| CPC H04N 7/15 (2013.01) [G06T 7/11 (2017.01); G06V 20/49 (2022.01); H04N 5/2628 (2013.01); H04N 5/278 (2013.01); G06T 2207/20132 (2013.01)] | 20 Claims |

|
1. A computer implemented method, comprising:
generating, by a sensor, a video stream that comprises a series of frames that each include a plurality of objects positioned within a conference environment;
determining the objects captured within at least one frame of the video stream;
assigning one or more croppings to each of the objects in the at least one frame of the video stream, wherein the assigning of the one or more croppings to each of the objects comprises:
determining a plurality of combinations of croppings that include at least one of the objects in the at least one frame; and
assigning a first cropping configuration to each of the determined croppings, wherein each of the assigned first cropping configurations include at least one object; and
adjusting each assigned first cropping configuration to determine a preferred cropping configuration for each of the determined croppings based on a cropping function, wherein the cropping function comprises two or more individual cropping loss values and a respective cropping weight for each of the two or more individual cropping loss values.
|