SAR Image Despeckling by Selective 3D Filtering of Multiple Compressive Reconstructed Images

A despeckling technique based on multiple image reconstruction and selective 3-dimensional filtering is proposed. Multiple SAR images are reconstructed from a single SAR image by employing compressive sensing (CS) theory. In order to obtain multiple images from single SAR image, multiple subsets of pixels are selected from input SAR image by imposing restriction that each subset has at least 20% different pixels than any other subset. These subsets are taken as measurement vectors in CS framework to obtain multiple SAR images. A despeckled image is obtained by employing selective 3-dimensional filtering to multiple reconstructed SAR image. The proposed technique is tested on single look complex TerraSAT-X data set, and experimental results exhibit that the proposed technique outperformed benchmark despekling methods in terms of visual quality and despeckling quality metrics.