A Review of Ground Segmentation Methods for Vehicle-Mounted LiDAR Point Clouds

With the rapid development of the autonomous driving industry, the robustness requirements for autonomous vehicle perception systems are increasing, and in-vehicle LiDAR has gradually become an essential sensing device. This article first introduces the types of vehicle-mounted laser mines and discu...

Full description

Saved in:
Bibliographic Details
Published in2023 IEEE 4th International Conference on Pattern Recognition and Machine Learning (PRML) pp. 236 - 242
Main Authors Mijit, Tayir, Ahat, Arzigul, Hamdulla, Askar
Format Conference Proceeding
LanguageEnglish
Published IEEE 04.08.2023
Subjects
autonomous vehicles
Deep learning
ground segmentation
Laser radar
LiDAR
perception systems
Point cloud compression
Real-time systems
Roads
Robustness
Online AccessGet full text

Cover

More Information
Summary:With the rapid development of the autonomous driving industry, the robustness requirements for autonomous vehicle perception systems are increasing, and in-vehicle LiDAR has gradually become an essential sensing device. This article first introduces the types of vehicle-mounted laser mines and discusses their advantages and disadvantages; Then, a comprehensive summary and classification of existing ground segmentation methods based on LiDAR point clouds were conducted. Finally, the advantages and disadvantages of these methods in various road environments were compared and analyzed comprehensively, and the future development direction of such research was prospected.
DOI:10.1109/PRML59573.2023.10348257