Granted Patent B2

US 12,615,347 · App. 18/516,194 · Granted Apr 28, 2026

Inventors: Anna Deng (San Jose, CA); Yanjia Duan (Milpitas, CA); Juntao Feng (Hangzhou, CN); Tianming Gu (Hangzhou, CN); Cynthia Eshiuan Lee (Austin, TX); Bo Ling (Saratoga, CA); Chong Lv (Hangzhou, CN); Jeffrey William Smith (Layton, UT); Menglin Wang (Hangzhou, CN); Huixi Zhao (San Jose, CA); Xingguo Zhu (Hangzhou, CN)

Assignee: Zoom Communications, Inc.

H04N7/15G06V40/103H04N23/90

Abstract

Claims (55)

1 . A method, comprising:

determining scores for video streams from cameras based on a representation of a conference participant within the video streams;

selecting a video stream based on the scores;

determining that a change policy related to at least one of a threshold time between video stream selection changes or a total number of video stream selection changes over a time period is met;

based on the determination that the change policy is met, providing an indication of the selected video stream for the conference participant; and

outputting the selected video stream for the conference participant within a user interface tile of conferencing software based on the indication.

2 . The method of claim 1 , wherein determining the scores for the video streams for the conference participant comprises:

determining scores for a subset of the video streams for the conference participant by evaluating representations of the conference participant within each video stream of the subset of video streams according to one or more factors.

3 . The method of claim 1 , comprising:

determining other scores for video streams from multiple cameras based on a representation of a second conference participant within the video streams;

selecting a second video stream having a highest other score of the other scores, wherein the second video stream is selected to be different than the selected video stream;

providing a second indication of the selected second video stream for the second conference participant; and

outputting the selected second video stream for the second conference participant for rendering within a different separate user interface tile of the conferencing software based on the second indication.

4 . The method of claim 1 , comprising:

determining new scores for the video streams for the conference participant on a discrete time interval basis or an event basis;

selecting a different video stream for the conference participant based on the determined new scores; and

outputting the selected different video stream for rendering within the user interface tile associated with the conference participant.

5 . The method of claim 1 , comprising:

adjusting one or more weights applied to one or more factors used to determine the scores according to output of a machine learning model using participant input.

6 . The method of claim 1 , comprising:

presenting data associated with one or more of the video streams to one or more participant devices connected to the conferencing software; and

selecting a different video stream for the conference participant based on feedback received from the one or more participant devices responsive to the data presentation.

7 . The method of claim 1 , comprising:

presenting data associated with each of the video streams which include representations of the conference participant to a companion device of the conference participant; and

selecting a different video stream for the conference participant based on feedback indicating a selection of one of the video streams which include the representations of the conference participant at the companion device.

8 . The method of claim 1 , further comprising:

identifying regions of interest within the video streams, wherein each of the regions of interest corresponds to one of multiple conference participants.

9 . The method of claim 1 , wherein the outputting of a selected video stream for the conference participant is delayed according to the change policy.

10 . The method of claim 1 , wherein factors used to determine a score for a video stream for the conference participant include one or more of a percentage of a face of the conference participant which is visible within the video stream, a direction of a face of the conference participant relative to a camera from which the video stream is obtained, a direction the conference participant is looking relative to the camera, or a degree to which a face of the conference participant is obscured within the video stream.

11 . A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:

determining scores for video streams from cameras based on a representation of a conference participant within the video streams;

selecting a video stream based on the scores;

determining that a change policy related to at least one of a threshold time between video stream selection changes or a total number of video stream selection changes over a time period is met;

based on the determination that the change policy is met, providing an indication of the selected video stream for the conference participant; and

outputting the selected video stream for the conference participant within a user interface tile of conferencing software based on the indication.

12 . The non-transitory computer readable medium of claim 11 , wherein the scores for each video stream are based on a percentage of a face of the conference participant which is visible within the video stream.

13 . The non-transitory computer readable medium of claim 11 , wherein the scores for each video stream are based on a direction of a face of the conference participant relative to a camera capturing the video stream.

14 . The non-transitory computer readable medium of claim 11 , wherein the scores are based on a direction the conference participant is looking relative to a camera capturing the video stream.

15 . The non-transitory computer readable medium of claim 11 , wherein the scores for a video stream are based on a degree to which a face of the conference participant is obscured within the video stream.

16 . The non-transitory computer readable medium of claim 11 , wherein the selected video stream for a first conference participant is from a first camera of the cameras and the selected video stream for a second conference participant is from a second camera of the cameras.

17 . An apparatus, comprising:

a memory; and

a processor configured to execute instructions stored in the memory to:

determine scores for video streams from cameras based on a representation of a conference participant within the video streams;

select a video stream based on the scores;

determine that a change policy related to at least one of a threshold time between video stream selection changes or a total number of video stream selection changes over a time period is met;

based on the determination that the change policy is met, provide an indication of the selected video stream for the conference participant; and

output the selected video stream for the conference participant within a user interface tile of conferencing software.

18 . The apparatus of claim 17 , wherein the processor is configured to execute the instructions to:

poll one or more participant devices connected to a conference implemented by the conferencing software for selections of ones of the video streams for the conference participant; and

select a new video stream for the conference participant based on the poll.

19 . The apparatus of claim 17 , wherein the processor is configured to execute the instructions to:

output a selected second video stream for a second conference participant for rendering within a different separate user interface tile of the conferencing software based on a second indication, wherein the selected second video stream is from a different camera than the selected video stream.

20 . The apparatus of claim 17 , wherein, to determine a score for a video stream from a camera for the conference participant, the processor is configured to execute instructions stored in the memory to:

weigh a percentage of a face of the conference participant which is visible within the video stream against one or more of a direction of a face of the conference participant relative to the camera, a direction of focus of the conference participant relative to the camera, or a degree to which a face of the conference participant is obscured within the video stream.

Assignments (2)

Continuity (3)

References Cited (154)