Target recognition performance analysis based on multi-aspect composite SAR images

doi:10.7523/j.issn.2095-6134.2019.02.010

Abstract

Abstract: Synthetic aperture radar (SAR) receives the backscatter of target within only a small range of azimuth during the synthetic aperture accumulation time, which makes the SAR image extremely sensitive to the change in observation azimuth. In this study, an SAR image with more obvious features is composed of multiple SAR images obtained at different azimuths by means of non-coherent composition, and then 2DPCA is used to extract features and the k-nearest neighbor method is used for target recognition.Finally the recognition performance is analyzed on two different datasets. The experimental results show that the multi-aspect SAR has a higher recognition rate than the single aspect, and has strong robustness to the change in depression angle.

Key words: target recognition, multi-aspect, synthetic aperture radar(SAR), non-coherent composition, performance analysis

CLC Number:

TP751

ZOU Hao, LIN Yun, HONG Wen. Target recognition performance analysis based on multi-aspect composite SAR images[J]. , 2019, 36(2): 226-234.

References

[1] 盖旭刚, 陈晋汶, 韩俊,等. 合成孔径雷达的现状与发展趋势[J]. 飞航导弹, 2011(3):82-86.
[2] 张红. 高分辨率SAR图像目标识别[M]. 北京:科学出版社, 2009.
[3] Moreira A, Prats-Iraola P, Younis M, et al. A tutorial on synthetic aperture radar[J]. IEEE Geoscience & Remote Sensing Magazine, 2013, 1(1):6-43.
[4] 洪文. 圆迹SAR成像技术研究进展[J]. 雷达学报, 2012, 1(2):124-135.
[5] 向卫力, 李晓辉, 周勇胜,等. 一种鲁棒的多尺度稀疏表示SAR目标识别方法[J]. 中国科学院大学学报, 2017, 34(1):99-105.
[6] O'Sullivan J A, Devore M D, Kedia V, et al. SAR ATR performance using a conditionally Gaussian model[J]. IEEE Transactions on Aerospace & Electronic Systems, 2001, 37(1):91-108.
[7] He Z, Lu J, Kuang G. A fast SAR target recognition approach using PCA features[C]//International Conference on Image and Graphics. Sichuan:IEEE, 2007:580-585.
[8] Tao M, Zhou F, Liu Y, et al. Tensorial independent component analysis-based feature extraction for polarimetric SAR data classification[J]. IEEE Transactions on Geoscience & Remote Sensing, 2015, 53(5):2481-2495.
[9] Anagnostopoulos G C. SVM-based target recognition from synthetic aperture radar images using target region outline descriptors[J]. Nonlinear Analysis, 2009, 71(12):2934-2939.
[10] Cui Z, Cao Z, Yang J, et al. SAR target recognition using nonnegative matrix factorization with L1/2 constraint[C]//Radar Conference. Cincinnati:IEEE, 2014:382-386.
[11] Huan R H, Zhang P, Pan Y. SAR target recognition using PCA, ICA and Gabor wavelet decision fusion[J]. Journal of Remote Sensing, 2012, 16(2):262-274.
[12] Lin C, Peng F, Wang B H, et al. Research on PCA and KPCA self-fusion based MSTAR SAR automatic target recognition algorithm[J]. Journal of Electronic Science and Technology, 2012, 10(4):352-357.
[13] Chen S, Wang H. SAR target recognition based on deep learning[C]//International Conference on Data Science and Advanced Analytics. IEEE, 2015:541-547.
[14] Zhan R H, Tian Z Z, Hu J M, et al. SAR automatic target recognition based on deep convolutional neural network[C]//2016 International Conference on Artificial Intelligence:Techniques and Applications. AITA, 2016:170-178.
[15] Brendel G F, Horowitz L L. Benefits of aspect diversity for SAR ATR:fundamental and experimental results[C]//Algorithms for Synthetic Aperture Radar Imagery VⅡ. SPIE, 2000:567-578.
[16] Huan R H, Pan Y. Target recognition for multi-aspect SAR images with fusion strategies[J]. Progress in Electromagnetics Research, 2013, 134(1):267-288.
[17] Cao Z J, Xu L Y, Feng J L. Automatic target recognition with joint sparse representation of heterogeneous multi-view SAR images over a locally adaptive dictionary[J]. Signal Processing, 2016, 126(1):27-34.
[18] Yang J, Zhang D, Frangi A F, et al. Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2004, 26(1):131-137.
[19] Cover T, Hart P. Nearest neighbor pattern classification[J]. IEEE Transactions on Information Theory, 1967, 13(1):21-27.
[20] Solberg A H S, Jain A K, Taxt T. Multisource classification of remotely sensed data:fusion of Landsat TM and SAR images[J]. IEEE Transactions on Geoscience & Remote Sensing, 1994, 32(4):768-778.
[21] 阳方林, 郭红阳, 杨风暴. 像素级图像融合效果的评价方法研究[J]. 测试技术学报, 2002, 16(4):276-279.
[22] 李航. 统计学习方法[M]. 北京:清华大学出版社, 2012.
[23] Amoon M, Rezai-Rad G A. Automatic target recognition of synthetic aperture radar (SAR) images based on optimal selection of Zernike moments features[J]. Computer Vision IET, 2013, 8(2):77-85.
[24] Dong G, Kuang G. Classification on the monogenic scale space:application to target recognition in SAR image[J]. IEEE Transactions on Image Processing, 2015, 24(8):2527-2539.
[25] Anagnostopoulos G C. SVM-based target recognition from synthetic aperture radar images using target region outline descriptors[J]. Nonlinear Analysis, 2009, 71(12):2934-2939.
[26] Mishra A K. Validation of PCA and LDA for SAR ATR[C]//2008 IEEE Region 10 Conference. Hyderabad:IEEE, 2009:1-6.
[27] Cui Z Y, Cao Z J, Yang J Y. Target recognition in synthetic aperture radar images via non-negative matrix factorization[J], IET Radar Sonar & Navigation, 2015, 9(9):1376-1385.
[28] Zhang H, Nasrabadi N M, Zhang Y, et al. Multi-view automatic target recognition using joint sparse representation[J]. Aerospace & Electronic Systems IEEE Transactions, 2012, 48(3):2481-2497.