A combined wavelet analysis-fuzzy adaptive algorithm for radar/infrared data fusion

This paper presents a new algorithm that combines a fuzzy adaptive fusion and wavelet analysis to form an efficient data fusion technique for the target tracking system. The fuzzy adaptive fusion algorithm is a powerful tool to make the actual value of the residual covariance consistent with its theoretical value. To overcome the defect of the dependence on the knowledge of the process and measurement noise statistics of extended Kalman filter (EKF), wavelet analysis is introduced, which needs no prior knowledge of the process and measurement noise. And fuzzy inference system is applied for its simplicity of the approach and its capability of processing imprecise information. In addition, the paper highlights the use of a new wavelet-based thresholding method to enhance the computational ability of wavelet coefficients. The simulation experiments on the novel adaptive fusion algorithm have been performed. The experimental results show that the proposed algorithm can effectively strengthen the system robustness and improve the tracking precision. It is obvious that the algorithm has significant advantages over the traditional EKF algorithm in tracking application via comparison of data.