Ground Segmentation Algorithm Based on 3D Lidar Point Cloud

DOI

10.2991/meees-18.2018.4How to use a DOI?

Keywords

3D lidar, ground segmentation, line segment feature, real-time.

Abstract

Aiming at the problem of accurately and efficiently segmenting the ground from the 3D Lidar point cloud, a ground segmentation algorithm based on the features of the scanning line segment is proposed. The algorithm performs denoising and pose correction on the 3D point cloud and divides the scan line according to the Euclidean distance and vertical height difference between adjacent points. Then analyze the characteristics of the adjacent line segments, such as pitch, slope, and height difference, and mark them as the ground segments and obstacle segments according to the classification rules. Finally, the comparison experiments show that this algorithm can accurately segment the ground in real time.

Copyright

© 2018, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ziyang Cheng
AU  - Guoquan Ren
AU  - Yin Zhang
PY  - 2018/05
DA  - 2018/05
TI  - Ground Segmentation Algorithm Based on 3D Lidar Point Cloud
BT  - Proceedings of the 2018 International Conference on Mechanical, Electrical, Electronic Engineering & Science (MEEES 2018)
PB  - Atlantis Press
SP  - 16
EP  - 21
SN  - 2352-5401
UR  - https://doi.org/10.2991/meees-18.2018.4
DO  - 10.2991/meees-18.2018.4
ID  - Cheng2018/05
ER  -