Real time prediction method of urban dynamic traffic data flow based on Kalman filter

The urban dynamic traffic data flow has a certain randomness and fast change speed, which leads to the problem of high data flow extraction error in the existing methods. This paper proposes a real-time prediction method of urban dynamic traffic data flow based on Kalman filter. The feature vector of urban dynamic traffic data flow is obtained by Lyapunov exponent method, and the vector is placed in a fixed area to complete the extraction. The urban dynamic traffic data flow is regarded as an unstable whole and transformed into data series, and the grey correlation degree is used to determine the correlation degree in the data flow, The process equation and observation equation of Kalman filtering algorithm are constructed to determine the optimal estimation value and modify the optimal estimation value to complete the real-time prediction. The results show that the prediction accuracy of this method is about 97%.