Crowd Management Research Articles

During peak hours, the large-scale and spatiotemporal imbalance of passenger flow in subway stations results in passenger crowding, queuing issues, and uneven utilization of facility capacities. These problems not only decrease the overall throughput efficiency of the station but also increase safety risks related to large passenger gatherings. This research constructed a pedestrian facility network for subway station access and egress by defining minimum capacity control units of node facilities (including station entrances/exits, fare gates, security check machines, and staircases/escalators) as network nodes and the connecting channels among these nodes were assumed as edges. With the optimization objectives of minimizing both the average walking time of passengers in the pedestrian facility network and the risk of passenger flow aggregation at nodes, an integrated optimization model for passenger flow control and service capacity configuration in the pedestrian facility network of subway stations is established. The ε-constraint method is employed to transform it into a single-objective linear integer programming model, which is then directly solved using the Gurobi optimizer version 11.0. The following conclusion were drawn form a case study on the National Convention and Exhibition Center Station of Shanghai Metro: compared with pre-optimization conditions, the optimized solution reduced the average walking time of access/egress passengers during peak hours by 11%, decreased the number of nodes with queue overflow by 76%, lowered node-level crowding risks by 45%, and reduced facility supply–demand balance standard deviation by 22.8%. Compared to single-objective optimization approaches, the proposed method only increased the average walking time by 8% while decreasing the number of overflow-prone nodes by 60% and crowding risk by 26.1%. These findings provided scientific support for the formulation of crowd management strategies and optimization of operational control in subway stations under heavy passenger flow conditions.

The Hajj and Umrah pilgrimage attract millions of Muslim pilgrims around the world every year, which exerts heavy load on the transportation system, crowd management systems and Hajj pilgrim experience in general. The flow of such mass populations in a restricted and sacred space are logistically, safely and spiritually challenged. This article examines how Hajj and Umrah pilgrim movement could be transformed by use of Artificial Intelligence (AI) and smart mobility technologies. Based on recent advancements in AI-driven mobility systems, Internet of Things (IoT) infrastructure and blockchain-based frameworks, we outline the integrative model based on data-driven decision-making so that pilgrimage experience can be experience-filled and spiritual. The analysis of the 26 academic sources in a systematic manner reveals the main enablers, case studies, and applications of smart cities worldwide to religious tourism in the specific context of Saudi Arabia, Vision 2030. The paper also reviews deep learning, mobile crowd sensing, and digital twins as fundamental technologies of real-time monitoring, scalable intervention and predictive analytics. Using this, we are presenting a multi-layered AI-informed framework that is Islamic compliant and pilgrimage friendly in the area of logistics. Finally, this paper shows that smart mobility can decrease congestion, add safety, and increase satisfaction and be compatible with religious, cultural, and ethical values.

In the era of big data, the rapid proliferation of user-generated content enriched with geolocations offers new perspectives and datasets for probing the spatiotemporal dynamics of tourist mobility. Mining large-scale geospatial traces has become central to tourism geography: it reveals preferences for attractions and routes to enable intelligent recommendation, enhance visitor experience, and advance smart tourism, while also informing spatial planning, crowd management, and sustainable destination development. Using Mount Huangshan—a UNESCO World Cultural and Natural Heritage site—as a case study, we integrate GPS trajectories and geo-tagged photographs from 2017–2023. We apply a Density-Field Hotspot Detector (DF-HD), a Space–Time Cube (STC), and spatial gridding to analyze behavior from temporal, spatial, and fully spatiotemporal perspectives. Results show a characteristic “double-peak, double-trough” seasonal pattern in the number of GPS tracks, cumulative track length, and geo-tagged photos. Tourist behavior exhibits pronounced elevation dependence, with clear vertical differentiation. DF-HD efficiently delineates hierarchical hotspot areas and visitor interest zones, providing actionable evidence for demand-responsive crowd diversion. By integrating sequential time slices with geography in a 3D framework, the STC exposes dynamic spatiotemporal associations and evolutionary regularities in visitor flows, supporting real-time crowd diagnosis and optimized spatial resource allocation. Comparative findings further confirm that Huangshan’s seasonal intensity is significantly lower than previously reported, while the high agreement between trajectory density and gridded photos clarifies the multi-tier clustering of route popularity. These insights furnish a scientific basis for designing secondary tour loops, alleviating pressure on core areas, and charting an effective pathway toward internal structural optimization and sustainable development of the Mount Huangshan Scenic Area.

The emergence of artificial intelligence (AI) and autonomous aerial systems has transformed the landscape of both defense and humanitarian operations. This paper introduces an innovative concept of an AI-based multipurpose military drone that integrates hybrid mesh + LTE communication networks to provide temporary connectivity in remote or satellite-shadowed regions. The proposed system is designed to perform a variety of tasks such as surveillance, payload transport, crowd management, criminal tracking, and disaster response. The drone leverages AI-driven navigation, sensor fusion, and autonomous path optimization to execute missions efficiently under diverse environmental conditions. Built with lightweight, modular, and portable architecture, it ensures rapid deployment and adaptability. The study explores the design methodology, communication framework, ethical considerations, and performance analysis of this system, emphasizing its dual-use potential in both military and civilian contexts. By uniting AI, IoT, and next-generation networking, the proposed drone aims to enhance situational awareness, operational efficiency, and safety in mission-critical environments

Crowd management employing nudge theory for safe elevator use by masses of occupants during a high-rise building evacuation

How to conduct rapid and efficient personnel evacuation following maritime accidents remains a complex and challenging issue, while the mixed dynamics of heterogeneous behaviors and the impact of gravity under special environmental contexts have received insufficient research attention. Motivated by this gap, we employ the social force model to investigate heterogeneous crowd evacuation dynamics with imitative behavior in inclined environments. The results indicate that cautious passengers typically prolong evacuation time under emergency conditions when their number is relatively large. However, a controlled presence of cautious individuals may efficiently mitigate adverse effects caused by wicked passengers, due to the imitation. Furthermore, exit orientation plays a critical role in shaping evacuation dynamics, particularly under extreme maritime conditions. This study provides quantitative insights into crowd management strategies for marine evacuation scenarios involving heterogeneous passengers with imitative behaviors.

Qualitative and quantitative hybrid analysis of heterogeneous crowds involving individuals with diverse types of disabilities passing through bottleneck.

Field theories for complex systems traditionally focus on collective behaviours emerging from simple, reciprocal pairwise interaction rules. However, many natural and artificial systems exhibit behaviours driven by microscopic decision-making processes that introduce both nonreciprocity and many-body interactions, challenging these conventional approaches. We develop a theoretical framework to incorporate decision-making into field theories using the shepherding problem from swarm robotics as a paradigmatic example of a multi-agent control system, where agents, the herders, must coordinate to confine another group of agents, the targets, within a prescribed region. By introducing continuous approximations of two key decision-making elements - target selection and trajectory planning - we derive field equations that capture the essential features of this distributed control problem. Our theory reveals that different decision-making strategies emerge at the continuum level, from average attraction to highly selective choices, and from undirected to goal-oriented motion, driving transitions between homogeneous and confined configurations. The resulting nonreciprocal field theory not only describes the shepherding problem but provides a general framework for incorporating decision-making into continuum theories of collective behaviour, with implications for applications ranging from robotic swarms to traffic and crowd management systems.

Real-time detection of violent behavior through surveillance technologies is increasingly important for public safety. This study tackles the challenge of automatically distinguishing violent from non-violent activities in continuous video streams. Traditional surveillance depends on human monitoring, which is time-consuming and error-prone, highlighting the need for intelligent systems that detect abnormal behaviors accurately with low computational cost. A key difficulty lies in the ambiguity of defining violent actions and the reliance on large annotated datasets, which are costly to produce. Many existing approaches also demand high computational resources, limiting real-time deployment on resource-constrained devices. To overcome these issues, the present work employs the lightweight MobileNet deep learning architecture for violence detection in surveillance videos. MobileNet is well-suited for embedded devices such as Raspberry Pi and Jetson Nano while maintaining competitive accuracy. In Python-based simulations on the Hockey Fight dataset, MobileNet is compared with AlexNet, VGG-16, and GoogleNet. Results show that MobileNet achieved 96.66% accuracy with a loss of 0.1329, outperforming the other models in both accuracy and efficiency. These findings demonstrate MobileNet’s superior balance of precision, computational cost, and real-time feasibility, offering a robust framework for intelligent surveillance in public safety monitoring, crowd management, and anomaly detection.

We investigate the dynamics of pedestrian crossing flows with varying crossing angles to classify different scenarios and derive implications for crowd management. Probability density functions of four key features—velocity, density, avoidance number, and intrusion number—were analyzed to characterize pedestrian behavior. Velocity–density fundamental diagrams were constructed for each crossing angle and fitted with functional forms from existing literature. Classification attempts using avoidance–intrusion numbers and velocity–density phase spaces revealed significant overlaps, highlighting the limitations of these metrics alone for scenario differentiation. To address this, machine learning models, such as logistic regression and random forest, were employed using all four features. Results showed robust classification performance with velocity and avoidance number emerging as the most influential features. Insights from feature importance metrics and classification accuracy offer practical guidance for managing high-density crowds, optimizing pedestrian flow, and designing safer public spaces. Funding: This research was supported by the National Science Center, Poland through SONATA [Grant 2022/47/D/HS4/02576]. Supplemental Material: The online appendix is available at https://doi.org/10.1287/trsc.2024.0996 .

Abstract Accurate human counting in indoor environments is essential for optimizing people-centric applications, such as crowd management, disaster response, and monitoring in settings like shopping malls and healthcare facilities. Traditional vision approaches face challenges with poor lighting conditions and raise privacy concerns. WiFi-based solutions enable device-free human counting by detecting disruptions in wireless signals caused by human presence. However, methods using received signal strength indicator are unreliable due to physical obstructions, multipath fading, radio interference, and fluctuating access point power. While WiFi channel state information-based systems are more sensitive to environmental changes, they lack standardization, limiting their practicality. To overcome these limitations, this paper presents Time4Count, an innovative device-free indoor human counting system that leverages round trip time measurements to achieve high accuracy and scalability. Time4Count capitalizes on human-induced fluctuations in signal propagation time to accurately estimate the number of individuals in a space. By employing a multivariate transformer-based feature extraction method, the system effectively mitigates non-line-of-sight errors and signal distortions, ensuring robust performance even in cluttered indoor environments. Additionally, Time4Count integrates spatial discretization and multi-label classification techniques, enabling it to count an unlimited number of individuals in real-time. The system was rigorously evaluated in two realistic, cluttered environments using commodity hardware, involving up to 15 participants. Experimental results reveal that Time4Count achieves an high counting accuracy of 92.7%. To our knowledge, Time4Count is the first RTT-based indoor counting system, providing a precise solution for indoor monitoring. Implementation is available at: https://github.com/mclab-osaka/time4count.

ABSTRACT This study explores the nuanced impact of crowding at religious sites on place identity (PI), destination image (DI), and behavioral intentions (BI). Based on data from 457 respondents at Kamakhya Temple, the analysis shows a curvilinear (inverted-U shaped) relationship between crowding and PI, DI and BI. Moderate crowding levels enhance PI and DI, which, in turn, exert a profound and significant positive influence on BI. Additionally, PI and DI independently contribute to favorable behavioral intentions, underscoring their pivotal roles. However, deviations from optimal crowding – whether excessive or minimal – diminish these positive associations. The findings highlight the necessity of strategic crowd management at sacred destinations to balance visitor satisfaction with the preservation of a compelling destination image. By shedding light on the intricate interplay between crowding dynamics and visitor perceptions, this study provides valuable guidance for fostering sustainable tourism practices in culturally significant settings.

Adaptive safety management of bidirectional crowd in metro stations considering robustness: From data-driven identification to prediction control

The management of crowds during the Hajj and Umrah pilgrimages is a multifaceted challenge due to the massive influx of pilgrims to sacred sites in Makkah and Madinah, Saudi Arabia. With millions of pilgrims visiting these sacred sites, Saudi Arabia has adopted a variety of smart solutions to ensure safety, efficiency, and comfort. Radiofrequency identification is central to these efforts, enabling real-time tracking and access to personal data for security and service delivery. The integration of Internet of Things devices and the Global Positioning System allows for continuous monitoring, emergency response, and smooth navigation. Surveillance systems enhanced with computer vision and convolutional neural networks enable real-time video analysis, early congestion detection, and facial recognition. Big data analytics processes multisource data to optimize crowd flow and transportation. Artificial intelligence–driven smartphone applications and social media platforms support communication and multilingual engagement. Wearable technologies like Hajj Bracelets track health status and trigger emergency alerts. Collectively, these innovations significantly improve crowd control, safety, and the overall pilgrimage experience. Furthermore, technologies have broader implications for global crowd management in other large-scale events. The successful application of AI, the Internet of Things, and real-time systems marks a paradigm shift in managing large gatherings, aligning with the broader vision of smart and secure public event planning.

Human detection and counting in visual surveillance systems is a critical task for enhancing security, monitoring crowd behavior, and improving safety in various environments such as public spaces, retail stores, transportation hubs, and industrial settings. This paper presents a robust approach for detecting and counting individuals in real-time using computer vision and machine learning techniques. The proposed system aims to accurately identify and track human figures within video footage, providing reliable data on foot traffic, crowd density, and movement patterns. The system employs a combination of deep learning-based object detection models, such as Convolutional Neural Networks (CNNs), and more advanced architectures like You Only Look Once (YOLO) or Faster R-CNN, to detect human figures in a wide range of environments and lighting conditions. These models are trained to recognize human bodies, even in crowded or occluded settings, and to differentiate between humans and other objects in the scene. The counting functionality is achieved by tracking individual detections across video frames, ensuring that each person is counted once, even as they move through complex environments. Real-time human detection is achieved through a pipeline that processes video frames from surveillance cameras. The system provides outputs such as the number of people present in a given area, their movement trajectories, and density estimation. Alerts can be generated for abnormal crowd conditions, such as overcrowding or unusual movement patterns, which are valuable for security personnel or operational monitoring. Additionally, the system supports integration with existing surveillance infrastructure, providing a seamless solution for automated crowd management. Key Words: Violence detection, Yolo, Video analytics, CNN, computer vision

In recent years, pilgrim destinations across India have witnessed overwhelming crowd influxes, especially during festivals and auspicious days. This often results in long queues, safety risks, and an unsatisfactory experience for devotees. To address this issue, we propose an intelligent Online Ticket Booking and Bidding System enhanced with Machine Learning to optimize crowd management, minimize waiting times, and ensure a seamless pilgrimage experience. The system allows pilgrims to book time slots for darshan through a user-friendly web or mobile application. In addition to regular bookings, a bidding mechanism is introduced for high-demand slots, enabling pilgrims to bid for priority access. Machine learning models are integrated to predict crowd density, demand surges, and optimize time slot allocation, using historical visit data and calendar patterns. The platform ensures fairness, transparency, and efficiency through secure identity verification, real-time updates, and fraud prevention mechanisms. By leveraging ML algorithms such as time series forecasting, anomaly detection, and clustering, the system dynamically adjusts ticket availability and bid recommendations. This not only improves crowd distribution but also enhances safety and convenience for temple authorities and pilgrims alike. This project demonstrates how digital transformation and AI can be effectively used in spiritual and public settings to create a smarter and more inclusive pilgrimage experience. KEYWORDS: Online Ticket Booking, Bidding System, Crowd Management, Pilgrimage Destinations, Machine Learning, Time Slot Allocation, Demand Forecasting, Devotee Experience, Anomaly Detection, Time Series Forecasting, Slot Booking, Intelligent Scheduling, Real-time Updates, Fraud Prevention, AI in Pilgrimage, Digital Transformation, User-friendly Application, Crowd Density Prediction, Smart Temple Management, Secure Identity Verification.

This paper reviews the variability of passenger service time (PST) at the platform–train interface (PTI), a critical performance indicator in metro systems shaped by the infrastructure design, affecting passenger behavior and accessibility. Despite its operational importance, PST remains underexplored in relation to crowd management strategies. This review synthesizes findings from empirical and experimental research to clarify the main factors influencing PST and their implications for platform-level interventions. Key contributors to PST variability include door width, gap dimensions, crowd density, and user characteristics such as mobility impairments. Design elements—such as platform edge doors, yellow safety lines, and vertical handrails—affect flow efficiency and spatial dynamics during boarding and alighting. Advanced tracking and simulation tools (e.g., PeTrack and YOLO-based systems) are identified as essential for evaluating pedestrian behavior and supporting Level of Service (LOS) analysis. To complement traditional LOS metrics, the paper introduces Level of Interaction (LOI) and a multidimensional LOS framework that captures spatial conflicts and user interaction zones. Control strategies such as platform signage, seating arrangements, and visual cues are also reviewed, with experimental evidence showing that targeted design interventions can reduce PST by up to 35%. The review highlights a persistent gap between academic knowledge and practical implementation. It calls for greater integration of empirical evidence into policy, infrastructure standards, and operational contracts. Ultimately, it advocates for human-centered, data-informed approaches to PTI planning that enhance efficiency, inclusivity, and resilience in high-demand transit environments.

ABSTRACT Partisan demonstrations in the United States between the years of 2020 and 2021 led to criticisms about the visible differences in police responses depending on whether the protests were left- or right-wing. Right-wing demonstrations were often heavily and openly armed with rifles and other weapons, but police presence was largely absent. Conversely, media images of indiscriminate police force used on unarmed left-wing demonstrators drew much controversy. This exploratory study is the first to conduct a quantitative content analysis of protest images captured by AP News, Reuters, ABC, and PBS to determine police responses to these protests and potential predictors of responses using a codebook informed by extant use of force literature. Descriptive results confirm a far greater presence of firearms, other weapons, and aggression towards police from right-wing demonstrators but far lower police presence and show more frequent police uses of force against left-wing protesters despite lower frequencies of weapon presence and aggression towards police. Logistic regression models show that, when controlling for right-wing protesters with weapons, the right-wing partisanship of the protest significantly decreases the likelihood of police presence, and when controlling for other factors that influence police use of force, police are more likely to use indiscriminate force against left-wing demonstrators. Implications for police crowd management policy and avenues for future research are shared to address partisan police behaviour in democratic societies.

This study investigates user perceptions of circulation and spatial layout efficiency at Ikeja City Mall (ICM), one of Lagos’ most prominent shopping and entertainment centers. With an emphasis on understanding how these factors influence user satisfaction, a survey was conducted with 100 randomly selected individuals who visited the mall on various days, including during festive seasons. The study adopts a quantitative research design, utilizing structured questionnaires to gather data on key elements such as circulation efficiency, spatial layout, and overall user satisfaction. The findings reveal that 74% of respondents expressed satisfaction with ICM’s circulation efficiency, citing wide corridors, clear signage, and the strategic placement of amenities as contributing factors. However, 26% of visitors noted difficulties in navigating congested areas, particularly during peak periods. In terms of spatial layout, 70% of respondents were satisfied with the organization of the mall, appreciating the separation of retail, leisure, and service areas. Nonetheless, 30% of respondents reported congestion in specific zones, especially near the food court and cinema. Overall, 78% of respondents were satisfied with their experience at ICM, although visitors during festive seasons expressed lower satisfaction levels due to overcrowding. The study concludes that while ICM is generally well-planned, there is room for improvement, particularly in managing crowd flow during busy periods. Recommendations include enhancing the wayfinding system, spatially reconfiguring high-traffic areas, and implementing temporary crowd management strategies during festive seasons. These measures could further improve circulation and spatial layout efficiency, ensuring a more seamless user experience.

From data to insights: a comprehensive analysis of pilgrims stress and fatigue during Hajj using wearable remote sensing systems