Cargando…

Uniaxial Partitioning Strategy for Efficient Point Cloud Registration

In 3D reconstruction applications, an important issue is the matching of point clouds corresponding to different perspectives of a particular object or scene, which is addressed by the use of variants of the Iterative Closest Point (ICP) algorithm. In this work, we introduce a cloud-partitioning str...

Descripción completa

Detalles Bibliográficos
Autores principales: Souza Neto, Polycarpo, Marques Soares, José, Pereira Thé, George André
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9030376/
https://www.ncbi.nlm.nih.gov/pubmed/35458872
http://dx.doi.org/10.3390/s22082887
_version_ 1784692123845525504
author Souza Neto, Polycarpo
Marques Soares, José
Pereira Thé, George André
author_facet Souza Neto, Polycarpo
Marques Soares, José
Pereira Thé, George André
author_sort Souza Neto, Polycarpo
collection PubMed
description In 3D reconstruction applications, an important issue is the matching of point clouds corresponding to different perspectives of a particular object or scene, which is addressed by the use of variants of the Iterative Closest Point (ICP) algorithm. In this work, we introduce a cloud-partitioning strategy for improved registration and compare it to other relevant approaches by using both time and quality of pose correction. Quality is assessed from a rotation metric and also by the root mean square error (RMSE) computed over the points of the source cloud and the corresponding closest ones in the corrected target point cloud. A wide and plural set of experimentation scenarios was used to test the algorithm and assess its generalization, revealing that our cloud-partitioning approach can provide a very good match in both indoor and outdoor scenes, even when the data suffer from noisy measurements or when the data size of the source and target models differ significantly. Furthermore, in most of the scenarios analyzed, registration with the proposed technique was achieved in shorter time than those from the literature.
format Online
Article
Text
id pubmed-9030376
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-90303762022-04-23 Uniaxial Partitioning Strategy for Efficient Point Cloud Registration Souza Neto, Polycarpo Marques Soares, José Pereira Thé, George André Sensors (Basel) Article In 3D reconstruction applications, an important issue is the matching of point clouds corresponding to different perspectives of a particular object or scene, which is addressed by the use of variants of the Iterative Closest Point (ICP) algorithm. In this work, we introduce a cloud-partitioning strategy for improved registration and compare it to other relevant approaches by using both time and quality of pose correction. Quality is assessed from a rotation metric and also by the root mean square error (RMSE) computed over the points of the source cloud and the corresponding closest ones in the corrected target point cloud. A wide and plural set of experimentation scenarios was used to test the algorithm and assess its generalization, revealing that our cloud-partitioning approach can provide a very good match in both indoor and outdoor scenes, even when the data suffer from noisy measurements or when the data size of the source and target models differ significantly. Furthermore, in most of the scenarios analyzed, registration with the proposed technique was achieved in shorter time than those from the literature. MDPI 2022-04-09 /pmc/articles/PMC9030376/ /pubmed/35458872 http://dx.doi.org/10.3390/s22082887 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Souza Neto, Polycarpo
Marques Soares, José
Pereira Thé, George André
Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title_full Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title_fullStr Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title_full_unstemmed Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title_short Uniaxial Partitioning Strategy for Efficient Point Cloud Registration
title_sort uniaxial partitioning strategy for efficient point cloud registration
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9030376/
https://www.ncbi.nlm.nih.gov/pubmed/35458872
http://dx.doi.org/10.3390/s22082887
work_keys_str_mv AT souzanetopolycarpo uniaxialpartitioningstrategyforefficientpointcloudregistration
AT marquessoaresjose uniaxialpartitioningstrategyforefficientpointcloudregistration
AT pereirathegeorgeandre uniaxialpartitioningstrategyforefficientpointcloudregistration