File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Two-view multibody structure from motion

TitleTwo-view multibody structure from motion
Authors
Keywords3-D motion segmentation
Generalized PCA (GPCA)
Multibody epipolar constraint
Multibody fundamental matrix
Multibody structure from motion
Issue Date2006
Citation
International Journal of Computer Vision, 2006, v. 68, n. 1, p. 7-25 How to Cite?
AbstractWe present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our approach exploits the algebraic and geometric properties of the so-called multibody epipolar constraint and its associated multibody fundamental matrix, which are natural generalizations of the epipolar constraint and of the fundamental matrix to multiple motions. We derive a rank constraint on a polynomial embedding of the correspondences, from which one can estimate the number of independent motions as well as linearly solve for the multibody fundamental matrix. We then show how to compute the epipolar lines from the first-order derivatives of the multibody epipolar constraint and the epipoles by solving a plane clustering problem using Generalized PCA (GPCA). Given the epipoles and epipolar lines, the estimation of individual fundamental matrices becomes a linear problem. The clustering of the feature points is then automatically obtained from either the epipoles and epipolar lines or from the individual fundamental matrices. Although our approach is mostly designed for noise-free correspondences, we also test its performance on synthetic and real data with moderate levels of noise. © 2006 Springer Science + Business Media, LLC.
Persistent Identifierhttp://hdl.handle.net/10722/326700
ISSN
2023 Impact Factor: 11.6
2023 SCImago Journal Rankings: 6.668
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorVidal, René-
dc.contributor.authorMa, Yi-
dc.contributor.authorSoatto, Stefano-
dc.contributor.authorSastry, Shankar-
dc.date.accessioned2023-03-31T05:25:53Z-
dc.date.available2023-03-31T05:25:53Z-
dc.date.issued2006-
dc.identifier.citationInternational Journal of Computer Vision, 2006, v. 68, n. 1, p. 7-25-
dc.identifier.issn0920-5691-
dc.identifier.urihttp://hdl.handle.net/10722/326700-
dc.description.abstractWe present an algebraic geometric approach to 3-D motion estimation and segmentation of multiple rigid-body motions from noise-free point correspondences in two perspective views. Our approach exploits the algebraic and geometric properties of the so-called multibody epipolar constraint and its associated multibody fundamental matrix, which are natural generalizations of the epipolar constraint and of the fundamental matrix to multiple motions. We derive a rank constraint on a polynomial embedding of the correspondences, from which one can estimate the number of independent motions as well as linearly solve for the multibody fundamental matrix. We then show how to compute the epipolar lines from the first-order derivatives of the multibody epipolar constraint and the epipoles by solving a plane clustering problem using Generalized PCA (GPCA). Given the epipoles and epipolar lines, the estimation of individual fundamental matrices becomes a linear problem. The clustering of the feature points is then automatically obtained from either the epipoles and epipolar lines or from the individual fundamental matrices. Although our approach is mostly designed for noise-free correspondences, we also test its performance on synthetic and real data with moderate levels of noise. © 2006 Springer Science + Business Media, LLC.-
dc.languageeng-
dc.relation.ispartofInternational Journal of Computer Vision-
dc.subject3-D motion segmentation-
dc.subjectGeneralized PCA (GPCA)-
dc.subjectMultibody epipolar constraint-
dc.subjectMultibody fundamental matrix-
dc.subjectMultibody structure from motion-
dc.titleTwo-view multibody structure from motion-
dc.typeConference_Paper-
dc.description.naturelink_to_subscribed_fulltext-
dc.identifier.doi10.1007/s11263-005-4839-7-
dc.identifier.scopuseid_2-s2.0-30144446374-
dc.identifier.volume68-
dc.identifier.issue1-
dc.identifier.spage7-
dc.identifier.epage25-
dc.identifier.eissn1573-1405-
dc.identifier.isiWOS:000238228900002-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats