Show simple item record

dc.contributor.authorMihalik, J.
dc.contributor.authorMichalcin, V.
dc.date.accessioned2016-04-22T06:14:51Z
dc.date.available2016-04-22T06:14:51Z
dc.date.issued2006-06cs
dc.identifier.citationRadioengineering. 2006, vol. 15, č. 2, s. 37-44. ISSN 1210-2512cs
dc.identifier.issn1210-2512
dc.identifier.urihttp://hdl.handle.net/11012/57953
dc.description.abstractThe paper deals with the new algorithm of estimation of large 3D motion of the human head by using the optical flow and the model Candide. In the algorithm prediction of 3D motion parameters in a feedback loop and with multiple iterations was applied. The prediction of 3D motion parameters does not require creating of the synthesized frames but directly uses the frames of input videosequence. Next the algorithm does not need extracting of feature points inside the frames because they are given by the vertices of the used calibrated model Candide. As achieved experimental results show, the iteration process in prediction of 3D motion parameters increased the accuracy of estimation above all the large 3D motion. Such a way the estimation error is decreased without its accumulation in long videosequence. Finally the experimental results show that for 3 iterations a state of saturation was achieved what means that by next increasing of the number of iterations practically no significant increasing of the accuracy of estimation of 3D motion parameters is occurred.en
dc.formattextcs
dc.format.extent37-44cs
dc.format.mimetypeapplication/pdfen
dc.language.isoencs
dc.publisherSpolečnost pro radioelektronické inženýrstvícs
dc.relation.ispartofRadioengineeringcs
dc.relation.urihttp://www.radioeng.cz/fulltexts/2006/06_02_37_44.pdfcs
dc.rightsCreative Commons Attribution 3.0 Unported Licenseen
dc.rights.urihttp://creativecommons.org/licenses/by/3.0/en
dc.subjectOptical flowen
dc.subject3D motionen
dc.subjectestimationen
dc.subjectpredictionen
dc.subjectmodelingen
dc.subjecthuman headen
dc.subjectalgorithmen
dc.title3D Motion Estimation of Human Head by Using Optical Flowen
eprints.affiliatedInstitution.facultyFakulta eletrotechniky a komunikačních technologiícs
dc.coverage.issue2cs
dc.coverage.volume15cs
dc.rights.accessopenAccessen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Creative Commons Attribution 3.0 Unported License
Except where otherwise noted, this item's license is described as Creative Commons Attribution 3.0 Unported License