File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Projective reconstruction of ellipses from multiple images

TitleProjective reconstruction of ellipses from multiple images
Authors
KeywordsConic correspondence
Ellipse reconstruction
Multiple views
Projective reconstruction
Issue Date2010
PublisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pr
Citation
Pattern Recognition, 2010, v. 43 n. 3, p. 545-556 How to Cite?
AbstractThis paper presents a new approach for reconstructing 3D ellipses (including circles) from a sequence of 2D images taken by uncalibrated cameras. Our strategy is to estimate an ellipse in 3D space by reconstructing N (≥ 5) 3D points (called representative points) on it, where the representative points are reconstructed by minimizing the distances from their projections to the measured 2D ellipses on different images (i.e., 2D reprojection error). This minimization problem is transformed into a sequence of minimization sub-problems that can be readily solved by an algorithm which is guaranteed to converge to a (local) minimum of the 2D reprojection error. Our method can reconstruct multiple 3D ellipses simultaneously from multiple images and it readily handles images with missing and/or partially occluded ellipses. The proposed method is evaluated using both synthetic and real data. © 2009 Elsevier Ltd. All rights reserved.
Persistent Identifierhttp://hdl.handle.net/10722/124711
ISSN
2015 Impact Factor: 3.399
2015 SCImago Journal Rankings: 2.051
ISI Accession Number ID
Funding AgencyGrant Number
Council of Hong Kong Special Administrative Region, ChinaHKU 712808E
HKU 711208E
CRCG of the University of Hong Kong
Funding Information:

The work in this paper was supported by the Research Grants Council of Hong Kong Special Administrative Region, China (GRF Projects HKU 712808E and HKU 711208E) and CRCG of the University of Hong Kong.

References
Grants

 

DC FieldValueLanguage
dc.contributor.authorMai, Fen_HK
dc.contributor.authorHung, YSen_HK
dc.contributor.authorChesi, Gen_HK
dc.date.accessioned2010-10-31T10:49:50Z-
dc.date.available2010-10-31T10:49:50Z-
dc.date.issued2010en_HK
dc.identifier.citationPattern Recognition, 2010, v. 43 n. 3, p. 545-556en_HK
dc.identifier.issn0031-3203en_HK
dc.identifier.urihttp://hdl.handle.net/10722/124711-
dc.description.abstractThis paper presents a new approach for reconstructing 3D ellipses (including circles) from a sequence of 2D images taken by uncalibrated cameras. Our strategy is to estimate an ellipse in 3D space by reconstructing N (≥ 5) 3D points (called representative points) on it, where the representative points are reconstructed by minimizing the distances from their projections to the measured 2D ellipses on different images (i.e., 2D reprojection error). This minimization problem is transformed into a sequence of minimization sub-problems that can be readily solved by an algorithm which is guaranteed to converge to a (local) minimum of the 2D reprojection error. Our method can reconstruct multiple 3D ellipses simultaneously from multiple images and it readily handles images with missing and/or partially occluded ellipses. The proposed method is evaluated using both synthetic and real data. © 2009 Elsevier Ltd. All rights reserved.en_HK
dc.languageengen_HK
dc.publisherElsevier BV. The Journal's web site is located at http://www.elsevier.com/locate/pren_HK
dc.relation.ispartofPattern Recognitionen_HK
dc.subjectConic correspondenceen_HK
dc.subjectEllipse reconstructionen_HK
dc.subjectMultiple viewsen_HK
dc.subjectProjective reconstructionen_HK
dc.titleProjective reconstruction of ellipses from multiple imagesen_HK
dc.typeArticleen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0031-3203&volume=43, No.3&spage=545&epage=556&date=2010&atitle=Projective+reconstruction+of+ellipses+from+multiple+imagesen_HK
dc.identifier.emailHung, YS:yshung@eee.hku.hken_HK
dc.identifier.emailChesi, G:chesi@eee.hku.hken_HK
dc.identifier.authorityHung, YS=rp00220en_HK
dc.identifier.authorityChesi, G=rp00100en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1016/j.patcog.2009.07.003en_HK
dc.identifier.scopuseid_2-s2.0-70449704335en_HK
dc.identifier.hkuros173433en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-70449704335&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume43en_HK
dc.identifier.issue3en_HK
dc.identifier.spage545en_HK
dc.identifier.epage556en_HK
dc.identifier.isiWOS:000273094100001-
dc.publisher.placeNetherlandsen_HK
dc.relation.projectAn Integrated Approach to 3D Shape Recovery from Multiple Views-
dc.identifier.scopusauthoridMai, F=12804393400en_HK
dc.identifier.scopusauthoridHung, YS=8091656200en_HK
dc.identifier.scopusauthoridChesi, G=7006328614en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats