基于时域回波相关性特征的飞机目标分类方法  

Aircraft Target Classification Based on Correlation Features from Time-domain Echoes

作　　者：杜兰[1] 李林森[1] 李玮璐[1] 王宝帅[1] 史蕙若 

机构地区：[1]西安电子科技大学雷达信号处理国家重点实验室,西安710071

出　　处：《雷达学报（中英文）》2015年第6期621-629,共9页Journal of Radars

基　　金：国家自然科学基金(61271024;61201292;61322103);高等学校博士学科点专项科研基金博导类基金(20130203110013);陕西省自然科学基础研究计划(2015JZ016)~~

摘　　要：该文研究了常规窄带雷达体制下利用时域回波调制周期的差异实现直升机、螺旋桨飞机和喷气式飞机3类飞机目标的分类问题。首先分析3类飞机时域回波调制周期的差异;然后针对3类飞机目标时域回波调制周期的不同,基于时域回波相关性提取了2维特征向量;最后基于仿真数据和实测数据,利用支持向量机(Support Vector Machine,SVM)分类器的分类结果证明了在脉冲重复频率较低时,多普勒谱有一定程度混叠的情况下,时域相关性特征仍能表现出相对较好的分类性能。This paper reports the classification of helicopters, propeller-driven aircraft, and turbojet based on differences in their time-domain modulation periods using a conventional radar system. First, we determine the modulation periods of their time-domain echoes. Then, based on the differences in the time-domain modulation periods, we propose a method for the extraction of time-domain correlation features. Finally, based on the simulated and measured data, via a support vector machine classifier, it is proved that the time-domain correlation features can yield the good classification performance, even with the relatively low pulse repetition frequency, which may induce the ambiguity in Doppler-frequency domain.

关 键 词：目标分类 特征提取 微多普勒效应 时域信号 

分 类 号：TN957.51[电子电信—信号与信息处理]