OKSI and Northwestern University propose to develop a super-resolution (SR) methodology for mid-wave infrared (MWIR) imagery that produces extreme enhancement of low resolution images. Image enhancement of at least 4x is expected using a standard imaging system. OKSI and Northwestern University will also develop a detector-limited imaging system specifically designed to be used with the SR methodology for which even higher levels of image enhancement can be attained. The newly developed SR methodology will directly address the Navys desire for variable resolution MWIR imagery achieved through post-processing, as well as the imaging needs of other government agencies. During Phase-I, OKSI and Northwestern University will demonstrate a proof-of-concept for the SR methodology and quantify the image enhancement that is attained. In Phase-II, OKSI and Northwestern University will build and demonstrate a prototype imaging system with near real-time post-processing for small image segments.
Benefit: If successful, the Navy and other customer will be provided with a dramatic improvement in the super-resolution image enhancement that can be achieved for MWIR imagery. This will enable the Navy to increase deployed capability while reducing or maintain SWaP-C for MWIR imagers. Other customers will benefit from improved MWIR data products.
Keywords: Regularization, Regularization, Image Enhancement, super-resolution, MWIR, implicit prior, Machine Learning