Systems and methods for integrating user personas with content during video conferencing
A system and method is disclosed for extracting a user persona from a video and embedding that persona into a background feed that may have other content, such as text, graphics, or additional video content. The extracted video and background feed are combined to create a composite video that comprises the display in a videoconference. Embodiments cause the user persona to be embedded at preset positions, or in preset formats, or both, depending on the configuration, position, or motion of the user's body.
1. A computer-implemented method for controlling the embedding of a video persona into a background feed, the method comprising:
creating a foreground video that comprises a foreground portion by removing a background portion from a first video, wherein the foreground portion comprises a persona of a user;
receiving a background feed;
identifying a set of user-position conditions that correspond with respective persona-embedding directions;
determining which user-position conditions are met; and
generating a composite video by embedding the foreground video into the background feed in accordance with the persona-embedding directions corresponding to the met user-position conditions.
2. The computer-implemented method of claim 1 , wherein the set of user-position conditions comprises:
a user movement being within a threshold distance from an initial position, corresponding to a persona-embedding direction that an embedded persona movement be similar to the user movement; and
the user movement being beyond the threshold distance, corresponding to a persona-embedding direction that the embedded persona movement be a factor greater than the user movement.
3. The computer-implemented method of claim 2 , wherein the factor is determined by a first order linear equation, a second order equation, or an exponential equation.
4. The computer-implemented method of claim 1 , wherein the set of user-position conditions comprises:
a user being within a threshold area, corresponding to a persona-embedding direction that the embedded persona is rendered transparent if the user is not within the threshold area.
5. The computer-implemented method of claim 4 , wherein the set of user-position conditions comprises:
a user being within a border adjacent to a perimeter of the threshold area, wherein the embedded persona is rendered gradually transparent depending on a user position within the border.
6. The computer-implemented method of claim 4 , wherein a location of the threshold area is based on performance characteristics of a camera being used to create the first video.
7. The computer-implemented method of claim 1 , wherein the set of user-position conditions comprises:
the user assuming a standing position, corresponding to a persona-embedding direction that the embedded persona is rendered in a central position of the background feed; and
the user assuming a seated position, corresponding to a persona-embedding direction that the embedded persona is rendered in a non-central position of the background feed.
8. The computer-implemented method of claim 1 , wherein a user position is given by a center of mass of the user, the center of mass of the user being the spatial center of an image of the user's torso.
9. The computer-implemented method of claim 1 , wherein the set of user-position conditions comprises:
the user assuming a seated position, corresponding to a persona-embedding direction that the persona is rendered in a non-central position of the background feed and in either or both of (i) a diminished size and (ii) black and white.
10. The computer-implemented method of claim 1 , wherein embedding the persona into the background feed is further based on at least one input from a set consisting of a gesture from the user, a mouse click, a remote control input, an input into a smartphone application, and a keyboard stroke.
11. The computer-implemented method of claim 8 , wherein the center of mass of the user is used to improve embedded persona image stability within the background feed.
12. A non-transitory computer-readable medium comprising a set of instructions which, when executed by a computer, embed a video persona into a background feed, said instructions for:
creating a foreground video by extracting that comprises a foreground portion by removing a background portion from a first video, wherein the foreground portion comprises a persona of a user;
receiving a background feed;
identifying a set of user-position conditions that correspond with respective persona-embedding directions;
determining which user-position conditions are met; and
generating a composite video by embedding the foreground video into the background feed in accordance with the persona-embedding directions corresponding to the met user-position conditions.
13. The non-transitory computer-readable medium of claim 12 , wherein a user position is given by a center of mass of the user, the center of mass of the user being the spatial center of an image of the user's torso.
14. The non-transitory computer-readable medium of claim 12 , wherein the set of user-position conditions comprises:
a user movement being within a threshold distance from an initial position, corresponding to a persona-embedding direction that an embedded persona movement be similar to the user movement; and
the user movement being beyond the threshold distance, corresponding to a persona-embedding direction that the embedded persona movement be a factor greater than the user movement.
15. The non-transitory computer-readable medium of claim 14 , wherein the factor is determined by a first order linear equation, a second order equation, or an exponential equation.
16. The non-transitory computer-readable medium of claim 12 , wherein the set of user-position conditions and comprises:
a user being within a threshold area, corresponding to a persona-embedding direction that the embedded persona is rendered transparent if the user is not within the threshold area.
17. The non-transitory computer-readable medium of claim 16 , wherein the set of user-position conditions comprises:
a user being within a border adjacent to a perimeter of the threshold area, wherein the embedded persona is rendered gradually transparent depending on a user position within the border.
18. The non-transitory computer-readable medium of claim 16 , wherein a location of the threshold area is based on performance characteristics of a camera being used to create the first video.
19. The non-transitory computer-readable medium of claim 12 , wherein the set of user-position conditions comprises:
the user assuming a standing position, corresponding to a persona-embedding direction that the embedded persona is rendered in a central position of the background feed; and
the user assuming a seated position, corresponding to a persona-embedding direction that the embedded persona is rendered in a non-central position of the background feed.
20. The non-transitory computer-readable medium of claim 12 , wherein the set of user-position conditions comprises:
the user assuming a seated position, corresponding to a persona-embedding direction that the persona is rendered in a non-central position of the background feed and in either or both of a diminished size and black and white.