基于快速密度搜索聚类算法的极化HRRP分类方法

Target Recognition for Polarimetric HRRP Based on Fast Density Search Clustering Method

该文针对人造目标的极化高分辨距离像,提出一种基于快速密度搜索聚类算法的分类方法。首先根据散射结构在频率和极化维度的特性,对散射中心的类型进行判别,在此基础上构造目标分类的特征矢量。然后采用快速密度搜索聚类算法,实现目标的分类。仿真实验结果表明,文中构建的特征矢量能较好地描述目标的结构属性,具有较强的可分性。而快速密度搜索聚类算法简单高效,在人造目标的分类识别中具有极大的应用潜力。

A classification algorithm based on the fast density search clustering method is proposed for polarimetric High Resolution Range Profile （HRRP） of man-made target. The polarization and frequency features are used to discriminate scattering centers in order to obtain the feature vectors for target classification. After that, the fast density search clustering method is applied to classifying the man-made target. The experiments show that the feature vectors for target classification can describe the structural properties of the target and can easily be classified. The fast density search clustering method operates simply and efficiently and can be applied to the man-made target classification with excellent performance.