Granted Patent B2

US 12,501,085 · App. 18/542,526 · Granted Dec 16, 2025

Inventors: Sabine Roessel (Munich, DE); Christian Drewes (Germering, DE); Matthias Sauer (San Jose, CA); Danila Zaev (Munich, DE); Bernhard Raaf (Neuried, DE); Bernd Wurth (Landsberg am Lech, DE); Max Dmitrichenko (Munich, DE)

Assignee: Apple Inc.

H04N21/2343H04N21/2402H04N21/2405

Abstract

Claims (47)

1 . One or more processors configured for semantic encoding by performing operations comprising:

determining an expected power consumption for encoding video data that includes semantic features, the semantic features representing a meaning of information represented in video frames of the video data;

encoding one or more video frames of the video data using a selected semantic representation of one or more video frames of the video data, the semantic representation being selected based on the expected power consumption that is determined; and

outputting for transmission the encoded video data including the semantic representation.

2 . The one or more processors of claim 1 , the operations further comprising:

determining a quality level for a channel for a time period in which the video data are being transmitted over the channel; and

based on the determined quality level of the channel, encoding the video frame with one or more elements of the semantic representation.

3 . The one or more processors of claim 2 , wherein the determined channel quality level is a predicted channel quality level, the operations further comprising:

receiving an actual channel quality level at a time of transmitting the encoded video data;

determining that the actual channel quality level has a reduced quality relative to the predicted channel quality level;

removing one or more semantic elements from the encoded video frame, based on one or more priority rules or by changing one or more configurable frame rates for semantic elements including the one or more semantic elements; and

outputting for transmission the encoded video data without the removed one or more semantic elements.

4 . The one or more processors of claim 2 , wherein determining the quality level comprises:

monitoring channel features comprising one or more of a size of upload grants, a measurement for a handover, or a reference symbol; and

generating a prediction of an upload data rate for transmitting the video data.

5 . The one or more processors of claim 1 , wherein the semantic representation is selected based on a source quality indicator associated with the video data.

6 . The one or more processors of claim 1 , wherein selecting the semantic representation comprises determining one or more semantic elements to include based on the expected power consumption.

7 . The one or more processors of claim 1 , wherein the semantic representation is selected from a set of semantic representations, wherein the selected semantic representation is configured based on a plurality of features representing a soft decision value, and wherein each of the semantic representations of the set includes a different number or complexity of semantic features for encoding the video data.

8 . The one or more processors of claim 1 , wherein selecting the semantic representation comprises determining one or more semantic elements to include based on a number of annotations for extracting from the video data.

9 . The one or more processors of claim 8 , wherein determining one or more semantic elements to include comprises determining an amount of bandwidth available for semantic elements;

assigning each semantic element a priority; and

including higher priority semantic elements until the amount of bandwidth available is exhausted.

10 . The one or more processors of claim 9 , further comprising:

assigning a privacy marker to the one or more semantic elements, the privacy marker requiring a permission to access a semantic element.

11 . The one or more processors of claim 10 , wherein the semantic element comprises an identifier of a person or object.

12 . The one or more processors of claim 10 , further comprising performing end-to-end encryption of the one or more semantic elements associated with the privacy marker.

13 . The one or more processors of claim 1 , wherein the UE the one or more processors are included in an extended reality device.

14 . An apparatus user equipment configured for semantic encoding, the apparatus comprising:

at least one processor; and

a memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform operations comprising:

determining an expected power consumption for encoding video data that includes semantic features, the semantic features representing a meaning of information represented in video frames of the video data;

encoding one or more video frames of the video data using a selected a semantic representation of one or more video frames of the video data, the semantic representation being selected based on the expected power consumption that is determined; and

transmitting the encoded video data including the semantic representation.

15 . The apparatus of claim 14 , the operations further comprising:

determining a quality level for a channel for a time period in which the video data are being transmitted over the channel; and

based on the determined quality level of the channel, encoding the video frame with one or more elements of the semantic representation.

16 . The apparatus of claim 15 , wherein the determined channel quality level is a predicted channel quality level, the operations further comprising:

receiving an actual channel quality level at a time of transmitting the encoded video data;

determining that the actual channel quality level has a reduced quality relative to the predicted channel quality level;

removing one or more semantic elements from the encoded video frame, based on one or more priority rules or by changing one or more configurable frame rates for semantic elements; and

transmitting the encoded video data without the removed one or more semantic elements.

17 . The apparatus of claim 15 , wherein determining the quality level comprises:

monitoring channel features comprising one or more of a size of upload grants, a measurement for a handover, or a reference symbol; and

generating a prediction of an upload data rate for transmitting the video data.

18 . The apparatus of claim 14 , wherein the semantic representation is selected based on a source quality indicator associated with the video data.

19 . The apparatus of claim 14 , wherein selecting the semantic representation comprises determining one or more semantic elements to include based on the expected power consumption.

20 . The apparatus of claim 14 , wherein the semantic representation is selected from a set of semantic representations, wherein the selected semantic representation is configured based on a plurality of features representing a soft decision value, and wherein each of the semantic representations of the set includes a different number or complexity of semantic features for encoding the video data.

Assignments (1)

Continuity (3)

References Cited (24)