Have a personal or library account? Click to login
Long-term Target Tracking Based on Template Updating and Redetection Cover
By: Shuping Xu and  Yinglong Li  
Open Access
|Dec 2024

Figures & Tables

Figure 1.

Block diagram of long-term target tracking algorithm
Block diagram of long-term target tracking algorithm

Figure 2.

Template updater based on state judgment
Template updater based on state judgment

Figure 3.

Confidence score chart
Confidence score chart

Figure 4.

SiamRPN tracking results
SiamRPN tracking results

Figure 5.

Flow chart of target loss judgment mechanism
Flow chart of target loss judgment mechanism

Figure 6.

Template-based re-detection algorithm
Template-based re-detection algorithm

Figure 7.

Different ts corresponding success rates and accuracy
Different ts corresponding success rates and accuracy

Figure 8.

Results of parameter optimization
Results of parameter optimization

Figure 9.

Diagram of LaSOT experimental results
Diagram of LaSOT experimental results

Figure 10.

Results of qualitative analysis of bird1 video sequence
Results of qualitative analysis of bird1 video sequence

Figure 11.

yamaha video sequence qualitative analysis results
yamaha video sequence qualitative analysis results

Figure 12.

Ablation experiment results
Ablation experiment results

Experimental Results on VOT2018_LT

AlgorithmF-valueAccuracyFrame rateRecall rate
SiamFC0.4290.628840.323
MBMD0.6130.63640.576
DASiamRPN_LT0.6040.625630.585
SPLT0.6140.629260.602
SiamRPN++0.6250.646350.606
Ours0.6440.659280.626

Introduction of 2 groups of video sequences

Video SourcesNameNumber of framesType of challenge
VOT2018_LTYamaha3143Out of sight, occlusion, deformation
VOT2018_LTbird12437Analogue interference, out of view, blocking
Language: English
Page range: 35 - 47
Published on: Dec 31, 2024
Published by: Xi’an Technological University
In partnership with: Paradigm Publishing Services
Publication frequency: 4 issues per year

© 2024 Shuping Xu, Yinglong Li, published by Xi’an Technological University
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.