Lane detection for a situation adaptive lane keeping support system, the SAFELANE system

The goal of the SAFELANE project is to develop a situation-adaptive system for enhanced lane keeping support. A prerequisite for lane keeping is reliable information of the vehicle environment. Especially the vehicle position within the lane and the course of the road ahead is important. This information is provided by the lane detection component. The lane tracker is mainly vision based but it is also supplemented by map, positioning and vehicle data. A high dynamic range camera provides the processing unit with image data. Measurement points of lane borders, calculated by a robust edge detection algorithm, are used to estimate a 3D clothoid model of the lane. A new approach for getting an initial lane models is introduced which can be dynamically adapted from map and positioning data. The detection is extended to the neighbour lanes and lane markings type classifying component is added.