Automated Detection in SAR Images by Using Wavelet Filtering and Hough Transform

摘要

A novel method of automatic detection of straight lines in Synthetic Aperture Radar (SAR) images is presented in this paper. The proposed technique has been tested on a simulated SAR image, and on a real SAR image. It is based on the joint exploitation of a Wavelet Filtering Algorithm (WFA) and Hough Transform (HT) to extract geometric regular features and to detect lineaments in the considered image. The detail images produced by the proposed Wavelet Filtering Algorithm have the same resolution as the original image. The algorithm has been integrated with a moving mask method on the detected lines in order to find the beginning and the end of the segments. The experiment shows that it has a more efficient tool with respect to the traditional approach.