Please use this identifier to cite or link to this item: http://hdl.handle.net/10397/35485
Title: Fast visual tracking via dense spatio-temporal context learning
Authors: Zhang, K
Zhang, L 
Liu, Q
Zhang, D 
Yang, MH
Issue Date: 2014
Publisher: Springer
Source: In D Fleet, T Pajdla, B Schiele & T Tuytelaar (Eds.), Computer vision-- ECCV 2014 : 13th European Conference, Zurich, Switzerland, September 6-12, 2014 : proceedings. Part V, p. 127-141. Cham : Springer, 2014 How to cite?
Series/Report no.: Lecture notes in computer science, 2014, v. 8693
Abstract: In this paper, we present a simple yet fast and robust algorithm which exploits the dense spatio-temporal context for visual tracking. Our approach formulates the spatio-temporal relationships between the object of interest and its locally dense contexts in a Bayesian framework, which models the statistical correlation between the simple low-level features (i.e., image intensity and position) from the target and its surrounding regions. The tracking problem is then posed by computing a confidence map which takes into account the prior information of the target location and thereby alleviates target location ambiguity effectively. We further propose a novel explicit scale adaptation scheme, which is able to deal with target scale variations efficiently and effectively. The Fast Fourier Transform (FFT) is adopted for fast learning and detection in this work, which only needs 4 FFT operations. Implemented in MATLAB without code optimization, the proposed tracker runs at 350 frames per second on an i7 machine. Extensive experimental results show that the proposed algorithm performs favorably against state-of-the-art methods in terms of efficiency, accuracy and robustness.
URI: http://hdl.handle.net/10397/35485
ISBN: 3319106023 (pt.5 : electronic bk.)
9783319106021 (pt.5 : electronic bk.)
ISSN: 0302-9743 (print)
1611-3349 (online)
DOI: 10.1007/978-3-319-10602-1_9
Appears in Collections:Book Chapter

Access
View full-text via PolyU eLinks SFX Query
Show full item record

SCOPUSTM   
Citations

98
Last Week
0
Last month
Citations as of May 20, 2017

Page view(s)

47
Last Week
1
Last month
Checked on Jun 18, 2017

Google ScholarTM

Check

Altmetric



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