In the last few years, driver-assistance systems are increasingly being investigated in automotive field to provide a higher degree of comfort and safety. Lane position determination plays a critical role toward the development of autonomous and computer-aided driving. This paper presents an accurate and robust method for detecting lateral road marking with applications in autonomous vehicles and driver support systems. Much like other lane detection systems, ours is based on computer vision and Hough transform. Our approach, however, is unique in that it combines geometrical and intensity information of the image, based on a fuzzy logic inference system implementing in-depth understanding of different driving and environmental conditions. We call it Fuzzy Logic lane (FLane) tracking system. Details of the main components of the FLane module are presented along with experimental results obtained under varying lighting and road conditions. It is shown that the proposed method is reliable and effective in detecting road border and can be successfully employed for driver assistance.
Effective Development of Fuzzy-Logic Rules for Real-time Control of Autonomous Vehicles
