Improvement of multiple pedestrians tracking thanks to semantic information

This work presents an interacting multiple pedestrian tracking method for monocular systems that incorporates a prior knowledge about the movement and interactions of the targets. We consider 4 cases of pedestrian behaviors: going straight; finding the way; walking around and stand still. Those are combined within an Interacting Multiple Model Particle Filter strategy. We model targets interactions with social forces, included as potential functions in the weighting process of the Particle Filter (PF). We use different social force models in each motion model to handle high level behaviors (collision avoidance, flocking.. .). We evaluate our algorithm on challenging datasets and demonstrate that such semantic information improve the tracker performance.