Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Chinese Journal of Lasers, Volume. 51, Issue 17, 1706001(2024)

A Grid‐Based BP Neural Network Positioning Method for a Space Optical Communication Spot Center

Tianci Liu1, Keyan Dong1,2、*, Bo Zhang2, Yansong Song2, Zonglin Liang1, Jinwang Li1, Yanbo Wang1, Lei Zhang1, Gangqi Yan1, and Wenyi Hu1
Author Affiliations
  • 1School of Opto-Electronic Engineering, Changchun University of Science and Technology, Changchun 130022, Jilin , China
  • 2Institute of Space Photo-Electronic Technology, Changchun University of Science and Technology, Changchun 130022, Jilin , China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (11)
    Equations (0)
    References (16)
    Tools
    Paper Information
    Topics
    Figures & Tables(11)
    Flow chart of neural network localization with gridding of spot center

    Fig. 1. Flow chart of neural network localization with gridding of spot center

    Download full size
    Energy distributions of a Gaussian spot. (a) Center unexposed energy distribution; (b) center overexposed energy distribution

    Fig. 2. Energy distributions of a Gaussian spot. (a) Center unexposed energy distribution; (b) center overexposed energy distribution

    Download full size
    Maximum entropy threshold segmentation for spot ROI image. (a) Original image; (b) segmented image

    Fig. 3. Maximum entropy threshold segmentation for spot ROI image. (a) Original image; (b) segmented image

    Download full size
    2×2 grid division schematic for threshold segmentation image. (a) Original image; (b) divisional image

    Fig. 4. 2×2 grid division schematic for threshold segmentation image. (a) Original image; (b) divisional image

    Download full size
    Structure diagram of a three-layer BP neural network

    Fig. 5. Structure diagram of a three-layer BP neural network

    Download full size
    Experimental images with different spot types. (a) Center unexposed; (b) center overexposed

    Fig. 6. Experimental images with different spot types. (a) Center unexposed; (b) center overexposed

    Download full size
    Absolute error comparison of center unexposed spot image groups

    Fig. 7. Absolute error comparison of center unexposed spot image groups

    Download full size
    Absolute error comparison of center overexposed spot image groups

    Fig. 8. Absolute error comparison of center overexposed spot image groups

    Download full size
    Spot center positioning results. (a) Center unexposed; (b) center overexposed

    Fig. 9. Spot center positioning results. (a) Center unexposed; (b) center overexposed

    Download full size

    • Table 1. Comparison of root mean square of absolute error of different algorithms

      View table

      Table 1. Comparison of root mean square of absolute error of different algorithms

      Algorithm

      Root mean square of absolute error for

      group A /pixel

      Root mean square of absolute error for

      group B /pixel

      X coordinateY coordinateX coordinateY coordinate
      Centroid algorithm0.60540.67980.62920.8148
      Circle-fitting algorithm0.77500.95641.00210.9267
      Proposed algorithm0.54090.46330.45260.4565

    • Table 2. Comparison of standard deviation of absolute error of different algorithms

      View table

      Table 2. Comparison of standard deviation of absolute error of different algorithms

      Algorithm

      Standard deviation of absolute error for

      group A /pixel

      Standard deviation of absolute error for

      group B /pixel

      X coordinateY coordinateX coordinateY coordinate
      Centroid algorithm0.27110.26900.25860.3184
      Circle-fitting algorithm0.29370.32660.34480.3572
      Proposed algorithm0.26140.24870.18170.1773
    Tools

    Get Citation

    Copy Citation Text

    Tianci Liu, Keyan Dong, Bo Zhang, Yansong Song, Zonglin Liang, Jinwang Li, Yanbo Wang, Lei Zhang, Gangqi Yan, Wenyi Hu. A Grid‐Based BP Neural Network Positioning Method for a Space Optical Communication Spot Center[J]. Chinese Journal of Lasers, 2024, 51(17): 1706001

    Download Citation

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

    Category: Fiber optics and optical communication

    Received: Oct. 10, 2023

    Accepted: Dec. 7, 2023

    Published Online: Aug. 31, 2024

    The Author Email: Dong Keyan (dongkeyan@cust.edu.cn)

    DOI:10.3788/CJL231272

    CSTR:32183.14.CJL231272

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology