Zezhong Xu

Learn More
Lane detection, lane tracking, or lane departure warning have been the earliest components of vision-based driver assistance systems. At first (in the 1990s), they have been designed and implemented for situations defined by good viewing conditions and clear lane markings on highways. Since then, accuracy for particular situations (also for challenging(More)
Starting from the disadvantage and two research results of the convergence of the previous genetic algorithm, three operations are added to the standard genetic algorithm to make the algorithm converge to a global optimum without the change of the search randomicity. A path planning method is proposed using the fitness of the roadside constraint, dynamic(More)
Obstacle detection and road following are two foundational abilities in ALV autonomous navigation. Vision based method is not robust to different weather, illuminance, road surface condition. In this paper we use a laser rangefinder with four layers to implement obstacle detection and road following in outdoor environment. Obstacle detection is based on(More)
Lane-border detection is one of the best developed modules in vision-based driver assistance systems today. However, still there is a need to improve for challenging road and traffic situations, and also a need to design tools for quantitative performance evaluation. This paper discusses and refines a method to generate ground truth for lane markings from(More)
The Hough transform is a popular technique used in the field of image processing and computer vision. With a Hough transform technique, not only the normal angle and distance of a line but also the line-segment's length and midpoint (centroid) can be extracted by analysing the voting distribution around a peak in the Hough space. In this paper, a method(More)