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. 57, Issue 20, 201503(2020)

Research on Two-Stage Variable Scale Three-Dimensional Point Cloud Registration Algorithm

Sheng Lu1, Jungang Han1, Lianzhe Wang1, Haipeng Tang2, Quan Qi3, Ningyu Feng4, and Shaojie Tang5、*
Author Affiliations
  • 1School of Computer Science & Technology, Xi'an University of Posts & Telecommunications, Xi'an, Shaanxi 710121, China;
  • 2School of Computing Sciences and Computer Engineering, University of Southern Mississippi, MS 39406, USA
  • 3College of Information Science and Technology, Shihezi University, Shihezi, Xinjiang 832000, China
  • 4Otolaryngological Wards, General Hospital of Ningxia Medical University, Yinchuan, Ningxia 750004, China
  • 5School of Automation, Xi'an University of Posts & Telecommunications, Xi'an, Shaanxi 710121, China;
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (0)
    References (19)
    Cited By (2)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Flow chart of proposed algorithm

    Fig. 1. Flow chart of proposed algorithm

    Download full size
    Registration result when geometric parameter is at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Fig. 2. Registration result when geometric parameter is at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Download full size
    Registration result when geometric parameter is not at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Fig. 3. Registration result when geometric parameter is not at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Download full size
    Butterfly model data collection. (a) Butterfly model in kind; (b) butterfly point cloud data

    Fig. 4. Butterfly model data collection. (a) Butterfly model in kind; (b) butterfly point cloud data

    Download full size
    Registration result when geometric parameter is at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Fig. 5. Registration result when geometric parameter is at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Download full size
    Registration result when geometric parameter is not at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Fig. 6. Registration result when geometric parameter is not at the lattice point. (a) Original point cloud; (b) ICP algorithm; (c) SICP algorithm; (d) first stage registration+ICP algorithm; (e) proposed algorithm

    Download full size

    • Table 1. Registration error and relative scale error of Bunny point cloud data

      View table

      Table 1. Registration error and relative scale error of Bunny point cloud data

      AlgorithmPosition of geometricparameterRegistrationerror /mmRelative scaleerror /%
      ICP algorithm[1]On lattice0.00392
      Not on lattice0.00403
      SICP algorithm[16]On lattice1.436120.1
      Not on lattice1.895570.1
      First stage registration+ICP algorithmOn lattice8.4361×10-68.1
      Not on lattice4.5778×10-58.7
      Proposed algorithmOn lattice5.3226×10-300
      Not on lattice9.5239×10-110

    • Table 2. Registration error and relative scale error of butterfly point cloud

      View table

      Table 2. Registration error and relative scale error of butterfly point cloud

      AlgorithmPosition of geometricparameterRegistrationerror /mmRelative scaleerror /%
      ICP algorithm[1]On lattice308.2834
      Not on lattice453.6902
      SICP algorithm[16]On lattice4.8101×1050.1
      Not on lattice4.8316×1050.1
      First stage registration+ICP algorithmOn lattice1.32489.3
      Not on lattice2.98449.6
      Proposed algorithmOn lattice2.7156×10-50
      Not on lattice3.1674×10-40
    Tools

    Get Citation

    Copy Citation Text

    Sheng Lu, Jungang Han, Lianzhe Wang, Haipeng Tang, Quan Qi, Ningyu Feng, Shaojie Tang. Research on Two-Stage Variable Scale Three-Dimensional Point Cloud Registration Algorithm[J]. Laser & Optoelectronics Progress, 2020, 57(20): 201503

    Download Citation

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

    Category: Machine Vision

    Received: Jan. 19, 2020

    Accepted: Feb. 24, 2020

    Published Online: Oct. 10, 2020

    The Author Email: Shaojie Tang (tangshaojie@xupt.edu.cn)

    DOI:10.3788/LOP57.201503

    Topics

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