Gibbs random field model based 3-D motion estimation from video sequences

dc.citation.epage637en_US
dc.citation.spage626en_US
dc.citation.volumeNumber2308en_US
dc.contributor.authorAlatan, A. A.en_US
dc.contributor.authorLevent, O.en_US
dc.date.accessioned2016-02-08T10:52:45Z
dc.date.available2016-02-08T10:52:45Z
dc.date.issued1994en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.description.abstractIn contrast to previous global 3D motion concept, a Gibbs random field based method, which models local interactions between motion parameters defined at each point on the object, is proposed. An energy function which gives the joint probability distribution of motion vectors, is constructed. The energy function is minimized in order to find the most likely motion vector set. Some convergence problems, due to ill-posedness of the problem, are overcome by using the concept of hierarchical rigidity. In hierarchical rigidity, the objects are assumed to be almost rigid in the coarsest level and this rigidness is weakened at each level until the finest level is reached. The propagation of motion information between levels, is encouraged. At the finest level, each point have a motion vector associated with it and the interaction between these vectors are described by the energy function. The minimization of the energy function is achieved by using hierarchical rigidity, without trapping into a local minimum. The results are promising.en_US
dc.description.provenanceMade available in DSpace on 2016-02-08T10:52:45Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 70227 bytes, checksum: 26e812c6f5156f83f0e77b261a471b5a (MD5) Previous issue date: 1994en
dc.identifier.doi10.1109/ICIP.1994.413679en_US
dc.identifier.issn0277-786X
dc.identifier.urihttp://hdl.handle.net/11693/25942
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://doi.org/10.1109/ICIP.1994.413679en_US
dc.source.titleProceedings of SPIE - The International Society for Optical Engineeringen_US
dc.subjectGibbs random fielden_US
dc.subjectMotion estimationen_US
dc.subjectThree dimensional motionen_US
dc.subjectComputer visionen_US
dc.subjectProbabilityen_US
dc.subjectThree dimensionalen_US
dc.subjectVideo signal processingen_US
dc.subjectImage processingen_US
dc.titleGibbs random field model based 3-D motion estimation from video sequencesen_US
dc.typeArticleen_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Gibbs random field model based 3D motion estimation from video sequences.pdf
Size:
620.38 KB
Format:
Adobe Portable Document Format
Description:
Full printable version