Lane mark segmentation method based on maximum entropy

In order to realize lane mark identifying and tracking on such conditions as uneven road surface materials and different illumination etc, this paper proposes a new method which combines an image segmentation technique based on maximum entropy with a bi-normalized adjustable template. First, applying image window variation technology, this method first realizes the better road image segmentation based on maximize one-dimension entropy. Second, lane mark parameters can be acquired based on the bi-normalized adjustable template. Finally lane mark real-time tracking is realized by applying trapezia AOI method.