摘要
目标的雷达散射截面(RCS)包含了丰富的目标类别信息,如何有效利用目标RCS特征对空间目标的雷达识别具有重要意义.文中提取中心矩作为特征向量,采用主分量分析(PCA)进一步进行特征压缩,利用支撑矢量机(SVM)分类算法来实现识别.基于实测数据的仿真实验结果表明,该方法具有较好的识别性能和推广能力.
The radar cross section (RCS) of targets contains abundant classification information, which is very important to radar automatic space target recognition. A multi-class support vector machine (SVM) classifier is designed to classify space objects based on the selected central moments features by using principal component analysis(PCA). The experimental comparisons based on measured data show that the proposed method achieves good classification performance and low computational complexity.
出处
《应用科技》
CAS
2007年第1期1-4,共4页
Applied Science and Technology
基金
国家自然科学基金资助项目(60302009)
关键词
中心矩特征
主分量分析
支撑向量机
目标识别
central moment feature
principal component analysis
support vector machine
target recognition