Fast-CenLaneNet: A Lightweight Instance Segmentation-Based Network for Real-Time Lane Detection
Journal of Imaging · 13.07.2026 · 12 (7) · 320
DOI: 10.3390/jimaging12070320 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Imaging, online erschienen am 13.07.2026. Verfasst von Qidong Han und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Automobile, Chang'an University, Xi'an 710064, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Xi'an Bureau of Science and Technology, National Natural Science Foundation of China, Xi’an Bureau of Science and Technology.
Abstract (Originalsprache)
Lane detection is a critical component of autonomous driving systems, requiring both high accuracy and real-time performance under complex driving scenarios. Unlike current methods that rely on predefined lane counts, instance segmentation methods can handle an arbitrary number of lanes, making them more adaptable in real-world applications. However, this flexibility typically relies on dense pixel-level predictions, which necessitate large-scale networks and result in prohibitively high computational costs, hindering deployment on embedded platforms. To address these challenges, we present Fast-CenLaneNet, a lightweight architecture that improves inference efficiency while maintaining detection accuracy. Specifically, we design a lightweight backbone to reduce model parameters and computational cost, propose a learnable spatial similarity attention module to capture spatial dependencies within lane regions and enhance feature discriminability, and construct multi-branch output heads with Ghost convolutions to refine lane-related features with low computational overhead. Experiments on the TuSimple and CULane benchmarks demonstrate that Fast-CenLaneNet achieves a favorable accuracy–efficiency trade-off. On TuSimple, Fast-CenLaneNet obtains 96.40 ± 0.06% accuracy and 162.7 ± 6.8 FPS with 4.7 M parameters and 9.9 GFLOPs. Compared with CenLaneNet, it reduces the number of parameters by 89.1% and improves forward inference speed by 107.5%, with an accuracy decrease of only 0.08 percentage points.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- School of Automobile, Chang'an University, Xi'an 710064, China.
- School of Construction Machinery, Chang'an University, Xi'an 710064, China.
- School of Modern Post, Xi'an University of Posts and Telecommunications, Xi'an 710061, China.
Förderung
- Xi'an Bureau of Science and Technology
- National Natural Science Foundation of China
- Xi’an Bureau of Science and Technology
Zitieren
APA
Han, Q., Feng, S., Gao, Y., Li, M., Meng, T., Li, K., & Yang, Y. (2026). Fast-CenLaneNet: A Lightweight Instance Segmentation-Based Network for Real-Time Lane Detection. Journal of Imaging, 12(7), 320. https://doi.org/10.3390/jimaging12070320
Vancouver
Han Q, Feng S, Gao Y, Li M, Meng T, Li K, et al. Fast-CenLaneNet: A Lightweight Instance Segmentation-Based Network for Real-Time Lane Detection. Journal of Imaging. 2026;12(7):320. doi:10.3390/jimaging12070320
BibTeX
@article{Han2026,
author = {Han, Qidong and Feng, Shuo and Gao, Yang and Li, Mengyao and Meng, Teng and Li, Ke and Yang, Yuhao},
title = {Fast-CenLaneNet: A Lightweight Instance Segmentation-Based Network for Real-Time Lane Detection},
journal = {Journal of Imaging},
year = {2026},
volume = {12},
number = {7},
pages = {320},
doi = {10.3390/jimaging12070320}
}
EUVIMED