Systems and methods for automatic detection of meeting regions and framing of meeting participants within an environment

A video conferencing camera configured to generate a video output representative of an environment, the video conferencing camera comprising:

• at least one video processing unit configured to:
• determine, for a plurality of subjects represented in the video output, whether each of the plurality of subjects is inside or outside of a meeting region within the environment based on a determination of whether each of the plurality of subjects resides within a spatial envelope with predetermined dimensions;
• determine a frame configuration for a primary video stream, constituting a portion of the video output, to be shown on a display based on one or more characteristics of at least one subject, among the plurality of subjects, determined to be located inside the meeting region;
• and
• in determining the frame configuration for the primary video stream, ignore one or more subjects, among the plurality of subjects, determined to be located outside the meeting region.

A video conferencing camera configured to generate a video output representative of an environment, the video conferencing camera comprising:

• at least one video processing unit configured to:
• determine, for a plurality of subjects represented in the video output, whether each of the plurality of subjects is inside or outside of a meeting region within the environment based on an output of a trained neural network, wherein the trained neural network receives as input at least one frame of the video output and outputs an indication of whether each of the plurality of subjects resides on a side of a glass wall opposite to the video conferencing camera;
• determine a frame configuration for a primary video stream, constituting a portion of the video output, to be shown on a display based on one or more characteristics of at least one subject, among the plurality of subjects, determined to be located inside the meeting region;
• and
• in determining the frame configuration for the primary video stream, ignore one or more subjects, among the plurality of subjects, determined to be located outside the meeting region.

A video conferencing camera configured to generate a video output representative of an environment, the video conferencing camera comprising:

• at least one video processing unit configured to:
• determine, for a plurality of subjects represented in the video output, whether each of the plurality of subjects is inside or outside of a meeting region within the environment based on an output of a trained neural network, wherein the trained neural network receives as input at least one frame of the video output and outputs an indication of whether each of the plurality of subjects resides within a spatial envelope of predetermined dimensions;
• determine a frame configuration for a primary video stream, constituting a portion of the video output, to be shown on a display based on one or more characteristics of at least one subject, among the plurality of subjects, determined to be located inside the meeting region;
• and
• in determining the frame configuration for the primary video stream, ignore one or more subject, among the plurality of subjects, determined to be located outside the meeting region.

A video conferencing camera configured to generate a video output representative of an environment, the video conferencing camera comprising:

• at least one video processing unit configured to:
• determine, for a plurality of subjects represented in the video output, whether each of the plurality of subjects is inside or outside of a meeting region within the environment based on a distance measurement representative of a distance between each of the plurality of subjects and the video conferencing camera;
• determine a frame configuration for a primary video stream, constituting a portion of the video output, to be shown on a display based on one or more characteristics of at least one subject, among the plurality of subjects, determined to be located inside the meeting region;
• and
• in determining the frame configuration for the primary video stream, ignore one or more subjects, among the plurality of subjects, determined to be located outside the meeting region.

A video conferencing camera configured to generate a video output representative of an environment, the video conferencing camera comprising:

• at least one video processing unit configured to:
• determine, for a plurality of subjects represented in the video output, whether each of the plurality of subjects is inside or outside of a meeting region within the environment based on a participant score determined for each of the plurality of subjects, wherein the participant score for each particular subject, among the plurality of subjects, is based on a combination of a determined location for the particular subject, a determined motion associated with the particular subject, and a detected interaction between the particular subject and at least one other subject among the plurality of subjects;
• determine a frame configuration for a primary video stream, constituting a portion of the video output, to be shown on a display based on one or more characteristics of at least one subject, among the plurality of subjects, determined to be located inside the meeting region;
• and
• in determining the frame configuration for the primary video stream, ignore one or more subjects, among the plurality of subjects, determined to be located outside the meeting region.