RailBEV: A Vision-Based Bird’s-Eye-View Representation Network for 3-D Railway Object Detection
- 19 May 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74 (00189456) , 1-12
Abstract
Three-dimensional railway object detection is vital to the environmental perception of intelligent railway transportation systems. However, owing to the complexity of railway environments, critical issues such as the detection of multiscale and distant objects remain to be overcome. This study proposes a vision-based architecture called RailBEV, which introduces bird’s-eye-view (BEV) representation within 3-D railway object detection. RailBEV is mainly divided into two parallel parts: the depth supervision view transformation (DSVT) and long-range supervision (LRS) modules. Specifically, the DSVT module designed a novel depth supervision method to transform the front view (FV) images into the BEV plane. The LRS module leverages an additional 3-D detection head to guide a 2-D image backbone to learn extra 3-D object information and enhance the capability of long-range object detection. Experimental results demonstrate that the proposed RailBEV exhibits a mean average precision (mAP) of 38.6%, which is 4.4% higher than the baseline 3-D object detection network BEVDepth. Moreover, the results show that RailBEV effectively supports long-range detection and identifies multiscale and short-range objects. All these indicate that RailBEV has the potential to be readily applicable in 3-D railway object detection.Keywords
Funding Information
- Natural Science Foundation of Beijing Municipality (L231015)
- National Key Research and Development Program of China (2023YFB3211102)
This publication has 42 references indexed in Scilit:
- FSD-BEV: Foreground Self-distillation for Multi-view 3D Object Detection2024
- BEVFormer: Learning Bird’s-Eye-View Representation from Multi-camera Images via Spatiotemporal Transformers2022
- SAT-GCN: Self-attention graph convolutional network-based 3D object detection for autonomous drivingKnowledge-Based Systems, 2022
- PETR: Position Embedding Transformation for Multi-view 3D Object Detection2022
- Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs by Implicitly Unprojecting to 3D2020
- Monocular Differentiable Rendering for Self-supervised 3D Object Detection2020
- Train-movement situation recognition for safety justification using moving-horizon TBM-based multisensor data fusionKnowledge-Based Systems, 2019
- Stacked Hourglass Networks for Human Pose Estimation2016
- Deep Residual Learning for Image Recognition2016
- Sensory system for obstacle detection on high-speed linesTransportation Research Part C: Emerging Technologies, 2009