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 10, 101101(2020)

Point Cloud Registration Algorithm Based on Image Feature and Singular Value Decomposition

Fuqun Zhao1、* and Guohua Geng2
Author Affiliations
  • 1School of Information, Xi'an University of Finance and Economics, Xi'an, Shaanxi 710100, China
  • 2School of Information Science and Technology, Northwest University, Xi'an, Shaanxi 710127, China
    • show less
    AbstractGet PDF(in Chinese)
    Figures&Tables (7)
    Equations (0)
    References (14)
    Cited By (5)
    Tools
    Paper Information
    Topics
    Figures & Tables(7)
    Framework of registration algorithm

    Fig. 1. Framework of registration algorithm

    Download full size
    Pixel gray level of BA image

    Fig. 2. Pixel gray level of BA image

    Download full size
    Histogram of IDSC features at different sampling points. (a) Three sampling points for head contour; (b) IDSC histogram at three sampling points

    Fig. 3. Histogram of IDSC features at different sampling points. (a) Three sampling points for head contour; (b) IDSC histogram at three sampling points

    Download full size
    Four groups of point clouds to be registered. (a) Bunny; (b) Dragon; (c) skull; (d) cultural relic

    Fig. 4. Four groups of point clouds to be registered. (a) Bunny; (b) Dragon; (c) skull; (d) cultural relic

    Download full size
    Rough registration results of four groups of point clouds. (a) Bunny; (b) Dragon; (c) skull; (d) cultural relic

    Fig. 5. Rough registration results of four groups of point clouds. (a) Bunny; (b) Dragon; (c) skull; (d) cultural relic

    Download full size
    Fine registration results of four groups of point clouds. (a) Bunny; (b) Dragon;(c) skull; (d) cultural relic

    Fig. 6. Fine registration results of four groups of point clouds. (a) Bunny; (b) Dragon;(c) skull; (d) cultural relic

    Download full size

    • Table 1. Comparison of registration results of four algorithms

      View table

      Table 1. Comparison of registration results of four algorithms

      Point cloudNumber of pointsRegistration algorithmRegistration error /mmRunning time /s
      Bunny40256, 40096ICP0.02895.2
      Ref. [13]0.02474.5
      Ref. [14]0.02013.7
      Proposed0.01852.8
      Dragon41841, 22092ICP0.03186.3
      Ref. [13]0.02745.3
      Ref. [14]0.02294.1
      Proposed0.02013.5
      Skull46842, 39787ICP0.03207.8
      Ref. [13]0.02746.6
      Ref. [14]0.02245.2
      Proposed0.01994.6
      Cultural relic44731, 39629ICP0.03268.5
      Ref. [13]0.02817.4
      Ref. [14]0.02356.0
      Proposed0.02065.4
    Tools

    Get Citation

    Copy Citation Text

    Fuqun Zhao, Guohua Geng. Point Cloud Registration Algorithm Based on Image Feature and Singular Value Decomposition[J]. Laser & Optoelectronics Progress, 2020, 57(10): 101101

    Download Citation

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

    Category: Imaging Systems

    Received: Jul. 17, 2019

    Accepted: Oct. 11, 2019

    Published Online: May. 8, 2020

    The Author Email: Fuqun Zhao (fuqunzhao@126.com)

    DOI:10.3788/LOP57.101101

    Topics

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