Makine Öğrenimi Tekniklerini Kullanarak SAR Görüntülemesinden Otomatik Hedef Tanıma (OHT)

Sentetik açıklıklı radar (SAR) görüntülerinde Otomatik Hedef Tanıma (OHT), içerdiği yüksek seviyeli gürültü nedeniyle çözümü çok zor bir sorun haline gelmiştir. Bu çalışmada, SAR görüntülerini kullanarak farklı hareketli ve sabit hedefleri tespit etmek için makine öğrenmesine dayalı bir yöntem önerilmiştir. Birinci Derece İstatistik (BDİ) özellikleri, gri seviyedeki SAR görüntülerinde Hızlı Fourier Dönüşümü (HFD), Ayrık Kosinüs Dönüşümü (AKD) ve Ayrık Dalgacık Dönüşümü (ADD) uygulandıktan sonra elde edilmiştir. Gri Seviye Eş Oluşum Matrisi (GSEOM), Gri Seviye Çalışma Uzunluğu Matrisi (GSÇUM) ve Gri Seviye Boyutu Bölge Matrisi (GSBBM) algoritmaları da özellik elde edilmesi için kullanılmaktadır. Bu özellikler, eğitim ve test aşaması için Gaussian çekirdeklere sahip Destek Vektör Makinesi (DVM) modeli için girdi olarak verilmiştir. Performans değerlendirmesinde 4 katlı çapraz doğrulama yapılmıştır. Elde edilen sonuçlar, GSEOM + DVM algoritmasının % 95.26 doğrulukla en iyi model olduğunu göstermiştir. Önerilen bu yöntem, MSTAR veri tabanındaki hareketli ve sabit hedeflerin yüksek performansla tanınabileceğini göstermektedir.

Anahtar Kelimeler:

SAR, Hedef Tanıma, Makine Öğrenmesi, Özellik Çıkarımı, Destek Vektör Makinesi

Automatic Target Recognition (ATR) from SAR Imaginary by Using Machine Learning Techniques

Automatic Target Recognition (ATR) in Synthetic aperture radar (SAR) images becomes a very challenging problem owing to containing high level noise. In this study, a machine learning-based method is proposed to detect different moving and stationary targets using SAR images. First Order Statistical (FOS) features were obtained from Fast Fourier Transform (FFT), Discrete Cosine Transform (DCT) and Discrete Wavelet Transform (DWT) on gray level SAR images. Gray Level Co-occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM) and Gray Level Size Zone Matrix (GLSZM) algorithms are also used. These features are provided as input for the training and testing stage Support Vector Machine (SVM) model with Gaussian kernels. 4-fold cross-validations were implemented in performance evaluation. Obtained results showed that GLCM + SVM algorithm is the best model with 95.26% accuracy. This proposed method shows that moving and stationary targets in MSTAR database could be recognized with high performance.

Keywords:

SAR, Target Recognition, Machine Learning, Feature Extraction, Support Vector Machine,

PDF

___

Dong, G., Kuang, G., Wang, N., Zhao, L., & Lu, J. (2015). SAR target recognition via joint sparse representation of monogenic signal. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(7), 3316-3328.
Dong, G., Kuang, G., Wang, N., & Wang, W. (2017). Classification via sparse representation of steerable wavelet frames on Grassmann manifold: Application to target recognition in SAR image. IEEE Transactions on Image Processing, 26(6), 2892-2904.
Eltoukhy, M. M., Faye, I., & Samir, B. B. (2012). A statistical based feature extraction method for breast cancer diagnosis in digital mammogram using multiresolution representation. Computers in biology and medicine, 42(1), 123-128.
Gorovyi, I. M., & Sharapov, D. S. (2017, June). Efficient object classification and recognition in SAR imagery. In 2017 18th International Radar Symposium (IRS) (pp. 1-7). IEEE.
Jianxiong, Z., Zhiguang, S., Xiao, C., & Qiang, F. (2011). Automatic target recognition of SAR images based on global scattering center model. IEEE transactions on Geoscience and remote sensing, 49(10), 3713-3729.
Kulkarni, S. R., & Harman, G. (2011). Statistical learning theory: a tutorial. Wiley Interdisciplinary Reviews: Computational Statistics, 3(6), 543-556.
Liu, H., & Li, S. (2013). Decision fusion of sparse representation and support vector machine for SAR image target recognition. Neurocomputing, 113, 97-104.
Martone, A., Innocenti, R., & Ranney, K. (2009). Moving target indication for transparent urban structures. US Army Research Laboratory Adelphi United States.
Novak, L. M., Owirka, G. J., & Netishen, C. M. (1993). Performance of a high-resolution polarimetric SAR automatic target recognition system. Lincoln Laboratory Journal, 6(1).
Novak, L. M., Owirka, G. J., & Brower, W. S. (1998, November). An efficient multi-target SAR ATR algorithm. In Conference Record of Thirty-Second Asilomar Conference on Signals, Systems and Computers (Cat. No. 98CH36284) (Vol. 1, pp. 3-13). IEEE.
Pan, Z., Qiu, X., Huang, Z., & Lei, B. (2016). Airplane recognition in TerraSAR-X images via scatter cluster extraction and reweighted sparse representation. IEEE Geoscience and Remote Sensing Letters, 14(1), 112-116.
O'Sullivan, J. A., DeVore, M. D., Kedia, V., & Miller, M. I. (2001). SAR ATR performance using a conditionally Gaussian model. IEEE Transactions on Aerospace and Electronic Systems, 37(1), 91-108.
Quan, S., Xiong, B., Xiang, D., & Kuang, G. (2018). Derivation of the orientation parameters in built-up areas: With application to model-based decomposition. IEEE Transactions on Geoscience and Remote Sensing, 56(8), 4714-4730.
Singleton, R. C. (1968). Algorithms: Algorithm 338: algol procedures for the fast Fourier transform. Communications of the ACM, 11(11), 773-776.
Soh, L. K., & Tsatsoulis, C. (1999). Texture analysis of SAR sea ice imagery using gray level co-occurrence matrices. IEEE Transactions on geoscience and remote sensing, 37(2), 780-795.
Solomon, C., & Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley & Sons.
Thibault, G., Fertil, B., Navarro, C., Pereira, S., Cau, P., Levy, N., ... & Mari, J. L. (2013). Shape and texture indexes application to cell nuclei classification. International Journal of Pattern Recognition and Artificial Intelligence, 27(01), 1357002.