer, “Clutter Removal Techniques in Ground Penetrating Radar for Landmine Detection: A Survey.” In Operations Research for Military Organizations, IGI Global, pp. 375–399, 2019.

[9] D. Kumlu and I. Erer, “A comparative study on clutter reduction techniques in GPR images.” In International Conference on Electrical and Electronics Eng., pp.23– 328, April 2017.

[10] D. Kumlu and I. Erer, “Clutter removal in GPR images using nonnegative matrix factorization,” Journal of Electromagnetic Waves and Applications, Vol. 32, No. 16, pp. 2055–2066, 2018.

[11] M. P. Masarik, J. Burns; B. T. Thelen; J. Kelly and T. C. Havens, “GPR anomaly detection with robust principal component analysis.” In Detection and Sensing of Mines, Explosive objects, and Obscured targets XX, May 2015.

[12] L. Liu, Q. Chen, Y. Han, H. Xu, J. Li, and B. Wang, “Improved Clutter Removal by Robust Principal Component Analysis for Chaos Through-Wall Imaging Radar.” Electronics, Vol. 9, No. 1, pp .25, 2020.

[13] H. Abdi, The Method of Least Squares. Thousand Oaks, CA: Sage, 2010.

[14] D. Kumlu and I. Erer, “Combining Clutter Learning with LS for Improved Buried Target Detection in GPR.” In 9th International Conference on Recent Advances in Space Technologies (RAST), pp. 607-611, June 2019.

[15] E. J. Candès, X. Li; Y. Ma and J. Wright, “Robust principal component analysis?.” Journal of the ACM, Vol. 58, No. 1, pp. 1-37, 2009.

[16] Xu, Y., Wu, Z., Xiao, F., Zhan, T. and Wei, Z, “A target detection method based on low-rank regularized least squares model for hyperspectral images.” IEEE Geoscience and Remote Sensing Letters, Vol. 13, No. 8, pp.1129-1133, 2016.

[17] C. Warren, A. Giannopoulos and I. Giannakis, “gprMax: Open source software to simulate electromagnetic wave propagation for ground penetrating radar.” Computer Physics Comm, Vol. 209, pp. 163-170, 2009.

[18] Real GPR data. Vrije Univ. Brussel (VUB), accessed on Sep. 01, 2011. [Online]. Available: http://www.minedet.etro.vub.ac.be

[19] J. Kim, G. Caire and A.F. Molisch, “Quality-aware streaming and scheduling for device-to-device video delivery.” IEEE/ACM Transactions on Networking, Vol. 24, No. 4, pp. 2319-2331, 2015.