中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 计算技术研究所
  3. 中国科学院计算技术研究所
  4. 中国科学院计算技术研究所期刊论文
  5. 英文
Beyond appearance model: Learning appearance variations for object tracking

文献类型：期刊论文

作者Li, Guorong1,2,3; Ma, Bingpeng1,2,3; Huang, Jun1; Huang, Qingming1,2,3; Zhang, Weigang4
刊名NEUROCOMPUTING
出版日期2016-11-19
卷号214页码:796-804
关键词Object tracking Appearance model Appearance prediction
ISSN号0925-2312
DOI10.1016/j.neucom.2016.06.058
英文摘要In this paper, we present a novel appearance variation prediction model which can be embedded into the existing generative appearance model based tracking framework. Different from the existing works, which online learn appearance model with obtained tracking results, we propose to predict appearance reconstruction error. We notice that although the learned appearance model can precisely describe the target in the previous frames, the tracking result is still not accurate if in the following frame, the patch that is most similar to appearance model is assumed to be the target. We first investigate the above phenomenon by conducting experiments on two public sequences and discover that in most cases the best target is not the one with minimal reconstruction error. Then we design three kinds of features which can encode motion, appearance, appearance reconstruction error information of target's surrounding image patches, and capture potential factors that may cause variations of target's appearance as well as its reconstruction error. Finally, with these features, we learn an effective random forest for predicting reconstruction error of the target during tracking. Experiments on various datasets demonstrate that the proposed method can be combined with many existing trackers and improve their performances significantly. (C) 2016 Elsevier B.V. All rights reserved.
资助项目National Basic Research Program of China (973 Program)[2012CB316400] ; National Basic Research Program of China (973 Program)[2015CB351802] ; National Natural Science Foundation of China[61303153] ; National Natural Science Foundation of China[61332016] ; National Natural Science Foundation of China[61572465]
WOS研究方向Computer Science
语种英语
WOS记录号WOS:000386741300075
出版者ELSEVIER SCIENCE BV
源URL[http://119.78.100.204/handle/2XEOYT63/7799]  
专题中国科学院计算技术研究所期刊论文_英文
通讯作者Ma, Bingpeng
作者单位1.Univ Chinese Acad Sci, Sch Comp & Control Engn, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100080, Peoples R China
3.Chinese Acad Sci, Key Lab Big Data Min & Knowledge Management, Beijing, Peoples R China
4.Harbin Inst Technol, Sch Comp Sci & Technol, Harbin, Peoples R China
推荐引用方式
GB/T 7714		 Li, Guorong,Ma, Bingpeng,Huang, Jun,et al. Beyond appearance model: Learning appearance variations for object tracking[J]. NEUROCOMPUTING,2016,214:796-804.
APA Li, Guorong,Ma, Bingpeng,Huang, Jun,Huang, Qingming,&Zhang, Weigang.(2016).Beyond appearance model: Learning appearance variations for object tracking.NEUROCOMPUTING,214,796-804.
MLA Li, Guorong,et al."Beyond appearance model: Learning appearance variations for object tracking".NEUROCOMPUTING 214(2016):796-804.

入库方式： OAI收割

来源：计算技术研究所

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。