Wavelet-Transformation Based Unscented Kalman Filter and Its Application

It is well known that the successful application of UKF depends on whether the prior knowledge of the statistics of the measurement noise is known.In this paper,the UKF algorithm is first analyzed briefly.The feature of wavelet transformation of separating a noise signal into signal part and noise part in real time is combined into UKF.A new method is then proposed that makes the UKF under unknown measurement noise covariance condition valid.This presented method can track the changes of the measurement noise covariance in real time.Finally,the applications of the proposed method for information fusion are discussed.The simulation results verify the effectiveness of the proposed method.