sibadiНаучный рецензируемый журнал "Вестник СибАДИ"The Russian Automobile and Highway Industry Journal2071-72962658-5626The Siberian State Automobile and Highway University10.26518/2071-7296-2025-22-2-238-247PPKZFCsibadi-1995Research ArticleТРАНСПОРТTRANSPORTОбзор и выбор методов автоматизированного подсчета пассажиров на общественном наземном транспорте для эффективного управления перевозкамиReview and Selection of Methods for Automated Passenger Counting on Public Land Transport for Effective Transportation Managementhttps://orcid.org/0009-0005-3334-5106ПлахтийА. Д.PlakhtiiAndrei D.

Плахтий Андрей Дмитриевич – аспирант, 

199034, г. Санкт-Петербург, Университетская наб. 7/9.  

Plakhtii Andrei D. – Postgraduate Student,

7-9, Universitetskaya emb., St. Petersburg, 199034.

st110081@student.spbu.ruhttps://orcid.org/0009-0007-7163-3453КорчагинД. С.KorchaginDenis S.

Корчагин Денис Сергеевич – аспирант; Генеральный директор,

190005, г. Санкт-Петербург, 2-я Красноармейская ул., д.4;

192019, г. Санкт-Петербург, Хрустальная улица, 18 Литера А, Офис 414А.

Korchagin Denis S. – Postgraduate Student; CEO,

4, 2nd Krasnoarmeiskaya Str., St Petersburg, 190005;

Nr.18, Liter A, Office 414A, Khrustalnaya Street,  St Petersburg, 192019.

Dsk@transportsoft.ruСанкт-Петербургский государственный университетРоссияSt. Petersburg State UniversityRussian FederationСанкт-Петербургский государственный архитектурно-строительный университет; ООО «Современные технологии»РоссияFederal State Budgetary Educational Institution of Higher Education “Saint Petersburg State University of Architecture and Civil Engineering”; Modern Technologies LLCRussian Federation202530042025222238247Copyright © Плахтий А.Д., Корчагин Д.С., 20252025Плахтий А.Д., Корчагин Д.С.Plakhtii A.D., Korchagin D.S.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://vestnik.sibadi.org/jour/article/view/1995Введение

Введение. Цель исследования заключается в обзоре современных методов автоматического подсчета пассажиропотоков в общественном транспорте. Исследование посвящено актуальной проблеме подсчета пассажиропотока в общественном транспорте с использованием современных технологий, таких как видеонаблюдение, инфракрасные сенсоры и LiDAR.

Материалы и методы

Материалы и методы. Представлен обзор технологий, включая датчики, камеры, LiDAR и RFID, а также методы анализа, основанные на теоретических и эмпирических подходах. Использована информация от компаний-разработчиков для сравнения точности технологий в реальных условиях.

Результаты

Результаты. Сравнения показывают, что наилучшую точность обеспечивают LiDAR и камеры с машинным обучением, особенно в условиях высокой плотности пассажиров. Технологии на основе Wi-Fi и Bluetooth имеют ограниченную точность, но комбинированные решения могут преодолеть их недостатки.

Обсуждение и заключение

Обсуждение и заключение. Для точного подсчёта пассажиров наиболее эффективны LiDAR и видеонаблюдение с машинным обучением. Рекомендуется дальнейшее тестирование комбинированных технологий и развитие гибких систем, а также использование инновационных подходов в обучении нейронных сетей для улучшения точности.

Introduction

Introduction. The study aims to analyze modern automatic passenger counting methods in public transport. The study addresses the pressing issue of passenger flow counting in public transport using modern technologies such as video surveillance, infrared sensors, and LiDAR.

Materials and Methods

Materials and Methods. An overview of technologies is provided, including sensors, cameras, LiDAR, and RFID, along with analysis methods based on theoretical and empirical approaches. Information from development companies is used to compare the accuracy of technologies in real-world conditions.

Results

Results. The comparison results indicate that LiDAR and cameras with machine learning offer the highest accuracy, particularly in high passenger density scenarios. Wi-Fi and Bluetooth-based technologies have limited accuracy, but combined solutions can overcome their drawbacks.

Discussions and Conclusions. The conclusion emphasizes that LiDAR and video surveillance with machine learning are the most effective for accurate passenger counting. Further testing of combined technologies and the development of flexible systems are recommended, along with innovative approaches in neural network training to enhance accuracy.

пассажиропотокавтоматический подсчетобщественный транспорттранспортная аналитикауправление транспортоминтеллектуальные системыpassenger flowautomatic countingpublic transporttransport analyticstransport managementsmart systemsReferencesKuipers R.A., Palmqvist C.-W. Passenger Volumes and Dwell Times for Commuter Trains: A Case Study Using Automatic Passenger Count Data in Stockholm // Appl. Sci. 2022. Т. 12, №12. https://doi.org/10.3390/app12125983.Kuipers, R. A., & Palmqvist, C.-W., “Passenger Volumes and Dwell Times for Commuter Trains: A Case Study Using Automatic Passenger Count Data in Stockholm”. Appl. Sci. 2022; vol. 12, no. 12: 5983, Jun. 2022. https://doi.org/10.3390/app12125983.Андреев К.П. Совершенствование транспортного обслуживания населения // Транспортное Дело России. 2017. № 3. С. 7–9.Andreev K.P. The Improvement of Transport Services of the Population. Transport Business in Russia. 2017; 3: 7–9. (In Russ.)Петрова Д.В. Современные подходы к организации мониторинга пассажиропотоков общественного транспорта городских агломераций // Int. J. Open Inf. Technol. 2020. Т. 8, № 1. С. 47–57.Petrova D.V. Modern Approaches to the Organization of Public Transport Passenger Traffic Monitoring in Urban Agglomerations. International Journal of Open Information Technologies. 2020; Vol. 8, No. 1: 47–57 (In Russ.)Ковалев А.М., Егоров К.В., Санжапов Р.Р., Прыткова Е.Г. Тестирование системы аппаратного учета пассажиропотока в реальных условиях городского маршрута // Технико-технологические проблемы сервиса. 2021. № 4 (58). С. 12–18.Kovalev A.M., Egorov K.V., Sanzhapov R.R., Prytkova E.G. Testing of the system of hardware accounting of passenger traffic in real conditions of the city route. Technical and technological problems of the service. 2021; 4 (58): 12–18 (In Russ.)Grgurević I., Juršić K., Rajič V. Review of Automatic Passenger Counting Systems in Public Urban Transport. 5th EAI International Conference on Management of Manufacturing Systems. Cham: Springer, 2022. pp. 1–15. https://doi.org/10.1007/978-3-030-67241-6_1.Grgurević I., Juršić K., Rajič V. Review of Automatic Passenger Counting Systems in Public Urban Transport. 5th EAI International Conference on Management of Manufacturing Systems. Cham: Springer. 2022: 1–15. https://doi.org/10.1007/978-3-030-67241-6_1.Kotz A., Kittelson D.B., Northrop W.F. Novel Vehicle Mass-Based Automated Passenger Counter for Transit Applications // Transp. Res. Rec. 2016. Т. 2536. https://doi.org/10.3141/2536-05.Kotz A., Kittelson D.B., Northrop W.F. Novel Vehicle Mass-Based Automated Passenger Counter for Transit Applications. Transp. Res. Rec. 2016. Т. 2536. https://doi.org/10.3141/2536-05.Nitti M., Pinna F., Pintor L., et al. iABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System // Energies. 2020. Т. 13, no 6. https://doi.org/10.3390/en13061446.Nitti M., Pinna F., Pintor L., et al. iABACUS: A Wi-Fi-Based Automatic Bus Passenger Counting System. Energies. 2020; Т. 13, no 6. https://doi.org/10.3390/en13061446.Jiang H., Chen S., Xiao Z., et al. Pa-Count: Passenger Counting in Vehicles Using Wi-Fi Signals // IEEE Trans. Mob. Comput. 2024. Т. 23, no 4. pp. 2684–2697. https://doi.org/10.1109/TMC.2023.3263229.Jiang H., Chen S., Xiao Z., et al. Pa-Count: Passenger Counting in Vehicles Using Wi-Fi Signals. IEEE Trans. Mob. Comput. 2024; Т. 23, no 4: 2684–2697. https://doi.org/10.1109/TMC.2023.3263229.Khan S., Yousaf M.H., Murtaza F., Velastin S. Passenger Detection and Counting for Public Transport System // NED Univ. J. Res. 2020. Т. XVII. pp. 35–46. https://doi.org/10.35453/NEDJR-ASCN-2019-0016.Khan S., Yousaf M.H., Murtaza F., Velastin S. Passenger Detection and Counting for Public Transport System. NED Univ. J. Res. 2020; Т. XVII: 35–46. https://doi.org/10.35453/NEDJR-ASCN-2019-0016.Labit-Bonis C., Thomas J., Lerasle F. Visual and Automatic Bus Passenger Counting Based on a Deep Tracking-by-Detection System. [Электронный ресурс]. URL: https://hal.science/hal-03363502 (режим доступа: 30.10.2024)Labit-Bonis C., Thomas J., Lerasle F. Visual and Automatic Bus Passenger Counting Based on a Deep Tracking-by-Detection System. Available at: https://hal.science/hal-03363502 (acceded: 30.10.2024)Seidel R., Jahn N., Seo S., et al. NAPC: A Neural Algorithm for Automated Passenger Counting in Public Transport on a Privacy-Friendly Dataset // IEEE Open J. Intell. Transp. Syst. 2022. Т. 3. pp. 33–44. https://doi.org/10.1109/OJITS.2021.3139393.Seidel R., Jahn N., Seo S., et al. NAPC: A Neural Algorithm for Automated Passenger Counting in Public Transport on a Privacy-Friendly Dataset. IEEE Open J. Intell. Transp. Syst. 2022; Т. 3: 33–44. https://doi.org/10.1109/OJITS.2021.3139393.Pronello C., Ruiz X.R.G. Evaluating the Performance of Video-Based Automated Passenger Counting Systems in Real-World Conditions: A Comparative Study // Sensors. 2023. Т. 23, no 18. https://doi.org/10.3390/s23187719.Pronello C., Ruiz X.R.G. Evaluating the Performance of Video-Based Automated Passenger Counting Systems in Real-World Conditions: A Comparative Study. Sensors. 2023; Т. 23, no 18. https://doi.org/10.3390/s23187719Hsu Y.-W., Wang T.-Y., Perng J.-W. Passenger Flow Counting in Buses Based on Deep Learning Using Surveillance Video // Optik. 2020. Т. 202. https://doi.org/10.1016/j.ijleo.2019.163675.Hsu Y.-W., Wang T.-Y., Perng J.-W. Passenger Flow Counting in Buses Based on Deep Learning Using Surveillance Video. Optik. 2020; Т. 202. https://doi.org/10.1016/j.ijleo.2019.163675.Ge L., Sarhani M., Voß S., Xie L. Review of Transit Data Sources: Potentials, Challenges and Complementarity // Sustainability. 2021. Т. 13, no 20. pp. 11450. https://doi.org/10.3390/su132011450.Ge L., Sarhani M., Voß S., Xie L. Review of Transit Data Sources: Potentials, Challenges and Complementarity. Sustainability. 2021; Т. 13, no 20^ 11450. https://doi.org/10.3390/su132011450.Zhang J., et al. A Real-Time Passenger Flow Estimation and Prediction Method for Urban Bus Transit Systems // IEEE Trans. Intell. Transp. Syst. 2017. Т. 18, no 11. https://doi.org/10.1109/tits.2017.2686876.Zhang J., et al. A Real-Time Passenger Flow Estimation and Prediction Method for Urban Bus Transit Systems. IEEE Trans. Intell. Transp. Syst. 2017; Т. 18, no 11. https://doi.org/10.1109/tits.2017.2686876.Demissie M.G., et al. Inferring Passenger Travel Demand to Improve Urban Mobility in Developing Countries Using Cell Phone Data: A Case Study of Senegal // IEEE Trans. Intell. Transp. Syst. 2016. Т. 17, no 9. pp. 2466–2478. https://doi.org/10.1109/TITS.2016.2521830.Demissie M.G., et al. Inferring Passenger Travel Demand to Improve Urban Mobility in Developing Countries Using Cell Phone Data: A Case Study of Senegal. IEEE Trans. Intell. Transp. Syst. 2016; Т. 17, no 9: 2466–2478. https://doi.org/10.1109/TITS.2016.2521830.Mccarthy C., et al. A Field Study of Internet of Things-Based Solutions for Automatic Passenger Counting // IEEE Open J. Intell. Transp. Syst. 2021. Т. 2. pp. 384–401. https://doi.org/10.1109/OJITS.2021.3111052.Mccarthy C., et al. A Field Study of Internet of Things-Based Solutions for Automatic Passenger Counting. IEEE Open J. Intell. Transp. Syst. 2021; Т. 2: 384–401. https://doi.org/10.1109/OJITS.2021.3111052.Kuchár P., Pirník R., Janota A., et al. Passenger Occupancy Estimation in Vehicles: A Review of Current Methods and Research Challenges // Sustainability. 2023. Т. 15, no 2. pp. 1332. https://doi.org/10.3390/su15021332.Kuchár P., Pirník R., Janota A., et al. Passenger Occupancy Estimation in Vehicles: A Review of Current Methods and Research Challenges. Sustainability. 2023; Т. 15, no 2: 1332. https://doi.org/10.3390/su15021332.

The authors declare that there are no conflicts of interest present.