Research on point cloud matching algorithm based on point pair feature and improved ICP

Chaoya Qi; Zhexue Qe; Haiyang Sun; Qingyu Cai; Fang Wang; Mingzhe Zhao; Xiaoan Tang

doi:10.1117/12.3011099

2 November 2023 Research on point cloud matching algorithm based on point pair feature and improved ICP

Chaoya Qi, Zhexue Qe, Haiyang Sun, Qingyu Cai, Fang Wang, Mingzhe Zhao, Xiaoan Tang

Proceedings Volume 12919, International Conference on Electronic Materials and Information Engineering (EMIE 2023); 129191M (2023) https://doi.org/10.1117/12.3011099
Event: 3rd International Conference on Electronic Materials and Information Engineering (EMIE 2023), 2023, Guangzhou,, China

Abstract

A point cloud matching algorithm based on point pair features with improved ICP is proposed to address the problems of slow target recognition and low accuracy in complex scenes such as occlusion and overlap. In the offline training phase, the algorithm creates a global model description based on directed point pair features and uses hash table storage to speed up the finding time; in the online matching phase, the generalized Hoff voting strategy is used to complete the point pair matching and generate candidate poses; finally, the obtained candidate poses are clustered and filtered and the poses are optimized by the overlap rate between the field point cloud and the model point cloud and the improved ICP algorithm. In this paper, the proposed algorithm is experimented for different complex scenes, and the experimental results prove that the recognition rate and feature point matching rate of this paper are high and have good robustness for the point cloud data with large data volume and poor quality.

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Chaoya Qi, Zhexue Qe, Haiyang Sun, Qingyu Cai, Fang Wang, Mingzhe Zhao, and Xiaoan Tang "Research on point cloud matching algorithm based on point pair feature and improved ICP", Proc. SPIE 12919, International Conference on Electronic Materials and Information Engineering (EMIE 2023), 129191M (2 November 2023); https://doi.org/10.1117/12.3011099

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Point clouds

Detection and tracking algorithms

Data modeling

Target recognition

3D modeling

Matrices

Mathematical optimization

Show All Keywords

Keywords/Phrases

Search In:

Publication Years