# US 11,908,153 B2 · System and method of measuring distances related to an object utilizing ancillary objects > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,153 B2 - Document ID: US11908153B2 - Status: Granted - Kind: B2 - Application number: 17/238,296 - Filed: 2021-04-23 - Published: 2021-10-28 - Granted: 2024-02-20 - Earliest claimed: 2020-04-23 - Assignees: WexEnergy Innovations LLC - Applicants: WexEnergy Innovations LLC - Inventors: John Patrick Spence; Ronald Myron Wexler - Web page: https://patentgrep.com/patent/US11908153B2 ## CPC - G06T 7/60: Analysis of geometric attributes - G06T 7/62: of area, perimeter, diameter or volume - G06T 7/13: Edge detection - G06T 7/50: Depth or shape recovery - G06T 7/73: using feature-based methods - G06T 2207/10024: Color image - G06T 2207/20164: Salient point detection; Corner detection - G06T 2207/30204: Marker - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system and method for measuring distances related to a target object depicted in an image. A captured digital image is obtained containing a scene with a target object whose dimension is to be measured. The digital image may contain a target object dimension identified by one or more ancillary objects and a reference object in the same or different planes. Image processing is performed to find the reference object using known fiducial patterns printed on the reference object, metadata supplied by a user and/or by the detection of colored papers in the scene of the captured image. Once located and measured, the reference object is used to calculate a pixel scale factor used to measure the target object dimensions. Target object dimensions are provided to an automated or semi-automated measurement process, design and manufacturing system such that customized parts for a supplemental fenestration are provided to end users. ## Claims ### Claim 1 A method of estimating target object dimensions within digital images, the method implemented by one or more computing devices and comprising: obtaining a digital image containing a target object and a first reference object having a first fiducial pattern having a highly saturated color, wherein the first reference object further has at least one of: an optical transmittance between about 2 percent and about 80 percent, a reflectance between about 15 percent and about 85 percent, a diffuse transmittance between about 5 percent and about 65 percent, or a direct transmittance less than about 10 percent and another diffuse transmittance greater than the direct transmittance; locating the first reference object in the digital image; calculating a pixel scale factor for the digital image based on both measured and known dimensions of the first reference object; locating the target object in the digital image; and calculating a dimension of the target object based on the pixel scale factor. ### Claim 2 (depends on 1) The method according to claim 1, wherein the digital image further comprises one or more ancillary objects, the method further comprises identifying the one or more ancillary objects and a corner or edge thereof in the digital image, and the target object is located in the digital image further based on the corner or edge of the one or more ancillary objects. ### Claim 3 (depends on 2) The method according to claim 2, wherein the one or more ancillary objects are one or more pane ancillary objects or comprise at least one colored object. ### Claim 4 (depends on 1) The method according to claim 1, wherein the first reference object has a first feature located at a known location relative to an edge of the first reference object that is used to calculate the pixel scale factor. ### Claim 5 (depends on 4) The method according to claim 4, wherein the first feature is a line segment. ### Claim 6 (depends on 1) The method according to claim 1, wherein the digital image contains a second reference object and the method further comprises: locating the second reference object in the digital image; and performing one or more calibrations for the digital image based on the first reference object and the second reference object. ### Claim 7 (depends on 6) The method according to claim 6, wherein the target image comprises a rectangular object, the digital image further comprises a third reference object and a fourth reference object, and each of the first, second, third, and fourth reference objects is located at a respective corner of the target object. ### Claim 8 (depends on 6) The method according to claim 6, wherein the first reference object has a first feature located at a known location relative to an edge of the first reference object, the second reference object has a second feature located at a known location relative to an edge of the second reference object, the first feature is a first line segment, the second feature is a second line segment, and the method further comprises: digitally extending each of the first line segment and the second line segment such that the first line segment and the second line segment meet at an intersection point; and identifying a corner or an edge area of the target object based on the intersection point of the first line segment and the second line segment. ### Claim 9 A non-transitory machine readable medium having stored thereon instructions for estimating target object dimensions within digital images comprising executable code that, when executed by one or more processors, causes the one or more processors to: obtain a digital image containing a target object and a first reference object having a first fiducial pattern having a highly saturated color, wherein the first reference object further has at least one of: an optical transmittance between about 2 percent and about 80 percent, a reflectance between about 15 percent and about 85 percent, a diffuse transmittance between about 5 percent and about 65 percent, or a direct transmittance less than about 10 percent and another diffuse transmittance greater than the direct transmittance; locate the first reference object in a digital image; calculate a pixel scale factor for the digital image based on both measured and known dimensions of the first reference object; locate the target object in the digital image; and calculate a dimension of the target object based on the pixel scale factor. ### Claim 10 (depends on 9) The medium according to claim 9, wherein the digital image further comprises one or more ancillary objects, the executable code, when executed by the one or more processors, further causes the one or more processors to identify the one or more ancillary objects and a corner or edge thereof in the digital image, and the target object is located in the digital image further based on the corner or edge of the one or more ancillary objects. ### Claim 11 (depends on 10) The medium according to claim 10, wherein the one or more ancillary objects are one or more pane ancillary objects or comprise at least one colored object. ### Claim 12 (depends on 9) The medium according to claim 9, wherein the first reference object has a first feature located at a known location relative to an edge of the first reference object that is used to calculate the pixel scale factor. ### Claim 13 (depends on 12) The medium according to claim 12, wherein the first feature is a line segment. ### Claim 14 (depends on 9) The medium according to claim 9, wherein the digital image contains a second reference object and the executable code, when executed by the one or more processors, further causes the one or more processors to: locate the second reference object in the digital image; and perform one or more calibrations for the digital image based on the first reference object and the second reference object. ### Claim 15 (depends on 14) The medium according to claim 14, wherein the target image comprises a rectangular object, the digital image further comprises a third reference object and a fourth reference object, and each of the first, second, third and fourth reference objects is located at a respective corner of the target object. ### Claim 16 (depends on 14) The medium according to claim 14, wherein the first reference object has a first feature located at a known location relative to an edge of the first reference object, the second reference object has a second feature located at a known location relative to an edge of the second reference object, the first feature is a first line segment, the second feature is a second line segment, and the executable code, when executed by the one or more processors, further causes the one or more processors to: digitally extend each of the first line segment and the second line segment such that the first line segment and the second line segment meet at an intersection point; and identify a corner or an edge area of the target object based on the intersection point of the first line segment and the second line segment. ### Claim 17 A method implemented by a computing device and comprising: obtaining a digital image captured by an imaging capture device, the digital image comprising a target object, a reference object, and one or more pane ancillary objects, wherein each of the one or more pane ancillary objects is a colored object having a saturation level; calculating a pixel scale factor based on measured and known dimensions of the reference object, wherein the reference object has at least one of: an optical transmittance between about 2 percent and about 80 percent, a reflectance between about 15 percent and about 85 percent, a diffuse transmittance between about 5 percent and about 65 percent, or a direct transmittance less than about 10 percent and another diffuse transmittance greater than the direct transmittance; identifying the one or more pane ancillary objects and a corner or edge thereof in the digital image; locating the target object in the digital image based on the identified corner or edge of the one or more pane ancillary objects; and calculating at least one dimension of the target object in accordance with the pixel scale factor. ### Claim 18 (depends on 17) The method according to claim 17, wherein the one or more pane ancillary objects are highly saturated colored objects.