No abstract

Abstract. This paper presents a Road Detection and Classification algorithm for Driver Assistance Systems (DAS), which tracks several road lanes and identifies the type of lane boundaries. The algorithm uses an edge filter to extract the longitudinal road markings to which a straight lane model is fitted. Next, the type of right and left lane boundaries (continuous, broken or merge line) is identified using a Fourier analysis. Adjacent lanes are searched when broken or merge lines are detected. Although the knowledge of the line type is essential for a robust DAS, it has been seldom considered in previous works. This knowledge helps to guide the search for other lanes, and it is the basis to identify the type of road (one-way, two-way or freeway), as well as to tell the difference between allowed and forbidden maneuvers, such as crossing a continuous line.

Vision-based Driver Assistance Systems need to establish a correspondence between the position of the objects on the road, and its projection in the image. Although intrinsic parameters can be calibrated before installation, calibration of extrinsic parameters can only be done with the cameras mounted in the vehicle. In this paper the self-calibration system of the IVVI (Intelligent Vehicle based on Visual Information) project is presented. It pretends to ease the process of installation in commercial vehicles. The system is able to self calibrate a stereo-vision system using only basic road infrastructure.

Human errors are the cause of most traffic accidents, with drivers' inattention and wrong driving decisions being the two main sources. These errors can be reduced, but not completely eliminated. That is why Advanced Driver Assistance Systems (ADAS) can reduce the number, danger and severity of traffic accidents. Several ADAS, which nowadays are being researched for Intelligent vehicles, are based on Artificial Intelligence and Robotics technologies. In this article a research platform for the implementation of systems based on computer vision is presented, and different visual perception modules useful for some ADAS such as Line Keeping System, Adaptive Cruise Control, Pedestrian Protector, or Speed Supervisor, are described.

a Absmzct-This paper presents a Road Lanes Detection and Interpretation algorithm for Driver Assistance Systems @AS). The algorithm uses an edge filter to extract fane borders to which a straight lane model is fitted. Next, the lane mark type (continuous, discontinuous or merge) is recognized using a Fourier analysis. The Une type is essentiaI for a robust DAS. Nevertheless, it has been seldom considered in previous works. The knowledge of the line types of the road helps to guide the search for other lines, to automaticatly detect the type of the road (one-way, two way or highway), and to telt the difference between atlowed and forbidden maneuvers, such as crossing a continuous line, Furthermore, the system is able to auto calibrate, thus easing the process of installation in commercial vehicles.