FugSeg: Fast Uncertainty-Aware Ground Segmentation for 3-D Point Cloud
IEEE Transactions on Intelligent Transportation Systems · 2026-08 · 27 (8) · 9288-9301
DOI: 10.1109/tits.2026.3682176 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Intelligent Transportation Systems, 2026-08. Verfasst von Yu Li und 1 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben. Gefördert von: Institute of Engineering Geodesy, University of Stuttgart.
Abstract (Originalsprache)
In LiDAR-based environment perception systems, ground segmentation is a key preprocessing step supporting various applications such as mapping and navigation. Although extensively studied, problems such as reflection noise and isolated ground remain challenging. To address these issues, we propose FugSeg, a fast uncertainty-aware ground segmentation method. A polar grid map is adopted as the point cloud representation to ensure generalizability across LiDAR types. Building on that, we develop a within- and cross-segment ground labeling strategy that identifies not only directly visible ground cells but also those that are isolated or occluded. During this process, an adaptive slope is introduced, which incorporates measurement uncertainties to enhance its reliability under complex terrain. Finally, to achieve point-level ground segmentation, a fine-grained ground elevation estimation method is introduced. Throughout the complete workflow, reflection noise is explicitly handled via the proposed noisy ground cells. We conduct comprehensive evaluations on four public datasets covering both structured and unstructured environments. Results show that FugSeg outperforms state-of-the-art non-learning methods, achieving the highest $\mathbf {F_{1}}$ , accuracy, and mIoU across all datasets, while maintaining the fastest runtime (135 Hz and 487 Hz for 64- and 32-layer LiDARs) using a single CPU thread, making it suitable for resource-limited systems. The code will be available at https://github.com/Leo-YuLi/FugSeg
Förderung
- Institute of Engineering Geodesy, University of Stuttgart
Zitieren
APA
Li, Y., & Schwieger, V. (2026). FugSeg: Fast Uncertainty-Aware Ground Segmentation for 3-D Point Cloud. IEEE Transactions on Intelligent Transportation Systems, 27(8), 9288-9301. https://doi.org/10.1109/tits.2026.3682176
Vancouver
Li Y, Schwieger V. FugSeg: Fast Uncertainty-Aware Ground Segmentation for 3-D Point Cloud. IEEE Transactions on Intelligent Transportation Systems. 2026;27(8):9288-9301. doi:10.1109/tits.2026.3682176
BibTeX
@article{Li2026,
author = {Li, Yu and Schwieger, Volker},
title = {FugSeg: Fast Uncertainty-Aware Ground Segmentation for 3-D Point Cloud},
journal = {IEEE Transactions on Intelligent Transportation Systems},
year = {2026},
volume = {27},
number = {8},
pages = {9288--9301},
doi = {10.1109/tits.2026.3682176}
}
EUVIMED