The main challenge in object tracking is how to track a target in real time and accurately in complex and changing environments. Correlation filters (CFs) have unique advantages in the field of target tracking and are widely used in unmanned aerial vehicle (UAV) platforms. We propose a new tracking algorithm that introduces adaptive background residuals to reduce the environmental interference during tracking. Experimental results on two benchmark datasets show that our tracking algorithm achieves first place in accuracy and success rate compared to nine other state-of-the-art tracking algorithms. Our tracker has excellent tracking performance.
Adaptive Background Residual Correlation Filters for UAV Tracking
Lect. Notes Electrical Eng.
International Conference on Artificial Intelligence and Autonomous Transportation ; 2024 ; Beijing, China December 06, 2024 - December 08, 2024
The Proceedings of 2024 International Conference on Artificial Intelligence and Autonomous Transportation ; Kapitel : 6 ; 60-68
19.04.2025
9 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Adaptive correlation filters for pattern recognition
British Library Online Contents | 2006
|Adaptive Control using Residual Mode Filters Applied to Wind Turbines
British Library Conference Proceedings | 2011
|Adaptive Gaussian Sum Filters for Space Surveillance Tracking
Online Contents | 2012
|