TY - GEN
T1 - Linearization to nonlinear learning for visual tracking
AU - Ma, Bo
AU - Hu, Hongwei
AU - Shen, Jianbing
AU - Zhang, Yuping
AU - Porikli, Fatih
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/2/17
Y1 - 2015/2/17
N2 - Due to unavoidable appearance variations caused by occlusion, deformation, and other factors, classifiers for visual tracking are nonlinear as a necessity. Building on the theory of globally linear approximations to nonlinear functions, we introduce an elegant method that jointly learns a nonlinear classifier and a visual dictionary for tracking objects in a semi-supervised sparse coding fashion. This establishes an obvious distinction from conventional sparse coding based discriminative tracking algorithms that usually maintain two-stage learning strategies, i.e., learning a dictionary in an unsupervised way then followed by training a classifier. However, the treating dictionary learning and classifier training as separate stages may not produce both descriptive and discriminative models for objects. By contrast, our method is capable of constructing a dictionary that not only fully reflects the intrinsic manifold structure of the data, but also possesses discriminative power. This paper presents an optimization method to obtain such an optimal dictionary, associated sparse coding, and a classifier in an iterative process. Our experiments on a benchmark show our tracker attains outstanding performance compared with the state-of-the-art algorithms.
AB - Due to unavoidable appearance variations caused by occlusion, deformation, and other factors, classifiers for visual tracking are nonlinear as a necessity. Building on the theory of globally linear approximations to nonlinear functions, we introduce an elegant method that jointly learns a nonlinear classifier and a visual dictionary for tracking objects in a semi-supervised sparse coding fashion. This establishes an obvious distinction from conventional sparse coding based discriminative tracking algorithms that usually maintain two-stage learning strategies, i.e., learning a dictionary in an unsupervised way then followed by training a classifier. However, the treating dictionary learning and classifier training as separate stages may not produce both descriptive and discriminative models for objects. By contrast, our method is capable of constructing a dictionary that not only fully reflects the intrinsic manifold structure of the data, but also possesses discriminative power. This paper presents an optimization method to obtain such an optimal dictionary, associated sparse coding, and a classifier in an iterative process. Our experiments on a benchmark show our tracker attains outstanding performance compared with the state-of-the-art algorithms.
UR - http://www.scopus.com/inward/record.url?scp=84973867129&partnerID=8YFLogxK
U2 - 10.1109/ICCV.2015.500
DO - 10.1109/ICCV.2015.500
M3 - Conference contribution
T3 - Proceedings of the IEEE International Conference on Computer Vision
SP - 4400
EP - 4407
BT - 2015 International Conference on Computer Vision, ICCV 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 15th IEEE International Conference on Computer Vision, ICCV 2015
Y2 - 11 December 2015 through 18 December 2015
ER -