13th Asia Pacific Transportation Development Conference
Application of Train Intelligent Detection System in Large-Volume Operated Lines
Publication: Resilience and Sustainable Transportation Systems
ABSTRACT
As one of the most important public transportation, urban rail transit bears great operational pressure and relies completely on signaling system to maintain its safety and efficiency. In order to improve train operation efficiency and safety, train active obstacle perception is a good solution. In this paper, we introduce the train intelligent detection system (TIDS) and its application in practical line. TIDS consists of data pre-processing layer, perception layer, and decision-making layer. The data pre-processing layer mainly includes data acquisition and spatio-temporal synchronization. The perception layer applied convolutional neural network to achieve rail area detection and train detection simultaneously in each camera image, and further combine lidar points to measure the train distance. And the decision-making layer judge the relationship between detected trains and the rail area, so as to determine whether the detected trains affect the normal running of the train. At this stage, TIDS system has been comprehensively tested on Beijing Yanfang Line, Shanghai Line 6, Chengdu Line 3, Hong Kong Tsuen Wan, etc. It has been tested and accumulated more than 2 TB data. In addition, we analyze the running accuracy of TIDS system in detail, the results showed that the leak detected rate (LDR) is 0.007 and the mistakenly detected rate (MDR) is 0.000478. Particularly, the system is being practical applied in Hong Kong Tsuen Wan line.
Get full access to this article
View all available purchase options and get full access to this chapter.
ACKNOWLEDGMENTS
This work is partially supported by the Beijing Municipal Science and Technology Project under Grant # Z181100008918003. The MTR Corporation Ltd. in Hong Kong has provided the testing field in co-researching the proposed forward train detection method and technology. The authors would also like to thank the insightful and constructive comments from anonymous reviewers.
REFERENCES
Liu, Y., Tang, T., and Yue, L. (2018) “An Intelligent train regulation algorithm for metro using deep reinforcement learning.” 2018 21st International Conference on Intelligent Transportation Systems (ITSC). IEEE.
Li, S., Yang, L., and Gao, Z. (2018). “Optimal switched control design for automatic train regulation of metro lines with time-varying passengers arrival flow.” Transportation Research Part C: Emerging Technologies, 86, 425-440.
Cheng, R., Song, Y., and Chen, D. (2017), “Intelligent localization of a high-speed train using LSSVM and the online sparse optimization approach”. IEEE Transactions on Intelligent Transportation Systems, 18(8), 2071-2084.
Wang, Z., Wu, X., and Yu, G. (2018), “Efficient rail area detection using convolutional neural network”. IEEE Access, 6, 77656-77664.
Yang, Z., Cheung, V., and Gao, C. (2019), “Train Intelligent Detection System Based on Convolutional Neural Network”. International Conference on Applied Human Factors and Ergonomics. Springer, Cham, 157-165.
Grisham, W. T., & Roberts, M. D. (2004). “Railroad collision avoidance system and method for preventing train accidents.” U.S. Patent No. 6,759,948. Washington, DC: U.S. Patent and Trademark Office.
Mukojima, H., Deguchi, D., and Kawanishi, Y. (2016), “Moving camera background-subtraction for obstacle detection on railway tracks”. 2016 IEEE International Conference on Image Processing(ICIP). IEEE, 3967-3971.
Yu, M., Yang, P., and Wei, S. (2018), “Railway obstacle detection algorithm using neural network”. AIP Conference Proceedings. AIP Publishing, (1), 040017.
He, K., Zhang, X., and Ren, S. (2016), “Deep residual learning for image recognition”. Proceedings of the IEEE conference on computer vision and pattern recognition. 770-778.
Information & Authors
Information
Published In
Resilience and Sustainable Transportation Systems
Pages: 377 - 384
Editors: Fengxiang Qiao, Ph.D., Texas Southern University, Yong Bai, Ph.D., Marquette University, Pei-Sung Lin, Ph.D., University of South Florida, Steven I Jy Chien, Ph.D., New Jersey Institute of Technology, Yongping Zhang, Ph.D., California State Polytechnic University, and Lin Zhu, Ph.D., Shanghai University of Engineering Science
ISBN (Online): 978-0-7844-8290-2
Copyright
© 2020 American Society of Civil Engineers.
History
Published online: Jun 29, 2020
Published in print: Jun 29, 2020
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.