Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing
This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric att...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on geoscience and remote sensing 2019-05, Vol.57 (5), p.2709-2724 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 2724 |
|---|---|
| container_issue | 5 |
| container_start_page | 2709 |
| container_title | IEEE transactions on geoscience and remote sensing |
| container_volume | 57 |
| creator | Salembier, Philippe Liesegang, Sergi Lopez-Martinez, Carlos |
| description | This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters , two new filtering notions emerge from this analysis: tree and branch filters . Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the tree-based representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public. |
| doi_str_mv | 10.1109/TGRS.2018.2876603 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_2215067133</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>8529215</ieee_id><sourcerecordid>2215067133</sourcerecordid><originalsourceid>FETCH-LOGICAL-c378t-1b1475321ba0d0037aea728fef44557c8a1a495d5ed02483782a99bca7e06a883</originalsourceid><addsrcrecordid>eNpNkE1Lw0AQhhdRsFZ_gHhZ8Jy6n9nNsX7VQkVpK3hbpptpm9ImcTcF_femtqiHYZhhnpfhIeSSsx7nLLuZDsaTnmDc9oQ1acrkEelwrW3CUqWOSYfxLE2EzcQpOYtxxRhXmpsOeZ8si5reY4O-KaqSFiWd9Md0uIEFRnoLEXParp_hswmIdIx1wIhlAz_XUOZ0EKBe0kmxKGFNX0PlMcaiXJyTkzmsI14cepe8PT5M756S0ctgeNcfJV4a2yR8xpXRUvAZsJwxaQDBCDvHuVJaG2-Bg8p0rjFnQtmWEZBlMw8GWQrWyi7h-1wft94F9Bg8NK6C4m_YlWBGOCnTLFUtc71n6lB9bDE2blVtQ_t_dEJwzVLDpfyXHKoYA85dHYoNhC_HmdtJdzvpbifdHaS3zNWeKRDx995qkbW58hsSKnwc</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2215067133</pqid></control><display><type>article</type><title>Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing</title><source>IEEE Electronic Library (IEL)</source><creator>Salembier, Philippe ; Liesegang, Sergi ; Lopez-Martinez, Carlos</creator><creatorcontrib>Salembier, Philippe ; Liesegang, Sergi ; Lopez-Martinez, Carlos</creatorcontrib><description>This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters , two new filtering notions emerge from this analysis: tree and branch filters . Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the tree-based representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public.</description><identifier>ISSN: 0196-2892</identifier><identifier>EISSN: 1558-0644</identifier><identifier>DOI: 10.1109/TGRS.2018.2876603</identifier><identifier>CODEN: IGRSD2</identifier><language>eng</language><publisher>New York: IEEE</publisher><subject>Algorithms ; Architecture ; Branch filter ; Ciències de la terra ; Ciències de la terra i de la vida ; Correlation ; Detection ; Earth sciences ; Enginyeria agroalimentària ; Enginyeria de la telecomunicació ; Filters ; Filtration ; Graph filter ; Graph signal processing ; Graphical representations ; Graphs ; Image detection ; Image processing ; Information processing ; Learning algorithms ; Machine learning ; Marine vehicles ; Maxtree ; Nodes ; Nonlinear analysis ; Object detection ; Radar detection ; Radar imaging ; Radiocomunicació i exploració electromagnètica ; Radiometry ; Remote sensing ; SAR (radar) ; Ship detection ; Ships ; Signal processing ; support vector machine (SVM) ; Synthetic aperture radar ; synthetic-aperture radar (SAR) ; Teledetecció ; Tree filter ; Trees ; Àrees temàtiques de la UPC</subject><ispartof>IEEE transactions on geoscience and remote sensing, 2019-05, Vol.57 (5), p.2709-2724</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019</rights><rights>info:eu-repo/semantics/openAccess</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c378t-1b1475321ba0d0037aea728fef44557c8a1a495d5ed02483782a99bca7e06a883</citedby><cites>FETCH-LOGICAL-c378t-1b1475321ba0d0037aea728fef44557c8a1a495d5ed02483782a99bca7e06a883</cites><orcidid>0000-0001-8884-9604 ; 0000-0002-7806-4755</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/8529215$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,780,784,796,885,26974,27924,27925,54758</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/8529215$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Salembier, Philippe</creatorcontrib><creatorcontrib>Liesegang, Sergi</creatorcontrib><creatorcontrib>Lopez-Martinez, Carlos</creatorcontrib><title>Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing</title><title>IEEE transactions on geoscience and remote sensing</title><addtitle>TGRS</addtitle><description>This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters , two new filtering notions emerge from this analysis: tree and branch filters . Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the tree-based representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public.</description><subject>Algorithms</subject><subject>Architecture</subject><subject>Branch filter</subject><subject>Ciències de la terra</subject><subject>Ciències de la terra i de la vida</subject><subject>Correlation</subject><subject>Detection</subject><subject>Earth sciences</subject><subject>Enginyeria agroalimentària</subject><subject>Enginyeria de la telecomunicació</subject><subject>Filters</subject><subject>Filtration</subject><subject>Graph filter</subject><subject>Graph signal processing</subject><subject>Graphical representations</subject><subject>Graphs</subject><subject>Image detection</subject><subject>Image processing</subject><subject>Information processing</subject><subject>Learning algorithms</subject><subject>Machine learning</subject><subject>Marine vehicles</subject><subject>Maxtree</subject><subject>Nodes</subject><subject>Nonlinear analysis</subject><subject>Object detection</subject><subject>Radar detection</subject><subject>Radar imaging</subject><subject>Radiocomunicació i exploració electromagnètica</subject><subject>Radiometry</subject><subject>Remote sensing</subject><subject>SAR (radar)</subject><subject>Ship detection</subject><subject>Ships</subject><subject>Signal processing</subject><subject>support vector machine (SVM)</subject><subject>Synthetic aperture radar</subject><subject>synthetic-aperture radar (SAR)</subject><subject>Teledetecció</subject><subject>Tree filter</subject><subject>Trees</subject><subject>Àrees temàtiques de la UPC</subject><issn>0196-2892</issn><issn>1558-0644</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2019</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>XX2</sourceid><recordid>eNpNkE1Lw0AQhhdRsFZ_gHhZ8Jy6n9nNsX7VQkVpK3hbpptpm9ImcTcF_femtqiHYZhhnpfhIeSSsx7nLLuZDsaTnmDc9oQ1acrkEelwrW3CUqWOSYfxLE2EzcQpOYtxxRhXmpsOeZ8si5reY4O-KaqSFiWd9Md0uIEFRnoLEXParp_hswmIdIx1wIhlAz_XUOZ0EKBe0kmxKGFNX0PlMcaiXJyTkzmsI14cepe8PT5M756S0ctgeNcfJV4a2yR8xpXRUvAZsJwxaQDBCDvHuVJaG2-Bg8p0rjFnQtmWEZBlMw8GWQrWyi7h-1wft94F9Bg8NK6C4m_YlWBGOCnTLFUtc71n6lB9bDE2blVtQ_t_dEJwzVLDpfyXHKoYA85dHYoNhC_HmdtJdzvpbifdHaS3zNWeKRDx995qkbW58hsSKnwc</recordid><startdate>20190501</startdate><enddate>20190501</enddate><creator>Salembier, Philippe</creator><creator>Liesegang, Sergi</creator><creator>Lopez-Martinez, Carlos</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><general>Institute of Electrical and Electronics Engineers (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7UA</scope><scope>8FD</scope><scope>C1K</scope><scope>F1W</scope><scope>FR3</scope><scope>H8D</scope><scope>H96</scope><scope>KR7</scope><scope>L.G</scope><scope>L7M</scope><scope>XX2</scope><orcidid>https://orcid.org/0000-0001-8884-9604</orcidid><orcidid>https://orcid.org/0000-0002-7806-4755</orcidid></search><sort><creationdate>20190501</creationdate><title>Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing</title><author>Salembier, Philippe ; Liesegang, Sergi ; Lopez-Martinez, Carlos</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c378t-1b1475321ba0d0037aea728fef44557c8a1a495d5ed02483782a99bca7e06a883</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Algorithms</topic><topic>Architecture</topic><topic>Branch filter</topic><topic>Ciències de la terra</topic><topic>Ciències de la terra i de la vida</topic><topic>Correlation</topic><topic>Detection</topic><topic>Earth sciences</topic><topic>Enginyeria agroalimentària</topic><topic>Enginyeria de la telecomunicació</topic><topic>Filters</topic><topic>Filtration</topic><topic>Graph filter</topic><topic>Graph signal processing</topic><topic>Graphical representations</topic><topic>Graphs</topic><topic>Image detection</topic><topic>Image processing</topic><topic>Information processing</topic><topic>Learning algorithms</topic><topic>Machine learning</topic><topic>Marine vehicles</topic><topic>Maxtree</topic><topic>Nodes</topic><topic>Nonlinear analysis</topic><topic>Object detection</topic><topic>Radar detection</topic><topic>Radar imaging</topic><topic>Radiocomunicació i exploració electromagnètica</topic><topic>Radiometry</topic><topic>Remote sensing</topic><topic>SAR (radar)</topic><topic>Ship detection</topic><topic>Ships</topic><topic>Signal processing</topic><topic>support vector machine (SVM)</topic><topic>Synthetic aperture radar</topic><topic>synthetic-aperture radar (SAR)</topic><topic>Teledetecció</topic><topic>Tree filter</topic><topic>Trees</topic><topic>Àrees temàtiques de la UPC</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Salembier, Philippe</creatorcontrib><creatorcontrib>Liesegang, Sergi</creatorcontrib><creatorcontrib>Lopez-Martinez, Carlos</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>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>Civil Engineering Abstracts</collection><collection>Aquatic Science & Fisheries Abstracts (ASFA) Professional</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Recercat</collection><jtitle>IEEE transactions on geoscience and remote sensing</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Salembier, Philippe</au><au>Liesegang, Sergi</au><au>Lopez-Martinez, Carlos</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing</atitle><jtitle>IEEE transactions on geoscience and remote sensing</jtitle><stitle>TGRS</stitle><date>2019-05-01</date><risdate>2019</risdate><volume>57</volume><issue>5</issue><spage>2709</spage><epage>2724</epage><pages>2709-2724</pages><issn>0196-2892</issn><eissn>1558-0644</eissn><coden>IGRSD2</coden><abstract>This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters , two new filtering notions emerge from this analysis: tree and branch filters . Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the tree-based representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public.</abstract><cop>New York</cop><pub>IEEE</pub><doi>10.1109/TGRS.2018.2876603</doi><tpages>16</tpages><orcidid>https://orcid.org/0000-0001-8884-9604</orcidid><orcidid>https://orcid.org/0000-0002-7806-4755</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0196-2892 |
| ispartof | IEEE transactions on geoscience and remote sensing, 2019-05, Vol.57 (5), p.2709-2724 |
| issn | 0196-2892 1558-0644 |
| language | eng |
| recordid | cdi_proquest_journals_2215067133 |
| source | IEEE Electronic Library (IEL) |
| subjects | Algorithms Architecture Branch filter Ciències de la terra Ciències de la terra i de la vida Correlation Detection Earth sciences Enginyeria agroalimentària Enginyeria de la telecomunicació Filters Filtration Graph filter Graph signal processing Graphical representations Graphs Image detection Image processing Information processing Learning algorithms Machine learning Marine vehicles Maxtree Nodes Nonlinear analysis Object detection Radar detection Radar imaging Radiocomunicació i exploració electromagnètica Radiometry Remote sensing SAR (radar) Ship detection Ships Signal processing support vector machine (SVM) Synthetic aperture radar synthetic-aperture radar (SAR) Teledetecció Tree filter Trees Àrees temàtiques de la UPC |
| title | Ship Detection in SAR Images Based on Maxtree Representation and Graph Signal Processing |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T13%3A14%3A31IST&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=Ship%20Detection%20in%20SAR%20Images%20Based%20on%20Maxtree%20Representation%20and%20Graph%20Signal%20Processing&rft.jtitle=IEEE%20transactions%20on%20geoscience%20and%20remote%20sensing&rft.au=Salembier,%20Philippe&rft.date=2019-05-01&rft.volume=57&rft.issue=5&rft.spage=2709&rft.epage=2724&rft.pages=2709-2724&rft.issn=0196-2892&rft.eissn=1558-0644&rft.coden=IGRSD2&rft_id=info:doi/10.1109/TGRS.2018.2876603&rft_dat=%3Cproquest_RIE%3E2215067133%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=2215067133&rft_id=info:pmid/&rft_ieee_id=8529215&rfr_iscdi=true |