Deep generative model for remote sensing

The practice of identifying and monitoring an area's physical features by detecting its reflected and transmitted radiation from a distance is known as remote sensing (typically from satellite or aircraft). Researchers can "sense" characteristics about the Earth by using special camer...

Full description

Saved in:
Bibliographic Details
Main Author: Kok, Melvin Xinwei
Other Authors: Wen Bihan
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/158052
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-158052
record_format dspace
spelling sg-ntu-dr.10356-1580522023-07-07T19:27:39Z Deep generative model for remote sensing Kok, Melvin Xinwei Wen Bihan School of Electrical and Electronic Engineering bihan.wen@ntu.edu.sg Engineering::Electrical and electronic engineering The practice of identifying and monitoring an area's physical features by detecting its reflected and transmitted radiation from a distance is known as remote sensing (typically from satellite or aircraft). Researchers can "sense" characteristics about the Earth by using special cameras to acquire remotely sensed imagery. While the concept of satellite imagery would bring typical Electro-Optical (EO) Red Green Blue (RGB) images to mind, in remote sensing, there are many other important computational imaging systems such as synthetic aperture radar imaging (SAR), multispectral image fusion, as well as infra-red imaging. These non-EO-RGB imaging systems all have their unique advantages and properties, but the most common imaging system is SAR imaging, which is the focus of this project. SAR imaging is particularly useful due to its ability to always captures image of the Earth’s surface, regardless of day and night, and regardless of weather condition. This is in contrast to the EO imagery, whose quality is subject to changes in illumination from the sun and also changes in weather conditions like cloud cover. However, unlike EO images which have good availability due to large commercial projects (e.g., Google Maps), SAR image data is more scarce and more expensive to obtain. In the project, image-to-image translation is performed on EO images to transfer them to the SAR domain to provide more data for machine learning models on learn on SAR datasets. To transfer large-scale optical RGB images to the desired imaging modality i.e., SAR, a series of image-to-image translation techniques based on GANs were tested. These techniques include Pix2Pix and CycleGAN. Through testing, it was determined that using GANs to perform image-to-image translation on satellite imagery was possible but requires refining to capture all the features from the source domain adequately. Bachelor of Engineering (Electrical and Electronic Engineering) 2022-05-26T06:09:02Z 2022-05-26T06:09:02Z 2022 Final Year Project (FYP) Kok, M. X. (2022). Deep generative model for remote sensing. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158052 https://hdl.handle.net/10356/158052 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
Kok, Melvin Xinwei
Deep generative model for remote sensing
description The practice of identifying and monitoring an area's physical features by detecting its reflected and transmitted radiation from a distance is known as remote sensing (typically from satellite or aircraft). Researchers can "sense" characteristics about the Earth by using special cameras to acquire remotely sensed imagery. While the concept of satellite imagery would bring typical Electro-Optical (EO) Red Green Blue (RGB) images to mind, in remote sensing, there are many other important computational imaging systems such as synthetic aperture radar imaging (SAR), multispectral image fusion, as well as infra-red imaging. These non-EO-RGB imaging systems all have their unique advantages and properties, but the most common imaging system is SAR imaging, which is the focus of this project. SAR imaging is particularly useful due to its ability to always captures image of the Earth’s surface, regardless of day and night, and regardless of weather condition. This is in contrast to the EO imagery, whose quality is subject to changes in illumination from the sun and also changes in weather conditions like cloud cover. However, unlike EO images which have good availability due to large commercial projects (e.g., Google Maps), SAR image data is more scarce and more expensive to obtain. In the project, image-to-image translation is performed on EO images to transfer them to the SAR domain to provide more data for machine learning models on learn on SAR datasets. To transfer large-scale optical RGB images to the desired imaging modality i.e., SAR, a series of image-to-image translation techniques based on GANs were tested. These techniques include Pix2Pix and CycleGAN. Through testing, it was determined that using GANs to perform image-to-image translation on satellite imagery was possible but requires refining to capture all the features from the source domain adequately.
author2 Wen Bihan
author_facet Wen Bihan
Kok, Melvin Xinwei
format Final Year Project
author Kok, Melvin Xinwei
author_sort Kok, Melvin Xinwei
title Deep generative model for remote sensing
title_short Deep generative model for remote sensing
title_full Deep generative model for remote sensing
title_fullStr Deep generative model for remote sensing
title_full_unstemmed Deep generative model for remote sensing
title_sort deep generative model for remote sensing
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/158052
_version_ 1772829063102070784