Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery
SAR Polarimetry has become a valuable tool in spaceborne SAR based sea ice analysis. The two major objectives in SAR based remote sensing of sea ice is on the one hand to have a large coverage of the imaged ground area, and on the other hand to obtain a radar response that carries as much Informatio...
Published in: | 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) |
---|---|
Main Authors: | , , |
Format: | Conference Object |
Language: | German |
Published: |
IEEE Xplore
2016
|
Subjects: | |
Online Access: | https://elib.dlr.de/102298/ https://elib.dlr.de/102298/1/07730261.pdf https://doi.org/10.1109/IGARSS.2016.7730261 |
id |
ftdlr:oai:elib.dlr.de:102298 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:102298 2024-05-19T07:41:23+00:00 Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery Ressel, Rudolf Singha, Suman Lehner, Susanne 2016-11-03 application/pdf https://elib.dlr.de/102298/ https://elib.dlr.de/102298/1/07730261.pdf https://doi.org/10.1109/IGARSS.2016.7730261 de ger IEEE Xplore https://elib.dlr.de/102298/1/07730261.pdf Ressel, Rudolf und Singha, Suman und Lehner, Susanne (2016) Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery. In: Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, Seiten 4835-4838. IEEE Xplore. IGARSS 2016, 2016-07-10 - 2016-07-15, Peking, China. doi:10.1109/IGARSS.2016.7730261 <https://doi.org/10.1109/IGARSS.2016.7730261>. ISBN 978-1-5090-3332-4. ISSN 2153-7003. Institut für Methodik der Fernerkundung SAR-Signalverarbeitung Konferenzbeitrag NonPeerReviewed 2016 ftdlr https://doi.org/10.1109/IGARSS.2016.7730261 2024-04-25T00:36:21Z SAR Polarimetry has become a valuable tool in spaceborne SAR based sea ice analysis. The two major objectives in SAR based remote sensing of sea ice is on the one hand to have a large coverage of the imaged ground area, and on the other hand to obtain a radar response that carries as much Information as possible. Whereas single-polarimetric acquisitions of existing sensors offer a wide coverage on the ground, dual polarimetric, or even better fully polarimetric data offer a higher information content which allows for a more reliable automated sea ice analysis. In order to reconcile the advantages of fully polarimetric acquisitions with the higher ground coverage of acquisitions with fewer polarimetric channels, hybrid polarimetric acquisitions offer a trade-off between the mentioned objectives. With the advent of the RISAT-1 satellite platform, we are able to explore the potential of hybrid dual pol acquisitions for sea ice analysis and classification. Our algorithmic approach for an automated sea ice classificationconsists of two steps. In the first step, we perform a Feature etraction procedure. The resulting feature vectors are then ingested into a trained neural network classifier to arrive at a pixelwise supervised classification. We present first results on a dataset acquired off the eastern Greenland coast. Conference Object Greenland Sea ice German Aerospace Center: elib - DLR electronic library 2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 4835 4838 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
German |
topic |
Institut für Methodik der Fernerkundung SAR-Signalverarbeitung |
spellingShingle |
Institut für Methodik der Fernerkundung SAR-Signalverarbeitung Ressel, Rudolf Singha, Suman Lehner, Susanne Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
topic_facet |
Institut für Methodik der Fernerkundung SAR-Signalverarbeitung |
description |
SAR Polarimetry has become a valuable tool in spaceborne SAR based sea ice analysis. The two major objectives in SAR based remote sensing of sea ice is on the one hand to have a large coverage of the imaged ground area, and on the other hand to obtain a radar response that carries as much Information as possible. Whereas single-polarimetric acquisitions of existing sensors offer a wide coverage on the ground, dual polarimetric, or even better fully polarimetric data offer a higher information content which allows for a more reliable automated sea ice analysis. In order to reconcile the advantages of fully polarimetric acquisitions with the higher ground coverage of acquisitions with fewer polarimetric channels, hybrid polarimetric acquisitions offer a trade-off between the mentioned objectives. With the advent of the RISAT-1 satellite platform, we are able to explore the potential of hybrid dual pol acquisitions for sea ice analysis and classification. Our algorithmic approach for an automated sea ice classificationconsists of two steps. In the first step, we perform a Feature etraction procedure. The resulting feature vectors are then ingested into a trained neural network classifier to arrive at a pixelwise supervised classification. We present first results on a dataset acquired off the eastern Greenland coast. |
format |
Conference Object |
author |
Ressel, Rudolf Singha, Suman Lehner, Susanne |
author_facet |
Ressel, Rudolf Singha, Suman Lehner, Susanne |
author_sort |
Ressel, Rudolf |
title |
Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
title_short |
Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
title_full |
Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
title_fullStr |
Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
title_full_unstemmed |
Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery |
title_sort |
neural network based automatic sea ice classification for cl-pol risat-1 imagery |
publisher |
IEEE Xplore |
publishDate |
2016 |
url |
https://elib.dlr.de/102298/ https://elib.dlr.de/102298/1/07730261.pdf https://doi.org/10.1109/IGARSS.2016.7730261 |
genre |
Greenland Sea ice |
genre_facet |
Greenland Sea ice |
op_relation |
https://elib.dlr.de/102298/1/07730261.pdf Ressel, Rudolf und Singha, Suman und Lehner, Susanne (2016) Neural Network based automatic Sea Ice Classification for CL-pol RISAT-1 Imagery. In: Geoscience and Remote Sensing Symposium (IGARSS), 2016 IEEE International, Seiten 4835-4838. IEEE Xplore. IGARSS 2016, 2016-07-10 - 2016-07-15, Peking, China. doi:10.1109/IGARSS.2016.7730261 <https://doi.org/10.1109/IGARSS.2016.7730261>. ISBN 978-1-5090-3332-4. ISSN 2153-7003. |
op_doi |
https://doi.org/10.1109/IGARSS.2016.7730261 |
container_title |
2016 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) |
container_start_page |
4835 |
op_container_end_page |
4838 |
_version_ |
1799480976937582592 |