Estimating depth for a video stream captured with a monocular rgb camera
US10984545B2 · kind B2 · utility
Assignee
Inventors
Key dates
| Filing date | Jun 12, 2019 |
| Grant date | Apr 20, 2021 |
| Priority date | — |
| Expiry date | Nov 26, 2039 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH04N2013/0081
- WIPO fieldAudio-visual technology
- WIPO sectorElectrical engineering
Abstract
Techniques for estimating depth for a video stream captured by a monocular image sensor are disclosed. A sequence of image frames are captured by the monocular image sensor. A first neural network is configured to process at least a portion of the sequence of image frames to generate a depth probability volume. The depth probability volume includes a plurality of probability maps corresponding to a number of discrete depth candidate locations over a range of depths defined for the scene. The depth probability volume can be updated using a second neural network that is configured to generate adaptive gain parameters to integrate the DPVs over time. A third neural network is configured to refine the updated depth probability volume from a lower resolution to a higher resolution that matches the original resolution of the sequence of image frames. A depth map can be calculated based on the depth probability volume.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.