IOE OpenIR  > 光电探测与信号处理研究室(五室)
A visual tracking method based on improved online multiple instance learning
He, Xianhui1,2; Wei, Yuxing1
2016
Source PublicationProceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment
ISSN0277-786X
Volume9684Pages:968433
SubtypeC
AbstractVisual tracking is an active research topic in the field of computer vision and has been well studied in the last decades. The method based on multiple instance learning (MIL) was recently introduced into the tracking task, which can solve the problem that template drift well. However, MIL method has relatively poor performance in running efficiency and accuracy, due to its strong classifiers updating strategy is complicated, and the speed of the classifiers update is not always same with the change of the targets' appearance. In this paper, we present a novel online effective MIL (EMIL) tracker. A new update strategy for strong classifier was proposed to improve the running efficiency of MIL method. In addition, to improve the t racking accuracy and stability of the MIL method, a new dynamic mechanism for learning rate renewal of the classifier and variable search window were proposed. Experimental results show that our method performs good performance under the complex scenes, with strong stability and high efficiency. © 2016 SPIE.
KeywordComputer Vision Efficiency Learning Systems Manufacture Optical Testing Tracking (Position)
DOI10.1117/12.2243218
Indexed ByEi
Language英语
Funding OrganizationChinese Academy of Sciences, Institute of Optics and Electronics (IOE) ; The Chinese Optical Society (COS)
WOS IDWOS:000387429500111
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ioe.ac.cn/handle/181551/8517
Collection光电探测与信号处理研究室(五室)
Affiliation1. Institute of Optics and Electronics, Chinese Academy of Sciences, Chengdu
2.610209, China
3. University of Chinese Academy of Sciences, Beijing
4.100039, China
Recommended Citation
GB/T 7714
He, Xianhui,Wei, Yuxing. A visual tracking method based on improved online multiple instance learning[J]. Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment,2016,9684:968433.
APA He, Xianhui,&Wei, Yuxing.(2016).A visual tracking method based on improved online multiple instance learning.Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment,9684,968433.
MLA He, Xianhui,et al."A visual tracking method based on improved online multiple instance learning".Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment 9684(2016):968433.
Files in This Item:
File Name/Size DocType Version Access License
2016-2149.pdf(1198KB)期刊论文作者接受稿开放获取CC BY-NC-SAApplication Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[He, Xianhui]'s Articles
[Wei, Yuxing]'s Articles
Baidu academic
Similar articles in Baidu academic
[He, Xianhui]'s Articles
[Wei, Yuxing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[He, Xianhui]'s Articles
[Wei, Yuxing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.