• Laser & Optoelectronics Progress
  • Vol. 60, Issue 20, 2010004 (2023)
Yong Tong1, Fangyong Xu2, Ning Yang1, and Hui Chen1,*
Author Affiliations
  • 1College of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China
  • 2Changfeng County Power Supply Company, State Grid Anhui Electric Power Co., Ltd., Hefei 231100, Anhui , China
  • show less
    DOI: 10.3788/LOP222968 Cite this Article Set citation alerts
    Yong Tong, Fangyong Xu, Ning Yang, Hui Chen. Incomplete Laser 3D Point Cloud Classification and Completion Approach Based on Object Symmetry under Occlusion Conditions[J]. Laser & Optoelectronics Progress, 2023, 60(20): 2010004 Copy Citation Text show less
    Approach architecture and system construction. (a) Proposed method framework; (b) schematic of system construction
    Fig. 1. Approach architecture and system construction. (a) Proposed method framework; (b) schematic of system construction
    Partial complete point cloud after multi-station collection and fusion
    Fig. 2. Partial complete point cloud after multi-station collection and fusion
    Schematic of establishing a symmetric plane of incomplete point cloud
    Fig. 3. Schematic of establishing a symmetric plane of incomplete point cloud
    Redundant point removal algorithm
    Fig. 4. Redundant point removal algorithm
    Completion results of half residual defect point cloud. (a) Rectangular pyramid; (b) hexagonal pyramid
    Fig. 5. Completion results of half residual defect point cloud. (a) Rectangular pyramid; (b) hexagonal pyramid
    Completion results of incomplete point cloud less than half (single acquisition). (a) Iron tower;(b)pyramid;(c)dodecahedron;(d)hexagonal prism
    Fig. 6. Completion results of incomplete point cloud less than half (single acquisition). (a) Iron tower;(b)pyramid;(c)dodecahedron;(d)hexagonal prism
    Completion results of incomplete point cloud less than half (self defect). (a) House; (b) missile car
    Fig. 7. Completion results of incomplete point cloud less than half (self defect). (a) House; (b) missile car
    Completion results of incomplete point cloud more than half. (a) Cross; (b) sofa
    Fig. 8. Completion results of incomplete point cloud more than half. (a) Cross; (b) sofa
    Completion results of incomplete point cloud more than half (cross)
    Fig. 9. Completion results of incomplete point cloud more than half (cross)
    Fusion results of extremely defective point cloud
    Fig. 10. Fusion results of extremely defective point cloud
    Completion results of extremely defective point cloud
    Fig. 11. Completion results of extremely defective point cloud
    NameParameter setting
    Point cloud acquisition deviceZivid One+ Medium
    Optimal acquisition range /m1‒3
    Distance of acquisition d /m2
    Angle of acquisition α /(°)45
    Table 1. System equipment and parameter setting
    CategorySample graphFeature and definition
    Half residual defect point cloud or ,and at least
    Incomplete point clouds less than half,,
    Incomplete point clouds more than half∀Di>0 or ∀Di<0,min{n,m}=0,max{n,m}>0,100σ≥min{Di}>σ or less than N10000Di≤σ2
    Extremely defective point cloud or ,,,and
    Table 2. Classification of incomplete point cloud
    Evaluation indexHexagonal pyramidRectangular pyramid
    RMS /cm0.10280.1702
    Surface area of half residual defect point cloud /cm2113.17188.51
    Surface area of the full model point cloud /cm2200.81327.90
    Surface area of the fused point cloud /cm2199.40327.09
    Surface area approximation of the fused point cloud to the full model point cloud /%99.399.8
    Table 3. Evaluation index value of half residual defect point cloud
    Evaluation indexIron towerPyramidDodecahedronHexagonal prismsHouseMissile car
    RMS /cm0.13790.08060.08670.09450.17460.1288
    Surface area of incomplete point cloud less than half /cm267.5671.02124.04209.92122.4556.92
    Surface area of the full model point cloud /cm2117.51138.74219.13275.73134.7875.06
    Surface area of the fused point cloud /cm2117.29136.79217.51270.67134.3173.72
    Surface area approximation of the fused point cloud to the full model point cloud /%99.898.699.398.299.798.2
    Table 4. Evaluation index value of incomplete point cloud less than half
    Evaluation indexCrossSofa
    RMS /cm0.14840.1382
    Surface area of incomplete point cloud more than half /cm2148.7721225.35
    Surface area of the full model point cloud /cm2356.2650048.46
    Surface area of the fused point cloud /cm2362.0650318.77
    Surface area approximation of the fused point cloud to the full model point cloud /%98.499.5
    Table 5. Evaluation index value of incomplete point cloud more than half
    Evaluation indexFaucetArmchair
    RMS /cm0.05490.1210
    Surface area of extremely defective point cloud /cm2630.0310330.24
    Surface area of the full model point cloud /cm22051.7431776.47
    Surface area of the fused point cloud /cm22082.1931079.61
    Surface area approximation of the fused point cloud to the full model point cloud /%98.597.8
    Table 6. Evaluation index value of extremely defective point cloud
    Yong Tong, Fangyong Xu, Ning Yang, Hui Chen. Incomplete Laser 3D Point Cloud Classification and Completion Approach Based on Object Symmetry under Occlusion Conditions[J]. Laser & Optoelectronics Progress, 2023, 60(20): 2010004
    Download Citation