Fuzzy integral is an effective decision level fusion method for target recognition.The core problem in using fuzzy integral is to determine the fuzzy densities which can reflect the importance of the sensors.Presently

the main methods of determining fuzzy densities include using confusion matrix or genetic algorithm.These methods only use the a priori static information of the training samples to determine the fuzzy densities.A new method of determining fuzzy densities adaptively is presented in this paper

which uses the a priori static information of the training samples and the dynamic information contained in each sensor's decision.The simulation experiment shows that better fusion result can be obtained by using this method.