Real-time video-based lane tracing system with the sliding focus window

Lane tracing is the problem of estimating the geometric shape of the lane boundaries based on the image grabbed by a camera on board a vehicle. In this paper, a real-time video-based lane detection method is presented. By analysing the result of lane tracing, the behaviour of the vehicle is traced and the focus windows are placeable, which provides useful information to the next round detection recursively. The system is porting on both PC and iPhone 3G to verify the recognition rate and performance through field testing. With the knowledge of road model, it is applicable to the marked and the unmarked roads, as well as the dash and the solid paint line roads. Experimental results show that the proposed method is robust and the performance is capable for practical applications.