Non-linear weighted multiband fusion image algorithm

Abstract

In the process of image fusion, the spectral resolution of the sensor makes the information of image fusion be easy to lose, and so affects the quality of the image. Traditional image fusion algorithm has large amount of calculation and poor real-time performance, and does not carefully consider the influence of fusion rules of low-frequency component and the neighborhood characteristics of high-frequency component on the fusion at the same time, so it cannot get the ideal fusion effect. In order to solve the above problems, this paper proposed the nonlinear weighted multiband fusion algorithm which introduced the nonlinear weighted value. The simulation result shows that the calculated amount of the improved image fusion algorithm is significantly reduced, and the real-time performance is also increased significantly. Compared with the traditional Laplacian pyramid fusion algorithm, the precision of the image fusion is also improved effectively.