A new approach for tracking lanes by fusing image measurements with map data

This paper presents a multi sensor approach for tracking the road borders and lanes in highway scenarios. It is based on extended Kalman filtering and estimates the parameters of circle segments. In addition to a greyscale camera, our approach uses digital map information in combination with GPS, yaw and velocity measurements. The solution combines the localization task with the task of fusing white lines in the image with data from maps. Therefore, the state space contains movement parameters as well as the parameters of more than one circle segment. Simulations show that the algorithm is also very successful in situations when the vehicle makes rapid lane changes or the white lines in front of the car are temporarily not visible, because they are hidden by another object. Also in situations when the highway goes over the top of a hill, a precise estimation of the road course in front of the car is not possible. Simulated and real tests show the improvement reached by the approach. Results are compared with others which are known from the literature.