A RPCA and RANSAC Based Algorithm for Ship Wake Detection in SAR Images

摘要

We present a novel algorithm for ship wake detection in synthetic aperture radar (SAR) images with complex background. First, a sparse decomposition is implemented by the robust principal component analysis (RPCA) for the extrapolation of sparse objects of interest consisting of ship wakes. Then, to roughly detect linear features, the Radon transform is employed. The random sampling consensus (RANSAC) algorithm is subsequently utilized to find the actual wake position. Finally, the detection results are used for the estimation of ship heading and speed. Experimental results show that the proposed algorithm has high detection accuracy for linear wake features in complex background.