Linear cyclic pursuit based prediction of personal space violation in surveillance video

Abstract

Analysis of human interaction in a social gathering is of high interest in security and surveillance applications. It is also of psychological interest to study the interaction to get a better understanding of the participant behavior. This paper is an attempt to explore and analyze interactions among the individuals from a single calibrated camera. We are particularly interested in trajectory prediction. These predicted trajectories of individuals are then used in predicting personal space violation. Each individual, represented by a feature point in a 2.5D coordinate system, is tracked using Lucas-Kanade tracking algorithm. We use the linear cyclic pursuit framework to model this point motion. This model is used for short-term prediction of individual trajectory. We demonstrate these ideas on different types of datasets.