基于压缩感知的二维GTD模型参数估计方法  

A Novel Method for Parametric Estimation of 2D Geometrical Theory of Diffraction Model Based on Compressed Sensing

作　　者：占荣辉[1] 胡杰民[1] 张军[1] 

机构地区：[1]国防科技大学电子科学与工程学院长沙410073

出　　处：《电子与信息学报》2013年第2期419-425,共7页Journal of Electronics & Information Technology

基　　金：国防科技大学科研计划(JC12-04-01);国家自然科学基金(61002022)资助课题

摘　　要：几何绕射理论(Geometrical Theory of Diffraction,GTD)模型能够精确描述高频区雷达目标的电磁散射机理。该文在分析雷达回波稀疏特性的基础上,将参数估计问题转化为压缩感知理论中的稀疏信号重构问题,据此提出了一种基于压缩感知的2维GTD模型参数估计方法。该方法首先利用2维傅里叶变换成像确定目标散射中心的支撑区域,然后在支撑区域内对散射中心的GTD参数进行估计,最后利用聚类方法和最小二乘方法对估计结果进行修正。仿真和暗室测量数据实验结果表明,与现有方法相比,所提方法能有效改善模型参数的估计性能,且对提高散射中心类型参数的估计精度更为明显。The electromagnetic scattering mechanism of radar target in high frequency domain can be characterized exactly by Geometrical Theory of Diffraction （GTD） model. In this paper, a novel parameter estimating method for 2D GTD model is proposed based on the anMysis of the radar echoes＇ sparse characteristic. The parameters estimation is converted to the issue of sparse signal reconstruction in the framework of Compressed Sensing （CS）. In the proposed method, the signal support is first determined using 2D Fourier transform imaging and then the parameters of GTD model are estimated from the support region. To further improve the estimation precision of the parameters, clustering algorithms and linear least squares algorithms also adopted. Experiment results from both synthetic and real data show that the presented method is superior to the ones in existence, especially for the estimation of the scattering center type.

关 键 词：压缩感知 电磁散射 几何绕射理论模型 散射中心 稀疏 

分 类 号：TN95[电子电信—信号与信息处理]