Total variation regularization-based adaptive pixel level image fusion

In this paper a total variation (TV) regularization-based approach is proposed for pixel level fusion to fuse images acquired using multiple sensors. In this approach, fusion is posed as an inverse problem and a locally affine model is used as the forward model. A total variation regularization in conjunction with an adaptive estimation of forward model parameters is used iteratively to estimate the fused image. The feasibility of the proposed algorithm is demonstrated on images from visible-band and infrared as well as computed tomography (CT) and magnetic resonance imaging (MRI) sensors. The results clearly indicate the feasibility of the proposed approach.