Simulation-Based Performance Evaluation of 3D Object Detection Methods with Deep Learning for a LiDAR Point Cloud Dataset in a SOTIF-related Use Case
- Safety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a methodology examining the adaptability and performance evaluation of the 3D object detection methods on a LiDAR point cloud dataset generated by simulating a SOTIF-related Use Case. The major contributions of this paper include defining and modeling a SOTIF-related Use Case with 21 diverse weather conditions and generating a LiDAR point cloud dataset suitable for application of 3D object detection methods. The dataset consists of 547 frames, encompassing clear, cloudy, rainy weather conditions, corresponding to different times of the day, including noon, sunset, and night. Employing MMDetection3D and OpenPCDET toolkits, the performance of State-of-the-Art (SOTA) 3D object detection methods is evaluated and compared by testing the pre-trained Deep Lea rning (DL) models on the generated dataset usingSafety of the Intended Functionality (SOTIF) addresses sensor performance limitations and deep learning-based object detection insufficiencies to ensure the intended functionality of Automated Driving Systems (ADS). This paper presents a methodology examining the adaptability and performance evaluation of the 3D object detection methods on a LiDAR point cloud dataset generated by simulating a SOTIF-related Use Case. The major contributions of this paper include defining and modeling a SOTIF-related Use Case with 21 diverse weather conditions and generating a LiDAR point cloud dataset suitable for application of 3D object detection methods. The dataset consists of 547 frames, encompassing clear, cloudy, rainy weather conditions, corresponding to different times of the day, including noon, sunset, and night. Employing MMDetection3D and OpenPCDET toolkits, the performance of State-of-the-Art (SOTA) 3D object detection methods is evaluated and compared by testing the pre-trained Deep Lea rning (DL) models on the generated dataset using Average Precision (AP) and Recall metrics.…
Author: | Milin PatelORCiD, Rolf Jung |
---|---|
DOI: | https://doi.org/10.5220/0012707300003702 |
Identifier: | 978-989-758-703-0 OPAC HS OPAC extern |
Identifier: | 2184-495X OPAC HS OPAC extern |
Parent Title (English): | Proceedings of the 10th International Conference on Vehicle Technology and Intelligent Transport Systems |
Publisher: | SciTePress |
Place of publication: | Setúbal, Portugal |
Document Type: | conference proceeding (article) |
Conference: | 10th International Conference on Vehicle Technology and Intelligent Transport Systems - VEHITS, 02. - 04. Mai 2024, Angers France |
Language: | English |
Year of first Publication: | 2024 |
Tag: | 3D Object Detection; Deep Learning; LiDAR Point Cloud; Performance Evaluation; SOTIF-related Use Case; Simulation-Based |
Number of pages: | 12 Seiten |
First Page: | 415 |
Last Page: | 426 |
Institutes: | IFM - Institut für Fahrerassistenz und vernetzte Mobilität |
Dewey Decimal Classification: | 6 Technik, Medizin, angewandte Wissenschaften / 60 Technik |
Open Access: | open_access |
Research focus: | FSP2: Mobilität |
Publication Lists: | Jung, Rolf |
Patel, Milin | |
Publication reviewed: | begutachtet |
Licence (German): | ![]() |
Release Date: | 2024/05/14 |