Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/86248
Citations
Scopus Web of Science® Altmetric
?
?
Type: Conference paper
Title: Globally optimal multi-target tracking on a hexagonal lattice
Author: Milan, A.
Schindler, K.
Citation: Computer Vision - ECCV 2010, 11th European Conference on Computer Vision, Heraklion, Crete, Greece, September 5-11, 2010, Proceedings, Part I, 2010 / Daniilidis, K., Maragos, P., Paragios, N. (ed./s), pp.466-479
Publisher: Springer
Publisher Place: Berlin
Issue Date: 2010
ISBN: 9783642155499
Conference Name: 11th European Conference on Computer Vision (ECCV 2010) (05 Sep 2010 - 11 Sep 2010 : Heraklion, Greece)
Statement of
Responsibility: 
Anton Andriyenko and Konrad Schindler
Abstract: We propose a global optimisation approach to multi-target tracking. The method extends recent work which casts tracking as an integer linear program, by discretising the space of target locations. Our main contribution is to show how dynamic models can be integrated in such an approach. The dynamic model, which encodes prior expectations about object motion, has been an important component of tracking systems for a long time, but has recently been dropped to achieve globally optimisable objective functions. We re-introduce it by formulating the optimisation problem such that deviations from the prior can be measured independently for each variable. Furthermore, we propose to sample the location space on a hexagonal lattice to achieve smoother, more accurate trajectories in spite of the discrete setting. Finally, we argue that non-maxima suppression in the measured evidence should be performed during tracking, when the temporal context and the motion prior are available, rather than as a preprocessing step on a per-frame basis. Experiments on five different recent benchmark sequences demonstrate the validity of our approach.
Description: Also cited as: Lecture Notes in Computer Science, 2009; 6311:466-479
Rights: © Springer-Verlag Berlin Heidelberg 2010
RMID: 0020137024
DOI: 10.1007/978-3-642-15549-9_34
Appears in Collections:Computer Science publications

Files in This Item:
There are no files associated with this item.


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