论文部分内容阅读
研究了一种基于前向散射雷达的车辆目标自动识别方法:分析了前向散射雷达回波与目标速度、轮廓等目标特性之间的关系;提出了主瓣对齐的功率谱预处理方法,采用主成分分析方法分析了不同类别车辆的前向散射雷达功率谱的特性;提出了基于多元线性回归的目标特征提取方法,比较了K最近邻法和Bayes分类器对不同特征集的识别性能.实现结果表明,本文采用的特征提取方法显著改善了识别效果.
A vehicle target automatic recognition method based on forward scatter radar is studied. The relationship between forward scatter radar echoes and target speed, contour and other target characteristics is analyzed. A power spectrum preprocessing method with main lobe alignment is proposed. Principal Component Analysis (PCA) method is used to analyze the characteristics of the power spectrum of forward scatter radar in different types of vehicles. A target feature extraction method based on multivariate linear regression is proposed, and the recognition performance of different feature sets is compared between K nearest neighbor method and Bayes classifier. The results show that the feature extraction method used in this paper has significantly improved the recognition effect.