Research papers · 2024
Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case
Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case
Overview
The study simulates a SOTIF-related use case across weather and lighting conditions to generate LiDAR data. Pretrained 3D detectors are compared using precision and recall to examine performance insufficiencies under controlled conditions.
Author-supplied source information
Author-supplied information on arXiv.
Proceedings of the 10th International Conference on Vehicle Technology and Intelligent Transport Systems VEHITS - Volume 1, 415-426, 2024 , Angers, France
Version: arXiv v1 — manuscript revision