NAOC Open IR
Correlation filter via random-projection based CNNs features combination for visual tracking
Zhang, Mingke1; Xu, Long2; Xiong, Jing1; Zhang, Xuande1
2021-05-01
Source PublicationJOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION
ISSN1047-3203
Volume77Pages:6
AbstractObject tracking based on the Convolutional Neural Networks (CNNs) with multiple feature correlation filter (CF) has become one of the best object tracking frameworks. In this paper, we propose a novel approach of CNNs based CF, which combines deep features from CNNs into low-dimensional features. To achieve the dimensionality reduction, random-projection is used due to its data-independence and superior computational efficiency over other widely used. In our proposed approach, the spectral graph theory is applied to generate a random projection matrix. This method bypasses the time-consuming Gram-Schmidt orthogonalization, where the dimension of the feature is high. The combined features have very low dimensions, less than one tenth of the dimensions of the original deep features from CNNs, offering an improvement of tracking speed and without loss of performance simultaneously. Extensive experiments are conducted on large-scale benchmark datasets. The results demonstrate that the proposed algorithm outperforms the state-of-the-art methods.
KeywordObject tracking Correlation filter Deep features Random-projection
Funding OrganizationNational Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China
DOI10.1016/j.jvcir.2021.103082
WOS KeywordOBJECT TRACKING
Language英语
Funding ProjectNational Natural Science Foundation of China[61871260]
Funding OrganizationNational Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; National Natural Science Foundation of China
WOS Research AreaComputer Science
WOS SubjectComputer Science, Information Systems ; Computer Science, Software Engineering
WOS IDWOS:000663341400004
PublisherACADEMIC PRESS INC ELSEVIER SCIENCE
Citation statistics
Document Type期刊论文
Identifierhttp://ir.bao.ac.cn/handle/114a11/77479
Collection中国科学院国家天文台
Corresponding AuthorZhang, Xuande
Affiliation1.Shaanxi Univ Sci & Technol, Sch Elect Informat & Artificial Intelligence, Xian 710021, Shaanxi, Peoples R China
2.Chinese Acad Sci, Natl Astron Observ, Key Lab Solar Act, Beijing 100101, Peoples R China
Recommended Citation
GB/T 7714
Zhang, Mingke,Xu, Long,Xiong, Jing,et al. Correlation filter via random-projection based CNNs features combination for visual tracking[J]. JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,2021,77:6.
APA Zhang, Mingke,Xu, Long,Xiong, Jing,&Zhang, Xuande.(2021).Correlation filter via random-projection based CNNs features combination for visual tracking.JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION,77,6.
MLA Zhang, Mingke,et al."Correlation filter via random-projection based CNNs features combination for visual tracking".JOURNAL OF VISUAL COMMUNICATION AND IMAGE REPRESENTATION 77(2021):6.
Files in This Item:
There are no files associated with this item.
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhang, Mingke]'s Articles
[Xu, Long]'s Articles
[Xiong, Jing]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhang, Mingke]'s Articles
[Xu, Long]'s Articles
[Xiong, Jing]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhang, Mingke]'s Articles
[Xu, Long]'s Articles
[Xiong, Jing]'s Articles
Terms of Use
No data!
Social Bookmark/Share
All comments (0)
No comment.
 

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