Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: van Kempen, Raphael, Rehbronn, Tim, Jose, Abin, Stegmaier, Johannes, Lampe, Bastian, Woopen, Timo, Eckstein, Lutz
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866914643393380352
author van Kempen, Raphael
Rehbronn, Tim
Jose, Abin
Stegmaier, Johannes
Lampe, Bastian
Woopen, Timo
Eckstein, Lutz
author_facet van Kempen, Raphael
Rehbronn, Tim
Jose, Abin
Stegmaier, Johannes
Lampe, Bastian
Woopen, Timo
Eckstein, Lutz
contents Automated vehicles require an accurate perception of their surroundings for safe and efficient driving. Lidar-based object detection is a widely used method for environment perception, but its performance is significantly affected by adverse weather conditions such as rain and fog. In this work, we investigate various strategies for enhancing the robustness of lidar-based object detection by processing sequential data samples generated by lidar sensors. Our approaches leverage temporal information to improve a lidar object detection model, without the need for additional filtering or pre-processing steps. We compare $10$ different neural network architectures that process point cloud sequences including a novel augmentation strategy introducing a temporal offset between frames of a sequence during training and evaluate the effectiveness of all strategies on lidar point clouds under adverse weather conditions through experiments. Our research provides a comprehensive study of effective methods for mitigating the effects of adverse weather on the reliability of lidar-based object detection using sequential data that are evaluated using public datasets such as nuScenes, Dense, and the Canadian Adverse Driving Conditions Dataset. Our findings demonstrate that our novel method, involving temporal offset augmentation through randomized frame skipping in sequences, enhances object detection accuracy compared to both the baseline model (Pillar-based Object Detection) and no augmentation.
format Preprint
id arxiv_https___arxiv_org_abs_2401_09049
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time
van Kempen, Raphael
Rehbronn, Tim
Jose, Abin
Stegmaier, Johannes
Lampe, Bastian
Woopen, Timo
Eckstein, Lutz
Computer Vision and Pattern Recognition
Robotics
Automated vehicles require an accurate perception of their surroundings for safe and efficient driving. Lidar-based object detection is a widely used method for environment perception, but its performance is significantly affected by adverse weather conditions such as rain and fog. In this work, we investigate various strategies for enhancing the robustness of lidar-based object detection by processing sequential data samples generated by lidar sensors. Our approaches leverage temporal information to improve a lidar object detection model, without the need for additional filtering or pre-processing steps. We compare $10$ different neural network architectures that process point cloud sequences including a novel augmentation strategy introducing a temporal offset between frames of a sequence during training and evaluate the effectiveness of all strategies on lidar point clouds under adverse weather conditions through experiments. Our research provides a comprehensive study of effective methods for mitigating the effects of adverse weather on the reliability of lidar-based object detection using sequential data that are evaluated using public datasets such as nuScenes, Dense, and the Canadian Adverse Driving Conditions Dataset. Our findings demonstrate that our novel method, involving temporal offset augmentation through randomized frame skipping in sequences, enhances object detection accuracy compared to both the baseline model (Pillar-based Object Detection) and no augmentation.
title Enhancing Lidar-based Object Detection in Adverse Weather using Offset Sequences in Time
topic Computer Vision and Pattern Recognition
Robotics
url https://arxiv.org/abs/2401.09049