[1]陈婕,廖志平.基于增强字典稀疏表示分类的SAR目标识别方法[J].探测与控制学报,2020,42(03):75.[doi:.]
 CHEN Jie,LIAO Zhiping.SAR Target Recognition Based on Enhanced Dictionary Sparse Representation Classification[J].,2020,42(03):75.[doi:.]
点击复制

基于增强字典稀疏表示分类的SAR目标识别方法()
分享到:

《探测与控制学报》[ISSN:1008-1194/CN:61-1316/TJ]

卷:
42
期数:
2020年03
页码:
75
栏目:
出版日期:
2020-06-15

文章信息/Info

Title:
SAR Target Recognition Based on Enhanced Dictionary Sparse Representation Classification
文章编号:
1008-1194(2020)03-0075-07
作者:
陈婕廖志平
桂林电子科技大学信息科技学院, 广西 桂林 541004
Author(s):
CHEN Jie LIAO Zhiping
Institute of Information Technology, Guilin University of Electronic Technology, Guilin 541004, China
关键词:
合成孔径雷达目标识别增强字典稀疏表示分类
Keywords:
synthetic aperture radar automatic target recognition enhanced dictionary spare representation-based classification
分类号:
TN957
DOI:
.
文献标志码:
A
摘要:
针对合成孔径雷达(SAR)目标识别方法中分类决策存在的不足,提出基于增强字典稀疏表示分类的SAR目标识别方法。该方法通过对原始训练样本进行多信噪比、多分辨率样本构造,进而构建描述能力更强、对于扩展操作条件更稳健的增强字典进而采用稀疏表示分类器提高目标识别的整体性能。基于MSTAR数据集的实验结果表明,该方法在对于3类和10类目标的平均识别率可分别达到98.61%和98.12%,验证其区分多类目标的能力;通过测试在不同信噪比、不同分辨率下的识别性能,验证了该方法对于噪声干扰、分辨率变化具有较强的稳健性。
Abstract:
Considering the defaults in synthetic aperture radar (SAR) image classification decision, a SAR target recognition method of sparse representation-based classification (SRC) based on the enhanced dictionary was proposed. The original training sample were added with noises and represented at multiple resolutions to enrich the available training samples. An enhanced dictionary was established, which included much more training sample with higher discrimination and robustness for extended operating conditions. Therefore, the overall recognition performance of SAR target recognition could be improved. According to the experimental results on the MSTAR dataset, the proposed method could achieve average recognition rates of 98.61% and 98.12% for 3-class and 10-class recognition problems. For conditions under noise corruption and resolution variances, the proposed method could maintain relatively high robustness.

参考文献/References:

[1] EL-DARYMLI K, GILL E W, McGUIRE P, et al.Automatic target recognition in synthetic aperture radar imagery: a state-of-the-art review [J]. IEEE Access, 2016, 4:6014-6058.
[2] 文贡坚,朱国强,殷红成,等.基于三维电磁散射参数化模型的SAR目标识别方法[J].雷达学报, 2017, 6(2):115-135.
[3] MISHRA K. Validation of PCA and LDA for SAR ATR[C]//Proceeding of IEEE Region 10 Conference. US: IEEE, 2008:1-6.
[4] 韩萍,王欢. 结合KPCA和稀疏表示的SAR目标识别方法研究[J].信号处理, 2013, 29(13):1696-1701.
[5] CUI Z Y, CAO Z J, YANG J Y, et al. Target recognition in synthetic aperture radar via non-negative matrix factorization [J]. IET Radar, Sonar and Navigation, 2015, 9(9): 1376-1385.
[6] 赵鹏举,甘凯. 基于互补特征层次决策融合的SAR目标识别方法[J]. 电光与控制, 2018, 5(10):28-32.
[7] ANAGNOSTOPOULOS G C. SVM-based target recognition from synthetic aperture radar images using target region outline descriptors [J]. Nonlinear Analysis, 2009, 71(2):2934-2939.
[8] 丁柏圆,文贡坚,余连生,等.属性散射中心匹配及其在SAR目标识别中的应用[J].雷达学报, 2017, 6(2):157-166.
[9] DING B Y, WEN G J, ZHONG J R, et al. A robust similarity measure for attributed scattering center sets with application to SAR ATR [J]. Neurocomputing, 2017, 219:130-143.
[10] ZHAO Q, PRINCIPE J C. Support vector machines for SAR automatic target recognition[J]. IEEE Transactions on Aerospace and Electronic System, 2001, 37(2):643-654.
[11] LIU H C, LI S T. Decision fusion of sparse representation and support vector machine for SAR image target recognition [J]. Neurocomputing 2013, 113, 97-104.
[12] THIAGARAIANM J, RAMAMURTHY K, KNEE P P, et al. Sparse representations for automatic target classification in SAR images [C]//4th Communications, Control and Signal Processing. US: IEEE, 2010: 1-4.
[13] CHEN S Z, WANG H P, XU F, et al.Target classification using the deep convolutional networks for SAR images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2016, 54(8): 4806-4817.
[14] YAN Y. Convolutional neural networks based on augmented training samples for synthetic aperture radar target recognition [J]. Journal of Electronic Imaging, 2018, 27(2):023024.
[15] 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.
[16] ZHANG L, TAO Z, WANG B. SAR image target recognition using kernel sparse representation based on reconstruction coefficient energy maximization rule [C]//ICASSP, 2016. US: IEEE, 2016: 2369-2373.

相似文献/References:

[1]高尔心,孙 杰,余春明,等.基于频谱分析恒虚警技术的脉冲多普勒引信[J].探测与控制学报,2007,(06):32.
 GAO Er-xin,SUN Jie,YU Chun-ming,et al.A Pulsed Doppler Fuze Based on Constant False Alarm Rate Technology of Spectral Analysis[J].,2007,(03):32.
[2]张志虎,李铁,杨小军.脉冲激光照射下目标散射特性研究[J].探测与控制学报,2007,(05):63.
 ZHANG Zhi-hu,LI Tie,YANG Xiao-jun.The Mathematical Model of the TTR of Laser Scattering[J].,2007,(03):63.
[3]刘澎,姚钦.可信度估计在目标识别融合系统中的应用[J].探测与控制学报,2007,(01):28.
 LIU Peng,YAO Qin.Application of Confidence Estimation to a Fusion System for Target Identification[J].,2007,(03):28.
[4]李炯,雷虎民,刘兴堂.一种D-S证据理论的改进方法及其在目标识别中的应用[J].探测与控制学报,2007,(01):76.
 LI Jiong,LEI Hu-min,LIU Xing-tang.Target Recognition of Multi-mode Compound Control and Guidance Based on Dempster-Shafer Theory[J].,2007,(03):76.
[5]王加,蒋晓瑜,杜登崇,等.基于伪彩色编码和图像融合的伪装目标识别方法[J].探测与控制学报,2008,(02):43.
 WANG Jia,JIANG Xiao-yu,DU Deng-chong,et al.A Disguised Target Recognition Method Based on Pseudo-color Coding and Image Fusion[J].,2008,(03):43.
[6]栾英宏,李跃华,卫永平.粗神经元网络在辐射计目标识别中的应用[J].探测与控制学报,2008,(05):38.
 LUAN Ying-hong,LI Yue-hua,WEI Yong-ping.Application of Rough Neural Network in Radiometer Signal Identification[J].,2008,(03):38.
[7]栾英宏,李跃华.一维距离像识别的相关向量机法[J].探测与控制学报,2009,(02):19.
 LUAN Ying-hong,LI Yue-hua.Relevance Vector Machine for 1-D Range Profile Recognition[J].,2009,(03):19.
[8]李源,杨丽丽,陈惠连,等.基于功率谱三值化的联合变换相关目标识别方法[J].探测与控制学报,2009,(03):51.
 LI Yuan,YANG Li-li,CHEN Hui-lian,et al.Joint Transform Correlation for Target Recognition Based on Ternary-valued Power Spectrum[J].,2009,(03):51.
[9]耿志祥,陈遵田.考虑时间因子的激光引信海面散射模型[J].探测与控制学报,2009,(03):64.
 GENG Zhi-xiang,CHEN Zun-tian.Sea Surface Scattering Model of Laser Fuze Taking Account of Time Factor[J].,2009,(03):64.
[10]吕金建,丁建江,项清,等.弹道导弹识别技术发展综述[J].探测与控制学报,2010,(04):7.
 Lü Jinjian,DING Jianjiang,XIANG Qing,et al.Review of Target Recognition Techniques for Ballistic Missile[J].,2010,(03):7.
[11]丁慧洁.基于非下采样剪切波特征提取的SAR图像目标识别方法[J].探测与控制学报,2020,42(01):75.[doi:.]
 DING Huijie.SAR Target Recognition Based on Non-subsampled Shearlet Transform (NSST) Feature Extraction[J].,2020,42(03):75.[doi:.]

备注/Memo

备注/Memo:
收稿日期:2019-12-20
作者简介:陈婕(1984—),女,广西桂林人,硕士,讲师,研究方向:图像处理、计算机应用技术。E-mail: lobida123@sina.com.
更新日期/Last Update: 2020-07-15