Object Level Fusion and Tracking Strategies for Modeling Driving Situations

Abstract

Object detection and tracking is a crucial task as a basis for advanced driver assistance and automation systems. For this purpose a fusion system at object level is proposed, which allows high availability and reliability, since a high independence of the sensors can be reached. In order to deal with common challenges of object detection and tracking, such as maneuvering vehicles, data outliers, partial observability and split and merge effects, a series of novel strategies have been developed. These include the adaptive noise modeling, the definition of an object logical reference, the partial observability modeling, the multiple association of observations, and strategies to duplicate and unify object hypotheses. The proposed fusion system has been prototypically implemented based on a camera and a laser scanner. Furthermore, it has been tested with both simulated and real data. The test results show a win in data quality and robustness, with which an improvement of driver assistance and automation systems can be reached.