The road network is of great importance to the modern traffic system, which changes frequently as its high speed of development. Simultaneously, a growing number of satellites provide a considerable number of remote sensing images that can be used for road extraction. However, most existing methods cannot get accurate results in the high-resolution remote sensing, since the complex background like the shadows and occlusions. Consequently, we proposed a method utilizing the volunteered geographic information data to extract the road from satellite images. At first, from Mapbox platform, the Volunteered Geographic Information data, OpenStreetMap vector tiles are collected to guide the downloading of corresponding road satellite images. Then a level set method is used to extract the road areas from the satellite images supported by the road vector. After that, a superpixel method is applied to improve the road areas by fusing the superpixels with the previous results. Experiments are performed on the satellite images from Mapbox, Google, and Yahoo in the Tianjin Port district on accuracy and efficiency. Experimental results demonstrate that our approach is more accurate and of higher performance than the other two state-of-the-art methods.

Aiming at producing the road labels for deep neural networks (DNNs), this letter proposes a graph-cut-based method to make road annotations on very high-resolution (VHR) remote-sensing images. With the aid of OpenStreetMap (OSM), a superpixel method and the graph cut method are employed for road segmentation. After that, the road areas are refined by the OSM. In this process, the road annotations are made automatically. In experiments, two traditional methods, two deep learning methods, and the proposed method are utilized to segment the roads on two types of satellite images in Tianjin port area. The results show that the proposed method creates more accurate and integrated road labels compared with other methods.