Optics and Precision Engineering, Volume. 31, Issue 4, 533(2023)

Quantitative evaluation method for structural similarity of multidimensional point cloud

Ziqian YANG1...2, Yanqiu WANG1,2, Fu ZHENG1,2, and Zhibin SUN12,* |Show fewer author(s)
Author Affiliations
  • 1National Space Science Center, Chinese Academy of Sciences, Beijing0090,China
  • 2University of Chinese Academy of Sciences, Beijing100049, China
  • show less
    Figures & Tables(11)
    System structure diagram of 3D-SSIM
    Bunny, dragon and buddha models’ point clouds before add and remove Gaussian noise
    X-axis, y-axis, and z-axis structural similarity curves with different confidence levels and three-dimensional structural similarity curves:
    Similarity curves for cat models with different confidence levels regarding the z-axis
    Cat model of Top view of the point cloud with different confidence levels:
    Cat, car, man, head, aircraft carrier, plane point cloud datasets the pictures from top to bottom are:respectively, standard dataset, target extraction dataset, radius filtering, statistical filtering, low-pass filtering
    Correspondence between three-dimensional structure similarity values of bunny, dragon and armadillo and root mean square error of registration
    • Table 1. SSIM of bunny, dragon and Buddha before and after adding Gaussian noise

      View table
      View in Article

      Table 1. SSIM of bunny, dragon and Buddha before and after adding Gaussian noise

      标准数据-标准数据添加高斯噪声-标准数据
      x-SSIMy-SSIMz-SSIM3D-SSIMx-SSIMy-SSIMz-SSIM3D-SSIM
      Bunny11110.921 860.994 690.960 30.880 56
      Dragon11110.971 790.999 920.984 610.956 76
      Buddha11110.981 970.999 940.989 420.971 52
    • Table 2. 3D-SSIM evaluation method of point cloud dataset based on cat, car, man, head, aircraft carrier and plane models

      View table
      View in Article

      Table 2. 3D-SSIM evaluation method of point cloud dataset based on cat, car, man, head, aircraft carrier and plane models

      滤波方法Cat点云数据集Car点云数据集
      x-SSIMy-SSIMz-SSIM3DSSIMx-SSIMy-SSIMz-SSIM3DSSIM
      半径滤波0.947 9710.981 3530.999 5740.929 897 90.894 8880.986 7960.999 4220.882 561
      统计滤波0.948 6350.981 3090.999 580.930 5130.893 1040.986 7190.999 4250.880 736
      低通滤波0.947 4890.981 0060.999 5630.929 086 20.893 2480.986 720.999 3960.880 853 3
      滤波方法Man点云数据集Head点云数据集
      x-SSIMy-SSIMz-SSIM3DSSIMx-SSIMy-SSIMz-SSIM3DSSIM
      半径滤波0.999 3040.951 5420.996 9850.948 012 80.997 3470.995 3410.998 9680.991 675 9
      统计滤波0.999 2460.967 3780.996 8660.963 6190.996 3170.998 4510.999 680.994 455
      低通滤波0.999 2270.936 8210.996 3730.932 701 60.996 3060.996 210.996 3730.988 930 1
      滤波方法Aircraft carrier点云数据集Plane点云数据集
      x-SSIMy-SSIMz-SSIM3DSSIMx-SSIMy-SSIMz-SSIM3DSSIM
      半径滤波0.992 450.994 530.998 780.985 817 10.964 0510.994 530.998 780.957 607 9
      统计滤波0.997 520.998 3240.999 2360.995 0870.964 130.999 620.996 9310.960 805 8
      低通滤波0.996 3040.996 2070.999 0290.991 561 30.983 4940.996 230.996 910.976 759
    • Table 3. Point cloud registration of different 3D structure similarity values of bunny,dragon and armadillo

      View table
      View in Article

      Table 3. Point cloud registration of different 3D structure similarity values of bunny,dragon and armadillo

      BunnyDragonArmadillo
      对照内容KNNSOR添加噪声原图KNNSOR添加噪声原图KNNSOR添加噪声原图
      匹配点对个数1 8202 0972 1821 5672 6603 1602 1731 9941 7251 9292 0391 424
      距离最大值3.384 673.447 4412.007 483.622 261.785 311.758 231.478 261.327 444.115 623.606 463.704 683.430 48
      距离最小值00000.006 550.006 810.017 530.012 780000
      均方根误差1.562 441.856 021.966 591.465 462.782 922.645 832.454 162.080 552.308 171.832 082.023 541.759 13
    • Table 4. similarity values of different 3D structures of bunny,dragon and armadillo

      View table
      View in Article

      Table 4. similarity values of different 3D structures of bunny,dragon and armadillo

      BunnyDragonArmadillo
      对照内容KNNSOR添加噪声原图KNNSOR添加噪声原图KNNSOR添加噪声原图
      x-SSIM0.875 9110.677 2150.637 22810.884 630.908 260.889 3710.628 1340.999 860.623 1891
      y-SSIM0.971 3330.971 3650.902 46310.988 590.988 590.988 2710.329 7170.350 260.340 3841
      z-SSIM0.822 7130.821 9840.823 096 110.817 140.803 920.814 0510.967 0660.870 750.870 993 11
      3D-SSIM0.699 965 20.540 719 90.473 341 710.714 630.721 850.715 5010.200 2850.304 950.184 758 161
    Tools

    Get Citation

    Copy Citation Text

    Ziqian YANG, Yanqiu WANG, Fu ZHENG, Zhibin SUN. Quantitative evaluation method for structural similarity of multidimensional point cloud[J]. Optics and Precision Engineering, 2023, 31(4): 533

    Download Citation

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

    Category: Information Sciences

    Received: Feb. 23, 2022

    Accepted: --

    Published Online: Mar. 7, 2023

    The Author Email: SUN Zhibin (zbsun@nssc.ac.cn)

    DOI:10.37188/OPE.20233104.0533

    Topics