简涛,,
徐从安,
何友,
孙顺
海军航空大学 ??烟台 ??264001
基金项目:国家自然科学基金(61471379, 61790551, 61102166),泰山****工程专项
详细信息
作者简介:郭晨:女,1990年生,博士生,研究方向为雷达目标识别、深度学习
简涛:男,1980年生,副教授,研究方向为雷达信号处理、目标识别
徐从安:男,1987年生,讲师,研究方向为多目标跟踪、信息融合、深度学习
何友:男,1956年生,教授,研究方向为信息融合、军事大数据
孙顺:男,1992年生,博士生,研究方向为信息融合、无源定位、协同控制
通讯作者:简涛 work_jt@163.com
中图分类号:TN957.51计量
文章访问数:2670
HTML全文浏览量:1785
PDF下载量:173
被引次数:0
出版历程
收稿日期:2018-07-06
修回日期:2019-01-10
网络出版日期:2019-01-22
刊出日期:2019-06-01
Radar HRRP Target Recognition Based on Deep Multi-Scale 1D Convolutional Neural Network
Chen GUO,Tao JIAN,,
Congan XU,
You HE,
Shun SUN
Naval Aviation University, Yantai 264001, China
Funds:The National Natural Science Foundation of China (61471379, 61790551, 61102166), The Taishan Scholar Project of Shandong Province
摘要
摘要:为满足雷达舰船目标识别的高实时性和高泛化性的需求,该文提出了一种基于深度多尺度1维卷积神经网络的目标高分辨1维距离像(HRRP)识别方法。针对高分辨1维距离像特征提取难的问题,所提方法通过共享卷积核的权值,使用多尺度的卷积核提取不同精细度的特征,并构造中心损失函数来提高特征的分辨能力。实验结果表明,该模型可以显著提高目标在非理想条件下的识别正确率,克服目标姿态角敏感性问题,具有良好的鲁棒性和泛化性。
关键词:雷达目标识别/
高分辨1维距离像/
多尺度/
卷积神经网络/
中心损失函数
Abstract:In order to meet the demand for high real-time and high generalization performance of radar recognition, a radar High Resolution Range Profile (HRRP) recognition method based on deep multi-scale one dimension convolutional neural network is proposed. The multi-scale convolutional layer that can represent the complex features of HRRP is designed based on two features of the convolution kernels which are weight sharing and extraction of different fineness features from different scales, respectively. At last, the center loss function is used to improve the separability of features. Experimental results show that the model can greatly improve the accuracy of the target recognition under non-ideal conditions and solve the problem of the target aspect sensitivity, which also has good robustness and generalization performance.
Key words:Radar target recognition/
High Resolution Range Profile (HRRP)/
Multi-scale/
Convolutional Neural Network (CNN)/
Center loss
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=ed51baaf-2209-4105-bc36-a7bd8713bb69