Online multiple instance gradient feature selection for robust visual tracking

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Online multiple instance gradient feature selection for robust visual tracking
	Xie, Yuan2 ; Qu, Yanyun 1; Li, Cuihua 1; Zhang, Wensheng2
发表期刊	PATTERN RECOGNITION LETTERS
	2012-07-01
卷号	33 期号:9 页码:1075-1082
文章类型	Article
摘要	In this paper, we focus on learning an adaptive appearance model robustly and effectively for object tracking. There are two important factors to affect object tracking, the one is how to represent the object using a discriminative appearance model, the other is how to update appearance model in an appropriate manner. In this paper, following the state-of-the-art tracking techniques which treat object tracking as a binary classification problem, we firstly employ a new gradient-based Histogram of Oriented Gradient (HOG) feature selection mechanism under Multiple Instance Learning (MIL) framework for constructing target appearance model, and then propose a novel optimization scheme to update such appearance model robustly. This is an unified framework that not only provides an efficient way of selecting the discriminative feature set which forms a powerful appearance model, but also updates appearance model in online MIL Boost manner which could achieve robust tracking overcoming the drifting problem. Experiments on several challenging video sequences demonstrate the effectiveness and robustness of our proposal. (C) 2012 Elsevier B.V. All rights reserved.
关键词	Gradient-based Feature Selection Hog Multiple Instance Learning Online Object Tracking
WOS标题词	Science & Technology ; Technology
收录类别	SCI
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000304235500007
引用统计	被引频次：11[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/8007
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
作者单位	1.Xiamen Univ, Dept Comp Sci, Video & Image Lab, Xiamen 361005, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Intelligent Control & Management Co, Beijing 100190, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Xie, Yuan,Qu, Yanyun,Li, Cuihua,et al. Online multiple instance gradient feature selection for robust visual tracking[J]. PATTERN RECOGNITION LETTERS,2012,33(9):1075-1082.
APA	Xie, Yuan,Qu, Yanyun,Li, Cuihua,&Zhang, Wensheng.(2012).Online multiple instance gradient feature selection for robust visual tracking.PATTERN RECOGNITION LETTERS,33(9),1075-1082.
MLA	Xie, Yuan,et al."Online multiple instance gradient feature selection for robust visual tracking".PATTERN RECOGNITION LETTERS 33.9(2012):1075-1082.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Online multiple inst（1199KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载