For autonomous cars it is crucial to perceive its current environment to ensure safe driving maneuvers. Light detection and ranging sensors (LiDAR) are often used for object detection due to their accurate distance measurements. However, point clouds sensed by LiDAR provide information of the environment which are not important for object detection algorithms (e.g.: vegetation, buildings). Adding semantic segmentation information to the point cloud supports object detection algorithms and improves their performance.
Within this work we transfer well established semantic segmentation methods from the image domain to point clouds and evaluate the performance on solid state LiDAR data. We successfully show the applicability of semantic segmentation methods on this new sensor technology. Furthermore, we compare semantic segmentation approaches which operate on different input representations and discuss the benefit of additional information like intensity measurements on the algorithm’s performance. The evaluations are conducted on solid state LiDAR measurements from German highway scenarios.
Semantic Segmentation of Solid-State LiDAR Measurements for Automotive Applications
Proceedings
2021-05-14
12 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Deutsch
Semantic segmentation of solid state LiDAR measurements for automotive applications
Springer Verlag | 2020
|TransRVNet: LiDAR Semantic Segmentation With Transformer
IEEE | 2023
|SEMANTIC SEGMENTATION ON AUTOMOTIVE RADAR MAPS
British Library Conference Proceedings | 2019
|