Road Detection in Urban Areas Using High-Resolution Satellite Images and Lidar Data Based on Fuzzy Nearest-Neighbor Classification and Optimal Features

Automatic roads detection 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. For road detection, panchromatic or multi-spectral images, especially in urban areas, will yield ambiguous results, due to the additional complexities. For example, in an aerial photo or a high-resolution satellite image, both roads and buildings will appear similar, because their construction materials are usually the same. As a result, they cannot be readily distinguished. This becomes worse when they are in shadow or covered by roofs or walls of tall buildings. Accordingly, neither automatic nor semi-automatic methods will be entirely reliable in these dense urban areas. Moreover, the outputs of methods that use 2D images are more ambiguous than those with 3D inputs. Lidar point data have the potential to distinguish 3D features from one another, to distinguish 3D from 2D, and to distinguish 2D features from one another. However, Lidar intensity data are affected by a high amount of noise, and therefore are unable to distinguish roads from features with similar return signal power. Consequently, the full potential of the Lidar data cannot be exploited from raw data. Combining these two kinds of complementary data sources seem to be reasonably promising for road extraction, 3D urban modeling, etc. The main idea behind the integration of Lidar and optical imagery is that the strengths of one data type can compensate for the weaknesses of others. For example, being short of spectral information, Lidar data have high classification confusion between human-made and natural objects, whereas multispectral data have increasing classification confusion between spectrally identical objects in complex urban landscapes. In the light of these findings, in this paper, highresolution 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 ruleoriented strategy based on a masking approach. A supplementary strategy based on optimal design features was also used. Accordingly in the vegetation class, the accuracy was 93% and 93% for the producer and user accuracies respectively. In the case of the high road class, the accuracy 91 % and 84% and in the buildings class, the accuracy was 93% and 93% for the producer and user accuracies, respectively. In the low roads class, the accuracy 89% and 86% and in the open-space class, the accuracy was 80 % and 85% for the producer and user, respectively. Finally the overall precision of class identification is 90 % 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.