Early-exit optimization using mixed norm despeckling for SAR images

Speckle noise which is inherent to Synthetic Aperture Radar (SAR) imaging obstructs various image exploitation tasks such as edge detection, segmentation, change detection, and target recognition. Speckle reduction is generally used as a first step which has to smooth out homogeneous regions while preserving edges and point scatterers. In remote sensing applications, efficiency of computational load and memory consumption of despeckling must be improved for SAR images. In this paper, an early-exit total variation approach is proposed and this approach combines the l₁-norm and the l₂-norm in order to improve despeckling quality while keeping execution times of algorithm reasonably short. Speckle reduction performance, execution time and memory consumption are shown using spot mode SAR images.