A fast and stable road edge detection method based on LiDAR and camera
Measurement Science and Technology · 31.07.2025 · 36 (7) · 075205
DOI: 10.1088/1361-6501/adeace ↗Kurz gefasst
Fachartikel in der Zeitschrift Measurement Science and Technology, online erschienen am 10.07.2025. Verfasst von Shuang Liu und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 47 Literaturangaben. Gefördert von: Central Innovation Group Program of Hebei province, Major Program of National Natural Science Foundation of China.
Abstract (Originalsprache)
Accurate road edge detection plays a pivotal role in the perception and localization of autonomous vehicles. However, the reliability of road edge detection solely based on LiDAR is often compromised in complex road scenarios and under occlusions caused by obstacles. To address these challenges, this paper presents a fast and robust road edge point detection method that leverages the complementary strengths of LiDAR and camera data. The proposed method begins by applying the RANSAC algorithm to raw point cloud data to extract ground points. Next, an isosceles triangle-based approach is introduced for feature point extraction, demonstrating exceptional performance in identifying points at the intersection of two planes. Subsequently, a LiDAR-camera fusion strategy is utilized to segment feature points into left and right regions. Finally, iterative Bayesian ridge regression is employed to refine the feature points through secondary screening. The effectiveness of the proposed method is validated on diverse road scenarios using the KITTI dataset. Experimental results demonstrate that the proposed approach surpasses existing algorithms in terms of precision, recall, and harmonic mean. Moreover, with an average processing latency of 77.92 ms per frame, the method meets the real-time requirements for road-edge detection tasks.
Förderung
- Central Innovation Group Program of Hebei province
- Major Program of National Natural Science Foundation of China
Zitieren
APA
Liu, S., Zou, R., & Xu, P. (2025). A fast and stable road edge detection method based on LiDAR and camera. Measurement Science and Technology, 36(7), 075205. https://doi.org/10.1088/1361-6501/adeace
Vancouver
Liu S, Zou R, Xu P. A fast and stable road edge detection method based on LiDAR and camera. Measurement Science and Technology. 2025;36(7):075205. doi:10.1088/1361-6501/adeace
BibTeX
@article{Liu2025,
author = {Liu, Shuang and Zou, Rui and Xu, Peng},
title = {A fast and stable road edge detection method based on LiDAR and camera},
journal = {Measurement Science and Technology},
year = {2025},
volume = {36},
number = {7},
pages = {075205},
doi = {10.1088/1361-6501/adeace}
}
EUVIMED