基于Wigner-Ville分布的空间目标多姿态角特征融合识别算法  

Wigner-Ville Distribution-Based Space Target Multi-Attitude Angles Feature Fusion Recognition Algorithm

作　　者：李超[1] 陈曾平[2] 杨霄鹏[1] 许人灿[2] 高磊[2] 

机构地区：[1]空军工程大学电讯工程学院,陕两西安710077 [2]国防科技大学ATR实验室,湖南长沙410073

出　　处：《电子学报》2008年第3期531-536,共6页Acta Electronica Sinica

基　　金：“863”国防科研计划外项目(No．2004AA731270)

摘　　要：通过参考空间目标实测数据库,提出了一种基于Wigner-Ville(WV)分布的空间目标多姿态角特征融合识别算法.其利用信息融合技术及矩阵奇异值的特性,对不同姿态角的参考特征矢量进行加权处理,获得表征目标的融合特征矢量.通过大量实测数据验证,本方法对空间目标能够正确判决分类,并具有一定的实时性.Refer to the space object real measure database, a Wigner-Ville distribution-based space object multi-attitude angles feature fusion recognition method is presented. The algorithm designs the weights of referenced feature vectors with diverse attitude angles using information fusion technology and the specialities of matrix singularity value, and acquires fusion feature vector that can identify the space object with information fusion technology. By means of validation with measurement data, this method can recognize and classify space objects exactly and timely.

关 键 词：WIGNER-VILLE分布 多姿态角 信息融合 融合特征矢量 

分 类 号：TN957[电子电信—信号与信息处理]