基于独立分量分析的雷达目标识别方法

Radar target recognition method based on independent component analysis

通过分析雷达距离像的数学模型,利用独立分量分析(independent component analysis,ICA)技术提取雷达距离像信号中的独立分量,并定义为独立基波形。将观测信号投影到几个峰度大的独立基波形上,得到的各个投影分量作为待识别的信号特征。由于独立基波形实际上对应了目标回波中的散射中心响应,使得通过该方法提取的特征不仅保持了独立性,而且还具有实际的物理意义。在此基础上,使用支持矢量机(support vectormachine,SVM)作为分类器,进行了仿真实验和对比实验,实验结果表明该方法是有效和可行的。

Based on the analysis of the mathematic model of radar range profile, independent component analysis （ICA） technique is utilized to extract the independent components defined as independent basis waves from radar range profile signals. Through projecting the radar range profiles on the independent basis wave with big kurtosis value, some independent features are acquired. Because the independent basis waves are actually the scattering center responses contained in target echoes, extracted features are not only independent each other, but also have real physical meaning. Further, simulation test and comparison test are carried out using support vector machine （SVM）, and simulation results demonstrated the validity and feasibility of the proposed method.