Grid seeded region growing with Mixed ART for road extraction on DSM data

Region Growing with Mixed ART is one of the methods for road extraction based on segmentation processing. The method is based on Region Growing method but using ART approach as homogeneity measurement. However, a drawback of this method is time consuming. For road extraction problem, it is unnecessary to separate all the regions as in general segmentation approach. We only need some of the road data and then grow it to obtain the road network. In this paper, we proposed a grid seeded region growing with Mixed ART. Since the road will cross the grid, we can obtain the road network based on growing from these seed points. The experimental result shows that the proposed method performs faster up to four times than the conventional seed point with the similar quality. The accuracy of extracted road and non-road are 74% and 77% respectively.