Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Full metadata record
DC FieldValueLanguage
dc.contributor.authorMilan, A.en
dc.contributor.authorRikke, G.en
dc.contributor.authorDick, A.en
dc.contributor.authorMoeslund, T.en
dc.contributor.authorReid, I.en
dc.identifier.citationProceedings of the 13th European Conference on Computer Vision Workshop, Part IIIs, 2015 / vol.8927, pp.174-190en
dc.descriptionConference dates: September 6-7 & 12, 2014en
dc.description.abstractWe propose a scheme to explicitly detect and resolve ambiguous situations in multiple target tracking. During periods of uncertainty, our method applies multiple local single target trackers to hypothesise short term tracks. These tracks are combined with the tracks obtained by a global multi-target tracker, if they result in a reduction in the global cost function. Since tracking failures typically arise when targets become occluded, we propose a local data association scheme to maintain the target identities in these situations. We demonstrate a reduction of up to 50% in the global cost function, which in turn leads to superior performance on several challenging benchmark sequences. Additionally, we show tracking results in sports videos where poor video quality and frequent and severe occlusions between multiple players pose difficulties for state-of-the-art trackers.en
dc.description.statementofresponsibilityAnton Milan, Rikke Gade, Anthony Dick, Thomas B. Moeslund, and Ian Reiden
dc.relation.ispartofseriesLecture notes in Computer Science, vol. 8927en
dc.rights© Springer International Publishing Switzerland 2015en
dc.subjectMulti-target tracking, data associationen
dc.titleImproving global multi-target tracking with local updatesen
dc.typeConference paperen
dc.contributor.conference13th European Conference on Computer Vision Workshops (ECCV 2014) (06 Sep 2014 - 12 Sep 2014 : Zurich, Switzerland)en
pubs.library.collectionComputer Science publicationsen
dc.identifier.orcidDick, A. [0000-0001-9049-7345]en
dc.identifier.orcidReid, I. [0000-0001-7790-6423]en
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_107962.pdfRestricted Access2.15 MBAdobe PDFView/Open

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.