Crowd Behavior Research Articles

Crowd Management at Turnstiles in Metro Stations: A Pilot Study Based on Observation and Microsimulation

Crowd management at turnstiles in metro stations is a critical task for ensuring safety, efficiency, and comfort for passengers. A methodology based on observation and microsimulation provides an advanced understanding and optimization of crowd flow through these turnstiles. The aim is to optimize crowd management and prevent overcrowding and delays at metro turnstiles through innovative solutions. The methodology is based on simulating passenger movements through turnstiles to observe and optimize crowd behavior. The results show that passenger decisions (e.g., choosing which turnstile to use, adjusting pace) are based on perceived crowd density, level of service, and usage of space. For instance, the number of turnstiles, their location, and the layout are important variables to be considered in the decision-making sequence. These decisions can be influenced by parameters like turnstile availability, walking paths, and real-time data (e.g., density of passengers). The methodology can help metro operators decide where to place additional turnstiles or adjust operational schedules. By simulating crowd behavior, operators can make informed decisions to reduce congestion and improve the efficiency of turnstile usage. This methodology could be implemented in various metro systems to optimize operations during different crowd conditions and peak times, ensuring smooth, safe, and efficient passenger flow.

Real-Time Detection, Evaluation, and Mapping of Crowd Panic Emergencies Based on Geo-Biometrical Data and Machine Learning

Crowd panic emergencies can pose serious risks to public safety, and effective detection and mapping of such events are crucial for rapid response and mitigation. In this paper, we propose a real-time system for detecting and mapping crowd panic emergencies based on machine learning and georeferenced biometric data from wearable devices and smartphones. The system uses a Gaussian SVM machine learning classifier to predict whether a person is stressed or not and then performs real-time spatial analysis to monitor the movement of stressed individuals. To further enhance emergency detection and response, we introduce the concept of CLOT (Classifier Confidence Level Over Time) as a parameter that influences the system’s noise filtering and detection speed. Concurrently, we introduce a newly developed metric called DEI (Domino Effect Index). The DEI is designed to assess the severity of panic-induced crowd behavior by considering factors such as the rate of panic transmission, density of panicked people, and alignment with the road network. This metric offers immeasurable benefits by assessing the magnitude of the cascading impact, enabling emergency responders to quickly determine the severity of the event and take necessary actions to prevent its escalation. Based on individuals’ trajectories and adjacency, the system produces dynamic areas that represent the development of the phenomenon’s spatial extent in real time. The results show that the proposed system is effective in detecting and mapping crowd panic emergencies in real time. The system generates three types of dynamic areas: a dynamic Crowd Panic Area based on the initial stressed locations of the persons, a dynamic Crowd Panic Area based on the current stressed locations of the persons, and the dynamic geometric difference between these two. These areas provide emergency responders with a real-time understanding of the extent and development of the crowd panic emergency, allowing for a more targeted and effective response. By incorporating the CLOT and the DEI, emergency responders can better understand crowd behavior and develop more effective response strategies to mitigate the risks associated with panic-induced crowd movements. In conclusion, our proposed system, enhanced by the incorporation of these two new metrics, proves to be a dependable and efficient tool for detecting, mapping, and assessing the severity of crowd panic emergencies, leading to a more efficient response and ultimately safeguarding public safety.

Dynamic Effect of Bidirectional Crowd Behavior on Footbridges Considering Human–Structure Interaction

Dynamic Effect of Bidirectional Crowd Behavior on Footbridges Considering Human–Structure Interaction

Walk the Line: The role of gender and culture on the movement patterns of pedestrians based on a multicultural study

Experimental work has opened new avenues for studying crowd behavior under well-controlled conditions with desirable levels of measurement accuracy. However, unlike many other areas of behavioral science, little attention has been paid to how reproducible and transferable crowd phenomena are between different populations. As such, there is only limited knowledge about how universal and generalizable experimental observations on crowd behavior are. This research explores how gender and culture impact pedestrian dynamics in single-file movement, a topic previously studied in isolation through disjointed and varied experiments. Here, for the first time, and as an attempt to investigate external validity and generalizability across cultures, we conduct the same experiment in five different countries. Each experiment examines the effects of varying gender compositions on single-file pedestrian movement. We observed consistent effects of different gender compositions on pedestrian movement across countries, with no significant deviations in the fundamental diagrams, especially in the bounded regime. Although there was some variability in acceleration behavior across countries. Interaction levels, clustering behavior, and pedestrian spacing patterns remained consistent between different gender compositions and countries. These results suggest that, while the behavior of collective motion varies by culture and gender composition, most aspects of pedestrian movement exhibit universal traits. Understanding these variations and commonalities can allow for better infrastructure design and planning tailored to the population of interest.

Spatiotemporal Trajectories of Pedestrian Mobility at the Train Station: evidence of 24 million trajectories

Understanding pedestrian movement remains crucial for designing efficient and safe transportation structures such as terminals, stations, or airports. The significance of conducting a granular analysis in pedestrian mobility dynamics research is evident in refining crowd behavior modeling. It is essential for gaining insights into potential terminal layouts, crowd management strategies, and evacuation procedures, all of which enhance safety and efficiency. In this context, we offer an original empirical dataset of 24,000,000 samples of trajectory spatial movement at traffic terminals in Havlíčkův Brod and Pardubice, Czech Republic. The dataset was collected using a high-resolution camera system installed at the railway station. Subsequently, algorithmic post-processing was applied to extract anonymous data on the spatial movement of recorded pedestrians. Thanks to this dataset, researchers can delve into the distances between pedestrians in a transportation terminal, considering factors such as group composition, group-to-group distances, and movement speed.

Escape: an optimization method based on crowd evacuation behaviors

Meta-heuristic algorithms, particularly those based on swarm intelligence, are highly effective for solving black-box optimization problems. However, maintaining a balance between exploration and exploitation within these algorithms remains a significant challenge. This paper introduces a useful algorithm, called Escape or Escape Algorithm (ESC), inspired by crowd evacuation behavior, to solve real-world cases and benchmark problems. The ESC algorithm simulates the behavior of crowds during the evacuation, where the population is divided into calm, herding, and panic groups during the exploration phase, reflecting different levels of decision-making and emotional states. Calm individuals guide the crowd toward safety, herding individuals imitate others in less secure areas, and panic individuals make volatile decisions in the most dangerous zones. As the algorithm transitions into the exploitation phase, the population converges toward optimal solutions, akin to finding the safest exit. The effectiveness of the ESC algorithm is validated on two adjustable problem size test suites, CEC 2017 and CEC 2022. ESC ranked first in the 10-dimensional, 30-dimensional tests of CEC 2017, and the 10-dimensional and 20-dimensional tests of CEC 2022, and second in the 50-dimensional and 100-dimensional tests of CEC 2017. Additionally, ESC performed exceptionally well, ranking first in the engineering problems of pressure vessel design, tension/compression spring design, and rolling element bearing design, as well as in two 3D UAV path planning problems, demonstrating its efficiency in solving real-world complex problems, particularly complex problems like 3D UAV path planning. Compared with 12 other high-performance, classical, and advanced algorithms, ESC exhibited superior performance in complex optimization problems. The source codes of ESC algorithm will be shared at https://aliasgharheidari.com/ESC.html and other websites.

Virtual Crowds Rheology: Evaluating the Effect of Character Representation on User Locomotion in Crowds.

Crowd data is a crucial element in the modeling of collective behaviors, and opens the way to simulation for their study or prediction. Given the difficulty of acquiring such data, virtual reality is useful for simplifying experimental processes and opening up new experimental opportunities. This comes at the cost of the need to assess the biases introduced by the use of this technology. Our paper is part of this effort, and investigates the effect of the graphical representation of a crowd on the behavior of a user immersed within. More specifically, we inspect the virtual navigation through virtual crowds, in terms of travel speeds and local navigation choices as a function of the visual representation of the virtual agents that make up the crowd (simple geometric model, anthropomorphic model or realistic model). Through an experiment in which we ask a user to navigate virtual crowds of varying densities, we show that the effect of the visual representation is limited, but that an anthropomorphic representation offers the best trade-off between computational complexity and ecological validity, even though a more realistic representation can be preferred when user behaviour is studied in more details. Our work leads to clear recommendations on the design of immersive simulations for the study of crowd behavior.

Exploring Urbanization Strategies by Dissecting Aggregate Crowd Behaviors: A Case Study in China

Town development, a crucial stage of urbanization, has been increasingly prioritized in recent sustainable socio-economic growth strategies. Vitality, especially the one measured by aggregate crowd behaviors, is widely recognized as a crucial development element. Conducting comprehensive assessments of the drivers of town vitality, particularly crowd vitality, is thus essential for addressing challenges and monitoring progress. This study examines representative towns in China and employs multiple datasets along with XGBoost-SHAP to investigate the mechanisms of development environment factors on aggregate crowd vitality. Key findings highlight the study’s novelty and broader implications: (1) The degree of industrial agglomeration is the most significant factor impacting the dependent measures, providing new data-driven insights into the role of economic clustering in town development. (2) Other indicators, such as the minimum distance to the town center, the enclosure, and car and pedestrian friendliness, can effectively predict town vitality, offering practical considerations for town planning. (3) Industrial innovation and diversification, rational planning of living circles, and enhancement of town conditions emerge as three crucial strategies for promoting urbanization. This study enhances empirical insights with strategies for addressing urbanization challenges, emphasizing how crowd data can be used to inform urbanization policies and planning practices, aiding urban planners in building more sustainable systems.

Exploring the Spatiotemporal Heterogeneities in Urban Vitality Through Scalable Proxies from Mobile Data

Jane Jacob’s concepts of urban vitality and diversity have become prevailing urban planning philosophies in most countries for making cities more livable. Recent changes in demographics and the impacts of COVID-19 have exacerbated the economic and social challenges that cities commonly face, particularly spatiotemporal heterogeneities. Being able to understand these heterogeneities in scalable approaches is fundamental to tackling these challenges in cities. Therefore, this article aims to provide a new form of scalable estimation of urban vitality by using the de facto population. Instead of merely adopting static statistical information such as morphological characteristics in areas, we leverage dynamic factors such as internal mobility flows and energy use intensity as proxies for the spatiotemporal dynamics of indoor and outdoor behaviors of crowds. In this way, we combine dynamic attributes and static features to describe the patterns of urban vitality, which are directly related to spatiotemporal dynamics in urban places. We utilize GNSS-based mobile data and building energy usage intensity as dynamic proxies along with static data such as land use mix and age distribution. To better capture spatial heterogeneity, we use a Multiscale Geographically Weighted Regression (MGWR) model to identify the relationships between the de facto population and the dynamic and static factors. Drawing from the factors determining urban vitality, this article provides policy implications for alleviating spatiotemporal urban imbalances. These data-driven implications can fill the technical knowledge gaps in establishing planning strategies for achieving urban sustainability while enhancing overall subjective livability.

A Review of Abnormal Crowd Behavior Recognition Technology Based on Computer Vision

Abnormal crowd behavior recognition is one of the research hotspots in computer vision. Its goal is to use computer vision technology and abnormal behavior detection models to accurately perceive, predict, and intervene in potential abnormal behaviors of the crowd and monitor the status of the crowd system in public places in real time, to effectively prevent and deal with public security risks and ensure public life safety and social order. To this end, focusing on the abnormal crowd behavior recognition technology in the computer vision system, a systematic review study of its theory and cutting-edge technology is conducted. First, the crowd level and abnormal behaviors in public places are defined, and the challenges faced by abnormal crowd behavior recognition are expounded. Then, from the dimensions based on traditional methods and based on deep learning, the mainstream technologies of abnormal behavior recognition are discussed, and the design ideas, advantages, and limitations of various methods are analyzed. Next, the mainstream software tools are introduced to provide a comprehensive reference for the technical framework. Secondly, typical abnormal behavior datasets at home and abroad are sorted out, and the characteristics of these datasets are compared in detail from multiple perspectives such as scale, characteristics, and uses, and the performance indicators of different algorithms on the datasets are compared and analyzed. Finally, the full text is summarized and the future development direction of abnormal crowd behavior recognition technology is prospected.

The effect of apparent Police power at demonstrations against right-wing populism on Protestors' resistance using a virtual reality experiment.

Based on the Elaborated Social Identity Model of Crowd Behaviour, we tested in two experiments whether a forceful display of police power increases perceptions of illegitimacy of the police and the formation of resistance among protestors. In the high power condition, the police were dressed in riot gear (with helmets, armed with shields and batons). In the low power condition, the police were dressed in regular uniforms. In both studies, people participated in a demonstration against right-wing populism using a virtual reality setting and were either stopped by the police in riot gear or by the police in regular uniforms. The results of Study 1 (N = 155) show that the police in riot gear were evaluated as more illegitimate compared to the police in normal clothing. The results of Study 2 (N = 97) replicated this finding and illustrated that police in riot gear (compared to regular uniforms) increased protestors' intentions to engage in direct resistance against the police. This effect was mediated by perceptions of illegitimacy and anger directed at the police. Furthermore, weakly identified protestors were particularly affected by the display of power and were more likely to engage in anti-police resistance and collective action. Implications are discussed.

K-fold matching model for crowd behavioral anomaly detection from discontinuous inputs

Image and associated features detect behavioural anomalies in crowd scenes through matching. Existingmethods use continuous data inputs to track crowd behaviour. As a result, the systemmistakenly assumes normal behaviour during data gaps, leading to false positives or missing detections of small abnormalities. The design of precision-focused matching requires simplified yet robust validation for any number of crowd elements. This article presents a K-fold Matching Model (KFMM) with edge-to-edge correlation. This proposed model identifies the region edges of an input crowd image sequentially. The difference in edges due to crowd misbehaviour activities is validated using random and continuous image features in K number of steps. Considering the complexity of multiple K-steps, the confinement is performed using a neural sigmoid function where the K × K edge matching is reduced. This reduction is based on activity classification i.e. minimum and maximum between two consecutive input sequences. Therefore, as the classification increases, the K is halted with the maximum correlation; contrarily for a low number of classifications, the manifold matching is pursued until the maximum is reached. This correlation count is defined using the neural sigmoid with a linear function for the edges. For the maximum features, this proposed model achieves an 11.21 % high matching ratio, 8.15 % high classifications, 9.71 % high precision, 9.61 % less complexity, and 8.9 % less linear error.

ANALYSIS OF THE CROWD MANAGEMENT AND PEDESTRIAN MOVEMENT DURING HAJJ PILGRIMAGE ON MAKKAH

The Hajj pilgrimage, the world's largest annual mass gathering, poses significant challenges in crowd management and pedestrian movement due to the sheer number of participants and logistical complexities. This study emphasizes the need for effective strategies to ensure the safety of millions of pilgrims in Mecca, Saudi Arabia. By reviewing literature and analysing pedestrian movement systems, it identifies key bottlenecks and safety risks, especially during high-density periods like Nafra day. Field observations from 2019 to 2024, including the post-COVID-19 era, offer insights into crowd behaviour and the effectiveness of management strategies. The study highlights the importance of integrating advanced simulation tools with urban design to optimize pedestrian pathways and prevent overcrowding, contributing to Saudi Vision 2030's goals of enhancing the pilgrimage experience and ensuring participant safety.

Anomaly detection in crowded scenes: technologies, challenges and opportunities

The paper discusses advancements in intelligent video surveillance systems, particularly focused on anomaly detection in crowded environments. These systems aim to enhance public safety by automatically detecting unusual behavior and potential threats in real-time. Traditional video surveillance, relying heavily on human monitoring, faces limitations like reduced concentration and slow response times. In contrast, intelligent surveillance uses machine learning and AI algorithms to process vast amounts of video data, identifying patterns that deviate from normal behavior. Crowd anomaly detection is essential in densely populated areas like transportation hubs, stadiums, and public squares. The diversity of anomalies, ranging from minor disruptions to serious threats such as theft or terrorist attacks, presents a challenge for these systems. Anomalies can be difficult to detect due to their unpredictable nature, and what constitutes an anomaly varies depending on the context. The paper highlights the need for robust systems that can adapt to various environmental conditions and distinguish between normal variations and genuine threats. While supervised machine learning models show promise, they often require large amounts of labeled data, which is difficult to obtain in real-world settings. Unsupervised models and deep learning techniques, such as Convolution Neural Networks, have been effective in analyzing crowd behavior and detecting anomalies. However, these methods still face challenges, including scalability, high false positive rates, and the need for real-time processing in large-scale environments. The paper concludes by addressing the limitations of current crowd anomaly detection methods, such as their computational costs, ethical concerns, and inability to detect novel anomalies. It suggests directions for future research, including the integration of advanced learning techniques to improve system performance and scalability

Optimized deep maxout for crowd anomaly detection: A hybrid optimization-based model

ABSTRACT Monitoring Surveillance video is really time-consuming, and the complexity of typical crowd behaviour in crowded situations makes this even more challenging. This has sparked a curiosity about computer vision-based anomaly detection. This study introduces a new crowd anomaly detection method with two main steps: Visual Attention Detection and Anomaly Detection. The Visual Attention Detection phase uses an Enhanced Bilateral Texture-Based Methodology to pinpoint crucial areas in crowded scenes, improving anomaly detection precision. Next, the Anomaly Detection phase employs Optimized Deep Maxout Network to robustly identify unusual behaviours. This network’s deep learning capabilities are essential for detecting complex patterns in diverse crowd scenarios. To enhance accuracy, the model is trained using the innovative Battle Royale Coalesced Atom Search Optimization (BRCASO) algorithm, which fine-tunes optimal weights for superior performance, ensuring heightened detection accuracy and reliability. Lastly, using various performance metrics, the suggested work’s effectiveness will be contrasted with that of the other traditional approaches. The proposed crowd anomaly detection is implemented in Python. On observing the result showed that the suggested model attains a detection accuracy of 97.28% at a learning rate of 90%, which is much superior than the detection accuracy of other models, including ASO = 90.56%, BMO = 91.39%, BES = 88.63%, BRO = 86.98%, and FFLY = 89.59%.

SPCANet: congested crowd counting via strip pooling combined attention network.

Crowd counting aims to estimate the number and distribution of the population in crowded places, which is an important research direction in object counting. It is widely used in public place management, crowd behavior analysis, and other scenarios, showing its robust practicality. In recent years, crowd-counting technology has been developing rapidly. However, in highly crowded and noisy scenes, the counting effect of most models is still seriously affected by the distortion of view angle, dense occlusion, and inconsistent crowd distribution. Perspective distortion causes crowds to appear in different sizes and shapes in the image, and dense occlusion and inconsistent crowd distributions result in parts of the crowd not being captured completely. This ultimately results in the imperfect capture of spatial information in the model. To solve such problems, we propose a strip pooling combined attention (SPCANet) network model based on normed-deformable convolution (NDConv). We model long-distance dependencies more efficiently by introducing strip pooling. In contrast to traditional square kernel pooling, strip pooling uses long and narrow kernels (1×N or N×1) to deal with dense crowds, mutual occlusion, and overlap. Efficient channel attention (ECA), a mechanism for learning channel attention using a local cross-channel interaction strategy, is also introduced in SPCANet. This module generates channel attention through a fast 1D convolution to reduce model complexity while improving performance as much as possible. Four mainstream datasets, Shanghai Tech Part A, Shanghai Tech Part B, UCF-QNRF, and UCF CC 50, were utilized in extensive experiments, and mean absolute error (MAE) exceeds the baseline, which is 60.9, 7.3, 90.8, and 161.1, validating the effectiveness of SPCANet. Meanwhile, mean squared error (MSE) decreases by 5.7% on average over the four datasets, and the robustness is greatly improved.

Crowd dynamics analysis and behavior recognition in surveillance videos based on deep learning

Crowd dynamics analysis and behavior recognition in surveillance videos based on deep learning

The use of convolutional neural networks for abnormal behavior recognition in crowd scenes

This study introduces the Abnormality Converging Scene Analysis Method (ACSAM) to detect abnormal group behavior using monitored videos or CCTV images in crowded scenarios. Abnormal behavior recognition involves classifying activities and gestures in continuous scenes, which traditionally presents significant computational challenges, particularly in complex crowd scenes, leading to reduced recognition accuracy. To address these issues, ACSAM employs a convolutional neural network (CNN) enhanced with Abnormality and Crowd Behavior Training layers to accurately detect and classify abnormal activities, regardless of crowd density. The method involves extracting frames from the input scene and using CNN to perform conditional validation of abnormality factors, comparing current values with previous high values to maximize detection accuracy. As the abnormality factor increases, the identification rate improves with higher training iterations. The system was tested on 26 video samples and trained on 34 samples, demonstrating superior performance to other approaches like DeepROD, MSI-CNN, and PT-2DCNN. Specifically, ACSAM achieved a 12.55% improvement in accuracy, a 12.97% increase in recall, and a 10.23% enhancement in convergence rate. These results suggest that ACSAM effectively overcomes the computational challenges inherent in crowd scene detection, offering a robust solution for real-time abnormal behavior recognition in crowded environments.

Developing a Predictive Model of Crowd Behavior at Music Concerts and Festivals (MCF): A Proposal for a Research Framework

Music Concerts and Festivals (MCF) have experienced steady growth each year, transforming these events into large-scale international gatherings from their humble beginnings in the 1980s. The trend of increasing attendance by festival-goers and concert-goers at MCF has prominently emerged in the 21st century. The attendance of MCF contributes to the formation of crowds, which are indirectly influenced by risky behavior. Consequently, this trend has led to numerous incidents related to risky behavior at MCF. However, there is insufficient research on such behavior, and few existing studies address any predictive models specific to MCF. As a result, there has been a slight increase in aggressive behavioral incidents among festival-goers and concert-goers. This issue has demonstrated the importance of studying crowd behavior among those attending musical concerts and festivals. Therefore, this paper will focus on the important variables related to risky behavior that can cause crowd behavior and bridge the gap by identifying risky behavior among crowds. Additionally, this study will propose a research framework for the development of a crowd behavioral predictive model to anticipate future risk behavior among attendees. This research will employ a mixed-methods approach comprising both qualitative and quantitative methodologies as its method of investigation. The research framework will then be used to develop a predictive model of crowd behavior among attendees of MCF that will help to provide significant information for event and concert organizers to understand potential risky behavior among the crowd, hence, help in mitigating or preventing unwanted crowd safety incidents at MCF.

LIVE EVENT DETECTION FOR PEOPLE’S SAFETY USING NLP AND DEEP LEARNING

In recent years, ensuring public safety during live events has become a critical challenge due to the increasing scale of gatherings and potential risks. This study proposes a novel approach to Live Event Detection for People’s Safety using audio data and the LightGBM classifier. The system leverages real-time audio streams to identify anomalies, such as loud disturbances, explosions, or unusual crowd behavior, which could indicate potential safety threats. Audio features are extracted using advanced signal processing techniques, including Mel-frequency cepstral coefficients (MFCCs), spectral contrast, and chroma features. These features are fed into a LightGBM classifier, which provides efficient and robust performance for real-time classification of event categories and potential risks. The proposed methodology is evaluated using diverse datasets comprising audio samples from live events, including concerts, sports, and emergency situations, to ensure a comprehensive understanding of normal and abnormal patterns. The LightGBM model demonstrates high accuracy, low latency, and scalability, making it suitable for deployment in real-time applications. Additionally, the system integrates a feedback loop for continuous model improvement based on new audio data. The results highlight the system's ability to enhance situational awareness and proactively alert authorities to potential risks, ensuring timely interventions. This approach demonstrates a significant step toward leveraging machine learning and audio analytics to improve public safety at live events.