A visual tracking method based on improved online multiple instance learning
He, Xianhui1,2; Wei, Yuxing1
2016
发表期刊Proceedings of SPIE: 8th International Symposium on Advanced Optical Manufacturing and Testing Technology: Optical Test, Measurement Technology, and Equipment
ISSN0277-786X
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)
DOI10.1117/12.2243218
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
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[He, Xianhui]的文章
[Wei, Yuxing]的文章
百度学术
百度学术中相似的文章
[He, Xianhui]的文章
[Wei, Yuxing]的文章
必应学术
必应学术中相似的文章
[He, Xianhui]的文章
[Wei, Yuxing]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。