Show simple item record

dc.contributor.advisorOnural, Leventen_US
dc.contributor.authorBozdağı, Gözdeen_US
dc.date.accessioned2016-01-08T20:20:03Z
dc.date.available2016-01-08T20:20:03Z
dc.date.issued1994
dc.identifier.urihttp://hdl.handle.net/11693/18517
dc.descriptionAnkara : Department of Electrical and Electronics Engineering and the Institute of Engineering and Science of Bilkent Univ., 1994.en_US
dc.descriptionThesis (Ph.D.) -- Bilkent University, 1994.en_US
dc.descriptionIncludes bibliographical references leaves 81-89.en_US
dc.description.abstractWe propose a novel formulation where 3-D global and local motion estimation and the adaptation of a generic wire-frame model to a particular speaker are considered simultaneously within an optical flow based framework including the photometric effects of the motion. We use a flexible wire-frame model whose local structure is characterized by the normal vectors of the patches which are related to the coordinates of the nodes. Geometric constraints that describe the propagation of the movement of the nodes are introduced, which are then efficiently utilized to reduce the number of independent structure parameters. A stochastic relaxation algorithm has been used to determine optimum global motion estimates and the parameters describing the structure of the wire-frame model. For the initialization of the motion and structure parameters, a modified feature based algorithm is used whose performance has also been compared with the existing methods. Results with both simulated and real facial image sequences are provided.en_US
dc.description.statementofresponsibilityBozdağı, Gözdeen_US
dc.format.extentxi, 90 leavesen_US
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectImage sequence codingen_US
dc.subjectobject motion analysisen_US
dc.subjectobject shape analysisen_US
dc.subjectvery low bit rate codingen_US
dc.subjectvideophoneen_US
dc.subjectstochastic relaxationen_US
dc.subject3-D motion and structure estimationen_US
dc.subjectobject-based coding methodsen_US
dc.subject.lccTK5102.92 .B69 1994en_US
dc.subject.lcshData compression (Telecommunication).en_US
dc.subject.lcshCoding theory (Telecommunication).en_US
dc.titleThree-dimensional facial motion and structure estimation in video codingen_US
dc.typeThesisen_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.publisherBilkent Universityen_US
dc.description.degreePh.D.en_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record