Paper Info
Title
A Unified Online Dictionary Learning Framework with Label Information for Robust Object Tracking
Abstract
In this paper, a supervised approach to online learn a structured sparse and discriminative representation for object tracking is presented. Label information from training data is incorporated into the dictionary learning process to construct a robust and discriminative dictionary. This is accomplished by adding an ideal-code regularization term and classification error term to the unified objective function. By minimizing the unified objective function we learn the high quality dictionary and optimal linear multi-classifier jointly. Combined with robust sparse coding, the learned classifier is employed directly to separate the object from background. As the tracking continues, the proposed algorithm alternates between robust sparse coding and dictionary updating. Experimental evaluations on the challenging sequences show that the proposed algorithm performs favorably against state-of-the-art methods in terms of effectiveness, accuracy and robustness.
Year
DOI
Venue
2014
10.1109/ICPR.2014.401
ICPR
Keywords
DocType
ISSN
optimal linear multiclassifier,robust object tracking,label information, the unified objective function for online dictionary learning, optimal linear multi-classifier,structured sparse,learning (artificial intelligence),label information,optimal linear multi-classifier,dictionaries,unified online dictionary learning framework,the unified objective function for online dictionary learning,discriminative representation,image classification,object tracking,discriminative dictionary,high quality dictionary,supervised approach,ideal-code regularization term
Conference
1051-4651
Citations 
PageRank 
References 
0
0.34
0
Authors
4
Name
Order
Citations
PageRank
Baojie Fan14110.48
Jing Sun2323.10
Yang Cong368438.22
Yingkui Du4177.23