Skip to Main Content
Despite the availability of lane departure and lane keeping systems for highway assistance, unmarked and winding rural roads still pose challenges to lane recognition systems. To detect an upcoming curve as soon as possible, the viewing range of image-based lane recognition systems has to be extended. This is done by evaluating 3D information obtained from stereo vision or imaging radar in this paper. Both sensors deliver evidence grids as the basis for road course estimation. Besides known Kalman filter approaches, particle filters have recently gained interest since they offer the possibility to employ cues of a road, which can not be described as measurements needed for a Kalman filter approach. We propose to combine both principles and their benefits in a Kalman particle filter. The comparison between the results gained from this recently published filter scheme and the classical approaches using real world data proves the advantages of the Kalman particle filter.