.png){kind=icon}
返回
Discriminative local collaborative representation for online object tracking
.png){kind=icon}
PRE
AI
DOI：10.1016/j.knosys.2016.01.041.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Sparse representation has been widely applied to object tracking. However, most sparse representation based trackers only use the holistic template to encode the candidates, where the discriminative information to separate the target from the background is ignored. In addition, the sparsity assumption with the l(1) norm minimization is computationally expensive. In this paper, we propose a robust discriminative local collaborative (DLC) representation algorithm for online object tracking. DLC collaboratively uses the local image patches of both the target templates and the background ones to encode the candidates by an efficient local regularized least square solver with the l(2) norm minimization, where the feature vectors are obtained by employing an effective discriminative-pooling method. Furthermore, we formulate the tracking as a discriminative classification problem, where the classifier is online updated by using the candidates predicted according to the residuals of their local patches. To adapt to the appearance changes, we iteratively update the dictionary with the foreground and background templates from the current frame and take occlusions into account as well. Experimental results demonstrate that our proposed algorithm performs favorably against the state-of-the-art trackers on several challenging video sequences. (C) 2016 Elsevier B.V. All rights reserved.
Keyword:
Object tracking
Online learning
Collaborative representation
Local coding
Discriminative tracking
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
K
IF:
7.6
论文数:
1.3W
被引数:
4.5W
.png){kind=icon}
查看更多内容