Super resolution of DS-2 satellite imagery using deep convolutional neural network

Nour Aburaed*, Alavi Panthakkan, Saeed Almansoori III, Hussain Al-Ahmad

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution book

8 Citations (Scopus)
16 Downloads (Pure)

Abstract

Nowadays, Satellite images are used for various analysis, including building detection and road extraction, which are directly beneficial to governmental applications, such as urbanization and monitoring the environment. Spatial resolution is an element of crucial impact on the usage of remote sensing imagery. High spatial resolution means satellite images provide more detailed information. To improve the spatial resolution at the sensor level, many factors are ought to be taken into consideration, such as the manufacturing process. Moreover, once the satellite is launched, no further action can be taken from the perspective of hardware. Therefore, a more practical solution to improve the resolution of a satellite image is to use Single Image Super Resolution (SISR) techniques. This research proposal deals with the re-design, implementation, and evaluation of SISR technique using Deep Convolutional Neural Network with Skip Connections and Network in Network (DCSCN) for enlarging multispectral remote sensing images captured by DubaiSat-2 (DS-2) and estimating the missing high frequency details. The goal is to achieve high performance in terms of quality, and to test whether training the network using luminance channel only, which is extracted from YCbCr domain, can achieve high quality results. For this purpose, DCSCN is trained, evaluated, and tested using a dataset collected from DS-2. A single low resolution DS-2 image is used to construct its high resolution version by training the model from scratch and fine-tuning its hyper-parameters to produce optimal results. The performance is evaluated using various quality indices, such as Structural Similarity Index Measurement (SSIM), Peak Signal-to-Noise Ratio (PSNR), and Wavelet domain Signal-to-Noise Ratio (WSNR). The performance is compared to other state-of-the-art methods, such as Bil-inear, Bi-cubic, and Lanczos interpolation.

Original languageEnglish
Title of host publicationImage and Signal Processing for Remote Sensing XXV
EditorsLorenzo Bruzzone, Francesca Bovolo, Jon Atli Benediktsson
Place of PublicationBellingham
Volume11155
ISBN (Electronic)9781510630130
DOIs
Publication statusPublished - 7 Oct 2019
EventImage and Signal Processing for Remote Sensing XXV 2019 - Strasbourg, France
Duration: 9 Sept 201911 Sept 2019

Publication series

NameProceedings of SPIE - The International Society for Optical Engineering
Volume11155
ISSN (Print)0277-786X
ISSN (Electronic)1996-756X

Conference

ConferenceImage and Signal Processing for Remote Sensing XXV 2019
Country/TerritoryFrance
CityStrasbourg
Period9/09/1911/09/19

Keywords

  • deep learning
  • image reconstruction
  • multispectral
  • peak signal to noise ratio (PSNR)
  • structure similarity index measurement (SSIM).
  • super resolution
  • wavelet domain signal to noise ratio (WSNR)

Fingerprint

Dive into the research topics of 'Super resolution of DS-2 satellite imagery using deep convolutional neural network'. Together they form a unique fingerprint.

Cite this