About this Research Topic
Crowds build community and allow us to feel connected to others. This evokes positive feelings, such as liveliness and excitement, which benefit mental well-being. Conversely, the crowding of urban, public spaces is increasing, and the consequences of both permanent and temporary overcrowding can lead to psychological discomfort. Crowding can be stressful, and such environmental stressors are numerous in the built environment of cities.
Additionally, crowds entail significant physical safety risks. The spread of Covid-19 is familiar, which sometimes forced us to ban all crowds. Also, several tragic overcrowding incidents at events such as the Love Parade 2020 and Astroworld Festival 2021 are in our collective memory. To advance our understanding of crowd behavior, it is crucial to carefully measure, monitor and predict the density of a crowd.
The fundament of crowd safety and management is to ensure that everyone in the crowd is safe, healthy and comfortable. To ensure peoples' physical and mental well-being in crowded places, it is vital to gain insights into the best ways to measure, monitor and predict crowd densities and understand human behavior as a response to different types of densities. This requires research focusing on accurate and innovative technological density measurements as well as socio-psychological research gauging crowd members’ density perceptions and emotional responses as real-time as possible.
On a technological level, the lack of ground truth or reference figures for large crowds is currently still problematic (e.g. ethical, privacy-related issues; machine learning based on human-provided labels). Promising solutions include stereo cameras, infrared cameras, smartphone applications, cellular connections, Wi-Fi hardware addresses, Wi-Fi CSI, radio frequency attenuation, and advanced simulations that aim to prevent crowd incidents. Academic research regarding these solutions is greatly needed, but is unfortunately still scarce.
Technologies allow for top-down, external observations of crowd behavior on a crowd and group level. However, most methods do not allow us to make valid claims on the audience's psychological state, emotions and mood. Collecting (real-time) data on emotions among crowd members is crucial to interpret technological measures of density. Also, research on the role of contextual, situational, and individual factors that might explain if and why some individuals are more or less sensitive to specific density levels is highly valuable.
Advancements in technological, urban engineering, as well as socio-psychological crowd research will be essential and the key for an integrative approach on the understanding and prediction of crowd behavior. Therefore, this Research Topic aims to encourage studies and research on novel methods and solutions for crowd counting and crowd analytics.
We are looking for original research papers and review papers. Topics include but are not limited to:
• Technological crowd monitoring using regular cameras, depth cameras, infrared cameras, etc.
• Technological crowd monitoring using radar, device-free sensing in wireless sensor networks, etc.
• Technological crowd monitoring using Wi-Fi, Bluetooth, 4G, 5G, 6G etc.
• Technological crowd monitoring using smartphone apps, data aggregation, etc.
• Technological crowd monitoring using Internet of Things and edge-based approaches.
• Crowd data processing using machine learning, deep learning, neuromorphic processors, etc.
• Methods for spatial crowd classification.
• Methods for collecting psychological data from individual crowd members.
• Crowd behavior prediction and modeling in urban environments
• Impact of contextual, situational, and individual factors on crowding perceptions.
• Impact of contextual, situational, and individual factors on crowd members’ emotions and mood.
• Crowd behavior analysis and anomaly detection.
• Crowd management approaches.
• Crowd safety analysis.
• (Urban) crowd dynamics.
• Machine learning and AI for crowd monitoring, crowd simulation, crowd perception, crowd management, and crowd safety.
• Crowd monitoring for urban planning, engineering, and design.
• Smart infrastructure for crowd monitoring and management.
• Crowd monitoring for transportation planning.
• Crowd management during emergency response in built environment.
Additionally, crowds entail significant physical safety risks. The spread of Covid-19 is familiar, which sometimes forced us to ban all crowds. Also, several tragic overcrowding incidents at events such as the Love Parade 2020 and Astroworld Festival 2021 are in our collective memory. To advance our understanding of crowd behavior, it is crucial to carefully measure, monitor and predict the density of a crowd.
The fundament of crowd safety and management is to ensure that everyone in the crowd is safe, healthy and comfortable. To ensure peoples' physical and mental well-being in crowded places, it is vital to gain insights into the best ways to measure, monitor and predict crowd densities and understand human behavior as a response to different types of densities. This requires research focusing on accurate and innovative technological density measurements as well as socio-psychological research gauging crowd members’ density perceptions and emotional responses as real-time as possible.
On a technological level, the lack of ground truth or reference figures for large crowds is currently still problematic (e.g. ethical, privacy-related issues; machine learning based on human-provided labels). Promising solutions include stereo cameras, infrared cameras, smartphone applications, cellular connections, Wi-Fi hardware addresses, Wi-Fi CSI, radio frequency attenuation, and advanced simulations that aim to prevent crowd incidents. Academic research regarding these solutions is greatly needed, but is unfortunately still scarce.
Technologies allow for top-down, external observations of crowd behavior on a crowd and group level. However, most methods do not allow us to make valid claims on the audience's psychological state, emotions and mood. Collecting (real-time) data on emotions among crowd members is crucial to interpret technological measures of density. Also, research on the role of contextual, situational, and individual factors that might explain if and why some individuals are more or less sensitive to specific density levels is highly valuable.
Advancements in technological, urban engineering, as well as socio-psychological crowd research will be essential and the key for an integrative approach on the understanding and prediction of crowd behavior. Therefore, this Research Topic aims to encourage studies and research on novel methods and solutions for crowd counting and crowd analytics.
We are looking for original research papers and review papers. Topics include but are not limited to:
• Technological crowd monitoring using regular cameras, depth cameras, infrared cameras, etc.
• Technological crowd monitoring using radar, device-free sensing in wireless sensor networks, etc.
• Technological crowd monitoring using Wi-Fi, Bluetooth, 4G, 5G, 6G etc.
• Technological crowd monitoring using smartphone apps, data aggregation, etc.
• Technological crowd monitoring using Internet of Things and edge-based approaches.
• Crowd data processing using machine learning, deep learning, neuromorphic processors, etc.
• Methods for spatial crowd classification.
• Methods for collecting psychological data from individual crowd members.
• Crowd behavior prediction and modeling in urban environments
• Impact of contextual, situational, and individual factors on crowding perceptions.
• Impact of contextual, situational, and individual factors on crowd members’ emotions and mood.
• Crowd behavior analysis and anomaly detection.
• Crowd management approaches.
• Crowd safety analysis.
• (Urban) crowd dynamics.
• Machine learning and AI for crowd monitoring, crowd simulation, crowd perception, crowd management, and crowd safety.
• Crowd monitoring for urban planning, engineering, and design.
• Smart infrastructure for crowd monitoring and management.
• Crowd monitoring for transportation planning.
• Crowd management during emergency response in built environment.
Keywords: Crowd monitoring, crowd simulation, crowd perception, crowd management, crowd safety, crowd sensors, crowd data aggregation, crowd data analysis, crowd psychology, crowd behavior, crowd control, crowd science, crowd flow, crowd prediction, crowd dynamics, urban crowds, urban crowding, event safety, crowd mood, crowd emotions.
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
