摘要
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。
Aiming at the target＇ s electromagnetism scatter characteristic mismatch problem caused by equiangular division in radar high-resolution range profile （HRRP） recognition, an approach based on kernel principle component analysis reconstruction is proposed in this paper. First, it utilizes the kernel principle component analysis to extract eigen subspace in each equiangular sector, and then, the test sample is reconstructed by projecting it into the eigen subspace of each angular sector, finally, the type of test sample is determined by calculating the minimum reconstruction error. The simulation results for five aircraft models show that the proposed approach relaxes the angular sector and the requirement for angular division precision, and effectively improves the recognition accuracy compared with the principle component analysis reconstruction and maximum correlation coefficient template matching methods.
出处
《兵工学报》
EI
CAS
CSCD
北大核心
2010年第6期697-702,共6页
Acta Armamentarii
基金
装备预研重点基金(N601-41)
中电集团第十四研究所院士基金(2008041001)
关键词
信息处理技术
高分辨距离像
雷达自动目标识别
核主分量分析重构
information processing
high-resolution range profile
radar automatic target recognition
kernel principle component analysis reconstruction
