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

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 prese...

Full description

Saved in:
Bibliographic Details
Published in:EURASIP journal on image and video processing Vol. 2024; no. 1; pp. 1 - 17
Main Authors: Lu, Xiaofeng, Wang, Xuan, Wang, Zhengyang, Hei, Xinhong
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 01.12.2024
Springer Nature B.V
SpringerOpen
Subjects:
Algorithms
Artificial Intelligence Based Techniques for Next Generation Image and Video Compression
Artificial neural networks
Biometrics
Classification
Engineering
Feature extraction
Feature maps
FPN
Fully convolutional Siamese networks
Image Processing and Computer Vision
Multilayers
Mutual information
Object tracking
Pattern Recognition
Signal,Image and Speech Processing
Template update
Tracking
Fully convolutional Siamese networks
Object tracking
FPN
Template update
Mutual information
ISSN:1687-5281, 1687-5176, 1687-5281
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1687-5281
1687-5176
1687-5281
DOI:10.1186/s13640-023-00616-x