Accurate Segmentation and Estimation of Parametric Motion Fields for Object-based Video Coding using Mean Field Theory

dc.contributor.authorHaridasan, Radhakrishanen_US
dc.contributor.authorBaras, John S.en_US
dc.contributor.departmentISRen_US
dc.contributor.departmentCSHCNen_US
dc.date.accessioned2007-05-23T10:05:18Z
dc.date.available2007-05-23T10:05:18Z
dc.date.issued1997en_US
dc.description.abstractWe formulate the problem of decomposing a scene into its constituent objects as one of partitioning the current frame into objects comprising it. The motion parameter is modeled as a nonrandom but unknown quantity and the problem is posed as one of Maximum Likelihood (ML) estimation. The MRF potentials which characterize the underlying segmentation field are defined in a way that the spatio-temporal segmentation is constrained by the static image segmentation of the current frame. To compute the motion parameter vector and the segmentation simultaneously we use the Expectation Maximization (EM) algorithm. The E-step of the EM algorithm, which computes the conditional expectation of the segmentation field, now reflects interdependencies more accurately because of neighborhood interactions. We take recourse to Mean Field theory to compute the expected value of the conditional MRF. Robust M-estimation methods are used in the M- step. To allow for motions of large magnitudes image frames are represented at various scales and the EM procedure is embedded in a hierarchical coarse-to-fine framework. Our formulation results in a highly parallel algorithm that computes robust and accurate segmentations as well as motion vectors for use in low bit rate video coding. <P><Center><I>This report has been submitted as a paper to the SPIE conference on Visual Communications and Image Processing - VCIP98 to be held in San Jose, California on Jan 24- 30, 1998. </I></Center>en_US
dc.format.extent249211 bytes
dc.format.mimetypeapplication/pdf
dc.identifier.urihttp://hdl.handle.net/1903/5928
dc.language.isoen_USen_US
dc.relation.ispartofseriesISR; TR 1997-82en_US
dc.relation.ispartofseriesCSHCN; TR 1997-31en_US
dc.subjectdata compressionen_US
dc.subjectestimationen_US
dc.subjectrobust information processingen_US
dc.subjectsignal processingen_US
dc.subjectmotion-based segmentationen_US
dc.subjectMarkov random fielden_US
dc.subjectmean field theoryen_US
dc.subjectexpectation-maximizationen_US
dc.subjectobject- based codingen_US
dc.subjectIntelligent Signal Processing en_US
dc.subjectCommunications Systemsen_US
dc.titleAccurate Segmentation and Estimation of Parametric Motion Fields for Object-based Video Coding using Mean Field Theoryen_US
dc.typeTechnical Reporten_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
TR_97-82.pdf
Size:
243.37 KB
Format:
Adobe Portable Document Format