Journals Articles Conferences News About CLP
Submit a paper Email Alert
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
2D MaterialsTransformation opticsQuantum PhotonicsSmall lasersSemiconductor UV PhotonicsSupersymmetric microring laser arrays

Laser & Optoelectronics Progress, Volume. 60, Issue 12, 1210023(2023)

Registration Algorithm for Differently Scaled Point Clouds Based on Artificial Bee Colony Optimization

Yiping Fan1,2, Baozhen Ge1,2, and Lei Chen3、*
Author Affiliations
  • 1School of Precision Instrument and Opto-Electronics Engineering, Tianjin University, Tianjin 300072, China
  • 2Key Laboratory of Opto-Electronic Information and Technology, Ministry of Education, Tianjin 300072, China
  • 3School of Information Engineering, Tianjin University of Commerce, Tianjin 300134, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (16)
    Equations (13)
    References (19)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(16)
    Flowchart of proposed algorithm

    Fig. 1. Flowchart of proposed algorithm

    Download full size
    Homologous point cloud data. (a) Bun000; (b) Bun045; (c) ArmadilloBack_0; (d) ArmadilloBack_30

    Fig. 2. Homologous point cloud data. (a) Bun000; (b) Bun045; (c) ArmadilloBack_0; (d) ArmadilloBack_30

    Download full size
    Cross-source point cloud data. (a) Bag_Kinect; (b) Bag_SFM; (c) Tsinghua gate_Lidar; (d) Tsinghua gate_SFM; (e) Life science building_Lidar; (f) Life science building_SFM

    Fig. 3. Cross-source point cloud data. (a) Bag_Kinect; (b) Bag_SFM; (c) Tsinghua gate_Lidar; (d) Tsinghua gate_SFM; (e) Life science building_Lidar; (f) Life science building_SFM

    Download full size
    Point clouds to be registered with different scaling factors. (a) Bunny, so=20; (b) Bunny, so=10; (c) Bunny, so=1.25; (d) Armadillo, so=20; (e) Armadillo, so=10; (f) Armadillo, so=1.25

    Fig. 4. Point clouds to be registered with different scaling factors. (a) Bunny, so=20; (b) Bunny, so=10; (c) Bunny, so=1.25; (d) Armadillo, so=20; (e) Armadillo, so=10; (f) Armadillo, so=1.25

    Download full size
    Registration results of various algorithms for Bunny point cloud under different scale factors. (a) EBABC-RS-IR; (b) ICP; (c) Scale-ICP; (d) CPD; (e) proposed algorithm

    Fig. 5. Registration results of various algorithms for Bunny point cloud under different scale factors. (a) EBABC-RS-IR; (b) ICP; (c) Scale-ICP; (d) CPD; (e) proposed algorithm

    Download full size
    Registration results of various algorithms for Armadillo point cloud under different scale factors. (a) EBABC-RS-IR; (b) ICP; (c) Scale-ICP; (d) CPD; (e) proposed algorithm

    Fig. 6. Registration results of various algorithms for Armadillo point cloud under different scale factors. (a) EBABC-RS-IR; (b) ICP; (c) Scale-ICP; (d) CPD; (e) proposed algorithm

    Download full size
    Point cloud registration results under different noise. (a) Bunny, 20 dB; (b) Bunny, 25 dB; (c) Bunny, 30 dB; (d) Armadillo, 20 dB; (e) Armadillo, 25 dB; (f) Armadillo, 30 dB

    Fig. 7. Point cloud registration results under different noise. (a) Bunny, 20 dB; (b) Bunny, 25 dB; (c) Bunny, 30 dB; (d) Armadillo, 20 dB; (e) Armadillo, 25 dB; (f) Armadillo, 30 dB

    Download full size
    Relative initial state of cross-source point clouds to be registered. (a) Bag; (b) Tsinghua gate; (c) Life science building

    Fig. 8. Relative initial state of cross-source point clouds to be registered. (a) Bag; (b) Tsinghua gate; (c) Life science building

    Download full size
    Local amplification effect of Bag registration

    Fig. 9. Local amplification effect of Bag registration

    Download full size
    Tsinghua gate point cloud registration results. (a) Main perspective; (b) prone perspective; (c) side perspective

    Fig. 10. Tsinghua gate point cloud registration results. (a) Main perspective; (b) prone perspective; (c) side perspective

    Download full size
    Life science building point cloud registration results. (a) Main perspective; (b) prone perspective; (c) side perspective

    Fig. 11. Life science building point cloud registration results. (a) Main perspective; (b) prone perspective; (c) side perspective

    Download full size

    • Table 1. Point cloud data information

      View table

      Table 1. Point cloud data information

      Point cloudImage to be registeredTarget /source point cloudNumber of pointsAngle of view
      BunnyBun000Target4025645°
      Bun045Source40097
      ArmadilloArmadilloBack_0Target1928330°
      ArmadilloBack_30Source12150
      BagBag_KinectTarget11595Unknown
      Bag_SFMSource21495
      Tsinghua gateTsinghua gate_LidarTarget33721Unknown
      Tsinghua gate_SFMSource971436
      Life science buildingLife science building _LidarTarget761729Unknown
      Life science building _SFMSource1813056

    • Table 2. RMSE for each registration algorithm with different scaling factors

      View table

      Table 2. RMSE for each registration algorithm with different scaling factors

      Point cloudsoScale-ICPCPDProposed algorithm
      Bunny201.425×10-22.127×10-31.970×10-3
      101.425×10-22.138×10-32.086×10-3
      1.251.425×10-22.152×10-31.985×10-3
      Armadillo201.503×10-21.652×10-28.525×10-3
      101.503×10-21.663×10-27.763×10-3
      1.251.503×10-21.629×10-27.758×10-3

    • Table 3. Time for each registration algorithm with different scaling factors

      View table

      Table 3. Time for each registration algorithm with different scaling factors

      Point cloudsoScale-ICPCPDProposed algorithm
      Bunny2044.28091.11017.120
      1043.44991.47017.670
      1.2543.45288.92816.852
      Armadillo209.62912.57712.335
      109.30615.45711.416
      1.259.59813.49914.477

    • Table 4. RMSE of the proposed algorithm under different noise

      View table

      Table 4. RMSE of the proposed algorithm under different noise

      Point cloudso20 dB25 dB30 dBNo noise
      Bunny208.229×10-34.594×10-33.799×10-31.970×10-3
      107.949×10-37.176×10-33.223×10-32.086×10-3
      1.258.358×10-34.704×10-33.073×10-31.985×10-3
      Armadillo201.010×10-28.815×10-38.034×10-38.525×10-3
      101.032×10-21.129×10-28.155×10-37.763×10-3
      1.251.184×10-28.804×10-38.312×10-37.758×10-3

    • Table 5. Time of the proposed algorithm under different noise

      View table

      Table 5. Time of the proposed algorithm under different noise

      Point cloudso20 dB25 dB30 dBNo noise
      Bunny2020.27920.87919.43217.120
      1020.28920.09920.60417.670
      1.2520.61719.99717.41916.852
      Armadillo2014.04514.77414.30812.335
      1014.93114.57013.65411.416
      1.2514.09814.82613.95614.477
    Tools

    Get Citation

    Copy Citation Text

    Yiping Fan, Baozhen Ge, Lei Chen. Registration Algorithm for Differently Scaled Point Clouds Based on Artificial Bee Colony Optimization[J]. Laser & Optoelectronics Progress, 2023, 60(12): 1210023

    Download Citation

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

    Category: Image Processing

    Received: May. 30, 2022

    Accepted: Jul. 14, 2022

    Published Online: Jun. 1, 2023

    The Author Email: Lei Chen (chenlei@tjcu.edu.cn)

    DOI:10.3788/LOP221735

    Topics

    laser devices and laser physics
    Lasers and Laser Optics
    Laser physics
    laser manufacturing
    Instrumentation, Measurement and Metrology