Radar target recognition based on few-shot learning

被引：29
|
作者：
Yang, Yue [1 ]
Zhang, Zhuo [1 ]
Mao, Wei [2 ]
Li, Yang [1 ,3 ]
Lv, Chengang [1 ]
机构：
[1] Tianjin Univ, Sch Elect & Informat Engn, Tianjin, Peoples R China
[2] China Acad Launch Vehicle Technol, Beijing, Peoples R China
[3] Shihezi Univ, Coll Mech & Elect Engn, Shihezi, Peoples R China
来源：
MULTIMEDIA SYSTEMS | 2023年 / 29卷 / 05期
基金：
中国国家自然科学基金;
关键词：
Radar target recognition; Radar cross-section (RCS); Few-shot learning; Active learning; The least confidence; Edge sampling;
D O I：
10.1007/s00530-021-00832-3
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
With the continuous development of target recognition technology, people pay more and more attention to the cost of sample generation, tag addition and network training. Active learning can choose as few samples as possible to achieve a better recognition effect. In this paper, a small number of the simulation generated radar cross-section time series are selected as the training data, combined with the least confidence and edge sampling, a sample selection method based on few-shot learning is proposed. The effectiveness of the method is verified by the target type recognition test in multi time radar cross-section time series. Using the algorithm in this paper, 10 kinds of trajectory data are selected from all 19 kinds of trajectory data, and the training model is tested, which can achieve similar results with 19 kinds of trajectory data training model. Compared with the random selection method, the accuracy is improved by 4-10% in different time lengths.
引用
收藏
页码：2865 / 2875
页数：11
相关论文
共 50 条
  • [21] Continuous Gesture Sequences Recognition Based on Few-Shot Learning
    Liu, Zhe
    Pan, Cao
    Wang, Hongyuan
    INTERNATIONAL JOURNAL OF AEROSPACE ENGINEERING, 2022, 2022
  • [22] Learning Compositional Representations for Few-Shot Recognition
    Tokmakov, Pavel
    Wang, Yu-Xiong
    Hebert, Martial
    2019 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2019), 2019, : 6381 - 6390
  • [23] Multimodal Few-Shot Learning for Gait Recognition
    Moon, Jucheol
    Nhat Anh Le
    Minaya, Nelson Hebert
    Choi, Sang-Il
    APPLIED SCIENCES-BASEL, 2020, 10 (21): : 1 - 15
  • [24] User-Definable Dynamic Hand Gesture Recognition Based on Doppler Radar and Few-Shot Learning
    Zeng, Xianglong
    Wu, Chaoyang
    Ye, Wen-Bin
    IEEE SENSORS JOURNAL, 2021, 21 (20) : 23224 - 23233
  • [25] Cross Frequency Adaptation for Radar-Based Human Activity Recognition Using Few-Shot Learning
    Dixit, Avinash
    Kulkarni, Vinay
    Reddy, V. V.
    IEEE GEOSCIENCE AND REMOTE SENSING LETTERS, 2023, 20
  • [26] Few-Shot Learning Sensitive Recognition Method Based on Prototypical Network
    Yuan, Guoquan
    Zhao, Xinjian
    Li, Liu
    Zhang, Song
    Wei, Shanming
    MATHEMATICS, 2024, 12 (17)
  • [27] Bronze inscription recognition with distribution calibration based on few-shot learning
    Zheng, Yi
    Yan, Yunfeng
    Qi, Donglian
    4TH INTERNATIONAL CONFERENCE ON INFORMATICS ENGINEERING AND INFORMATION SCIENCE (ICIEIS2021), 2022, 12161
  • [28] Few-shot disease recognition algorithm based on supervised contrastive learning
    Mu, Jiawei
    Feng, Quan
    Yang, Junqi
    Zhang, Jianhua
    Yang, Sen
    FRONTIERS IN PLANT SCIENCE, 2024, 15
  • [29] Few-shot learning-based human behavior recognition model
    Mahalakshmi, V.
    Sandhu, Mukta
    Shabaz, Mohammad
    Keshta, Ismail
    Prasad, K. D. V.
    Kuzieva, Nargiza
    Byeon, Haewon
    Soni, Mukesh
    COMPUTERS IN HUMAN BEHAVIOR, 2024, 151
  • [30] Fish Image Recognition Based on Residual Network and Few-shot Learning
    Yuan P.
    Song J.
    Xu H.
    Nongye Jixie Xuebao/Transactions of the Chinese Society for Agricultural Machinery, 2022, 53 (02): : 282 - 290
12345