Laser & Optoelectronics Progress, Volume. 60, Issue 4, 0410012(2023)

Moving Target Detection Algorithm Based on Vibe and Improved LBP in Complex Background

Weilin Chen1,2,3, Liya Qiu1,2,3, Zheng Li1,3、*, Jian Wang1,2,3, and Chang Tan1,2,3
Author Affiliations
  • 1Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai 200083, China
  • 2University of Chinese Academy of Sciences, Beijing 100049, China
  • 3Key Laboratory of Infrared System Detection and Imaging Technology, Chinese Academy of Sciences, Shanghai 200083, China
  • show less
    Figures & Tables(7)
    Calculation process of traditional LBP value. (a) Original 3×3 image; (b) binarization of difference value after comparison with central pixel; (c) weighted multiplication of corresponding positions
    SLBP process. (a) Traditional LBP process and processing results; (b) SLBP process and processing results
    Background modeling and processing results after improved LBP feature operator
    Processing results of different algorithms in complex scenes. (a) highway; (b) snowfall; (c) canoe; (d) pedestrians; (e) PETS2006; (f) library; (g) overpass
    Line chart comparing different algorithms in seven scenes
    • Table 1. Average time taken by Vibe and the proposed algorithm in seven scenarios

      View table

      Table 1. Average time taken by Vibe and the proposed algorithm in seven scenarios

      Scenehighwaysnowfallcanoepedestrians
      AlgorithmVibeProposed algorithmVibeProposed algorithmVibeProposed algorithmVibeProposed algorithm
      Average time /ms21.974321.001535.174835.957221.583523.021820.325822.8498
      ScenePETS2006libraryoverpass
      AlgorithmVibeProposed algorithmVibeProposed algorithmVibeProposed algorithm
      Average time /ms36.061352.289319.613520.867313.502014.5666
    • Table 2. Evaluation index results of each algorithm in seven scenes

      View table

      Table 2. Evaluation index results of each algorithm in seven scenes

      Scenehighwaysnowfallcanoe
      RPFPpwcRPFPpwcRPFPpwc
      Proposed algorithm0.72470.7420.73330.03040.70680.79500.74830.01660.65180.82110.72670.0270
      Vibe0.71320.6790.69570.0360.61560.84370.71180.01740.42830.53820.4770.0517
      KDE0.92780.29750.29750.13070.24370.04410.31470.03710.98080.63280.37360.1809
      GMM0.49850.40350.4460.07140.11370.04650.0660.11230.2810.27290.27690.0807
      ScenepedestriansPETS2006Library
      RPFPpwcRPFPpwcRPFPpwc
      Proposed algorithm0.85690.60710.71070.00850.99590.43050.62840.00740.92530.92070.9230.0338
      Vibe0.87170.50780.64180.01190.5230.64570.57790.00990.05920.76890.110.2097
      KDE0.9240.46940.62250.01370.99080.27890.45780.03330.01110.68110.02180.2175
      GMM0.46860.63320.53860.00980.56440.75870.64730.0080.07480.74170.13580.2081
      Sceneoverpass
      RPFPpwc
      Proposed algorithm0.75860.73050.74430.057
      Vibe0.58940.63650.6210.0387
      KDE0.97420.28320.43890.134
      GMM0.60270.64120.62140.0395
    Tools

    Get Citation

    Copy Citation Text

    Weilin Chen, Liya Qiu, Zheng Li, Jian Wang, Chang Tan. Moving Target Detection Algorithm Based on Vibe and Improved LBP in Complex Background[J]. Laser & Optoelectronics Progress, 2023, 60(4): 0410012

    Download Citation

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

    Category: Image Processing

    Received: Nov. 25, 2021

    Accepted: Dec. 21, 2021

    Published Online: Feb. 14, 2023

    The Author Email: Li Zheng (lizheng_sitp@163.com)

    DOI:10.3788/LOP213062

    Topics