Loading [MathJax]/extensions/MathMenu.js
Generative Adversarial Network with Residual Dense Generator for Remote Sensing Image Super Resolution | IEEE Conference Publication | IEEE Xplore

Generative Adversarial Network with Residual Dense Generator for Remote Sensing Image Super Resolution


Abstract:

Improving image resolution, especially spatial resolution, has been one of the most important concerns on remote sensing research communities. An efficient solution for i...Show More

Abstract:

Improving image resolution, especially spatial resolution, has been one of the most important concerns on remote sensing research communities. An efficient solution for improving spatial resolution is by using algorithm, known as super-resolution (SR). The super-resolution technique that received special attention recently is super-resolution based on deep learning. In this paper, we propose deep learning approach based on generative adversarial network (GAN) for remote sensing images super resolution. We used residual dense network (RDN) as generator network. Generally, deep learning with residual dense network (RDN) gives high performance on classical (objective) evaluation metrics meanwhile generative adversarial network (GAN) based approach shows a high perceptual quality. Experiment results show that combination of residual dense network generator with generative adversarial network training is found to be effective. Our proposed method outperforms the baseline method in terms of objective and perceptual quality evaluation metrics.
Date of Conference: 18-20 November 2020
Date Added to IEEE Xplore: 25 December 2020
ISBN Information:
Conference Location: Tangerang, Indonesia

I. Introduction

Remote sensing is the process of obtaining information about targeted objects or areas by measuring its reflected and emitted radiation from a distance. Remote sensing imaging can cover larger areas than other methods of telemetry data acquisition but it has low spatial resolution and very low in relation to the dimension of the sensed object. Higher resolution remote sensing images can be obtained by using better sensing devices, but it cost more. An effective way to increase image spatial resolution at lower cost is by using algorithm based approach, known as super-resolution (SR). SR in remote sensing applications is important because it can assist the visual interpretation of images in remote sensing application such as surveillance, target detection, agriculture, land use mapping, meteorology, etc.

References

References is not available for this document.