For the recognition of high-resolution range profile （HRRP） in radar, the weighted HRRP can reduce the instability of range cells caused by the attitude change of targets. A novel approach is proposed to optimize the weighted HRRP. In the approach, the separability of weighted HRRPs in different targets is measured by de- signing an objective function, and the weighted coefficients are computed by using the gradient descent method, thus enhancing the influence of stable range cells. Simulation results based on five aircraft models show that the approach can effectively optimize the weighted HRRP and improve the recognition accuracy.
该文针对雷达目标高分辨距离像(High-Resolution Range Profile,HRRP)识别中距离单元回波幅值统计建模所面临的概率密度模型选择问题,提出一种基于半参数化概率密度估计的雷达目标识别方法。半参数化概率密度估计从参数化概率密度估计出发,有效利用了高分辨距离像各距离单元幅值近似服从Gamma分布的经验知识,并且通过非参数化修正因子对Gamma模型进行修正,达到参数化方法和非参数化方法优缺互补的目的。基于5种飞机模型高分辨距离像数据的仿真实验证明了该文方法的有效性。
针对雷达目标高分辨距离像(High-Resolution Range Profile,HRRP)识别中等角域划分造成的目标散射特性失配问题,提出一种基于核主分量分析重构的雷达目标识别方法。该方法在等角域划分下利用核主分量分析提取每个角域内HRRP的特征子空间,再将测试样本投影到各角域特征子空间中进行重构,最后通过计算最小重构误差来判别测试样本的类别。基于5种飞机目标的仿真实验表明,核主分量分析重构方法可以松弛角域划分范围,降低角域划分的精度要求,相比主分量分析重构方法和最大相关系数模板匹配法有效提高了识别性能。
