LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sanchez, Raul David Dominguez, Ortiz, Xavier Diaz, Zhou, Xingcheng, Ronecker, Max Peter, Karner, Michael, Watzenig, Daniel, Knoll, Alois
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866908337577132032
author Sanchez, Raul David Dominguez
Ortiz, Xavier Diaz
Zhou, Xingcheng
Ronecker, Max Peter
Karner, Michael
Watzenig, Daniel
Knoll, Alois
author_facet Sanchez, Raul David Dominguez
Ortiz, Xavier Diaz
Zhou, Xingcheng
Ronecker, Max Peter
Karner, Michael
Watzenig, Daniel
Knoll, Alois
contents Railway systems, particularly in Germany, require high levels of automation to address legacy infrastructure challenges and increase train traffic safely. A key component of automation is robust long-range perception, essential for early hazard detection, such as obstacles at level crossings or pedestrians on tracks. Unlike automotive systems with braking distances of ~70 meters, trains require perception ranges exceeding 1 km. This paper presents an deep-learning-based approach for long-range 3D object detection tailored for autonomous trains. The method relies solely on monocular images, inspired by the Faraway-Frustum approach, and incorporates LiDAR data during training to improve depth estimation. The proposed pipeline consists of four key modules: (1) a modified YOLOv9 for 2.5D object detection, (2) a depth estimation network, and (3-4) dedicated short- and long-range 3D detection heads. Evaluations on the OSDaR23 dataset demonstrate the effectiveness of the approach in detecting objects up to 250 meters. Results highlight its potential for railway automation and outline areas for future improvement.
format Preprint
id arxiv_https___arxiv_org_abs_2504_18203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring
Sanchez, Raul David Dominguez
Ortiz, Xavier Diaz
Zhou, Xingcheng
Ronecker, Max Peter
Karner, Michael
Watzenig, Daniel
Knoll, Alois
Computer Vision and Pattern Recognition
Machine Learning
Railway systems, particularly in Germany, require high levels of automation to address legacy infrastructure challenges and increase train traffic safely. A key component of automation is robust long-range perception, essential for early hazard detection, such as obstacles at level crossings or pedestrians on tracks. Unlike automotive systems with braking distances of ~70 meters, trains require perception ranges exceeding 1 km. This paper presents an deep-learning-based approach for long-range 3D object detection tailored for autonomous trains. The method relies solely on monocular images, inspired by the Faraway-Frustum approach, and incorporates LiDAR data during training to improve depth estimation. The proposed pipeline consists of four key modules: (1) a modified YOLOv9 for 2.5D object detection, (2) a depth estimation network, and (3-4) dedicated short- and long-range 3D detection heads. Evaluations on the OSDaR23 dataset demonstrate the effectiveness of the approach in detecting objects up to 250 meters. Results highlight its potential for railway automation and outline areas for future improvement.
title LiDAR-Guided Monocular 3D Object Detection for Long-Range Railway Monitoring
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2504.18203