Acta Optica Sinica, Volume. 45, Issue 15, 1506001(2025)

Curvature Measurement Method Based on VggNet 16 and Specialty Optical Fiber Speckle

Zhan Shen1, Lu Cai1,2、*, Gang Yang1, and Shen Liu3
Author Affiliations
  • 1School of Control Engineering, Northeastern University at Qinhuangdao, Qinhuangdao 066004, Hebei , China
  • 2Hebei Key Laboratory of Micro-Nano Precision Optical Sensing and Measurement Technology, Northeastern University at Qinhuangdao, Qinhuangdao 066004, Hebei , China
  • 3Key Laboratory of Optoelectronic Devices and Systems of Ministry of Education and Guangdong Province, College of Physics and Optoelectronic Engineering, Shenzhen University, Shenzhen 518060, Guangdong , China
  • show less
    Figures & Tables(20)
    DCSHF. (a) 3D schematic diagram; (b) cross-section micrograph
    Experimental system of optical fiber specklegram. (a) 3D schematic(inset is SMF-MMF-DCSHF sensing structure); (b) 2D side view
    Logic diagram of automated experiment
    Schematic diagram of curvature auto-determination device (inset is detection result of scale alignment algorithm)
    Structure of VggNet 16
    Light speckle passes through feature maps of each layer of model
    Bending prediction of SMF-MMF structure based on VggNet 16 (classified)
    Schematic diagram of curvature calculation
    Curvature prediction of SMF-MMF structure based on VggNet 16 (classified)
    Loss trend chart of VggNet 16 (regression)
    Curvature prediction of SMF-MMF-DCSHF structure based on VggNet 16 (regression)
    Comparison of SMF-MMF light speckle
    Comparison of SMF-MMF-DCSHF light speckle
    Comparison of similarity parameters for SMF-MMF light speckle with different algorithms
    Comparison of similarity parameters for SMF-MMF-DCSHF light speckle with different algorithms
    Comparison of light speckle for two structures with different algorithms
    Curvature prediction of SMF-MMF structure based on VggNet 16 (regression)
    Curvature prediction of SMF-MMF-DCSHF structure based on ResNet 50 (regression)
    Analysis of activation area of model
    • Table 1. Wrong predictions of VggNet 16 (classified)

      View table

      Table 1. Wrong predictions of VggNet 16 (classified)

      Picture numberPredict valueTrue value
      0426222947_gray.bmp8182
      0426210154_gray.bmp9190
      0426213821_gray.bmp3534
      0426224032_gray.bmp12
      0426215854_gray.bmp45
      0426201843_gray.bmp6566
      0426202323_gray.bmp6159
      .........
    Tools

    Get Citation

    Copy Citation Text

    Zhan Shen, Lu Cai, Gang Yang, Shen Liu. Curvature Measurement Method Based on VggNet 16 and Specialty Optical Fiber Speckle[J]. Acta Optica Sinica, 2025, 45(15): 1506001

    Download Citation

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

    Category: Fiber Optics and Optical Communications

    Received: Mar. 5, 2025

    Accepted: Apr. 27, 2025

    Published Online: Aug. 15, 2025

    The Author Email: Lu Cai (cai_rourou@163.com)

    DOI:10.3788/AOS250693

    CSTR:32393.14.AOS250693

    Topics