In order to improve the performance and reliability of automatic target recognition system, an intelligent target recognition method based on the data fusion of radar and infrared sensor is proposed. For infrared sensor, the image target recognition algorithm based on wavelet moment and BP neural network is proposed; for radar sensor, the target recognition method based on fuzzy reasoning is proposed. Finally, Dempster-Shafer theory is used to combine the two basic probability assignment functions and achieve the data fusion of radar and infrared sensor. Simulation experiments indicate that the recognition results by data fusion of two sensors is better than that by single sensor.