E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision
Distinguishing sea ice and water is crucial for safe navigation and carrying out offshore activities in ice zones. However, due to the complexity and dynamics of the ice–water boundary, it is difficult for many deep learning-based segmentation algorithms to achieve accurate ice–water segmentation in...
Published in: | Remote Sensing |
---|---|
Main Authors: | , , , , |
Format: | Text |
Language: | English |
Published: |
Multidisciplinary Digital Publishing Institute
2022
|
Subjects: | |
Online Access: | https://doi.org/10.3390/rs14225753 |
id |
ftmdpi:oai:mdpi.com:/2072-4292/14/22/5753/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/2072-4292/14/22/5753/ 2023-08-20T04:09:43+02:00 E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision Wei Song Hongtao Li Qi He Guoping Gao Antonio Liotta agris 2022-11-14 application/pdf https://doi.org/10.3390/rs14225753 EN eng Multidisciplinary Digital Publishing Institute Ocean Remote Sensing https://dx.doi.org/10.3390/rs14225753 https://creativecommons.org/licenses/by/4.0/ Remote Sensing; Volume 14; Issue 22; Pages: 5753 ice–water segmentation edge prediction multi-scale attention mechanism semantic features ice concentration Text 2022 ftmdpi https://doi.org/10.3390/rs14225753 2023-08-01T07:20:18Z Distinguishing sea ice and water is crucial for safe navigation and carrying out offshore activities in ice zones. However, due to the complexity and dynamics of the ice–water boundary, it is difficult for many deep learning-based segmentation algorithms to achieve accurate ice–water segmentation in synthetic aperture radar (SAR) images. In this paper, we propose an ice–water SAR segmentation network, E-MPSPNet, which can provide effective ice–water segmentation by fusing semantic features and edge information. The E-MPSPNet introduces a multi-scale attention mechanism to better fuse the ice–water semantic features and designs an edge supervision module (ESM) to learn ice–water edge features. The ESM not only provides ice–water edge prediction but also imposes constraints on the semantic feature extraction to better express the edge information. We also design a loss function that focuses on both ice–water edges and semantic segmentations of ice and water for overall network optimization. With the AI4Arctic/ASIP Sea Ice Dataset as the benchmark, experimental results show our E-MPSPNet achieves the best performance compared with other commonly used segmentation models, reaching 94.2% for accuracy, 93.0% for F-score, and 89.2% for MIoU. Moreover, our E-MPSPNet shows a relatively smaller model size and faster processing speed. The application of the E-MPSPNet for processing a SAR scene demonstrates its potential for operational use in drawing near real-time navigation charts of sea ice. Text Sea ice MDPI Open Access Publishing Remote Sensing 14 22 5753 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
ice–water segmentation edge prediction multi-scale attention mechanism semantic features ice concentration |
spellingShingle |
ice–water segmentation edge prediction multi-scale attention mechanism semantic features ice concentration Wei Song Hongtao Li Qi He Guoping Gao Antonio Liotta E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
topic_facet |
ice–water segmentation edge prediction multi-scale attention mechanism semantic features ice concentration |
description |
Distinguishing sea ice and water is crucial for safe navigation and carrying out offshore activities in ice zones. However, due to the complexity and dynamics of the ice–water boundary, it is difficult for many deep learning-based segmentation algorithms to achieve accurate ice–water segmentation in synthetic aperture radar (SAR) images. In this paper, we propose an ice–water SAR segmentation network, E-MPSPNet, which can provide effective ice–water segmentation by fusing semantic features and edge information. The E-MPSPNet introduces a multi-scale attention mechanism to better fuse the ice–water semantic features and designs an edge supervision module (ESM) to learn ice–water edge features. The ESM not only provides ice–water edge prediction but also imposes constraints on the semantic feature extraction to better express the edge information. We also design a loss function that focuses on both ice–water edges and semantic segmentations of ice and water for overall network optimization. With the AI4Arctic/ASIP Sea Ice Dataset as the benchmark, experimental results show our E-MPSPNet achieves the best performance compared with other commonly used segmentation models, reaching 94.2% for accuracy, 93.0% for F-score, and 89.2% for MIoU. Moreover, our E-MPSPNet shows a relatively smaller model size and faster processing speed. The application of the E-MPSPNet for processing a SAR scene demonstrates its potential for operational use in drawing near real-time navigation charts of sea ice. |
format |
Text |
author |
Wei Song Hongtao Li Qi He Guoping Gao Antonio Liotta |
author_facet |
Wei Song Hongtao Li Qi He Guoping Gao Antonio Liotta |
author_sort |
Wei Song |
title |
E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
title_short |
E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
title_full |
E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
title_fullStr |
E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
title_full_unstemmed |
E-MPSPNet: Ice–Water SAR Scene Segmentation Based on Multi-Scale Semantic Features and Edge Supervision |
title_sort |
e-mpspnet: ice–water sar scene segmentation based on multi-scale semantic features and edge supervision |
publisher |
Multidisciplinary Digital Publishing Institute |
publishDate |
2022 |
url |
https://doi.org/10.3390/rs14225753 |
op_coverage |
agris |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
Remote Sensing; Volume 14; Issue 22; Pages: 5753 |
op_relation |
Ocean Remote Sensing https://dx.doi.org/10.3390/rs14225753 |
op_rights |
https://creativecommons.org/licenses/by/4.0/ |
op_doi |
https://doi.org/10.3390/rs14225753 |
container_title |
Remote Sensing |
container_volume |
14 |
container_issue |
22 |
container_start_page |
5753 |
_version_ |
1774723361916583936 |