# US 12,182,964 B2 · Vehicle undercarriage imaging > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,182,964 B2 - Document ID: US12182964B2 - Status: Granted - Kind: B2 - Application number: 18/531,614 - Filed: 2023-12-06 - Published: 2024-04-04 - Granted: 2024-12-31 - Earliest claimed: 2021-03-02 - Assignees: Fyusion, Inc. - Applicants: Fyusion, Inc. - Inventors: Stefan Johannes Josef Holzer; Krunal Ketan Chande; Matteo Munaro; Pavel Hanchar; Aidas Liaudanskas; Wook Yeon Hwang; Johan Nordin; Milos Vlaski; Martin Markus Hubert Wawro; Nick Stetco; Martin Saelzle - Web page: https://patentgrep.com/patent/US12182964B2 ## CPC - G06T 3/4038: Image mosaicing, e.g. composing plane images from plane sub-images - G06T 7/0004: {Industrial image inspection} - G06T 7/50: Depth or shape recovery - G06T 2207/10028: Range image; Depth image; 3D point clouds - G06T 2207/20221: Image fusion; Image merging - G06T 2207/30252: Vehicle exterior; Vicinity of vehicle - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Images of an undercarriage of a vehicle may be captured via one or more cameras. A point cloud may be determined based on the images. The point cloud may includes points positioned in a virtual three-dimensional space. A stitched image may be determined based on the point cloud by projecting the point cloud onto a virtual camera view. The stitched image may be stored on a storage device. ## Claims ### Claim 1 A method comprising: capturing a first plurality of vehicle undercarriage images, the first plurality of vehicle undercarriage images captured using a first camera, the first plurality of vehicle undercarriage images captured as a vehicle moves relative to the first camera; determining a first designated point cloud using the first plurality of vehicle undercarriage images via a processor, the first designated point cloud including a first plurality of points positioned in a first virtual three-dimensional space; capturing a second plurality of vehicle undercarriage images; determining a designated stitched image based on the first designated point cloud and the second plurality of vehicle undercarriage images, wherein the stitched image is determined by projecting the first designated point cloud onto a virtual camera view and identifying a plurality of vehicle undercarriage feature correspondence points and a plurality of point correspondence transformations associating a first location of the first point in a first image in the second plurality of vehicle undercarriage images with a second location of the second point in a second image in the second plurality of vehicle undercarriage images; and storing the designated stitched image on a storage device. ### Claim 2 (depends on 1) The method recited in claim 1, wherein the virtual camera view is a two-dimensional plane in the virtual three-dimensional space. ### Claim 3 (depends on 1) The method recited in claim 1, wherein the virtual camera view is a point in the virtual three-dimensional space. ### Claim 4 (depends on 1) The method recited in claim 1, wherein determining the designated point cloud comprises determining a plurality of point clouds. ### Claim 5 (depends on 4) The method recited in claim 4, wherein determining the designated point cloud comprises generating a three-dimensional model of the vehicle undercarriage. ### Claim 6 (depends on 4) The method recited in claim 4, wherein each of the point clouds corresponds with a respective image. ### Claim 7 (depends on 1) The method recited in claim 1, wherein the designated point cloud is determined based at least in part on depth information captured from one or more depth sensors. ### Claim 8 (depends on 1) The method recited in claim 1, wherein determining the stitched image comprises identifying a plurality of correspondence points, each of the correspondence points indicating a visual feature included in two or more of the second plurality of vehicle undercarriage images. ### Claim 9 (depends on 8) The method recited in claim 8, wherein determining the stitched image further comprises identifying a plurality of point correspondence transformations, each of the point correspondence transformations identifying a respective spatial relationship between the first location of a designated one of the correspondence points in a first one of the images and the second location of the designated correspondence point in a second one of the images. ### Claim 10 (depends on 9) The method recited in claim 9, wherein determining the stitched image further comprises determining an image correspondence providing a mathematical transformation between the first and second images in a two or three dimensional coordinate space based on the plurality of correspondence transformations. ### Claim 11 (depends on 10) The method recited in claim 10, wherein the image correspondence is a numerical average of one or more of the point correspondence transformations, the numerical average determined based on a cost function. ### Claim 12 (depends on 1) The method recited in claim 1, wherein the designated stitched image is one of a plurality of stitched images determined based on the designated point cloud. ### Claim 13 (depends on 12) The method recited in claim 12, wherein the designated stitched image is a multi-view interactive digital media representation navigable in multiple dimensions. ### Claim 14 A system comprising: a camera configured to capture a first plurality of vehicle undercarriage images, the first plurality of vehicle undercarriage images captured using a first camera, the first plurality of vehicle undercarriage images captured as a vehicle moves relative to the first camera, wherein a second plurality of vehicle undercarriage images is captured; a processor configured to determine a first designated point cloud using the first plurality of vehicle undercarriage images via a processor, the first designated point cloud including a first plurality of points positioned in a first virtual three-dimensional space, the processor further configured to determine a designated stitched image based on the first designated point cloud and the second plurality of vehicle undercarriage images, wherein the stitched image is determined by projecting the first designated point cloud onto a virtual camera view and identifying a plurality of vehicle undercarriage feature correspondence points and a plurality of point correspondence transformations associating a first location of the first point in a first image in the second plurality of vehicle undercarriage images with a second location of the second point in a second image in the second plurality of vehicle undercarriage images; and a memory device configured to store the designated stitched image. ### Claim 15 (depends on 14) The system recited in claim 14, wherein the virtual camera view is a two-dimensional plane in the virtual three-dimensional space. ### Claim 16 (depends on 14) The system recited in claim 14, wherein the virtual camera view is a point in the virtual three-dimensional space. ### Claim 17 (depends on 14) The system recited in claim 14, wherein determining the designated point cloud comprises determining a plurality of point clouds. ### Claim 18 (depends on 17) The system recited in claim 17, wherein determining the designated point cloud comprises generating a three-dimensional model of the vehicle undercarriage. ### Claim 19 (depends on 17) The system recited in claim 17, wherein each of the point clouds corresponds with a respective image. ### Claim 20 An apparatus comprising: means for capturing a first plurality of vehicle undercarriage images, the first plurality of vehicle undercarriage images captured, the first plurality of vehicle undercarriage images captured as a vehicle moves relative to the means for capturing the first plurality of vehicle undercarriage images; means for determining a first designated point cloud using the first plurality of vehicle undercarriage images, the first designated point cloud including a first plurality of points positioned in a first virtual three-dimensional space; means for capturing a second plurality of vehicle undercarriage images; means for determining a designated stitched image based on the first designated point cloud and the second plurality of vehicle undercarriage images, wherein the stitched image is determined by projecting the first designated point cloud onto a virtual camera view and identifying a plurality of vehicle undercarriage feature correspondence points and a plurality of point correspondence transformations associating a first location of the first point in a first image in the second plurality of vehicle undercarriage images with a second location of the second point in a second image in the second plurality of vehicle undercarriage images; and means for storing the designated stitched image.