Computer vision driven actions based on user availability during video conferences
In one embodiment, a method is disclosed comprising: analyzing, by a process, real-time video of a user participating on a video conference; determining, by the process and based on analyzing, a level of engagement of the user to the video conference; detecting, by the process, that the level of engagement of the user to the video conference is below a given threshold of engagement for a minimum length of time, wherein the minimum length of time is configurable based on one or more engagement indicators; and enacting, by the process, one or more video conference privacy measures for the user within the video conference in response to the level of engagement being below the given threshold of engagement for the minimum length of time.
1 . A method, comprising:
analyzing, by a process, real-time video of a user participating on a video conference;
determining, by the process and based on analyzing, a level of engagement of the user to the video conference;
determining, by the process, a confidence level in an accuracy of the level of engagement based on one or more engagement indicators;
detecting, by the process, that the level of engagement of the user to the video conference is below a given threshold of engagement for a minimum length of time, wherein the minimum length of time is automatically adjusted based on the confidence level in the level of engagement; and
enacting, by the process, one or more video conference privacy measures for the user within the video conference in response to the level of engagement being below the given threshold of engagement for the minimum length of time.
2 . The method as in claim 1 , wherein enacting the one or more video conference privacy measures is further based on a confidence of the level of engagement.
3 . The method as in claim 2 , wherein the confidence of the level of engagement is based on the one or more engagement indicators.
4 . The method as in claim 1 , wherein the level of engagement is based on the one or more engagement indicators selected from a group consisting of: user body presence; user face presence; user eye gaze direction; user distance; user hand gesture; empty seat presence; user body movement; user speaking level; and background noise.
5 . The method as in claim 1 , wherein the one or more video conference privacy measures are selected from a group consisting of: blurring user video input to the video conference; stopping user video input to the video conference; replacing user video input to the video conference; and muting user audio input to the video conference.
6 . The method as in claim 1 , wherein the one or more video conference privacy measures are user-configured.
7 . The method of claim 1 , wherein the minimum length of time is reduced from an original minimum length of time based on detected movement of the user toward an edge of a video frame.
8 . The method of claim 1 , wherein the confidence level is determined based on a predictive accuracy of the one or more engagement indicators.
9 . The method of claim 1 , further comprising:
ensuring that a person on camera at a device of the user is the user based on facial recognition.
10 . The method of claim 9 , wherein the level of engagement of the user is based on ensuring that the person is the user.
11 . The method of claim 10 , further comprising:
preventing one or both of video output or audio output from the video conference in response to the person not being the user.
12 . A tangible, non-transitory, computer-readable medium having computer-executable instructions stored thereon that, when executed by a processor on a computer, cause the computer to perform a method comprising:
analyzing real-time video of a user participating on a video conference;
determining, based on analyzing, a level of engagement of the user to the video conference;
determining a confidence level in an accuracy of the level of engagement based on one or more engagement indicators;
detecting that the level of engagement of the user to the video conference is below a given threshold of engagement for a minimum length of time, wherein the minimum length of time is automatically adjusted based on the confidence level in the level of engagement; and
enacting one or more video conference privacy measures for the user within the video conference in response to the level of engagement being below the given threshold of engagement for the minimum length of time.
13 . The method as in claim 12 , wherein enacting the one or more video conference privacy measures is further based on a confidence of the level of engagement.
14 . The method as in claim 13 , wherein the confidence of the level of engagement is based on the one or more engagement indicators.
15 . The method as in claim 12 , wherein the level of engagement is based on one or more engagement indicators selected from a group consisting of: user body presence; user face presence; user eye gaze direction; user distance; user hand gesture; empty seat presence; user body movement; user speaking level; and background noise.
16 . The method as in claim 12 , wherein the one or more video conference privacy measures are selected from a group consisting of: blurring user video input to the video conference; stopping user video input to the video conference; replacing user video input to the video conference; and muting user audio input to the video conference.
17 . The method of claim 12 , wherein the one or more video conference privacy measures are user-configured.
18 . The method of claim 12 , wherein the minimum length of time is reduced from an original minimum length of time based on detected movement of the user toward an edge of a video frame.
19 . The method of claim 12 , wherein the minimum length of time is automatically increased when the confidence level indicates a low predictive accuracy of the one or more engagement indicators and wherein the minimum length of time is automatically decreased when the confidence level indicates a high predictive accuracy of the one or more engagement.
20 . An apparatus, comprising:
one or more network interfaces to communicate with a network;
a processor coupled to the one or more network interfaces and configured to execute one or more processes; and
a memory configured to store a process that is executable by the processor, the process, when executed, configured to:
analyze real-time video of a user participating on a video conference;
determine, based on analyzing, a level of engagement of the user to the video conference;
determine a confidence level in an accuracy of the level of engagement based on one or more engagement indicators;
detect that the level of engagement of the user to the video conference is below a given threshold of engagement for a minimum length of time, wherein the minimum length of time is automatically adjusted based on the confidence level in the level of engagement; and
enact one or more video conference privacy measures for the user within the video conference in response to the level of engagement being below the given threshold of engagement for the minimum length of time.