Abstract

Satellite remote sensing imagery currently sits at the heart of many applications and has been the leading technique for marine/land monitoring and surveillance purposes due to its capability to capture wide-angle area imagery under challenging weather conditions and for various sea states. Among those remote sensing techniques, synthetic aperture radar (SAR) imagery is one of the most important ones with its all-weather, cloud-free and day-night data collection properties. SAR can provide useful information in a multitude of applications, including climate change, environmental monitoring, meteorology, high dimensional mapping, ship monitoring, or planetary exploration. In this talk, we discuss current advances in solutions to a number of inverse problems encountered in SAR imaging such as ship wake detection, despeckling, super-resolution and image formation. The techniques covered will include some model-based approaches such as proximal splitting algorithms along with some seminal data-driven machine-learning approaches.