File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Illumination direction estimation for augmented reality using a surface input real valued output regression network

TitleIllumination direction estimation for augmented reality using a surface input real valued output regression network
Authors
Issue Date2010
Citation
Pattern Recognition, 2010, v. 43 n. 4, p. 1700-1716 How to Cite?
AbstractDue to low cost for capturing depth information, it is worthwhile to reduce the illumination ambiguity by employing scenario depth information. In this article, a neural computation approach is reported that estimates illuminant direction from scenario reflectance map. Since the reflectance map recovered from depth map and image is a variable sized point cloud, we propose to parameterize it as a two dimensional polynomial function. Afterwards, a novel network model is presented for mapping from continuous function (reflectance map) to vectorial output (illuminant direction). Experimental results show that the proposed model works well on both synthetic and real scenes. © 2009 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/196677
ISSN
2015 Impact Factor: 3.399
2015 SCImago Journal Rankings: 2.051
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorChow, CK-
dc.contributor.authorYuen, SY-
dc.date.accessioned2014-04-24T02:10:33Z-
dc.date.available2014-04-24T02:10:33Z-
dc.date.issued2010-
dc.identifier.citationPattern Recognition, 2010, v. 43 n. 4, p. 1700-1716-
dc.identifier.issn0031-3203-
dc.identifier.urihttp://hdl.handle.net/10722/196677-
dc.description.abstractDue to low cost for capturing depth information, it is worthwhile to reduce the illumination ambiguity by employing scenario depth information. In this article, a neural computation approach is reported that estimates illuminant direction from scenario reflectance map. Since the reflectance map recovered from depth map and image is a variable sized point cloud, we propose to parameterize it as a two dimensional polynomial function. Afterwards, a novel network model is presented for mapping from continuous function (reflectance map) to vectorial output (illuminant direction). Experimental results show that the proposed model works well on both synthetic and real scenes. © 2009 Elsevier Ltd. All rights reserved.-
dc.languageeng-
dc.relation.ispartofPattern Recognition-
dc.titleIllumination direction estimation for augmented reality using a surface input real valued output regression network-
dc.typeArticle-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.patcog.2009.10.008-
dc.identifier.scopuseid_2-s2.0-74449091092-
dc.identifier.volume43-
dc.identifier.issue4-
dc.identifier.spage1700-
dc.identifier.epage1716-
dc.identifier.isiWOS:000274954100042-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats