Fusion of visible and infrared images using multiobjective evolutionary algorithm based on decomposition

Integration of images from different sensing modalities can produce information that cannot be obtained by viewing the sensor outputs separately and consecutively. In order to enhance the contrast of the fused image and reduce the loss of fine details in the process of image fusion, an innovative fusion method of visible and infrared images is presented in this paper, which uses a multiobjective evolutionary algorithm based decomposition (MOEA/D). First of all, we employ contrast pyramid (CP) decomposition into every level of each original image. Second, MOEA/D is introduced to optimize fusion coefficients, thus the weighted coefficients can be adjusted automatically according to fitness function. Finally, obtain the fused images by the weight integration of the optimal fusion coefficients and CP reconstruction. Experimental results show that the fusion algorithm proposed in this paper achieves better effect than the other fusion algorithms both in visual effect and quantitative metrics, and the fused images are more suitable for human visual or machine perception. (C) 2015 Published by Elsevier B.V.