Methods and systems for training an object detection algorithm
US10402657B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Nov 9, 2017 |
| Grant date | Sep 3, 2019 |
| Priority date | — |
| Expiry date | Dec 8, 2037 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06T2207/20081
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
A method comprising: acquiring, from a camera, a video sequence of a real object; deriving a pose of the real object included in at least one image frame using a 3D model corresponding to the real object in the case where the at least one image frame is selected from the video sequence; tracking or deriving the pose of the real object included in image frames in the video sequence in forward and/or backward directions from the at least one image frame; and storing, for at least one of the tracked or derived pose, appearance information obtained from the corresponding image frame and data of a 2D model obtained from a projection of the 3D model using the corresponding tracked pose so that the appearance information and the data of the 2D model are associated with the corresponding tracked or derived pose.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.