西安电子科技大学学报 ›› 2024, Vol. 51 ›› Issue (1): 41-51.doi: 10.19665/j.issn1001-2400.20230402

• 信息与通信工程 • 上一篇    下一篇

基于注意力自相关机制的剩余杂波抑制方法

申露1(), 苏洪涛1(), 汪晋1,2(), 毛智1(), 景鑫琛1(), 李泽1()   

  1. 1.西安电子科技大学 雷达信号处理全国重点实验室,陕西 西安 710071
    2.南京电子研究所,江苏 南京 210039
  • 收稿日期:2022-10-25 出版日期:2023-05-17 发布日期:2023-05-17
  • 通讯作者: 苏洪涛(1974—),男,教授,E-mail:suht@xidian.edu.cn
  • 作者简介:申露(1995—),男,西安电子科技大学博士研究生,E-mail:imlbtr@163.com;
    汪晋(1985—),男,西安电子科技大学博士研究生,E-mail:wjkbf1926@sina.com;
    毛智(1997—),男,西安电子科技大学博士研究生,E-mail:zmao@stu.xidian.edu.cn;
    景鑫琛(1997—),男,西安电子科技大学博士研究生,E-mail:18292814263@163.com;
    李泽(1992—),女,西安电子科技大学博士研究生,E-mail:himmelize@163.com.
  • 基金资助:
    国家自然科学基金(62201429);中央高校基本科研业务费专项资金(QTZX22156)

Attention autocorrelation mechanism-based residual clutter suppression method

SHEN Lu1(), SU Hongtao1(), WANG Jin1,2(), MAO Zhi1(), JING Xinchen1(), LI Ze1()   

  1. 1. National Key Laboratory of Radar Signal Processing,Xidian University,Xi’an 710071,China
    2. Nanjing Research Institute of Electronics Technology,Nanjing 210039,China
  • Received:2022-10-25 Online:2023-05-17 Published:2023-05-17

摘要:

雷达工作时面临着复杂多变的环境,杂波特性经常呈现非均匀性和时变性。未被完全抑制的杂波剩余可能会产生大量虚警,进而导致虚假航迹产生或目标跟踪精度降低。在严重情况下,这些虚警还可能使雷达数据处理系统饱和,影响雷达系统的探测能力。传统的剩余杂波抑制算法需要进行特征提取和构建分类器两个步骤,存在泛化能力差、特征组合难和分类器要求高等问题。为解决这些问题,受到自注意力机制和领域知识的启发,提出了一种数据与知识双驱动的注意力自相关机制。该机制可以有效提取用于区分目标和杂波的雷达回波相互关系的深度特征。同时,基于该机制,构建了一种剩余杂波抑制方法,充分利用雷达回波特征,提高了算法在剩余杂波抑制方面的性能。仿真和实测数据处理结果表明,该方法在剩余杂波抑制方面具有显著的性能优势和泛化能力。此外,该方法的并行计算结构可以提高算法的运行效率。

关键词: 剩余杂波抑制, 注意力自相关机制, 深层特征, 神经网络

Abstract:

Radar systems are subject to an ever-changing and complex environment that creates a non-uniform and time-varying clutter.The unsuppressed residual clutter can produce a significant number of false alarms,leading to a degraded target tracking performance,spurious trajectories creation,or saturation data processing systems,which in turn decreases the detection ability of the radar system.Conventional residual clutter suppression algorithms typically require feature extraction and classifier construction.These steps can result in poor generalization capability,difficulty in feature combination,and high requirements for the classifier.To address these issues,inspired by self-attention mechanisms and domain knowledge,this paper proposes a data- and knowledge-driven attention autocorrelation mechanism,which can effectively extract deep features of the radar echo to distinguish between targets and clutter,on the basis of which a residual clutter suppression method is constructed using the attention autocorrelation mechanism,which makes full use of the radar echo feature,thereby improving the residual clutter suppression capability.Simulation and measurement results demonstrate that this method has advantages of a significant performance and generalization capability for residual clutter suppression.Additionally,its parallel computing structure enhances the operational efficiency of the algorithm.

Key words: residual clutter suppression, attention autocorrelation mechanism, deep-features, neural networks

中图分类号: 

  • TN957