EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Rail-BEV: A LiDAR-Centric and Sensor-Aware BEV Perception Framework for Long-Range Railway Obstacle Detection

Jinghan Huang, Wentao Hu, Zifeng He, Chixiang Ma, Wenbo Song, Xinci Liu, Mingxin Yang

Sensors · 07.06.2026 · 26 (12) · 3637

DOI: 10.3390/s26123637 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 07.06.2026. Verfasst von Jinghan Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: School of Civil Engineering and Architecture, East China Jiaotong University, Nanchang 330013, China. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Reliable long-range onboard perception is a prerequisite for future railway safety systems, where potential obstacles must be recognized under long braking distances, sparse far-field returns, and strongly constrained rail-corridor geometry. This paper presents Rail-BEV as an initial reproducible baseline study for LiDAR-centric, sensor-aware bird’s-eye-view (BEV) railway obstacle perception. LiDAR is used as the primary geometric sensing modality, while a front-center RGB camera provides lightweight auxiliary visual evidence through calibrated LiDAR-to-image projection. The aligned geometric and visual cues are organized within a unified railway-oriented BEV backend that integrates geometry-aware fusion, rail-geometry prediction, and lightweight inference-time structural refinement. Evaluation was conducted on a scene-isolated railway benchmark with range-stratified center-distance matching, and all model variants were assessed on independent test sequences rather than on validation-selected checkpoints. Compared with CenterPoint and BEVFusion baselines evaluated under the same settings, Rail-BEV achieved the highest overall mAP of 0.6669, with particularly improved long-range pedestrian perception. The controlled ablation further shows that front-view RGB evidence improves the LiDAR-only baseline from 0.5612 to 0.5750 mAP, while ROI-based rail-corridor refinement further increases mAP to 0.5916 and Rail-BEV mIoU to 0.1193. These results indicate that LiDAR-centered sensing, lightweight visual assistance, and coarse rail-aware structural reasoning can be jointly organized to support reproducible long-range railway obstacle perception. This study also clarifies the remaining limitations in rail-geometry quality, calibration robustness, sensor degradation, and strict railway-oriented localization.

Schlagwörter

Stichwörter der Autor:innen

BEV perceptionLiDAR-centric perceptionRGB–LiDAR fusionlong-range perceptionrail geometryrail-aware refinementrailway obstacle detection

Autor:innen und Institutionen

  • School of Civil Engineering and Architecture, East China Jiaotong University, Nanchang 330013, China.
  • State Key Laboratory of Safety and Resilience of Civil Engineering in Mountain Area, East China Jiaotong University, Nanchang 330013, China.
  • School of Information and Software Engineering, East China Jiaotong University, Nanchang 330013, China.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Huang, J., Hu, W., He, Z., Ma, C., Song, W., Liu, X., & Yang, M. (2026). Rail-BEV: A LiDAR-Centric and Sensor-Aware BEV Perception Framework for Long-Range Railway Obstacle Detection. Sensors, 26(12), 3637. https://doi.org/10.3390/s26123637

Vancouver

Huang J, Hu W, He Z, Ma C, Song W, Liu X, et al. Rail-BEV: A LiDAR-Centric and Sensor-Aware BEV Perception Framework for Long-Range Railway Obstacle Detection. Sensors. 2026;26(12):3637. doi:10.3390/s26123637

BibTeX
@article{Huang2026,
  author = {Huang, Jinghan and Hu, Wentao and He, Zifeng and Ma, Chixiang and Song, Wenbo and Liu, Xinci and Yang, Mingxin},
  title = {Rail-BEV: A LiDAR-Centric and Sensor-Aware BEV Perception Framework for Long-Range Railway Obstacle Detection},
  journal = {Sensors},
  year = {2026},
  volume = {26},
  number = {12},
  pages = {3637},
  doi = {10.3390/s26123637}
}
Kostenlos starten →