OPT OpenIR  > 空间光学技术研究室
A high-speed multi-scale kernel correlation filter tracking algorithm
Fu, Bin1,2; Song, Zongxi1; Wang, Feng1; Gao, Wei1; Zhang, Shuang1; Liu, Jiwei1
2019
会议名称11th International Conference on Digital Image Processing, ICDIP 2019
会议录名称Eleventh International Conference on Digital Image Processing, ICDIP 2019
卷号11179
会议日期2019-05-10
会议地点Guangzhou, China
出版者SPIE
产权排序1
摘要

Recently, Kernel Correlation Filter (KCF) is recognized as one of the best visual tracking algorithms which provide excellent tracking performance and high possessing speed. However, how to adapt to the scale change of target in real time and accurately is still an open problem. In this paper, a multi-scale improved method based on one-dimensional scale correlation filtering is proposed. We use the kernel function to solve the regularized least squares classifier, and the translation filter template is obtained to estimate the target position. Then, we collect a series of samples of different scales at the target position to construct a one-dimensional scale filter template for estimating the most suitable scale. The filter is learned and updated online in the tracking process. In scale estimation, we employed the dimension reduction method to reduce the computational complexity, and the interpolation method is used to increase the number of multi-scale to obtain more accurate scale location. A number of experimental results and data show that the target region overlap rate and tracking rate of the improved algorithm are improved by 9% and 60% on average compared with the best of other scale adaptive tracking algorithms. Compared with the KCF algorithm, the average position tracking error is reduced by 23.9% and the overlap rate is increased by 46%. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词visual tracking kernel correlation filter scale estimation dimension reduction interpolation
作者部门空间光学技术研究室
DOI10.1117/12.2539759
收录类别EI ; CPCI
ISBN号9781510630758
语种英语
ISSN号0277786X;1996756X
WOS记录号WOS:000511106700142
EI入藏号20193907475230
引用统计
文献类型会议论文
条目标识符http://ir.opt.ac.cn/handle/181661/31867
专题空间光学技术研究室
作者单位1.Xi'An Institute of Optics and Precision Mechanics of CAS, Xi'an; 710071, China;
2.University of Chinese Academy of Science, Beijing; 100049, China
推荐引用方式
GB/T 7714
Fu, Bin,Song, Zongxi,Wang, Feng,et al. A high-speed multi-scale kernel correlation filter tracking algorithm[C]:SPIE,2019.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A high-speed multi-s(779KB)会议论文 限制开放CC BY-NC-SA请求全文
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
[Fu, Bin]的文章
[Song, Zongxi]的文章
[Wang, Feng]的文章
百度学术
百度学术中相似的文章
[Fu, Bin]的文章
[Song, Zongxi]的文章
[Wang, Feng]的文章
必应学术
必应学术中相似的文章
[Fu, Bin]的文章
[Song, Zongxi]的文章
[Wang, Feng]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。