Gibbs model based 3D motion and structure estimation for object-based video coding applications

dc.citation.epage393en_US
dc.citation.spage355en_US
dc.citation.volumeNumber378en_US
dc.contributor.authorOnural, Leventen_US
dc.contributor.authorAlatan, A. A.en_US
dc.contributor.editorLi, H. H.
dc.contributor.editorSun, S.
dc.contributor.editorDerin, H.
dc.date.accessioned2019-04-22T11:59:14Z
dc.date.available2019-04-22T11:59:14Z
dc.date.issued1997en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionChapter 10
dc.description.abstractMotion analysis is essential for any video coding scheme. A moving object in a 3D environment can be analyzed better by a 3D motion model instead of 2D models, and better modeling might lead to improved coding efficiency. Gibbs formulated joint segmentation and estimation of 2D motion not only improves the performance of each stage, but also generates robust point correspondences which are necessary for rigid 3D motion estimation algorithms. Estimated rigid 3D motion parameters of a segmented object are used to find the 3D structure of those objects by minimizing another Gibbs energy. Such an approach achieves error immunity compared to linear algorithms. A more general (non-rigid) motion model can also be proposed using Gibbs formulation which permits local elastic interactions in contrast to ultimately tight rigidity between object points. Experimental results are promising for both rigid and non-rigid 3D motion models and put these models forward as strong candidates to be used in object-based coding algorithms.en_US
dc.description.provenanceSubmitted by Evrim Ergin (eergin@bilkent.edu.tr) on 2019-04-22T11:59:14Z No. of bitstreams: 1 Gibbs_model_based_3D_motion_and_structure_estimation_for_object_based_video_coding_applications.pdf: 5195972 bytes, checksum: 98d511bc52d5b874cda9d8b10e8265a0 (MD5)en
dc.description.provenanceMade available in DSpace on 2019-04-22T11:59:14Z (GMT). No. of bitstreams: 1 Gibbs_model_based_3D_motion_and_structure_estimation_for_object_based_video_coding_applications.pdf: 5195972 bytes, checksum: 98d511bc52d5b874cda9d8b10e8265a0 (MD5) Previous issue date: 1997en
dc.identifier.doi10.1007/978-1-4615-6239-9_10en_US
dc.identifier.eisbn9781461562399
dc.identifier.isbn9781461378624
dc.identifier.urihttp://hdl.handle.net/11693/50879
dc.language.isoEnglishen_US
dc.publisherSpringeren_US
dc.relation.ispartofVideo data compression for multimedia computing statistically based and biologically inspired techniquesen_US
dc.relation.ispartofseriesThe Springer International Series in Engineering and Computer Science
dc.relation.isversionofhttps://doi.org/10.1007/978-1-4615-6239-9_10en_US
dc.relation.isversionofhttps://doi.org/10.1007/978-1-4615-6239-9en_US
dc.subjectMotion vectoren_US
dc.subjectMotion estimationen_US
dc.subjectVideo codeen_US
dc.subjectIterate conditional modeen_US
dc.subjectDepth fielden_US
dc.titleGibbs model based 3D motion and structure estimation for object-based video coding applicationsen_US
dc.typeBook Chapteren_US

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Gibbs_model_based_3D_motion_and_structure_estimation_for_object_based_video_coding_applications.pdf
Size:
4.96 MB
Format:
Adobe Portable Document Format
Description:
View / Download

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description: