An adaptive Kalman filter for manoeuvring targets tracking is developed The approach is based on adding a scale factor to the process noise, therefore the noise level can be adapted depend on the manoeuvres of the tracking targets. At each epoch a time-average of the sum of the diagonal elements of the covariance matrix for the innovation is computed and compared with the value from dynamic and observable models, if the difference is lager than a predetermined threshold, the scale factor will be set to update the level of the process noise. Some computer simulations are carried out to compare the performance of the adaptive algorithm and the conventional Kalman filter..
