A unified bayesian approach for tracking and situation assessment

Tracking and situation assessment are crucial components of many Advanced Driver Assistance Systems (ADASs). Current tracking algorithms usually provide a probabilistic representation of relevant entities in the vehicle environment. Similarly, different approaches for handling uncertainties during situation assessment have been proposed. However, the interface between tracking and situation assessment is still an unsolved issue. In this paper, a direct link between the Bayes filters used by the tracking modules and the situation assessment based on Bayesian networks is proposed. The method is illustrated on the example of a system which automatically determines lane change maneuver recommendations. The presented results using both simulated and real data show that the proposed approach is capable of providing a unified approach of handling uncertainties for ADAS applications.