Cloud detection and classification with artificial intelligence for satellite optical image

Cloud is a very common weather phenomenon in the world. For optical satellite imaging, it is very often that more than 50% of imaging areas are covered by clouds. It sounds easy but practically very challenging to detect clouds accurately without confusing the detection with white ground, including...

Full description

Saved in:
Bibliographic Details
Main Author: Yao, Yuhan
Other Authors: LU Yilong
Format: Thesis-Master by Coursework
Language:English
Published: Nanyang Technological University 2020
Subjects:
Online Access:https://hdl.handle.net/10356/141043
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-141043
record_format dspace
spelling sg-ntu-dr.10356-1410432023-07-04T16:31:09Z Cloud detection and classification with artificial intelligence for satellite optical image Yao, Yuhan LU Yilong School of Electrical and Electronic Engineering EYLU@ntu.edu.sg Engineering::Electrical and electronic engineering Cloud is a very common weather phenomenon in the world. For optical satellite imaging, it is very often that more than 50% of imaging areas are covered by clouds. It sounds easy but practically very challenging to detect clouds accurately without confusing the detection with white ground, including areas covered snow or ice. This project is to study and test innovative approaches for accurate detection and classification of clouds by applying machine intelligence and big data. The project scope includes the study of image processing fundamentals, literature review of machine intelligence and cloud detection, implementation of the proposed approach, collection of cloud and snow samples, test the implemented code and detailed analysis of the results, evaluation of the detection accuracy. Master of Science (Signal Processing) 2020-06-03T08:43:06Z 2020-06-03T08:43:06Z 2020 Thesis-Master by Coursework https://hdl.handle.net/10356/141043 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
Yao, Yuhan
Cloud detection and classification with artificial intelligence for satellite optical image
description Cloud is a very common weather phenomenon in the world. For optical satellite imaging, it is very often that more than 50% of imaging areas are covered by clouds. It sounds easy but practically very challenging to detect clouds accurately without confusing the detection with white ground, including areas covered snow or ice. This project is to study and test innovative approaches for accurate detection and classification of clouds by applying machine intelligence and big data. The project scope includes the study of image processing fundamentals, literature review of machine intelligence and cloud detection, implementation of the proposed approach, collection of cloud and snow samples, test the implemented code and detailed analysis of the results, evaluation of the detection accuracy.
author2 LU Yilong
author_facet LU Yilong
Yao, Yuhan
format Thesis-Master by Coursework
author Yao, Yuhan
author_sort Yao, Yuhan
title Cloud detection and classification with artificial intelligence for satellite optical image
title_short Cloud detection and classification with artificial intelligence for satellite optical image
title_full Cloud detection and classification with artificial intelligence for satellite optical image
title_fullStr Cloud detection and classification with artificial intelligence for satellite optical image
title_full_unstemmed Cloud detection and classification with artificial intelligence for satellite optical image
title_sort cloud detection and classification with artificial intelligence for satellite optical image
publisher Nanyang Technological University
publishDate 2020
url https://hdl.handle.net/10356/141043
_version_ 1772828905674113024