File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Segmentation of motion textures using mixed-state Markov Random Fields

TitleSegmentation of motion textures using mixed-state Markov Random Fields
Authors
KeywordsImage motion analysis
Image texture analysis
Markov random fields
Segmentation
Issue Date2006
PublisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xml
Citation
Proceedings Of Spie - The International Society For Optical Engineering, 2006, v. 6315 How to Cite?
AbstractThe aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes (rivers, sea-waves, smoke, fire, grass etc) where some sort of stationarity and homogeneity of motion is present. We adopt the mixed-state Markov Random Fields models recently introduced to represent so-called motion textures. The approach consists in describing the distribution of some motion measurements which exhibit a mixed nature: a discrete component related to absence of motion and a continuous part for measurements different from zero. We propose several extensions on the spatial schemes. In this context, Gibbs distributions are analyzed, and a deep study of the associated partition functions is addressed. Our approach is valid for general Gibbs distributions. Some particular cases of interest for motion texture modeling are analyzed. This is crucial for problems of segmentation, detection and classification. Then, we propose an original approach for image motion segmentation based on these models, where normalization factors are properly handled. Results for motion textures on real natural sequences demonstrate the accuracy and efficiency of our method.
Persistent Identifierhttp://hdl.handle.net/10722/132616
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorCrivelli, Ten_HK
dc.contributor.authorCernuschiFrías, Ben_HK
dc.contributor.authorBouthemy, Pen_HK
dc.contributor.authorYao, JFen_HK
dc.date.accessioned2011-03-28T09:27:01Z-
dc.date.available2011-03-28T09:27:01Z-
dc.date.issued2006en_HK
dc.identifier.citationProceedings Of Spie - The International Society For Optical Engineering, 2006, v. 6315en_HK
dc.identifier.issn0277-786Xen_HK
dc.identifier.urihttp://hdl.handle.net/10722/132616-
dc.description.abstractThe aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes (rivers, sea-waves, smoke, fire, grass etc) where some sort of stationarity and homogeneity of motion is present. We adopt the mixed-state Markov Random Fields models recently introduced to represent so-called motion textures. The approach consists in describing the distribution of some motion measurements which exhibit a mixed nature: a discrete component related to absence of motion and a continuous part for measurements different from zero. We propose several extensions on the spatial schemes. In this context, Gibbs distributions are analyzed, and a deep study of the associated partition functions is addressed. Our approach is valid for general Gibbs distributions. Some particular cases of interest for motion texture modeling are analyzed. This is crucial for problems of segmentation, detection and classification. Then, we propose an original approach for image motion segmentation based on these models, where normalization factors are properly handled. Results for motion textures on real natural sequences demonstrate the accuracy and efficiency of our method.en_HK
dc.languageengen_US
dc.publisherS P I E - International Society for Optical Engineering. The Journal's web site is located at http://spie.org/x1848.xmlen_HK
dc.relation.ispartofProceedings of SPIE - The International Society for Optical Engineeringen_HK
dc.subjectImage motion analysisen_HK
dc.subjectImage texture analysisen_HK
dc.subjectMarkov random fieldsen_HK
dc.subjectSegmentationen_HK
dc.titleSegmentation of motion textures using mixed-state Markov Random Fieldsen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailYao, JF: jeffyao@hku.hken_HK
dc.identifier.authorityYao, JF=rp01473en_HK
dc.description.naturelink_to_subscribed_fulltexten_US
dc.identifier.doi10.1117/12.674648en_HK
dc.identifier.scopuseid_2-s2.0-33750601052en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-33750601052&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume6315en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridCrivelli, T=25824832900en_HK
dc.identifier.scopusauthoridCernuschiFrías, B=7003558300en_HK
dc.identifier.scopusauthoridBouthemy, P=7005146506en_HK
dc.identifier.scopusauthoridYao, JF=7403503451en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats