Urban road network extraction based on zebra crossing detection from a very high resolution RGB aerial image and DSM data

Recently, road network extraction in urban areas using high resolution data, has attracted many researchers because it is very challenging and important work in order to provide an intelligent spatial processing. In this work, we use two types of data: an extremely high-resolution image in which the signature of the road, such as zebra crossing, road lines, cars, and the like, can be seen in detail, and DSM data, which is based on the elevation of the surface. We propose a road extraction based on zebra crossings detection where there is a simple peculiar pattern to recognise. In this task, we employ a circle mask template matching and Speeded Up Robust Features (SURF) method in order to detect and evaluate the zebra crossing location in an RGB aerial image. These locations of zebra crossings represent the starting point of the road and we associate it to the corresponding DSM data to obtain the elevation information. In the DSM data, the elevation of the road and the building differ significantly, therefore, we expand the starting point based on a local thresholding and seeded region growing to create an initial road region quickly. Furthermore, we utilise morphological opening operation with a line shape structural element to produce the road line and remove the false alarms. The experimental result shows that the proposed method is run quick enough with good accuracy.