2023
DOI: 10.1111/phor.12448
|View full text |Cite
|
Sign up to set email alerts
|

A histogram‐based sampling method for point cloud registration

Abstract: Accurate and efficient point cloud registration is essential in various fields, such as robotics, autonomous driving and medical imaging. The size of point clouds presents a significant challenge for existing registration methods. In this paper, a novel point cloud sampling method to improve the performance of the point cloud registration process is proposed. Instead of geometric feature preservation, which is preferred in most existing sampling methods, our approach scales every point and groups the scaled po… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 34 publications
0
3
0
Order By: Relevance
“…The RMSE of Euclidean distance was then calculated to evaluate the algorithm's performance. Furthermore, rotational and translational errors between the transformed point cloud data and the target point cloud data were examined (Ervan & Temeltas, 2023). The registration error heat map and the registration error histogram (Liu et al, 2020) were also adopted as the evaluation indicators.…”
Section: Accuracy Verificationmentioning
confidence: 99%
“…The RMSE of Euclidean distance was then calculated to evaluate the algorithm's performance. Furthermore, rotational and translational errors between the transformed point cloud data and the target point cloud data were examined (Ervan & Temeltas, 2023). The registration error heat map and the registration error histogram (Liu et al, 2020) were also adopted as the evaluation indicators.…”
Section: Accuracy Verificationmentioning
confidence: 99%
“…After more than 30 years of development, many mature variants of ICP have emerged. These variants improve one or several steps of the original ICP framework, including subset sampling (e.g., random sampling, octree sampling [Schnabel & Klein, 2006], Voxelgrid filtering [Rusu & Cousins, 2011], histogram sampling [Ervan & Temeltas, 2023]), distance metrics (e.g., pointto-line [Censi, 2008], point-to-plane [Chen & Medioni, 1992], symmetric point-to-plane [Rusinkiewicz, 2019], plane-to-plane [Koide et al, 2021b;Segal et al, 2009]), outlier rejection (e.g., sparse norm [Bouaziz et al, 2013;Li, Hu, & Ai, 2020a], anisotropy ICP [Maier-Hein et al, 2011], M-estimation [Chetverikov et al, 2005;Li, Hu, Ai, & Wang, 2021;Zhang et al, 2022]), and computational efficiency (e.g., Fast ICP [Zhang et al, 2022], EfficientVarICP [Rusinkiewicz & Levoy, 2001], and Anderson-accelerated ICP [Pavlov et al, 2018]).…”
Section: Scan Matchingmentioning
confidence: 99%
“…To reconstruct the geometric information of the scene in the image, several reconstruction frameworks are used, such as CMPMVS (Schonberger & Frahm, 2016), multiview environment structure from motion (SFM) (Schonberger & Frahm, 2016)/MVS, OpenMVS (Cernea, 2020), patch‐based multiview stereo frame (PMVS) (Furukawa & Ponce, 2007), and the shading‐aware multiview stereo (SMVS) framework (Langguth et al., 2016). The surface reconstruction algorithm (Labatut et al., 2009) mainly includes Poisson or Delauny network construction, and mesh texture mapping (Allene et al., 2008) assigns two‐dimensional (2D) space point information (such as colour and brightness) to the 3D space points in the object space through a certain mapping relationship (Ervan & Temeltas, 2023). The photometric consistency of the model is maintained by requiring uniform light between blocks (Luo, 2015).…”
Section: Related Workmentioning
confidence: 99%