Submesoscale oceanic eddy detection in SAR images using context and edge association network
Oceanic eddies have a non-negligible impact on ocean energy transfer, nutrient distribution, and biological migration in global oceans. The fine detection of oceanic eddies is significant for the development of marine science. Remarkable achievements of eddy recognition were achieved by mining the s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-12-01
|
| Series: | Frontiers in Marine Science |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fmars.2022.1023624/full |
| _version_ | 1811177681803280384 |
|---|---|
| author | Linghui Xia Ge Chen Ge Chen Xiaoyan Chen Linyao Ge Baoxiang Huang Baoxiang Huang |
| author_facet | Linghui Xia Ge Chen Ge Chen Xiaoyan Chen Linyao Ge Baoxiang Huang Baoxiang Huang |
| author_sort | Linghui Xia |
| collection | DOAJ |
| description | Oceanic eddies have a non-negligible impact on ocean energy transfer, nutrient distribution, and biological migration in global oceans. The fine detection of oceanic eddies is significant for the development of marine science. Remarkable achievements of eddy recognition were achieved by mining the satellite altimeter data and its derived data. However, due to the limited spatial resolution of the altimeters, it is difficult to detect the submesoscale oceanic eddies with radial dimensions less than 10 km. Different from the previous works, the context and edge association network (CEA-Net) is proposed to identify submesoscale oceanic eddies with high spatial resolution Sentinel-1 data. The edge information fusion module (EIFM) is designed to associate the context and edge feature more accurately and efficiently. Furthermore, a multi-scale eddy detection strategy is proposed and applied to Sentinel-1 interferometric wide swath data to solve the scale problem of oceanic eddy detection. Specifically, a manually interpreted dataset, SAR-Eddy 2019, was constructed to address the dilemma of insufficient datasets for submesoscale oceanic eddy detection. The experimental results demonstrate that CEA-Net can outperform other mainstream models with the highest mAP reaching 85.47% with SAR-Eddy 2019 dataset. The CEA-Net proposed in this research provides important significance for the study of submesoscale oceanic eddies. |
| first_indexed | 2024-04-11T06:06:27Z |
| format | Article |
| id | doaj.art-691b03d8c46143c28f594daccc781471 |
| institution | Directory Open Access Journal |
| issn | 2296-7745 |
| language | English |
| last_indexed | 2024-04-11T06:06:27Z |
| publishDate | 2022-12-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Marine Science |
| spelling | doaj.art-691b03d8c46143c28f594daccc7814712022-12-22T04:41:30ZengFrontiers Media S.A.Frontiers in Marine Science2296-77452022-12-01910.3389/fmars.2022.10236241023624Submesoscale oceanic eddy detection in SAR images using context and edge association networkLinghui Xia0Ge Chen1Ge Chen2Xiaoyan Chen3Linyao Ge4Baoxiang Huang5Baoxiang Huang6Frontiers Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China, Qingdao, Shandong, ChinaFrontiers Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China, Qingdao, Shandong, ChinaLaboratory for Regional Oceanography and Numerical Modeling, Laoshan Laboratory, Qingdao, Shandong, ChinaFrontiers Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China, Qingdao, Shandong, ChinaFrontiers Science Center for Deep Ocean Multispheres and Earth System, Ocean University of China, Qingdao, Shandong, ChinaLaboratory for Regional Oceanography and Numerical Modeling, Laoshan Laboratory, Qingdao, Shandong, ChinaDepartment of Computer Science and Technology, Qingdao University, Qingdao, ChinaOceanic eddies have a non-negligible impact on ocean energy transfer, nutrient distribution, and biological migration in global oceans. The fine detection of oceanic eddies is significant for the development of marine science. Remarkable achievements of eddy recognition were achieved by mining the satellite altimeter data and its derived data. However, due to the limited spatial resolution of the altimeters, it is difficult to detect the submesoscale oceanic eddies with radial dimensions less than 10 km. Different from the previous works, the context and edge association network (CEA-Net) is proposed to identify submesoscale oceanic eddies with high spatial resolution Sentinel-1 data. The edge information fusion module (EIFM) is designed to associate the context and edge feature more accurately and efficiently. Furthermore, a multi-scale eddy detection strategy is proposed and applied to Sentinel-1 interferometric wide swath data to solve the scale problem of oceanic eddy detection. Specifically, a manually interpreted dataset, SAR-Eddy 2019, was constructed to address the dilemma of insufficient datasets for submesoscale oceanic eddy detection. The experimental results demonstrate that CEA-Net can outperform other mainstream models with the highest mAP reaching 85.47% with SAR-Eddy 2019 dataset. The CEA-Net proposed in this research provides important significance for the study of submesoscale oceanic eddies.https://www.frontiersin.org/articles/10.3389/fmars.2022.1023624/fullsubmesoscale oceanic eddyobject detectiondeep learningmultiple spatial-scaleSentinel-1 |
| spellingShingle | Linghui Xia Ge Chen Ge Chen Xiaoyan Chen Linyao Ge Baoxiang Huang Baoxiang Huang Submesoscale oceanic eddy detection in SAR images using context and edge association network Frontiers in Marine Science submesoscale oceanic eddy object detection deep learning multiple spatial-scale Sentinel-1 |
| title | Submesoscale oceanic eddy detection in SAR images using context and edge association network |
| title_full | Submesoscale oceanic eddy detection in SAR images using context and edge association network |
| title_fullStr | Submesoscale oceanic eddy detection in SAR images using context and edge association network |
| title_full_unstemmed | Submesoscale oceanic eddy detection in SAR images using context and edge association network |
| title_short | Submesoscale oceanic eddy detection in SAR images using context and edge association network |
| title_sort | submesoscale oceanic eddy detection in sar images using context and edge association network |
| topic | submesoscale oceanic eddy object detection deep learning multiple spatial-scale Sentinel-1 |
| url | https://www.frontiersin.org/articles/10.3389/fmars.2022.1023624/full |
| work_keys_str_mv | AT linghuixia submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT gechen submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT gechen submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT xiaoyanchen submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT linyaoge submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT baoxianghuang submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork AT baoxianghuang submesoscaleoceaniceddydetectioninsarimagesusingcontextandedgeassociationnetwork |