Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/107962
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Improving global multi-target tracking with local updates
Author: Milan, A.
Rikke, G.
Dick, A.
Moeslund, T.
Reid, I.
Citation: Lecture Notes in Artificial Intelligence, 2015 / Agapito, L., Bronstein, M.M., Rother, C. (ed./s), vol.8927, pp.174-190
Publisher: Springer
Issue Date: 2015
Series/Report no.: Lecture notes in Computer Science, vol. 8927
ISBN: 978-3-319-16198-3
ISSN: 0302-9743
1611-3349
Conference Name: 13th European Conference on Computer Vision Workshops (ECCV 2014) (6 Sep 2014 - 12 Sep 2014 : Zurich, Switzerland)
Editor: Agapito, L.
Bronstein, M.M.
Rother, C.
Statement of
Responsibility: 
Anton Milan, Rikke Gade, Anthony Dick, Thomas B. Moeslund, and Ian Reid
Abstract: We 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.
Keywords: Multi-target tracking, data association
Description: Conference dates: September 6-7 & 12, 2014
Rights: © Springer International Publishing Switzerland 2015
DOI: 10.1007/978-3-319-16199-0_13
Grant ID: http://purl.org/au-research/grants/arc/FL130100102
Published version: http://dx.doi.org/10.1007/978-3-319-16199-0_13
Appears in Collections:Aurora harvest 3
Computer Science publications

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


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