File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Learned probabilistic image motion models for event detection in videos

TitleLearned probabilistic image motion models for event detection in videos
Authors
KeywordsData Acquisition
Image Analysis
Information Analysis
Pattern Recognition
Probability
Semantics
Issue Date2004
PublisherIEEE, Computer Society
Citation
Proceedings - International Conference On Pattern Recognition, 2004, v. 4, p. 207-210 How to Cite?
AbstractWe present new probabilistic motion models of interest for the detection of relevant dynamic contents (or events) in videos. We separately handle the dominant image motion assumed to be due to the camera motion and the residual image motion related to scene motion. These two motion components are then represented by different probabilistic models which are further recombined for the event detection task. The motion models associated to pre-identified classes of meaningful events are learned from a training set of video samples. The event detection scheme proceeds in two steps which exploit different kinds of information and allow us to progressively select the video segments of interest using Maximum Likelihood (ML) criteria. The efficiency of the proposed approach is demonstrated on sports videos.
Persistent Identifierhttp://hdl.handle.net/10722/132623
ISSN
2023 SCImago Journal Rankings: 0.584
References

 

DC FieldValueLanguage
dc.contributor.authorPiriou, Gen_HK
dc.contributor.authorBouthemy, Pen_HK
dc.contributor.authorYao, JFen_HK
dc.date.accessioned2011-03-28T09:27:04Z-
dc.date.available2011-03-28T09:27:04Z-
dc.date.issued2004en_HK
dc.identifier.citationProceedings - International Conference On Pattern Recognition, 2004, v. 4, p. 207-210en_HK
dc.identifier.issn1051-4651en_HK
dc.identifier.urihttp://hdl.handle.net/10722/132623-
dc.description.abstractWe present new probabilistic motion models of interest for the detection of relevant dynamic contents (or events) in videos. We separately handle the dominant image motion assumed to be due to the camera motion and the residual image motion related to scene motion. These two motion components are then represented by different probabilistic models which are further recombined for the event detection task. The motion models associated to pre-identified classes of meaningful events are learned from a training set of video samples. The event detection scheme proceeds in two steps which exploit different kinds of information and allow us to progressively select the video segments of interest using Maximum Likelihood (ML) criteria. The efficiency of the proposed approach is demonstrated on sports videos.en_HK
dc.languageengen_US
dc.publisherIEEE, Computer Societyen_US
dc.relation.ispartofProceedings - International Conference on Pattern Recognitionen_HK
dc.subjectData Acquisitionen_US
dc.subjectImage Analysisen_US
dc.subjectInformation Analysisen_US
dc.subjectPattern Recognitionen_US
dc.subjectProbabilityen_US
dc.subjectSemanticsen_US
dc.titleLearned probabilistic image motion models for event detection in videosen_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/ICPR.2004.1333740en_HK
dc.identifier.scopuseid_2-s2.0-10044261768en_HK
dc.relation.referenceshttp://www.scopus.com/mlt/select.url?eid=2-s2.0-10044261768&selection=ref&src=s&origin=recordpageen_HK
dc.identifier.volume4en_HK
dc.identifier.spage207en_HK
dc.identifier.epage210en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridPiriou, G=22433503700en_HK
dc.identifier.scopusauthoridBouthemy, P=7005146506en_HK
dc.identifier.scopusauthoridYao, JF=7403503451en_HK
dc.identifier.issnl1051-4651-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats