Colored Point Cloud Registration by Depth Filtering

In the last stage of colored point cloud registration, depth measurement errors hinder the achievement of accurate and visually plausible alignments. Recently, an algorithm has been proposed to extend the Iterative Closest Point (ICP) algorithm to refine the measured depth values instead of the pose...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Ouk Choi, Wonjun Hwang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	point cloud registration ICP depth filtering Chemical technology TP1-1185
Acceso en línea:	https://doaj.org/article/66b9172a1215480286c5b860e2ff5bf5
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:66b9172a1215480286c5b860e2ff5bf5
record_format	dspace
spelling	oai:doaj.org-article:66b9172a1215480286c5b860e2ff5bf52021-11-11T19:03:31ZColored Point Cloud Registration by Depth Filtering10.3390/s212170231424-8220https://doaj.org/article/66b9172a1215480286c5b860e2ff5bf52021-10-01T00:00:00Zhttps://www.mdpi.com/1424-8220/21/21/7023https://doaj.org/toc/1424-8220In the last stage of colored point cloud registration, depth measurement errors hinder the achievement of accurate and visually plausible alignments. Recently, an algorithm has been proposed to extend the Iterative Closest Point (ICP) algorithm to refine the measured depth values instead of the pose between point clouds. However, the algorithm suffers from numerical instability, so a postprocessing step is needed to restrict erroneous output depth values. In this paper, we present a new algorithm with improved numerical stability. Unlike the previous algorithm heavily relying on point-to-plane distances, our algorithm constructs a cost function based on an adaptive combination of two different projected distances to prevent numerical instability. We address the problem of registering a source point cloud to the union of the source and reference point clouds. This extension allows all source points to be processed in a unified filtering framework, irrespective of the existence of their corresponding points in the reference point cloud. The extension also improves the numerical stability of using the point-to-plane distances. The experiments show that the proposed algorithm improves the registration accuracy and provides high-quality alignments of colored point clouds.Ouk ChoiWonjun HwangMDPI AGarticlepoint cloud registrationICPdepth filteringChemical technologyTP1-1185ENSensors, Vol 21, Iss 7023, p 7023 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	point cloud registration ICP depth filtering Chemical technology TP1-1185
spellingShingle	point cloud registration ICP depth filtering Chemical technology TP1-1185 Ouk Choi Wonjun Hwang Colored Point Cloud Registration by Depth Filtering
description	In the last stage of colored point cloud registration, depth measurement errors hinder the achievement of accurate and visually plausible alignments. Recently, an algorithm has been proposed to extend the Iterative Closest Point (ICP) algorithm to refine the measured depth values instead of the pose between point clouds. However, the algorithm suffers from numerical instability, so a postprocessing step is needed to restrict erroneous output depth values. In this paper, we present a new algorithm with improved numerical stability. Unlike the previous algorithm heavily relying on point-to-plane distances, our algorithm constructs a cost function based on an adaptive combination of two different projected distances to prevent numerical instability. We address the problem of registering a source point cloud to the union of the source and reference point clouds. This extension allows all source points to be processed in a unified filtering framework, irrespective of the existence of their corresponding points in the reference point cloud. The extension also improves the numerical stability of using the point-to-plane distances. The experiments show that the proposed algorithm improves the registration accuracy and provides high-quality alignments of colored point clouds.
format	article
author	Ouk Choi Wonjun Hwang
author_facet	Ouk Choi Wonjun Hwang
author_sort	Ouk Choi
title	Colored Point Cloud Registration by Depth Filtering
title_short	Colored Point Cloud Registration by Depth Filtering
title_full	Colored Point Cloud Registration by Depth Filtering
title_fullStr	Colored Point Cloud Registration by Depth Filtering
title_full_unstemmed	Colored Point Cloud Registration by Depth Filtering
title_sort	colored point cloud registration by depth filtering
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/66b9172a1215480286c5b860e2ff5bf5
work_keys_str_mv	AT oukchoi coloredpointcloudregistrationbydepthfiltering AT wonjunhwang coloredpointcloudregistrationbydepthfiltering
_version_	1718431649203486720

Colored Point Cloud Registration by Depth Filtering

Ejemplares similares