Fake It, Mix It, Segment It: Bridging the Domain Gap Between Lidar Sensors

Frederik Hasecke, Frederik Hasecke, Pascal Colling, Anton Kummert

2023

Abstract

Lidar segmentation provides detailed information about the environment surrounding robots or autonomous vehicles. Current state-of-the-art neural networks for lidar segmentation are tailored to specific datasets. Changing the lidar sensor without retraining on a large annotated dataset from the new sensor results in a significant decrease in performance due to a ”domain shift.” In this paper, we propose a new method for adapting lidar data to different domains by recreating annotated panoptic lidar datasets in the structure of a different lidar sensor. We minimize the domain gap by generating panoptic data from one domain in another and combining it with partially labeled data from the target domain. Our method improves the SemanticKITTI (Behley et al., 2019) to nuScenes (Caesar et al., 2020) domain adaptation performance by up to +51.5 mIoU points, and the SemanticKITTI to nuScenes domain adaptation by up to +48.3 mIoU. We compare two stateof-the-art methods for domain adaptation of lidar semantic segmentation to ours and demonstrate a significant improvement of up to +21.2 mIoU over the previous best method. Furthermore we successfully train well performing semantic segmentation networks for two entirely unlabeled datasets of the state-of-the-art lidar sensors Velodyne Alpha Prime and InnovizTwo

Paper Citation

in Harvard Style

Hasecke F., Colling P. and Kummert A. (2023). Fake It, Mix It, Segment It: Bridging the Domain Gap Between Lidar Sensors. In Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-626-2, pages 743-750. DOI: 10.5220/0011618500003411

in Bibtex Style

@conference{icpram23,
author={Frederik Hasecke and Pascal Colling and Anton Kummert},
title={Fake It, Mix It, Segment It: Bridging the Domain Gap Between Lidar Sensors},
booktitle={Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2023},
pages={743-750},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011618500003411},
isbn={978-989-758-626-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 12th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Fake It, Mix It, Segment It: Bridging the Domain Gap Between Lidar Sensors
SN - 978-989-758-626-2
AU - Hasecke F.
AU - Colling P.
AU - Kummert A.
PY - 2023
SP - 743
EP - 750
DO - 10.5220/0011618500003411