Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information
This paper proposed a method that uses shadow change information in bi-temporal images to improve accuracy of urban building damage detection. The initial building damage detection was conducted by object-based bitemporal classification using One-Class Support Vector Machine (OCSVM). The shadow chan...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1412 |
|---|---|
| container_issue | |
| container_start_page | 1409 |
| container_title | |
| container_volume | |
| creator | Peijun Li Benqin Song Haiqing Xu |
| description | This paper proposed a method that uses shadow change information in bi-temporal images to improve accuracy of urban building damage detection. The initial building damage detection was conducted by object-based bitemporal classification using One-Class Support Vector Machine (OCSVM). The shadow changes extracted from the images were then used to refine the results produced in previous step. The experimental results using bitemporal Quickbird images acquired in Dujiangyan, Sichuan of China showed the proposed method significantly improved the detection accuracy. In particular, the commission error of the building damage was significantly reduced. Further work is required to make more sophisticated rule sets to obtain better results. |
| doi_str_mv | 10.1109/IGARSS.2011.6049330 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6049330</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6049330</ieee_id><sourcerecordid>6049330</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-1f012b6c1a2c720d11c6996fd0f9f10a641c31a9a88c694ce6f9c56aaf9a58be3</originalsourceid><addsrcrecordid>eNo1kN1OwkAQhde_RESegJt9geJMt912LwlRJMGQiBjvyHR_YE1pzS5qeHuL4rmZ5Hwnk5PD2BBhhAjqbjYdPy-XoxQQRxIyJQScsYEqSszyokCAXJ6zXoq5SAoAccFu_oF4uzwBqZS8ZoMY36GTlApR9ZhfhYoaXn362vhmww3taGO5sXur975tuAvtjn_ZcOBbv9nyYGNbf_4Sf0x2fnXgi8Ymk5pi5MvXJ06N4XFLpv3mvnFt2NExf8uuHNXRDk63z1YP9y-Tx2S-mM4m43niscj3CTrAtJIaKdVFCgZRH5s7A045BJIZaoGkqCw7kGkrndK5JHKK8rKyos-Gf3-9tXb9Ebqa4bA-rSZ-ALFsXiQ</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Peijun Li ; Benqin Song ; Haiqing Xu</creator><creatorcontrib>Peijun Li ; Benqin Song ; Haiqing Xu</creatorcontrib><description>This paper proposed a method that uses shadow change information in bi-temporal images to improve accuracy of urban building damage detection. The initial building damage detection was conducted by object-based bitemporal classification using One-Class Support Vector Machine (OCSVM). The shadow changes extracted from the images were then used to refine the results produced in previous step. The experimental results using bitemporal Quickbird images acquired in Dujiangyan, Sichuan of China showed the proposed method significantly improved the detection accuracy. In particular, the commission error of the building damage was significantly reduced. Further work is required to make more sophisticated rule sets to obtain better results.</description><identifier>ISSN: 2153-6996</identifier><identifier>ISBN: 145771003X</identifier><identifier>ISBN: 9781457710032</identifier><identifier>EISSN: 2153-7003</identifier><identifier>EISBN: 9781457710056</identifier><identifier>EISBN: 9781457710049</identifier><identifier>EISBN: 1457710056</identifier><identifier>EISBN: 1457710048</identifier><identifier>DOI: 10.1109/IGARSS.2011.6049330</identifier><language>eng</language><publisher>IEEE</publisher><subject>Accuracy ; building ; Buildings ; change detection ; damage assessment ; Earthquakes ; Image resolution ; Image segmentation ; One-Class SVM ; Remote sensing ; Support vector machines ; very high resolution</subject><ispartof>2011 IEEE International Geoscience and Remote Sensing Symposium, 2011, p.1409-1412</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6049330$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,2052,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6049330$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Peijun Li</creatorcontrib><creatorcontrib>Benqin Song</creatorcontrib><creatorcontrib>Haiqing Xu</creatorcontrib><title>Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information</title><title>2011 IEEE International Geoscience and Remote Sensing Symposium</title><addtitle>IGARSS</addtitle><description>This paper proposed a method that uses shadow change information in bi-temporal images to improve accuracy of urban building damage detection. The initial building damage detection was conducted by object-based bitemporal classification using One-Class Support Vector Machine (OCSVM). The shadow changes extracted from the images were then used to refine the results produced in previous step. The experimental results using bitemporal Quickbird images acquired in Dujiangyan, Sichuan of China showed the proposed method significantly improved the detection accuracy. In particular, the commission error of the building damage was significantly reduced. Further work is required to make more sophisticated rule sets to obtain better results.</description><subject>Accuracy</subject><subject>building</subject><subject>Buildings</subject><subject>change detection</subject><subject>damage assessment</subject><subject>Earthquakes</subject><subject>Image resolution</subject><subject>Image segmentation</subject><subject>One-Class SVM</subject><subject>Remote sensing</subject><subject>Support vector machines</subject><subject>very high resolution</subject><issn>2153-6996</issn><issn>2153-7003</issn><isbn>145771003X</isbn><isbn>9781457710032</isbn><isbn>9781457710056</isbn><isbn>9781457710049</isbn><isbn>1457710056</isbn><isbn>1457710048</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1kN1OwkAQhde_RESegJt9geJMt912LwlRJMGQiBjvyHR_YE1pzS5qeHuL4rmZ5Hwnk5PD2BBhhAjqbjYdPy-XoxQQRxIyJQScsYEqSszyokCAXJ6zXoq5SAoAccFu_oF4uzwBqZS8ZoMY36GTlApR9ZhfhYoaXn362vhmww3taGO5sXur975tuAvtjn_ZcOBbv9nyYGNbf_4Sf0x2fnXgi8Ymk5pi5MvXJ06N4XFLpv3mvnFt2NExf8uuHNXRDk63z1YP9y-Tx2S-mM4m43niscj3CTrAtJIaKdVFCgZRH5s7A045BJIZaoGkqCw7kGkrndK5JHKK8rKyos-Gf3-9tXb9Ebqa4bA-rSZ-ALFsXiQ</recordid><startdate>201107</startdate><enddate>201107</enddate><creator>Peijun Li</creator><creator>Benqin Song</creator><creator>Haiqing Xu</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201107</creationdate><title>Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information</title><author>Peijun Li ; Benqin Song ; Haiqing Xu</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-1f012b6c1a2c720d11c6996fd0f9f10a641c31a9a88c694ce6f9c56aaf9a58be3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Accuracy</topic><topic>building</topic><topic>Buildings</topic><topic>change detection</topic><topic>damage assessment</topic><topic>Earthquakes</topic><topic>Image resolution</topic><topic>Image segmentation</topic><topic>One-Class SVM</topic><topic>Remote sensing</topic><topic>Support vector machines</topic><topic>very high resolution</topic><toplevel>online_resources</toplevel><creatorcontrib>Peijun Li</creatorcontrib><creatorcontrib>Benqin Song</creatorcontrib><creatorcontrib>Haiqing Xu</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Peijun Li</au><au>Benqin Song</au><au>Haiqing Xu</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information</atitle><btitle>2011 IEEE International Geoscience and Remote Sensing Symposium</btitle><stitle>IGARSS</stitle><date>2011-07</date><risdate>2011</risdate><spage>1409</spage><epage>1412</epage><pages>1409-1412</pages><issn>2153-6996</issn><eissn>2153-7003</eissn><isbn>145771003X</isbn><isbn>9781457710032</isbn><eisbn>9781457710056</eisbn><eisbn>9781457710049</eisbn><eisbn>1457710056</eisbn><eisbn>1457710048</eisbn><abstract>This paper proposed a method that uses shadow change information in bi-temporal images to improve accuracy of urban building damage detection. The initial building damage detection was conducted by object-based bitemporal classification using One-Class Support Vector Machine (OCSVM). The shadow changes extracted from the images were then used to refine the results produced in previous step. The experimental results using bitemporal Quickbird images acquired in Dujiangyan, Sichuan of China showed the proposed method significantly improved the detection accuracy. In particular, the commission error of the building damage was significantly reduced. Further work is required to make more sophisticated rule sets to obtain better results.</abstract><pub>IEEE</pub><doi>10.1109/IGARSS.2011.6049330</doi><tpages>4</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2153-6996 |
| ispartof | 2011 IEEE International Geoscience and Remote Sensing Symposium, 2011, p.1409-1412 |
| issn | 2153-6996 2153-7003 |
| language | eng |
| recordid | cdi_ieee_primary_6049330 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Accuracy building Buildings change detection damage assessment Earthquakes Image resolution Image segmentation One-Class SVM Remote sensing Support vector machines very high resolution |
| title | Urban building damage detection from very high resolution imagery by One-Class SVM and shadow information |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-12T17%3A43%3A06IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Urban%20building%20damage%20detection%20from%20very%20high%20resolution%20imagery%20by%20One-Class%20SVM%20and%20shadow%20information&rft.btitle=2011%20IEEE%20International%20Geoscience%20and%20Remote%20Sensing%20Symposium&rft.au=Peijun%20Li&rft.date=2011-07&rft.spage=1409&rft.epage=1412&rft.pages=1409-1412&rft.issn=2153-6996&rft.eissn=2153-7003&rft.isbn=145771003X&rft.isbn_list=9781457710032&rft_id=info:doi/10.1109/IGARSS.2011.6049330&rft_dat=%3Cieee_6IE%3E6049330%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781457710056&rft.eisbn_list=9781457710049&rft.eisbn_list=1457710056&rft.eisbn_list=1457710048&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6049330&rfr_iscdi=true |