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: | Article in Journal/Newspaper |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2310.17122 https://arxiv.org/abs/2310.17122 |
id |
ftdatacite:10.48550/arxiv.2310.17122 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2310.17122 2023-12-03T10:30:01+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/10.48550/arxiv.2310.17122 https://arxiv.org/abs/2310.17122 unknown arXiv 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 Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences ScholarlyArticle Text article-journal Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2310.1712210.1080/01431161.2023.2248560 2023-11-03T11:11:09Z 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, ... Article in Journal/Newspaper Sea ice DataCite Metadata Store (German National Library of Science and Technology) Pyramid ENVELOPE(157.300,157.300,-81.333,-81.333) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
spellingShingle |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences 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 |
Image and Video Processing eess.IV Computer Vision and Pattern Recognition cs.CV FOS Electrical engineering, electronic engineering, information engineering FOS Computer and information sciences |
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 |
Article in 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 |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2310.17122 https://arxiv.org/abs/2310.17122 |
long_lat |
ENVELOPE(157.300,157.300,-81.333,-81.333) |
geographic |
Pyramid |
geographic_facet |
Pyramid |
genre |
Sea ice |
genre_facet |
Sea ice |
op_relation |
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/10.48550/arxiv.2310.1712210.1080/01431161.2023.2248560 |
_version_ |
1784255653957599232 |