Target tracking algorithm based on extreme learning machine and multiple kernel boosting learning

被引：1
作者：
Zhang D. [1 ]
Sun R. [1 ]
Gao J. [1 ]
机构：
[1] School of Computer and Information, Hefei University of Technology, Hefei
来源：
Xi Tong Gong Cheng Yu Dian Zi Ji Shu/Systems Engineering and Electronics | 2017年 / 39卷 / 09期
关键词：
Boosting learning; Extreme learning machine (ELM); Multiple kernel learning; Target tracking;
D O I：
10.3969/j.issn.1001-506X.2017.09.33
中图分类号：
学科分类号：
摘要：
How to construct a robust classifier is always a hot research spot in target tracking based on discriminant. In recent years, multiple kernel learning combining multiple classifier to achieve better classification performance has attract wide attention. Traditional multiple kernel learning cannot be directly used in target tracking because it has a very complicated optimal question. A multiple kernel learning is proposed which is based on boosting framework. It assures target tracking can keep efficient and accurate in complicated scenes. In order to decrease the computation and increase the classify performance, extreme learning machine (ELM) is used as the base classifier. ELM has a very simple structure and rapid training speed. Compared to support vector machine, ELM has a better generalization ability. Finally, the proposed algorithm is compared with other state-of-art tracking algorithms in some challenge videos to verify the effectiveness of the proposed algorithm. © 2017, Editorial Office of Systems Engineering and Electronics. All right reserved.
引用
收藏
页码：2149 / 2156
页数：7
相关论文
共 28 条
[21]  
Kasun L.L.C., Zhou H., Huang G.B., Representational learning with extreme learning machine for big data, IEEE Intelligent Systems, 28, 6, pp. 31-34, (2013)
[22]  
Vanli N.D., Sayint N.O., Sequential nonlinear learning for distributed multiagent systems via extreme learning machines, IEEE Trans. on Neural Networks and Learning Systems, 28, 3, pp. 1-13, (2016)
[23]  
Huang G.B., Zhou H., Ding X., Extreme learning machine for regression and multiclass classification, IEEE Trans. on Systems, 42, 2, pp. 513-529, (2012)
[24]  
Huang G.B., Chen L., Siew C.K., Universal approximation using incremental constructive feed forward networks with random hidden nodes, IEEE Trans. on Neural Networks, 17, 4, pp. 879-892, (2006)
[25]  
Huang G.B., Song S., Semi-supervised and unsupervised extreme learning machines, IEEE Trans. on Cybernetics, 44, 12, pp. 2405-2417, (2014)
[26]  
Liang N.Y., Huang G.B., A fast and accurate online sequential learning algorithm for feed forward networks, IEEE Trans. on Neural Networks, 17, 6, pp. 1411-1423, (2006)
[27]  
Amit A., Rivlin E., Robust fragments-based tracking using the integral histogram, Proc. of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2597-2605, (2006)
[28]  
Zhang K.H., Zhang L., Fast compressive tracking, IEEE Trans. on Pattern Analysis and Machine Intelligence, 36, 10, pp. 2002-2015, (2014)
123