On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT
International audience The above classification model (one 20x20 km imagette = one label) is then used over a full Wide Swath S-1 image using local class estimates with a convolution approach to provide a semantic segmentation. Multi-class (and multi-label , i.e. one pixel several classes) semantic...
Main Authors: | , , , , |
---|---|
Other Authors: | , , , , , , , , , , , |
Format: | Conference Object |
Language: | English |
Published: |
HAL CCSD
2019
|
Subjects: | |
Online Access: | https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/document https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/file/20190619_SWOTPoster_DLOcean.pdf |
id |
ftccsdartic:oai:HAL:hal-02156712v1 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |
op_collection_id |
ftccsdartic |
language |
English |
topic |
[STAT.AP]Statistics [stat]/Applications [stat.AP] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere |
spellingShingle |
[STAT.AP]Statistics [stat]/Applications [stat.AP] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere Longépé, Nicolas Husson, Romain Wang, Chen Mouche, Alexis Tandeo, Pierre On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
topic_facet |
[STAT.AP]Statistics [stat]/Applications [stat.AP] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere |
description |
International audience The above classification model (one 20x20 km imagette = one label) is then used over a full Wide Swath S-1 image using local class estimates with a convolution approach to provide a semantic segmentation. Multi-class (and multi-label , i.e. one pixel several classes) semantic segmentation is now feasible with DL , pending starting with a good and sufficient training database, and active learning process to enrich it, To this end, annotation tools and adequate framework should be consolidated and tuned to our problematic: 1) massive processing needed to raise specific issues (for instance, "sea ice" North of Madagascar should be re-tagged as internal waves), 2) additional information from ancillary metocean data might be provided , … The entire S-1 Wave Mode archive from 2016 is being processed. Below the occurrence of each class as classified by the DL model is provided on a monthly basis. This classified database could be used as input for a systematic collocation process with SWOT data. That will 1) help to understand Ka-band near nadir imaging processes for a given phenomenon, 2) serve during the Cal/val campaign, and 3) be used to build a training database with tagged SWOT images serving also DL model. With the upcoming launch of SWOT, new Ka-band near-nadir SAR image will be produced. Whereas the legacy of ocean SAR imaging is huge for L-C-or X-band SAR sensors with intermediate incidence angle, the interaction of Ka-band near-nadir EM waves and its associated SAR image formation lead to some uncertainties on how metocean features will be imaged on SWOT image. To name a few, atmospheric fronts, ocean fronts, rain cells, convective microcells, internal waves, gravity waves, biological slicks, upwelling or wind trails are phenomena that will be imaged by SWOT. These phenomena could be a source of errors and bias for SSH products. Meanwhile, they are of potential interest for the scientific communities. In this study, we aim to propose a methodology to flag and detect these phenomena ... |
author2 |
Collecte Localisation Satellites (CLS) Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER)-Centre National d'Études Spatiales Toulouse (CNES) Institut Français de Recherche pour l'Exploitation de la Mer - Brest (IFREMER Centre de Bretagne) Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER) Lab-STICC_IMTA_CID_TOMS Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC) École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT) Département Signal et Communications (IMT Atlantique - SC) IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) |
format |
Conference Object |
author |
Longépé, Nicolas Husson, Romain Wang, Chen Mouche, Alexis Tandeo, Pierre |
author_facet |
Longépé, Nicolas Husson, Romain Wang, Chen Mouche, Alexis Tandeo, Pierre |
author_sort |
Longépé, Nicolas |
title |
On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
title_short |
On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
title_full |
On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
title_fullStr |
On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
title_full_unstemmed |
On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT |
title_sort |
on the detection and segmentation of metocean features on sar images using deep learning: perspectives for swot |
publisher |
HAL CCSD |
publishDate |
2019 |
url |
https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/document https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/file/20190619_SWOTPoster_DLOcean.pdf |
op_coverage |
Talence, France |
genre |
Sea ice |
genre_facet |
Sea ice |
op_source |
SWOT Science Team Meeting https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 SWOT Science Team Meeting, Jun 2019, Talence, France |
op_relation |
hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/document https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/file/20190619_SWOTPoster_DLOcean.pdf |
op_rights |
info:eu-repo/semantics/OpenAccess |
_version_ |
1766195731695140864 |
spelling |
ftccsdartic:oai:HAL:hal-02156712v1 2023-05-15T18:18:57+02:00 On the detection and segmentation of metocean features on SAR images using Deep Learning: perspectives for SWOT Longépé, Nicolas Husson, Romain Wang, Chen Mouche, Alexis Tandeo, Pierre Collecte Localisation Satellites (CLS) Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER)-Centre National d'Études Spatiales Toulouse (CNES) Institut Français de Recherche pour l'Exploitation de la Mer - Brest (IFREMER Centre de Bretagne) Institut Français de Recherche pour l'Exploitation de la Mer (IFREMER) Lab-STICC_IMTA_CID_TOMS Laboratoire des sciences et techniques de l'information, de la communication et de la connaissance (Lab-STICC) École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-École Nationale d'Ingénieurs de Brest (ENIB)-Université de Bretagne Sud (UBS)-Université de Brest (UBO)-École Nationale Supérieure de Techniques Avancées Bretagne (ENSTA Bretagne)-Institut Mines-Télécom Paris (IMT)-Centre National de la Recherche Scientifique (CNRS)-Université Bretagne Loire (UBL)-IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT) Département Signal et Communications (IMT Atlantique - SC) IMT Atlantique Bretagne-Pays de la Loire (IMT Atlantique) Institut Mines-Télécom Paris (IMT)-Institut Mines-Télécom Paris (IMT) Talence, France 2019-06-17 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/document https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/file/20190619_SWOTPoster_DLOcean.pdf en eng HAL CCSD hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/document https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712/file/20190619_SWOTPoster_DLOcean.pdf info:eu-repo/semantics/OpenAccess SWOT Science Team Meeting https://hal-imt-atlantique.archives-ouvertes.fr/hal-02156712 SWOT Science Team Meeting, Jun 2019, Talence, France [STAT.AP]Statistics [stat]/Applications [stat.AP] [SDU.OCEAN]Sciences of the Universe [physics]/Ocean Atmosphere info:eu-repo/semantics/conferenceObject Poster communications 2019 ftccsdartic 2021-11-07T01:52:06Z International audience The above classification model (one 20x20 km imagette = one label) is then used over a full Wide Swath S-1 image using local class estimates with a convolution approach to provide a semantic segmentation. Multi-class (and multi-label , i.e. one pixel several classes) semantic segmentation is now feasible with DL , pending starting with a good and sufficient training database, and active learning process to enrich it, To this end, annotation tools and adequate framework should be consolidated and tuned to our problematic: 1) massive processing needed to raise specific issues (for instance, "sea ice" North of Madagascar should be re-tagged as internal waves), 2) additional information from ancillary metocean data might be provided , … The entire S-1 Wave Mode archive from 2016 is being processed. Below the occurrence of each class as classified by the DL model is provided on a monthly basis. This classified database could be used as input for a systematic collocation process with SWOT data. That will 1) help to understand Ka-band near nadir imaging processes for a given phenomenon, 2) serve during the Cal/val campaign, and 3) be used to build a training database with tagged SWOT images serving also DL model. With the upcoming launch of SWOT, new Ka-band near-nadir SAR image will be produced. Whereas the legacy of ocean SAR imaging is huge for L-C-or X-band SAR sensors with intermediate incidence angle, the interaction of Ka-band near-nadir EM waves and its associated SAR image formation lead to some uncertainties on how metocean features will be imaged on SWOT image. To name a few, atmospheric fronts, ocean fronts, rain cells, convective microcells, internal waves, gravity waves, biological slicks, upwelling or wind trails are phenomena that will be imaged by SWOT. These phenomena could be a source of errors and bias for SSH products. Meanwhile, they are of potential interest for the scientific communities. In this study, we aim to propose a methodology to flag and detect these phenomena ... Conference Object Sea ice Archive ouverte HAL (Hyper Article en Ligne, CCSD - Centre pour la Communication Scientifique Directe) |