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

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 ba...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Jinghan Huang, Wentao Hu, Zifeng He, Chixiang Ma, Wenbo Song, Xinci Liu, Mingxin Yang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	MDPI AG 2026-06-01
coleção:	Sensors
Assuntos:	railway obstacle detection LiDAR-centric perception RGB–LiDAR fusion BEV perception rail geometry long-range perception
Acesso em linha:	https://www.mdpi.com/1424-8220/26/12/3637
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!