Automated Verification of Road Network Data by Vhr Satellite Images Using Road Statistics

A method is explored to assess the quality of road network data based on image information in a reliable and accurate way. Therefore, the quality of the image information resulting from a ridge extraction procedure is characterized in terms of detection rate. The optimal parameter set for the ridge extraction is predicted based on typical road samples extracted from the image, resulting in an optimal performance of the road detection. In the field of geography, an accuracy assessment method, called buffer-overlaystatistics, is known to assess the spatial quality of a line data set by using another line data set of higher spatial accuracy. Here, the method is adapted to assess the quality of a line data set based on image information rather than vector data. The average displacement accuracy measure is redefined, such that it is able to take into account line detection errors (fragmentation and noise). Experiments were conducted on IKONOS panchromatic and Quickbird multispectral satellite images.