全极化高分辨雷达距离像统计识别方法

在全极化、高分辨雷达体制背景下，提出一种将极化信息与高分辨距离像相结合的雷达目标统计识别方法。采用物理统计非高斯模型对全极化高分辨距离像建模，用模型参数分别表征具有较强散射强度分辨单元的多少和强弱，将全极化下的模型参数直接作为特征矢量，并采用Parzen窗法估计模型参数的概率分布密度，用贝叶斯分类器进行分类识别。对实测的导弹类目标识别结果表明，该方法能有效克服距离像特征依赖于方位信息的缺点，达到令人满意的识别结果。

A Statistical Identification Method of Polarimetric High Resolution Rangeprofile

For the polarimetric and high-resolution radar system, a novel method is proposed, where the polarization and high resolution range profile are integrated for radar target recognition. The physical-statistical non-Gaussian model is used to model for polarimetric high resolution range profile. The model parameters describe the scattering physical characteristics of radar target and are adopted as feature vector for radar target recognition. Furthermore, Parzen window is used to estimate the probability distribution function of model parameter and the classifier is designed via Bayes theorem. The method is applied to the classification of several kinds of missile. Numerical eresults have shown that the method can extract the features which are independent to target orientation and are effective to radar target recognition.