Single Image Super-resolution with a Switch Guided Hybrid Network for Satellite Images

TL;DR

This paper explores a hybrid super-resolution network for satellite images that uses a switch classifier to select the best model for different patch types, improving resolution and object identification.

Contribution

It introduces a switch-guided hybrid network that automatically chooses the optimal super-resolution model for different satellite image patches.

Findings

Hybrid network improves super-resolution quality.

Switch classifier effectively categorizes patches.

Enhanced object recognition in satellite images.

Abstract

The major drawbacks with Satellite Images are low resolution, Low resolution makes it difficult to identify the objects present in Satellite images. We have experimented with several deep models available for Single Image Superresolution on the SpaceNet dataset and have evaluated the performance of each of them on the satellite image data. We will dive into the recent evolution of the deep models in the context of SISR over the past few years and will present a comparative study between these models. The entire Satellite image of an area is divided into equal-sized patches. Each patch will be used independently for training. These patches will differ in nature. Say, for example, the patches over urban areas have non-homogeneous backgrounds because of different types of objects like vehicles, buildings, roads, etc. On the other hand, patches over jungles will be more homogeneous in nature. Hence, different deep models will fit on different kinds of patches. In this study, we will try to explore this further with the help of a Switching Convolution Network. The idea is to train a switch classifier that will automatically classify a patch into one category of models best suited for it.