Research Of Road Detection In Vision Navigation

Recent years, Intelligent Vehicle System has become a new field which attracts more attention over the world, where Vision Navigation System should detect the running environment and locate the boundary of the road in real-time so as to guarantee the intelligent vehicle to drive autonomously steadily and safely without manual operation.For structural road, this paper primarily studies the problem about the road detection and adopts following operations sequences: image processing, image edge detection, road edge extraction used Hough transform. Secondly do a research on the road detection algorithm. The algorithm includes two main steps: searching of the white line starting points and window-following of lane. The test result are given, which show that our algorithm is efficient in detecting solid and broken, clear and blurred white lane under all kinds of illumination environment.For nonstructural road, the method avoids analyzing each pixel of image. Performs with less calculation and higher speed, and satisfies robust real-time basically. It also resists the effect of shadows and water marks.Finally uses SVM to do road detection. Using SVM to solve the classification problems promote the precision of the detection.