A visual tracking method based on improved online multiple instance learning | |
He, Xianhui1,2; Wei, Yuxing1 | |
Source Publication | Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment
![]() |
Volume | 9684Pages:968433 |
2016 | |
Language | 英语 |
ISSN | 0277-786X |
DOI | 10.1117/12.2243218 |
Indexed By | Ei |
WOS ID | WOS:000387429500111 |
Subtype | C |
Abstract | Visual 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. |
Keyword | Computer Vision Efficiency Learning Systems Manufacture Optical Testing Tracking (Position) |
Citation statistics | |
Document Type | 期刊论文 |
Identifier | http://ir.ioe.ac.cn/handle/181551/8517 |
Collection | 光电探测与信号处理研究室(五室) |
Affiliation | 1. 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-SA | View Application Full Text |
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment