Preventing the number of meeting attendees at a videoconferencing endpoint from becoming unsafe

A videoconferencing system comprising:

• at least one camera configured to capture a video feed corresponding to a geographic location;
• and
• at least one processor coupled to the at least one camera,
• wherein the processor is configured to:
• detect, based on data of the video feed, a presence of one or more persons corresponding to the geographic location;
• determine, based on the data of the video feed, a quantity of persons corresponding to the geographic location;
• determine that the quantity of persons corresponding to the geographic location exceeds a first predetermined threshold;
• render a first alert message responsive to determining that the quantity of persons corresponding to the geographic location exceeds the first predetermined threshold;
• determine that the quantity of persons corresponding to the geographic location exceeds a second predetermined threshold;
• render a second alert message responsive to determining that the quantity of persons corresponding to the geographic location exceeds the second predetermined threshold;
• and
• issuing a third alert message responsive to determining that the quantity of persons corresponding to the geographic location exceeds the second predetermined threshold,
• wherein the third alert message indicates that a room corresponding to the geographic location must be deep cleaned,
• wherein the first alert message comprises:
• a capacity message indicating that the quantity of persons corresponding to the geographic location exceeds the first predetermined threshold,
• wherein the plurality of key points corresponding to a first person of the one or more persons includes a hand key point and an elbow key point,
• wherein determining the quantity of persons corresponding to the geographic location comprises:
• detecting a plurality of key points corresponding to each of the one or more persons, and
• determining a gesture corresponding to each of the one or more persons based, at least in part, on the detected key points, and
• wherein determining the gesture corresponding to the first person comprises determining that the hand key point is above the elbow key point.

A non-transitory computer readable medium storing instructions executable by a processor, wherein the instructions comprise instructions to:

• capture a data stream using one or more cameras, the data stream comprising a plurality of frames;
• detect, in the data stream, data indicating a presence of one or more persons at a videoconferencing endpoint;
• determine a quantity of persons corresponding to the videoconferencing endpoint based on the data indicating the presence of one or more persons at the videoconferencing endpoint;
• determine that the quantity of persons corresponding to the videoconferencing endpoint exceeds a first predetermined threshold;
• render a first alert message responsive to determining that the quantity of persons corresponding to the videoconferencing endpoint exceeds the first predetermined threshold;
• determine that the quantity of persons corresponding to the videoconferencing endpoint exceeds a second predetermined threshold;
• render a second alert message responsive to determining that the quantity of persons corresponding to the videoconferencing endpoint exceeds the second predetermined threshold;
• and
• issue a third alert message responsive to determining that the quantity of persons corresponding to the geographic location exceeds the second predetermined threshold, wherein the third alert message indicates that a room corresponding to the geographic location must be deep cleaned,
• wherein the first alert message comprises:
• a capacity message indicating that the quantity of persons corresponding to the geographic location exceeds the first predetermined threshold,
• wherein determining the quantity of persons corresponding to the videoconferencing endpoint comprises:
• detecting a plurality of key points corresponding to each of the one or more persons, and
• determining a gesture corresponding to each of the one or more persons based, at least in part, on the detected key points, and
• wherein determining at least one gesture corresponding to at least one of the persons comprises determining that a hand key point is above an elbow key point.