# US 11,551,439 B2 · Some automated and semi-automated tools for linear feature extraction in two and three dimensions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,551,439 B2 - Document ID: US11551439B2 - Status: Granted - Kind: B2 - Application number: 17/037,305 - Filed: 2020-09-29 - Published: 2021-01-21 - Granted: 2023-01-10 - Earliest claimed: 2014-06-03 - Assignees: DigitalGlobe, Inc. - Applicants: DigitalGlobe, Inc. - Inventors: Jacek Grodecki; Seth Malitz; Josh Nolting - Web page: https://patentgrep.com/patent/US11551439B2 ## CPC - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06F 18/40: Software arrangements specially adapted for pattern recognition, e.g. user interfaces or toolboxes therefor - G06V 10/469: {Contour-based spatial representations, e.g. vector-coding} - G06V 10/945: {User interactive design; Environments; Toolboxes} - G06V 20/13: Satellite images - G06T 17/05: Geographic models - G06V 20/182: {Network patterns, e.g. roads or rivers} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract A system for vector extraction comprising a vector extraction engine stored and operating on a network-connected computing device that loads raster images from a database stored and operating on a network-connected computing device, identifies features in the raster images, and computes a vector based on the features, and methods for feature and vector extraction. ## Claims ### Claim 1 A system for three-dimensional feature extraction from imagery of a surface, comprising: a vector extraction engine operating on a computing device or network of computing devices; wherein the vector extraction engine: receives a stereoscopic raster image pair of the surface, the stereoscopic image pair comprising a first raster image and a second raster image; identifies one or more image features that are homologous between the first raster image and second raster image; computes a vector difference between the first raster image and the second raster image for each of the identified image features; constructs a three-dimensional digital surface model of the surface based on the vector differences. ### Claim 2 (depends on 1) The system of claim 1, further comprising a three-dimensional viewer operating on the computing device or network of computing devices; wherein the three-dimensional viewer: displays the surface on a user interface; receives from the user interface a user-selected first point on the surface and a user-selected second point on the surface; calculates a three-dimensional path along the digital surface model between the first point and the second point; and displays a three-dimensional representation of the surface on the display showing the three-dimensional path along the surface. ### Claim 3 (depends on 2) The system of claim 2, wherein the surface is displayed on the user interface as a two-dimensional representation. ### Claim 4 (depends on 2) The system of claim 2, wherein the surface is displayed on the user interface as a three-dimensional representation. ### Claim 5 (depends on 2) The system of claim 2, wherein the three-dimensional path is shown along the surface slightly raised from the three dimensional representation of the surface. ### Claim 6 (depends on 2) The system of claim 2, wherein the three-dimensional path is calculated using a least-cost algorithm. ### Claim 7 (depends on 2) The system of claim 2, further comprising additional user selected points on the surface between the first point and the second point, and wherein the three-dimensional path between the first point and the second point passes through each of the additional user selected points. ### Claim 8 A method for three-dimensional feature extraction from image data of a surface, comprising the steps of: receiving, using a vector extraction engine operating on a computing device or network of computing devices, a stereoscopic raster image pair of the surface, the stereoscopic image pair comprising a first raster image and a second raster image; and identifying, using a vector extraction engine stored and operating on a workstation computer, one or more image features that are homologous between the first raster image and second raster image; computing a vector difference between the first raster image and the second raster image for each of the identified image features; and constructing a three-dimensional digital surface model of the surface based on the vector differences. ### Claim 9 (depends on 8) The method of claim 8, further comprising the step of operating a three-dimensional viewer on the computing device or network of computing devices; wherein the three-dimensional viewer: displays the surface on a user interface; receives from the user interface a user-selected first point on the surface and a user-selected second point on the surface; calculates a three-dimensional path along the digital surface model between the first point and the second point; and displays a three-dimensional representation of the surface on the display showing the three-dimensional path along the surface. ### Claim 10 (depends on 8) The method of claim 8, further comprising the step of displaying the surface on the user interface as a two-dimensional representation. ### Claim 11 (depends on 8) The method of claim 8, further comprising the step of displaying the surface on the user interface as a three-dimensional representation. ### Claim 12 (depends on 8) The method of claim 8, further comprising the step of showing the three-dimensional path along the surface slightly raised from the three dimensional representation of the surface. ### Claim 13 (depends on 8) The method of claim 8, further comprising the step of calculating the three-dimensional path using a least-cost algorithm. ### Claim 14 (depends on 8) The method of claim 8, further comprising the steps of receiving additional user selected points on the surface between the first point and the second point, and ensuring that the three-dimensional path between the first point and the second point passes through each of the additional user selected points.