Tensor voting based 3-D point cloud processing for downsampling and registration

Osman Ervan; Hakan Temeltas

doi:10.1145/3449301.3449312

Tensor voting based 3-D point cloud processing for downsampling and registration

Osman Ervan, Hakan Temeltas

Department of Control and Automation Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

Point cloud registration is related with many significant and compelling 3D perception problems including simultaneous localization and mapping (SLAM), 3D object reconstruction, dense 3D environment generation, pose estimation, and object tracking. A point cloud can be defined as a data format that consists of a combination of multiple points used to identify an object or environment. The aim of this study is to propose a point cloud registration method, which ensures that the point clouds obtained with 3D LiDAR are sampled while preserving their geometric features and the point clouds are registered with high success rate. For this process, it is inspired from the method known in the literature as Tensor Voting, which is originally used to extract geometric features in N-dimensional space. In point cloud registration process, a coarse registration step has been proposed, which focusses on feature registration instead of point registration.

Original language	English
Title of host publication	2020 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020
Publisher	Association for Computing Machinery
Pages	57-63
Number of pages	7
ISBN (Electronic)	9781450388597
DOIs	https://doi.org/10.1145/3449301.3449312
Publication status	Published - 20 Nov 2020
Event	6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020 - Singapore, Singapore Duration: 20 Nov 2020 → 22 Nov 2020

Publication series

Name	ACM International Conference Proceeding Series

Conference

Conference	6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020
Country/Territory	Singapore
City	Singapore
Period	20/11/20 → 22/11/20

Bibliographical note

Publisher Copyright:
© 2020 ACM.

Funding

This project is financially supported by the Turkish Scientific andTechnological Research Council (TUBITAK) under the 116E178 grand number.

Funders	Funder number
TUBITAK	116E178
Turkish Scientific andTechnological Research Council

Keywords

Downsampling
LiDAR
Mobile robotics
Point cloud
Registration
Tensor voting

Access to Document

10.1145/3449301.3449312

Cite this

@inproceedings{94581f99a5dc4655bc1dc2a408e4b1b7,

title = "Tensor voting based 3-D point cloud processing for downsampling and registration",

abstract = "Point cloud registration is related with many significant and compelling 3D perception problems including simultaneous localization and mapping (SLAM), 3D object reconstruction, dense 3D environment generation, pose estimation, and object tracking. A point cloud can be defined as a data format that consists of a combination of multiple points used to identify an object or environment. The aim of this study is to propose a point cloud registration method, which ensures that the point clouds obtained with 3D LiDAR are sampled while preserving their geometric features and the point clouds are registered with high success rate. For this process, it is inspired from the method known in the literature as Tensor Voting, which is originally used to extract geometric features in N-dimensional space. In point cloud registration process, a coarse registration step has been proposed, which focusses on feature registration instead of point registration.",

keywords = "Downsampling, LiDAR, Mobile robotics, Point cloud, Registration, Tensor voting",

author = "Osman Ervan and Hakan Temeltas",

note = "Publisher Copyright: {\textcopyright} 2020 ACM.; 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020 ; Conference date: 20-11-2020 Through 22-11-2020",

year = "2020",

month = nov,

day = "20",

doi = "10.1145/3449301.3449312",

language = "English",

series = "ACM International Conference Proceeding Series",

publisher = "Association for Computing Machinery",

pages = "57--63",

booktitle = "2020 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020",

}

Ervan, O & Temeltas, H 2020, Tensor voting based 3-D point cloud processing for downsampling and registration. in 2020 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020., 3449312, ACM International Conference Proceeding Series, Association for Computing Machinery, pp. 57-63, 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020, Singapore, Singapore, 20/11/20. https://doi.org/10.1145/3449301.3449312

Tensor voting based 3-D point cloud processing for downsampling and registration. / Ervan, Osman ; Temeltas, Hakan.
2020 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020. Association for Computing Machinery, 2020. p. 57-63 3449312 (ACM International Conference Proceeding Series).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Tensor voting based 3-D point cloud processing for downsampling and registration

AU - Ervan, Osman

AU - Temeltas, Hakan

PY - 2020/11/20

Y1 - 2020/11/20

N2 - Point cloud registration is related with many significant and compelling 3D perception problems including simultaneous localization and mapping (SLAM), 3D object reconstruction, dense 3D environment generation, pose estimation, and object tracking. A point cloud can be defined as a data format that consists of a combination of multiple points used to identify an object or environment. The aim of this study is to propose a point cloud registration method, which ensures that the point clouds obtained with 3D LiDAR are sampled while preserving their geometric features and the point clouds are registered with high success rate. For this process, it is inspired from the method known in the literature as Tensor Voting, which is originally used to extract geometric features in N-dimensional space. In point cloud registration process, a coarse registration step has been proposed, which focusses on feature registration instead of point registration.

AB - Point cloud registration is related with many significant and compelling 3D perception problems including simultaneous localization and mapping (SLAM), 3D object reconstruction, dense 3D environment generation, pose estimation, and object tracking. A point cloud can be defined as a data format that consists of a combination of multiple points used to identify an object or environment. The aim of this study is to propose a point cloud registration method, which ensures that the point clouds obtained with 3D LiDAR are sampled while preserving their geometric features and the point clouds are registered with high success rate. For this process, it is inspired from the method known in the literature as Tensor Voting, which is originally used to extract geometric features in N-dimensional space. In point cloud registration process, a coarse registration step has been proposed, which focusses on feature registration instead of point registration.

KW - Downsampling

KW - LiDAR

KW - Mobile robotics

KW - Point cloud

KW - Registration

KW - Tensor voting

UR - http://www.scopus.com/inward/record.url?scp=85108163202&partnerID=8YFLogxK

U2 - 10.1145/3449301.3449312

DO - 10.1145/3449301.3449312

M3 - Conference contribution

AN - SCOPUS:85108163202

T3 - ACM International Conference Proceeding Series

SP - 57

EP - 63

BT - 2020 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020

PB - Association for Computing Machinery

T2 - 6th International Conference on Robotics and Artificial Intelligence, ICRAI 2020

Y2 - 20 November 2020 through 22 November 2020

ER -

Tensor voting based 3-D point cloud processing for downsampling and registration

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this