Robust mean-shift tracker with local saliency feature and spatial pattern preserved metric
Linshan Liu; Suiwu Zheng; Hong Qiao; Min Wang
2013
会议名称2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)
会议录名称Proceedings 2013 International Conference on Mechatronic Sciences, Electric Engineering and Computer (MEC)
会议日期20-22 Dec. 2013
会议地点Shengyang, China
摘要Robust object tracking in crowded and cluttered dynamic scenes is a very difficult task in robotic vision due to complex and changeable environment and similar features between the background and foreground. In this paper, we present an improved mean-shift tracker which uses discriminative localsaliency feature and a new spatial pattern preserved similarity metric method to overcome above difficulties in mean-shift based tracking approaches. The local saliency feature, which is composed of contrast color, texture and gradient around the target, is proposed to find the most distinguished features between the target and background, and it could enhance the tracking performance greatly in the cluttered and complex environment. Another important benefit of this feature is that the saliencymap form could be easily embedded into the mean-shift framework. The new similarity metric try to preserve the spatial pattern to reduce the similarity errors caused by different spatial structure. It is beneficial to the mean-shift tracker to face the targets and scenes which has identical texture and colorfeature and with different spatial patterns. Finally, the efficiency of the proposed improved mean-shifttracker is validated through the plenty experimental results and analysis.
关键词None
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/12870
专题复杂系统管理与控制国家重点实验室_机器人理论与应用
通讯作者Linshan Liu
推荐引用方式
GB/T 7714
Linshan Liu,Suiwu Zheng,Hong Qiao,et al. Robust mean-shift tracker with local saliency feature and spatial pattern preserved metric[C],2013.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Linshan Liu]的文章
[Suiwu Zheng]的文章
[Hong Qiao]的文章
百度学术
百度学术中相似的文章
[Linshan Liu]的文章
[Suiwu Zheng]的文章
[Hong Qiao]的文章
必应学术
必应学术中相似的文章
[Linshan Liu]的文章
[Suiwu Zheng]的文章
[Hong Qiao]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。