基于Choi-Williams时频图像特征的雷达辐射源识别
白航;赵拥军;胡德秀;徐永刚
【期刊名称】《数据采集与处理》 【年(卷),期】2012(027)004
【摘要】针对复杂体制雷达辐射源识别,提出一种基于Choi-Williams时频图像的雷达辐射源信号特征提取和识别方法,将信号识别转化为图像识别问题.首先对雷达辐射源信号进行Choi-Williams时频变换,将得到的时频图转化为灰度图像；然后采用一系列图像处理方法对时频图像进行增强和去噪,之后将灰度图像转化为二值图像,并剪切掉不含信号的图像区域；最后分别提取二值图像的中心矩和伪Zernike矩作为识别特征,并采用支持向量机分类器实现信号的分类识别.文中针对8种常见雷达信号识别进行了仿真实验,结果表明在较大的信噪比范围内,该方法能获得较为满意的识别率,其中当信噪比为—3 dB时,采用伪Zernike矩特征平均识别率仍能达到92％,验证了所提出方法的有效性.%To correctly classify advanced radar emitter signals, a novel approach using the image feature of Choi-Williams time-frequency distribution for radar emitter signal recognition is proposed. It transforms the classification of emitter signals into image processing and image recognition. Time-frequency images of radar emitter signals are obtained by using Choi-Williams distribution, and then these images are transformed into grayscale ones. A series of image processing methods are adopted for time-frequency image enhancement and de-noising. After that, the grayscale images are converted into binary images. Moreover, the areas
基于Choi-Williams时频图像特征的雷达辐射源识别
