%0 Journal Article
%T 基于深度学习的钢轨病害检测算法研究<br>Research on Rail Diseases Detection Algorithm Based on Deep Learning
%A 张国粹
%A 张长伦
%J Artificial Intelligence and Robotics Research
%P 340-350
%@ 2326-3423
%D 2023
%I Hans Publishing
%R 10.12677/AIRR.2023.124037
%X 钢轨病害的存在严重威胁行车安全，因此，对钢轨病害进行有效检测对提升车辆运行的安全性具有至关重要的意义。本文旨在综述基于深度学习的钢轨病害检测算法。首先，对基于深度学习的钢轨病害检测网络进行了全面介绍；其次，根据数据的采集模态，将钢轨病害检测方法划分为两类：基于单一模态数据(轮轨加速度信号、图像、结构光点云)的典型算法以及基于多模态数据融合的算法；最后，对未来钢轨病害检测技术进行了综述和展望。<br />
The presence of rail diseases poses a significant threat to driving safety, underscoring the critical importance of effective rail disease detection to enhance vehicle operational safety. This article endeavors to review algorithms for rail disease detection utilizing deep learning methodologies. Initially, a thorough introduction is provided for the rail disease detection network based on deep learning. Subsequently, rail disease detection methods are categorized into two groups based on the data collection mode: Those reliant on single-modal data (such as wheel-rail acceleration signals, images, and structured light point clouds) and algorithms founded on multi-modal data fusion. Lastly, a comprehensive review and forward-looking insights into future rail disease detection technologies are presented.
%K 钢轨病害，深度学习，多模态融合<br>Rail Disease
%K Deep Learning
%K Multi-Modal Fusion
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=75801