Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches
We demonstrate how established applications and tools for image classification and change detection can profit from advanced information theory together with automated quality control strategies. As a typical example, we deal with the task of coastline detection in satellite images; here, rapid and...
Main Authors: | , , , , , |
---|---|
Other Authors: | , , , , , |
Format: | Book Part |
Language: | unknown |
Published: |
Springer Nature Switzerland AG
2020
|
Subjects: | |
Online Access: | https://elib.dlr.de/138139/ https://link.springer.com/book/10.1007/978-3-030-43981-1 |
id |
ftdlr:oai:elib.dlr.de:138139 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:138139 2023-09-05T13:19:53+02:00 Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches Dumitru, Corneliu Octavian Schwarz, Gottfried Dax, Gabriel Vlad, Andrei Ao, Dongyang Datcu, Mihai Arabnia, H. R. Daimi, K. Stahlbock, R. Soviany, C. Heilig, L. Brussau, K. 2020 https://elib.dlr.de/138139/ https://link.springer.com/book/10.1007/978-3-030-43981-1 unknown Springer Nature Switzerland AG Dumitru, Corneliu Octavian und Schwarz, Gottfried und Dax, Gabriel und Vlad, Andrei und Ao, Dongyang und Datcu, Mihai (2020) Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches. In: Principles of Data Science Transactions on Computational Science and Computational Intelligence. Springer Nature Switzerland AG. Seiten 207-231. doi:10.1007/978-3-030-43981-1_10 <https://doi.org/10.1007/978-3-030-43981-1_10>. ISSN ISSN 2569-7072. info:eu-repo/semantics/restrictedAccess EO Data Science Beitrag in einem Lehr- oder Fachbuch PeerReviewed info:eu-repo/semantics/bookPart 2020 ftdlr https://doi.org/10.1007/978-3-030-43981-1_10 2023-08-20T23:21:36Z We demonstrate how established applications and tools for image classification and change detection can profit from advanced information theory together with automated quality control strategies. As a typical example, we deal with the task of coastline detection in satellite images; here, rapid and correct image interpretation is of utmost importance for riskless shipping and accurate event monitoring. If we combine current machine learning algorithms with new approaches, we can see how current deep learning concepts can still be enhanced. Here, information theory paves the way towards interesting innovative solutions. The validation of the proposed methods will be demonstrated on two target areas: the first one is the Danube Delta, which is the second largest river delta in Europe and is the best preserved one on the continent. Since 1991, the Danube Delta has been inscribed on the UNESCO World Heritage List due do its biological uniqueness. The second one is Belgica Bank in the north-east of Greenland which is an area of extensive fast land-locked ice that is ideal for monitoring seasonal variations of the ice cover and icebergs. Book Part Greenland German Aerospace Center: elib - DLR electronic library Belgica Bank ENVELOPE(-15.000,-15.000,78.467,78.467) Greenland 207 231 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
unknown |
topic |
EO Data Science |
spellingShingle |
EO Data Science Dumitru, Corneliu Octavian Schwarz, Gottfried Dax, Gabriel Vlad, Andrei Ao, Dongyang Datcu, Mihai Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
topic_facet |
EO Data Science |
description |
We demonstrate how established applications and tools for image classification and change detection can profit from advanced information theory together with automated quality control strategies. As a typical example, we deal with the task of coastline detection in satellite images; here, rapid and correct image interpretation is of utmost importance for riskless shipping and accurate event monitoring. If we combine current machine learning algorithms with new approaches, we can see how current deep learning concepts can still be enhanced. Here, information theory paves the way towards interesting innovative solutions. The validation of the proposed methods will be demonstrated on two target areas: the first one is the Danube Delta, which is the second largest river delta in Europe and is the best preserved one on the continent. Since 1991, the Danube Delta has been inscribed on the UNESCO World Heritage List due do its biological uniqueness. The second one is Belgica Bank in the north-east of Greenland which is an area of extensive fast land-locked ice that is ideal for monitoring seasonal variations of the ice cover and icebergs. |
author2 |
Arabnia, H. R. Daimi, K. Stahlbock, R. Soviany, C. Heilig, L. Brussau, K. |
format |
Book Part |
author |
Dumitru, Corneliu Octavian Schwarz, Gottfried Dax, Gabriel Vlad, Andrei Ao, Dongyang Datcu, Mihai |
author_facet |
Dumitru, Corneliu Octavian Schwarz, Gottfried Dax, Gabriel Vlad, Andrei Ao, Dongyang Datcu, Mihai |
author_sort |
Dumitru, Corneliu Octavian |
title |
Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
title_short |
Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
title_full |
Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
title_fullStr |
Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
title_full_unstemmed |
Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches |
title_sort |
active and machine learning for earth observation image analysis with traditional and innovative approaches |
publisher |
Springer Nature Switzerland AG |
publishDate |
2020 |
url |
https://elib.dlr.de/138139/ https://link.springer.com/book/10.1007/978-3-030-43981-1 |
long_lat |
ENVELOPE(-15.000,-15.000,78.467,78.467) |
geographic |
Belgica Bank Greenland |
geographic_facet |
Belgica Bank Greenland |
genre |
Greenland |
genre_facet |
Greenland |
op_relation |
Dumitru, Corneliu Octavian und Schwarz, Gottfried und Dax, Gabriel und Vlad, Andrei und Ao, Dongyang und Datcu, Mihai (2020) Active and Machine Learning for Earth Observation Image Analysis with Traditional and Innovative Approaches. In: Principles of Data Science Transactions on Computational Science and Computational Intelligence. Springer Nature Switzerland AG. Seiten 207-231. doi:10.1007/978-3-030-43981-1_10 <https://doi.org/10.1007/978-3-030-43981-1_10>. ISSN ISSN 2569-7072. |
op_rights |
info:eu-repo/semantics/restrictedAccess |
op_doi |
https://doi.org/10.1007/978-3-030-43981-1_10 |
container_start_page |
207 |
op_container_end_page |
231 |
_version_ |
1776200675511762944 |