A visual tracking method based on improved online multiple instance learning

doi:10.1117/12.2243218

	A visual tracking method based on improved online multiple instance learning
	He, Xianhui 1,2; Wei, Yuxing 1
	2016
发表期刊	Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment
ISSN	0277-786X
卷号	9684 页码:968433
文章类型	C
摘要	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.
关键词	Computer Vision Efficiency Learning Systems Manufacture Optical Testing Tracking (Position)
DOI	10.1117/12.2243218
收录类别	Ei
语种	英语
项目资助者	Chinese Academy of Sciences, Institute of Optics and Electronics (IOE) ; The Chinese Optical Society (COS)
WOS记录号	WOS:000387429500111
引用统计
文献类型	期刊论文
条目标识符	http://ir.ioe.ac.cn/handle/181551/8517
专题	光电探测与信号处理研究室（五室）
作者单位	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
推荐引用方式 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.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
2016-2149.pdf（1198KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	请求全文