Repository logo
 
Publication

Tracking with Bayesian networks: extension to arbitrary topologies

dc.contributor.authorJorge, Pedro
dc.contributor.authorAbrantes, Arnaldo
dc.contributor.authorMarques, Jorge S.
dc.date.accessioned2021-05-24T12:57:29Z
dc.date.available2021-05-24T12:57:29Z
dc.date.issued2005-11-14
dc.description.abstractIt was recently proposed an object tracking method, which is able to deal with object occlusions and group tracking, using Bayesian networks. The Bayesian network (BN) tracker has shown promising results in difficult situations but its architecture is limited to a maximum of 2 parents/2 children per node, in order to avoid the combinatorial explosion and difficult network generation procedures from the video signal. This paper addresses the major limitation of the BN tracker and presents a method to generalize the tracker to cope with arbitrary topologies, allowing the tracker to operate in more complex scenes.pt_PT
dc.description.versioninfo:eu-repo/semantics/publishedVersionpt_PT
dc.identifier.citationJORGE, Pedro M.; ABRANTES, Arnaldo J.; MARQUES, Jorge S. – Tracking with Bayesian networks: extension to arbitrary topologies. In IEEE International Conference on Image Processing 2005. Genova, Italy: IEEE, 2005. ISBN 0-7803-9134-9, pp. 1-4pt_PT
dc.identifier.doi10.1109/ICIP.2005.1530077pt_PT
dc.identifier.eissn2381-8549
dc.identifier.isbn0-7803-9134-9
dc.identifier.issn1522-4880
dc.identifier.urihttp://hdl.handle.net/10400.21/13380
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherIEEEpt_PT
dc.relationPOSI 37844/01 - FCT under project LTTpt_PT
dc.relation.publisherversionhttps://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1530077pt_PT
dc.subjectBayesian networkspt_PT
dc.subjectArbitrary topologiespt_PT
dc.titleTracking with Bayesian networks: extension to arbitrary topologiespt_PT
dc.typeconference object
dspace.entity.typePublication
oaire.citation.conferencePlace14-14 Sept. 2005 - Genova, Italypt_PT
oaire.citation.endPage4pt_PT
oaire.citation.startPage1pt_PT
oaire.citation.titleIEEE International Conference on Image Processing 2005pt_PT
person.familyNameAbrantes
person.familyNameMarques
person.givenNameArnaldo
person.givenNameJorge
person.identifier.ciencia-idF61C-F1EB-88B8
person.identifier.ciencia-id7B1E-D0E8-5319
person.identifier.ciencia-idCC1B-CA80-97DF
person.identifier.orcid0000-0003-1597-410X
person.identifier.orcid0000-0002-9911-6833
person.identifier.orcid0000-0002-3800-7756
person.identifier.ridC-1427-2010
person.identifier.scopus-author-id7003329558
person.identifier.scopus-author-id7203033359
rcaap.rightsopenAccesspt_PT
rcaap.typeconferenceObjectpt_PT
relation.isAuthorOfPublicationaaf73613-1657-426b-bfad-61538719c7a1
relation.isAuthorOfPublication7fb56aaa-cf87-4ce3-8047-b07e2a8bc758
relation.isAuthorOfPublication6f7b0989-09bf-417c-9b28-88d06f42894c
relation.isAuthorOfPublication.latestForDiscoveryaaf73613-1657-426b-bfad-61538719c7a1

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Tracking_PMJorge.pdf
Size:
200.38 KB
Format:
Adobe Portable Document Format