Access the full text.
Sign up today, get DeepDyve free for 14 days.
S Avidan (2004)
Support vector trackingIEEE Trans. Pattern Anal. Mach. Intell., 26
M Black (1998)
EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based RepresentationInt. J. Comput. Vision, 26
A Yilmaz, O Javed, M Shah (2006)
Object Tracking: A surveyACM Comput. Surv., 38
W Liu, P Pokharel, J Principe (2007)
Correntropy: Properties and applications in Non-Gaussian signal processingIEEE Trans. Signal Process., 55
B Babenko, M Yang, S Belongie (2011)
Visual tracking with online multiple instance learningIEEE Trans. Pattern Anal. Mach. Intell., 33
D Ross, J Lim, R Lin, M Yang (2008)
Incremental learning for robust visual trackingInt. J. Comput. Vis., 77
M Arulampalam, S Maskell, N Gordon, T Clapp (2002)
A tutorial on particle filters for online nonlinear/non-gaussian bayesian trackingIEEE Trans. Signal Process., 50
H Ran, S Zheng, H Gang (2011)
Maximum correntropy criterion for robust face recognitionIEEE Trans. Pattern Anal. Mach. Intell., 33
A Adam, E Rivlin, I Shimshoni (2006)
Proceedings of the International Conference on Computer Vision and Pattern Recognition
J Wright, AY Yang, A Ganesh, SS Sastry, Y Ma (2009)
Roubust face recognition via sparse representationIEEE Trans. Pattern Anal. Mach. Intell., 31
D Comaniciu, V Member, P Meer (2003)
Kernel-based object trackingIEEE Trans. Pattern Anal. Mach. Intell., 25
R Collins, Y Liu, M Leordeanu (2004)
Online selection of discriminative tracking featuresIEEE Trans. Pattern Anal. Mach. Intell., 27
D Wang, H Lu, M Yang (2013)
Online object tracking with sparse prototypesIEEE Trans. Image Process., 22
X Mei, H Ling (2011)
Robust visual tracking and vehicle classification via sparse representationIEEE Trans. Pattern Anal. Mach. Intell., 33
This paper presents a novel online object tracking algorithm with sparse representation for learning effective appearance models under a particle filtering framework. Compared with the state-of-the-art ℓ 1 sparse tracker, which simply assumes that the image pixels are corrupted by independent Gaussian noise, our proposed method is based on information theoretical Learning and is much less sensitive to corruptions; it achieves this by assigning small weights to occluded pixels and outliers. The most appealing aspect of this approach is that it can yield robust estimations without using the trivial templates adopted by the previous sparse tracker. By using a weighted linear least squares with non-negativity constraints at each iteration, a sparse representation of the target candidate is learned; to further improve the tracking performance, target templates are dynamically updated to capture appearance changes. In our template update mechanism, the similarity between the templates and the target candidates is measured by the earth movers’ distance(EMD). Using the largest open benchmark for visual tracking, we empirically compare two ensemble methods constructed from six state-of-the-art trackers, against the individual trackers. The proposed tracking algorithm runs in real-time, and using challenging sequences performs favorably in terms of efficiency, accuracy and robustness against state-of-the-art algorithms.
Annals of Mathematics and Artificial Intelligence – Springer Journals
Published: Mar 23, 2017
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.