Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning

It is widely known that optical satellite image is vulnerable to cloud contamination. Our task is to solve the problem of cloud removal by image blending based on the provided high-resolution composite images. The wide spread of machine learning, especially deep learning (DL), makes our problem solv...

Full description

Saved in:
Bibliographic Details
Main Author: Zhan, Hang
Other Authors: Lu Yilong
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/154878
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-154878
record_format dspace
spelling sg-ntu-dr.10356-1548782023-07-04T17:42:30Z Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning Zhan, Hang Lu Yilong School of Electrical and Electronic Engineering EYLU@ntu.edu.sg Engineering::Electrical and electronic engineering It is widely known that optical satellite image is vulnerable to cloud contamination. Our task is to solve the problem of cloud removal by image blending based on the provided high-resolution composite images. The wide spread of machine learning, especially deep learning (DL), makes our problem solvable. We put forward a framework to leverage the advantages of Generative Adversarial Networks (GAN) and the traditional gradient-based method. Concretely, Gaussian-Poisson Equation is employed to formulate the problem of high-resolution image blending, which can be regarded as a joint optimization constrained by image color and gradient information. In our work, two deep learning models were built and tested. Firstly, to obtain the color constraint, we put forward a model named Blending GAN to learn the mapping between the composite images and the well-blended ones, which could generate lowresolution but realistic images. Secondly, we can obtain gradient constraint using the gradient filter. However, the discontinuity may exist in the gradient map due to inaccurate image composition. As we know, the Synthetic Aperture Radar (SAR) data is attracting equal attention from both industry and academia. One major advantage is its robustness against cloud contamination. Hence, we propose a Gradient Repair GAN and explore the use of SAR data to produce more accurate gradient maps, which can be better used for following processing. After integration of color with gradient information based on Gaussian-Poisson Equation, the ultimate high-resolution well-blended image, i.e. cloudless images could be obtained. The final performance is numerically evaluated based on PSNR and shows promising performance Master of Science (Signal Processing) 2022-01-13T03:34:14Z 2022-01-13T03:34:14Z 2021 Thesis-Master by Coursework Zhan, H. (2021). Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/154878 https://hdl.handle.net/10356/154878 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
spellingShingle Engineering::Electrical and electronic engineering
Zhan, Hang
Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
description It is widely known that optical satellite image is vulnerable to cloud contamination. Our task is to solve the problem of cloud removal by image blending based on the provided high-resolution composite images. The wide spread of machine learning, especially deep learning (DL), makes our problem solvable. We put forward a framework to leverage the advantages of Generative Adversarial Networks (GAN) and the traditional gradient-based method. Concretely, Gaussian-Poisson Equation is employed to formulate the problem of high-resolution image blending, which can be regarded as a joint optimization constrained by image color and gradient information. In our work, two deep learning models were built and tested. Firstly, to obtain the color constraint, we put forward a model named Blending GAN to learn the mapping between the composite images and the well-blended ones, which could generate lowresolution but realistic images. Secondly, we can obtain gradient constraint using the gradient filter. However, the discontinuity may exist in the gradient map due to inaccurate image composition. As we know, the Synthetic Aperture Radar (SAR) data is attracting equal attention from both industry and academia. One major advantage is its robustness against cloud contamination. Hence, we propose a Gradient Repair GAN and explore the use of SAR data to produce more accurate gradient maps, which can be better used for following processing. After integration of color with gradient information based on Gaussian-Poisson Equation, the ultimate high-resolution well-blended image, i.e. cloudless images could be obtained. The final performance is numerically evaluated based on PSNR and shows promising performance
author2 Lu Yilong
author_facet Lu Yilong
Zhan, Hang
format Thesis-Master by Coursework
author Zhan, Hang
author_sort Zhan, Hang
title Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
title_short Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
title_full Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
title_fullStr Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
title_full_unstemmed Cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
title_sort cloud removal in optical remote sensing imagery based on multimodality image reconstruction using deep learning
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/154878
_version_ 1772828531547439104