This study describes a new approach for pedestrian behaviour analysis in simulated urban environments. A software system was developed to analyse the dynamics of pedestrians with a focus on their movement trajectories and the angle between the pedestrian's movement vector and their gaze vector. One-class support vector machines and dynamic time warping were applied for outlier detection in order to indentify noticeable changes in the visual behavior of individuals in a group of simulated pedestrians who walk past visually attractive objects. Results of simulation experiments demonstrate how different pedestrian behaviour characteristics can be detected and distinguished in a variety of abstract urban design scenarios. The described software system was designed to allow future real world applications by feeding video recordings of real pedestrians into the model.
3rd International Workshop on Advanced Computational Intelligence (IWACI 2010). Proceedings of the3rd International Workshop on Advanced Computational Intelligence, IWACI 2010 (Suzhou, China 25-27 May, 2010) p. 442-447