Robust Object Tracking by Nonlinear Learning
Date
2018-10
Authors
Ma, Bo
Hu, Hongwei
Shen, Jianbing
Zhang, Yuping
Shao, Ling
Porikli, Fatih
Journal Title
Journal ISSN
Volume Title
Publisher
Institute of Electrical and Electronics Engineers
Abstract
We propose a method that obtains a discriminative visual dictionary and a nonlinear classifier for visual tracking tasks in a sparse coding manner based on the globally linear approximation for a nonlinear learning theory. Traditional discriminative tracking methods based on sparse representation learn a dictionary in an unsupervised way and then train a classifier, which may not generate both descriptive and discriminative models for targets by treating dictionary learning and classifier learning separately. In contrast, the proposed tracking approach can construct a dictionary that fully reflects the intrinsic manifold structure of visual data and introduces more discriminative ability in a unified learning framework. Finally, an iterative optimization approach, which computes the optimal dictionary, the associated sparse coding, and a classifier, is introduced. Experiments on two benchmarks show that our tracker achieves a better performance compared with some popular tracking algorithms.
Description
Keywords
global linear approximation, local coordinate coding (LCC), nonlinear learning, object tracking
Citation
Collections
Source
IEEE Transactions on Neural Networks and Learning Systems
Type
Journal article
Book Title
Entity type
Access Statement
Open Access
License Rights
Restricted until
Downloads
File
Description