Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ...
Sea ice is a crucial component of the Earth's climate system and is highly sensitive to changes in temperature and atmospheric conditions. Accurate and timely measurement of sea ice parameters is important for understanding and predicting the impacts of climate change. Nevertheless, the amount...
Main Authors: | , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2306.07649 https://arxiv.org/abs/2306.07649 |
id |
ftdatacite:10.48550/arxiv.2306.07649 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2306.07649 2023-07-23T04:21:41+02:00 Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... Ristea, Nicolae-Catalin Anghel, Andrei Datcu, Mihai 2023 https://dx.doi.org/10.48550/arxiv.2306.07649 https://arxiv.org/abs/2306.07649 unknown arXiv Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering CreativeWork Preprint article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2306.07649 2023-07-03T18:50:32Z Sea ice is a crucial component of the Earth's climate system and is highly sensitive to changes in temperature and atmospheric conditions. Accurate and timely measurement of sea ice parameters is important for understanding and predicting the impacts of climate change. Nevertheless, the amount of satellite data acquired over ice areas is huge, making the subjective measurements ineffective. Therefore, automated algorithms must be used in order to fully exploit the continuous data feeds coming from satellites. In this paper, we present a novel approach for sea ice segmentation based on SAR satellite imagery using hybrid convolutional transformer (ConvTr) networks. We show that our approach outperforms classical convolutional networks, while being considerably more efficient than pure transformer models. ConvTr obtained a mean intersection over union (mIoU) of 63.68% on the AI4Arctic data set, assuming an inference time of 120ms for a 400 x 400 squared km product. ... Report 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 |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
spellingShingle |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering Ristea, Nicolae-Catalin Anghel, Andrei Datcu, Mihai Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
topic_facet |
Computer Vision and Pattern Recognition cs.CV Image and Video Processing eess.IV FOS Computer and information sciences FOS Electrical engineering, electronic engineering, information engineering |
description |
Sea ice is a crucial component of the Earth's climate system and is highly sensitive to changes in temperature and atmospheric conditions. Accurate and timely measurement of sea ice parameters is important for understanding and predicting the impacts of climate change. Nevertheless, the amount of satellite data acquired over ice areas is huge, making the subjective measurements ineffective. Therefore, automated algorithms must be used in order to fully exploit the continuous data feeds coming from satellites. In this paper, we present a novel approach for sea ice segmentation based on SAR satellite imagery using hybrid convolutional transformer (ConvTr) networks. We show that our approach outperforms classical convolutional networks, while being considerably more efficient than pure transformer models. ConvTr obtained a mean intersection over union (mIoU) of 63.68% on the AI4Arctic data set, assuming an inference time of 120ms for a 400 x 400 squared km product. ... |
format |
Report |
author |
Ristea, Nicolae-Catalin Anghel, Andrei Datcu, Mihai |
author_facet |
Ristea, Nicolae-Catalin Anghel, Andrei Datcu, Mihai |
author_sort |
Ristea, Nicolae-Catalin |
title |
Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
title_short |
Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
title_full |
Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
title_fullStr |
Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
title_full_unstemmed |
Sea Ice Segmentation From SAR Data by Convolutional Transformer Networks ... |
title_sort |
sea ice segmentation from sar data by convolutional transformer networks ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2306.07649 https://arxiv.org/abs/2306.07649 |
genre |
Sea ice |
genre_facet |
Sea ice |
op_rights |
Creative Commons Attribution Non Commercial Share Alike 4.0 International https://creativecommons.org/licenses/by-nc-sa/4.0/legalcode cc-by-nc-sa-4.0 |
op_doi |
https://doi.org/10.48550/arxiv.2306.07649 |
_version_ |
1772187701779365888 |