Abstract
Video sensors constitute a great innovation in the automotive sector and road safety as they contribute to the development of driver assistance systems. These video systems use image processing techniques to inform drivers of impending dangers. One such development is the Lane Departure Warning System (LDWS) which play a key role in the prevention from accidents. The main function of this system is the detection of lane boundary lines using artificial vision.
In this paper, we present a feature-based method for lane detection. We simplify the process of edge detection by using a horizontal differencing filter. The detected edge points are grouped into lines with a modified Hough transform.