[1]朱克凡,王杰贵,吴世俊.基于GAN的半监督低分辨雷达目标识别算法[J].探测与控制学报,2019,41(06):57.[doi:.]
 ZHU Kefan,WANG Jiegui,WU Shijun.Semi-supervised Low-resolution Radar Target Recognition Technology Based on Generative Adversarial Network[J].,2019,41(06):57.[doi:.]
点击复制

基于GAN的半监督低分辨雷达目标识别算法()
分享到:

《探测与控制学报》[ISSN:1008-1194/CN:61-1316/TJ]

卷:
41
期数:
2019年06
页码:
57
栏目:
出版日期:
2020-01-15

文章信息/Info

Title:
Semi-supervised Low-resolution Radar Target Recognition Technology Based on Generative Adversarial Network
文章编号:
1008-1194(2019)06-0057-07
作者:
朱克凡1王杰贵1吴世俊2
1.国防科技大学电子对抗学院,安徽 合肥 230037;2.中国人民解放军96713部队,江西 上饶 334100
Author(s):
ZHU Kefan1 WANG Jiegui1 WU Shijun2
1. Electronic Countermeasure Institute of National University of Defense Technology, Hefei 230037, China;2. Unit 96713 of PLA, Shangrao 334100, China
关键词:
低分辨雷达目标识别深度学习生成对抗网络卷积神经网络
Keywords:
low-resolution radar target recognition deep learning generative adversarial network(GAN) convolutional neural networks(CNN)
分类号:
TN959.1
DOI:
.
文献标志码:
A
摘要:
针对雷达侦察过程中数据库标签样本不足导致目标识别率难以提高的问题,提出了基于生成对抗网络(GAN)的半监督低分辨雷达目标识别算法。该算法将现有的少量标签样本和接收到的大量无标签样本作为样本集,使用卷积神经网络(CNN)替代GAN的判别器部分,利用GAN强大的对抗生成能力,提高小标签样本条件下对低分辨雷达目标的分类识别能力。仿真实验结果表明,该算法较传统半监督雷达目标识别方法具有更短的识别时间和更好的识别效果,证明了算法的优越性。
Abstract:
Modern radar target recognition usually encountered the problem of receiving a large number of target echo signals, but the recognition rate was difficult to improve due to insufficient label samples. To achieve low-resolution radar target recognition under small training samples, this paper proposed a semi-supervised low-resolution radar target recognition algorithm based on Generative Adversarial Network (GAN). The algorithm used Convolutional Neural Networks (CNN) instead of the discriminator part of GAN, and used a small number of existing label samples and a large number of unlabeled samples as sample sets, which improved the CNN’s low-resolution radar target under small training sample conditions. The simulation experiment proved that the GAN-based semi-supervised low-resolution radar target recognition method had shorter recognition time and better recognition effect than the traditional semi-supervised radar target recognition method.

参考文献/References:

[1]陈志仁,顾红,苏卫民,等.改进的支持向量机低分辨雷达目标分类算法[J].系统工程与电子技术,2017(11):70-76.
[2]李秋生,谢晓春,朱红,等.分数阶Fourier域低分辨雷达飞机回波的分形特性分析与目标分类[J].计算机应用研究,2018,35(9):315-318+322.[3]王福友,罗钉,刘宏伟.低分辨机载雷达空地运动目标的分类识别算法[J].雷达学报,2014,3(5):497-504.
[4]陈志仁,顾红,苏卫民,等.低分辨雷达目标分类的最小代价拒判算法[J].自动化学报,2018,44(6):104-113.
[5]徐丹蕾,杜兰,王鹏辉,等.采用多任务稀疏学习的雷达HRRP小样本目标识别[J].西安电子科技大学学报,2016,43(2): 23-28.
[6]吴剑旗,田西兰.一种基于半监督学习的窄带雷达目标识别系统[J].中国电子科学研究院学报,2015,10(1): 49-53+101.
[7]田西兰,郭法滨,赵洪立.一种基于半监督学习的弹道目标识别方法[J].雷达科学与技术,2017,15(6):651-655.
[8]李倩,裴炳南,常芳芳.基于多层卷积神经网络的SAR图像分类方法[J].探测与控制学报,2018,40(3):85-90.
[9]HU Guang, WANG Kejun, PENG Yuan, et al. Deep Learning Methods for Underwater Target Feature Extraction and Recognition[J]. Computational Intelligence and Neuroscience, 2018(3):1-10.
[10]王思雨, 高鑫, 孙皓, 等. 基于卷积神经网络的高分辨率SAR图像飞机目标检测方法[J].雷达学报,2017,6(2):195-203.
[11]杨予昊, 孙晶明, 虞盛康, 等. 基于卷积神经网络的高分辨距离像目标识别[J].现代雷达,2017,39(12):24-28.
[12]姚瑶,王战红.基于时频预处理下卷积网络的雷达信号识别[J].探测与控制学报,2018,40(6):99-105.
[13]Salimans T, Goodfellow I, Zaremba W, et al. Improved Techniques for Training GANs [OL]. https://arxiv.org/pdf/ 1606.03498.pdf.
[14]Hong Y, Hwang U, Yoo J, et al. How generative adversarial networks and their variants work: an overview[J]. ACM Computing Surveys, 2017.
[15]唐贤伦, 杜一铭, 刘雨微,等. 基于条件深度卷积生成对抗网络的图像识别方法[J].自动化学报,2018, 44(5):855-864.
[16]FIORE U, SANTIA A D, PERLA F, et al. Using generative adversarial networks for improving classification effectiveness in credit card fraud detection[J]. Information Sciences, 2019,479:448-455.


相似文献/References:

[1]李倩,裴炳南,常芳芳.基于多层卷积神经网络的SAR图像分类方法[J].探测与控制学报,2018,40(03):85.[doi:.]
 LI Qian,PEI Bingnan,CHANG Fangfang.SAR Image Classification Method Based on Multilayer Convolution Neural Network[J].,2018,40(06):85.[doi:.]
[2]阮怀林,杨兴宇.基于栈式稀疏自编码器的有源欺骗干扰识别[J].探测与控制学报,2018,40(04):62.[doi:.]
 RUAN Huailin,YANG Xingyu.Radar Active Deception Identification Method Based on Stacked Sparse Autoencoder[J].,2018,40(06):62.[doi:.]

备注/Memo

备注/Memo:
收稿日期:2019-06-15
基金项目:国防预研基金项目资助(9140C100404120C1003)
作者简介:朱克凡(1994—),男,山东青岛人,硕士研究生,研究方向:深度学习,智能信息处理研究。E-mail:13865993110@163.com.

更新日期/Last Update: 2020-01-13