Performing object modeling by combining visual data from images with motion data of the image acquisition device
US11741618B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Mar 22, 2021 |
| Grant date | Aug 29, 2023 |
| Priority date | — |
| Expiry date | Nov 13, 2041 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2219/2004
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
Techniques are described for automated analysis and use of images acquired of an object and of associated image acquisition metadata, such as for manmade largescale objects at fixed locations in outdoor environments, and to automatically generate a 3D computer model of the object (e.g., the 3D shape of the object exterior's surface) from visual data in the acquired images and from image acquisition device motion data during the image acquisition, to use the computer model to automatically determine measurements for object attribute(s), and to display or otherwise provide information about the generated computer model and/or determined object attributes. The image acquisition metadata may include motion data from IMU (inertial measurement unit) sensors on the image acquisition device, and include additional related data that is determined based at least in part on that motion data (e.g., acquisition pose data for particular acquired images, 3D positions on object exterior, etc.).
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.