摘要
分析了直升机目标回波微多普勒特点,提出了表征频域纹理特征的一维局部二进制模式直方图实现流程;通过主分量分析降维处理提取特征;采用支持向量机分类器对3类直升机进行实验验证,给出了不同条件下该方法的识别结果。文中方法在较低重频、强杂波背景、低信噪比时仍能保持良好的识别性能,便于工程实现。
Firstly,the micro-Doppler effect of helicopter is analyzed.Then,one-dimensional local binary pattern(LBP)method is proposed to represent the texture feature of micro-Doppler,followed by the principal component analysis(PCA)to reduce feature dimensions.Finally,the support vector machine(SVM)classifier is utilized to recognize three-class helicopters,and results in different situations are given.The experimental results demonstrate the effectiveness of the proposed method under low pulse repetition frequency,strong clutter or low signal noise ratio conditions,the method is easy to implement.
作者
罗丁利
杨磊
陈尹翔
王勇
徐丹蕾
LUO Dingli;YANG Lei;CHEN Yinxiang;WANG Yong;XU danlei(Xi’an Electronic Engineering Research Institute,Xi’an 710100,China)
出处
《弹箭与制导学报》
CSCD
北大核心
2017年第6期139-144,148,共7页
Journal of Projectiles,Rockets,Missiles and Guidance
关键词
微多普勒
纹理特征
局部二进制模式
主成分分析
支持向量机
micro-Doppler
texture feature
local binary pattern
principal component analysis
support vector machine
作者简介
罗丁利(1974-),男,陕西富平人,研究员,硕士,研究方向:雷达信号处理及目标分类识别技术。
