Super-Resolution Image Reconstruction

The SRIR Technology is a practical, robust, low computation overhead algorithm to obtain high resolution (HR) images from low resolution (LR), under-sampled digital imaging equipment. This US Army patented algorithm increases the resolution of the reconstructed output image using the existing imaging device from a sequence of low resolution, under sampled, imagery. By removing aliasing due to under-sampling, SRIR can also improve range performance of the sensor. Background and Technology Super-Resolution Image Reconstruction exploits the subpixel movement of an image sequence. When LR images have subpixel shifts between successive frames, they convey different information about the same scene. SRIR takes advantage of this distinct information and fuses the information from the LR frames during reconstruction to generate a high quality HR image of the true scene. Benefits Few Frames: 4 frames for 2X liner (4X pixel) resolution improvement, low computational overhead, fast processing, realistic mimicking of fast moving targets Uses subpixel movement of unknown nature: Easy to implement, examples include natural jitter from a moving platform and expansion and contraction of blood vessels Versatile: Tested by inventor on video, forward looking IR, and flash LADAR; many other applications possible including mobile phones, medical imaging, remote sensing target recognition, biometric recognition, and industrial inspection Multiple implementation options: Currently written in MatLab; can be built into FPGAs and FFT chips, or distributed as a stand alone or C shared library Status and Opportunity Available for license and commercialization - except for the field of Law Enforcement. One issued patent (7,602,997) and one published US patent application (2010/0067822) Peer-reviewed journal articles available Potential for Research & Development collaboration with the inventor