<font face="宋体">基于微多普勒特征的目标分类</font>

基于微多普勒特征的目标分类

摘要: 讨论了基于微多普勒特征的目标分类. 目标的回波由散射中心模拟，经由希尔伯特黄变换得到各固有模态函数的瞬时振幅与瞬时频率，以其范数作为特征向量，而分类器采用支持向量机. 算例表明该方法具有较高识别率.

Abstract: Target classification by microDoppler feature is discussed in this paper. The returned wave is simulated by scattering centers. HilbertHuang Transform (HHT) is applied to returned waves to extract the instantaneous amplitudes and frequencies of intrinsic mode functions(IMF). The norm of amplitudes and frequencies are adopted as feature vectors, and support vector machine(SVM) is used as a classifier. Examples show that the proposed method has high recognition rate under low signalnoise ratio.