Back to Search Start Over

Multi-layer features template update object tracking algorithm based on SiamFC++.

Authors :
Lu, Xiaofeng
Wang, Xuan
Wang, Zhengyang
Hei, Xinhong
Source :
EURASIP Journal on Image & Video Processing. 1/4/2024, Vol. 2024 Issue 1, p1-17. 17p.
Publication Year :
2024

Abstract

SiamFC++ only extracts the object feature of the first frame as a tracking template, and only uses the highest level feature maps in both the classification branch and the regression branch, so that the respective characteristics of the two branches are not fully utilized. In view of this, the present paper proposes an object tracking algorithm based on SiamFC++. The algorithm uses the multi-layer features of the Siamese network to update template. First, FPN is used to extract feature maps from different layers of Backbone for classification branch and regression branch. Second, 3D convolution is used to update the tracking template of the object tracking algorithm. Next, a template update judgment condition is proposed based on mutual information. Finally, AlexNet is used as the backbone and GOT-10K as training set. Compared with SiamFC++, our algorithm obtains improved results on OTB100, VOT2016, VOT2018 and GOT-10k data sets, and the tracking process is real time. [ABSTRACT FROM AUTHOR]

Details

Language :
English
ISSN :
16875176
Volume :
2024
Issue :
1
Database :
Academic Search Index
Journal :
EURASIP Journal on Image & Video Processing
Publication Type :
Academic Journal
Accession number :
174601671
Full Text :
https://doi.org/10.1186/s13640-023-00616-x