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. 59, Issue 8, 0810016(2022)

Point Cloud Registration Algorithm Based on NDT and Feature Point Detection

Yilin Yang1,2、*, Jiying Li1,2, Yan Wang1,2, and Yongqian Yu1,2
Author Affiliations
  • 1School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou , Gansu 730070, China
  • 2Gansu Industrial Transportation Automation Engineering Technology Research Center, Lanzhou , Gansu 730070, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (8)
    Equations (6)
    References (16)
    Cited By (4)
    Tools
    Paper Information
    Topics
    Figures & Tables(8)
    Block diagram of the proposed algorithm

    Fig. 1. Block diagram of the proposed algorithm

    Download full size
    Flow chart of the proposed algorithm

    Fig. 2. Flow chart of the proposed algorithm

    Download full size
    Key point extraction results。 (a) Original point cloud; (b) result after key point extraction

    Fig. 3. Key point extraction results。 (a) Original point cloud; (b) result after key point extraction

    Download full size
    Registration result of the proposed algorithm. (a) Original point cloud; (b) registration result of the proposed algorithm

    Fig. 4. Registration result of the proposed algorithm. (a) Original point cloud; (b) registration result of the proposed algorithm

    Download full size
    Bunny model. (a) Original point cloud; (b) registration result of ICP algorithm; (c) coarse registration of NDT algorithm; (d) registration result of proposed algorithm

    Fig. 5. Bunny model. (a) Original point cloud; (b) registration result of ICP algorithm; (c) coarse registration of NDT algorithm; (d) registration result of proposed algorithm

    Download full size
    Armadillo model. (a) Original point cloud; (b) registration result of ICP algorithm; (c) coarse registration of NDT algorithm; (d) registration result of proposed algorithm

    Fig. 6. Armadillo model. (a) Original point cloud; (b) registration result of ICP algorithm; (c) coarse registration of NDT algorithm; (d) registration result of proposed algorithm

    Download full size

    • Table 1. Running time of point cloud registration under different algorithms

      View table

      Table 1. Running time of point cloud registration under different algorithms

      DatasetTraditional ICP algorithmCoarse registration using NDT algorithmFine registration after key point extractionProposed algorithmAlgorithm in Ref.［14］
      Bunny2.3280.630.1560.7863.653
      Armadillo3.5390.920.3161.2365.561

    • Table 2. RMSE of point cloud registration under different algorithms

      View table

      Table 2. RMSE of point cloud registration under different algorithms

      DatasetTraditional ICP algorithmNDT algorithmAlgorithm in Ref.［14］Proposed algorithm
      Bunny3.697×10-43.896×10-43.369×10-43.156×10-4
      Armadillo3.986×10-44.185×10-43.712×10-43.592×10-4
    Tools

    Get Citation

    Copy Citation Text

    Yilin Yang, Jiying Li, Yan Wang, Yongqian Yu. Point Cloud Registration Algorithm Based on NDT and Feature Point Detection[J]. Laser & Optoelectronics Progress, 2022, 59(8): 0810016

    Download Citation

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

    Category: Image Processing

    Received: Feb. 26, 2021

    Accepted: May. 7, 2021

    Published Online: Apr. 11, 2022

    The Author Email: Yang Yilin (2235931584@qq.com)

    DOI:10.3788/LOP202259.0810016

    Topics

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