Application of optimized Kalman filtering in target tracking based on improved Gray Wolf algorithm

Area of Science:

• Control Systems Engineering
• Signal Processing
• Optimization Algorithms

Background:

• High precision is critical in target tracking applications.
• Traditional Gray Wolf Optimization (GWO) suffers from slow convergence.
• GWO performance is sensitive to wolf population and iteration count.

Purpose of the Study:

• To improve target tracking prediction accuracy.
• To develop an optimized Kalman filter (OKF) using an enhanced GWO.
• To address the limitations of traditional GWO for optimization tasks.

Main Methods:

• Proposed an improved Gray Wolf Optimization (IGWO) algorithm with a nonlinear control parameter adjustment strategy.
• Optimized Kalman filter's process noise covariance and observation noise covariance matrices using IGWO.
• Applied the IGWO-OKF approach to target tracking scenarios.

Main Results:

• The IGWO algorithm demonstrated faster convergence compared to traditional GWO.
• The IGWO-OKF approach achieved low prediction error.
• Experimental results confirmed high accuracy and effective prediction capabilities.

Conclusions:

• The proposed IGWO-OKF approach significantly enhances target tracking precision.
• The IGWO algorithm offers an effective optimization method for Kalman filter parameters.
• This method provides a robust solution for improving prediction accuracy in target tracking.