Lane detection for nighttime structured roads based on sensor fusion
Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering · 04.05.2026
DOI: 10.1177/09544070261444089 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering, online erschienen am 04.05.2026. Verfasst von Xuejing Du und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Heilongjiang Province Key R&D Program Guidance Category Project, Heilongjiang Provincial Transportation Investment Group Co, LTD Project.
Abstract (Originalsprache)
To address the issues of misdetection and missed detection in nighttime lane marking detection due to factors such as occlusion, insufficient lighting, glare, and interference from objects similar to lane markings, this paper proposes a nighttime structured road lane marking detection method based on LiDAR and camera fusion. LiDAR is used in the first stage to detect road boundaries and define the lane detection region based on the extracted boundary points. In the second stage, a camera performs lane detection within the LiDAR-defined region using an improved UFLD method. The first-stage method achieves an accuracy of 93.2% on a randomly selected 300 frames from the KITTI dataset. The second-stage method achieves F1 scores of 73.8% on the CULane dataset and accuracies of 95.26% and 77.61% on the TuSimple and self-built datasets, respectively. The real-world deployment of the fusion method shows a 1.05% improvement in accuracy compared to the non-fused algorithm. The experimental results demonstrate that the proposed method has good performance in lane marking detection on structured roads at night.
Förderung
- National Natural Science Foundation of China
- Heilongjiang Province Key R&D Program Guidance Category Project
- Heilongjiang Provincial Transportation Investment Group Co, LTD Project
Zitieren
APA
Du, X., Yu, C., Shen, S., Ding, W., & Li, G. (2026). Lane detection for nighttime structured roads based on sensor fusion. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. https://doi.org/10.1177/09544070261444089
Vancouver
Du X, Yu C, Shen S, Ding W, Li G. Lane detection for nighttime structured roads based on sensor fusion. Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering. 2026. doi:10.1177/09544070261444089
BibTeX
@article{Du2026,
author = {Du, Xuejing and Yu, Chengyin and Shen, Sitong and Ding, Wenhua and Li, Guorui},
title = {Lane detection for nighttime structured roads based on sensor fusion},
journal = {Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering},
year = {2026},
doi = {10.1177/09544070261444089}
}
EUVIMED