Extraction of Features from Mobile Laser Scanning Data for Future Driver Assistance Systems

Research and development of driver assistance systems is currently a very active field. One building block of future systems will be an accurate and reliable positioning, which can be realized by relative measurement, using on-board sensors and maps of the environment. However, a prerequisite will be that such maps can be produced fully automatically. This paper explores the use of dense laser scans from mobile laser scanning systems for the production of such maps. After presenting the problem and the matching approach, we introduce our test field which consists of a 22 km scan of roads, both inner city streets as well as highways. It is shown how suitable features can be extracted fully automatically. Finally, for a given trajectory, we evaluate how positioning will perform and draw conclusions regarding applicability and future work.