Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers
A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on cybernetics 2010-10, Vol.40 (5), p.1267-1279 |
|---|---|
| Hauptverfasser: | , , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1279 |
|---|---|
| container_issue | 5 |
| container_start_page | 1267 |
| container_title | IEEE transactions on cybernetics |
| container_volume | 40 |
| creator | Tarabalka, Y Chanussot, J Benediktsson, J A |
| description | A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed, and the most reliable classified pixels are chosen as markers. Each classification-derived marker is associated with a class label. Each tree in the MSF grown from a marker forms a region in the segmentation map. By assigning a class of each marker to all the pixels within the region grown from this marker, a spectral-spatial classification map is obtained. Furthermore, the classification map is refined using the results of a pixelwise classification and a majority voting within the spatially connected regions. Experimental results are presented for three hyperspectral airborne images. The use of different dissimilarity measures for the construction of the MSF is investigated. The proposed scheme improves classification accuracies, when compared to previously proposed classification techniques, and provides accurate segmentation and classification maps. |
| doi_str_mv | 10.1109/TSMCB.2009.2037132 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_ieee_primary_5371866</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5371866</ieee_id><sourcerecordid>2717301631</sourcerecordid><originalsourceid>FETCH-LOGICAL-c527t-d1415d0920b5ac2117e0afd31240d7e9e8da4376420e5700cfa940b8d1255a813</originalsourceid><addsrcrecordid>eNp9kc2O0zAUhSMEYoaBFwAJWWIBLDJc_8XxslR0OlIrFp1ZW27iFA-JnbETUFe8Og4pXbBgY1vH3zny9cmy1xiuMQb56W63XX6-JgAyLVRgSp5kl1gynAOT5Gk6Q0lzxrC8yF7E-ACJBCmeZxfJwzFlxWX2a2cOnXGDHqx3SLsaLVsdo21sNUu-Qetjb0LsTTUE3aLbTh9MRPfRugPaWme7sUO7Xjs3CSsfTBzQTfA_HVoF36HFOPguZVW6bY9oZ9qUY2q01eF7Sn2ZPWt0G82r036V3a--3C3X-ebrze1ysckrTsSQ15hhXoMksOe6IhgLA7qpKSYMamGkKWvNqCgYAcMFQNVoyWBf1phwrktMr7KPc-433ao-2E6Ho_LaqvVioyYt_YgoS1b-mNj3M9sH_zimcVRnY2XaVjvjx6gE57gATmQiP_yXxEVqhXMmaELf_YM--DG4NLPCQAShAvgUSGaqCj7GYJrzWzGoqXT1p3Q1la5OpSfT21P0uO9Mfbb8bTkBb2bAGmPO1zy5y6KgvwFIyK-I</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1027237059</pqid></control><display><type>article</type><title>Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers</title><source>IEEE/IET Electronic Library</source><creator>Tarabalka, Y ; Chanussot, J ; Benediktsson, J A</creator><creatorcontrib>Tarabalka, Y ; Chanussot, J ; Benediktsson, J A</creatorcontrib><description>A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed, and the most reliable classified pixels are chosen as markers. Each classification-derived marker is associated with a class label. Each tree in the MSF grown from a marker forms a region in the segmentation map. By assigning a class of each marker to all the pixels within the region grown from this marker, a spectral-spatial classification map is obtained. Furthermore, the classification map is refined using the results of a pixelwise classification and a majority voting within the spatially connected regions. Experimental results are presented for three hyperspectral airborne images. The use of different dissimilarity measures for the construction of the MSF is investigated. The proposed scheme improves classification accuracies, when compared to previously proposed classification techniques, and provides accurate segmentation and classification maps.</description><identifier>ISSN: 1083-4419</identifier><identifier>ISSN: 2168-2267</identifier><identifier>EISSN: 1941-0492</identifier><identifier>EISSN: 2168-2275</identifier><identifier>DOI: 10.1109/TSMCB.2009.2037132</identifier><identifier>PMID: 20051346</identifier><identifier>CODEN: ITSCFI</identifier><language>eng</language><publisher>United States: IEEE</publisher><subject>Algorithms ; Artificial Intelligence ; Biomarkers - analysis ; Classification ; Computer Science ; Construction ; Cybernetics ; Decision Support Techniques ; Environmental Monitoring - methods ; Forests ; hyperspectral images ; Hyperspectral imaging ; Hyperspectral sensors ; Image classification ; Image Processing ; Image segmentation ; Laboratories ; Layout ; Machine vision ; marker selection ; Markers ; minimum spanning forest (MSF) ; Pattern Recognition, Automated - methods ; Pixel ; Pixels ; Segmentation ; Spectrum Analysis - methods ; Speech ; Studies ; Trees - chemistry ; Trees - classification ; Voting</subject><ispartof>IEEE transactions on cybernetics, 2010-10, Vol.40 (5), p.1267-1279</ispartof><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Oct 2010</rights><rights>Distributed under a Creative Commons Attribution 4.0 International License</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c527t-d1415d0920b5ac2117e0afd31240d7e9e8da4376420e5700cfa940b8d1255a813</citedby><cites>FETCH-LOGICAL-c527t-d1415d0920b5ac2117e0afd31240d7e9e8da4376420e5700cfa940b8d1255a813</cites><orcidid>0000-0003-4817-2875</orcidid></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/5371866$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,314,777,781,793,882,27905,27906,54739</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5371866$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/20051346$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink><backlink>$$Uhttps://hal.science/hal-00578848$$DView record in HAL$$Hfree_for_read</backlink></links><search><creatorcontrib>Tarabalka, Y</creatorcontrib><creatorcontrib>Chanussot, J</creatorcontrib><creatorcontrib>Benediktsson, J A</creatorcontrib><title>Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers</title><title>IEEE transactions on cybernetics</title><addtitle>TSMCB</addtitle><addtitle>IEEE Trans Syst Man Cybern B Cybern</addtitle><description>A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed, and the most reliable classified pixels are chosen as markers. Each classification-derived marker is associated with a class label. Each tree in the MSF grown from a marker forms a region in the segmentation map. By assigning a class of each marker to all the pixels within the region grown from this marker, a spectral-spatial classification map is obtained. Furthermore, the classification map is refined using the results of a pixelwise classification and a majority voting within the spatially connected regions. Experimental results are presented for three hyperspectral airborne images. The use of different dissimilarity measures for the construction of the MSF is investigated. The proposed scheme improves classification accuracies, when compared to previously proposed classification techniques, and provides accurate segmentation and classification maps.</description><subject>Algorithms</subject><subject>Artificial Intelligence</subject><subject>Biomarkers - analysis</subject><subject>Classification</subject><subject>Computer Science</subject><subject>Construction</subject><subject>Cybernetics</subject><subject>Decision Support Techniques</subject><subject>Environmental Monitoring - methods</subject><subject>Forests</subject><subject>hyperspectral images</subject><subject>Hyperspectral imaging</subject><subject>Hyperspectral sensors</subject><subject>Image classification</subject><subject>Image Processing</subject><subject>Image segmentation</subject><subject>Laboratories</subject><subject>Layout</subject><subject>Machine vision</subject><subject>marker selection</subject><subject>Markers</subject><subject>minimum spanning forest (MSF)</subject><subject>Pattern Recognition, Automated - methods</subject><subject>Pixel</subject><subject>Pixels</subject><subject>Segmentation</subject><subject>Spectrum Analysis - methods</subject><subject>Speech</subject><subject>Studies</subject><subject>Trees - chemistry</subject><subject>Trees - classification</subject><subject>Voting</subject><issn>1083-4419</issn><issn>2168-2267</issn><issn>1941-0492</issn><issn>2168-2275</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2010</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNp9kc2O0zAUhSMEYoaBFwAJWWIBLDJc_8XxslR0OlIrFp1ZW27iFA-JnbETUFe8Og4pXbBgY1vH3zny9cmy1xiuMQb56W63XX6-JgAyLVRgSp5kl1gynAOT5Gk6Q0lzxrC8yF7E-ACJBCmeZxfJwzFlxWX2a2cOnXGDHqx3SLsaLVsdo21sNUu-Qetjb0LsTTUE3aLbTh9MRPfRugPaWme7sUO7Xjs3CSsfTBzQTfA_HVoF36HFOPguZVW6bY9oZ9qUY2q01eF7Sn2ZPWt0G82r036V3a--3C3X-ebrze1ysckrTsSQ15hhXoMksOe6IhgLA7qpKSYMamGkKWvNqCgYAcMFQNVoyWBf1phwrktMr7KPc-433ao-2E6Ho_LaqvVioyYt_YgoS1b-mNj3M9sH_zimcVRnY2XaVjvjx6gE57gATmQiP_yXxEVqhXMmaELf_YM--DG4NLPCQAShAvgUSGaqCj7GYJrzWzGoqXT1p3Q1la5OpSfT21P0uO9Mfbb8bTkBb2bAGmPO1zy5y6KgvwFIyK-I</recordid><startdate>20101001</startdate><enddate>20101001</enddate><creator>Tarabalka, Y</creator><creator>Chanussot, J</creator><creator>Benediktsson, J A</creator><general>IEEE</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><general>Institute of Electrical and Electronics Engineers</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>7TB</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>H8D</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><scope>1XC</scope><scope>VOOES</scope><orcidid>https://orcid.org/0000-0003-4817-2875</orcidid></search><sort><creationdate>20101001</creationdate><title>Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers</title><author>Tarabalka, Y ; Chanussot, J ; Benediktsson, J A</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c527t-d1415d0920b5ac2117e0afd31240d7e9e8da4376420e5700cfa940b8d1255a813</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Algorithms</topic><topic>Artificial Intelligence</topic><topic>Biomarkers - analysis</topic><topic>Classification</topic><topic>Computer Science</topic><topic>Construction</topic><topic>Cybernetics</topic><topic>Decision Support Techniques</topic><topic>Environmental Monitoring - methods</topic><topic>Forests</topic><topic>hyperspectral images</topic><topic>Hyperspectral imaging</topic><topic>Hyperspectral sensors</topic><topic>Image classification</topic><topic>Image Processing</topic><topic>Image segmentation</topic><topic>Laboratories</topic><topic>Layout</topic><topic>Machine vision</topic><topic>marker selection</topic><topic>Markers</topic><topic>minimum spanning forest (MSF)</topic><topic>Pattern Recognition, Automated - methods</topic><topic>Pixel</topic><topic>Pixels</topic><topic>Segmentation</topic><topic>Spectrum Analysis - methods</topic><topic>Speech</topic><topic>Studies</topic><topic>Trees - chemistry</topic><topic>Trees - classification</topic><topic>Voting</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Tarabalka, Y</creatorcontrib><creatorcontrib>Chanussot, J</creatorcontrib><creatorcontrib>Benediktsson, J A</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005–Present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEEE/IET Electronic Library</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Mechanical & Transportation Engineering Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><collection>Aerospace Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><collection>Hyper Article en Ligne (HAL)</collection><collection>Hyper Article en Ligne (HAL) (Open Access)</collection><jtitle>IEEE transactions on cybernetics</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Tarabalka, Y</au><au>Chanussot, J</au><au>Benediktsson, J A</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers</atitle><jtitle>IEEE transactions on cybernetics</jtitle><stitle>TSMCB</stitle><addtitle>IEEE Trans Syst Man Cybern B Cybern</addtitle><date>2010-10-01</date><risdate>2010</risdate><volume>40</volume><issue>5</issue><spage>1267</spage><epage>1279</epage><pages>1267-1279</pages><issn>1083-4419</issn><issn>2168-2267</issn><eissn>1941-0492</eissn><eissn>2168-2275</eissn><coden>ITSCFI</coden><abstract>A new method for segmentation and classification of hyperspectral images is proposed. The method is based on the construction of a minimum spanning forest (MSF) from region markers. Markers are defined automatically from classification results. For this purpose, pixelwise classification is performed, and the most reliable classified pixels are chosen as markers. Each classification-derived marker is associated with a class label. Each tree in the MSF grown from a marker forms a region in the segmentation map. By assigning a class of each marker to all the pixels within the region grown from this marker, a spectral-spatial classification map is obtained. Furthermore, the classification map is refined using the results of a pixelwise classification and a majority voting within the spatially connected regions. Experimental results are presented for three hyperspectral airborne images. The use of different dissimilarity measures for the construction of the MSF is investigated. The proposed scheme improves classification accuracies, when compared to previously proposed classification techniques, and provides accurate segmentation and classification maps.</abstract><cop>United States</cop><pub>IEEE</pub><pmid>20051346</pmid><doi>10.1109/TSMCB.2009.2037132</doi><tpages>13</tpages><orcidid>https://orcid.org/0000-0003-4817-2875</orcidid><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1083-4419 |
| ispartof | IEEE transactions on cybernetics, 2010-10, Vol.40 (5), p.1267-1279 |
| issn | 1083-4419 2168-2267 1941-0492 2168-2275 |
| language | eng |
| recordid | cdi_ieee_primary_5371866 |
| source | IEEE/IET Electronic Library |
| subjects | Algorithms Artificial Intelligence Biomarkers - analysis Classification Computer Science Construction Cybernetics Decision Support Techniques Environmental Monitoring - methods Forests hyperspectral images Hyperspectral imaging Hyperspectral sensors Image classification Image Processing Image segmentation Laboratories Layout Machine vision marker selection Markers minimum spanning forest (MSF) Pattern Recognition, Automated - methods Pixel Pixels Segmentation Spectrum Analysis - methods Speech Studies Trees - chemistry Trees - classification Voting |
| title | Segmentation and Classification of Hyperspectral Images Using Minimum Spanning Forest Grown From Automatically Selected Markers |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-17T17%3A22%3A54IST&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=Segmentation%20and%20Classification%20of%20Hyperspectral%20Images%20Using%20Minimum%20Spanning%20Forest%20Grown%20From%20Automatically%20Selected%20Markers&rft.jtitle=IEEE%20transactions%20on%20cybernetics&rft.au=Tarabalka,%20Y&rft.date=2010-10-01&rft.volume=40&rft.issue=5&rft.spage=1267&rft.epage=1279&rft.pages=1267-1279&rft.issn=1083-4419&rft.eissn=1941-0492&rft.coden=ITSCFI&rft_id=info:doi/10.1109/TSMCB.2009.2037132&rft_dat=%3Cproquest_RIE%3E2717301631%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=1027237059&rft_id=info:pmid/20051346&rft_ieee_id=5371866&rfr_iscdi=true |