模糊聚类在舰船目标识别标准模型库的应用

Application of Fuzzy Clustering Analysis in Model Database of Identify Vessels

对于给定特征的海上舰船目标,使用了模糊聚类的方法(包括三种解算方法),获得目标的分类并形成标准模型库。同时引入了聚类分析有效性评价的F统计量,实现了模糊聚类的自适应性,避免了聚类数目选择上存在的主观性。聚类结果表明:对于复杂的战场环境,此方法设计可行有效,建立了标准模型库就可以对获得目标特征样本在标准模型库中进行匹配,进而完成目标识别,具有一定的应用前景。

For the targets on the sea with given characteristics, using the fuzzy clustering method （including 3 kinds of solution method）, and a classification standard model database is formed. F-statistic is introduced to evaluate the effectiveness of the cluster analysis for re alizing a self-adaptive fuzzy clustering and avoiding subjectivity in the selection of cluster number. The results showed that in the complex bat tlefield environment,the combination of the method is feasible and effective. For the characteristics of the target obtained subsequently, a standard model database is usd for matching them.