Segmentation of satellite SAR images using squeeze and attention based deep networks

Abstract

Automatic extraction of objects of interests from high-resolution satellite images has been an active research area. Numerous recent papers have investigated on various deep learning-based semantic segmentation techniques for improved seg-mentation accuracy. Despite the fact that existing literature provides a wealth of information on land cover and land use (e.g., segmentation of structures, roads, and water area), the majority of them have been focused on segmentation on electro-optical-based (EO) images. A recent focus has been segmenting such ob-jects of interest in Synthetic-Aperture-Radar-based (SAR) images to overcome the limitations of using the visible spectrum. While the optical data taken at the visible spectrum is still widely preferred and used in many aerial applications, such applications typically need a clear sky and minimal cloud cover in order to function with high accuracy. SAR imaging is particularly useful as an alterna-tive imaging technique to alleviate such visibility-related problems such as when weather and cloud may obscure conventional optical sensors (as in during severe weather conditions and cloud cover). Recent segmentation techniques use multi-ple deep solutions based on U-Net. Recent attention based developments in deep learning when combined with the SAR image features, segmentation of objects of interests can be increased especially under low visibility conditions. In this thesis, a squeeze and attention based network is proposed for semantic segmentation in satellite SAR images. In particular, we show how squeeze and attention concept can be used within a U-Net based architecture for segmenting objects of interests in remote sensing images and study its performance on multiple public datasets. Our experiments demonstrate our proposed method yields superior results when compared to multiple baseline networks on all the used datasets.