File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Mixed-state Markov random fields for motion texture modeling and segmentation

TitleMixed-state Markov random fields for motion texture modeling and segmentation
Authors
KeywordsImage motion analysis
Image segmentation
Image texture analysis
Stochastic fields
Issue Date2006
PublisherI E E E. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349
Citation
Proceedings - International Conference On Image Processing, Icip, 2006, p. 1857-1860 How to Cite?
AbstractThe aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes. We adopt the mixed-state Markov Random Fields (MRF) models recently introduced to represent so-called motion textures. The approach consists in describing the spatial distribution of some motion measurements which exhibit mixed-state nature: a discrete component related to the absence of motion and a continuous part for measurements different from zero. We propose several significative extensions to this model. We define an original motion texture segmentation method which does not assume conditional independence of the observations for each texture and normalizing factors are properly handled. Results on real examples demonstrate the accuracy and efficiency of our method. ©2006 IEEE.
Persistent Identifierhttp://hdl.handle.net/10722/132615
ISSN
References

 

DC FieldValueLanguage
dc.contributor.authorCrivelli, Ten_HK
dc.contributor.authorCernuschiFrias, 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 - International Conference On Image Processing, Icip, 2006, p. 1857-1860en_HK
dc.identifier.issn1522-4880en_HK
dc.identifier.urihttp://hdl.handle.net/10722/132615-
dc.description.abstractThe aim of this work is to model the apparent motion in image sequences depicting natural dynamic scenes. We adopt the mixed-state Markov Random Fields (MRF) models recently introduced to represent so-called motion textures. The approach consists in describing the spatial distribution of some motion measurements which exhibit mixed-state nature: a discrete component related to the absence of motion and a continuous part for measurements different from zero. We propose several significative extensions to this model. We define an original motion texture segmentation method which does not assume conditional independence of the observations for each texture and normalizing factors are properly handled. Results on real examples demonstrate the accuracy and efficiency of our method. ©2006 IEEE.en_HK
dc.languageengen_US
dc.publisherI E E E. The Journal's web site is located at http://ieeexplore.ieee.org/xpl/conhome.jsp?punumber=1000349en_HK
dc.relation.ispartofProceedings - International Conference on Image Processing, ICIPen_HK
dc.subjectImage motion analysisen_HK
dc.subjectImage segmentationen_HK
dc.subjectImage texture analysisen_HK
dc.subjectStochastic fieldsen_HK
dc.titleMixed-state Markov random fields for motion texture modeling and segmentationen_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.doi10.1109/ICIP.2006.312842en_HK
dc.identifier.scopuseid_2-s2.0-51449122841en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-51449122841&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.spage1857en_HK
dc.identifier.epage1860en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridCrivelli, T=25824832900en_HK
dc.identifier.scopusauthoridCernuschiFrias, B=35271044900en_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