陈渤1,,,
介茜2,
1.西安电子科技大学雷达信号处理国家重点实验室 西安 710071
2.西安电子科技大学计算机科学与技术学院 西安 710071
基金项目:国家自然科学基金(61771361, 61701379)，国家****科学基金(61525105)
详细信息
作者简介:刘家麒(1994–)，男，河北人，西安电子科技大学在读硕士研究生，研究方向为雷达自动目标识别、机器学习、深度学习。E-mail: jqliu_2@stu.xidian.edu.cn
陈渤：陈 渤(1979–)，男，河南人，博士，教授，博士生导师，主要研究方向为机器学习、统计信号处理、雷达目标识别与检测、深度学习网络、大规模数据处理。E-mail: bchen@mail.xidian.edu.cn
介茜：介 茜(1993–)，女，陕西人，西安电子科技大学在读硕士研究生，研究方向为大数据处理与机器学习。E-mail: xjie@stu.xidian.edu.cn
通讯作者:陈渤 bchen@mail.xidian.edu.cn
中图分类号:TN959.1; TP183计量
文章访问数:2173
HTML全文浏览量:674
PDF下载量:245
被引次数:0
出版历程
收稿日期:2019-01-29
修回日期:2019-04-07
网络出版日期:2019-05-24
Radar High-resolution Range Profile Target Recognition Based on Attention Mechanism and Bidirectional Gated Recurrent
LIU Jiaqi1,,CHEN Bo1,,,
JIE Xi2,
1. National Laboratory of Radar Signal Processing, Xidian University, Xi’an 710071, China
2. School of Computer Science and Technology, Xidian University, Xi’an 710071, China
Funds:The National Natural Science Foundation of China (61771361, 61701379), The National Science Fund for Distinguished Young Scholars (61525105)
More Information
Corresponding author:CHEN Bo, bchen@mail.xidian.edu.cn
摘要
摘要:针对雷达高分辨距离像(HRRP)目标识别问题，传统方法只考虑样本的包络信息而忽略了距离单元间的时序相关性，该文提出了一种基于注意力机制的双向自循环神经网络模型。该模型将时域的HRRP数据通过滑窗分为正反两个序列，并将其分别通过两个相互独立的GRU网络进行特征提取，然后将同时刻提取到的特征进行拼接，从而利用了距离像双向的时序信息。考虑到不同时刻的序列对目标分类的重要性不同，通过注意力机制自适应地对各时刻隐层特征赋予不同的权值，最后根据加权求和后的隐层特征进行目标的识别与分类。实测数据实验结果表明，该文所提方法可以有效完成高分辨距离像的目标识别问题，并且在数据发生一定的时序偏移情况下，仍然可以准确找到目标区域。
关键词:雷达自动目标识别/
高分辨距离像(HRRP)/
门控循环单元/
注意力机制/
平移敏感性
Abstract:To address the problem of radar High-Resolution Range Profile (HRRP) target recognition, traditional methods only consider the envelope information of the sample and ignore the temporal correlation between the range cells. In this study, we propose a bidirectional self-recurrent neural network model based on an attention mechanism. The model divides the HRRP data in the time domain into two sequences, i.e., forward and backward using a sliding window, then extracts the features through two independent GRU networks, and splices the extracted features simultaneously, thus utilizing the bidirectional temporal information of HRRP. Considering that sequences at different moments have different degrees of importance to the target classification, different attention weights are assigned to the hidden layer features at each moment. Finally, the model uses the hidden features weighted summation to obtain target recognition and classification result. Experimental results show that the proposed method can effectively solve the target recognition problem of HRRP, and that the target area can still be accurately identified when the time shift occurs.
Key words:Radar Automatic Target Recognition (RATR)/
High-Resolution Range Profile (HRRP)/
Gated Recurrent Unit (GRU)/
Attention mechanism/
Time-shift sensitivity
PDF全文下载地址:
https://plugin.sowise.cn/viewpdf/198_18f357ed-7a0b-479a-a13f-ef04168373f1_R19014
