Atrous cGAN for SAR to Optical Image Translation
Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed gene...
Gespeichert in:
| Veröffentlicht in: | IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5 |
|---|---|
| Hauptverfasser: | , , , , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 5 |
|---|---|
| container_issue | |
| container_start_page | 1 |
| container_title | IEEE geoscience and remote sensing letters |
| container_volume | 19 |
| creator | Noa Turnes, Javier Castro, Jose David Bermudez Torres, Daliana Lobo Vega, Pedro Juan Soto Feitosa, Raul Queiroz Happ, Patrick N. |
| description | Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed generator and discriminator networks rely on atrous convolutions and incorporate an atrous spatial pyramid pooling (ASPP) module to enhance fine details in the generated optical image by exploiting spatial context at multiple scales. This letter reports experiments carried out to assess the performance of atrous-cGAN for the synthesis of Landsat-8 images from Sentinel-1A data based on three public data sets. The experimental analysis indicated that the atrous-cGAN consistently outperformed the classical pix2pix counterpart in terms of visual quality, similar to the true optical image, and as a feature learning tool for semantic segmentation. |
| doi_str_mv | 10.1109/LGRS.2020.3031199 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2610990333</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9241239</ieee_id><sourcerecordid>2610990333</sourcerecordid><originalsourceid>FETCH-LOGICAL-c402t-e8b8a3a9beca7b94477d210d96779ec4f8d642fc5b61ead45a7d2804590bb2023</originalsourceid><addsrcrecordid>eNo9kE9LAzEQxYMoWKsfQLwEPG-d_Nskx6XoWigW2greQjablS3bpibbg9_eXVqcywzMezO8H0KPBGaEgH5ZluvNjAKFGQNGiNZXaEKEUBkISa7HmYtMaPV1i-5S2gFQrpScICj6GE4Ju7L4wE2IeFOscR_w6ti3znZ4sbffHm-jPaTO9m043KObxnbJP1z6FH2-vW7n79lyVS7mxTJzHGifeVUpy6yuvLOy0pxLWVMCtc6l1N7xRtU5p40TVU68rbmww14BFxqqasjBpuj5fPcYw8_Jp97swikehpeG5kNiDWyoKSJnlYshpegbc4zt3sZfQ8CMYMwIxoxgzAXM4Hk6e1rv_b9eU04o0-wPYZVcsw</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2610990333</pqid></control><display><type>article</type><title>Atrous cGAN for SAR to Optical Image Translation</title><source>IEEE Electronic Library (IEL)</source><creator>Noa Turnes, Javier ; Castro, Jose David Bermudez ; Torres, Daliana Lobo ; Vega, Pedro Juan Soto ; Feitosa, Raul Queiroz ; Happ, Patrick N.</creator><creatorcontrib>Noa Turnes, Javier ; Castro, Jose David Bermudez ; Torres, Daliana Lobo ; Vega, Pedro Juan Soto ; Feitosa, Raul Queiroz ; Happ, Patrick N.</creatorcontrib><description>Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed generator and discriminator networks rely on atrous convolutions and incorporate an atrous spatial pyramid pooling (ASPP) module to enhance fine details in the generated optical image by exploiting spatial context at multiple scales. This letter reports experiments carried out to assess the performance of atrous-cGAN for the synthesis of Landsat-8 images from Sentinel-1A data based on three public data sets. The experimental analysis indicated that the atrous-cGAN consistently outperformed the classical pix2pix counterpart in terms of visual quality, similar to the true optical image, and as a feature learning tool for semantic segmentation.</description><identifier>ISSN: 1545-598X</identifier><identifier>EISSN: 1558-0571</identifier><identifier>DOI: 10.1109/LGRS.2020.3031199</identifier><identifier>CODEN: IGRSBY</identifier><language>eng</language><publisher>Piscataway: IEEE</publisher><subject>Artificial satellites ; Atrous spatial pyramid pooling (ASPP) ; Convolutional codes ; generative adversarial networks ; Generators ; Image enhancement ; Image quality ; Image segmentation ; Landsat ; Optical imaging ; Optical interferometry ; Optical sensors ; Performance assessment ; Radar imaging ; Remote sensing ; SAR (radar) ; Satellite imagery ; Synthesis ; Synthetic aperture radar ; synthetic aperture radar (SAR)-optical synthesis ; Translation</subject><ispartof>IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c402t-e8b8a3a9beca7b94477d210d96779ec4f8d642fc5b61ead45a7d2804590bb2023</citedby><cites>FETCH-LOGICAL-c402t-e8b8a3a9beca7b94477d210d96779ec4f8d642fc5b61ead45a7d2804590bb2023</cites><orcidid>0000-0001-9573-2228 ; 0000-0001-8344-5096 ; 0000-0002-4516-5787 ; 0000-0001-7916-9463 ; 0000-0001-5396-8531 ; 0000-0003-3280-5471</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/9241239$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,4010,27900,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9241239$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Noa Turnes, Javier</creatorcontrib><creatorcontrib>Castro, Jose David Bermudez</creatorcontrib><creatorcontrib>Torres, Daliana Lobo</creatorcontrib><creatorcontrib>Vega, Pedro Juan Soto</creatorcontrib><creatorcontrib>Feitosa, Raul Queiroz</creatorcontrib><creatorcontrib>Happ, Patrick N.</creatorcontrib><title>Atrous cGAN for SAR to Optical Image Translation</title><title>IEEE geoscience and remote sensing letters</title><addtitle>LGRS</addtitle><description>Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed generator and discriminator networks rely on atrous convolutions and incorporate an atrous spatial pyramid pooling (ASPP) module to enhance fine details in the generated optical image by exploiting spatial context at multiple scales. This letter reports experiments carried out to assess the performance of atrous-cGAN for the synthesis of Landsat-8 images from Sentinel-1A data based on three public data sets. The experimental analysis indicated that the atrous-cGAN consistently outperformed the classical pix2pix counterpart in terms of visual quality, similar to the true optical image, and as a feature learning tool for semantic segmentation.</description><subject>Artificial satellites</subject><subject>Atrous spatial pyramid pooling (ASPP)</subject><subject>Convolutional codes</subject><subject>generative adversarial networks</subject><subject>Generators</subject><subject>Image enhancement</subject><subject>Image quality</subject><subject>Image segmentation</subject><subject>Landsat</subject><subject>Optical imaging</subject><subject>Optical interferometry</subject><subject>Optical sensors</subject><subject>Performance assessment</subject><subject>Radar imaging</subject><subject>Remote sensing</subject><subject>SAR (radar)</subject><subject>Satellite imagery</subject><subject>Synthesis</subject><subject>Synthetic aperture radar</subject><subject>synthetic aperture radar (SAR)-optical synthesis</subject><subject>Translation</subject><issn>1545-598X</issn><issn>1558-0571</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2022</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><recordid>eNo9kE9LAzEQxYMoWKsfQLwEPG-d_Nskx6XoWigW2greQjablS3bpibbg9_eXVqcywzMezO8H0KPBGaEgH5ZluvNjAKFGQNGiNZXaEKEUBkISa7HmYtMaPV1i-5S2gFQrpScICj6GE4Ju7L4wE2IeFOscR_w6ti3znZ4sbffHm-jPaTO9m043KObxnbJP1z6FH2-vW7n79lyVS7mxTJzHGifeVUpy6yuvLOy0pxLWVMCtc6l1N7xRtU5p40TVU68rbmww14BFxqqasjBpuj5fPcYw8_Jp97swikehpeG5kNiDWyoKSJnlYshpegbc4zt3sZfQ8CMYMwIxoxgzAXM4Hk6e1rv_b9eU04o0-wPYZVcsw</recordid><startdate>2022</startdate><enddate>2022</enddate><creator>Noa Turnes, Javier</creator><creator>Castro, Jose David Bermudez</creator><creator>Torres, Daliana Lobo</creator><creator>Vega, Pedro Juan Soto</creator><creator>Feitosa, Raul Queiroz</creator><creator>Happ, Patrick N.</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TG</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>JQ2</scope><scope>KL.</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><orcidid>https://orcid.org/0000-0001-9573-2228</orcidid><orcidid>https://orcid.org/0000-0001-8344-5096</orcidid><orcidid>https://orcid.org/0000-0002-4516-5787</orcidid><orcidid>https://orcid.org/0000-0001-7916-9463</orcidid><orcidid>https://orcid.org/0000-0001-5396-8531</orcidid><orcidid>https://orcid.org/0000-0003-3280-5471</orcidid></search><sort><creationdate>2022</creationdate><title>Atrous cGAN for SAR to Optical Image Translation</title><author>Noa Turnes, Javier ; Castro, Jose David Bermudez ; Torres, Daliana Lobo ; Vega, Pedro Juan Soto ; Feitosa, Raul Queiroz ; Happ, Patrick N.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c402t-e8b8a3a9beca7b94477d210d96779ec4f8d642fc5b61ead45a7d2804590bb2023</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2022</creationdate><topic>Artificial satellites</topic><topic>Atrous spatial pyramid pooling (ASPP)</topic><topic>Convolutional codes</topic><topic>generative adversarial networks</topic><topic>Generators</topic><topic>Image enhancement</topic><topic>Image quality</topic><topic>Image segmentation</topic><topic>Landsat</topic><topic>Optical imaging</topic><topic>Optical interferometry</topic><topic>Optical sensors</topic><topic>Performance assessment</topic><topic>Radar imaging</topic><topic>Remote sensing</topic><topic>SAR (radar)</topic><topic>Satellite imagery</topic><topic>Synthesis</topic><topic>Synthetic aperture radar</topic><topic>synthetic aperture radar (SAR)-optical synthesis</topic><topic>Translation</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Noa Turnes, Javier</creatorcontrib><creatorcontrib>Castro, Jose David Bermudez</creatorcontrib><creatorcontrib>Torres, Daliana Lobo</creatorcontrib><creatorcontrib>Vega, Pedro Juan Soto</creatorcontrib><creatorcontrib>Feitosa, Raul Queiroz</creatorcontrib><creatorcontrib>Happ, Patrick N.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Meteorological & Geoastrophysical Abstracts</collection><collection>Water Resources Abstracts</collection><collection>Technology Research Database</collection><collection>Environmental Sciences and Pollution Management</collection><collection>ASFA: Aquatic Sciences and Fisheries Abstracts</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) 2: Ocean Technology, Policy & Non-Living Resources</collection><collection>ProQuest Computer Science Collection</collection><collection>Meteorological & Geoastrophysical Abstracts - Academic</collection><collection>Civil Engineering Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><jtitle>IEEE geoscience and remote sensing letters</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Noa Turnes, Javier</au><au>Castro, Jose David Bermudez</au><au>Torres, Daliana Lobo</au><au>Vega, Pedro Juan Soto</au><au>Feitosa, Raul Queiroz</au><au>Happ, Patrick N.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Atrous cGAN for SAR to Optical Image Translation</atitle><jtitle>IEEE geoscience and remote sensing letters</jtitle><stitle>LGRS</stitle><date>2022</date><risdate>2022</risdate><volume>19</volume><spage>1</spage><epage>5</epage><pages>1-5</pages><issn>1545-598X</issn><eissn>1558-0571</eissn><coden>IGRSBY</coden><abstract>Conditional (cGAN)-based methods proposed so far for synthetic aperture radar (SAR)-to-optical image synthesis tend to produce noisy and unsharp optical outcomes. In this work, we propose the atrous-cGAN, a novel cGAN architecture that improves the SAR-to-optical image translation. The proposed generator and discriminator networks rely on atrous convolutions and incorporate an atrous spatial pyramid pooling (ASPP) module to enhance fine details in the generated optical image by exploiting spatial context at multiple scales. This letter reports experiments carried out to assess the performance of atrous-cGAN for the synthesis of Landsat-8 images from Sentinel-1A data based on three public data sets. The experimental analysis indicated that the atrous-cGAN consistently outperformed the classical pix2pix counterpart in terms of visual quality, similar to the true optical image, and as a feature learning tool for semantic segmentation.</abstract><cop>Piscataway</cop><pub>IEEE</pub><doi>10.1109/LGRS.2020.3031199</doi><tpages>5</tpages><orcidid>https://orcid.org/0000-0001-9573-2228</orcidid><orcidid>https://orcid.org/0000-0001-8344-5096</orcidid><orcidid>https://orcid.org/0000-0002-4516-5787</orcidid><orcidid>https://orcid.org/0000-0001-7916-9463</orcidid><orcidid>https://orcid.org/0000-0001-5396-8531</orcidid><orcidid>https://orcid.org/0000-0003-3280-5471</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1545-598X |
| ispartof | IEEE geoscience and remote sensing letters, 2022, Vol.19, p.1-5 |
| issn | 1545-598X 1558-0571 |
| language | eng |
| recordid | cdi_proquest_journals_2610990333 |
| source | IEEE Electronic Library (IEL) |
| subjects | Artificial satellites Atrous spatial pyramid pooling (ASPP) Convolutional codes generative adversarial networks Generators Image enhancement Image quality Image segmentation Landsat Optical imaging Optical interferometry Optical sensors Performance assessment Radar imaging Remote sensing SAR (radar) Satellite imagery Synthesis Synthetic aperture radar synthetic aperture radar (SAR)-optical synthesis Translation |
| title | Atrous cGAN for SAR to Optical Image Translation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T03%3A54%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Atrous%20cGAN%20for%20SAR%20to%20Optical%20Image%20Translation&rft.jtitle=IEEE%20geoscience%20and%20remote%20sensing%20letters&rft.au=Noa%20Turnes,%20Javier&rft.date=2022&rft.volume=19&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.issn=1545-598X&rft.eissn=1558-0571&rft.coden=IGRSBY&rft_id=info:doi/10.1109/LGRS.2020.3031199&rft_dat=%3Cproquest_RIE%3E2610990333%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=2610990333&rft_id=info:pmid/&rft_ieee_id=9241239&rfr_iscdi=true |