In this paper a fully automatic road detection algorithm is introduced. It comprises of pre-processing the image via a series of wavelet based filter banks and reducing the yielding data into a single image which is of the same size as the original optical grayscale satellite image, then utilizing a fuzzy inference algorithm to carry out the road detection which can then be used as an input to a geographical information system for cartographic or for other purposes that are in need. We use a trous algorithm twice with two different wavelet bases in order to filter and de-noise the satellite image. Each wavelet function resolves features at a different resolution level associated with the frequency response of the corresponding FIR filter. Resulting two images are fused together using Karhounen-Louve transform (KLT) which is based on principal component analysis (PCA). This process underlines the prominent features of the original image as well as de-noising it, since the prominent features appear in both of the wavelet transformed images while noise does not strongly correlate between scales. Next a fuzzy logic inference algorithm which is based on statistical information and on geometry is used to extract the road pixels.
Fully Automatic Road Network Extraction from Satellite Images
01.06.2007
5496645 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch