Acta Optica Sinica, Volume. 45, Issue 16, 1606005(2025)

Application of Visible Light Positioning System Based on Fingerprint Correction and Network Fusion Algorithms

Jianyong Yu1, Xiaoli Hu2、*, Qian Wang1, Ling Qin1、**, Fengying Wang3, and Xinchao Kou1
Author Affiliations
  • 1School of Digital and Intelligent Industry, Inner Mongolia University of Science and Technology, Baotou 014010, Inner Mongolia , China
  • 2School of Automation and Electrical Engineering, Inner Mongolia University of Science and Technology, Baotou 014010, Inner Mongolia , China
  • 3Engineering Training Center, Inner Mongolia University of Science and Technology, Baotou 014010, Inner Mongolia , China
  • show less
    Figures & Tables(18)
    Real environment channel model
    PD distribution of safety helmet. (a) Top view; (b) 3D stereogram; (c) rotation tilt diagram
    Block design. (a) Original MobileNetV3 block; (b) separate token mixer and channel mixer; (c) deep fusion block
    Block diagram of ViTs-MNV3 algorithm
    Curve of loss function with number of iterations
    Cumulative distribution of positioning errors
    Ideal environment 3D positioning result map
    Point cloud triangulation. (a) Wall point cloud; (b) rotated wall point cloud; (c) wall point cloud after Delaunay triangulation
    Optical power distributions and positioning errors. (a) Left wall primary reflected power; (b) right wall primary reflected power; (c) total power; (d) positioning results
    Received power and positioning results. (a) Vertical simulation of optical power distribution; (b) tilt simulation optical power distribution; (c) tilted optical power matching vertical database positioning results
    Experimental environment of the mine
    3D positioning results at different heights in real environment
    Real environment power distribution. (a) Vertical acquisition training set power distribution; (b) skewed power distribution of the training set after vertical power transformation
    Power correction effect and positioning results. (a) Comparison between the converted power and the real collected power; (b) converted power matching real acquisition power positioning result plot
    • Table 1. Root mean square error and mean error for different batch sizes

      View table

      Table 1. Root mean square error and mean error for different batch sizes

      Batch sizeRMSE /cmMean error /cmTraining time /min
      3212.6211.9311.1
      6411.669.016.8
      12810.958.364.2
      25611.4210.153.7
      51212.0312.562.5
    • Table 2. Comparison of positioning errors and complexity of different network algorithms

      View table

      Table 2. Comparison of positioning errors and complexity of different network algorithms

      Positioning

      algorithm

      RMSE /

      cm

      Mean

      error /cm

      FLOPs /

      109

      Time /

      min

      MobileNetV328.3023.682.6910.3
      Transformer25.8022.951.584.6
      ViTs-MNV310.958.361.424.2
      BP16.1515.771.675.9
      LSTM14.8014.611.464.5
    • Table 3. Channel simulation parameter

      View table

      Table 3. Channel simulation parameter

      SymbolParameterValue
      L×W×HRoom size /(m×m×m)4.0×3.0×2.5
      φTilt angle of PD /(°)30
      ωRotation angle of safety helmet /(°)45
      γTilt angle of safety helmet /(°)15
      ApPhysical area of photo-detector / cm21
      mLambert index1
      ρReflection coefficient0.5
      T(*)Gain of optical filter1
      g(*)Gain of optical concertrator2.55
      FOVField of view /(°)90
      Ф1/2Semi-angle at half power /(°)70
      PtAverage transmitted power /W20
    • Table 4. Model training parameters

      View table

      Table 4. Model training parameters

      SymbolParameterValue
      epochsModel iterations1000
      k_sKernel size3
      e_fExpansion factor2
      o_cOutput channel128
      h_sHard-swish1
      strideStride length2
      b_sBatch size128
    Tools

    Get Citation

    Copy Citation Text

    Jianyong Yu, Xiaoli Hu, Qian Wang, Ling Qin, Fengying Wang, Xinchao Kou. Application of Visible Light Positioning System Based on Fingerprint Correction and Network Fusion Algorithms[J]. Acta Optica Sinica, 2025, 45(16): 1606005

    Download Citation

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

    Category: Fiber Optics and Optical Communications

    Received: Mar. 31, 2025

    Accepted: May. 22, 2025

    Published Online: Aug. 8, 2025

    The Author Email: Xiaoli Hu (hxl7756@163.com), Ling Qin (qinling1979@imust.edu.cn)

    DOI:10.3788/AOS250821

    CSTR:32393.14.AOS250821

    Topics