AI/ML - Vision-Based Smart Track Intrusion Alert Solution for Unsecured/Unprotected Track Zones
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V5I4P106Keywords:
Track Intrusion, Machine learning, Computer vision, Deep learning, Object detection, IoT, Edge computingAbstract
This paper focuses on the railway track safety for trains on unsecured and unprotected tracks for trespassers and obstacles which are a factor of concern to the train and individuals. The old traditional tracking systems are done by human methods where people physically move around the tracks to check for any intruder, and this is coupled with simple sensors that give a basic alarm when intruders are detected. This paper presents a vision-based smart track intrusion alert system which would use various components such as deep learning, IoT-enabled surveillance cameras and computer vision. The adopted model involves the use of CNNs for object detection, real-time alerting and edge computing for real-time output. This is especially useful in detecting intrusions such as human intrusions, animals on the tracks, or even an object on the tracks, making it difficult to produce false alarms and delays in response. It is also demonstrated that through the training of the datasets that reflect real-life experiences, the model provides high precision and recall ratios for the detection of intrusions. This system contributes to the increase of the railway security level, the decrease of possible accidents, and the optimization of train operations. These can explain why the present system is feasible to perform real-time surveillance and also show the possibility of its massive application to railway systems
References
[1] Cao, Z., Qin, Y., Xie, Z., Liu, Q., Zhang, E., Wu, Z., & Yu, Z. (2022). An effective railway intrusion detection method using dynamic intrusion region and lightweight neural network. Measurement, 191, 110564.
[2] Pan, H., Li, Y., Wang, H., & Tian, X. (2022). Railway obstacle intrusion detection based on convolution neural network multitask learning. Electronics, 11(17), 2697.
[3] GBADAMOSI, A. Q. O. (2023). An Internet of Things enabled system for real-time monitoring and predictive maintenance of railway infrastructure (Doctoral dissertation, Dissertation, University of the West of England, Bristol).
[4] Gbadamosi, A. Q., Oyedele, L. O., Delgado, J. M. D., Kusimo, H., Akanbi, L., Olawale, O., & Muhammed-Yakubu, N. (2021). IoT for predictive assets monitoring and maintenance: An implementation strategy for the UK rail industry. Automation in Construction, 122, 103486.
[5] Binder, M., Mezhuyev, V., & Tschandl, M. (2023). Predictive maintenance for railway domain: A systematic literature review. IEEE Engineering Management Review, 51(2), 120-140.
[6] Salierno, G., Morvillo, S., Leonardi, L., & Cabri, G. (2020, May). An architecture for predictive maintenance of railway points based on big data analytics. In International Conference on Advanced Information Systems Engineering (pp. 29-40). Cham: Springer International Publishing.
[7] Durazo-Cardenas, I., Starr, A., Turner, C. J., Tiwari, A., Kirkwood, L., Bevilacqua, M., ... & Emmanouilidis, C. (2018). An autonomous system for maintenance scheduling data-rich complex infrastructure: Fusing the railways’ condition, planning and cost. Transportation Research Part C: Emerging Technologies, 89, 234-253.
[8] Crawford, E. G., & Kift, R. L. (2018). Keeping track of railway safety and the mechanisms for risk. Safety Science, 110, 195-205.
[9] Cheng, W., Wang, S., & Cheng, X. (2014). Virtual track: Applications and challenges of the RFID system on roads. IEEE Network, 28(1), 42-47.
[10] Costa, B. J. A., & Figueiras, J. A. (2012). Evaluation of a strain monitoring system for existing steel railway bridges. Journal of Constructional Steel Research, 72, 179-191.
[11] Ngamkhanong, C., Kaewunruen, S., & Costa, B. J. A. (2018). State-of-the-art review of railway track resilience monitoring. Infrastructures, 3(1), 3.
[12] Li, C., Luo, S., Cole, C., & Spiryagin, M. (2017). An overview: modern techniques for railway vehicle on-board health monitoring systems. Vehicle system dynamics, 55(7), 1045-1070.
[13] Ngigi, R. W., Pislaru, C., Ball, A., & Gu, F. (2012, May). Modern techniques for condition monitoring of railway vehicle dynamics. In Journal of Physics: conference series (Vol. 364, No. 1, p. 012016). IOP Publishing.
[14] Fernández-Bobadilla, H. A., & Martin, U. (2023). Modern tendencies in vehicle-based condition monitoring of the railway track. IEEE Transactions on Instrumentation and Measurement, 72, 1-44.
[15] García, R., & Martínez, F. (2018). "A Vision-Based Surveillance System for Track Intrusion Detection in Railway Networks." IEEE Transactions on Intelligent Transportation Systems, 19(12), 3856-3866. https://doi.org/10.1109/TITS.2018.2812540Kim.
[16] S. H., & Lim, S. C. (2018). Intelligent intrusion detection system featuring a virtual fence, active intruder detection, classification, tracking, and action recognition. Annals of Nuclear Energy, 112, 845-855.
[17] Kim, H., & Lee, C. (2017). "Smart Railway Track Security System Using Computer Vision and Machine Learning." Proceedings of the 2017 International Conference on Big Data and Smart Computing (BigComp), 123-128. https://doi.org/10.1109/BIGCOMP.2017.20.
[18] Ji, A., Woo, W. L., Wong, E. W. L., & Quek, Y. T. (2021). Rail track condition monitoring: A review on deep learning approaches. Intelligence & Robotics, 1(2), 151-175.
[19] Petrović, A. D., Banić, M., Simonović, M., Stamenković, D., Miltenović, A., Adamović, G., & Rangelov, D. (2022). Integration of computer vision and convolutional neural networks in the system for detection of rail tracks and signals on the railway. Applied Sciences, 12(12), 6045.
[20] Singh, P., Dulebenets, M. A., Pasha, J., Gonzalez, E. D. S., Lau, Y. Y., & Kampmann, R. (2021). Deployment of autonomous trains in rail transportation: Current trends and existing challenges. IEEE Access, 9, 91427-91461.
[21] Kumar, S. (2020). Gantry Protection for Railways and Train Detection System with Railroad Worker Protection Solution. International Journal of Emerging Trends in Computer Science and Information Technology, 1(2), 17-25. https://doi.org/10.63282/3050-9246.IJETCSIT-V1I2P103
[22] Kumar, S. (2021). Rail Defect Measurement System: Integrating AI and IoT for Predictive Operations. International Journal of Artificial Intelligence, Data Science, and Machine Learning, 2(2), 39-50. https://doi.org/10.63282/3050-9262.IJAIDSML-V2I2P105
[23] Kumar, S. (2022). Implementing Agile in Railway Product Development: A Balance of Compliance and Innovation. International Journal of Emerging Research in Engineering and Technology, 3(3), 20-28. https://doi.org/10.63282/3050-922X.IJERET-V3I3P103
[24] Kumar, S. (2024). Advancing Railway Safety through Sensor Fusion and AI-Based Decision Systems. International Journal of AI, BigData, Computational and Management Studies, 5(1), 49-58. https://doi.org/10.63282/3050-9416.IJAIBDCMS-V5I1P106
