电信科学 ›› 2022, Vol. 38 ›› Issue (2): 84-91.doi: 10.11959/j.issn.1000-0801.2022024

• 研究与开发 • 上一篇    下一篇

基于时频图像和高次频谱特征的雷达信号识别

李世通, 全大英, 唐泽雨, 陈赟, 汪晓峰, 金小萍   

  1. 中国计量大学，浙江 杭州 310018
  • 修回日期:2022-01-28 出版日期:2022-02-20 发布日期:2022-02-01
  • 作者简介:李世通（1996- ），男，中国计量大学信息工程学院硕士生，主要研究方向为电子侦察信号处理
    全大英（1979- ），男，中国计量大学副教授、高级工程师，主要研究方向为无线测试系统设计、电子侦察信号处理和智能频谱测量计量
    唐泽雨（1996- ），男，中国计量大学信息工程学院硕士生，主要研究方向为电子侦察信号处理
    陈赟（1997- ），男，中国计量大学信息工程学院硕士生，主要研究方向为电子侦察信号处理
    汪晓锋（1984- ），男，博士，中国计量大学信息工程学院讲师，主要研究方向为复杂数据分析、机器学习及图神经网络
    金小萍（1978- ），女，中国计量大学信息工程学院副教授、硕士生导师，主要研究方向为5G通信、通信检测、物联网通信
  • 基金资助:
    浙江省自然科学基金资助项目(LQ20F020021);浙江省电磁波信息技术与计量检测重点实验室开放式项目(2019KF0003)

Time-frequency image and high-order spectrum characteristics based radar signal recognition

Shitong LI, Daying QUAN, Zeyu TANG, Yun CHEN, Xiaofeng WANG, Xiaoping JIN   

  1. China Jiliang University, Hangzhou 310018, China
  • Revised:2022-01-28 Online:2022-02-20 Published:2022-02-01
  • Supported by:
    Zhejiang Provincial Natural Science Foundation of China(LQ20F020021);Open Project Funding of the Key Laboratory of Electromagnetic Wave Information Technology and Metrology of Zhejiang Province(2019KF0003)

在线阅读

13

PDF下载

102

摘要：

针对低信噪比下雷达信号识别准确率较低的问题，提出了一种基于时频图像和高次频谱特征联合的雷达信号识别算法。该算法首先对信号采用Choi-Williams分布（Choi-Williams distribution，CWD）变换获取时频图像，接着对时频图预处理并用灰度共生矩阵（gray level co-occurrence matrix，GLCM）提取纹理特征；然后利用对称Holder系数提取信号的高次频谱特征；再将纹理特征和高次频谱特征构成一组联合特征向量，最后通过支持向量机（support vector machine，SVM）实现雷达信号的分类识别。通过对8种典型雷达信号进行实验，结果表明本算法在信噪比为-8 dB时，不同信号的识别准确率能达到90%以上。

关键词: 雷达信号识别, 高次频谱, Choi-Williams时频分布, 支持向量机

Abstract:

Aiming at improving the accuracy of radar signal recognition under a low signal-to-noise ratio, a radar signal recognition algorithm based both on time-frequency image and high-order spectrum feature was proposed.Firstly, the time-frequency image was obtained by Choi-Williams distribution (CWD) transform, based on which the time-frequency image was preprocessed and the texture features were extracted by gray level co-occurrence matrix (GLCM) in sequence.Meanwhile, the symmetrical holder coefficient was used to extract the high-order spectral features of the signal.Then, the texture features and high-order spectrum features were form a new set of joint feature vectors.Finally, with the proposed feature vector the classification and recognition of radar signals were implemented by a support vector machine.The algorithm was verified on the data set with eight typical radar signals.Experimental results show that the recognition accuracy of different radar signals can achieve higher than 90% when the signal-to-noise ratio is -8 dB.

Key words: radar signal recognition, high order spectrum, Choi-Williams time frequency distribution, support vector machine

中图分类号: 

No Suggested Reading articles found!