Amazon patents camera tech that adjusts video quality based on scene detail
This patent describes a method for cameras to estimate how complex a video scene is in real time. It calculates a score based on the level of detail in the image and the amount of motion, then uses that score to pick the right data rate for sending the video.
In the filing’s own words
Video scene complexity can be estimated at a camera in real time. The camera may store associations between video complexity score ranges and corresponding bitrate values and between maximum key frame sizes and corresponding compression parameter values. As video is captured, a compression parameter value, a size of a compressed key frame, and a maximum key frame size associated with the compression parameter value can be used to estimate spatial complexity (e.g., a degree of detail within the video). The number of predicted frames corresponding to the key frame can be used to estimate temporal complexity (e.g., an amount of motion within the video). A video complexity score can be calculated from these spatial and temporal complexity estimations and used to select a bitrate for subsequent video transmissions, enabling improved bandwidth usage and storage planning while maintaining video quality.
What exactly they claim (claim 1)
1. A computer-implemented method, comprising: obtaining, by a processor of a video capture device, a first mapping that maps a plurality of video complexity score ranges to corresponding bitrates; obtaining, by the processor, a second mapping that maps a plurality of compression parameter values to a corresponding plurality of maximum frame sizes; obtaining, by the processor, a group of video frames of a video; identifying, by the processor, a key frame of the group of video frames, one or more predicted frames of the group of video frames, and a total number of frames in the group of video frames; determining, by the processor, a key frame size and a compression parameter value used by the video capture device for compression; calculating a video complexity score for the group of video frames, the video complexity score being calculated based at least in part on a spatial complexity score that indicates a degree of detail depicted within the key frame and a temporal complexity score that indicates an amount of motion depicted with the group of video frames, the temporal complexity score being calculated based at least in part on a quantity of the one or more predicted frames and the total number of video frames in the group of video frames; and assigning, by the processor, a bitrate to be used by the processor for transmitting subsequent video, the bitrate being determined based at least in part on the first mapping and the video complexity score for the group of video frames.
Facts
- Company
- Amazon (Amazon Technologies, Inc.)
- Official title
- Techniques for estimating video complexity
- Patent number
- US12739461B1
- Application number
- 18965485
- Filed
- Dec 2, 2024
- Granted
- Sep 15, 2026
- Inventors
- 2
- Claims
- 18
Classified under
H04N 21/2662 Electricity & electronicsG06T 7/20 Physics & computingH04N 19/172 Electricity & electronicsSummaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.