Real-Time Inspection System for Ballast Railway Fasteners Based on Point Cloud Deep Learning

IEEE Access

Jian Li¹  Qingzhou Mao²  Qingwu Hu²  Hao Cui³ 

[1] School of Geoscience and Technology, Zhengzhou University, Zhengzhou, China;School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China;School of Water Science and Engineering, Zhengzhou University, Zhengzhou, China;

关键词: Ballast railway fasteners;    fastener inspection;    deep learning;    neural network;    point cloud semantic segmentation;   

DOI  :  10.1109/ACCESS.2019.2961686

来源: DOAJ

【 摘 要 】

Rail fasteners are the most numerous components in railways and they should be inspected periodically. Manual inspection is currently a common solution, which is laborious and low-efficient. Some automatic inspection approaches are proposed. But for ballast railway fasteners inspection, debris, especially ballast along tracks may cover the fasteners, which is still a tricky problem. In this paper, a real-time inspection system for ballast railway fasteners based on point cloud deep learning is developed. Dense and precise point cloud of fastener is obtained from the structured light sensors in the system. The point cloud of fastener is segmented into different parts to avoid the interference of debris on fasteners. A ballast fastener point cloud semantic segmentation dataset is created based on automatic annotation method. Several deep learning point cloud segmentation models are tested in this dataset and PointNet++ is selected to be deployed in the real-time deep learning module of the system. Field tests on ballast railways show excellent accuracy and efficiency of this system.

【 授权许可】

Unknown