Title
Learning correlation filters in independent feature channels for robust visual tracking
Abstract
•Three infects of most existing correlation filter-based tracking algorithms are investigated.•Specific correlation filters are learned for independent feature channels.•The final response map is generated according to the confidence of independent feature channels.•Adaptive learning rates varying with the interframe variance of independent feature channels are exploited.•In addition to the accuracy of our approach, the real-time performance is excellent running at 70 FPS.
Year
DOI
Venue
2019
10.1016/j.patrec.2018.09.009
Pattern Recognition Letters
Keywords
Field
DocType
Visual tracking,Correlation filter,Multiple feature channels
Computer vision,BitTorrent tracker,Correlation filter,Feature vector,Pattern recognition,Communication channel,Eye tracking,Correlation,Artificial intelligence,Mathematics
Journal
Volume
ISSN
Citations 
127
0167-8655
1
PageRank 
References 
Authors
0.35
17
4
Name
Order
Citations
PageRank
Cailing Wang111.03
Yechao Xu210.69
Huajun Liu311.03
Xiao-Yuan Jing476955.18