The application of SVD-based speckle reduction and Tophat Transform in preprocessing of ship detection

In this paper, the SVD (Singular Value Decomposition) and Tophat Transform is applied in the preprocessing of the ship detection in SAR images. First, Using Singular Value Decomposition and reconstruction, the speckle can be greatly reduced while the details of the images will be mostly kept. Furthermore, by using Tophat Transform, The local background non-homogeneity caused by waves is greatly reduced. The Signal-to-Clutter-Rate (SCR) of the images is greatly enhanced, which is favor for detection. The simulation results prove the algorithm´s effectiveness.