Trajectory Analysis for Sport and Video Surveillance

Abstract

In video surveillance and sports analysis applications, trajectories offer the possibility of extracting rich information on the underlying behavior of the moving targets. To this end we introduce an extension of Point Distribution Models (PDM) to analyze trajectories in their spatial, temporal and spatiotemporal dimensions. These trajectory models represent trajectories as an average trajectory and a set of deformation modes, in the spatial, temporal and spatiotemporal domains. Thus any given trajectory can be expressed in terms of its modes, which in turn can be ascribed to a particular behavior. The proposed analysis tool has been tested on trajectory data extracted from a vision system that was tracking radio-guided cars running inside a circuit. This affords an easier interpretation of results, because the shortest lap provides a reference behavior. Besides showing an actual analysis we discuss how to normalize trajectories to have a meaningful analysis.