Fusing Multiple Multiband Images

TL;DR

This paper introduces a novel fusion algorithm for multiple multiband images that leverages maximum-likelihood estimation, regularization, and efficient computation to improve fusion quality over existing methods.

Contribution

It develops a new maximum-likelihood based fusion method with regularization and efficient optimization for arbitrary numbers of multiband images.

Findings

Outperforms state-of-the-art algorithms in experiments

Handles more than two images effectively

Utilizes regularization for improved robustness

Abstract

We consider the problem of fusing an arbitrary number of multiband, i.e., panchromatic, multispectral, or hyperspectral, images belonging to the same scene. We use the well-known forward observation and linear mixture models with Gaussian perturbations to formulate the maximum-likelihood estimator of the endmember abundance matrix of the fused image. We calculate the Fisher information matrix for this estimator and examine the conditions for the uniqueness of the estimator. We use a vector total-variation penalty term together with nonnegativity and sum-to-one constraints on the endmember abundances to regularize the derived maximum-likelihood estimation problem. The regularization facilitates exploiting the prior knowledge that natural images are mostly composed of piecewise smooth regions with limited abrupt changes, i.e., edges, as well as coping with potential ill-posedness of the fusion problem. We solve the resultant convex optimization problem using the alternating direction method of multipliers. We utilize the circular convolution theorem in conjunction with the fast Fourier transform to alleviate the computational complexity of the proposed algorithm. Experiments with multiband images constructed from real hyperspectral datasets reveal the superior performance of the proposed algorithm in comparison with the state-of-the-art algorithms, which need to be used in tandem to fuse more than two multiband images.