Region of interest-based frame rate adjustment
Frame rates for rendering video streams depicting conference participants within a physical space are adjusted based on motion detected with respect to those conference participants. Regions of interest are identified within an initial video stream captured by a video capture device. The video capture device is caused to capture, at an initial frame rate, video streams each associated with a different one of the regions of interest. An adjusted frame rate for a region of interest of the regions of interest is determined based on information associated with content depicted within the region of interest. A frame rate of a video stream of the video streams is then adjusted from the initial frame rate to the adjusted frame rate, in which the video stream is associated with the region of interest.
1. A method, comprising:
causing, during a video conference wherein a video capture device captures an initial video stream depicting multiple conference participants, the video capture device to capture, at an initial frame rate, a first video stream limited to a first region of interest of the initial video stream and a second video stream limited to a second region of interest of the initial video stream, wherein the first region of interest depicts a first conference participant of the multiple conference participants and the second region of interest depicts a second conference participant of the multiple conference participants;
determining, based on detected movement information of the first conference participant within the first video stream relative to detected movement information of the second conference participant within the second video stream, a first adjusted frame rate for increasing the initial frame rate for the first video stream and a second adjusted frame rate for decreasing the initial frame rate for the second video stream; and
causing the video capture device to capture the first video stream at the first adjusted frame rate and the second video stream at the second adjusted frame rate.
2. The method of claim 1 , wherein the detected movement information of the first conference participant corresponds to motion information for video data associated with the first region of interest meeting a pixel threshold.
3. The method of claim 1 , wherein the detected movement information of the first conference participant corresponds to motion information for video data associated with the first region of interest meeting a temporal threshold.
4. The method of claim 1 , wherein frame rates for other video streams associated with other regions of interest remain unchanged in connection with the capture of the first video stream at the first adjusted frame rate and the capture of the second video stream at the second adjusted frame rate.
5. The method of claim 1 , comprising:
further adjusting one or both of the first adjusted frame rate or the second adjusted frame rate on a periodic basis during a conference.
6. The method of claim 1 , comprising:
further adjusting the first adjusted frame rate based on an event detected in connection with the first conference participant.
7. A non-transitory computer readable medium storing instructions operable to cause one or more processors to perform operations comprising:
causing, during a video conference wherein a video capture device captures an initial video stream depicting multiple conference participants, the video capture device to capture, at an initial frame rate, a first video stream limited to a first region of interest of the initial video stream and a second video stream limited to a second region of interest of the initial video stream, wherein the first region of interest depicts a first conference participant of the multiple conference participants and the second region of interest depicts a second conference participant of the multiple conference participants;
determining, based on detected movement information of the first conference participant within the first video stream relative to detected movement information of the second conference participant within the second video stream, a first adjusted frame rate for increasing the initial frame rate for the first video stream and a second adjusted frame rate for decreasing the initial frame rate for the second video stream; and
causing the video capture device to capture the first video stream at the first adjusted frame rate and the second video stream at the second adjusted frame rate.
8. The non-transitory computer readable medium of claim 7 , wherein the detected movement information of the first conference participant is different from the detected movement information of the second conference participant.
9. The non-transitory computer readable medium of claim 7 , wherein the first adjusted frame rate is based on profile information associated with the first conference participant.
10. The non-transitory computer readable medium of claim 7 , wherein the detected movement information of the first conference participant corresponds to at least one of an amount of spatial motion detected within the first region of interest or an amount of temporal motion detected within the first region of interest.
11. The non-transitory computer readable medium of claim 7 , wherein one or both of the first adjusted frame rate or the second adjusted frame rate is further adjusted incrementally during the video conference according to network bandwidth.
12. An apparatus, comprising:
a memory; and
a processor configured to execute instructions stored in the memory to:
cause, during a video conference wherein a video capture device captures an initial video stream depicting multiple conference participants, the video capture device to capture, at an initial frame rate, a first video stream limited to a first region of interest of the initial video stream and a second video stream limited to a second region of interest of the initial video stream, wherein the first region of interest depicts a first conference participant of the multiple conference participants and the second region of interest depicts a second conference participant of the multiple conference participants;
determine, based on detected movement information of the first conference participant within the first video stream relative to detected movement information of the second conference participant within the second video stream, a first adjusted frame rate for increasing the initial frame rate for the first video stream and a second adjusted frame rate for decreasing the initial frame rate for the second video stream; and
cause the video capture device to capture the first video stream at the first adjusted frame rate and the second video stream at the second adjusted frame rate.
13. The apparatus of claim 12 , wherein, to cause the video capture device to capture the first video stream at the first adjusted frame rate and the second video stream at the second adjusted frame rate, the processor is configured to execute the instructions to:
adjust a frame rate of the first video stream from the initial frame rate to the first adjusted frame rate; and
adjust a frame rate of the second video stream from the initial frame rate to the second adjusted frame rate.
14. The apparatus of claim 12 , wherein, to determine the first adjusted frame rate, the processor is configured to execute the instructions to:
evaluate the detected movement information of the first conference participant against at least one of a pixel threshold or a temporal threshold.
15. The apparatus of claim 12 , wherein, to determine the first adjusted frame rate, the processor is configured to execute the instructions to:
determine to increase or decrease a frame rate of the first video stream from the initial frame rate to the first adjusted frame rate based on the detected movement information of the first conference participant.
16. The apparatus of claim 12 , wherein the first adjusted frame rate is determined based on the detected movement information of the first conference participant and based on historical conference participation data associated with the first conference participant.
17. The apparatus of claim 12 , wherein the first adjusted frame rate is determined based on the detected movement information of the first conference participant and based on priority status information associated with the first conference participant.
18. The apparatus of claim 12 , wherein the processor is configured to execute the instructions to:
incrementally update one or both of the first adjusted frame rate or the second adjusted frame rate on a periodic basis according to network information.
19. The method of claim 1 , wherein the first video stream depicts the first conference participant for use in a first user interface tile of a conferencing software user interface and the second video stream depicts the second conference participant for use in a second user interface tile of the conferencing software user interface, wherein the first adjusted frame rate is higher than the second adjusted frame rate such that motions of the first conference participant in the first user interface tile have a similar fluidity appearance to motions of the second conference participant in the second user interface tile.
20. The apparatus of claim 12 , wherein the first video stream depicts the first conference participant for use in a first user interface tile of a conferencing software user interface and the second video stream depicts the second conference participant for use in a second user interface tile of the conferencing software user interface.