The building recognition of high resolution satellite remote sensing image based on wavelet analysis

This paper imported wavelet analysis and wavelet descriptor into the building recognition of high resolution satellite remote sensing image, and brought forward the building recognition method based on wavelet descriptor in theory: firstly used wavelet analysis to do image segmentation in order to wipe off the large blocks of vegetation area in the image, then used dyadic wavelet to extract the edge, and used coordinate wavelet descriptor to describe the detected building contour, after that, computed the affine invariants to recognize the buildings, at last employed shadow validating to ascertain if the detected edge was the real building edge. This paper also constructed the building recognition pattern database, and used a QuickBird RS image of Peking University to do the experiment and the experimental result proved the feasibility of the method.