基于时频图像三维熵特征的雷达信号识别

针对雷达信号识别算法存在着准确率低以及抗噪性差的问题,提出基于时频图像三维熵特征的雷达信号识别算法。该方法对雷达信号时频变换后得到的时频灰度图提取其香农熵(Sh En)、奇异谱熵(Ss En)和范数熵(No En),并将三维熵值作为信号识别的特征向量,采用支持向量机实现信号的分类识别。仿真实验表明,提出的算法能够在低信噪比下得到较高的正确识别率。

Radar Signal Recognition Based on Three Dimensional Entropy Features of Time-Frequency Image

To solve the existing problems of low recognition rate and noise problem in radar signal recognition,this paper proposes a new method. This method extracts the shannon entropy (ShEn), singular spectrum entropy (SsEn)and norm entropy (NoEn)from the time-frequency image of radar signal. The three dimensional entropy feature vector realizes the recognition of the signal classification based on Support Vector Machine (SVM). Simulation results show that this method can get very satisfactory recognition correct rate when SNR varies in the larger range. It is proved to be a valid and practical approach.