Published Papers

Volume 33 - Issue 1 (Regular Issue)
Transactions Papers

Intelligent Crowd Diversion System (ICDS) – elevating operations and passenger experiences at world-class-event stations

Man Yan Cho, Sherry Yip, Cheuk Hin Harry Wong and Wai Pan Tam
Pages: 1-11Published: 30 Apr 2026
DOI: 10.33430/V33N1THIE-2025-0014
Cite thisHide

Cho MY, Yip S, Wong CH Harry, Tam WP, Intelligent Crowd Diversion System (ICDS) – elevating operations and passenger experiences at world-class-event stations, HKIE Transactions, Vol. 33, No. 1 (Regular Issue), Article THIE-2025-0014.R1, 2026, 10.33430/V33N1THIE-2025-0014

 Copy

Abstract:

An Intelligent Crowd Diversion System (ICDS) has been developed, utilising Artificial Intelligence (AI) and Machine Learning (ML) technologies to assist in crowd management at Kai Tak (KAT) and Sung Wong Toi (SUW) stations during mega events. The ICDS integrates real-time CCTV data and tailored AI-based video analytics to provide accurate people counting and crowd control metrics. The ICDS predicts real-time platform waiting times for dispersal based on statistics, including previous waiting times, crowd densities, and a unique formula for reliable measurement. Real-time updates are displayed on LCD panels for passenger guidance. A dashboard offers an overview of station busyness status, empowering station managers to make real-time adjustments and provide information for upcoming events during non-event days. The incorporation of AI technologies enables predictive measures for managing sudden increases in crowd volumes during largescale events. Data exchange with MTR Data Studio allows enhancing the comprehensiveness of databases and increasing the accuracy of predictions. Estimated waiting times benefit by keeping passengers informed with timely information, ensuring a smooth flow of passengers and improving the mobility efficiency. With the implementation of innovative crowd diversion, MTR can replace traditional manual crowd control management with the ICDS and become a modern railway system in the world.

Keywords:

artificial intelligence; computer vision; crowd control; railway; machine learning; safety; surveillance

Reference List:

1. MTR, "MTR." Accessed: Jan. 21, 2025. [Online]. Available: http://www.mtr.com.hk
2. J. Struniawski, "Crowd management during mass events," Zeszyty Naukowe SGSP, vol. 2, no. 89, pp.27–38, 2024, doi: 10.5604/01.3001.0054.3100.
3. G. A. Macriga, S. Bavyatha, S. H. Abhinidhi, and N.Jagadeesh, "Crowd Management using AI & ML," in Proc. 2024 Int. Conf. Power, Energy, Control Transm. Syst. (ICPECTS), Chennai, India, 2024, pp. 1–5, doi:10.1109/ICPECTS62210.2024.1078050.
4. D. Helbing and P. Molnár, "Social force model for pedestrian dynamics," Phys. Rev. E, vol. 51, no. 5, pp. 4282–4286, May 1995, doi: 10.1103/PhysRevE.51.4282.
5. R. L. Hughes, "A continuum theory for the flow of pedestrians," Transp. Res. Part B, Methodol., vol. 36, no. 6, pp. 507–535, Jul. 2002, doi: 10.1016/S0191-2615(01)00015-7.
6. W. Daamen and S. P. Hoogendoorn, "Experimental research of pedestrian walking behavior," Transp. Res. Rec., no. 1828, pp. 20–30, 2003, doi: 10.3141/1828-03.
7. Y. Zhang, D. Zhou, S. Chen, S. Gao, and Y. Ma, "Single-image crowd counting via multi-column convolutional neural network," in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Las Vegas, NV, USA, Jun. 2016, pp. 589–597, doi: 10.1109/CVPR.2016.70.
8. Y. Li, X. Zhang, and D. Chen, "CSRNet: Dilated convolutional neural networks for understanding the highly congested scenes," in Proc. IEEE/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR), Salt Lake City, UT, USA, Jun. 2018, pp. 1091–1100, doi: 10.1109/CVPR.2018.00121.
9. V. A. Sindagi and V. M. Patel, "A survey of recent advances in CNN-based single image crowd counting and density estimation," Pattern Recognit. Lett., vol. 107, pp. 3–16, May 2018, doi: 10.1016/j.patrec.2017.07.007.
10. D. Peng et al., "Detecting heads using feature refine net and cascaded multi-scale architecture," arXiv preprint arXiv:1803.09256, 2018.
11. T. H. Vu, A. Osokin, and I. Laptev, "Context-aware CNNs for person head detection," in Proc. IEEE Int. Conf. Comput. Vis. Workshops (ICCVW), Santiago, Chile, Dec. 2015, pp. 2893–2901, doi: 10.1109/ICCVW.2015.88.
12. P. Jiang, D. Ergu, F. Liu, Y. Cai, and B. Ma, "A review of Yolo algorithm developments," Procedia Comput. Sci., vol. 199, pp. 1066–1073, 2022, doi: 10.1016/j.procs.2022.01.135.
13. J. Redmon and A. Farhadi, "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767, 2018.
14. A. Bochkovskiy, C.-Y. Wang, and H.-Y. M. Liao, "YOLOv4: Optimal speed and accuracy of object detection," arXiv preprint arXiv:2004.10934, 2020.
15. A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple online and realtime tracking," in Proc. IEEE Int. Conf. Image Process. (ICIP), Phoenix, AZ, USA, Sep. 2016, pp. 3464–3468, doi: 10.1109/ICIP.2016.7533003.
16. N. Wojke, A. Bewley, and D. Paulus, "Simple online and realtime tracking with a deep association metric,"
in Proc. IEEE Int. Conf. Image Process. (ICIP), Beijing, China, Sep. 2017, pp. 3645–3649, doi: 10.1109/ICIP.2017.8296962.
17. D. Tolikas, E. D. Spyrou, and V. Kappatos, "Passenger routing algorithm for COVID-19 spread prevention by minimising overcrowding," Computers, vol. 13, no. 2, p. 47, Feb. 2024, doi: 10.3390/computers13020047.
18. X. Chen, H. Li et al., "Real-time metro passenger flow monitoring and forecasting via CCTV," IEEE Access, vol. 6, pp. 74638–74650, 2018.
19. Z. Zheng, Z. Yang et al., "Predicting station congestion using smart card and video data," Transp. Res. Rec., vol. 2673, no. 5, pp. 66–77, 2019.
20. Y. Zhang, C. Wang et al., "Multimodal transit analytics," Transp. Res. Part C, Emerg. Technol., vol. 77, pp. 275–291, 2017.
21. E. Negri, L. Fumagalli, and M. Macchi, "A review of the roles of digital twin in CPS-based production systems," Procedia Manuf., vol. 11, pp. 939–948, 2017, doi: 10.1016/j.promfg.2017.07.198.
22. A. Fuller, Z. Fan, C. Day, and C. Barlow, "Digital twin: Enabling technologies, challenges and open research," IEEE Access, vol. 8, pp. 108952–108971, 2020, doi: 10.1109/ACCESS.2020.2998358.
23. A. Garcia, J. Pérez et al., "Digital twins for metro station crowd management," Simul. Model. Pract. Theory, vol. 128, Art. no. 102642, 2023.
24. M. Wolff, A. Mahdavian et al., "Effectiveness of evacuation signage in public spaces," Saf. Sci., vol. 120, pp. 142–153, Dec. 2019.
25. M. Galesic, R. Garcia-Retamero et al., "Communicating risk and uncertainty via public displays," J. Risk Res., vol. 24, no. 9, pp. 1133–1153, 2021.
26. European Union, "General Data Protection Regulation (GDPR) guidance on video analytics in public spaces," 2018.
27. Information Commissioner’s Office (ICO), "Video surveillance code of practice," 2021.
28. National Institute of Standards and Technology (NIST), "Towards a standard for trustworthy AI," 2020.
29. CENELEC, "EN 50126 / EN 50128 / EN 50129:Railway Applications – The Specification and Demonstration of Reliability, Availability, Maintainability and Safety (RAMS)," 2017–2018.
30. International Electrotechnical Commission (IEC), "IEC 62290: Railway applications – Urban guided transport management and command/control systems," 2019.
31. S. Albawi, T. A. Mohammed, and S. Al-Zawi, "Understanding of a convolutional neural network," in Proc. Int. Conf. Eng. Technol. (ICET), Antalya, Turkey, 2017, pp. 1–6, doi: 10.1109/ICEngTechnol.2017.8308186.
32. H. Schulzrinne, A. Rao, R. Lanphier, and M. Westerlund, "Real-Time Streaming Protocol Version 2.0," Internet Engineering Task Force, RFC 7826, Dec. 2016, doi: 10.17487/RFC7826.
>> more<< less