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

Infrared and Laser Engineering, Volume. 50, Issue 11, 20210071(2021)

Camera calibration method based on double neural network

Wenyi Chen1...2, Jie Xu1,* and Hui Yang1 |Show fewer author(s)
Author Affiliations
  • 1Industry School of Modern Post, Xi’an University of Posts and Telecommunications, Xi’an 710061, China
  • 2Collaborative Innovation Center for Modern Post, Xi’an University of Posts and Telecommunications, Xi’an 710121, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (15)
    Equations (14)
    References (17)
    Tools
    Paper Information
    Topics
    Figures & Tables(15)
    Relationship between coordinate systems

    Fig. 1. Relationship between coordinate systems

    Download full size
    View in Article
    Camera calibration based on double neural networks

    Fig. 2. Camera calibration based on double neural networks

    Download full size
    View in Article
    Schematic diagram of BP network model

    Fig. 3. Schematic diagram of BP network model

    Download full size
    View in Article
    Flow chart of PSO-BP algorithm

    Fig. 4. Flow chart of PSO-BP algorithm

    Download full size
    View in Article
    Schematic diagram of optical axis correction

    Fig. 5. Schematic diagram of optical axis correction

    Download full size
    View in Article
    Schematic diagram of calibration plate correction

    Fig. 6. Schematic diagram of calibration plate correction

    Download full size
    View in Article
    Experimental platform

    Fig. 7. Experimental platform

    Download full size
    View in Article
    Training chart of PSO-BP double neural network algorithm

    Fig. 8. Training chart of PSO-BP double neural network algorithm

    Download full size
    View in Article
    Training curve of traditional BP neural network

    Fig. 9. Training curve of traditional BP neural network

    Download full size
    View in Article
    Result of Z-axis output error

    Fig. 10. Result of Z-axis output error

    Download full size
    View in Article
    Image of 3D reconstruction

    Fig. 11. Image of 3D reconstruction

    Download full size
    View in Article
    Distorted image

    Fig. 12. Distorted image

    Download full size
    View in Article

    • Table 1. Influence of hidden layer node number on experimental results

      View table
      View in Article

      Table 1. Influence of hidden layer node number on experimental results

      Number of hidden layer nodes$error_{xz} /{\rm mm}$$error_{ {yz} } /{\rm mm}$
      60.1300.0987
      80.1640.148
      100.08220.0683
      120.07510.0797
      140.06470.0622
      160.0002100.000274
      180.0002420.000381
      200.0001950.00159
      220.0005690.000889

    • Table 2. Error of partial calibration point

      View table
      View in Article

      Table 2. Error of partial calibration point

      Expert outputProposed methodMethod in Ref. [13]
      ${X_{\rm{w} } }/{\rm mm}$${Y_{\rm{w} } }/{\rm mm}$${Z_{\rm{w} } }/{\rm mm}$${X_{\rm{w} } }/{\rm mm}$${Y_{\rm{w} } }/{\rm mm}$${Z_{\rm{w} } }/{\rm mm}$${X_{\rm{w} } }/{\rm mm}$${Y_{\rm{w} } }/{\rm mm}$${Z_{\rm{w} } }/{\rm mm}$
      30603.765030.013259.98263.517729.780359.76363.5139
      3012018.790030.0824120.10318.846430.1413119.84618.4452
      6030108.920059.981929.8937108.994059.657529.9067108.3465
      9090108.920089.903389.9493108.883690.088790.2409107.9858
      120240108.9200119.8934240.051108.8500119.7397240.082108.9832
      15030108.9200150.106029.8590108.9702149.739629.9120109.1905
      18060105.1450179.851259.9526105.0527179.762959.9960104.9458
      210180105.1450210.1164179.833105.0298210.2637179.878105.3433
      240210105.1450240.0994210.101105.0015240.2051210.132104.9842
      330240108.9200330.2025240.035108.9867330.0932240.1141108.6544
      $E$0.17860.4378

    • Table 3. Calibration error of different methods under the condition of high lens distortion

      View table
      View in Article

      Table 3. Calibration error of different methods under the condition of high lens distortion

      Proposed methodMethod in Ref. [13]BP method
      ${\rm Error/mm}$$X,Z$$Y,Z$$X,Y$$Z$$X,Y,Z$
      $best$0.0003430.0004140.0003700.0008350.031687
      $avg$0.31930.50161.2126
    Tools

    Get Citation

    Copy Citation Text

    Wenyi Chen, Jie Xu, Hui Yang. Camera calibration method based on double neural network[J]. Infrared and Laser Engineering, 2021, 50(11): 20210071

    Download Citation

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

    Category: Photoelectric measurement

    Received: Jan. 27, 2021

    Accepted: --

    Published Online: Dec. 7, 2021

    The Author Email: Xu Jie (1141849828@qq.com)

    DOI:10.3788/IRLA20210071

    Topics

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