File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Motion recovery for uncalibrated turntable sequences using silhouettes and a single point

TitleMotion recovery for uncalibrated turntable sequences using silhouettes and a single point
Authors
KeywordsRestoration
Rotation
Visual communication
Best estimates
Camera intrinsic matrixes
Issue Date2008
PublisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/
Citation
The 10th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2008), Juan-les-Pins, France, 20-24 October 2008. In Lecture Notes in Computer Science, 2008, v. 5259, p. 796-807 How to Cite?
AbstractThis paper addresses the problem of self-calibration and motion recovery for turntable sequences. Previous works exploited silhouette correspondences induced by epipolar tangencies to estimate the image invariants under turntable motion and recover the epipolar geometry. These approaches, however, require the camera intrinsics in order to obtain an Euclidean motion, and a dense sequence is required to provide a precise initialization of the image invariants. This paper proposes a novel approach to estimate the camera intrinsics, the image invariants and the rotation angles from a sparse turntable sequence. The silhouettes and a single point correspondence are extracted from the image sequence. The point traces out a conic in the sequence, from which the fixed entities (i.e., the image of the rotation axis, the horizon, the vanishing point of the coordinates, the circular points and a scalar) can be recovered given a simple initialization of the camera intrinsic matrix. The rotation angles are then recovered by estimating the epipoles that minimize the transfer errors of the outer epipolar tangents to the silhouettes for each pair of images. The camera intrinsics can be further refined by the above optimization. Based on a given range of the initial focal length, a robust method is proposed to give the best estimate of the camera intrinsics, the image invariants, the full camera positions and orientations, and hence a Euclidean reconstruction. Experimental results demonstrate the simplicity of this approach and the accuracy in the estimated motion and reconstruction. © 2008 Springer Berlin Heidelberg.
DescriptionLNCS v. 5259 is the conference proceedings of ACIVS 2008
Persistent Identifierhttp://hdl.handle.net/10722/137151
ISSN
2005 Impact Factor: 0.402
2015 SCImago Journal Rankings: 0.252
References

 

DC FieldValueLanguage
dc.contributor.authorZhang, Hen_HK
dc.contributor.authorShao, Len_HK
dc.contributor.authorWong, KYKen_HK
dc.date.accessioned2011-08-24T07:11:12Z-
dc.date.available2011-08-24T07:11:12Z-
dc.date.issued2008en_HK
dc.identifier.citationThe 10th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2008), Juan-les-Pins, France, 20-24 October 2008. In Lecture Notes in Computer Science, 2008, v. 5259, p. 796-807en_HK
dc.identifier.issn0302-9743en_HK
dc.identifier.urihttp://hdl.handle.net/10722/137151-
dc.descriptionLNCS v. 5259 is the conference proceedings of ACIVS 2008-
dc.description.abstractThis paper addresses the problem of self-calibration and motion recovery for turntable sequences. Previous works exploited silhouette correspondences induced by epipolar tangencies to estimate the image invariants under turntable motion and recover the epipolar geometry. These approaches, however, require the camera intrinsics in order to obtain an Euclidean motion, and a dense sequence is required to provide a precise initialization of the image invariants. This paper proposes a novel approach to estimate the camera intrinsics, the image invariants and the rotation angles from a sparse turntable sequence. The silhouettes and a single point correspondence are extracted from the image sequence. The point traces out a conic in the sequence, from which the fixed entities (i.e., the image of the rotation axis, the horizon, the vanishing point of the coordinates, the circular points and a scalar) can be recovered given a simple initialization of the camera intrinsic matrix. The rotation angles are then recovered by estimating the epipoles that minimize the transfer errors of the outer epipolar tangents to the silhouettes for each pair of images. The camera intrinsics can be further refined by the above optimization. Based on a given range of the initial focal length, a robust method is proposed to give the best estimate of the camera intrinsics, the image invariants, the full camera positions and orientations, and hence a Euclidean reconstruction. Experimental results demonstrate the simplicity of this approach and the accuracy in the estimated motion and reconstruction. © 2008 Springer Berlin Heidelberg.en_HK
dc.languageeng-
dc.publisherSpringer Verlag. The Journal's web site is located at http://springerlink.com/content/105633/en_HK
dc.relation.ispartofLecture Notes in Computer Scienceen_HK
dc.rightsThe original publication is available at www.springerlink.com-
dc.subjectRestoration-
dc.subjectRotation-
dc.subjectVisual communication-
dc.subjectBest estimates-
dc.subjectCamera intrinsic matrixes-
dc.titleMotion recovery for uncalibrated turntable sequences using silhouettes and a single pointen_HK
dc.typeConference_Paperen_HK
dc.identifier.openurlhttp://library.hku.hk:4550/resserv?sid=HKU:IR&issn=0302-9743&volume=5259&spage=796&epage=807&date=2008&atitle=Motion+recovery+for+uncalibrated+turntable+sequences+using+silhouettes+and+a+single+point-
dc.identifier.emailWong, KYK:kykwong@cs.hku.hken_HK
dc.identifier.authorityWong, KYK=rp01393en_HK
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/978-3-540-88458-3-72en_HK
dc.identifier.scopuseid_2-s2.0-57049164841en_HK
dc.identifier.hkuros148742-
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-57049164841&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume5259 LNCSen_HK
dc.identifier.spage796en_HK
dc.identifier.epage807en_HK
dc.publisher.placeGermanyen_HK
dc.description.otherThe 10th International Conference on Advanced Concepts for Intelligent Vision Systems (ACIVS 2008), Juan-les-Pins, France, 20-24 October 2008. In Lecture Notes in Computer Science, 2008, v. 5259, p. 796-807-
dc.identifier.scopusauthoridZhang, H=7409191962en_HK
dc.identifier.scopusauthoridShao, L=8216509700en_HK
dc.identifier.scopusauthoridWong, KYK=24402187900en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats