File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Motion characterization by temporal slices analysis

TitleMotion characterization by temporal slices analysis
Authors
KeywordsAlgorithms
Cameras
Computer vision
Image segmentation
Motion compensation
Object recognition
Issue Date2000
PublisherIEEE, Computer Society
Citation
Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2000, v. 2, p. 768-773 How to Cite?
AbstractThis paper describes an approach to characterize camera and object motions based on the analysis of spatio-temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram computation algorithm to represent these patterns. The motion trajectories in a histogram are tracked to describe both the camera and object motions. In addition, we exploit the similarity of the temporal slices in a volume to reliably partition a volume into motion tractable units.
Persistent Identifierhttp://hdl.handle.net/10722/65593
ISSN

 

DC FieldValueLanguage
dc.contributor.authorNgo, ChongWahen_HK
dc.contributor.authorPong, TingChuenen_HK
dc.contributor.authorZhang, HongJiangen_HK
dc.contributor.authorChin, Roland Ten_HK
dc.date.accessioned2010-08-31T07:16:23Z-
dc.date.available2010-08-31T07:16:23Z-
dc.date.issued2000en_HK
dc.identifier.citationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2000, v. 2, p. 768-773en_HK
dc.identifier.issn1063-6919en_HK
dc.identifier.urihttp://hdl.handle.net/10722/65593-
dc.description.abstractThis paper describes an approach to characterize camera and object motions based on the analysis of spatio-temporal image volumes. In the spatio-temporal slices of image volumes, motion is depicted as oriented patterns. We propose a tensor histogram computation algorithm to represent these patterns. The motion trajectories in a histogram are tracked to describe both the camera and object motions. In addition, we exploit the similarity of the temporal slices in a volume to reliably partition a volume into motion tractable units.en_HK
dc.languageengen_HK
dc.publisherIEEE, Computer Societyen_HK
dc.relation.ispartofProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognitionen_HK
dc.subjectAlgorithmsen_HK
dc.subjectCamerasen_HK
dc.subjectComputer visionen_HK
dc.subjectImage segmentationen_HK
dc.subjectMotion compensationen_HK
dc.subjectObject recognitionen_HK
dc.titleMotion characterization by temporal slices analysisen_HK
dc.typeConference_Paperen_HK
dc.identifier.emailChin, Roland T: rchin@hku.hken_HK
dc.identifier.authorityChin, Roland T=rp01300en_HK
dc.description.naturelink_to_subscribed_fulltexten_HK
dc.identifier.scopuseid_2-s2.0-0033725288en_HK
dc.identifier.volume2en_HK
dc.identifier.spage768en_HK
dc.identifier.epage773en_HK
dc.publisher.placeUnited Statesen_HK
dc.identifier.scopusauthoridNgo, ChongWah=7005184304en_HK
dc.identifier.scopusauthoridPong, TingChuen=7004618149en_HK
dc.identifier.scopusauthoridZhang, HongJiang=7409194828en_HK
dc.identifier.scopusauthoridChin, Roland T=7102445426en_HK

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats