一种基于Gabor变换的HRRP目标识别方法  

A New Method Based on Gabor Transform for HRRP Target Recognition

作　　者：王锦章 徐冰超 任杰[2] 杨欧[2] 卢文良[2] 刘先康[2] 魏存伟[2] 

机构地区：[1]海军驻北京地区电子设备军事代表室,北京100015 [2]中国人民解放军海军701工厂研发部,北京100015

出　　处：《电子科技》2017年第4期19-21,共3页Electronic Science and Technology

基　　金：国防预研基金资助项目

摘　　要：从模式分类角度讨论了基于高分辨距离像的舰船目标识别问题,提出了一种基于Gabor变换的HRRP目标识别方法。通过对数据进行Gabor变换去除噪声,利用基于小波包分解能量的方法得到信号在不同频带的能量分布特性,最终通过支持向量机进行识别。通过对6类目标实测数据的分析,验证结果表明,该方法在舰船目标识别领域具有良好的应用前景。This paper discuss target recognition by HRRP from the point of view of pattern classification,and propose a new method based on Gabor Transform for HRRP target recognition. Firstly,the de-noise signal could be obtained by the Gabor transform. Then,wavelet packet energy method was used to obtain the energy distribution features in these bands. Finally,the targets are recognized by SVM. The result of experiment with the measured data of6 HRRP targets indicates that the proposed method is efficient and very useful in ship target classification.

关 键 词：高分辨距离像 GABOR变换 小波包能量谱 支持向量机 

分 类 号：TN957.51[电子电信—信号与信息处理]