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, gray-level co-occurrence matrix(GLCM)-based texture features are extracted from the image. In the second step, these data are fed into an artificial n...
Published in: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
IEEE
2015
|
Subjects: | |
Online Access: | https://doi.org/10.1109/JSTARS.2015.2436993 https://doaj.org/article/49c5e7e7f8ec4c0083650360433a16c0 |
id |
ftdoajarticles:oai:doaj.org/article:49c5e7e7f8ec4c0083650360433a16c0 |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:49c5e7e7f8ec4c0083650360433a16c0 2023-05-15T15:38:56+02:00 A Neural Network-Based Classification for Sea Ice Types on X-Band SAR Images Rudolf Ressel Anja Frost Susanne Lehner 2015-01-01T00:00:00Z https://doi.org/10.1109/JSTARS.2015.2436993 https://doaj.org/article/49c5e7e7f8ec4c0083650360433a16c0 EN eng IEEE https://ieeexplore.ieee.org/document/7122229/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2015.2436993 https://doaj.org/article/49c5e7e7f8ec4c0083650360433a16c0 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 8, Iss 7, Pp 3672-3680 (2015) Earth and atmospheric sciences pattern analysis remote sensing texture Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 article 2015 ftdoajarticles https://doi.org/10.1109/JSTARS.2015.2436993 2022-12-31T06:19:13Z 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, gray-level co-occurrence matrix(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, when 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 toward operational, near-realtime ice charting. Article in Journal/Newspaper Barents Sea Sea ice Directory of Open Access Journals: DOAJ Articles Barents Sea IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 8 7 3672 3680 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
Earth and atmospheric sciences pattern analysis remote sensing texture Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
spellingShingle |
Earth and atmospheric sciences pattern analysis remote sensing texture Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Rudolf Ressel Anja Frost Susanne Lehner A Neural Network-Based Classification for Sea Ice Types on X-Band SAR Images |
topic_facet |
Earth and atmospheric sciences pattern analysis remote sensing texture Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 |
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, gray-level co-occurrence matrix(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, when 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 toward operational, near-realtime ice charting. |
format |
Article in Journal/Newspaper |
author |
Rudolf Ressel Anja Frost Susanne Lehner |
author_facet |
Rudolf Ressel Anja Frost Susanne Lehner |
author_sort |
Rudolf Ressel |
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 |
publishDate |
2015 |
url |
https://doi.org/10.1109/JSTARS.2015.2436993 https://doaj.org/article/49c5e7e7f8ec4c0083650360433a16c0 |
geographic |
Barents Sea |
geographic_facet |
Barents Sea |
genre |
Barents Sea Sea ice |
genre_facet |
Barents Sea Sea ice |
op_source |
IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 8, Iss 7, Pp 3672-3680 (2015) |
op_relation |
https://ieeexplore.ieee.org/document/7122229/ https://doaj.org/toc/2151-1535 2151-1535 doi:10.1109/JSTARS.2015.2436993 https://doaj.org/article/49c5e7e7f8ec4c0083650360433a16c0 |
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_ |
1766370348475875328 |