Downsample-Based Improved Dense Point Cloud Registration Framework

Shuai Yang*, Chunlei Song, Yongqiang Han, Jiabin Chen, Zhengquan Piao, Zhenhao Wang

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

In LiDAR-based SLAM algorithms, the process of point cloud registration stands as a pivotal step. When the actual sensor is used to collect point cloud data, the quantity of points within the collected point cloud is frequently immense. Traditional point cloud registration algorithms cannot effectively and quickly handle the registration of dense point clouds. This paper presents a Downsample-based Improved Dense Point Cloud Registration Framework. On the basis of ensuring the registration accuracy, the registration of tens of millions of point clouds can be quickly realized, which saves a lot of time for the entire mapping process. After experimental verification, the algorithm can realize the registration of tens of millions of point clouds within 2 min, which provides a solution for the registration of dense point clouds.

Original languageEnglish
Title of host publicationAdvances in Guidance, Navigation and Control - Proceedings of 2024 International Conference on Guidance, Navigation and Control Volume 6
EditorsLiang Yan, Haibin Duan, Yimin Deng
PublisherSpringer Science and Business Media Deutschland GmbH
Pages354-365
Number of pages12
ISBN (Print)9789819622191
DOIs
Publication statusPublished - 2025
EventInternational Conference on Guidance, Navigation and Control, ICGNC 2024 - Changsha, China
Duration: 9 Aug 202411 Aug 2024

Publication series

NameLecture Notes in Electrical Engineering
Volume1342 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on Guidance, Navigation and Control, ICGNC 2024
Country/TerritoryChina
CityChangsha
Period9/08/2411/08/24

Keywords

  • Dense Point Cloud
  • Downsample-based
  • Point Cloud Registration

Fingerprint

Dive into the research topics of 'Downsample-Based Improved Dense Point Cloud Registration Framework'. Together they form a unique fingerprint.

Cite this