摘要
针对多极化雷达高分辨距离像（HRRP）识别中数据量大、分布复杂和识别算法复杂的问题，提出了基于核函数的识别方法．该方法首先定义了两种基于多极化HRRP的核函数，然后将其分别应用到核主分量分析（KPCA）中降维和提取特征，最后采用最近邻（1NN）分类器和支持矢量机（SVM）分类器对目标进行分类．该方法可以在不丢失极化信息的情况下，将多极化HRRP作为一个整体进行识别，降低了识别算法的复杂度．多极化HRRP数据的仿真实验结果显示，该方法的识别率比单极化HRRP提高7％～10％；与其他多极化HRRP识别方法相比，该方法不仅降低了提取特征的维数，而且还提高了识别性能．
Aiming at the great quantity of multi-polarization high resolution range profile （HRRP）, the complexity of the data distribution and the recognition algorithm, the methods based on kernel methods are proposed. Firstly two kernel functions based on the multi-polarization HRRP are defined, and then two kernel functions are used to the kernel principal component analysis （KPCA） respectively. Finally, the nearest neighbor （1NN） classifier and the support vector machine （SVM） classifier are used for classifying targets. The multi-polarized radar HRRP can be recognized as a whole in the proposed methods, so the complexity of the recognition algorithm is reduced. Experimental results based on simulated multi-polarization HRRP data show that the methods based on the proposed kernel functions can raise the correct recognition rate greatly compared with the methods of single-polarized HRRP recognition. Also, the feature dimension can be decreased and the recognition performance can be improved to some extent compared with other methods of the multi-polarization HRRP.
出处
《西安电子科技大学学报》
EI
CAS
CSCD
北大核心
2010年第1期49-55,共7页
Journal of Xidian University
基金
教育部长江学者和创新团队支持计划资助项目(IRT0645)
国家自然科学基金资助项目(60772140)
国家部委预研项目资助项目
国家部委预研基金资助项目
关键词
高分辨距离像
极化
雷达目标识别
核函数
high-resolution range profile
polarization
radar target recognition
kernel function
