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. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 人工智能与机器学习
Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking

文献类型：期刊论文

作者Yang, Yehui1; Xie, Yuan1; Zhang, Wensheng1; Hu, Wenrui1; Tan, Yuanhua2
刊名NEUROCOMPUTING
出版日期2015-07-21
卷号160页码:191-205
关键词Visual tracking Sparse representation Dictionary learning Coupled learning Consistency ensuring
英文摘要This paper presents a robust tracking algorithm by sparsely representing the object at both global and local levels. Accordingly, the algorithm is constructed by two complementary parts: Global Coupled Learning (GCL) part and Local Consistencies Ensuring (LCE) part. The global part is a discriminative model which aims to utilize the holistic features of the object via an over-complete global dictionary and classifier, and the dictionary and classifier are coupled learning to construct an adaptive GCL part. While in LCE part, we explore the object's local features by sparsely coding the object patches via a local dictionary, then both temporal and spatial consistencies of the local patches are ensured to refine the tracking results. Moreover, the GCL and LCE parts are integrated into a Bayesian framework for constructing the final tracker. Experiments on fifteen benchmark challenging sequences demonstrate that the proposed algorithm has more effectiveness and robustness than the alternative ten state-of-the-art trackers. (C) 2015 Elsevier B.V. All rights reserved.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence
研究领域[WOS]Computer Science
关键词[WOS]ROBUST VISUAL TRACKING ; APPEARANCE MODEL ; OBJECT TRACKING ; REPRESENTATION ; REGRESSION
收录类别SCI
语种英语
WOS记录号WOS:000354139100017
公开日期2015-09-22
源URL[http://ir.ia.ac.cn/handle/173211/8073]  
专题精密感知与控制研究中心_人工智能与机器学习
作者单位1.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
2.Karamay Hongyou Software CO LTD, Karamay 834000, Peoples R China
推荐引用方式
GB/T 7714		 Yang, Yehui,Xie, Yuan,Zhang, Wensheng,et al. Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking[J]. NEUROCOMPUTING,2015,160:191-205.
APA Yang, Yehui,Xie, Yuan,Zhang, Wensheng,Hu, Wenrui,&Tan, Yuanhua.(2015).Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking.NEUROCOMPUTING,160,191-205.
MLA Yang, Yehui,et al."Global Coupled Learning and Local Consistencies Ensuring for sparse-based tracking".NEUROCOMPUTING 160(2015):191-205.

入库方式： OAI收割

来源：自动化研究所

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。