Journals
Advanced Photonics
Photonics Insights
Advanced Photonics Nexus
Photonics Research
Advanced Imaging
View All Journals
Chinese Optics Letters
High Power Laser Science and Engineering
Articles
Optics
Physics
Geography
View All Subjects
Conferences
CIOP
HPLSE
AP
View All Events
News
About CLP
Search by keywords or author
Login
Registration
Login in
Registration
Search
Search
Articles
Journals
News
Advanced Search
Top Searches
laser
the
2D Materials
Transformation optics
Quantum Photonics
Journals >
Acta Optica Sinica >
Volume 41 >
Issue 6 >
Page 0615002 > Article
Acta Optica Sinica
Vol. 41, Issue 6, 0615002 (2021)
Global-Aware Siamese Network for Thermal Infrared Object Tracking
Chang Li, Dedong Yang
*
, Peng Song, and Chang Guo
Author Affiliations
School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, China
show less
DOI:
10.3788/AOS202141.0615002
Cite this Article
Set citation alerts
Chang Li, Dedong Yang, Peng Song, Chang Guo. Global-Aware Siamese Network for Thermal Infrared Object Tracking[J]. Acta Optica Sinica, 2021, 41(6): 0615002
Copy Citation Text
EndNote(RIS)
BibTex
Plain Text
show less
Fig. 1.
Global-aware object tracking framework
Download full size
Fig. 2.
Visualization of feature fusion
Download full size
Fig. 3.
Architecture of proposed global-aware network model
Download full size
Fig. 4.
Encoding-decoding module in self-attention mechanism
Download full size
Fig. 5.
Overall accuracy and success rate of different algorithms. (a) Precision; (b) success rate
Download full size
Fig. 6.
Precision of different attributes videos on PTB-TIR dataset. (a) Deformation; (b) occlusion; (c) scale variation; (d) background clutter; (e) low resolution; (f) fast motion; (g) motion blur; (h) out of view; (i) thermal crossover
Download full size
Fig. 7.
Success rates of different attributes videos on PTB-TIR dataset. (a) Deformation; (b) occlusion; (c) scale variation; (d) background clutter; (e) low resolution; (f) fast motion; (g) motion blur; (h) out of view; (i) thermal crossover
Download full size
Fig. 8.
Actual tracking results of six algorithms. (a) Airplane; (b) campus; (c) conversation; (d) road; (e) meetion; (f) crowd
Download full size
Tracker
PTB-TIR
Pre↑
Suc↑
CFNet
0.623
0.444
CFNet+GA
0.682
0.493
CFNet+ST
0.709
0.519
CFNet+GA+ST(proposed)
0.735
0.530
Table 1.
Comparison of results of ablation experiments on PTB-TIR dataset
Category
Tracker
PTB-TIR
Speed /
(frame·s
-1
)
Pre↑
Suc↑
Hand-crafted Feature based CF
DSST
0.708
0.526
45.4
KCF
0.588
0.394
301.3
Deep feature based CF
MCFTS
0.685
0.488
4.8
Other deep tracker
CREST
0.706
0.520
0.7
SiamFC
0.617
0.475
66.7
CFNet
0.623
0.444
37.0
SiamFC-tri
0.601
0.454
60.0
Matching based deep tracker
UDT
0.694
0.525
82.8
HSSNet
0.684
0.464
18.0
MLSSNet
0.727
0.512
19.8
Proposed
0.735
0.530
20.2
Table 2.
Comparison of experimental results of 11 trackers on PTB-TIR dataset
Abstract
Get PDF(in Chinese)
Figures&Tables (10)
Equations (0)
References (31)
Cited By (7)
Get Citation
Copy Citation Text
Chang Li, Dedong Yang, Peng Song, Chang Guo. Global-Aware Siamese Network for Thermal Infrared Object Tracking[J]. Acta Optica Sinica, 2021, 41(6): 0615002
Download Citation
EndNote(RIS)
BibTex
Plain Text
Set citation alerts for the article
Tools
Share
Set citation alerts for the article
Save the article for my favorites
Paper Information
Category: Machine Vision
Received: Sep. 8, 2020
Accepted: Nov. 11, 2020
Published Online: Mar. 23, 2021
The Author Email: Yang Dedong (ydd12677@163.com)
DOI:
10.3788/AOS202141.0615002
Recommended Topics
laser devices and laser physics
Lasers and Laser Optics
Laser physics
laser manufacturing
Instrumentation, Measurement and Metrology
Set citation alerts for the article
Please enter your email address
Cancel
Confirm