Motion estimation for multi-camera systems using global optimization

Simple item page
dc.contributor.authorKim, J.-H.
dc.contributor.authorLi, H.
dc.contributor.authorHartley, R.
dc.contributor.conferenceIEEE Conference on Computer Vision and Pattern Recognition (23 Jun 2013 - 28 Jun 2013 : Anchorage, AK)
dc.date.issued2008
dc.description.abstractWe present a motion estimation algorithm for multi-camera systems consisting of more than one calibrated camera securely attached on a moving object. So, they move all together, but do not require to have overlapping views across the cameras. The geometrically optimal solution of the motion for the multi-camera systems under Linfin norm is provided in this paper using a global optimization technique which has been introduced recently in the computer vision research field. Taking advantage of an optimal estimate of the essential matrix through searching rotation space, we provide the optimal solution for translation by using linear programming and branch & bound algorithm. Synthetic and real data experiments are conducted, and they show more robust and improved performance than the previous methods.
dc.description.statementofresponsibilityJae-Hak Kim, Hongdong Li, Richard Hartley
dc.identifier.citationProceedings / CVPR, IEEE Computer Society Conference on Computer Vision and Pattern Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2008, pp.1-8
dc.identifier.doi10.1109/CVPR.2008.4587680
dc.identifier.isbn9781424422432
dc.identifier.issn1063-6919
dc.identifier.urihttp://hdl.handle.net/2440/85491
dc.language.isoen
dc.publisherIEEE
dc.rights©2008 IEEE
dc.source.urihttp://dx.doi.org/10.1109/cvpr.2008.4587680
dc.titleMotion estimation for multi-camera systems using global optimization
dc.typeConference paper
pubs.publication-statusPublished

Files

Collections

Computer Science publications