Journals / Havacılık ve Uzay Teknolojileri Dergisi / 2020 / Cilt: 13 - Sayı: 2

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

YNR Görüntülerinde Gömülü Hedef Tespitini için Kargaşa Öğrenme Tabanlı LS Metodu

Pages
217–225
Publication Date
2022-10-18
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

Moreover, due tothe regularization, the proposed method is more robust to noise caused by theirregularities of the soil.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:A regularized version of the least squares (LS) target detection method iscombined with the subspace-based clutter learning for buried target detectionin ground penetrating radar (GPR) images.
📊
Key Findings & Data:Thus, for A-scanscontaining target information, LS method will provide an increase in theestimation error indicating target presence at this location.
💡
Conclusion & Impact:Moreover, due tothe regularization, the proposed method is more robust to noise caused by theirregularities of the soil.
🔬Design:Research Article
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

A regularized version of the least squares (LS) target detection method iscombined with the subspace-based clutter learning for buried target detectionin ground penetrating radar (GPR) images. The LS method is used to estimatethe next A-scans from previously observed A-scans which are assumed tobelong to the clutter component. Generally, A-scans used in the initial stageare accepted as target-free for the LS to work correctly. However, this is notguaranteed and if the first observed A-scan samples contain any targetinformation, LS method will fail. In this paper, the clutter information isretrieved via robust principal component analysis (RPCA) as a preprocessingstage and used in the LS estimation of the actual A-scan. Thus, for A-scanscontaining target information, LS method will provide an increase in theestimation error indicating target presence at this location. Moreover, due tothe regularization, the proposed method is more robust to noise caused by theirregularities of the soil.

Özet

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.

🔖

Cite This Article

KUMLU, D., ERER, I. (2022). Clutter Learning Based LS Method for Buried Target Detection in GPR Images. Havacılık ve Uzay Teknolojileri Dergisi, Cilt: 13 - Sayı: 2, 217–225. https://ajindex.com/articles/535182

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (14)

  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.