mlsanityData to 14 Oct 2026

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

arXiv 2504.18203 ↗First posted 25 Apr 2025cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 51 references that are in the map. First posted on arXiv 25 Apr 2025.

Builds on

26 of 51 references.

References · 26

  1. 2016Densely Connected Convolutional Networkscited by 6,720
  2. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  3. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
  5. 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,495
  6. 2019PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detectioncited by 891
  7. 2016Multi-View 3D Object Detection Network for Autonomous Drivingcited by 724
  8. 2017Frustum PointNets for 3D Object Detection from RGB-D Datacited by 640
  9. 2022BEVDepth: Acquisition of Reliable Depth for Multi-view 3D Object Detectioncited by 572
  10. 2024YOLOv9: Learning What You Want to Learn Using Programmable Gradient Informationcited by 425
  11. 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 327
  12. 2019Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Drivingcited by 188
14 more
  1. 2018High Quality Monocular Depth Estimation via Transfer Learningcited by 133
  2. 2022MonoDETR: Depth-guided Transformer for Monocular 3D Object Detectioncited by 86
  3. 2023Virtual Sparse Convolution for Multimodal 3D Object Detectioncited by 81
  4. 2023LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusioncited by 80
  5. 2022Waymo Open Dataset: Panoramic Video Panoptic Segmentationcited by 58
  6. 2022Voxel Field Fusion for 3D Object Detectioncited by 50
  7. 2022Homogeneous Multi-modal Feature Fusion and Interaction for 3D Object Detectioncited by 26
  8. 2023OSDaR23: Open Sensor Data for Rail 2023cited by 17
  9. 2020Faraway-Frustum: Dealing with Lidar Sparsity for 3D Object Detection using Fusioncited by 15
  10. 2020FRSign: A Large-Scale Traffic Light Dataset for Autonomous Trainscited by 10
  11. 2021Absolute distance prediction based on deep learning object detection and monocular depth estimation modelscited by 8
  12. 2024YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systemscited by 7
  13. 2024Towards Unified 3D Object Detection via Algorithm and Data Unificationcited by 6
  14. 2024Improving Distant 3D Object Detection Using 2D Box Supervisioncited by 6

Built on by

Not cited yet.