系统工程与电子技术 ›› 2025, Vol. 47 ›› Issue (7): 2146-2153.doi: 10.12305/j.issn.1001-506X.2025.07.08

• 传感器与信号处理 • 上一篇    

基于高分辨谱估计的雷达目标分类方法

张梦泽, 田黎育   

  1. 北京理工大学集成电路与电子学院智能电子信息系统研究所, 北京 100081
  • 收稿日期:2024-05-15 出版日期:2025-07-16 发布日期:2025-07-22
  • 通讯作者: 田黎育
  • 作者简介:张梦泽 (1999—), 男, 硕士研究生, 主要研究方向为雷达信号处理、目标分类和识别
    田黎育 (1975—), 男, 副教授, 博士, 主要研究方向为雷达信号处理、目标分类和识别

Radar target classification method based on high resolution spectral estimation

Mengze ZHANG, Liyu TIAN   

  1. Institute of Intelligent Electronic Information System, School of Integrated Circuits and Electronics, Beijing Institute of Technology, Beijing 100081, China
  • Received:2024-05-15 Online:2025-07-16 Published:2025-07-22
  • Contact: Liyu TIAN

摘要:

针对常规窄带雷达体制下利用高分辨谱估计的方法对人、车、无人机等地面及低空运动目标的分类问题,首先通过高分辨谱估计的方法提取回波信号频谱的能量分布特征。然后,对回波信号时域和频域特性进行分析, 提取目标的速度、雷达截面积(radar cross section, RCS)、时域波形熵、幅度相对值、频域方差等特征, 并根据目标实际运动情况划分速度区间, 设计相应的反向传播(back-propagation, BP)神经网络模型。最后,基于实测雷达回波数据验证了所提高分辨谱估计的目标分类算法具有较好的分类效果。

关键词: 高分辨谱估计, 能量分布特征, 速度区间, 反向传播神经网络

Abstract:

To address the classification problem of ground and low-altitude moving targets such as people, vehicles, and unmanned aerial vehicles using high-resolution spectrum estimation in conventional narrowband radar system, the energy distribution characteristics of the echo signal spectrum are extracted through high-resolution spectral estimation firstly. Then, the time domain and frequency domain characteristics of the echo signal are analyzed, and the target speed, radar cross section (RCS), time domain waveform entropy, amplitude relative value, and frequency domain variance are extracted. According to the actual motion of the target, the velocity interval is divided, and a corresponding back-propagation (BP) neural network model is designed. Finally, the experiment based on the measured radar echo data proves that the target classification algorithm with high-resolution spectrum estimation has a significant classification effect.

Key words: high-resolution spectrum estimation, energy distribution characteristic, velocity interval, back-propagation (BP) neural network

中图分类号: