摘要
本文讨论了基于径向基函数网络(RBFN)的雷达目标识別问题。在分析了一维距离象特点的基础上,提出了采用非相关幅度平均一维距离象以获取稳定模式这一有效方法。在指出传统经验公式局限性后,给出了一种基于训练样本空间分布来估计高斯核函数形状参数的方法。用微波暗室试验数据进行转台成象并对一维距离象三种模式进行识别分类的结果表明,本文所提出的方法用于研究雷达目标识别是有效的。
The problem of radar target recognition based on a radial basis function network is discussed. On the basis of analyzing the features of one-dimensional range profile, an effective method is proposed, which performs amplitude average of the range profiles to obtain more stable patterns. After pointing out the limitedness of traditional experimental formula, this paper also gives a method of estimating the shape parameter a of a Guassian kernel function based on the spacial distribution of training samples. It is shown from theoretical analysis and experimental results of rotating platform imaging based on data acquired in a microwave anechoic chamber that the method proposed in this paper is promissing in the application of radar target recognition.
基金
电子工业邮电科院基金
关键词
神经网络
径向基函数
距离象
目标识别
雷达
Neural network, Radial basis function, Range profile, Target recog nition