Laser & Optoelectronics Progress, Volume. 58, Issue 20, 2015007(2021)

Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference

Na Li1,2, Kuangang Fan1,2、*, Yahui Liu1,2, and Qinghua Ouyang1,2
Author Affiliations
  • 1School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou, Jiangxi 341000, China
  • 2Key Laboratory of Magnetic Levitation Technology in Jiangxi Province, Ganzhou, Jiangxi 341000, China
  • show less
    Figures & Tables(6)
    Flow chart of improved algorithm
    Comparison results of UAV detection using different algorithms under different background sequences
    Gaussian noise detection results with different variances
    • Table 1. Measured value P,R,F of various algorithms

      View table

      Table 1. Measured value P,R,F of various algorithms

      VideoFive-Frame Difference+ViBe+Optical Flow+GMM+TVRPCAProposed algorithm
      RPFRPFRPFRPFRPFRPF
      (a)0.850.910.890.920.750.830.890.830.860.620.900.730.870.940.900.910.930.92
      (b)0.460.830.590.880.740.800.810.630.710.820.660.730.860.840.850.920.910.91
      (c)0.580.790.670.860.700.770.870.710.780.630.770.700.850.860.850.890.850.87
      (d)0.530.870.660.840.730.780.920.720.810.630.810.710.860.810.830.910.920.91
      (e)0.370.880.520.890.620.730.900.890.890.590.800.680.890.900.890.940.930.93
      (f)0.790.850.820.710.800.750.920.490.640.110.570.180.840.830.830.870.850.86
      (g)0.510.860.640.810.790.800.790.800.790.210.870.330.860.890.870.930.880.90
    • Table 2. Measured value P, R, F of Gaussian noise with different variances

      View table

      Table 2. Measured value P, R, F of Gaussian noise with different variances

      AlgorithmVarianceRPF
      0.0010.460.810.59
      Five-Frame Difference+0.0050.460.780.58
      0.010.460.540.50
      0.020.470.360.41
      0.0010.820.660.73
      GMM+0.0050.820.620.71
      0.010.810.530.64
      0.020.810.500.62
      0.0010.880.740.80
      ViBe+0.0050.880.630.73
      0.010.870.550.67
      0.020.850.430.57
      0.0010.910.880.89
      TVRPCA0.0050.900.850.87
      0.010.900.820.85
      0.020.890.780.83
      0.0010.860.630.71
      Optical Flow+0.0050.860.630.71
      0.010.860.630.71
      0.020.860.630.71
      0.0010.920.900.91
      Proposed algorithm0.0050.920.890.90
      0.010.910.880.89
      0.020.910.870.89
    • Table 3. Comparison of running time of different algorithms unit: s

      View table

      Table 3. Comparison of running time of different algorithms unit: s

      Algorithm(a)(b)(c)(d)(e)Average
      Five-Frame Difference+24.8025.2327.0224.2426.2826.30
      ViBe+98.7893.4395.8796.1396.4195.12
      Optical Flow+101.14102.62101.98104.34102.82103.27
      GMM+76.5975.3176.5976.2373.7275.69
      TVRPCA256.30236.45255.23232.27246.46226.37
      Proposed algorithm31.1630.7930.2731.3030.0330.71
    Tools

    Get Citation

    Copy Citation Text

    Na Li, Kuangang Fan, Yahui Liu, Qinghua Ouyang. Unmanned Aerial Vehicle Detection Based on ASRPCA Fused with Five-Frame Difference[J]. Laser & Optoelectronics Progress, 2021, 58(20): 2015007

    Download Citation

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

    Category: Machine Vision

    Received: Dec. 3, 2020

    Accepted: Jan. 21, 2021

    Published Online: Oct. 14, 2021

    The Author Email: Fan Kuangang (kuangangfriend@163.com)

    DOI:10.3788/LOP202158.2015007

    Topics