Crowd Behavior Analysis: A Survey

Swathi, H. Y.; Shivakumar, G.; Mohana, H. S.

doi:10.1109/icraect.2017.66

Cited by 21 publications

(7 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The emergent dynamics of crowd behavior have been fruitfully modeled according to biological phenomena such as swarm behavior (Kok, Lim, & Chan, 2016). Classification of emergent crowd dynamics, often using computer vision technology, has typically relied on analysis of video data for features, such as crowd density estimation, motion detection, and movement/behavior tracking of individual signals or group behavior (Kok et al, 2016;Swathi, Shivakumar, & Mohana, 2017). However, it is not always feasible to obtain high-quality image, video, or speech data of a crowd in action, nor is it always feasible to obtain signals measured from each individual in an interacting crowd.…”

Section: Introductionmentioning

confidence: 99%

Recurrence Quantification Analysis of Crowd Sound Dynamics

Proksch,

Reeves,

Gee

et al. 2023

Cognitive Science

View full text Add to dashboard Cite

When multiple individuals interact in a conversation or as part of a large crowd, emergent structures and dynamics arise that are behavioral properties of the interacting group rather than of any individual member of that group. Recent work using traditional signal processing techniques and machine learning has demonstrated that global acoustic data recorded from a crowd at a basketball game can be used to classify emergent crowd behavior in terms of the crowd's purported emotional state. We propose that the description of crowd behavior from such global acoustic data could benefit from nonlinear analysis methods derived from dynamical systems theory. Such methods have been used in recent research applying nonlinear methods to audio data extracted from music and group musical interactions. In this work, we used nonlinear analyses to extract features that are relevant to the behavioral interactions that underlie acoustic signals produced by a crowd attending a sporting event. We propose that recurrence dynamics measured from these audio signals via recurrence quantification analysis (RQA) reflect information about the behavioral dynamics of the crowd itself. We analyze these dynamics from acoustic signals recorded from crowds attending basketball games, and that were manually labeled according to the crowds' emotional state across six categories: angry noise, applause, cheer, distraction noise, positive chant, and negative chant. We show that RQA measures are useful to differentiate the emergent acoustic behavioral dynamics between these categories, and can provide insight into the recurrence patterns that underlie crowd interactions.

show abstract

Section: Introductionmentioning

confidence: 99%

Recurrence Quantification Analysis of Crowd Sound Dynamics

Proksch,

Reeves,

Gee

et al. 2023

Cognitive Science

View full text Add to dashboard Cite

show abstract

“…In traditional crowd behavior research, the use of behavior observations, interview surveys, questionnaire surveys, and other survey methods consume a lot of manpower and material resources, and this often interferes with the target, resulting in certain theoretical errors. Modern digital technology provides a new option for the study of crowd behavior patterns [18]. Generating pedestrian behavior heat maps based on big data has achieved good results [19,20].…”

Section: Influencing Factors and Evaluation Indicators Of Microclimatesmentioning

confidence: 99%

“…Buildings 2023, 13, x FOR PEER REVIEW 4 of 15 theoretical errors. Modern digital technology provides a new option for the study of crowd behavior patterns [18]. Generating pedestrian behavior heat maps based on big data has achieved good results [19,20].…”

Section: Influencing Factors and Evaluation Indicators Of Microclimatesmentioning

confidence: 99%

Study on Camping Behavior Patterns for Thermal Comfort at Riverside Parks

Liu

2023

Buildings

View full text Add to dashboard Cite

People-oriented landscape experiences have become the focus of park design with the increasing demand of outdoor activities from urban residents, whereas thermal-comfort-guided landscape design has attracted more attention in academic circles. Based on the investigation of the microclimate of typical subregions in riverside parks, this paper uses AI recognition to analyze the spatiotemporal distribution of camping crowds, and considers the correlation between landscape morphological parameters, microclimates, and crowd behavior. Finally, we built a model to raise the number of landscape optimization strategies for landscape design. The results show that landscape morphological parameters, such as tree height, crown canopy, and sky visibility factor (SVF), can significantly affect the air temperature (Ta), relative humidity (RH), and physiological temperature (PET) in an environment, while hardly affecting wind speed (WS). For microclimate parameters, Ta has a moderate correlation with camping behavior, with a correlation coefficient of −0.145 and a p-value of 0.040, while the corresponding correlation with PET was non-significant with a p-value of 0.622. The temporal distribution of the number of campers per day show a linear upward trend with a reasonable goodness-of-fit, with an adjusted R2 above 0.789 for all subregions. The model based on landscape morphological parameters has a good fit, with coefficients of tree height and crown canopy of −0.195 and 1.316, respectively. This study provides theoretical support and design suggestions for the design of riverside parks based on crowd behavior patterns.

show abstract

“…For instance, Li et al (2015) cover motion analysis, behavior recognition, and anomaly detection but does not cover counting, density estimation, object detection, crowd prediction, and so forth. Swathi, Shivakumar, and Mohana (2017) cover density estimation, motion detection, and behavior recognition, but do not cover object detection, and anomaly detection. Similarly, Zhang, Yu, and Yu (2018) cover only physics-inspired methods for crowd analysis and focuses on motion analysis in videos.…”

Section: Similar and Related Studiesmentioning

confidence: 99%

Visual crowd analysis: Open research problems

Khan,

Menouar,

Hamila

2023

AI Magazine

View full text Add to dashboard Cite

Over the last decade, there has been a remarkable surge in interest in automated crowd monitoring within the computer vision community. Modern deep‐learning approaches have made it possible to develop fully automated vision‐based crowd‐monitoring applications. However, despite the magnitude of the issue at hand, the significant technological advancements, and the consistent interest of the research community, there are still numerous challenges that need to be overcome. In this article, we delve into six major areas of visual crowd analysis, emphasizing the key developments in each of these areas. We outline the crucial unresolved issues that must be tackled in future works, in order to ensure that the field of automated crowd monitoring continues to progress and thrive. Several surveys related to this topic have been conducted in the past. Nonetheless, this article thoroughly examines and presents a more intuitive categorization of works, while also depicting the latest breakthroughs within the field, incorporating more recent studies carried out within the last few years in a concise manner. By carefully choosing prominent works with significant contributions in terms of novelty or performance gains, this paper presents a more comprehensive exposition of advancements in the current state‐of‐the‐art.

show abstract

Crowd Behavior Analysis: A Survey

Cited by 21 publications

References 47 publications

Recurrence Quantification Analysis of Crowd Sound Dynamics

Recurrence Quantification Analysis of Crowd Sound Dynamics

Study on Camping Behavior Patterns for Thermal Comfort at Riverside Parks

Visual crowd analysis: Open research problems

Contact Info

Product

Resources

About