LiDAR Snowfall Simulation for Robust 3D Object Detection

3D object detection is a central task for applications such as autonomous driving, in which the system needs to localize and classify surrounding traffic agents, even in the presence of adverse weather. In this paper, we address the problem of LiDAR-based 3D object detection under snow-fall. Due to...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Proceedings (IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Online) S. 16343 - 16353
Hauptverfasser: Hahner, Martin, Sakaridis, Christos, Bijelic, Mario, Heide, Felix, Yu, Fisher, Dai, Dengxin, Van Gool, Luc
Format: Tagungsbericht
Sprache:Englisch
Veröffentlicht: IEEE 01.01.2022
Schlagworte:
categorization
Image and video synthesis and generation; Computational photography; Datasets and evaluation; Navigation and autonomous driving; Physics-based vision and shape-from-X; Recognition: detection
Laser radar
Object detection
Point cloud compression
retrieval; Robot vision; Scene analysis and understanding
Solid modeling
Three-dimensional displays
Training
Training data
ISSN:1063-6919
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:3D object detection is a central task for applications such as autonomous driving, in which the system needs to localize and classify surrounding traffic agents, even in the presence of adverse weather. In this paper, we address the problem of LiDAR-based 3D object detection under snow-fall. Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds. Our method samples snow particles in 2D space for each LiDAR line and uses the in-duced geometry to modify the measurement for each LiDAR beam accordingly. Moreover, as snowfall often causes wet-ness on the ground, we also simulate ground wetness on LiDAR point clouds. We use our simulation to generate par-tially synthetic snowy LiDAR data and leverage these data for training 3D object detection models that are robust to snowfall. We conduct an extensive evaluation using several state-of-the-art 3D object detection methods and show that our simulation consistently yields significant performance gains on the real snowy STF dataset compared to clear-weather baselines and competing simulation approaches, while not sacrificing performance in clear weather. Our code is available at github.com/SysCV/LiDAR_snow_sim.
ISSN:1063-6919
DOI:10.1109/CVPR52688.2022.01588