Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ...
Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely availabl...
Main Authors: | , , , , , |
---|---|
Format: | Other Non-Article Part of Journal/Newspaper |
Language: | unknown |
Published: |
Taylor & Francis
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.6084/m9.figshare.24089798.v1 https://tandf.figshare.com/articles/journal_contribution/Enhancing_sea_ice_segmentation_in_Sentinel-1_images_with_atrous_convolutions/24089798/1 |
id |
ftdatacite:10.6084/m9.figshare.24089798.v1 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.6084/m9.figshare.24089798.v1 2023-11-05T03:44:53+01:00 Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... de Lima, Rafael Pires Vahedi, Behzad Hughes, Nick Barrett, Andrew P. Meier, Walter Karimzadeh, Morteza 2023 https://dx.doi.org/10.6084/m9.figshare.24089798.v1 https://tandf.figshare.com/articles/journal_contribution/Enhancing_sea_ice_segmentation_in_Sentinel-1_images_with_atrous_convolutions/24089798/1 unknown Taylor & Francis https://dx.doi.org/10.6084/m9.figshare.24089798 https://dx.doi.org/10.1080/01431161.2023.2248560 Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 Space Science Medicine Environmental Sciences not elsewhere classified Chemical Sciences not elsewhere classified Sociology FOS Sociology Biological Sciences not elsewhere classified Journal contribution Text article-journal ScholarlyArticle 2023 ftdatacite https://doi.org/10.6084/m9.figshare.24089798.v110.6084/m9.figshare.2408979810.1080/01431161.2023.2248560 2023-10-09T10:56:34Z Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, ... Other Non-Article Part of Journal/Newspaper Sea ice DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Space Science Medicine Environmental Sciences not elsewhere classified Chemical Sciences not elsewhere classified Sociology FOS Sociology Biological Sciences not elsewhere classified |
spellingShingle |
Space Science Medicine Environmental Sciences not elsewhere classified Chemical Sciences not elsewhere classified Sociology FOS Sociology Biological Sciences not elsewhere classified de Lima, Rafael Pires Vahedi, Behzad Hughes, Nick Barrett, Andrew P. Meier, Walter Karimzadeh, Morteza Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
topic_facet |
Space Science Medicine Environmental Sciences not elsewhere classified Chemical Sciences not elsewhere classified Sociology FOS Sociology Biological Sciences not elsewhere classified |
description |
Due to the growing volume of remote sensing data and the low latency required for safe marine navigation, machine learning (ML) algorithms are being developed to accelerate sea ice chart generation, currently a manual interpretation task. However, the low signal-to-noise ratio of the freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery, the ambiguity of backscatter signals for ice types, and the scarcity of open-source high-resolution labelled data makes automating sea ice mapping challenging. We use Extreme Earth version 2, a high-resolution benchmark dataset generated for ML training and evaluation, to investigate the effectiveness of ML for automated sea ice mapping. Our customized pipeline combines ResNets and Atrous Spatial Pyramid Pooling for SAR image segmentation. We investigate the performance of our model for: i) binary classification of sea ice and open water in a segmentation framework; and ii) a multiclass segmentation of five sea ice types. For binary ice-water classification, ... |
format |
Other Non-Article Part of Journal/Newspaper |
author |
de Lima, Rafael Pires Vahedi, Behzad Hughes, Nick Barrett, Andrew P. Meier, Walter Karimzadeh, Morteza |
author_facet |
de Lima, Rafael Pires Vahedi, Behzad Hughes, Nick Barrett, Andrew P. Meier, Walter Karimzadeh, Morteza |
author_sort |
de Lima, Rafael Pires |
title |
Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
title_short |
Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
title_full |
Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
title_fullStr |
Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
title_full_unstemmed |
Enhancing sea ice segmentation in Sentinel-1 images with atrous convolutions ... |
title_sort |
enhancing sea ice segmentation in sentinel-1 images with atrous convolutions ... |
publisher |
Taylor & Francis |
publishDate |
2023 |
url |
https://dx.doi.org/10.6084/m9.figshare.24089798.v1 https://tandf.figshare.com/articles/journal_contribution/Enhancing_sea_ice_segmentation_in_Sentinel-1_images_with_atrous_convolutions/24089798/1 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
https://dx.doi.org/10.6084/m9.figshare.24089798 https://dx.doi.org/10.1080/01431161.2023.2248560 |
op_rights |
Creative Commons Attribution 4.0 International https://creativecommons.org/licenses/by/4.0/legalcode cc-by-4.0 |
op_doi |
https://doi.org/10.6084/m9.figshare.24089798.v110.6084/m9.figshare.2408979810.1080/01431161.2023.2248560 |
_version_ |
1781705968603627520 |