A track-to-track association method for automotive perception systems

Abstract

Recent and future driver assistance systems use more and more sensors, that have individual tracking modules. For target tracking, it becomes necessary to find techniques to manage as simply as possible the use of a great number of independent and heterogeneous sensors, at the different stages of the process. This paper presents a modular highlevel track-fusion architecture for a multisensor environment. This architecture allows the variation of the number and the types of the used sensors with no major change in the tracking algorithm. The paper also tackles the multisensor track-to-track association issue with a new algorithm based on a particular track-to-track distance computation. An example of target tracking method is shown to make use of the proposed architecture and the track-to-track association algorithm.