A new method for road detection in urban areas using high-resolution satellite images and Lidar data based on fuzzy nearest-neighbor classification and optimal features

Abstract

Detection of roads in urban areas is of greater importance and is a persistent research focus in the remote sensing community. The spectral and geometrical varieties of road pixels; their spectral similarity to other features such as buildings, parking lots, and sidewalks; and the occasional obstruction by vehicles and trees are obstacles to the precise identification of urban roads through satellite images. Lidar data, however, provide height information that can facilitate the identification of roads from other spectrally similar elements. Therefore, Lidar has been widely used alongside satellite images to identify features such as roads. In this paper, high-resolution QuickBird satellite imagery and Lidar data processed through nearest-neighbor classification based on optimal features have been used together to extract various types of urban roads. This work designed and implemented a rule-oriented strategy based on a masking approach. A supplementary strategy based on optimal design features was also used. The overall precision of class identification is 91 % with a kappa coefficient of 0.87, which shows a satisfactory precision according to different conditions and considerable interclass noise. The final results demonstrate the high capability of object-oriented methods in simultaneous identification of a wide variety of road elements in complex urban areas using both high-resolution satellite imagery and Lidar data.