Assessing the Perceived Realism of Agent Grouping Dynamics for Adaptation and Simulation

Virtual crowds are a prominent feature for a range of applications; from simulations for cultural heritage, to interactive elements in video games. A body of existing research seeks to develop and improve algorithms for crowd simulation, typically with a goal of achieving more realistic behaviours. For applications targeting human interaction however, what is judged as realistic crowd behaviour can be subjective, leading to situations where actual crowd data is not always perceived to be more real than simulation, making it difficult to identify a ground truth. We present a novel method using psychophysics to assess the perceived realism of behavioural features with respect to virtual crowds. In this instance, a focus is given to the grouping dynamics feature, whereby crowd composition in terms of group frequency and density is evaluated through thirty-six conditions based on crowd data captured from three pedestrianised real-world locations. The study, conducted with seventy-eight healthy participants, allowed for the calculation of perceptual thresholds, with configurations identified that appear most real to human viewers. The majority of these configurations correlate with the values extracted from the crowd data, with results suggesting that viewers have more perceptual flexibility when group frequency and density are increased, rather than decreased.