Blind estimation of speckle characteristics for sentinel polarimetric radar images
Victoriya Abramova, Sergey Abramov, Владимир Васильевич Лукин, Karen Egiazarian · 2017
A priori knowledge on noise characteristics is important for image processing applications in remote sensing. Although their estimation is sometimes possible in an interactive mode, blind estimation is becoming actual nowadays. For radar images, one needs to accurately estimate speckle variance. In this paper, we propose a blind and fully automatic method to perform such an estimation. One of the advantages of this method is that it is applicable for spatially correlated speckle often taking place in practice. The proposed method is applicable for multichannel data processing since it analyzes data in blocks of difference images. We have verified the proposed method on dual-polarization Sentinel-1 radar images and have obtained the results of high accuracy.