# US 12,597,109 B2 · Systems and methods for generating three-dimensional models using captured video > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,597,109 B2 - Document ID: US12597109B2 - Status: Granted - Kind: B2 - Application number: 18/470,698 - Filed: 2023-09-20 - Published: 2024-07-04 - Granted: 2026-04-07 - Earliest claimed: 2022-12-28 - Assignees: Schlumberger Technology Corporation - Applicants: Schlumberger Technology Corporation - Inventors: Kishore Mulchandani; Crispin Chatar - Web page: https://patentgrep.com/patent/US12597109B2 ## CPC - G06T 7/0002: {Inspection of images, e.g. flaw detection} - G06T 5/73: Deblurring; Sharpening - G06T 7/55: from multiple images - G06T 7/73: using feature-based methods - G06T 17/00: Three-dimensional [3D] modelling for computer graphics - G06T 17/20: Finite element generation, e.g. wire-frame surface description, {tesselation} - G06T 2207/10016: Video; Image sequence - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/20084: Artificial neural networks [ANN] - G06T 2207/30244: Camera pose - G06T 2210/56: Particle system, point based geometry or rendering - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Systems and methods of the present disclosure provide acquiring images corresponding to multiple perspectives of a piece of equipment to be modeled. A region of interest in a first image of the images determined to be less blurry than a blur threshold and a brightness of the first image is above a brightness threshold. Based on these threshold relationships a three-dimensional model of the piece of equipment is generated based at least in part on a subset of the images that include the first image. ## Claims ### Claim 1 A method, comprising: acquiring images via a camera in electrical communication with a processor, the images corresponding to a plurality of perspectives of a piece of equipment; determining, using the processor, that a region of interest in a first image of the images is less blurry than a blur threshold; determining, using the processor, that a brightness of the first image is above a brightness threshold; estimating, using the processor, a position of the camera based on the images; obtaining depth data for the piece of the equipment based on the position; generating, using the processor, a three-dimensional model of the piece of the equipment based on a subset of the images, wherein the subset of the images comprises the first image; and assigning a score to the three-dimensional model based on at least one of: holes present in the three-dimensional model in place of solid structures; or stretched textures present in the three-dimensional model. ### Claim 2 (depends on 1) The method of claim 1, wherein the images comprise frames of video. ### Claim 3 (depends on 1) The method of claim 1, wherein the region of interest comprises a whole of the first image. ### Claim 4 (depends on 1) The method of claim 1, wherein a size and a location of the region of interest in the first image is based on an expected shape of the piece of the equipment. ### Claim 5 (depends on 1) The method of claim 1, wherein a size and a location of the region of interest in the first image is based on the depth data. ### Claim 6 (depends on 1) The method of claim 1, wherein: the brightness is a first brightness; and the method further comprises: determining that an additional region of interest in a second image of the images is more blurry than the blur threshold, or determining that a second brightness of the second image is below the brightness threshold; and attempting to fix the second image to increase a sharpness of the second image or increase the brightness of the second image using image processing. ### Claim 7 (depends on 6) The method of claim 6, comprising: determining that the additional region of interest in the second image of the images is less blurry than the blur threshold and that the brightness of the second image is above the brightness threshold after the image processing; and including the second image in the subset of the images. ### Claim 8 (depends on 6) The method of claim 6, comprising: determining that the additional region of interest in the second image of the images is more blurry than the blur threshold or that the brightness of the second image is below the brightness threshold; and excluding the second image from the subset of the images. ### Claim 9 (depends on 6) The method of claim 6, wherein the image processing comprises deblurring of the second image. ### Claim 10 (depends on 9) The method of claim 9, wherein the deblurring of the second image is based on a movement speed of an image capture device used to capture the plurality of perspectives, a shutter speed of the image capture device, a frame rate of the image capture device, a distance of the image capture device and the piece of the equipment during capture of the plurality of perspectives, or a combination thereof. ### Claim 11 (depends on 6) The method of claim 6, wherein the image processing comprises brightening shadows in the second image. ### Claim 12 (depends on 1) The method of claim 1, wherein the acquiring the images comprises acquiring color images and the estimating of the position of the camera is based on the color images. ### Claim 13 (depends on 1) The method of claim 1, further comprising evaluating an accuracy metric for the three-dimensional model based on a pixel-to-pixel analysis in the three-dimensional model and in the subset of the images. ### Claim 14 A system, comprising: a memory storing instructions; and one or more processors, that when execute the instructions, are configured to: acquire a plurality of images corresponding to a plurality of perspectives of a piece of equipment to be modeled in three-dimensions; acquire depth data from at least one of the plurality of perspectives; select a subset of the plurality of images based at least in part on the depth data; estimate positions of a camera using the subset of the plurality of images; generate depth maps from the depth data; match features in the subset of the plurality of images to establish a cloud of points and to build a polygonal mesh from the cloud of points; build textures on planes of the polygonal mesh to generate a three-dimensional model of the piece of equipment; determine, using the one or more processors, that a region of interest in a first image of the plurality of images is less blurry than a blur threshold; determine, using the one or more processors, that a brightness of the first image is above a brightness threshold; estimate, using the one or more processors, a position of the camera based on the plurality of images; and evaluate and assign a score to the three-dimensional model based on at least one of: holes present in the three-dimensional model in place of solid structures; or stretched textures present in the three-dimensional model. ### Claim 15 (depends on 14) The system of claim 14, wherein the instructions are configured to cause the one or more processors to verify the cloud of points using an expected shape for the piece of equipment to be modeled. ### Claim 16 (depends on 14) The system of claim 14, wherein the instructions are configured to cause the one or more processors to verify the cloud of points using the depth data. ### Claim 17 (depends on 14) The system of claim 14, wherein the instructions are configured to cause the one or more processors to store the three-dimensional model if the score is above a threshold. ### Claim 18 (depends on 16) The system of claim 16, wherein the instructions are configured to cause the one or more processors to reconstruct a new three-dimensional model from the plurality of images and the depth data, ask for new images, reconstruct the new three-dimensional model from a different subset of the plurality of images and the depth data, or discard the three-dimensional model if the score is below the threshold. ### Claim 19 (depends on 14) The system of claim 14, wherein the evaluating and the assigning the score to the three-dimensional model is based at least in part on a presence of duplicated surfaces in the three-dimensional model and a presence of noisy surfaces in the three-dimensional model. ### Claim 20 (depends on 19) The system of claim 19, wherein at least some of the evaluating and assigning the score comprises using one or more neural networks trained for analyzing quality of the three-dimensional model. ### Claim 21 (depends on 14) The system of claim 14, wherein estimating the positions of the camera using the subset of the plurality of images is based at least in part on the features in the subset of the plurality of images and comprises discarding one or more potential camera locations based on times of respective image captures of the plurality of images, movement of an image acquisition system, heuristics, or a combination thereof. ### Claim 22 A system, comprising: a memory storing instructions; and one or more processors, that when execute the instructions, are configured to: obtain a plurality of images obtained from a plurality of perspectives of a piece of equipment using one or more cameras; determine whether a region of interest in each of the plurality of images satisfies a quality threshold for one or more parameters, including: determine, using the one or more processors, that a region of interest in a first image of the images is less blurry than a blur threshold; and determine, using the one or more processors, that a brightness of the first image is above a brightness threshold; fix one or more images as fixed images from the plurality of images that do not satisfy the quality threshold for the one or more parameters; estimate, using the one or more processors, a position of the one or more cameras based on the images; obtain depth data for the piece of the equipment based on the position; generate a three-dimensional model of the piece of equipment based at least in part on a subset of the plurality of images, wherein the subset of the plurality of images comprises the images of the plurality of images that initially satisfy the quality threshold and the fixed images; and analyze and assign a quality score to the three-dimensional model based on at least one of: holes present in the three-dimensional model in place of solid structures; or stretched textures present in the three-dimensional model. ### Claim 23 (depends on 22) The system of claim 22, wherein the fixing the one or more images comprises sharpening the regions of interest in the one or more images or brightening shadows in the regions of interest in the one or more images.