Acta Photonica Sinica, Volume. 53, Issue 12, 1201001(2024)

Application of Deep Neural Network in Wavefront Sensing Based on Transport of Intensity Equation

Huizhe YANG1,2, Haoran ZHANG1, Jin LIU1,2, Jing WAN1,2, Luming ZHAO1, and Yonghui LIANG1,2、*
Author Affiliations
  • 1College of Advanced Interdisciplinary Studies,National University of Defense Technology,Changsha 410073,China
  • 2Nanhu Laser Laboratory,National University of Defense Technology,Changsha 410073,China
  • show less
    Figures & Tables(11)
    The propagation of a collimated laser beam through the atmosphere turbulence
    Imaging of the Rayleigh backscattering
    WFE with epochs for training and testing sets for different backbone networks
    LWN design and test
    Overall model architecture
    Comparison of different loss functions and distribution of weight vectors
    Comparison of different optimizers for training and testing sets
    WFE of DNN and linear reconstruction
    Reconstructed first 20 Zernike coefficients
    Reconstruction phases of DNN and linear reconstruction
    • Table 1. Simulation parameters

      View table
      View in Article

      Table 1. Simulation parameters

      Telescope
      D=1 mN=128×128I0=exp-x2+y22a2-0.881 6 (a=1)
      Atmospheric turbulence
      r0=[0.050.10.15] m @500 nmL0=100 ml0=0.01 m
      One turbulence layerh=[0, 5, 10]km
      TIE wavefront sensor
      h1=10 kmh2=17 kmExposure time=2.5 ms
      Laser power=[5, 10, 20, 50, 100, 200, 300] W
    Tools

    Get Citation

    Copy Citation Text

    Huizhe YANG, Haoran ZHANG, Jin LIU, Jing WAN, Luming ZHAO, Yonghui LIANG. Application of Deep Neural Network in Wavefront Sensing Based on Transport of Intensity Equation[J]. Acta Photonica Sinica, 2024, 53(12): 1201001

    Download Citation

    EndNote(RIS)BibTexPlain Text
    Save article for my favorites
    Paper Information

    Category: Atmospheric and Oceanic Optics

    Received: Aug. 22, 2024

    Accepted: Oct. 29, 2024

    Published Online: Jan. 15, 2025

    The Author Email: Yonghui LIANG (yonghuiliang@sina.com)

    DOI:10.3788/gzxb20245312.1201001

    Topics