基于灰度共生矩阵的微动干扰分类识别

针对雷达成像中面临的调制转发微动干扰、微动散射波干扰、脉冲卷积微动干扰3种新型微动干扰样式的识别问题，提出一种基于灰度共生矩阵的干扰识别方法。该方法从图像域角度出发，首先对雷达接收信号矩阵进行灰度化处理，然后利用灰度共生矩阵提取其纹理参数并构造特征参数，最后采用KNN分类器实现了对雷达接收信号中目标回波和3种微动干扰样式的检测与识别。仿真实验结果表明，当信噪比为-5 dB时，不同干信比下4种信号样式的识别率均能够达到90%以上，每种信号样式整体识别率在98%以上；当信噪比为5 dB时，不同干信比下4种信号样式的识别率均能够达到95%以上，每种信号样式整体识别率在99%以上。

A Micro-Motion Jamming Classification and Recognition Method -Based on Gray-Level Co-Occurrence Matrix

A jamming recognition method based on gray-level co-occurrence matrix is proposed for discriminating micro-motion jamming patterns including modulation and repeater micro-motion jamming from micro-motion scatter-wave jamming and pulse convolution micro motion jamming. Firstly, from the perspective of image domain, the received radar signal matrix is grayed. Then, the texture parameters are extracted by using the gray level co occurrence matrix to construct feature parame ters. Finally, K Nearest Neighbor (KNN) classifier is adopted to test the jamming recognition rate. The simulation results show that the recognition method can effectively classify and recognize target echo without jamming and three kinds of micro motion jamming patterns under condition of noisy environment. When the signal to noise ratio is -5 dB, the overall recognition rate is over 98%. When the signal to noise ratio is -5 dB, the recognition rate of four kinds of signal is over 90% under different jammer to signal ratios, and the overall recognition rate of each kind of signal is over 98%. When the signal-to-noise ratio is 5 dB, the recognition rate of four kinds of signal is over 95% under different jammer-to-signal ratios, and the overall recognition rate of each kind of signal is over 99%.