Road network extraction from high-resolution satellite image for GIS applications

Abstract

Automatic extraction of roads from digital images has been an active research subject for over a decade because its significant role in many application area, like Intelligent Transportation Systems (ITS) and transportation navigation as well as GIS applications. Especially, road network is one of most important features in GIS layer. Traditionally, surveying and photogrammetry are the only ways to map details in urban areas even though it is well known that they are resource and time consuming. Recently, high-resolution satellite image has become widely available, and moreover, several high-resolution satellite images have become commercially available for civilian applications, due to the development of remote sensors and satellite technologies. This shows an opportunity for so-called urban remote sensing to challenge the topic of urban details mapping. The focus of this paper is on developing an approach for extracting urban and suburban road network from high-resolution satellite image. “Road mask” is defined in this research as a mask of road pixels, which are discriminated from others using commercial remote sensing software. “Road seed” is defined in this research as a directional point, indicating that a road is passing through the point along the direction. Road seeds are extracted from edge pixels. Road line extraction is conducted in a semi-automatic way by fusing both road mask and road seeds. Experiments are conducted using an IKONOS image with a ground resolution of 1 meter, and four bands, i.e. red, green, blue, and near infrared. Experimental results show that the method is valid in extracting main roads in high dense building area and most of the roads in countryside efficiently. Besides the general description of the approach, this paper describes the newly proposed line segment match method in detail.