摘要
针对传统稀疏表示不能有效区分目标和背景的缺点,提出一种判别稀疏表示算法,这种算法在传统稀疏表示目标函数中加入一个判别函数,大大降低干扰因素对目标跟踪的影响。基于判别稀疏表示和?_1约束,提出一种在线字典学习算法升级目标模板,有效降低背景信息对目标模板的影响。提取目标梯度方向的直方图(HOG)特征,利用其对光照和形变等复杂环境具有较强鲁棒性的优点,实现对目标更稳定的跟踪。实验结果表明,与现有跟踪方法相比,该算法的跟踪效果更好。
Traditional sparse representation can not effectively distinguish between target and background.Aiming atthese problems,a discriminative sparse representation is proposed.It adds a discriminative function to the traditionalsparse,thereby greatly reducing the influence of interference factors.An online dictionary learning algorithm based ondiscrimination sparse representation and?1constraint is proposed to upgrade target template.It can effectively reduce theimpact of the target and the background of the target template.In addition,Histograms of Oriented Gradient(HOG)feature is used to represent the target.The advantage is its robustness to illumination changes.The proposed tracker isempirically compared with state-of-the-art trackers on some challenging video sequences.Both quantitative and qualitativecomparisons show that the proposed tracker is superior and more stable.
作者
吉训生
陈赛
黄越
JI Xunsheng;CHEN Sai;HUANG Yue(School of Internet of Things, Jiangnan University, Wuxi, Jiangsu 214122, China;Department of Internet of Things Technology, Wuxi Institute of Technology, Wuxi, Jiangsu 214121, China)
出处
《计算机工程与应用》
CSCD
北大核心
2017年第3期211-215,共5页
Computer Engineering and Applications
基金
国家自然科学基金(No.61170120)
关键词
稀疏表示
目标跟踪
字典学习
梯度方向直方图
sparse representation
target tracking
dictionary learning
Histograms of Oriented Gradient(HOG)
