Adaptive remote-sensing image fusion based on dynamic gradient sparse and average gradient difference

Abstract

ABSTRACTA new method for remote-sensing image fusion based on variational methods and the image objective evaluation model is proposed. Different from the previous methods, the proposed method does not make big improvement on the variational model but focuses on how to make the calculation of existing method more accurate. The problem is that in the solving process of some variational models, it cannot be determined by the information of input images to gain the accurate calculation results. To solve this problem, a new model based on the average gradient of the objective evaluation index is proposed. The measured value of the proposed model is used in the iterations of the fusion algorithm as a feedback to adaptively adjust the algorithm to improve the quality of the fused results. Experiments show that the proposed adaptive method significantly improves the spatial information and well preserves the spectral information in the view of the subjective and objective evaluations.