Vision-based lane departure detection system in urban traffic scenes

A lane-departure detection system without intrinsic and extrinsic camera parameters calibration is proposed in this paper. The proposed system, which provides driving safety by lane detection and lane departure warning, is focused on urban road with complicated lane marks instead of simple highway scenes. Due to the complexity of urban traffic scenes, false lane detections are highly caused by warning lines and signs whose shape and color are similar to the lane boundary. In this study, two lane features, lane width and lane boundary continuity, are proposed to obtain reliable and quality lane detected results on urban traffic scenes. Lane departure warning decisions are then applied to provide driving safety. Experimental results of urban road sceneries have demonstrated feasibility and robustness of the proposed method.