| In this work, we proposed a new line detection method to detect roads in aerial imagery. In our approach, we applied the wavelet transform in a multiresolution sense by forming the products of wavelet coefficients at the different scales to locate and identify lines at different scales. Then, we used a nonmaxima suppression technique to remove line pixels. Finally, we used hysteresis thresholding to detect strong and weak lines, in support of drawing a complete road network. We found that our approach for road feature extraction from aerial imagery yields promising results. Therefore, our approach leads to an effective method to form the basis of an automated feature extraction approach. |
