The highly maneuverable target tracking problem of UAVs (Unmanned Aerial Vehicles) involves target detecting and flight control in image sequences. For the problems such as loss of target when the direction of the target rapidly changes, we propose a new tracking algorithm based on the fusion of position and attitude with UKF(Unscented Kalman Filter). The projection of the target position and attitude under the pixel coordinate system of the camera is calculated as the control input. A UKF controller is designed to predict the target state in the next frame to ensure that the target is close to the center of sight for effective tracking of the target. The effectiveness of the system is verified on a hardware-in-the-loop simulation platform. Video at the link: https://youtu.be/T5pr6LwQbs8.
UAV Maneuvering Target Tracking with Position-Attitude Fusion
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2022 ; Xi'an, China September 23, 2022 - September 25, 2022
Proceedings of 2022 International Conference on Autonomous Unmanned Systems (ICAUS 2022) ; Kapitel : 103 ; 1139-1148
2023-03-10
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Maneuvering target tracking with colored noise
IEEE | 1996
|Maneuvering Target Tracking with Hypothesis Testing
IEEE | 1987
|Maneuvering Target Tracking with Colored Noise
Online Contents | 1996
|Visual Tracking of a Maneuvering Target
AIAA | 2006
|