Sensing Technologies for Crowd Management, Adaptation, and Information Dissemination in Public Transportation Systems: A Review

Abstract

Management of crowd information in public transportation (PT) systems is crucial, both to foster sustainable mobility, by increasing the user's comfort and satisfaction during normal operation, as well as to cope with emergency situations, such as pandemic crises, as recently experienced with COVID-19 limitations. This paper presents a taxonomy and review of sensing technologies based on Internet of Things (IoT) for real-time crowd analysis, which can be adopted in the different segments of the PT system (buses/trams/trains, railway/metro stations, and bus/tram stops). To discuss such technologies in a clear systematic perspective, we introduce a reference architecture for crowd management, which employs modern information and communication technologies (ICT) in order to: (i) monitor and predict crowding events; (ii) implement crowd-aware policies for real-time and adaptive operation control in intelligent transportation systems (ITSs); (iii) inform in real-time the users of the crowding status of the PT system, by means of electronic displays installed inside vehicles or at bus/tram stops/stations, and/or by mobile transport applications. It is envisioned that the innovative crowd management functionalities enabled by ICT/IoT sensing technologies can be incrementally implemented as an add-on to state-of-the-art ITS platforms, which are already in use by major PT companies operating in urban areas. Moreover, it is argued that, in this new framework, additional services can be delivered to the passengers, such as, e.g., on-line ticketing, vehicle access control and reservation in severely crowded situations, and evolved crowd-aware route planning.

Deep Learning Based Efficient Crowd Counting System

“…Furthermore, the authors in [51] propose a deep learning-based method, utilizing a convolutional autoencoder and YOLOv3 architecture, to estimate passenger occupancy on buses in real-time, improving scheduling for transport operators and enhancing travel convenience for passengers but the proposed model is resource-constraining. Moreover, the authors in [52] propose incorporating IoT sensors into public transit networks to develop a "smart" crowd control solution. While it provides a well-structured reference architecture and predicts advantages beyond pandemic concerns, it lacks critical features.…”

A Review of Deep Learning Techniques for Crowd Management

“…Thomopoulos [4] provides insights into identifying risks and implementing measures to ensure the safety of attendees. Darsena et al [5] concentrate on crowd management in transportation settings during emergencies in rail transit systems. It offers recommendations and best practices to enhance preparedness and response in high-capacity transportation hubs.…”

The Effect of Seat Layout on the Interaction of Passengers Inside the Train Carriage: An Experimental Approach for Urban Services

“…At the PTI, measures for crowd management can be introduced to minimize the interaction between boarding and alighting of passengers. Crowd management in public transport systems refers to the systematic administration of people's movement, aimed at fostering appropriate behavior to enhance the utilization of pedestrian infrastructure [8]. The authors used sensor technologies to evaluate measures according to the space in which they are implemented.…”

“…Sustainability 2024, 16, x FOR PEER REVIEW 2 of 16 transport systems refers to the systematic administration of people's movement, aimed at fostering appropriate behavior to enhance the utilization of pedestrian infrastructure [8].…”