Thanks to the removal of the perspective effect, in a remapped image lane markings are represented by almost vertical bright lines of constant width, surrounded by a darker background. Thus the first phase of lane detection is based on the search for dark-bright-dark horizontal patterns with a given size. Every pixel is compared to its left and right horizontal neighbors at a given distance and a new grey-level image is computed. This image encodes the horizontal brightness transitions and the presence of lane markings. Different illumination conditions, such as shadows or sunny blobs, cause road markings to assume different brightness values; anyway the pixels corresponding to the lane markings maintain a brightness value higher than their horizontal neighbors. In addition, taking advantage of lane markings vertical correlation, the image is enhanced (figure 3.a) through few iterations of a geodesic morphological dilation.
Different illumination conditions and the nonuniformity of painted road signs require the use of an adaptive threshold that works on a 3 x 3 pixel neighborhood.