Fast Algorithm for Structured and Unstructured Road Detection

This paper presents a fast algorithm to detect the road lines and the road edges of structured and unstructured roads, respectively. In structured road detection, we firstly utilize vertical Sobel mask and color characteristic to detect the points of road lines. If the number of points is greater than a predefined threshold, we refine the detection results with slope filtering. And the least square approximation is employed to represent the road lines. The unstructured road detection starts while the number of detected points is not enough. We extract the road surface with the predefined sets of sampled blocks, and obtain the edge points from the vertical intervals. For the accuracy of detection, the new sampled set values are updated by the random sampling points from segmented regions.