Temporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning

doi:10.1109/TCYB.2016.2519532

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Temporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning
	Yang, Yehui; Hu, Wenrui; Xie, Yuan; Zhang, Wensheng; Zhang, Tianzhu; Wensheng Zhang
发表期刊	IEEE TRANSACTIONS ON CYBERNETICS
	2017-02-01
卷号	47 期号:2 页码:485-498
文章类型	Article
摘要	An effective representation model, which aims to mine the most meaningful information in the data, plays an important role in visual tracking. Some recent particle-filter-based trackers achieve promising results by introducing the low-rank assumption into the representation model. However, their assumed low-rank structure of candidates limits the robustness when facing severe challenges such as abrupt motion. To avoid the above limitation, we propose a temporal restricted reverse-low-rank learning algorithm for visual tracking with the following advantages: 1) the reverse-low-rank model jointly represents target and background templates via candidates, which exploits the low-rank structure among consecutive target observations and enforces the temporal consistency of target in a global level; 2) the appearance consistency may be broken when target suffers from sudden changes. To overcome this issue, we propose a local constraint via (l)1,2 mixed-norm, which can not only ensures the local consistency of target appearance, but also tolerates the sudden changes between two adjacent frames; and 3) to alleviate the inference of unreasonable representation values due to outlier candidates, an adaptive weighted scheme is designed to improve the robustness of the tracker. By evaluating on 26 challenge video sequences, the experiments show the effectiveness and favorable performance of the proposed algorithm against 12 state-of-the-art visual trackers.
关键词	Low-rank Sparse Representation Temporal Restriction Visual Tracking
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCYB.2016.2519532
关键词[WOS]	OBJECT TRACKING ; REPRESENTATION
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61402480 ; 61432008 ; 61472423 ; 61502495)
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence ; Computer Science, Cybernetics
WOS记录号	WOS:000395476200019
引用统计	被引频次：24[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/173211/12257
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Wensheng Zhang
作者单位	Chinese Acad Sci, Inst Automat, 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	Yang, Yehui,Hu, Wenrui,Xie, Yuan,et al. Temporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning[J]. IEEE TRANSACTIONS ON CYBERNETICS,2017,47(2):485-498.
APA	Yang, Yehui,Hu, Wenrui,Xie, Yuan,Zhang, Wensheng,Zhang, Tianzhu,&Wensheng Zhang.(2017).Temporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning.IEEE TRANSACTIONS ON CYBERNETICS,47(2),485-498.
MLA	Yang, Yehui,et al."Temporal Restricted Visual Tracking Via Reverse-Low-Rank Sparse Learning".IEEE TRANSACTIONS ON CYBERNETICS 47.2(2017):485-498.

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
07396944.pdf（4881KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载