Linearization to Nonlinear Learning for Visual Tracking

被引:59
作者
Ma, Bo [1 ]
Hu, Hongwei [1 ]
Shen, Jianbing [1 ]
Zhang, Yuping [1 ]
Porikli, Fatih [2 ,3 ]
机构
[1] Beijing Inst Technol, Sch Comp Sci, Beijing Lab Intelligent Informat Technol, Beijing, Peoples R China
[2] Australian Natl Univ, Res Sch Engn, Canberra, ACT, Australia
[3] NICTA Australia, Sydney, NSW, Australia
来源
2015 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV) | 2015年
关键词
DISCRIMINATIVE DICTIONARY; OBJECT TRACKING; SPARSE;
D O I
10.1109/ICCV.2015.500
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:4400 / 4407
页数:8
相关论文
共 37 条
[1]   K-SVD: An algorithm for designing overcomplete dictionaries for sparse representation [J].
Aharon, Michal ;
Elad, Michael ;
Bruckstein, Alfred .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2006, 54 (11) :4311-4322
[2]  
[Anonymous], 2015, IEEE TPAMI
[3]  
[Anonymous], IEEE VEH TECHN C VTC
[4]  
[Anonymous], 2009, Advances in Neural Information Processing Systems
[5]  
[Anonymous], 2008, 2008 IEEE C COMP VIS, DOI DOI 10.1109/CVPR.2008.4587652
[6]  
[Anonymous], 2008, 2008 IEEE C COMPUTER, DOI DOI 10.1109/CVPR.2008.4587408
[7]  
[Anonymous], 2010, Proceedings of the 27th International Conference on Machine Learning (ICML-10)
[8]  
Bao CL, 2012, PROC CVPR IEEE, P1830, DOI 10.1109/CVPR.2012.6247881
[9]   Object Detection with Discriminatively Trained Part-Based Models [J].
Felzenszwalb, Pedro F. ;
Girshick, Ross B. ;
McAllester, David ;
Ramanan, Deva .
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2010, 32 (09) :1627-1645
[10]  
Gao J, 2014, LECT NOTES COMPUT SC, V8691, P188, DOI 10.1007/978-3-319-10578-9_13