Artefacts detection and removal in remote optical imageries using artificial intelligence

Satellite images have increasingly been used in many different fields, such as detecting and locating ground information, and are used to support fields like urban planning, navigation systems and disaster monitoring. The main problem with satellite images are artefacts or other objects, such as...

Full description

Saved in:
Bibliographic Details
Main Author: You, Zongtao
Other Authors: Lu Yilong
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2022
Subjects:
Online Access:https://hdl.handle.net/10356/158868
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-158868
record_format dspace
spelling sg-ntu-dr.10356-1588682023-07-04T17:48:27Z Artefacts detection and removal in remote optical imageries using artificial intelligence You, Zongtao Lu Yilong School of Electrical and Electronic Engineering EYLU@ntu.edu.sg Engineering::Electrical and electronic engineering Satellite images have increasingly been used in many different fields, such as detecting and locating ground information, and are used to support fields like urban planning, navigation systems and disaster monitoring. The main problem with satellite images are artefacts or other objects, such as clouds and cloud shadows, that appear in the taken image. These are difficult to detect and remove with increasing image resolution. In this dissertation, both artefact detection and removal are studied. Images are a combination of pixels with different values, and finding a suitable pixel value threshold will improve the ability to detect artefacts. Image inpainting is required after artefact removals to recover the image. In this dissertation two popular image inpainting methods are studied. EdgeConnect uses a two-step process to fix an image: first it generates an edge map of the broken image, and then completes the holes with the help of the generated edges. The Learnable Bidirectional Attention Maps (LBAM) algorithm leverages partial convolution and attention map, and it focuses on completing irregular holes rather than regenerating a whole image. Overall, both methods achieve acceptable results on satellite images that feature irregular holes. LBAM performs slightly better than EdgeConnect because it does not rely on the edge map. It is hard to properly generate the accurate edges of the buildings beneath the artefacts. Master of Science (Computer Control and Automation) 2022-05-31T05:31:00Z 2022-05-31T05:31:00Z 2022 Thesis-Master by Coursework You, Z. (2022). Artefacts detection and removal in remote optical imageries using artificial intelligence. Master's thesis, Nanyang Technological University, Singapore. https://hdl.handle.net/10356/158868 https://hdl.handle.net/10356/158868 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
You, Zongtao
Artefacts detection and removal in remote optical imageries using artificial intelligence
description Satellite images have increasingly been used in many different fields, such as detecting and locating ground information, and are used to support fields like urban planning, navigation systems and disaster monitoring. The main problem with satellite images are artefacts or other objects, such as clouds and cloud shadows, that appear in the taken image. These are difficult to detect and remove with increasing image resolution. In this dissertation, both artefact detection and removal are studied. Images are a combination of pixels with different values, and finding a suitable pixel value threshold will improve the ability to detect artefacts. Image inpainting is required after artefact removals to recover the image. In this dissertation two popular image inpainting methods are studied. EdgeConnect uses a two-step process to fix an image: first it generates an edge map of the broken image, and then completes the holes with the help of the generated edges. The Learnable Bidirectional Attention Maps (LBAM) algorithm leverages partial convolution and attention map, and it focuses on completing irregular holes rather than regenerating a whole image. Overall, both methods achieve acceptable results on satellite images that feature irregular holes. LBAM performs slightly better than EdgeConnect because it does not rely on the edge map. It is hard to properly generate the accurate edges of the buildings beneath the artefacts.
author2 Lu Yilong
author_facet Lu Yilong
You, Zongtao
format Thesis-Master by Coursework
author You, Zongtao
author_sort You, Zongtao
title Artefacts detection and removal in remote optical imageries using artificial intelligence
title_short Artefacts detection and removal in remote optical imageries using artificial intelligence
title_full Artefacts detection and removal in remote optical imageries using artificial intelligence
title_fullStr Artefacts detection and removal in remote optical imageries using artificial intelligence
title_full_unstemmed Artefacts detection and removal in remote optical imageries using artificial intelligence
title_sort artefacts detection and removal in remote optical imageries using artificial intelligence
publisher Nanyang Technological University
publishDate 2022
url https://hdl.handle.net/10356/158868
_version_ 1772829022622842880