# US 2018/0005361 A1 · Super-resolution systems and methods > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0005361 A1 - Document ID: US20180005361A1 - Status: Published application - Kind: A1 - Application number: 15/638,772 - Filed: 2017-06-30 - Published: 2018-01-04 - Earliest claimed: 2016-07-01 - Assignees: Analytical Mechanics Associates, Inc. - Applicants: Analytical Mechanics Associates, Inc. - Inventors: Alexander Bulyshev - Web page: https://patentgrep.com/patent/US20180005361A1 ## CPC - G06T 5/50: using two or more images, e.g. averaging or subtraction - G06T 3/4053: based on super-resolution, i.e. the output image resolution being higher than the sensor resolution - G06T 12/20: Inverse problem, i.e. transformations from projection space into object space - G06T 2207/10048: Infrared image - G06T 2207/10116: X-ray image - G06T 2207/20056: Discrete and fast Fourier transform, [DFT, FFT] - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Exemplary super-resolution methods and systems may generate, or create, a super-resolution based on a plurality of low-resolution images. Such exemplary methods and systems may utilize image registration and back-projection to provide intermediate imaging data, and then use inverse problem solving to remove any back-projection effects as well as noise to generate a super-resolution image. ## Claims ### Claim 1 A method for generating a super-resolution image of an object of interest comprising: providing an initial low-resolution image of an object of interest; projecting the initial low-resolution image into a high-resolution grid, wherein the high-resolution grid defines a higher resolution than the initial low-resolution image; providing a plurality of low-resolution images of the object of interest obtained from a plurality of different positions relative to the object of interest; registering the plurality of low-resolution images within the high-resolution grid such that each image of the plurality of images is shifted less than one pixel away from the initial low-resolution image; projecting the plurality of low-resolution images into the high-resolution grid to provide an intermediate super-resolution image; and removing back-projection effects from the intermediate super-resolution image using inverse problem solving to provide a super-resolution image of the object of interest. ### Claim 2 (depends on 1) The method of claim 1, wherein removing back-projection effects from the intermediate super-resolution image to provide an improved image the object of interest comprises using an inverse transform. ### Claim 3 (depends on 1) The method of claim 1, wherein removing back-projection effects from the intermediate super-resolution image to provide an improved image the object of interest comprises using a function representative of the back-projection effects. ### Claim 4 (depends on 3) The method of claim 3, wherein the function representative of the back-projection effects is a triangular-shaped point spread function. ### Claim 5 (depends on 1) The method of claim 1, wherein the higher resolution image defines a resolution that is greater than 10 larger than the initial low-resolution image. ### Claim 6 (depends on 1) The method of claim 1, wherein registering the plurality of low-resolution images within the high-resolution grid comprises determining a state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid. ### Claim 7 (depends on 6) The method of claim 6, wherein determining a state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid comprises determine the state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid based on an image intensity density function. ### Claim 8 (depends on 6) The method of claim 6, wherein projecting the plurality of low-resolution images into the high-resolution grid comprises positioning the plurality of low-resolution images into the high-resolution grid based on an image intensity density function. ### Claim 9 (depends on 1) The method of claim 1, wherein the method further comprises or the computing apparatus is further configured to execute normalizing each pixel of the high-resolution grid. ### Claim 10 (depends on 9) The method of claim 9, wherein each pixel of the high-resolution grid comprises: a cumulative intensity value representative of the cumulative intensity of the plurality of low-resolution images projected on the pixel of the high-resolution grid; and a counter value representative of the number of times the plurality of low-resolution images projected on the pixel of the high-resolution grid, wherein normalizing each pixel of the high-resolution grid comprises dividing the cumulative intensity value by the counter value for each pixel of the high-resolution grid. ### Claim 11 (depends on 1) The method of claim 1, wherein removing back-projection effects from the intermediate super-resolution image using inverse problem solving further comprising applying an image stabilization function to remove at least some noise. ### Claim 12 (depends on 1) The method of claim 1, wherein the initial low-resolution image and the plurality of low-resolution images of the object of interest comprises one of infrared images, visual images, ultraviolet images, and X-ray images. ### Claim 13 A system for generating a super-resolution image of an object of interest comprising: imaging apparatus comprising one or more imaging sensors to capture low-resolution images of an object of interest; and computing apparatus comprising one or more processors, wherein the computing apparatus is configured to: receive a plurality of low-resolution images of the object of interest obtained from a plurality of different positions relative to the object of interest from the imaging apparatus; project an initial low-resolution image the plurality of low-resolution images into a high-resolution grid, wherein the high-resolution grid defines a higher resolution than the initial low-resolution image, register the remainder of the plurality of low-resolution images within the high-resolution grid such that each image of the plurality of images is shifted less than one pixel away from the initial low-resolution image, project the remainder of the plurality of low-resolution images into the high-resolution grid to provide an intermediate super-resolution image, and remove back-projection effects from the intermediate super-resolution image using inverse problem solving to provide a super-resolution image of the object of interest. ### Claim 14 (depends on 13) The system of claim 13, wherein removing back-projection effects from the intermediate super-resolution image to provide an improved image the object of interest comprises using an inverse transform. ### Claim 15 (depends on 13) The system of claim 13, wherein removing back-projection effects from the intermediate super-resolution image to provide an improved image the object of interest comprises using a function representative of the back-projection effects. ### Claim 16 (depends on 15) The system of claim 15, wherein the function representative of the back-projection effects is a triangular-shaped point spread function. ### Claim 17 (depends on 13) The system of claim 13, wherein the higher resolution image defines a resolution that is greater than 10 larger than the initial low-resolution image. ### Claim 18 (depends on 13) The system of claim 13, wherein registering the plurality of low-resolution images within the high-resolution grid comprises determining a state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid. ### Claim 19 (depends on 18) The system of claim 18, wherein determining a state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid comprises determine the state vector for each of the plurality of low-resolution images with respect to the projected initial low-resolution image within the high-resolution grid based on an image intensity density function. ### Claim 20 (depends on 18) The system of claim 18, wherein projecting the plurality of low-resolution images into the high-resolution grid comprises positioning the plurality of low-resolution images into the high-resolution grid based on an image intensity density function. ### Claim 21 (depends on 13) The system of claim 13, wherein the method further comprises or the computing apparatus is further configured to execute normalizing each pixel of the high-resolution grid. ### Claim 22 (depends on 21) The system of claim 21, wherein each pixel of the high-resolution grid comprises: a cumulative intensity value representative of the cumulative intensity of the plurality of low-resolution images projected on the pixel of the high-resolution grid; and a counter value representative of the number of times the plurality of low-resolution images projected on the pixel of the high-resolution grid, wherein normalizing each pixel of the high-resolution grid comprises dividing the cumulative intensity value by the counter value for each pixel of the high-resolution grid. ### Claim 23 (depends on 13) The system of claim 13, wherein removing back-projection effects from the intermediate super-resolution image using inverse problem solving further comprising applying an image stabilization function to remove at least some noise. ### Claim 24 (depends on 13) The system of claim 13, wherein the initial low-resolution image and the plurality of low-resolution images of the object of interest comprises one of infrared images, visual images, ultraviolet images, and X-ray images.