Learning weighted part models for object tracking

doi:10.1016/j.cviu.2015.10.004

	Learning weighted part models for object tracking
	Zhao, Chaoyang; Wang, Jinqiao; Zhu, Guibo; Wu, Yi; Lu, Hanqing
发表期刊	COMPUTER VISION AND IMAGE UNDERSTANDING
	2016-02-01
卷号	143 页码:173-182
文章类型	Article
摘要	Despite significant improvements have been made for visual tracking in recent years, tracking arbitrary object is still a challenging problem. In this paper, we present a weighted part model tracker that can efficiently handle partial occlusion and appearance change. Firstly, the object appearance is modeled by a mixture of deformable part models with a graph structure. Secondly, through modeling the temporal evolution of each part with a mixture of Gaussian distribution, we present a temporal weighted model to dynamically adjust the importance of each part by measuring the fitness to the historical temporal distributions in the tracking process. Moreover, the temporal weighted models are used to control the sample selections for the update of part models, which makes different parts update differently due to partial occlusion or drastic appearance change. Finally, the weighted part models are solved by structural learning to locate the object. Experimental results show the superiority of the proposed approach. (C) 2016 Elsevier Inc. All rights reserved.
关键词	Part Graph Model Gaussian Mixture Model Weighted Model
WOS标题词	Science & Technology ; Technology
DOI	10.1016/j.cviu.2015.10.004
关键词[WOS]	VISUAL TRACKING ; POSE ESTIMATION ; ONLINE
收录类别	SCI
语种	英语
项目资助者	863 Program(2014AA015104) ; National Natural Science Foundation of China(61273034 ; 61332016)
WOS研究方向	Computer Science ; Engineering
WOS类目	Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号	WOS:000369776200014
引用统计	被引频次：6[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/173211/11072
专题	紫东太初大模型研究中心_图像与视频分析
作者单位	Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing, Peoples R China
第一作者单位	模式识别国家重点实验室
推荐引用方式 GB/T 7714	Zhao, Chaoyang,Wang, Jinqiao,Zhu, Guibo,et al. Learning weighted part models for object tracking[J]. COMPUTER VISION AND IMAGE UNDERSTANDING,2016,143:173-182.
APA	Zhao, Chaoyang,Wang, Jinqiao,Zhu, Guibo,Wu, Yi,&Lu, Hanqing.(2016).Learning weighted part models for object tracking.COMPUTER VISION AND IMAGE UNDERSTANDING,143,173-182.
MLA	Zhao, Chaoyang,et al."Learning weighted part models for object tracking".COMPUTER VISION AND IMAGE UNDERSTANDING 143(2016):173-182.

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
parttracker-revised.（1213KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载