Abstract: Aiming to fusion question on the infrared and visible images, a novel effective image fusion method was proposed in this paper. Firstly, the high frequency coefficient after multiscale decomposition was divided into low and high layers, and then, according to the characteristics of each layer, the high frequency coefficient of the fused image was obtained by method based on pixel and method based on feature weighted respectively. Secondly, in order to further enhance the overall contrast of the fused image, and the capabilities of target indication, the low frequency coefficient of the fused image was obtained by adaptive weighted method based on regional average gradient. Finally, the fused image was obtained by inverse multi-scale transformation. The subjective observation and the comparison of the image's objective indexes prove together that the method proposed in this paper is better than the classical methods.