Utilization of improved recursive-shortest-spanning-tree method for video object segmentation

buir.advisorOnural, Levent
dc.contributor.authorTuncel, Ertem
dc.date.accessioned2016-01-08T20:19:09Z
dc.date.available2016-01-08T20:19:09Z
dc.date.issued1997
dc.descriptionAnkara : Department of Electrical and Electronics Engineering and Institute of Engineering and Sciences, Bilkent Univ., 1997.en_US
dc.descriptionThesis(Master's) -- Bilkent University, 1997.en_US
dc.descriptionIncludes bibliographical references leaves 77-81en_US
dc.description.abstractEmerging standards MPEG-4 and MPEG-7 do not standardize the video object segmentation tools, although their performance depends on them. There are a lot of still image segmentation algorithms in the literature, like clustering, split-and-merge, region merging, etc. One of these methods, namely the recursive shortest spanning tree (RSST) method, is improved so that a still image is approximated as a piecewise planar function, and well-approximated areas on the image are extracted cis regions. A novel video object segmentation algorithm, which takes the previously estimated 2-D dense motion vector field as input, and uses this improved RSST method to approximate each component of the motion vector field as a piecewise planar function, is proposed. The algorithm is successful in locating 3-D planar objects in the scene correctly, with acceptable accuracy at the boundaries. Unlike the existing algorithms in the literature, the proposed algorithm is fast, parameter-free and requires no initial guess about the segmentation result. Moreover, it is a hierarchical scheme which gives finest to coarsest segmentation results. The proposed algorithm is inserted into the current version of the emerging “Analysis Model (AM)” of the Europan COST21U'’’ project, and it is observed that the current AM is outperformed.en_US
dc.description.provenanceMade available in DSpace on 2016-01-08T20:19:09Z (GMT). No. of bitstreams: 1 1.pdf: 78510 bytes, checksum: d85492f20c2362aa2bcf4aad49380397 (MD5)en
dc.description.statementofresponsibilityTuncel, Ertemen_US
dc.format.extent81 leaves, illustrationsen_US
dc.identifier.urihttp://hdl.handle.net/11693/18424
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectVideo object segmentationen_US
dc.subjectRecursive shortest spanning tree methoden_US
dc.subject2-D motion estimationen_US
dc.subjectHierarchical segmentationen_US
dc.subjectMPEG-4en_US
dc.subjectMPEG-7en_US
dc.subject.lccTK6680.5 .T86 1997en_US
dc.subject.lcshDigital video.en_US
dc.subject.lcshImage processing.en_US
dc.titleUtilization of improved recursive-shortest-spanning-tree method for video object segmentationen_US
dc.typeThesisen_US
thesis.degree.disciplineElectrical and Electronic Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
B038373.pdf
Size:
9.61 MB
Format:
Adobe Portable Document Format
Description:
Full printable version