Assessing polarimetric SAR sea-ice classifications using consecutive day images
Source at https://doi.org/10.3189/2015AoG69A802 . This paper investigates automatic segmentation and classification of C-band, polarimetric synthetic aperture radar (SAR) satellite images of Arctic sea ice under freezing conditions prior to melt. The objective is to investigate the robustness of the...
Published in: | Annals of Glaciology |
---|---|
Main Authors: | , , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press
2015
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/14398 https://doi.org/10.3189/2015AoG69A802 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/14398 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/14398 2023-05-15T13:29:18+02:00 Assessing polarimetric SAR sea-ice classifications using consecutive day images Moen, Mari-Ann Anfinsen, Stian Normann Doulgeris, Anthony Paul Renner, Angelika Gerland, Sebastian 2015 https://hdl.handle.net/10037/14398 https://doi.org/10.3189/2015AoG69A802 eng eng Cambridge University Press Annals of Glaciology info:eu-repo/grantAgreement/RCN/NORDSATS/195143/Norway/Arctic Earth Observation and Surveillance Technologies// Moen, M.-A.N., Anfinsen, S.N., Doulgeris, A.P., Renner, A.H.H. & Gerland, S. (2015). Assessing polarimetric SAR sea-ice classifications using consecutive day images. Annals of Glaciology , 56(69), 285-294. https://doi.org/10.3189/2015AoG69A802 FRIDAID 1259429 doi:10.3189/2015AoG69A802 0260-3055 1727-5644 https://hdl.handle.net/10037/14398 openAccess VDP::Mathematics and natural science: 400::Geosciences: 450::Quaternary geology glaciology: 465 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450::Kvartærgeologi glasiologi: 465 remote sensing sea ice Journal article Tidsskriftartikkel Peer reviewed 2015 ftunivtroemsoe https://doi.org/10.3189/2015AoG69A802 2021-06-25T17:56:16Z Source at https://doi.org/10.3189/2015AoG69A802 . This paper investigates automatic segmentation and classification of C-band, polarimetric synthetic aperture radar (SAR) satellite images of Arctic sea ice under freezing conditions prior to melt. The objective is to investigate the robustness of the results obtained under slightly varying environmental conditions and different viewing geometries. Initially, three geographically overlapping SAR images from consecutive days are incidence-angle corrected and segmented into unknown classes. The segmentation is performed by an unsupervised mixture-of-Gaussian segmentation algorithm utilizing six features extracted from the polarimetric data. After segmentation, the segments are contextually smoothed. One segmented image is manually labelled based on in situ data and expert knowledge. Using this scene as reference, we consider two strategies for class labelling of the other scenes. The first manually labels the classes based on visual inspection of the reference; the second utilizes various statistical distance measures to automatically assign each unknown class to the statistically nearest reference class. These two scenes are also classified pixel-wise by a supervised classification algorithm based on the reference data. Poor classification results are obtained when the incidence angle is very different from the reference scene. Similar viewing geometries reveal good classification and labelling results, the latter regardless of the distance measure used. Article in Journal/Newspaper Annals of Glaciology Arctic Arctic Sea ice University of Tromsø: Munin Open Research Archive Arctic Annals of Glaciology 56 69 285 294 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Mathematics and natural science: 400::Geosciences: 450::Quaternary geology glaciology: 465 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450::Kvartærgeologi glasiologi: 465 remote sensing sea ice |
spellingShingle |
VDP::Mathematics and natural science: 400::Geosciences: 450::Quaternary geology glaciology: 465 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450::Kvartærgeologi glasiologi: 465 remote sensing sea ice Moen, Mari-Ann Anfinsen, Stian Normann Doulgeris, Anthony Paul Renner, Angelika Gerland, Sebastian Assessing polarimetric SAR sea-ice classifications using consecutive day images |
topic_facet |
VDP::Mathematics and natural science: 400::Geosciences: 450::Quaternary geology glaciology: 465 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450::Kvartærgeologi glasiologi: 465 remote sensing sea ice |
description |
Source at https://doi.org/10.3189/2015AoG69A802 . This paper investigates automatic segmentation and classification of C-band, polarimetric synthetic aperture radar (SAR) satellite images of Arctic sea ice under freezing conditions prior to melt. The objective is to investigate the robustness of the results obtained under slightly varying environmental conditions and different viewing geometries. Initially, three geographically overlapping SAR images from consecutive days are incidence-angle corrected and segmented into unknown classes. The segmentation is performed by an unsupervised mixture-of-Gaussian segmentation algorithm utilizing six features extracted from the polarimetric data. After segmentation, the segments are contextually smoothed. One segmented image is manually labelled based on in situ data and expert knowledge. Using this scene as reference, we consider two strategies for class labelling of the other scenes. The first manually labels the classes based on visual inspection of the reference; the second utilizes various statistical distance measures to automatically assign each unknown class to the statistically nearest reference class. These two scenes are also classified pixel-wise by a supervised classification algorithm based on the reference data. Poor classification results are obtained when the incidence angle is very different from the reference scene. Similar viewing geometries reveal good classification and labelling results, the latter regardless of the distance measure used. |
format |
Article in Journal/Newspaper |
author |
Moen, Mari-Ann Anfinsen, Stian Normann Doulgeris, Anthony Paul Renner, Angelika Gerland, Sebastian |
author_facet |
Moen, Mari-Ann Anfinsen, Stian Normann Doulgeris, Anthony Paul Renner, Angelika Gerland, Sebastian |
author_sort |
Moen, Mari-Ann |
title |
Assessing polarimetric SAR sea-ice classifications using consecutive day images |
title_short |
Assessing polarimetric SAR sea-ice classifications using consecutive day images |
title_full |
Assessing polarimetric SAR sea-ice classifications using consecutive day images |
title_fullStr |
Assessing polarimetric SAR sea-ice classifications using consecutive day images |
title_full_unstemmed |
Assessing polarimetric SAR sea-ice classifications using consecutive day images |
title_sort |
assessing polarimetric sar sea-ice classifications using consecutive day images |
publisher |
Cambridge University Press |
publishDate |
2015 |
url |
https://hdl.handle.net/10037/14398 https://doi.org/10.3189/2015AoG69A802 |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Annals of Glaciology Arctic Arctic Sea ice |
genre_facet |
Annals of Glaciology Arctic Arctic Sea ice |
op_relation |
Annals of Glaciology info:eu-repo/grantAgreement/RCN/NORDSATS/195143/Norway/Arctic Earth Observation and Surveillance Technologies// Moen, M.-A.N., Anfinsen, S.N., Doulgeris, A.P., Renner, A.H.H. & Gerland, S. (2015). Assessing polarimetric SAR sea-ice classifications using consecutive day images. Annals of Glaciology , 56(69), 285-294. https://doi.org/10.3189/2015AoG69A802 FRIDAID 1259429 doi:10.3189/2015AoG69A802 0260-3055 1727-5644 https://hdl.handle.net/10037/14398 |
op_rights |
openAccess |
op_doi |
https://doi.org/10.3189/2015AoG69A802 |
container_title |
Annals of Glaciology |
container_volume |
56 |
container_issue |
69 |
container_start_page |
285 |
op_container_end_page |
294 |
_version_ |
1765999819213504512 |