3-D Object Detection for Railway: A Comprehensive Survey

作者：Lirong Lian, Yong Qin, Zhiwei Cao, Yang Gao, Zhenhao Liu, Qiao Li, Xiaoqing Cheng · 发表于：IEEE Transactions on Instrumentation and Measurement · 年份：2026 · DOI：10.1109/tim.2026.3684649 · 被引用次数：1 · 研究领域：Advanced Neural Network Applications、Image and Object Detection Techniques、Vehicle License Plate Recognition

Reliable 3D perception is indispensable for the next generation of autonomous railways (GoA4). This paper presents a comprehensive survey of 3D object detection tailored for railway environments. Unlike conventional automotive-focused reviews, our contributions are threefold. First, we establish a robust metrological foundation by deriving quantitative sensor requirements, such as angular resolution and focal length, necessary to detect critical obstacles at ultra-long ranges (>500 m). Second, we propose a systematic hierarchical taxonomy that organizes the landscape of detection methods, encompassing LiDAR, cameras, and other vital sensors like millimeter-wave radar, distributed fiber optic sensing (DFOS), and infrared thermal imaging. We critically evaluate these modalities and their multi-modal fusion strategies against specific railway demands regarding data sparsity and operational reliability. Third, we offer insightful perspectives on key open challenges, including real-time edge deployment, uncertainty-based fail-safe mechanisms, and air-ground-vehicle cooperative perception. This survey bridges deep learning algorithms with railway instrumentation standards, providing a crucial reference for developing safer, more robust intelligent railway perception systems.