Volume 11 Issue 4
Aug.  2022
Turn off MathJax
Article Contents
WANG Ruyi, ZHANG Hanqing, HAN Bing, et al. Multiangle SAR dataset construction of aircraft targets based on angle interpolation simulation[J]. Journal of Radars, 2022, 11(4): 637–651. doi: 10.12000/JR21193
Citation: WANG Ruyi, ZHANG Hanqing, HAN Bing, et al. Multiangle SAR dataset construction of aircraft targets based on angle interpolation simulation[J]. Journal of Radars, 2022, 11(4): 637–651. doi: 10.12000/JR21193

Multiangle SAR Dataset Construction of Aircraft Targets Based on Angle Interpolation Simulation

DOI: 10.12000/JR21193
Funds:  The National Natural Science Foundation of China (61431018)
More Information
  • Corresponding author: HAN Bing, han_bing@mail.ie.ac.cn
  • Received Date: 2021-11-27
  • Accepted Date: 2022-01-27
  • Rev Recd Date: 2022-01-26
  • Available Online: 2022-02-11
  • Publish Date: 2022-03-10
  • With the expansion of Synthetic Aperture Radar (SAR) applications and the development of SAR data acquisition technology, multiangle SAR datasets of various typical targets need to be constructed. Presently, a comprehensive multiangle SAR image dataset for aircraft targets is still lacking. This study explores a method of dataset construction based on the acquisition of actual data and intelligent simulation. Multiangle SAR images of aircraft targets are collected through flight tests, and the interpolation simulations of SAR images of specific angles are realized based on scattering analysis and self-attention generative adversarial network, which provide a new solution for dataset construction and expansion. Finally, under the assumption that some data are missing, the similarities between the simulated and actual images are evaluated using six evaluation indices, which verify the effectiveness of the proposed method.

     

  • loading
  • [1]
    李彩萍, 张永军. 典型目标SAR图像模拟[J]. 指挥技术学院学报, 1999, 10(2): 60–64, 70.

    LI Caiping and ZHANG Yongjun. SAR image simulation of typical object[J]. Journal of Institute of Command and Technology, 1999, 10(2): 60–64, 70.
    [2]
    李国靖, 叶伟, 劳国超, 等. 欺骗目标仿真SAR图像可信度评估方法[J]. 电子信息对抗技术, 2018, 33(3): 53–58. doi: 10.3969/j.issn.1674-2230.2018.03.011

    LI Guojing, YE Wei, LAO Guochao, et al. Credibility assessment for simulated SAR image of deceptive target[J]. Electronic Information Warfare Technology, 2018, 33(3): 53–58. doi: 10.3969/j.issn.1674-2230.2018.03.011
    [3]
    GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial networks[J]. Advances in Nerual Information Processing System, 2014, 3: 2672–2680. doi: 10.1145/3422622
    [4]
    GUO Jiayi, LEI Bin, DING Chibiao, et al. Synthetic aperture radar image synthesis by using generative adversarial nets[J]. IEEE Geoscience and Remote Sensing Letters, 2017, 14(7): 1111–1115. doi: 10.1109/LGRS.2017.2699196
    [5]
    ZHANG Mingrui, CUI Zongyong, WANG Xianyuan, et al. Data augmentation method of SAR image dataset[C]. 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 2018: 5292–5295.
    [6]
    张明蕊. SAR图像数据分集与扩容方法研究[D]. [硕士论文], 电子科技大学, 2019.

    ZHANG Mingrui. Research of SAR image data dversity and data augmentation method[D]. [Master disseration] School of Information and Communication Engineering, 2019.
    [7]
    孙智博, 徐向辉. 基于谱归一化生成对抗网络的目标SAR图像仿真方法[J]. 计算机与现代化, 2020(8): 14–20. doi: 10.3969/j.issn.1006-2475.2020.08.003

    SUN Zhibo and XU Xianghui. Simulation method of target SAR image based on spectral normalization generative adversarial network[J]. Computer and Modernization, 2020(8): 14–20. doi: 10.3969/j.issn.1006-2475.2020.08.003
    [8]
    LIU Lei, PAN Zongxu, QIU Xiaolan, et al. SAR target classification with CycleGAN transferred simulated samples[C]. IGARSS 2018-2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 2018: 4411–4414.
    [9]
    林翊青, 李景文. 大距离徙动情况下距离多普勒(RD)算法与后向投影(BP)算法的比较[J]. 雷达科学与技术, 2004, 2(6): 349–354. doi: 10.3969/j.issn.1672-2337.2004.06.007

    LIN Yiqing and LI Jingwen. Comparison of RD algorithm and BP algorithm under severe range migration[J]. Radar Science and Technology, 2004, 2(6): 349–354. doi: 10.3969/j.issn.1672-2337.2004.06.007
    [10]
    黄培康, 殷红成, 许小剑. 雷达目标特性[M]. 北京: 电子工业出版社, 2005: 51–63.

    HUANG Peikang, YIN Hongcheng, and XU Xiaojian. Radar Target Characteristic[M]. Beijing: Publishing House of Electronics Industry, 2005: 51–63.
    [11]
    TENG Fei, HONG Wen, and LIN Yun. Aspect entropy extraction using circular SAR data and scattering anisotropy analysis[J]. Sensors, 2019, 19(2): 346. doi: 10.3390/s19020346
    [12]
    邹秀芳, 朱定局. 生成对抗网络研究综述[J]. 计算机系统应用, 2019, 28(11): 1–9. doi: 10.15888/j.cnki.csa.007156

    ZOU Xiufang and ZHU Dingju. Review on generative adversarial network[J]. Computer Systems &Applications, 2019, 28(11): 1–9. doi: 10.15888/j.cnki.csa.007156
    [13]
    ZHANG H, GOODFELLOW I, METAXAS D, et al. Self-attention generative adversarial networks[Z]. arXiv: 1805.08318, 2018.
    [14]
    MIYATO T, KATAOKA T, KOYAMA M, et al. Spectral normalization for generative adversarial networks[Z]. arXiv: 1802.05957, 2018.
    [15]
    张晗. SAR图像质量评估方法研究[D]. [硕士论文], 国防科学技术大学, 2012: 23–25.

    ZHANG Han. Research on the SAR image quality assessment[D]. [Master disseration] National University of Defense Technology, 2012: 23–25.
    [16]
    WANG Z, SIMONCELLI E P, and BOVIK A C. Multiscale structural similarity for image quality assessment[C]. The Thirty-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, Pacific Grove, USA, 2003: 1398–1402.
  • 加载中

Catalog

    通讯作者: 陈斌, bchen63@163.com
    • 1. 

      沈阳化工大学材料科学与工程学院 沈阳 110142

    1. 本站搜索
    2. 百度学术搜索
    3. 万方数据库搜索
    4. CNKI搜索
    Article views(3726) PDF downloads(306) Cited by()
    Proportional views
    Related

    /

    DownLoad:  Full-Size Img  PowerPoint