skip to main content
10.1145/3655532.3655581acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicrsaConference Proceedingsconference-collections
research-article

PCA Point cloud registration algorithm based on projection similarity

Published: 28 June 2024 Publication History

Abstract

To address the issue of slow speed and susceptibility to local optima in traditional iterative closest point (ICP) algorithms, a new algorithm was proposed that combines principal component analysis (PCA) and normal vector angle thresholding to remove error points. Firstly, the PCA method was used to find the principal coordinate system of the point cloud. After aligning the principal vectors in the coordinate system, there may be a situation where the direction of two principal vectors is reversed. For this situation, a method was proposed to correct the direction of the principal vectors by using a statistical matrix of the projected point cloud to calculate their similarity, greatly reducing the time for coarse registration. After obtaining a good initial pose for the point cloud, the overlapping parts of the two point clouds were extracted, and the ICP algorithm was improved by combining the normal vector angle of the point cloud for fine registration. Experimental results showed that this method can significantly improve registration efficiency and achieve good results.

References

[1]
Besl P J M. A method for registration of 3-D shapes[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1992, 14(2): 239-256.
[2]
Biber P, Straßer W. The normal distributions transform: A new approach to laser scan matching[C] Proceedings 2003 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2003)(Cat. No. 03CH37453). IEEE, 2003, 3: 2743-2748.
[3]
Huang J, Tao B, Zeng F. Point cloud registration algorithm based on ICP algorithm and 3D-NDT algorithm[J]. International Journal of Wireless and Mobile Computing, 2022, 22(2): 125-130.
[4]
Qin Q, Huang D, Yang Y, Point cloud registration algorithm based on improved ICP[C] International Conference on Computer Vision, Application, and Algorithm (CVAA 2022). SPIE, 2023, 12613: 273-277.
[5]
Chen A, Zhuang J, Han X. An Improved ICP Algorithm for 3D Point Cloud Registration[C] 2022 3rd International Conference on Pattern Recognition and Machine Learning (PRML). IEEE, 2022: 205-210.
[6]
Weng Z, Li Z, Zheng Z. Three-dimensional point cloud reconstruction and body ruler measurement of pig body under multi-angle KinectV2[C]//Proceedings of the 2023 3rd International Conference on Bioinformatics and Intelligent Computing. 2023: 39-44.
[7]
Wang H, Liu Y, Dong Z, You only hypothesize once: Point cloud registration with rotation-equivariant descriptors[C]//Proceedings of the 30th ACM International Conference on Multimedia. 2022: 1630-1641.
[8]
Aiger D, Mitra N J, Cohen-Or D. 4-points congruent sets for robust pairwise surface registration[J]. Acm Transactions on Graphics, 2008, 27(3):1-10.
[9]
Ma Guopeng, Ning Dianmin, Bian Yan.Research on point cloud registration algorithm based on ISS-Shot +3D-NDT[J] Mining Research and Development, 2021, 9 ( 5 ) :175-181.( in Chinese)
[10]
Jing L, Wu B, Li X S. Point cloud registration method based on SAC-IA and NDT fusion[J]. Journal of Grodesy and Geodynamics, 2021, 41(4): 378-381.
[11]
Qi C R, Su H, Mo K, Pointnet: Deep learning on point sets for 3d classification and segmentation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition. 2017: 652-660.
[12]
Kurobe A, Sekikawa Y, Ishikawa K, Corsnet: 3d point cloud registration by deep neural network[J]. IEEE Robotics and Automation Letters, 2020, 5(3): 3960-3966.
[13]
Lu W, Wan G, Zhou Y, Deepvcp: An end-to-end deep neural network for point cloud registration[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision. 2019: 12-21.
[14]
Qi C R, Yi L, Su H, Pointnet++: Deep hierarchical feature learning on point sets in a metric space[J]. Advances in neural information processing systems, 2017, 30.
[15]
Prokop M, Shaikh S A, Kim K S. Low overlapping point cloud registration using line features detection[J]. Remote Sensing, 2019, 12(1): 61.
[16]
Rajendra Y D, Mehrotra S C, Kale K V, Evaluation of Partially Overlapping 3D Point Cloud's Registration by using ICP variant and Cloud Compare[J]. The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, 2014, 40(8): 891.

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICRSA '23: Proceedings of the 2023 6th International Conference on Robot Systems and Applications
September 2023
335 pages
ISBN:9798400708039
DOI:10.1145/3655532
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 28 June 2024

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. ICP algorithm
  2. Normal vector entropy
  3. Point cloud registration
  4. Principal component analysis

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Conference

ICRSA 2023

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • 0
    Total Citations
  • 17
    Total Downloads
  • Downloads (Last 12 months)17
  • Downloads (Last 6 weeks)2
Reflects downloads up to 20 Feb 2025

Other Metrics

Citations

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media