An approach of rapidly computing the projective width of lanes is presented to predict the projective positions and widths of lanes. The Lane Marking Extraction Finite State Machine is designed to extract points with features of lane markings in the image, and a cubic B-spline is adopted to conduct curve fitting to reconstruct road geometry. A statistical search algorithm is also proposed to correctly and adaptively determine thresholds under various kinds of illumination conditions. Furthermore, the parameters of the camera in a moving car may change with the vibration, so a dynamic calibration algorithm is applied to calibrate camera parameters and lane widths with the information of lane projection. Moreover, a fuzzy logic is applied to determine the situation of occlusion. Finally, a region-of-interest determination strategy is developed to reduce the search region and to make the detection more robust with respect to the occlusion on the lane markings or complicated changes of curves and road boundaries.
