Optics and Precision Engineering, Volume. 30, Issue 3, 331(2022)

Detection of leaky cable fixture in high-speed railway tunnel with layered continuous gradient fusion feature

Yunzuo ZHANG*, Zhouchen SONG, Wei GUO, and Xu DONG
Author Affiliations
  • School of Information Science and Technology, Shijiazhuang Tiedao University, Shijiazhuang050043, China
  • show less
    Figures & Tables(10)
    LBP and CS-LBP sampling methods
    Calculation of direction characteristics of preliminary gradient
    Cell unit
    Calculation of characteristics of key gradient
    Down-sampling process
    Calculation of characteristics of continuous gradient
    Experiment flow chart of leaky cable fixture detection based on gradient fusion feature
    ROC curves
    • Table 1. Image effect analysis of different gray-thresholds

      View table
      View in Article

      Table 1. Image effect analysis of different gray-thresholds

      ImageAverage grayThreshold (T
      4567891011
      216
      186
      133
      99
      63
    • Table 2. Comparison of detection results

      View table
      View in Article

      Table 2. Comparison of detection results

      DescriptorRecallPrecisionBinTime/s
      LBP50.7780.58340962.602
      CS-LBP60.7780.4672561.548
      CLBP70.6920.60032002.607
      HOG80.5000.75023041.005
      TPLBP140.6360.58340964.508
      ARCS-LBP130.6250.83340962.675
      HOG_CLBP110.7270.80055043.618
      HOG_LBP90.8890.61564003.614
      LCG-LBP0.9230.85715363.632
    Tools

    Get Citation

    Copy Citation Text

    Yunzuo ZHANG, Zhouchen SONG, Wei GUO, Xu DONG. Detection of leaky cable fixture in high-speed railway tunnel with layered continuous gradient fusion feature[J]. Optics and Precision Engineering, 2022, 30(3): 331

    Download Citation

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

    Category: Information Sciences

    Received: Jul. 14, 2021

    Accepted: --

    Published Online: Mar. 4, 2022

    The Author Email: Yunzuo ZHANG (zhangyunzuo888@sina.com)

    DOI:10.37188/OPE.20223003.0331

    Topics