Super-resolution reconstruction-based channel estimation for measured data of passive radar

被引：0
|
作者：
Zhao Z. [1 ]
He S. [1 ]
Li B. [1 ]
Tao P. [1 ]
机构：
[1] School of Information Engineering, Nanchang University, Nanchang
来源：
Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition) | 2023年 / 51卷 / 09期
关键词：
channel estimation; deep learning; DRM-based passive radar; limited samples; super-resolution reconstruction;
D O I：
10.13245/j.hust.238693
中图分类号：
学科分类号：
摘要：
In order to solve the problem of insufficient accuracy in the measured reference channel estimation for DRM (digital radio mondial) based passive radar，this paper studies a super-resolution reconstruction network-based estimation method under limited measured samples．On the design of the deep network，the frequency domain channel response obtained by the LS (least squares) channel estimation method is regarded as a low-resolution image，and is reconstructed into a high-precision channel response through VDSR (very deep super-resolution reconstruction) network，and finally the accurate estimation of the reference signal is obtained．On the construction of the training data set，due to the difficulty of obtaining a large amount of measured data corresponding to different channel environments in DRM-based passive radar，the time domain channel response is first estimated based on the measured data by the LS method to roughly determine the approximate delays and gains of the multipath in the channel．Then，based on the simulation of DRM waveform，enough training data with different channel environments is obtained to train the proposed super-resolution reconstruction network． Finally，the pre-trained model is used to predict the measured data． The experimental results show that the proposed method can achieve higher accuracy than traditional channel estimation methods. © 2023 Huazhong University of Science and Technology. All rights reserved.
引用
收藏
页码：48 / 54
页数：6
相关论文
共 20 条
  • [11] YAROTSKY D，, IVANOV A, Machine learning-assisted channel estimation in massive MIMO receiver[C], Proc of 2021 IEEE 93rd Vehicular Technology Conference, pp. 1-5, (2021)
  • [12] ZHANG S Q, LIU Y Y，, SHI Q, LSRN：a recurrent residual learning framework for continuous wireless channel estimation using super-resolution concept[J], IEEE Access, 8, pp. 38098-38111, (2020)
  • [13] SOLTANI M，, POURAHMADI V，, MIZAEI A, Deep learning-based channel estimation[J], IEEE Communications Letters, 23, 4, pp. 652-655, (2019)
  • [14] HE H T，, WEN C K，, JIN S, Deep learning-based channel estimation for beamspace mmWave massive MIMO systems[J], IEEE Wireless Communications Letters, 7, 5, pp. 852-855, (2018)
  • [15] MA W Y, ZHANG Z C, Sparse channel estimation and hybrid precoding using deep learning for millimeter wave massive MIMO[J], IEEE Transactions on Communications, 68, 5, pp. 2838-2849, (2020)
  • [16] DONG C, LOY C C，, HE K M, Image super-resolution using deep convolutional networks[J], IEEE Transactions on Pattern Analysis and Machine Intelligence, 38, 2, pp. 295-307, (2015)
  • [17] SHI Q, LIU Y Y, ZHANG S Q, Channel estimation for wifi prototype systems with super-resolution image recovery[C], Proc of 2019 IEEE International Conference on Communications, pp. 1-6, (2019)
  • [18] KIM J, LEE J K, LEE K M．, Accurate image super-resolution using very deep convolutional networks[C], Proc of IEEE Conference on Computer Vision and Pattern Recognition, pp. 1646-1654, (2016)
  • [19] DONGHONG OUYANG, LI YUZHOU, WANG ZHI-ZHAN, Channel estimation for underwater acoustic OFDM communications： an image super-resolution approach[C], Proc of 2021 IEEE International Conference on Communications, pp. 1-6, (2021)
  • [20] 35, 4, pp. 871-876, (2013)
12