MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation
Sea ice segmentation from synthetic aperture radar (SAR) imagery is a key task in polar sea ice monitoring, which is crucial for global climate prediction and polar route planning. However, the existing sea ice segmentation algorithms for SAR images often fail to consider long-range contextual depen...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10930574/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849340818522898432 |
|---|---|
| author | Tianen Ma Xinwei Chen Linlin Xu Pengfei Ma Peilin Yu |
| author_facet | Tianen Ma Xinwei Chen Linlin Xu Pengfei Ma Peilin Yu |
| author_sort | Tianen Ma |
| collection | DOAJ |
| description | Sea ice segmentation from synthetic aperture radar (SAR) imagery is a key task in polar sea ice monitoring, which is crucial for global climate prediction and polar route planning. However, the existing sea ice segmentation algorithms for SAR images often fail to consider long-range contextual dependencies when capturing multiscale features, resulting in an inability to fully exploit multiscale global contextual information. To address this limitation, we proposed a novel encoder–decoder structure network for multitask sea ice segmentation. Initially, a cross-scale interaction module was constructed in the encoder that utilizes cross attention to seamlessly capture multiscale features, effectively bridging the semantic information gap between different layers. Subsequently, a context transformer block based on efficient multihead self-attention was developed to model remote dependencies across spatial and channel dimensions, thereby enhancing the extraction of multiscale global contextual information. Furthermore, a channel patch module was introduced that allows for the strategic refinement of differential features to emphasize changing areas and suppress artifacts. In the final stages, a refined multiscale feature fusion module was embedded in the decoder to strategically integrate the feature maps generated, thus iteratively merging layered features for enhanced segmentation. Our experiments on the AI4Arctic Sea Ice Challenge Dataset show that MFGC-Net achieves outstanding performance in multitask sea ice segmentation compared with current state-of-the-art methods, as demonstrated by both quantitative and qualitative results. |
| format | Article |
| id | doaj-art-e15915c23a00428daa60dae24e1e7e5a |
| institution | Kabale University |
| issn | 1939-1404 2151-1535 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj-art-e15915c23a00428daa60dae24e1e7e5a2025-08-20T03:43:47ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing1939-14042151-15352025-01-0118140151403510.1109/JSTARS.2025.355197610930574MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine SegmentationTianen Ma0https://orcid.org/0009-0007-0379-5282Xinwei Chen1https://orcid.org/0000-0003-0649-7284Linlin Xu2Pengfei Ma3Peilin Yu4School of Marine Science and Engineering, South China University of Technology, Guangzhou, ChinaSchool of Marine Science and Engineering, South China University of Technology, Guangzhou, ChinaDepartment of Geomatics Engineering, University of Calgary, Calgary, AB, CanadaChinese Antarctic Center of Surveying and Mapping, Wuhan University, Wuhan, ChinaSchool of Mechanical and Electrical Engineering, Guangzhou University, Guangzhou, ChinaSea ice segmentation from synthetic aperture radar (SAR) imagery is a key task in polar sea ice monitoring, which is crucial for global climate prediction and polar route planning. However, the existing sea ice segmentation algorithms for SAR images often fail to consider long-range contextual dependencies when capturing multiscale features, resulting in an inability to fully exploit multiscale global contextual information. To address this limitation, we proposed a novel encoder–decoder structure network for multitask sea ice segmentation. Initially, a cross-scale interaction module was constructed in the encoder that utilizes cross attention to seamlessly capture multiscale features, effectively bridging the semantic information gap between different layers. Subsequently, a context transformer block based on efficient multihead self-attention was developed to model remote dependencies across spatial and channel dimensions, thereby enhancing the extraction of multiscale global contextual information. Furthermore, a channel patch module was introduced that allows for the strategic refinement of differential features to emphasize changing areas and suppress artifacts. In the final stages, a refined multiscale feature fusion module was embedded in the decoder to strategically integrate the feature maps generated, thus iteratively merging layered features for enhanced segmentation. Our experiments on the AI4Arctic Sea Ice Challenge Dataset show that MFGC-Net achieves outstanding performance in multitask sea ice segmentation compared with current state-of-the-art methods, as demonstrated by both quantitative and qualitative results.https://ieeexplore.ieee.org/document/10930574/Contextual informationmultiscale featuresmultitask learningsea ice segmentationsynthetic aperture radar (SAR) |
| spellingShingle | Tianen Ma Xinwei Chen Linlin Xu Pengfei Ma Peilin Yu MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Contextual information multiscale features multitask learning sea ice segmentation synthetic aperture radar (SAR) |
| title | MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation |
| title_full | MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation |
| title_fullStr | MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation |
| title_full_unstemmed | MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation |
| title_short | MFGC-Net: Bridging and Fusing Multiscale Features and Global Contexts for Multitask Sea Ice Fine Segmentation |
| title_sort | mfgc net bridging and fusing multiscale features and global contexts for multitask sea ice fine segmentation |
| topic | Contextual information multiscale features multitask learning sea ice segmentation synthetic aperture radar (SAR) |
| url | https://ieeexplore.ieee.org/document/10930574/ |
| work_keys_str_mv | AT tianenma mfgcnetbridgingandfusingmultiscalefeaturesandglobalcontextsformultitaskseaicefinesegmentation AT xinweichen mfgcnetbridgingandfusingmultiscalefeaturesandglobalcontextsformultitaskseaicefinesegmentation AT linlinxu mfgcnetbridgingandfusingmultiscalefeaturesandglobalcontextsformultitaskseaicefinesegmentation AT pengfeima mfgcnetbridgingandfusingmultiscalefeaturesandglobalcontextsformultitaskseaicefinesegmentation AT peilinyu mfgcnetbridgingandfusingmultiscalefeaturesandglobalcontextsformultitaskseaicefinesegmentation |