Radar Target Recognition Method for HRRP Based on Geodesic Flow Kernel

被引：0
|
作者：
Yang W. [1 ]
Li W.-J. [1 ]
Liu Y.-X. [1 ]
Li X. [1 ]
机构：
[1] College of Electronic Science and Engineering, National University of Defense Technology, Hunan, Changsha
来源：
Tien Tzu Hsueh Pao/Acta Electronica Sinica | 2023年 / 51卷 / 03期
基金：
中国国家自然科学基金;
关键词：
geodesic flow kernel; high resolution range profile; radar target recognition; SNR mismatch; transfer learning;
D O I：
10.12263/DZXB.20211574
中图分类号：
学科分类号：
摘要：
Non-cooperative target recognition often faces a small number of incomplete training samples, and inconsistent signal-to-noise ratio (SNR) between training samples and test samples. A robust radar target recognition method for high resolution range profile (HRRP) based on geodesic flow kernel is proposed in this paper. It extracts invariant features along the geodesic integral in the Glassman manifold, and has an analytical expression through kernel function mapping. The method also can be used as a preprocessing tool to reduce data noise and improve the recognition performance of other algorithms. Experimental results show that the proposed method has robust recognition ability for SNR mismatch and a small number of incomplete samples, and meets the requirements of real-time. © 2023 Chinese Institute of Electronics. All rights reserved.
引用
收藏
页码：527 / 536
页数：9
相关论文
共 25 条
  • [1] WANG J, ZHENG T, LEI P, Et al., Study on deep learning in radar, Journal of Radars, 7, 4, pp. 395-411, (2018)
  • [2] HAN L, YAO L., A review of methods for HRRP target automatic recognition, Transactions of Beijing Institute of Technology, 40, 4, pp. 351-361, (2020)
  • [3] YANG Z T, DENG J, NALLANATHAN A., Moving target recognition based on transfer learning and three-dimensional over-complete dictionary, IEEE Sensors Journal, 16, 14, pp. 5671-5678, (2016)
  • [4] YANG Y H, SUN J M, YU S K., Aircraft target recognition based on convolutional neural network with transfer learning, Modern Radar, 41, 12, pp. 35-39, (2019)
  • [5] SI J X., Research and Implementation of Radar One-Dimensional Range Profile Target Recognition Method Based on Deep Learning, (2019)
  • [6] WEN Y, SHI L C, YU X, Et al., HRRP target recognition with deep transfer learning, IEEE Access, 8, pp. 57859-57867
  • [7] SHI L C, LIANG Z H, WEN Y, Et al., One-shot HRRP generation for radar target recognition, IEEE Geoscience and Remote Sensing Letters, 19, pp. 1-5, (2022)
  • [8] WANG P H., Study of Radar High Resolution Range Profile Target Recognition Based on Statistical Modeling, (2012)
  • [9] LI W J, YANG W, LI X, Et al., Robust high resolution range profile recognition method for radar targets in noisy environments, Journal of Radars, 9, 4, pp. 622-631, (2020)
  • [10] WANG G S, WANG W Y, LEI Z Y, Et al., A method to improve the generalization ability of HRRP recognition model-deep adaptation networks, 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference, pp. 799-803, (2020)
123