A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images
We examine the performance of an automated sea ice classification algorithm based on TerraSAR-X ScanSAR data. In the first step of our process chain, GLCM-based texture features are extracted from the image. In the second step, these data are fed into an artificial neural network to classify each pi...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
IEEE - Institute of Electrical and Electronics Engineers
2015
|
Subjects: | |
Online Access: | https://elib.dlr.de/90934/ http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7122229 |
id |
ftdlr:oai:elib.dlr.de:90934 |
---|---|
record_format |
openpolar |
spelling |
ftdlr:oai:elib.dlr.de:90934 2023-12-31T10:05:07+01:00 A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images Ressel, Rudolf Frost, Anja Lehner, Susanne 2015 https://elib.dlr.de/90934/ http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7122229 unknown IEEE - Institute of Electrical and Electronics Engineers Ressel, Rudolf und Frost, Anja und Lehner, Susanne (2015) A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8 (7), Seiten 3672-3680. IEEE - Institute of Electrical and Electronics Engineers. doi:10.1109/JSTARS.2015.2436993 <https://doi.org/10.1109/JSTARS.2015.2436993>. ISSN 1939-1404. SAR-Signalverarbeitung Institut für Methodik der Fernerkundung Zeitschriftenbeitrag PeerReviewed 2015 ftdlr https://doi.org/10.1109/JSTARS.2015.2436993 2023-12-04T00:24:00Z We examine the performance of an automated sea ice classification algorithm based on TerraSAR-X ScanSAR data. In the first step of our process chain, GLCM-based texture features are extracted from the image. In the second step, these data are fed into an artificial neural network to classify each pixel. Performance of our implementation is examined by utilizing a time series of ScanSAR images in the Western Barents Sea, acquired in spring 2013. The network is trained on the initial image of the time series and then applied to subsequent images. We obtain a reasonable classification accuracy of at least 70% depending on the choice of our ice type regime, given the incidence angle range of the training data matches that of the classified image. Computational cost of our approach is sufficiently moderate to consider this classification procedure a promising step towards operational, near real time ice charting. Article in Journal/Newspaper Barents Sea Sea ice German Aerospace Center: elib - DLR electronic library IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8 7 3672 3680 |
institution |
Open Polar |
collection |
German Aerospace Center: elib - DLR electronic library |
op_collection_id |
ftdlr |
language |
unknown |
topic |
SAR-Signalverarbeitung Institut für Methodik der Fernerkundung |
spellingShingle |
SAR-Signalverarbeitung Institut für Methodik der Fernerkundung Ressel, Rudolf Frost, Anja Lehner, Susanne A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
topic_facet |
SAR-Signalverarbeitung Institut für Methodik der Fernerkundung |
description |
We examine the performance of an automated sea ice classification algorithm based on TerraSAR-X ScanSAR data. In the first step of our process chain, GLCM-based texture features are extracted from the image. In the second step, these data are fed into an artificial neural network to classify each pixel. Performance of our implementation is examined by utilizing a time series of ScanSAR images in the Western Barents Sea, acquired in spring 2013. The network is trained on the initial image of the time series and then applied to subsequent images. We obtain a reasonable classification accuracy of at least 70% depending on the choice of our ice type regime, given the incidence angle range of the training data matches that of the classified image. Computational cost of our approach is sufficiently moderate to consider this classification procedure a promising step towards operational, near real time ice charting. |
format |
Article in Journal/Newspaper |
author |
Ressel, Rudolf Frost, Anja Lehner, Susanne |
author_facet |
Ressel, Rudolf Frost, Anja Lehner, Susanne |
author_sort |
Ressel, Rudolf |
title |
A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
title_short |
A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
title_full |
A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
title_fullStr |
A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
title_full_unstemmed |
A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images |
title_sort |
neural network based classification for sea ice types on x-band sar images |
publisher |
IEEE - Institute of Electrical and Electronics Engineers |
publishDate |
2015 |
url |
https://elib.dlr.de/90934/ http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=7122229 |
genre |
Barents Sea Sea ice |
genre_facet |
Barents Sea Sea ice |
op_relation |
Ressel, Rudolf und Frost, Anja und Lehner, Susanne (2015) A Neural Network Based Classification for Sea Ice Types on X-Band SAR Images. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8 (7), Seiten 3672-3680. IEEE - Institute of Electrical and Electronics Engineers. doi:10.1109/JSTARS.2015.2436993 <https://doi.org/10.1109/JSTARS.2015.2436993>. ISSN 1939-1404. |
op_doi |
https://doi.org/10.1109/JSTARS.2015.2436993 |
container_title |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
container_volume |
8 |
container_issue |
7 |
container_start_page |
3672 |
op_container_end_page |
3680 |
_version_ |
1786836608105840640 |