PROJECT TITLE :

Object-Oriented Bayesian Networks for Detection of Lane Change Maneuvers

ABSTRACT :

This article introduces a completely unique approach towards the popularity of typical driving maneuvers in structured highway situations and shows some key benefits of traffic scene modeling with object-oriented Bayesian networks (OOBNs). The approach exploits the benefits of an introduced lane-related coordinate system along with individual occupancy schedule grids for all modeled vehicles. This combination allows an economical classification of the prevailing vehicle-lane and vehicle- vehicle relations in traffic scenes and so substantially improves the understanding of complex traffic scenes. Chances and variances within the network are propagated systematically that ends up in probabilistic sets of the modeled driving maneuvers. Using this generic approach, the network is ready to classify a complete of twenty seven driving maneuvers together with merging and object following.