Edge detection of street trees in high-resolution remote sensing images using spectrum features

In this paper a method of Fourier spectrum features based edge detection of urban street trees is described. The QuickBird image was first transformed by 2-D discrete Fourier transform. Then the energy of the component in spatial frequency was calculated. The energy distribution of the angle in max energy was used for further study. Different frequency segments was analyzed, the frequency that can best describe the street tree edge was chosen as the cut-off frequency of the street trees edge. Odd Gabor filter in frequency domain with the cut-off frequency and the max-energy angle was applied for the edge detection. The road center line is extracted by a Gabor filter in frequency domain. Then the edge of the street trees is restricted by the road center line. The edge detection result is analyzed by Canny criteria, and the ΣV=1.00, and C=0.89.