Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle
Automated classification of sea-ice types in Synthetic Aperture Radar (SAR) imagery is complicated by the class-dependent decrease of backscatter intensity with Incidence Angle (IA). In the log-domain, this decrease is approximately linear over the typical range of space-borne SAR instruments. A glo...
Published in: | Annals of Glaciology |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Cambridge University Press
2020
|
Subjects: | |
Online Access: | https://hdl.handle.net/10037/18738 https://doi.org/10.1017/aog.2020.45 |
id |
ftunivtroemsoe:oai:munin.uit.no:10037/18738 |
---|---|
record_format |
openpolar |
spelling |
ftunivtroemsoe:oai:munin.uit.no:10037/18738 2023-05-15T13:29:27+02:00 Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle Lohse, Johannes Doulgeris, Anthony Paul Dierking, Wolfgang 2020-06-23 https://hdl.handle.net/10037/18738 https://doi.org/10.1017/aog.2020.45 eng eng Cambridge University Press Lohse, J.P. (2021). On Automated Classification of Sea Ice Types in SAR Imagery. (Doctoral thesis). https://hdl.handle.net/10037/20606 . Annals of Glaciology Norges forskningsråd: 237906 info:eu-repo/grantAgreement/RCN/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Lohse JP, Doulgeris ap, Dierking WFO. Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle. Annals of Glaciology. 2020 FRIDAID 1816176 doi:10.1017/aog.2020.45 0260-3055 1727-5644 https://hdl.handle.net/10037/18738 openAccess Copyright 2020 The Author(s) VDP::Technology: 500 VDP::Teknologi: 500 VDP::Mathematics and natural science: 400::Geosciences: 450 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450 Journal article Tidsskriftartikkel Peer reviewed publishedVersion 2020 ftunivtroemsoe https://doi.org/10.1017/aog.2020.45 2021-06-25T17:57:32Z Automated classification of sea-ice types in Synthetic Aperture Radar (SAR) imagery is complicated by the class-dependent decrease of backscatter intensity with Incidence Angle (IA). In the log-domain, this decrease is approximately linear over the typical range of space-borne SAR instruments. A global correction does not consider that different surface types show different rates of decrease in backscatter intensity. Here, we introduce a supervised classification algorithm that directly incorporates the surface-type dependent effect of IA. We replace the constant mean vector of a Gaussian probability density function in a Bayesian classifier with a linearly variable mean. During training, the classifier first retrieves the slope and intercept of the linear function describing the mean value and then calculates the covariance matrix as the mean squared deviation relative to this function. The IA dependence is no longer treated as an image property but as a class property. Based on training and validation data selected from overlapping SAR and optical images, we evaluate the proposed method in several case studies and compare to other classification algorithms for which a global IA correction is applied during pre-processing. Our results show that the inclusion of the per-class IA sensitivity can significantly improve the performance of the classifier. Article in Journal/Newspaper Annals of Glaciology Arctic Sea ice University of Tromsø: Munin Open Research Archive Annals of Glaciology 61 83 260 270 |
institution |
Open Polar |
collection |
University of Tromsø: Munin Open Research Archive |
op_collection_id |
ftunivtroemsoe |
language |
English |
topic |
VDP::Technology: 500 VDP::Teknologi: 500 VDP::Mathematics and natural science: 400::Geosciences: 450 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450 |
spellingShingle |
VDP::Technology: 500 VDP::Teknologi: 500 VDP::Mathematics and natural science: 400::Geosciences: 450 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450 Lohse, Johannes Doulgeris, Anthony Paul Dierking, Wolfgang Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
topic_facet |
VDP::Technology: 500 VDP::Teknologi: 500 VDP::Mathematics and natural science: 400::Geosciences: 450 VDP::Matematikk og Naturvitenskap: 400::Geofag: 450 |
description |
Automated classification of sea-ice types in Synthetic Aperture Radar (SAR) imagery is complicated by the class-dependent decrease of backscatter intensity with Incidence Angle (IA). In the log-domain, this decrease is approximately linear over the typical range of space-borne SAR instruments. A global correction does not consider that different surface types show different rates of decrease in backscatter intensity. Here, we introduce a supervised classification algorithm that directly incorporates the surface-type dependent effect of IA. We replace the constant mean vector of a Gaussian probability density function in a Bayesian classifier with a linearly variable mean. During training, the classifier first retrieves the slope and intercept of the linear function describing the mean value and then calculates the covariance matrix as the mean squared deviation relative to this function. The IA dependence is no longer treated as an image property but as a class property. Based on training and validation data selected from overlapping SAR and optical images, we evaluate the proposed method in several case studies and compare to other classification algorithms for which a global IA correction is applied during pre-processing. Our results show that the inclusion of the per-class IA sensitivity can significantly improve the performance of the classifier. |
format |
Article in Journal/Newspaper |
author |
Lohse, Johannes Doulgeris, Anthony Paul Dierking, Wolfgang |
author_facet |
Lohse, Johannes Doulgeris, Anthony Paul Dierking, Wolfgang |
author_sort |
Lohse, Johannes |
title |
Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
title_short |
Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
title_full |
Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
title_fullStr |
Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
title_full_unstemmed |
Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle |
title_sort |
mapping sea-ice types from sentinel-1 considering the surface-type dependent effect of incidence angle |
publisher |
Cambridge University Press |
publishDate |
2020 |
url |
https://hdl.handle.net/10037/18738 https://doi.org/10.1017/aog.2020.45 |
genre |
Annals of Glaciology Arctic Sea ice |
genre_facet |
Annals of Glaciology Arctic Sea ice |
op_relation |
Lohse, J.P. (2021). On Automated Classification of Sea Ice Types in SAR Imagery. (Doctoral thesis). https://hdl.handle.net/10037/20606 . Annals of Glaciology Norges forskningsråd: 237906 info:eu-repo/grantAgreement/RCN/SFI/237906/Norway/Centre for Integrated Remote Sensing and Forecasting for Arctic Operations/CIRFA/ Lohse JP, Doulgeris ap, Dierking WFO. Mapping sea-ice types from Sentinel-1 considering the surface-type dependent effect of incidence angle. Annals of Glaciology. 2020 FRIDAID 1816176 doi:10.1017/aog.2020.45 0260-3055 1727-5644 https://hdl.handle.net/10037/18738 |
op_rights |
openAccess Copyright 2020 The Author(s) |
op_doi |
https://doi.org/10.1017/aog.2020.45 |
container_title |
Annals of Glaciology |
container_volume |
61 |
container_issue |
83 |
container_start_page |
260 |
op_container_end_page |
270 |
_version_ |
1766000714571579392 |