Back to results
US 12,593,087 B1Granted
Video data storage
AssigneeNVIDIA Corporation
InventorsDivy Sitlani, Pankaj Kadtan
Life of this patent
Estimating the term…
Abstract
Apparatuses, systems, and techniques to store metadata including information indicating locations objects depicted in video frames to be stored in association with video data. In at least one embodiment, metadata is embedded in video data and used to generate annotations associated with objects depicted in one or more frames of the video data.
Claims20
A processor, comprising:
- one or more circuits to:
- determine one or more locations of one or more objects depicted in one or more video frames;
- embed the one or more locations as metadata within video data including the one or more video frames, wherein respective metadata is embedded within an encoding of each frame of the one or more video frames;
- and
- cause an encoded frame of the one or more video frames to be transmitted with the metadata embedded in the encoded frame such that the one or more locations of the one or more objects depicted in the encoded frame are transmitted with the encoded frame.
2 more elements
A method, comprising:
- determining one or more locations of one or more objects depicted in one or more video frames;
- embedding the one or more locations as metadata within video data including the one or more video frames, wherein respective metadata is embedded within an encoding of each frame of the one or more video frames;
- and
- transmitting an encoded frame of the one or more video frames with the metadata embedded in the encoded frame such that the one or more locations of the one or more objects depicted in the encoded frame are transmitted with the encoded frame.
1 more element
A system, comprising:
- one or more processors to:
- determine one or more locations of one or more objects depicted in one or more video frames;
- embed the one or more locations as metadata within video data including the one or more video frames, wherein respective metadata is embedded within an encoding of each frame of the one or more video frames;
- and
- cause an encoded frame of the one or more video frames to be transmitted with the metadata embedded in the encoded frame such that the one or more locations of the one or more objects depicted in the encoded frame are transmitted with the encoded frame.
2 more elements
Dependencies are inferred from the claim text.