Systems and methods for implementing privacy filters with variable obfuscation for video communications
In one embodiment, a method includes maintaining a video communication between two or more client devices with each client device comprising cameras and being associated with a respective video stream in the video communication, determining scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices, determining a privacy filter to apply to a first video stream associated with the first client device based on the scene data, and providing instructions to apply the privacy filter to the first video stream in the video communication.
1. A method comprising, by an electronic device:
maintaining a video communication between two or more client devices, wherein each client device comprises one or more cameras, and wherein each client device is associated with a respective video stream in the video communication;
determining scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices;
determining, based at least in part on the scene data, a level of engagement, with respect to the video communication, of a participant shown in a first video stream associated with the first client device;
determining, based on the level of engagement of the participant shown in the first video stream with the video stream, a privacy filter, which intentionally obfuscates at least a portion of the participant shown in the first video stream, to apply to the participant shown in the first video stream; and
providing instructions to apply the privacy filter to the first video stream in the video communication.
2. The method of claim 1 , wherein the privacy filter is a physical camera privacy filter comprising one or more of a movable element with transparency gradient, a semi-transparent layer, a movable patterned element with transparency gradient, a displacement of lenses associated with a camera, or two or more sheets with polarizing filters.
3. The method of claim 1 , wherein the privacy filter is a physical element placed in an optical path associated with a camera, and wherein the physical element is operable to change its transparency to at least four different transparency levels.
4. The method of claim 1 , wherein on the scene data comprises one or more of:
a level of activity;
a sound in the real-world environment;
a presence of a person within the field of view;
an absence of a person within the field of view;
a location of the real-world environment;
an engagement of a person with respect to the video communication;
a facial expression of a person within the field of view;
a gesture of a person within the field of view;
a pose of a person within the field of view;
a time at the real-world environment; or
weather at the real-world environment.
5. The method of claim 1 , wherein the privacy filter is a presence visualization based on one or more of a shape, a motion, a shade, or an animation.
6. The method of claim 1 , further comprising:
detecting, based on a person detection model, one or more people within the field of view;
determining, based on a pose detection model, one or more poses of one or more of the detected people; and
determining the scene data based on the determined poses of one or more of the detected people.
7. The method of claim 1 , wherein applying the privacy filter results in an obfuscation of the field of view based on one or more of:
a transformation of the field of view;
an overlay to the field of view;
a manipulation of the one or more of the cameras to obfuscate the field of view; or
a partial or complete replacement of the first video stream with one or more virtual elements.
8. An electronic device comprising:
one or more displays;
one or more non-transitory computer-readable storage media including instructions; and
one or more processors coupled to the storage media, the one or more processors configured to execute the instructions to:
maintain a video communication between two or more client devices, wherein each client device comprises one or more cameras, and wherein each client device is associated with a respective video stream in the video communication;
determine scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices;
determine, based at least in part on the scene data, a level of engagement, with respect to the video communication, of a participant shown in a first video stream associated with the first client device;
determine, based on the level of engagement of the participant shown in the first video stream with the video stream, a privacy filter, which intentionally obfuscates at least a portion of the participant shown in the first video stream, to apply to the participant shown in the first video stream; and
provide instructions to apply the privacy filter to the first video stream in the video communication.
9. The electronic device of claim 8 , wherein the privacy filter is a physical camera privacy filter comprising one or more of a movable element with transparency gradient, a semi-transparent layer, a movable patterned element with transparency gradient, a displacement of lenses associated with a camera, or two or more sheets with polarizing filters.
10. The electronic device of claim 8 , wherein the privacy filter is a physical element placed in an optical path associated with a camera, and wherein the physical element is operable to change its transparency to at least four different transparency levels.
11. The electronic device of claim 8 , wherein on the scene data comprises one or more of:
a level of activity;
a sound in the real-world environment;
a presence of a person within the field of view;
an absence of a person within the field of view;
a location of the real-world environment;
an engagement of a person with respect to the video communication;
a facial expression of a person within the field of view;
a gesture of a person within the field of view;
a pose of a person within the field of view;
a time at the real-world environment; or
weather at the real-world environment.
12. The electronic device of claim 8 , wherein the privacy filter is a presence visualization based on one or more of a shape, a motion, a shade, or an animation.
13. The electronic device of claim 8 , wherein the processors are further configured to execute the instructions to:
detect, based on a person detection model, one or more people within the field of view;
determine, based on a pose detection model, one or more poses of one or more of the detected people; and
determine the scene data based on the determined poses of one or more of the detected people.
14. The electronic device of claim 8 , wherein applying the privacy filter results in an obfuscation of the field of view based on one or more of:
a transformation of the field of view;
an overlay to the field of view;
a manipulation of the one or more of the cameras to obfuscate the field of view; or
a partial or complete replacement of the first video stream with one or more virtual elements.
15. A computer-readable non-transitory storage media comprising instructions executable by a processor to:
maintain a video communication between two or more client devices, wherein each client device comprises one or more cameras, and wherein each client device is associated with a respective video stream in the video communication;
determine scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices;
determine, based at least in part on the scene data, a level of engagement, with respect to the video communication, of a participant shown in a first video stream associated with the first client device;
determine, based on the level of engagement of the participant shown in the first video stream with the video stream, a privacy filter, which intentionally obfuscates at least a portion of the participant shown in the first video stream, to apply to the participant shown in the first video stream; and
provide instructions to apply the privacy filter to the first video stream in the video communication.
16. The media of claim 15 , wherein the privacy filter is a physical camera privacy filter comprising one or more of a movable element with transparency gradient, a semi-transparent layer, a movable patterned element with transparency gradient, a displacement of lenses associated with a camera, or two or more sheets with polarizing filters.
17. The media of claim 15 , wherein the privacy filter is a physical element placed in an optical path associated with a camera, and wherein the physical element is operable to change its transparency to at least four different transparency levels.
18. The media of claim 15 , wherein on the scene data comprises one or more of:
a level of activity;
a sound in the real-world environment;
a presence of a person within the field of view;
an absence of a person within the field of view;
a location of the real-world environment;
an engagement of a person with respect to the video communication;
a facial expression of a person within the field of view;
a gesture of a person within the field of view;
a pose of a person within the field of view;
a time at the real-world environment; or
weather at the real-world environment.
19. The media of claim 15 , wherein the privacy filter is a presence visualization based on one or more of a shape, a motion, a shade, or an animation.
20. The media of claim 15 , wherein the instructions are further executable by the processor to:
detect, based on a person detection model, one or more people within the field of view;
determine, based on a pose detection model, one or more poses of one or more of the detected people; and
determine the scene data based on the determined poses of one or more of the detected people.
21. A method comprising, by an electronic device:
maintaining a video communication between two or more client devices, wherein each client device comprises one or more cameras, and wherein each client device is associated with a respective video stream in the video communication;
determining scene data within a field of view in a real-world environment captured by one or more of the cameras of a first client device of the two or more client devices;
determining, based at least in part on the scene data, a level of engagement, with respect to the video communication, of a participant shown in a first video stream associated with the first client device;
determining, based on the level of engagement of the participant shown in the first video stream with the video stream, a privacy filter, which intentionally obfuscates at least a portion of the participant shown in the first video stream, to apply to the participant shown in the first video stream; and
providing instructions to change a transparency of the privacy filter associated with a first camera of the one or more cameras associated with the first client device of the two or more client devices in response to an electrical signal, wherein the privacy filter comprises a physical element placed in on optical path associated with the first camera, and wherein the physical element is operable to change the transparency of the privacy filter to at least four different transparency levels.
22. The method of claim 21 , wherein the privacy filter is a physical camera privacy filter comprising one or more of a movable element with transparency gradient, a semi-transparent layer, a movable patterned element with transparency gradient, a displacement of lenses associated with a camera, or two or more sheets with polarizing filters.