File Download
 
Links for fulltext
(May Require Subscription)
 
Supplementary

Conference Paper: Pose estimation from reflections for specular surface recovery
  • Basic View
  • Metadata View
  • XML View
TitlePose estimation from reflections for specular surface recovery
 
AuthorsLiu, M1
Wong, KKY1
Dai, Z2
Chen, Z1
 
KeywordsClosed form solutions
Colinearity
Incident rays
Pose estimation
Reference plane
 
Issue Date2011
 
PublisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149
 
CitationThe 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 November 2011. In Proceedings of IEEE ICCV, 2011, p. 579-586 [How to Cite?]
DOI: http://dx.doi.org/10.1109/ICCV.2011.6126291
 
AbstractThis paper addresses the problem of estimating the poses of a reference plane in specular shape recovery. Unlike existing methods which require an extra mirror or an extra reference plane and camera, our proposed method recovers the poses of the reference plane directly from its reflections on the specular surface. By establishing reflection correspondences on the reference plane in three distinct poses, our method estimates the poses of the reference plane in two steps. First, by applying a colinearity constraint to the reflection correspondences, a simple closed-form solution is derived for recovering the poses of the reference plane relative to its initial pose. Second, by applying a ray incidence constraint to the incident rays formed by the reflection correspondences and the visual rays cast from the image, a closed-form solution is derived for recovering the poses of the reference plane relative to the camera. The shape of the specular surface then follows. Experimental results on both synthetic and real data are presented, which demonstrate the feasibility and accuracy of our proposed method. © 2011 IEEE.
 
ISBN978-1-4577-1102-2
 
ISSN1550-5499
 
DOIhttp://dx.doi.org/10.1109/ICCV.2011.6126291
 
DC FieldValue
dc.contributor.authorLiu, M
 
dc.contributor.authorWong, KKY
 
dc.contributor.authorDai, Z
 
dc.contributor.authorChen, Z
 
dc.date.accessioned2011-08-26T14:30:34Z
 
dc.date.available2011-08-26T14:30:34Z
 
dc.date.issued2011
 
dc.description.abstractThis paper addresses the problem of estimating the poses of a reference plane in specular shape recovery. Unlike existing methods which require an extra mirror or an extra reference plane and camera, our proposed method recovers the poses of the reference plane directly from its reflections on the specular surface. By establishing reflection correspondences on the reference plane in three distinct poses, our method estimates the poses of the reference plane in two steps. First, by applying a colinearity constraint to the reflection correspondences, a simple closed-form solution is derived for recovering the poses of the reference plane relative to its initial pose. Second, by applying a ray incidence constraint to the incident rays formed by the reflection correspondences and the visual rays cast from the image, a closed-form solution is derived for recovering the poses of the reference plane relative to the camera. The shape of the specular surface then follows. Experimental results on both synthetic and real data are presented, which demonstrate the feasibility and accuracy of our proposed method. © 2011 IEEE.
 
dc.description.naturepublished_or_final_version
 
dc.description.otherThe 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 November 2011. In Proceedings of IEEE ICCV, 2011, p. 579-586
 
dc.identifier.citationThe 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 November 2011. In Proceedings of IEEE ICCV, 2011, p. 579-586 [How to Cite?]
DOI: http://dx.doi.org/10.1109/ICCV.2011.6126291
 
dc.identifier.doihttp://dx.doi.org/10.1109/ICCV.2011.6126291
 
dc.identifier.epage586
 
dc.identifier.hkuros191686
 
dc.identifier.isbn978-1-4577-1102-2
 
dc.identifier.issn1550-5499
 
dc.identifier.scopuseid_2-s2.0-84863060768
 
dc.identifier.spage579
 
dc.identifier.urihttp://hdl.handle.net/10722/137656
 
dc.languageeng
 
dc.publisherIEEE. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149
 
dc.publisher.placeUnited States
 
dc.relation.ispartofIEEE International Conference on Computer Vision Proceedings
 
dc.rightsIEEE International Conference on Computer Vision Proceedings. Copyright © IEEE.
 
dc.rights©2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
 
dc.rightsCreative Commons: Attribution 3.0 Hong Kong License
 
dc.subjectClosed form solutions
 
dc.subjectColinearity
 
dc.subjectIncident rays
 
dc.subjectPose estimation
 
dc.subjectReference plane
 
dc.titlePose estimation from reflections for specular surface recovery
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Liu, M</contributor.author>
<contributor.author>Wong, KKY</contributor.author>
<contributor.author>Dai, Z</contributor.author>
<contributor.author>Chen, Z</contributor.author>
<date.accessioned>2011-08-26T14:30:34Z</date.accessioned>
<date.available>2011-08-26T14:30:34Z</date.available>
<date.issued>2011</date.issued>
<identifier.citation>The 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 November 2011. In Proceedings of IEEE ICCV, 2011, p. 579-586</identifier.citation>
<identifier.isbn>978-1-4577-1102-2</identifier.isbn>
<identifier.issn>1550-5499</identifier.issn>
<identifier.uri>http://hdl.handle.net/10722/137656</identifier.uri>
<description.abstract>This paper addresses the problem of estimating the poses of a reference plane in specular shape recovery. Unlike existing methods which require an extra mirror or an extra reference plane and camera, our proposed method recovers the poses of the reference plane directly from its reflections on the specular surface. By establishing reflection correspondences on the reference plane in three distinct poses, our method estimates the poses of the reference plane in two steps. First, by applying a colinearity constraint to the reflection correspondences, a simple closed-form solution is derived for recovering the poses of the reference plane relative to its initial pose. Second, by applying a ray incidence constraint to the incident rays formed by the reflection correspondences and the visual rays cast from the image, a closed-form solution is derived for recovering the poses of the reference plane relative to the camera. The shape of the specular surface then follows. Experimental results on both synthetic and real data are presented, which demonstrate the feasibility and accuracy of our proposed method. &#169; 2011 IEEE.</description.abstract>
<language>eng</language>
<publisher>IEEE. The Journal&apos;s web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000149</publisher>
<relation.ispartof>IEEE International Conference on Computer Vision Proceedings</relation.ispartof>
<rights>IEEE International Conference on Computer Vision Proceedings. Copyright &#169; IEEE.</rights>
<rights>&#169;2011 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.</rights>
<rights>Creative Commons: Attribution 3.0 Hong Kong License</rights>
<subject>Closed form solutions</subject>
<subject>Colinearity</subject>
<subject>Incident rays</subject>
<subject>Pose estimation</subject>
<subject>Reference plane</subject>
<title>Pose estimation from reflections for specular surface recovery</title>
<type>Conference_Paper</type>
<description.nature>published_or_final_version</description.nature>
<identifier.doi>10.1109/ICCV.2011.6126291</identifier.doi>
<identifier.scopus>eid_2-s2.0-84863060768</identifier.scopus>
<identifier.hkuros>191686</identifier.hkuros>
<identifier.spage>579</identifier.spage>
<identifier.epage>586</identifier.epage>
<publisher.place>United States</publisher.place>
<description.other>The 2011 IEEE International Conference on Computer Vision (ICCV), Barcelona, Spain, 6-13 November 2011. In Proceedings of IEEE ICCV, 2011, p. 579-586</description.other>
<bitstream.url>http://hub.hku.hk/bitstream/10722/137656/1/Content.pdf</bitstream.url>
</item>
Author Affiliations
  1. The University of Hong Kong
  2. Frankfurt Institute for Advanced Studies