Object based 3-D motion and structure estimation

Simple item page
dc.citation.epage393en_US
dc.citation.spage390en_US
dc.contributor.authorAlatan, A. Aydınen_US
dc.contributor.authorOnural, Leventen_US
dc.coverage.spatialWashington DC, USAen_US
dc.date.accessioned2016-02-08T12:01:00Z
dc.date.available2016-02-08T12:01:00Z
dc.date.issued1996en_US
dc.departmentDepartment of Electrical and Electronics Engineeringen_US
dc.descriptionDate of Conference: 23-26 October 1995en_US
dc.descriptionConference Name: International Conference on Image Processing, IEEE 1995en_US
dc.description.abstractMotion analysis is the most crucial part of object-based coding. A motion in 3-D environment can be analyzed better by using a 3-D motion model compared to its 2-D counterpart and hence may improve coding efficiency. Gibbs formulated joint segmentation and estimation of 2-D motion not only improves performance, but also generates robust point correspondences which are necessary for linear 3-D motion estimation algorithms. Estimated 3-D motion parameters are used to find the structure of the previously segmented objects by minimizing another Gibbs energy. Such an approach achieves error immunity compared to linear algorithms. Experimental results are promising and hence the proposed motion and structure analysis method is a candidate to be used in object-based (or even knowledge-based) video coding schemes.en_US
dc.identifier.doi10.1109/ICIP.1995.529728en_US
dc.identifier.urihttp://hdl.handle.net/11693/27755
dc.language.isoEnglishen_US
dc.publisherIEEEen_US
dc.relation.isversionofhttp://doi.org/10.1109/ICIP.1995.529728en_US
dc.source.titleProceedings of the International Conference on Image Processing, IEEE 1995en_US
dc.subjectAlgorithmsen_US
dc.subjectGibbs free energyen_US
dc.subjectImage compressionen_US
dc.subjectImage segmentationen_US
dc.subjectKnowledge based systemsen_US
dc.subjectMathematical modelsen_US
dc.subjectOptical flowsen_US
dc.subjectParameter estimationen_US
dc.subjectThree dimensionalen_US
dc.subjectVectorsen_US
dc.subjectExponential joint distributionen_US
dc.subjectMotion analysisen_US
dc.subjectMotion estimation algorithmsen_US
dc.subjectObject segmentationen_US
dc.subjectImage codingen_US
dc.titleObject based 3-D motion and structure estimationen_US
dc.typeConference Paperen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Object_based_3_D_motion_and_structure_estimation.pdf
Size:
489.31 KB
Format:
Adobe Portable Document Format
Description:
View / Download
Download

Collections

Department of Electrical and Electronics Engineering