首页 | 本学科首页   官方微博 | 高级检索  
     

协方差矩阵结构的广义近似最大似然估计
引用本文:顾新锋,简涛,何友,郝晓琳. 协方差矩阵结构的广义近似最大似然估计[J]. 应用科学学报, 2013, 31(6): 585-592. DOI: 10.3969/j.issn.0255-8297.2013.06.006
作者姓名:顾新锋  简涛  何友  郝晓琳
作者单位:1. 海军航空工程学院信息融合技术研究所,山东烟台2640012. 中国卫星海上测控部,江苏江阴2144313. 烟台电力经济技术研究所,山东烟台264001
基金项目:国家自然科学基金(No. 61032001, No. 61102166)资助
摘    要:针对相关复合高斯杂波背景下相邻杂波纹理分量可能相同的情况,将杂波均匀分组进行推广,结合归一化采样协方差矩阵估计,提出了广义杂波分组的归一化采样协方差矩阵估计方法(generalized normalized sample covariance matrix, GNSCM). 利用最大似然估计方法,进一步推导了广义杂波分组背景下协方差矩阵结构最大似然估计的迭代过程,以GNSCM 为初始化矩阵进行迭代,得到协方差矩阵结构的广义近似最大似然(generalized approximate maximum likelihood, GAML) 估计. GAML 是对现有方法近似最大似然(approximate maximum likelihood, AML) 估计和约束迭代杂波分组估计(constrained recursive clutter-clustered estimator, CRCCE) 的推广,具有更强的杂波适应能力. 仿真结果表明,针对非均匀分组杂波环境,与AML 估计和CRCCE 相比,GAML 具有更高的估计精度,且相应的自适应检测器具有更好的恒虚警率特性和检测性能.

关 键 词:非高斯杂波  杂波分组  协方差矩阵估计  归一化匹配滤波器  恒虚警率  
收稿时间:2011-12-12
修稿时间:2012-02-16

Generalized Approximate Maximum Likelihood Estimation of Covariance Matrix Structure
GU Xin-feng,JIAN Tao,HE You,HAO Xiao-lin. Generalized Approximate Maximum Likelihood Estimation of Covariance Matrix Structure[J]. Journal of Applied Sciences, 2013, 31(6): 585-592. DOI: 10.3969/j.issn.0255-8297.2013.06.006
Authors:GU Xin-feng  JIAN Tao  HE You  HAO Xiao-lin
Affiliation:1. Research Institute of Information Fusion, Naval Aeronautical and Astronautical;University, Yantai 264001, Shandong Province, China;2. China Satellite Martime Tracking and Control Department, Jiangyin 214431, Jiangsu Province,China;3. Yantai Electricity and Economy Technical Institute, Yantai 264001, Shandong Province, China 
Abstract:By generalizing the clutter-clustered estimation method and considering the normalized sample covariance matrix (NSCM), a generalized NSCM(GNSCM) is proposed for covariance matrix structure estimation in correlated compound-Gaussian clutter. A maximum likelihood recursive estimation process of covariance matrix structure is derived in generalized clutter-clustered background. A generalized approximate maximum likelihood (GAML) estimator is then obtained by using GNSCM as the initialized estimation estimated matrix to recursive. GAML is an extension of the existing methods the approximate maximum likelihood (AML) and the constrained recursive clutter-clustered estimator (CRCCE). Simulation results show that, compared with
the two previous methods, GAML has higher estimation accuracy, and the corresponding adaptive detector has better constant false alarm ratio (CFAR) property and detection performance.
Keywords: non-Gaussian clutter  clutter-clustered  covariance matrix estimation  normalized matched filter  constant false alarm ratio  
点击此处可从《应用科学学报》浏览原始摘要信息
点击此处可从《应用科学学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号