Hybrid object-based video compression scheme using a novel content-based automatic segmentation algorithm

Hdl Handle:
http://hdl.handle.net/10149/99337
Title:
Hybrid object-based video compression scheme using a novel content-based automatic segmentation algorithm
Book Title:
IEEE International Conference on Communications
Authors:
Tsoligkas, N. A. (Nick); Xu, D. (Donglai); French, I. (Ian)
Affiliation:
University of Teesside. School of Science and Technology.
Citation:
Tsoligkas, N. A., Xu, D. and French, I. (2007) 'Hybrid object-based video compression scheme using a novel content-based automatic segmentation algorithm', 2007 IEEE international conference on communications, Glasgow, Scotland, June 24 - 28, in IEEE International Conference on Communications. IEEE, pp.2654-2659.
Publisher:
IEEE
Conference:
2007 IEEE international conference on communications, Glasgow, Scotland, June 24 - 28, 2007
Issue Date:
2007
URI:
http://hdl.handle.net/10149/99337
DOI:
10.1109/ICC.2007.440
Abstract:
This paper describes a hybrid object-based video coding scheme that achieves efficient compression by separating moving objects from stationary background and transmitting the shape, motion and residuals for each segmented object. In this scheme, a new content-based object segmentation algorithm is proposed, which does not assume any prior modeling of the objects being segmented. The binarization process, which finds large object regions, is based on a threshold function that calculates block histograms and takes image noise into account. The resultant binary mask is further processed using morphological operations. The motion vectors are estimated inside the change detection mask using block-matching method between two successive frames, and then the dense motion field is estimated using the motion vectors and the Horn-Schunck algorithm.
Type:
Meetings and Proceedings; Book Chapter
Language:
en
Keywords:
content-based video coding; motion compensation; motion estimation; motion failure area; object segmentation; variable length coding
ISSN:
0536-1486
ISBN:
9781424403530
Rights:
Author can archive publisher's version/PDF. For full details see http://www.sherpa.ac.uk/romeo/ [Accessed 19/05/2010]
Citation Count:
0 [Scopus, 19/05/2010]

Full metadata record

DC FieldValue Language
dc.contributor.authorTsoligkas, N. A. (Nick)en
dc.contributor.authorXu, D. (Donglai)en
dc.contributor.authorFrench, I. (Ian)en
dc.date.accessioned2010-05-19T15:53:26Z-
dc.date.available2010-05-19T15:53:26Z-
dc.date.issued2007-
dc.identifier.isbn9781424403530-
dc.identifier.issn0536-1486-
dc.identifier.doi10.1109/ICC.2007.440-
dc.identifier.urihttp://hdl.handle.net/10149/99337-
dc.description.abstractThis paper describes a hybrid object-based video coding scheme that achieves efficient compression by separating moving objects from stationary background and transmitting the shape, motion and residuals for each segmented object. In this scheme, a new content-based object segmentation algorithm is proposed, which does not assume any prior modeling of the objects being segmented. The binarization process, which finds large object regions, is based on a threshold function that calculates block histograms and takes image noise into account. The resultant binary mask is further processed using morphological operations. The motion vectors are estimated inside the change detection mask using block-matching method between two successive frames, and then the dense motion field is estimated using the motion vectors and the Horn-Schunck algorithm.en
dc.language.isoenen
dc.publisherIEEEen
dc.rightsAuthor can archive publisher's version/PDF. For full details see http://www.sherpa.ac.uk/romeo/ [Accessed 19/05/2010]en
dc.subjectcontent-based video codingen
dc.subjectmotion compensationen
dc.subjectmotion estimationen
dc.subjectmotion failure areaen
dc.subjectobject segmentationen
dc.subjectvariable length codingen
dc.titleHybrid object-based video compression scheme using a novel content-based automatic segmentation algorithmen
dc.typeMeetings and Proceedingsen
dc.typeBook Chapteren
dc.contributor.departmentUniversity of Teesside. School of Science and Technology.en
dc.title.bookIEEE International Conference on Communicationsen
dc.identifier.conference2007 IEEE international conference on communications, Glasgow, Scotland, June 24 - 28, 2007en
ref.citationcount0 [Scopus, 19/05/2010]en
or.citation.harvardTsoligkas, N. A., Xu, D. and French, I. (2007) 'Hybrid object-based video compression scheme using a novel content-based automatic segmentation algorithm', 2007 IEEE international conference on communications, Glasgow, Scotland, June 24 - 28, in IEEE International Conference on Communications. IEEE, pp.2654-2659.-
prism.startingPage2654-
prism.endingPage2659-
All Items in TeesRep are protected by copyright, with all rights reserved, unless otherwise indicated.