Vision-Based Lane Keeping - A Survey

Several intelligent transportation system applications, such as automatic steering systems, lane departure warning systems, and driver performance monitoring systems, depend on obtaining accurate estimates of the vehicle's trajectory with respect to the lane the vehicle is driving in. However, lane marking detection and tracking using video or laser sensors tend to be extremely noisy, requiring robust methods for lane marking detection and tracking. Therefore, it has been an active field of research for decades. In this paper, we survey methods for detecting lane marking as well as tracking lane boundaries in real time focusing on vision-based system. We present a generic problem and elaborate the broad ranged proposed method in vision-based system. Finally, we identify these gaps and recommend research direction that may bridge them.