Robust Pixel‐Level Lane Line Segmentation for Rubber‐Tyred Gantry Cranes via an Enhanced BiSeNet V2
Electronics Letters · 2026-01 · 62 (1)
DOI: 10.1049/ell2.70579 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics Letters, online erschienen am 05.04.2026. Verfasst von Qiang Dong und 2 weiteren Autor:innen. Die Arbeit nennt 13 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Accurate lane line segmentation is critical for auto‐gantry steering of Rubber‐Tyred Gantry (RTG) cranes in automated container terminals. RTG lanes are typically straight but often exhibit degradation due to surface wear, contamination or interference from nearby ground markings, making pixel‐level detection particularly challenging. This letter proposes a lightweight and robust segmentation algorithm based on an enhanced BiSeNet V2. Improvements include depthwise separable convolutions to reduce model complexity, efficient channel attention to enhance feature discriminability under contamination and weak contrast, and an edge‐aware loss function to address the thin‐line nature of RTG lanes. Experiments on a curated set of labelled RTG images demonstrate that the proposed method outperforms existing lightweight segmentation models in accuracy and robustness. The model achieves a favourable balance between precision and computational efficiency, making it suitable for real‐time use in port automation systems. To facilitate future research and reproducibility, the annotated RTG lane dataset used in this work is publicly available at: https://github.com/DONN‐RD/Lane‐line‐detection .
Zitieren
APA
Dong, Q., Shao, H., & Song, Z. (2026). Robust Pixel‐Level Lane Line Segmentation for Rubber‐Tyred Gantry Cranes via an Enhanced BiSeNet V2. Electronics Letters, 62(1). https://doi.org/10.1049/ell2.70579
Vancouver
Dong Q, Shao H, Song Z. Robust Pixel‐Level Lane Line Segmentation for Rubber‐Tyred Gantry Cranes via an Enhanced BiSeNet V2. Electronics Letters. 2026;62(1). doi:10.1049/ell2.70579
BibTeX
@article{Dong2026,
author = {Dong, Qiang and Shao, Haoshu and Song, Zenglu},
title = {Robust Pixel‐Level Lane Line Segmentation for Rubber‐Tyred Gantry Cranes via an Enhanced BiSeNet V2},
journal = {Electronics Letters},
year = {2026},
volume = {62},
number = {1},
doi = {10.1049/ell2.70579}
}
EUVIMED