Multiframe selective information fusion from robust error estimation theory.

Abstract

A dynamic procedure for selective information fusion from multiple image frames is derived from robust error estimation theory. The fusion rate is driven by the anisotropic gain function, defined to be the difference between the Gaussian smoothed-edge maps of a given input frame and of an evolving synthetic output frame. The gain function achieves both selection and rapid fusion of relatively sharper features from each input frame compared to the synthetic frame. Effective applications are demonstrated for image sharpening in imaging through atmospheric turbulence, for multispectral fusion of the RGB spectral components of a scene, for removal of blurred visual obstructions from in front of a distant focused scene, and for high-resolution two-dimensional display of three-dimensional objects in microscopy.