BP neural Network-Kalman filter fusion method for unmanned aerial vehicle target tracking

Liu, Yongqi; Nie, Liangcheng; Dong, Rui; Chen, Gang

doi:10.1177/0954406220983864

Cited by 6 publications

(3 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Back-propagation neural network (BPNN) has excellent performance and is most widely used in automatic classification tasks [16]. Therefore, in this paper, BPNN is chosen as a classifier for automatic classification of multiinstrument.…”

Section: Automatic Classification Methods Based On Neural Networkmentioning

confidence: 99%

Research on Neural Network-based Automatic Music Multi-Instrument Classification Approach

Guo

2024

IJACSA

View full text Add to dashboard Cite

The automatic classification of multi-instruments plays a crucial role in providing services for music retrieval and recommendation. This paper focuses on automatic multiinstrument classification. Firstly, instrument features were analyzed, and Mel-frequency cepstral coefficient (MFCC) and perceptual linear predictive coefficient (PLPC) were extracted from instrument signals. Features were selected using the entropy weight method. The optimal initial weight threshold of a back-propagation neural network (BPNN) was obtained by utilizing the sparrow search algorithm (SSA), achieving a SSA-BPNN classifier. Experiments were conducted using the IRMAS dataset. The results demonstrated that the combination of MFCC and PLPC selected through the entropy weight method achieved the best performance in automatic multi-instrument classification. The method yielded high P value, recall rate, and F1 value, 0.72, 0.71, and 0.71, respectively. Moreover, it outperformed other algorithms such as support vector machine and XGBoost. These results confirm the reliability of the automatic multi-instrument classification method proposed in this paper, making it suitable for practical applications.

show abstract

Section: Automatic Classification Methods Based On Neural Networkmentioning

confidence: 99%

Research on Neural Network-based Automatic Music Multi-Instrument Classification Approach

Guo

2024

IJACSA

View full text Add to dashboard Cite

show abstract

“…There have been some results of research on combining Kalman filter methods with other new techniques. For example, in the literature [16], a back propagation neural network based fusion Kalman filtering algorithm is proposed for the real-time position prediction of UAV target tracking, which has higher accuracy and robustness in predicting the target centre position coordinates, and the UAV can stably track the moving targets on the ground. Then, for example, in the literature [17], a high-precision UAV positioning system that integrates an inertial measurement unit and ultra-wideband (UWB) with an adaptive extended Kalman filter (EKF) is proposed to solve the problem of unpredictable propagation conditions and time-varying operating environments, where oscillations in positioning performance caused by changes in measurement noise may lead to instability of the UAV.…”

Section: Introductionmentioning

confidence: 99%

Development of Steady Aiming System Based on Kalman Filter and Coordinate Transformation

Lu¹,

Liang

Tang

et al. 2023

IEEE Access

View full text Add to dashboard Cite

The aiming accuracy of the Unmanned Aerial Vehicles (UAV) Steadicam head can be affected by many factors, such as the state of the UAV during the actual flight and the installation error of the system related hardware. In order to eliminate the influence of objective factors on the UAV Steadicam, a Kalman filter aiming algorithm based on the coordinate transformation method is proposed to eliminate the attitude error of the UAV Steadicam and improve the accuracy of the system. The algorithm uses coordinate transformation to eliminate mounting errors and combines coordinate transformation and Kalman filtering methods to eliminate objective errors of the UAV in flight. The experimental simulation results show that our method can accurately give the amount of azimuth and pitch angle error compensation during the flight of the UAV, improving the accuracy of the UAV Steadicam head. Ultimately, the method is applied to the development of a real product.INDEX TERMS Attitude error, coordinate transformation, error compensation, Kalman filtering, Steadicam head.

show abstract

“…The quadrotors are single rigid bodies when considering their dynamics which provides a good platform for applying various linear control methods including, LQR, 22 LQG, 23 proportional-integral-derivative (PID) control, 24 and PID control based on LQR/LQG. 25 Recently, much attention has been paid to the use of nonlinear control methods for the flight control of quadrotors such as feedback linearization, 26 neural network, 27,28 fuzzy logic, 29 sliding mode, 30 and back-stepping controller. 31 Sometimes in the inspection of power lines, in order to detect suspicious activity accurately, the quadrotor needs to hover or fly at low altitude in some critical areas.…”

Section: Introductionmentioning

confidence: 99%

RBFNN and projection operator based robust adaptive control with input saturation of a quadrotor equipped with two manipulators constrained to a high voltage line

Dehghani

Mohammadi

2022

Proceedings of the Institution of Mechanical Engineers, Part C:

View full text Add to dashboard Cite

The aim of this paper is to propose a robust adaptive control for a quadrotor equipped with two manipulators constrained along a high voltage line (HVL). Due to the urgent need of the HVL to inspect, the quadrotor compared to humans has many advantages such as cost and less time, higher accuracy, access to impassable points, and most importantly, reducing human victims. In this paper, two manipulators are used to hang the quadrotor from the HVL and move along it such that the quadrotor can perform monitoring operations more accurately. The motion equations are derived for the constrained quadrotor by the Lagrangian method. A control law is derived based on inverse dynamics of reduced-form equations. A robust adaptive controller is proposed for control of the constrained quadrotor in the presence of dynamic uncertainties and external disturbances. The nonlinear terms in the dynamic model are approximated by radial basis function neural network (RBFNN) and adaptive laws based on the projection operator. Moreover, saturation functions are considered for inputs in the controller by an auxiliary system. Stability analysis of the closed-loop system is performed by the Lyapunov theory. In order to confirm the effectiveness of the proposed method, some numerical simulations are carried out. The simulation results show the quadrotor can move along the HVL in the presence of the dynamic model uncertainties and the external disturbances and satisfy the considered constraints.

show abstract

BP neural Network-Kalman filter fusion method for unmanned aerial vehicle target tracking

Cited by 6 publications

References 18 publications

Research on Neural Network-based Automatic Music Multi-Instrument Classification Approach

Research on Neural Network-based Automatic Music Multi-Instrument Classification Approach

Development of Steady Aiming System Based on Kalman Filter and Coordinate Transformation

RBFNN and projection operator based robust adaptive control with input saturation of a quadrotor equipped with two manipulators constrained to a high voltage line

Contact Info

Product

Resources

About