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.

[1]  Ernst D. Dickmanns,et al.  Recursive 3-D Road and Relative Ego-State Recognition , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Gerd Wanielik,et al.  Multi-modal detection and parameter-based tracking of road borders with a laser scanner , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[3]  Deepak Khosla.  Accurate estimation of forward path geometry using two-clothoid road model , 2002, Intelligent Vehicle Symposium, 2002. IEEE.

[4]  Hans-Hellmut Nagel,et al.  Towards Active Machine-Vision-Based Driver Assistance for Urban Areas , 2002, International Journal of Computer Vision.

[5]  Udo Wehner,et al.  Aufbau und Auslegung eines Lane Keeping Systems / Design and application of a lane keeping system , 2003 .

[6]  Reinhold Behringer,et al.  Visuelle Erkennung und Interpretation des Fahrspurverlaufes durch Rechnersehen für ein autonomes Strassenfahrzeug , 1997 .

[7]  G. Wanielik,et al.  Hough transformation based approach for road border detection in infrared images , 2004, IEEE Intelligent Vehicles Symposium, 2004.

[8]  Jean-Philippe Tarel,et al.  On the design of a single lane-markings detectors regardless the on-board camera's position , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[9]  Alfred O. Hero,et al.  Simultaneous detection of lane and pavement boundaries using model-based multisensor fusion , 2000, IEEE Trans. Intell. Transp. Syst..

[10]  Romuald Aufrère,et al.  Accurate road following and reconstruction by computer vision , 2002, IEEE Trans. Intell. Transp. Syst..

[11]  Alexander Zelinsky,et al.  Robust vision based lane tracking using multiple cues and particle filtering , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[12]  Uwe Franke,et al.  System architecture for an intersection assistant fusing image, map, and GPS information , 2003, IEEE IV2003 Intelligent Vehicles Symposium. Proceedings (Cat. No.03TH8683).

[13]  A Kirchner,et al.  MODEL BASED DETECTION OF ROAD BOUNDARIES WITH A LASER SCANNER , 1998 .