Downsampling of a 3D LiDAR Point Cloud by a Tensor Voting Based Method

Osman Ervan, Hakan Temeltas

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

4 Citations (Scopus)

Abstract

A point cloud is a data format that consists of a combination of multiple points used to identify an object or environment. 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. The aim of this study is to ensure that the point clouds obtained with 3D LiDAR are sampled while preserving their geometric features. For this process, it is inspired from the method known in the literature as Tensor Voting, which is used to extract geometric features in N-dimensional space. After determining the areas with high density in the point cloud, with the help of tensor voting, it is aimed to express the same geometric attributes with a lower number of points by reducing the density.

Original languageEnglish
Title of host publicationELECO 2019 - 11th International Conference on Electrical and Electronics Engineering
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages880-884
Number of pages5
ISBN (Electronic)9786050112757
DOIs
Publication statusPublished - Nov 2019
Event11th International Conference on Electrical and Electronics Engineering, ELECO 2019 - Bursa, Turkey
Duration: 28 Nov 201930 Nov 2019

Publication series

NameELECO 2019 - 11th International Conference on Electrical and Electronics Engineering

Conference

Conference11th International Conference on Electrical and Electronics Engineering, ELECO 2019
Country/TerritoryTurkey
CityBursa
Period28/11/1930/11/19

Bibliographical note

Publisher Copyright:
© 2019 Chamber of Turkish Electrical Engineers.

Fingerprint

Dive into the research topics of 'Downsampling of a 3D LiDAR Point Cloud by a Tensor Voting Based Method'. Together they form a unique fingerprint.

Cite this