系统工程与电子技术 ›› 2020, Vol. 42 ›› Issue (8): 1703-1709.doi: 10.3969/j.issn.1001-506X.2020.08.09

• 传感器与信号处理 • 上一篇    下一篇

基于双谱-谱图特征和深度卷积神经网络的HRRP目标识别方法

卢旺(), 张雅声(), 徐灿(), 林财永()   

  1. 航天工程大学宇航科学与技术系, 北京 101400
  • 收稿日期:2019-10-23 出版日期:2020-08-01 发布日期:2020-08-03
  • 作者简介:卢旺 (1993-),男,博士研究生,主要研究方向为雷达信号识别、深度学习。E-mail:wanglu199310@163.com|张雅声 (1974-),女,研究员,博士研究生导师,博士,主要研究方向为航天任务分析、空间目标特性分析与识别。E-mail:lizhizys@139.com|徐灿 (1985-),男,讲师,硕士研究生导师,博士,主要研究方向为空间目标特性分析与识别、模式识别与机器学习。E-mail:13466509187@139.com|林财永 (1989-),男,讲师,博士,主要研究方向为目标识别、模式识别与机器学习。E-mail:lincyvip@163.com
  • 基金资助:
    国家自然科学基金(61304228)

HRRP target recognition method based on bispectrum-spectrogram feature and deep convolutional neural network

Wang LU(), Yasheng ZHANG(), Can XU(), Caiyong LIN()   

  1. Department of Aerospace Science and Technology, Space Engineering University, Beijing 101400, China
  • Received:2019-10-23 Online:2020-08-01 Published:2020-08-03
  • Supported by:
    国家自然科学基金(61304228)

摘要:

针对雷达高分辨距离像(high resolution range profile, HRRP)目标识别中有效表示和特征提取这一关键问题,提出了基于双谱-谱图特征和深度卷积神经网络(deep convolution neural network, DCNN)的识别方法。首先,提取HRRP的双谱-谱图特征表示作为CNN的输入。然后,通过网络训练提取出深层本质特征,实现对雷达目标的识别。最后,对不同特征表示的识别结果进行对比。采用卫星目标实测数据进行实验,结果表明,该方法可以准确有效地识别雷达目标,而且与其他常用特征表示相比,双谱-谱图特征表示具有更好的识别准确率和噪声鲁棒性。

关键词: 雷达自动目标识别, 高分辨距离像, 双谱-谱图特征, 深度卷积神经网络

Abstract:

Aiming at the key problem of effective representation and extraction of features in radar high resolution range profile (HRRP) target recognition, a recognition method based on bispectrum-spectrogram feature and deep convolution neural network (DCNN) is proposed. Firstly, this method extracts the bispectrum-spectrogram feature representation of HRRP as the input of the CNN. Then, the deep and essential features are extracted by the network training and the radar targets can be recognized. Finally, the recognition results of different feature representations are compared. The experimental results of the satellite target measured data show that the method can recognize radar target effectively and accurately, and the bispectrum-spectrogram feature has better recognition accuracy and noise robustness than other commonly used HRRP feature representations.

Key words: radar automatic target recognition (RATR), high resolution range profile (HRRP), bispectrum-spectrogram feature, deep convolution neural network (DCNN)

中图分类号: