Improved Image Processing for Low Resolution Imagery with Inter-Frame Pose Variation

With respect to digital imaging sensors and systems, obtaining as many pixels on target is a necessity to classify or identify a target for real-time operations and forensic analysis within the intelligence community. Rather than relying on improved sensors, the approach originally solicited and further refined here utilizes super-resolution image processing techniques to provide more detail in the imagery for the existing pixels on target by increasing the image resolution or amount of information contained within the output as compared to the input. Etegent’s past project development coupled with the work performed on the phase I effort for this topic demonstrate that Etegent and partners can provide the necessary skills, knowledge, and capabilities to produce a set tools capable of super-resolving low-resolution imagery to provide a significant resolution improvement over the input imagery. Under this proposed effort, Etegent will continue to work with our transition partner to develop a software library of super-resolution tools and processing components that integrate into an existing image processing framework or toolkit. Etegent’s experience and related work in image processing combined with IST’s expertise in image registration, atmospheric turbulence deblurring, and image enhancement provide a team that can deliver a robust super-resolution library.