Perception of emotions from crowd dynamics

Abstract

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.