Frontiers in Computational Neuroscience 10 (2016): 63. · Jul 8, 2016
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.
Digital Signal Processing (DSP), 2015 IEEE International Conference · Jul 24, 2015
Perceiving crowd emotions and understand the situation is vital to control the situations in surveillance applications. This paper introduces the evolution of methods for crowd emotion perception based on bio-inspired probabilistic models. The emotions have been perceived both in an offline and online manner from the crowd. We focus on the perception of emotion from crowd behavior and dynamics. The paper explains few probabilistic algorithms and compares these for detection of emotion of crowds and proposes a probabilistic modelling approach which is trained on data to perceive the emotions of the crowd in an area under surveillance. Emotions are defined as evolving dynamic patterns arising due to interaction of people in an environment with their relationships to the past interaction patterns. Camera sensors are used to track the motion of the individuals within a crowd scenario under observation. The data mining techniques are used to distinguish between different behaviors and events into positive and negative emotions. The results have been evaluated using simulated data from a proposed office environment.