基于Hough变换的低分辨率雷达目标识别  

Target Identification for Low-resolution Radar Based on Hough Transform

作　　者：赵林[1] 邱天爽[1] 

机构地区：[1]大连理工大学电子与信息工程学院,辽宁大连116024

出　　处：《现代雷达》2010年第8期58-61,65,共5页Modern Radar

基　　金：国家自然科学基金资助项目(60872122)

摘　　要：针对低分辨率雷达目标的识别问题,提出了一种基于Hough变换的特征提取方法。通过对Hough变换后参数空间进行特征定义来描述参数空间灰度图像的纹理分布特点,进而描述图像空间目标的形状特征。文中利用该方法结合径向基函数神经网络对低分辨率雷达船只目标轮廓像进行特征提取并识别,取得了较高的识别率。A new feature extraction method based on Hough transform is proposed in this paper to solve the problem of target identification for low-resolution radar.Some features are defined in the Hough transform parameter space to describe its texture distribution characteristics which aim to describe the shape of the target in the image space.This method,combined with RBF neural network is used in this paper to identify different ship profiles obtained by a low-resolution radar and achieves a high recognition rate.

关 键 词：低分辨率雷达 HOUGH变换 径向基函数神经网络 

分 类 号：TN957.52[电子电信—信号与信息处理]