Estimation of emotions is an essential aspect in developing intelligent systems intended for crowded environments. However, emotion estimation in crowds remains a challenging problem due to the complexity in which human emotions are manifested and the capability of a system to perceive them in such conditions. This paper proposes a hierarchical Bayesian model to learn in unsupervised manner the behavior of individuals and of the crowd as a single entity, and explore the relation between behavior and emotions to infer emotional states. Information about the motion patterns of individuals are described using a self-organizing map, and a hierarchical Bayesian network builds probabilistic models to identify behaviors and infer the emotional state of individuals and the crowd. This model is trained and tested using data produced from simulated scenarios that resemble real-life environments. The conducted experiments tested the efficiency of our method to learn, detect and associate behaviors with emotional states yielding accuracy levels of 74% for individuals and 81% for the crowd, similar in performance with existing methods for pedestrian behavior detection but with novel concepts regarding the analysis of crowds.
Emotions play an important role in human behavior, even more so in large congregations of people where emotional states are prompt to be contaged and amplified. This work presents a qualitative systematic review of the literature concerning the estimation of emotions and affects in real-life crowded environments, covering the aspects of methods and datasets. The academic search engine Scopus was inquired and the search was limited to publications in the English language addressing any of the aforementioned aspects. The aim of this contribution is to highlight advances, limitation and trends in addressing the estimation of emotions in crowds.
Inspired by Gustave Lebon's idea of crowds as single-minded entities, we present a novel approach to describe the behavior of a crowd as a single entity, based on the global movement of the entire aggregate of people conforming the crowd. The present work significantly differs from existing literature where the behavior of single individuals within the crowd are the building blocks to describe crowd behavior. A bidimensional neural gas network is implemented to learn the topology of the physical environment in an unsupervised fashion, then a self-organizing map and a Bayesian network are used to describe the behavior of the crowd as a single entity. Experiments were conducted using footage from New York Grand Central Station to test the accuracy of our model to learn and identify different behaviors of the crowd. Results show high accuracy to identify behaviors under usual circumstances and low but consistently increasing accuracy over time on less common cases
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.