Chinese Journal of Ship Research, Volume. 19, Issue 6, 275(2024)

Method of joint wavelet thresholding and F-NLM de-noising for high-resolution SAR ship detection

Liang TONG... Dan LIU, Zhongbo PENG, Han ZOU, Lumeng WANG and Chunyu ZHANG |Show fewer author(s)
Author Affiliations
  • School of Shipping and Naval Architecture, Chongqing Jiaotong University, Chongqing 400074, China
  • show less
    Figures & Tables(15)
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    [in Chinese]
    • Table 1. Test environment configuration parameters

      View table
      View in Article

      Table 1. Test environment configuration parameters

      硬件配置或软件环境参数或版本
      CPUi7-12700
      RAM16 GB
      GPUNVDIA RTX3050
      操作系统Windows 10
      编程语言及软件Python3.8,Matlab2019b
      架构CUDA10.1,cuDNN7.6
    • Table 2. SSDD dataset information

      View table
      View in Article

      Table 2. SSDD dataset information

      数据集传感器分辨率/m极化方式数量
      SSDDRadarSat-21~15HH,HVVV,VH
      TerraSAR-X1160
      Sentinel-1
    • Table 3. Comparison of de-noising performance in terms of PSNR and average run time using different methods

      View table
      View in Article

      Table 3. Comparison of de-noising performance in terms of PSNR and average run time using different methods

      输入图像噪声方差不同方法获得的峰值信噪比RPSNR/dB
      均值滤波Lee滤波小波阈值NLM滤波融合去噪
      A12019.2620.1921.1223.4823.71
      4016.9617.3017.9119.1520.94
      A22021.2922.2423.3725.2925.53
      4018.5519.5119.9820.3221.83
      A32021.7822.7123.3325.2825.52
      4018.8919.8320.0420.4322.03
      B12017.4318.5019.0020.6320.91
      4015.5615.8516.5816.6518.39
      B22017.8018.8119.0320.6821.43
      4015.5716.3816.5417.5419.65
      B32016.1717.8018.9520.1520.62
      4015.1216.1316.9817.5720.33
      C12015.7416.7918.4319.3619.60
      4014.2615.2915.8616.6418.39
      C22017.1418.1519.0320.7421.00
      4015.3216.3116.3817.5619.66
      C32018.5319.5419.7821.3422.42
      4016.3817.4016.9718.5520.32
      RPSNR平均值/dB17.3218.2718.8520.0821.24
      平均运行时间/s0.6250.6091.06856.3752.609
    • Table 4. Detection performance comparison of different datasets using the same detection model

      View table
      View in Article

      Table 4. Detection performance comparison of different datasets using the same detection model

      数据集P/%R/%AP50/%F1分数rFAR/%
      SSDD94.5796.1496.440.97156.20
      D-SSDD95.5996.6197.630.97984.15
    • Table 5. Comparison of target detection performance using different algorithms

      View table
      View in Article

      Table 5. Comparison of target detection performance using different algorithms

      方法P/%R/%AP50/%F1分数rFAR/%模型体积/MB
      Faster R-CNN89.3390.1293.250.930 49.75156.43
      EffcientDet94.1695.8196.070.965 17.0389.71
      YOLOv594.5796.1496.440.971 56.2014.40
      YOLOv795.3796.4797.360.977 64.1527.00
      YOLOv7+Bi-FPN96.6296.8598.690.98 792.3727.30
    Tools

    Get Citation

    Copy Citation Text

    Liang TONG, Dan LIU, Zhongbo PENG, Han ZOU, Lumeng WANG, Chunyu ZHANG. Method of joint wavelet thresholding and F-NLM de-noising for high-resolution SAR ship detection[J]. Chinese Journal of Ship Research, 2024, 19(6): 275

    Download Citation

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

    Category: Weapon, Electronic and Information System

    Received: Jul. 26, 2023

    Accepted: --

    Published Online: Mar. 14, 2025

    The Author Email:

    DOI:10.19693/j.issn.1673-3185.03477

    Topics