SIA OpenIR  > 光电信息技术研究室
基于背景约束与卷积特征的目标跟踪方法
Alternative TitleAn object tracking method based on background constraints and convolutional features. Computer Engineering and Applications
王思奎1,2,3,4; 刘云鹏1,2,4; 亓琳1,2,4; 张钟毓1,2,3,4; 林智远1,2,3,4
Department光电信息技术研究室
Source Publication计算机工程与应用
ISSN1002-8331
2019
Pages1-14
Contribution Rank1
Funding Organization中国科学院国防科技创新重点基金(No.Y8K4160401)
Keyword目标跟踪 多特征融合 背景约束 记忆滤波器 卷积特征
Abstract针对目标跟踪中因背景混叠和遮挡等因素导致的目标丢失问题,提出了一种基于背景约束与卷积特征的目标跟踪方法(TBCCF)。首先,对输入图像进行多特征融合并降维,增强目标特征判别性能的同时降低特征计算的复杂度;其次,在滤波器训练过程中引入背景约束,使得滤波器更专注于目标响应,以提升抗干扰能力;最后,通过设置记忆滤波器与峰值旁瓣比检测,判断目标是否丢失。若丢失,引入卷积特征滤波器进行重检测,实现目标的重捕获。在Visual Tracking Benchmark数据集50个复杂场景视频序列上的实验结果表明,所提算法总体精度和总体成功率优于现有的多数跟踪算法。
Other AbstractAn object tracking method, which is based on background constraints and convolutional features(TBCCF), is proposed to solve the target loss problem caused by background aliasing and occlusion in object tracking. Firstly, the feature of input image is fused and dimensionally reduced to enhance the performance of target feature discrimination and reduce the complexity of feature computation. Secondly, background constraints are introduced into the filter training process, which makes the filter more focused on the target response to improve the anti-jamming ability. Finally, by setting memory filter and the Peak to Sidelobe Ratio detection, the tracker can judge whether the target is missing or not. If the target is lost, a convolutional features filter is introduced to re-detect the target. The experimental results of 50 complex scene video sequences on Visual Tracking Benchmark datasets show that the proposed algorithm has better overall accuracy and overall success rate than most existing tracking algorithms.
Language中文
Document Type期刊论文
Identifierhttp://ir.sia.cn/handle/173321/24932
Collection光电信息技术研究室
Corresponding Author王思奎
Affiliation1.中国科学院沈阳自动化研究所
2.中国科学院机器人与智能制造创新研究院
3.中国科学院大学
4.中国科学院光电信息处理重点实验室
Recommended Citation
GB/T 7714
王思奎,刘云鹏,亓琳,等. 基于背景约束与卷积特征的目标跟踪方法[J]. 计算机工程与应用,2019:1-14.
APA 王思奎,刘云鹏,亓琳,张钟毓,&林智远.(2019).基于背景约束与卷积特征的目标跟踪方法.计算机工程与应用,1-14.
MLA 王思奎,et al."基于背景约束与卷积特征的目标跟踪方法".计算机工程与应用 (2019):1-14.
Files in This Item:
File Name/Size DocType Version Access License
基于背景约束与卷积特征的目标跟踪方法.p(1265KB)期刊论文出版稿开放获取CC BY-NC-SAView Application Full Text
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[王思奎]'s Articles
[刘云鹏]'s Articles
[亓琳]'s Articles
Baidu academic
Similar articles in Baidu academic
[王思奎]'s Articles
[刘云鹏]'s Articles
[亓琳]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[王思奎]'s Articles
[刘云鹏]'s Articles
[亓琳]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: 基于背景约束与卷积特征的目标跟踪方法.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.