An Improved Real Time Compressive Tracking
文献类型:会议论文
作者 | Xu, Rui; Gu, Xiaodong; Wei, Benjie |
出版日期 | 2013 |
会议名称 | 2nd IAPR Asian Conference on Pattern Recognition (ACPR) |
会议日期 | NOV 05-08, 2013 |
会议地点 | Naha, JAPAN |
关键词 | Object tracking sample bags sparse matrix online learning |
页码 | 692-696 |
通讯作者 | Xu, R (reprint author), Chinese Acad Sci, Natl Space Sci Ctr, Beijing, Peoples R China. |
英文摘要 | Recently, an algorithm called compressive tracking is utilized to cope with real time tracking, which use a very sparse measurement matrix to compress samples of targets and background, and then a classifier is trained to distinguish foreground and background. However, compressive tracking extracts foreground features that are limited to the current frame and does not consider the samples of previous frames in its learning procedure. This paper presents a novel enhanced compressive tracking, which extracts two kinds of samples of targets: current samples and previous samples. Our method use targets information from the previous and current frames to train a novel classifier which composes of two weighted classifiers based on different sample bags. Experimental results demonstrate the effectiveness and robustness of our method. |
收录类别 | EI ; CPCI |
会议主办者 | Int Assoc Pattern Recognit, IEEE, IEEE Comp Soc, KDDI Fdn, Support Ctr Adv Telecommunicat Technol Res, Pattern Recognit & Media Understanding, IEICE ISS, Comp Vis & Image Media, IPSJ, IEEE Comp Soc Fukuoka Chapter |
会议录 | 2013 SECOND IAPR ASIAN CONFERENCE ON PATTERN RECOGNITION (ACPR 2013)
![]() |
会议录出版者 | IEEE COMPUTER SOC |
语种 | 英语 |
ISBN号 | 978-1-4799-2190-4 |
源URL | [http://ir.nssc.ac.cn/handle/122/4732] ![]() |
专题 | 国家空间科学中心_空间技术部 |
推荐引用方式 GB/T 7714 | Xu, Rui,Gu, Xiaodong,Wei, Benjie. An Improved Real Time Compressive Tracking[C]. 见:2nd IAPR Asian Conference on Pattern Recognition (ACPR). Naha, JAPAN. NOV 05-08, 2013. |
入库方式: OAI收割
来源:国家空间科学中心
浏览0
下载0
收藏0
其他版本
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。