Mechanical Engineering Science

A System of Image Recognition-Based Railway Foreign Object Intrusion Monitoring Design

WANGBeiyuan (Shanghai Bearing Technology Research Institute Co., Ltd.), WANGLingqi (Shanghai Bearing Technology Research Institute Co., Ltd.), GUChuanya (Shanghai Bearing Technology Research Institute Co., Ltd.)


The monitoring system designed in this paper is on account of YOLOv5 (You Only Look Once) to monitor foreign objects on railway tracks and can broadcast the monitoring information to the locomotive in real time. First, the general structure of the system is determined through demand analysis and feasibility analysis, the foreign object intrusion recognition algorithm is designed, and the data set required for foreign object intrusion recognition is made. Secondly, according to the functional demands, the system selects a suitable neural web, and the programming is reasonable. At last, the system is simulated to validate its functionality (identification and classification of track intrusion and determination of a safe operating zone).


Railway; Deep learning; YOLOv5; Image intelligent recognition; Obstacle detection

Full Text:



Ping H, Ming C, Kexin C, et al.. A combined real-time intelligent fire detection and forecasting approach through cameras based on computer vision method[J]. Process Safety and Environmental Protection,2022,164.

GE Jing. Analysis of the development trend of computer image processing technology [J]. Information Technology Computer Products and circulation.2019(5):45-47.

WANG Quandong, Yang Yue, Luo Yiping, et al.. Review on detection methods of foreign bodies in railway encroachment [J]. Journal of Railway Science and Engineering,2019,16(12):3152-3159.

Zheng Yuanpan, Li Guangyang, Li Ye. Application of Deep learning in image recognition [J]. Computer Engineering and Applications, 2019,55(12):20-36.

Chen Chao, Qi Feng. Review on the development of Convolutional neural networks and their applications in computer vision [J]. Computer Science, 2019,46(3):63-73.

Chen Rongbao, Zhao Dan, Wang Qianlong. A speed measurement method for vehicles moving ahead based on Image processing [J]. Sensors and Microsystems,2018,37(04):17-19+23.

Xiang Jun, Zhang Jie, Pan Ru Ru et al.. Contour Extraction of Printed Fabric Pattern with Smooth Texture [J]. Journal of Textile Science,2017,38(11): 162-167.

Girshick R. Fast R-CNN[C]//Proceedings of the IEEE international conference on computer vision. 2015: 1440-1448.

Joseph Redmonl. You Only Look Once: Unified,Real-Time Object Detection.[J]. CoRR,2015,abs/1506.02640.



  • There are currently no refbacks.

Copyright (c) 2024 Beiyuan WANG, Lingqi WANG, Chuanya GU

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.