Real-time road-scene classification based on a multiple-lane tracker

A vision-guided autonomous vehicle is taken as an example for studying problems related to real-time recognition and classification of well-marked highway scenes. An algorithm is proposed, that is able to detect and to track the vehicle's lane, to search for additional lanes, and to classify the localized lane markers as solid or broken. On this basis a symbolic scene description is generated including the number of available lanes, which is visualized as a bird's eye view. Also, results from real-time tests of the algorithm, implemented in the vision system BVV 3, with several different highway-scenes are reported.<<ETX>>

[1]  Volker Graefe,et al.  Visual Recognition of Traffic Situations by a Robot Car Driver , 1992, Singapore International Conference on Intelligent Control and Instrumentation [Proceedings 1992].

[2]  K. P. Wershofen,et al.  An approach to the robust classification of pathway images for autonomous mobile robots , 1992, [1992] Proceedings of the IEEE International Symposium on Industrial Electronics.

[3]  Klaus Peter Wershofen,et al.  A Real-Time Multiple Lane Tracker for an Autonomous Road Vehicle , 1992 .

[4]  Martial Hebert,et al.  Vision and navigation for the Carnegie-Mellon Navlab , 1988 .

[5]  Volker Graefe,et al.  Dynamic monocular machine vision , 1988, Machine Vision and Applications.

[6]  Volker Graefe,et al.  The Bvv-Family of Robot Vision Systems , 1990, Proceedings of the IEEE International Workshop on Intelligent Motion Control.

[7]  Erik L. Dagless,et al.  Road edge tracking for robot road following: a real-time implementation , 1990, Image Vis. Comput..