FLane: An Adaptive Fuzzy Logic Lane Tracking System for Driver Assistance

摘要

In the last few years, driver assistance systems are increasingly being investigated in thenautomotive field to provide a higher degree of safety and comfort. Lane position determinationnplays a critical role toward the development of autonomous and computer-aidedndriving. This paper presents an accurate and robust method for detecting road markingsnwith applications to autonomous vehicles and driver support. Much like other lane detectionnsystems, ours is based on computer vision and Hough transform. The proposednapproach, however, is unique in that it uses fuzzy reasoning to combine adaptively geometricalnand intensity information of the scene in order to handle varying driving andnenvironmental conditions. Since our system uses fuzzy logic operations for lane detectionnand tracking, we call it “FLane.” This paper also presents a method for building theninitial lane model in real time, during vehicle motion, and without any a priori information.nDetails of the main components of the FLane system are presented along withnexperimental results obtained in the field under different lighting and road conditions.