Active pane configuration during video conferences

1 . A computer-implemented method comprising:

joining, by a client device, a video conference hosted by a video conference provider, the video conference comprising a plurality of client devices;

receiving an indication of a selection of an active pane view;

in response to receiving the indication, displaying an active pane on a display of the client device, wherein the active pane displays a currently speaking video conference participant;

determining a location of a camera of the client device comprising converting the location of the camera to screen coordinates of the display; and

displaying the active pane on the display adjacent to the camera.

2 . The method of claim 1 , wherein determining the location of the camera comprises:

accessing system data to gather first information about a device model of the client device;

accessing a database storing second information about built-in camera physical locations for a plurality of device models to retrieve a built-in camera physical location for the device model of the client device; and

converting from the built-in camera physical location for the device model of the client device to screen coordinates on the client device adjacent to the built-in camera physical location.

3 . The method of claim 1 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect one or more perspective lines;

determining a physical location of the camera based on the one or more perspective lines;

converting from the physical location of the camera to screen coordinates on the client device adjacent to the physical location of the camera; and

displaying the active pane at the screen coordinates on the client device adjacent to the physical location of the camera.

4 . The method of claim 3 , wherein the captured video from the camera is analyzed by using a machine-learning model to detect the one or more perspective lines using at least one of edge detection, object detection, image segmentation, or image matting.

5 . The method of claim 3 , wherein analyzing the captured video from the camera to detect the one or more perspective lines comprises:

accessing a model expected environment;

determining one or more expected perspective lines based on the model expected environment;

comparing the one or more perspective lines with the one or more expected perspective lines;

determining a difference in orientation between the physical location of the camera and a model camera orientation in the model expected environment; and

determining the physical location of the camera capturing video based on the difference.

6 . The method of claim 1 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect a landmark;

determining the location of the landmark using a database; and

determining the location of the camera relative to the landmark based on at least one of a size, a shape, or a scale of the landmark.

7 . The method of claim 1 , wherein the location of the camera comprises proportions of a screen of the client device, wherein the proportions are converted to screen coordinates using a screen size of the client device.

8 . A system comprising:

one or more processors; and

one or more computer-readable storage media storing instructions which, when executed by the one or more processors, cause the one or more processors to perform operations including:

joining, by a client device, a video conference hosted by a video conference provider, the video conference comprising a plurality of client devices;

receiving an indication of a selection of an active pane view;

in response to receiving the indication, displaying an active pane on a display of the client device, wherein the active pane displays a currently speaking video conference participant;

determining a location of a camera of the client device comprising converting the location of the camera to screen coordinates of the display; and

displaying the active pane on the display adjacent to the camera.

9 . The system of claim 8 , wherein determining the location of the camera comprises:

accessing system data to gather first information about a device model of the client device;

accessing a database storing second information about built-in camera physical locations for a plurality of device models to retrieve a built-in camera physical location for the device model of the client device; and

converting from the built-in camera physical location for the device model of the client device to screen coordinates on the client device adjacent to the built-in camera physical location.

10 . The system of claim 8 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect one or more perspective lines;

determining a physical location of the camera based on the one or more perspective lines;

converting from the physical location of the camera to screen coordinates on the client device adjacent to the physical location of the camera; and

displaying the active pane at the screen coordinates on the client device adjacent to the physical location of the camera.

11 . The system of claim 10 , wherein the captured video from the camera is analyzed by using a machine-learning model to detect the one or more perspective lines using at least one of edge detection, object detection, image segmentation, or image matting.

12 . The system of claim 10 , wherein analyzing the captured video from the camera to detect the one or more perspective lines comprises:

accessing a model expected environment;

determining one or more expected perspective lines based on the model expected environment;

comparing the one or more perspective lines with the one or more expected perspective lines;

determining a difference in orientation between the physical location of the camera and a model camera orientation in the model expected environment; and

determining the physical location of the camera capturing video based on the difference.

13 . The system of claim 8 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect a landmark;

determining the location of the landmark using a database; and

determining the location of the camera relative to the landmark based on at least one of a size, a shape, or a scale of the landmark.

14 . The system of claim 8 , wherein the location of the camera comprises proportions of a screen of the client device, wherein the proportions are converted to screen coordinates using a screen size of the client device.

15 . A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to perform operations including:

joining, by a client device, a video conference hosted by a video conference provider, the video conference comprising a plurality of client devices;

receiving an indication of a selection of an active pane view;

in response to receiving the indication, displaying an active pane on a display of the client device, wherein the active pane displays a currently speaking video conference participant;

determining a location of a camera of the client device comprising converting the location of the camera to screen coordinates of the display; and

displaying the active pane on the display adjacent to the camera.

16 . The non-transitory computer-readable medium of claim 15 , wherein determining the location of the camera comprises:

accessing system data to gather first information about a device model of the client device;

accessing a database storing second information about built-in camera physical locations for a plurality of device models to retrieve a built-in camera physical location for the device model of the client device; and

converting from the built-in camera physical location for the device model of the client device to screen coordinates on the client device adjacent to the built-in camera physical location.

17 . The non-transitory computer-readable medium of claim 15 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect one or more perspective lines;

determining a physical location of the camera based on the one or more perspective lines;

converting from the physical location of the camera to screen coordinates on the client device adjacent to the physical location of the camera; and

displaying the active pane at the screen coordinates on the client device adjacent to the physical location of the camera.

18 . The non-transitory computer-readable medium of claim 17 , wherein the captured video from the camera is analyzed by using a machine-learning model to detect the one or more perspective lines using at least one of edge detection, object detection, image segmentation, or image matting.

19 . The non-transitory computer-readable medium of claim 17 , wherein analyzing the captured video from the camera to detect the one or more perspective lines comprises:

accessing a model expected environment;

determining one or more expected perspective lines based on the model expected environment;

comparing the one or more perspective lines with the one or more expected perspective lines;

determining a difference in orientation between the physical location of the camera and a model camera orientation in the model expected environment; and

determining the physical location of the camera capturing video based on the difference.

20 . The non-transitory computer-readable medium of claim 15 , wherein determining the location of the camera comprises:

analyzing captured video from the camera to detect a landmark;

determining the location of the landmark using a database; and

determining the location of the camera relative to the landmark based on at least one of a size, a shape, or a scale of the landmark.