Infrared and Laser Engineering, Volume. 51, Issue 5, 20210342(2022)

Local neighborhood feature point extraction and matching for point cloud alignment

Mingjun Wang1...2, Fang Yi1, Le Li1 and Chaojun Huang2 |Show fewer author(s)
Author Affiliations
  • 1School of Automation and Information Engineering, Xi’an University of Technology, Xi’an 710048, China
  • 2School of Physics and Telecommunications Engineering, Shaanxi University of Technology, Hanzhong 723001, China
  • show less
    Figures & Tables(21)
    Changes in the surface of a local neighborhoods. (a) Relatively flat surface; (b) Undulating surface
    Feature point extraction of Dragon model under different artificially selected thresholds Dragon模型在人为选取不同阈值下的特征点提取情况
    Feature point extraction for Dragon 0°. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Feature point extraction for Bunny 0°. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Influence of neighborhood radius r on feature point extraction. (a) Relationship between registration error and feature point extraction radius r; (b) Relationship between registration time and feature point extraction radius r邻域半径对特征点提取的影响。(a)配准误差与特征点提取半径的关系;(b)配准时间与特征点提取半径的关系
    Rough matching results of Dragon in different feature point extraction methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Rough matching results of Bunny in different feature point extraction methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Results of fine registration for Dragon and Bunny. (a) ICP algorithm; (b) Proposed ICP algorithm
    Rough matching results of Bunny with 10% noise under different methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Rough matching results of Bunny with 20% noise under different methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Results of fine registration for Bunny with 10% and 20% noise. (a) ICP algorithm; (b) Proposed ICP algorithm
    Rough matching results of Room in different feature point extraction methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Rough matching results of Land in different feature point extraction methods. (a) ISS; (b) SIFT; (c) Harris3D; (d) Proposed method
    Results of fine registration for Room and Land. (a) ICP algorithm; (b) Proposed ICP algorithm
    • Table 1. Point cloud registration parameter settings

      View table
      View in Article

      Table 1. Point cloud registration parameter settings

      Parametersdminiter_maxεerror
      Value10 mr5010−6 mr
    • Table 2. Alignment efficiency comparison of Dragon and Bunny for coarse matching in different methods

      View table
      View in Article

      Table 2. Alignment efficiency comparison of Dragon and Bunny for coarse matching in different methods

      ModelBunnyDragon
      Matching error/10−6 m Time-consuming/sMatching error/10−6 m Time-consuming/s
      ISS2.3345.42.1043.2
      SIFT2.0285.92.1476.6
      Harris3D2.1442.62.6238.4
      Proposed method1.7825.81.9123.0
    • Table 3. Comparison of alignment efficiency for Dragon and Bunny fine alignment

      View table
      View in Article

      Table 3. Comparison of alignment efficiency for Dragon and Bunny fine alignment

      ModelAlgorithmMatching error/10−6 m Time-consuming/s
      BunnyICP0.0038521.1
      Proposed -ICP0.003912.5
      DragonICP1.133420.4
      Proposed -ICP1.191312.1
    • Table 4. Alignment efficiency comparison of Bunny with 10% and 20% noise for coarse matching in different methods

      View table
      View in Article

      Table 4. Alignment efficiency comparison of Bunny with 10% and 20% noise for coarse matching in different methods

      ModelBunny with 10% noiseBunny with 20% noise
      Matching error/10−6 m Time-consuming/sMatching error/10−6 m Time-consuming/s
      ISS3.2845.26.1743.2
      SIFT6.39105.4Fail
      Harris3DFailFail
      Proposed method3.11244.1523
    • Table 5. Alignment efficiency comparison of Bunny with 10% and 20% noise fine alignment

      View table
      View in Article

      Table 5. Alignment efficiency comparison of Bunny with 10% and 20% noise fine alignment

      ModelAlgorithmMatching error/ 10−6 m Time-consuming/ s
      Bunny with 10% noiseICP2.75143.3
      Proposed -ICP2.7234.1
      Bunny with 20% noiseICP2.42149.7
      Proposed -ICP2.3438.5
    • Table 6. Alignment efficiency comparison of Room and Land for coarse matching in different methods

      View table
      View in Article

      Table 6. Alignment efficiency comparison of Room and Land for coarse matching in different methods

      ModelRoomLand
      Matching error/mTime-consuming/sMatching error/mTime-consuming/s
      ISS0.4622121.70.0328167.4
      SIFT0.2091182.80.0294214.0
      Harris3D0.384589.50.0347138.6
      Proposed method0.196267.30.027367.3
    • Table 7. Alignment efficiency comparison of Room and Land fine alignment

      View table
      View in Article

      Table 7. Alignment efficiency comparison of Room and Land fine alignment

      ModelAlgorithmMatching error/10−6 m Time-consuming/s
      RoomICP0.16410817.1
      Proposed -ICP0.164576189.9
      LandICP0.023628420.4
      Proposed -ICP0.02380237
    Tools

    Get Citation

    Copy Citation Text

    Mingjun Wang, Fang Yi, Le Li, Chaojun Huang. Local neighborhood feature point extraction and matching for point cloud alignment[J]. Infrared and Laser Engineering, 2022, 51(5): 20210342

    Download Citation

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

    Category: Image processing

    Received: May. 27, 2021

    Accepted: --

    Published Online: Jun. 14, 2022

    The Author Email:

    DOI:10.3788/IRLA20210342

    Topics