The track fusion is an important aspect in the multi-sensor data fusion.Because of the public noise,the track estimate errors from the different sensors are not independent in the state estimate fusion system.So the fusion problem becomes complex.This article researched the simple fusion,adaptive track fusion and weighted covariance fusion.The comparison of data fusion methods shows that adaptive track fusion and weighted covariance fusion is effective to multi-sensor data fusion.The simulation indicates that the algorithm has preferable fusion result.