A Novel Technique For Indoor Object Distance Measurement By Using 3D Point Cloud and LiDAR

Jisoo Kim, Dongik Lee

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

1 Scopus citations

Abstract

The SLAM (Simultaneous Localization and Mapping) technology has been widely exploited to collect information of location and environment for indoor mobile robots. Usually, SLAM has a single LiDAR(Light Detection and Ranging) sensor which reveals its vulnerability to complex terrain or distinction between objects. A possible solution to overcome this problem is the data fusion technique with LiDAR and depth cameras. This paper presents a novel data fusion technique with LiDAR data and 3D-point cloud data for estimating the surrounding object locations. In the proposed technique, the surrounding object location data are extracted using the region-based segmentation technique in real time using 3D-point cloud images. The effectiveness of the proposed algorithm is demonstrated with a set of experiments based on ROS (Robot Operating System).

Original languageEnglish
Title of host publication2022 22nd International Conference on Control, Automation and Systems, ICCAS 2022
PublisherIEEE Computer Society
Pages1044-1048
Number of pages5
ISBN (Electronic)9788993215243
DOIs
StatePublished - 2022
Event22nd International Conference on Control, Automation and Systems, ICCAS 2022 - Busan, Korea, Republic of
Duration: 27 Nov 20221 Dec 2022

Publication series

NameInternational Conference on Control, Automation and Systems
Volume2022-November
ISSN (Print)1598-7833

Conference

Conference22nd International Conference on Control, Automation and Systems, ICCAS 2022
Country/TerritoryKorea, Republic of
CityBusan
Period27/11/221/12/22

Keywords

  • 3D point cloud
  • indoor mobile robot
  • LiDAR
  • region-based segmentation
  • ROS

Fingerprint

Dive into the research topics of 'A Novel Technique For Indoor Object Distance Measurement By Using 3D Point Cloud and LiDAR'. Together they form a unique fingerprint.

Cite this