Synthetic data generation for training a machine learning model for dynamic object compositing in scenes
US10867444B2 · kind B2 · utility
37Cited by
0References
20Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Nov 29, 2018 |
| Grant date | Dec 15, 2020 |
| Priority date | — |
| Expiry date | Dec 9, 2038 |
Classification
- Technology area (CPC G)Physics
- CPC primaryG06V40/20
- WIPO fieldComputer technology
- WIPO sectorElectrical engineering
Abstract
This application relates generally to augmenting images and videos with dynamic object compositing, and more specifically, to generating synthetic training data to train a machine learning model to automatically augment an image or video with a dynamic object. The synthetic training data may contain multiple data points from thousands of simulated dynamic object movements within a virtual environment. Based on the synthetic training data, the machine learning model may determine the movement of a new dynamic object within new virtual environment.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.