留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于对抗神经网络有限角度的磁层边界CT重构技术

王嘉璇 李大林 彭晓东 孙天然

王嘉璇, 李大林, 彭晓东, 孙天然. 基于对抗神经网络有限角度的磁层边界CT重构技术[J]. 空间科学学报, 2021, 41(4): 546-554. doi: 10.11728/cjss2021.04.546
引用本文: 王嘉璇, 李大林, 彭晓东, 孙天然. 基于对抗神经网络有限角度的磁层边界CT重构技术[J]. 空间科学学报, 2021, 41(4): 546-554. doi: 10.11728/cjss2021.04.546
WANG Jiaxuan, LI Dalin, PENG Xiaodong, SUN Tianran. Finite-angle Magnetosphere Boundary CT Reconstruction Technique Based on Generative Adversarial Networks[J]. Chinese Journal of Space Science, 2021, 41(4): 546-554. doi: 10.11728/cjss2021.04.546
Citation: WANG Jiaxuan, LI Dalin, PENG Xiaodong, SUN Tianran. Finite-angle Magnetosphere Boundary CT Reconstruction Technique Based on Generative Adversarial Networks[J]. Chinese Journal of Space Science, 2021, 41(4): 546-554. doi: 10.11728/cjss2021.04.546

基于对抗神经网络有限角度的磁层边界CT重构技术

doi: 10.11728/cjss2021.04.546 cstr: 32142.14.cjss2021.04.546
基金项目: 

空间科学先导专向预先研究项目(XDA15017000),国家自然科学基金面上项目(41774173),中国科学院国家空间科学中心“五个重点培育方向”课题(Y92115CE2S)共同资助

详细信息
    作者简介:
    • 王嘉璇,E-mail:wangjiaxuan17@mails.ucas.ac.cn
  • 中图分类号: P353

Finite-angle Magnetosphere Boundary CT Reconstruction Technique Based on Generative Adversarial Networks

  • 摘要: 对地球磁层进行软X射线成像探测是近年来磁层研究的前沿方向.由二维X射线成像图重构三维磁层边界的方法研究是与成像探测相关的重要研究课题.传统的计算机断层成像技术(CT)重构方法在图像数据很少时无法得到较好的重构结果,甚至无法重构三维结构.考虑到地球磁层空间分布范围方面的约束,当前卫星任务的轨道设计很难满足扫描角度的全方位覆盖,只能从有限角度观测磁层,这给磁层的CT重构带来困难.作为三维重构研究的基础,本文考查简化的二维磁层结构重构方法,采用基于对抗神经网络的CT技术对简化的地球磁层边界结构进行重构.首先使用改进的生成式对抗网络(GAN)对有限角度的卫星扫描图像进行图像补全,进而使用代数迭代重建方法(ART)重构磁层.实验表明,当扫描角度大于90°时,生成式对抗网络能有效准确地补全缺失图像,重构效果较好.

     

  • [1] NASSI M, BRODY W R, MEDOFFMEID B P, et al. Iterative reconstruction-reprojection:an algorithm for limited data cardiac-computed tomography[J]. IEEE Trans. Biom. Eng., 1982, 5:333-341
    [2] REEDS J A, SHEPP L A. Limited angle reconstruction in tomography via squashing[J]. IEEE Trans. Med. Imaging, 1987, 6(2):89-97
    [3] OLSON T, JAFFE J S. An explanation of the effects of squashing in limited angle tomography[J]. IEEE Trans. Med. Imaging, 1990, 9(3):242-246
    [4] NATTERER F, WUBBELING F. Mathematical Methods in Image Reconstruction[M]. Philadelphia:Society for Industrial and Applied Mathematics, 2001
    [5] JORGENSEN A M, SUN T, WANG C, et al. Boundary detection in three dimensions with application to the smile mission:the effect of photon noise[J]. J. Geophys. Res.:Space Phys., 2019, 124(6):4365-4383
    [6] GOODFELLOW I, POUGET-ABADIE J, MIRZA M, et al. Generative adversarial nets[C]//Advances in Neural Information Processing Systems. Montreal:IEEE, 2014:2672-2680
    [7] DENTON E, CHINTALA S, SZLAM A, et al. Deep generative image models using a Laplacian Pyramid of adversarial networks[C]. Neural Information Processing Systems. Montreal:IEEE, 2015:1486-1494
    [8] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[C]. International Conference on Learning Representations. ISan Juan:CLR, 2016
    [9] ZHU J Y, KR? HENBüHL P, SHECHTMAN E, et al. Generative visual manipulation on the natural image manifold[C]//European Conference on Computer Vision. Amsterdam:Springer, 2016:597-613
    [10] YEH R A, CHEN C, YIAN L T, et al. Semantic image inpainting with deep generative models[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Honolulu:IEEE, 2017:5485-5493
    [11] CHAO J K, WU D J, LIN C H, et al. Models for the size and shape of the Earth's magnetopause and bow shock[C]//Cospar Colloquia Series. Pergamon:COSPAR, 2002:127-135
    [12] LIU Z Q, LU J Y, WANG C, et al. A three-dimensional high Mach number asymmetric magnetopause model from global MHD simulation[J]. J. Geophys. Res.:Space Phys., 2015, 120(7):5645-5666
  • 1. Lianhai Tai, Chong Li, Xiaoxiao Yu, Zhijun Xu, Lei Sun. Unloading Technology and Application Research of Variable Diameter Drilling in Dynamic Pressure Roadway. Applied Sciences, 2024.
    2. Lianhai Tai, Chong Li, Shitan Gu, Xiaoxiao Yu, Zhijun Xu, Lei Sun. Research on dynamic response characteristics of normal fault footwall working face and rock burst prevention technology under the influence of the gob area. Scientific Reports, 2023.
    3. R. C. Wang, Dalin Li, Tianran Sun, Xiaodong Peng, Zhen Yang, J. Q. Wang. A 3D Magnetospheric CT Reconstruction Method Based on 3D GAN and Supplementary Limited‐Angle 2D Soft X‐Ray Images. Journal of Geophysical Research: Space Physics, 2023.
    1. 郑宗慧,梅秋平. 汽车注塑模具加工中数控机床误差控制. 机械设计与制造工程. 2025(01): 29-34 . 百度学术
  • 加载中
计量
  • 文章访问数:  766
  • HTML全文浏览量:  158
  • PDF下载量:  51
  • 被引次数: 

    3(来源:Crossref)

    1(来源:其他)

出版历程
  • 收稿日期:  2020-03-13
  • 修回日期:  2021-01-27
  • 刊出日期:  2021-07-15

目录

    /

    返回文章
    返回