Adaptive pixel classifier for binary structured light: A probabilistic kernel approach
The paper proposes an adaptive classification mechanism designed for structured light system to improve quality of reconstructed models. We observed that the conventional albedo-based thresholding fails when the lighting condition is not carefully considered. To address this problem, an adaptive mod...
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 | 372 |
|---|---|
| container_issue | |
| container_start_page | 367 |
| container_title | |
| container_volume | |
| creator | Hsiang-Jen Chien Chia-Yen Chen Chi-Fa Chen Yih-Ming Su |
| description | The paper proposes an adaptive classification mechanism designed for structured light system to improve quality of reconstructed models. We observed that the conventional albedo-based thresholding fails when the lighting condition is not carefully considered. To address this problem, an adaptive model is proposed. The core idea is to adjust decision boundary during extraction of sequence of binary-coded light patterns by taking the change of lighting condition into account. Base on this idea, a probabilistic kernel-based online learning procedure has been designed and applied to a structured light system. The experimental results show that the proposed method yields more reliable pixel classification as well as increased accuracy of the 3D scanner. It should be noted that the proposed method does not require any modification on conventional Gray-coded patterns. |
| doi_str_mv | 10.1109/IVCNZ.2009.5378378 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_5378378</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5378378</ieee_id><sourcerecordid>5378378</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-df420e283a4bdb11163a6575cf84acea15ee83532ff30696f54e217e7ced4cb43</originalsourceid><addsrcrecordid>eNpVUEtLAzEYjI-CtfYP6CV_YGu-PDaJt1J8FIpetAcvJZv9YqNruyRb0X_vivUgDAzMMMMwhJwDmwAwezlfzu6fJ5wxO1FCmx4HZGy1AcmllKU15pAMOSgoOGfq6J-n4fjPAwsDcvpTY5nUVpyQcc6vjDHgpuRGDclyWru2ix9I2_iJDfWNyzmGiImGbaJV3Lj0RXOXdr7bJaxpE1_W3RWd0jZtK1fFJuYuevqGadPHXdvLzq_PyCC4JuN4zyPydHP9OLsrFg-389l0UUTQqivqIDlDboSTVV0BQClcqbTywUjn0YFCNEIJHoJgpS2DkshBo_ZYS19JMSIXv70REVdtiu_93NX-MvENs6JaQg</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Adaptive pixel classifier for binary structured light: A probabilistic kernel approach</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Hsiang-Jen Chien ; Chia-Yen Chen ; Chi-Fa Chen ; Yih-Ming Su</creator><creatorcontrib>Hsiang-Jen Chien ; Chia-Yen Chen ; Chi-Fa Chen ; Yih-Ming Su</creatorcontrib><description>The paper proposes an adaptive classification mechanism designed for structured light system to improve quality of reconstructed models. We observed that the conventional albedo-based thresholding fails when the lighting condition is not carefully considered. To address this problem, an adaptive model is proposed. The core idea is to adjust decision boundary during extraction of sequence of binary-coded light patterns by taking the change of lighting condition into account. Base on this idea, a probabilistic kernel-based online learning procedure has been designed and applied to a structured light system. The experimental results show that the proposed method yields more reliable pixel classification as well as increased accuracy of the 3D scanner. It should be noted that the proposed method does not require any modification on conventional Gray-coded patterns.</description><identifier>ISSN: 2151-2191</identifier><identifier>ISBN: 9781424446971</identifier><identifier>ISBN: 142444697X</identifier><identifier>EISSN: 2151-2205</identifier><identifier>EISBN: 9781424446988</identifier><identifier>EISBN: 1424446988</identifier><identifier>DOI: 10.1109/IVCNZ.2009.5378378</identifier><identifier>LCCN: 2009904793</identifier><language>eng</language><publisher>IEEE</publisher><subject>adaptive structured light ; binary pattern ; Cameras ; Computer science ; Computer vision ; Frequency ; Gray code ; Image reconstruction ; intensity ratio ; Kernel ; Layout ; online learning ; Pixel ; pixel classification ; Reflective binary codes ; Robustness</subject><ispartof>2009 24th International Conference Image and Vision Computing New Zealand, 2009, p.367-372</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/5378378$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,778,782,787,788,2054,27912,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5378378$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Hsiang-Jen Chien</creatorcontrib><creatorcontrib>Chia-Yen Chen</creatorcontrib><creatorcontrib>Chi-Fa Chen</creatorcontrib><creatorcontrib>Yih-Ming Su</creatorcontrib><title>Adaptive pixel classifier for binary structured light: A probabilistic kernel approach</title><title>2009 24th International Conference Image and Vision Computing New Zealand</title><addtitle>IVCNZ</addtitle><description>The paper proposes an adaptive classification mechanism designed for structured light system to improve quality of reconstructed models. We observed that the conventional albedo-based thresholding fails when the lighting condition is not carefully considered. To address this problem, an adaptive model is proposed. The core idea is to adjust decision boundary during extraction of sequence of binary-coded light patterns by taking the change of lighting condition into account. Base on this idea, a probabilistic kernel-based online learning procedure has been designed and applied to a structured light system. The experimental results show that the proposed method yields more reliable pixel classification as well as increased accuracy of the 3D scanner. It should be noted that the proposed method does not require any modification on conventional Gray-coded patterns.</description><subject>adaptive structured light</subject><subject>binary pattern</subject><subject>Cameras</subject><subject>Computer science</subject><subject>Computer vision</subject><subject>Frequency</subject><subject>Gray code</subject><subject>Image reconstruction</subject><subject>intensity ratio</subject><subject>Kernel</subject><subject>Layout</subject><subject>online learning</subject><subject>Pixel</subject><subject>pixel classification</subject><subject>Reflective binary codes</subject><subject>Robustness</subject><issn>2151-2191</issn><issn>2151-2205</issn><isbn>9781424446971</isbn><isbn>142444697X</isbn><isbn>9781424446988</isbn><isbn>1424446988</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2009</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNpVUEtLAzEYjI-CtfYP6CV_YGu-PDaJt1J8FIpetAcvJZv9YqNruyRb0X_vivUgDAzMMMMwhJwDmwAwezlfzu6fJ5wxO1FCmx4HZGy1AcmllKU15pAMOSgoOGfq6J-n4fjPAwsDcvpTY5nUVpyQcc6vjDHgpuRGDclyWru2ix9I2_iJDfWNyzmGiImGbaJV3Lj0RXOXdr7bJaxpE1_W3RWd0jZtK1fFJuYuevqGadPHXdvLzq_PyCC4JuN4zyPydHP9OLsrFg-389l0UUTQqivqIDlDboSTVV0BQClcqbTywUjn0YFCNEIJHoJgpS2DkshBo_ZYS19JMSIXv70REVdtiu_93NX-MvENs6JaQg</recordid><startdate>200911</startdate><enddate>200911</enddate><creator>Hsiang-Jen Chien</creator><creator>Chia-Yen Chen</creator><creator>Chi-Fa Chen</creator><creator>Yih-Ming Su</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>200911</creationdate><title>Adaptive pixel classifier for binary structured light: A probabilistic kernel approach</title><author>Hsiang-Jen Chien ; Chia-Yen Chen ; Chi-Fa Chen ; Yih-Ming Su</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-df420e283a4bdb11163a6575cf84acea15ee83532ff30696f54e217e7ced4cb43</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2009</creationdate><topic>adaptive structured light</topic><topic>binary pattern</topic><topic>Cameras</topic><topic>Computer science</topic><topic>Computer vision</topic><topic>Frequency</topic><topic>Gray code</topic><topic>Image reconstruction</topic><topic>intensity ratio</topic><topic>Kernel</topic><topic>Layout</topic><topic>online learning</topic><topic>Pixel</topic><topic>pixel classification</topic><topic>Reflective binary codes</topic><topic>Robustness</topic><toplevel>online_resources</toplevel><creatorcontrib>Hsiang-Jen Chien</creatorcontrib><creatorcontrib>Chia-Yen Chen</creatorcontrib><creatorcontrib>Chi-Fa Chen</creatorcontrib><creatorcontrib>Yih-Ming Su</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Hsiang-Jen Chien</au><au>Chia-Yen Chen</au><au>Chi-Fa Chen</au><au>Yih-Ming Su</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Adaptive pixel classifier for binary structured light: A probabilistic kernel approach</atitle><btitle>2009 24th International Conference Image and Vision Computing New Zealand</btitle><stitle>IVCNZ</stitle><date>2009-11</date><risdate>2009</risdate><spage>367</spage><epage>372</epage><pages>367-372</pages><issn>2151-2191</issn><eissn>2151-2205</eissn><isbn>9781424446971</isbn><isbn>142444697X</isbn><eisbn>9781424446988</eisbn><eisbn>1424446988</eisbn><abstract>The paper proposes an adaptive classification mechanism designed for structured light system to improve quality of reconstructed models. We observed that the conventional albedo-based thresholding fails when the lighting condition is not carefully considered. To address this problem, an adaptive model is proposed. The core idea is to adjust decision boundary during extraction of sequence of binary-coded light patterns by taking the change of lighting condition into account. Base on this idea, a probabilistic kernel-based online learning procedure has been designed and applied to a structured light system. The experimental results show that the proposed method yields more reliable pixel classification as well as increased accuracy of the 3D scanner. It should be noted that the proposed method does not require any modification on conventional Gray-coded patterns.</abstract><pub>IEEE</pub><doi>10.1109/IVCNZ.2009.5378378</doi><tpages>6</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 2151-2191 |
| ispartof | 2009 24th International Conference Image and Vision Computing New Zealand, 2009, p.367-372 |
| issn | 2151-2191 2151-2205 |
| language | eng |
| recordid | cdi_ieee_primary_5378378 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | adaptive structured light binary pattern Cameras Computer science Computer vision Frequency Gray code Image reconstruction intensity ratio Kernel Layout online learning Pixel pixel classification Reflective binary codes Robustness |
| title | Adaptive pixel classifier for binary structured light: A probabilistic kernel approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T19%3A05%3A32IST&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=Adaptive%20pixel%20classifier%20for%20binary%20structured%20light:%20A%20probabilistic%20kernel%20approach&rft.btitle=2009%2024th%20International%20Conference%20Image%20and%20Vision%20Computing%20New%20Zealand&rft.au=Hsiang-Jen%20Chien&rft.date=2009-11&rft.spage=367&rft.epage=372&rft.pages=367-372&rft.issn=2151-2191&rft.eissn=2151-2205&rft.isbn=9781424446971&rft.isbn_list=142444697X&rft_id=info:doi/10.1109/IVCNZ.2009.5378378&rft_dat=%3Cieee_6IE%3E5378378%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781424446988&rft.eisbn_list=1424446988&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5378378&rfr_iscdi=true |