Automatic camera selection for videoconferencing
View Patent ↗In videoconference camera selection, audio inputs associated with cameras for a videoconference are each processed into first and second audio energies respectively for first and second frequency ranges. The selection then determines which of the audio inputs has a greatest ratio of the first audio energy to the second audio energy and selects the associated camera view for outputting video for the videoconference. The selection can also process video inputs from the cameras either alone or in combination with the audio processing. Either way, the selection processes each of the video inputs for at least one facial characteristic and determines which of the video inputs has a greatest likelihood of framing a human face. In the end, the selection selects the associated camera view for outputting video for the videoconference based at least in part on this video-based determination.
1. A videoconference camera selection method, comprising:
obtaining a plurality of audio inputs for a videoconference, each of the audio inputs associated with one of a plurality of camera views;
processing each of the audio inputs into first audio energy for a first frequency range and into second audio energy for a second frequency range, the first frequency range being higher than the second frequency range;
determining which of the audio inputs has a greatest ratio of the first audio energy relative to the second audio energy;
selecting the camera view associated with the audio input having the greatest ratio; and
outputting video of the selected camera view for the videoconference.
2. The method of claim 1 , wherein the first frequency range is greater than a threshold of about 2500 Hz, and wherein the second frequency range is less than the threshold.
3. The method of claim 1 , wherein processing each of the audio inputs into the first audio energy for the first frequency range comprises using the first frequency range of about 4000 Hz to about 7000 Hz.
4. The method of claim 3 , wherein processing each of the audio inputs into the second audio energy of the second frequency range comprises using the second frequency range of about 500 Hz to about 1000 Hz.
5. The method of claim 1 , further comprising detecting audio indicative of speech as a prerequisite to processing each of the audio inputs.
6. The method of claim 1 , wherein selecting the associated camera view comprises switching for output from one of the camera views to another of the camera views.
7. The method of claim 1 , further comprising adjusting one or more of a pan, a tilt, and a zoom of the selected camera view.
8. The method of claim 1 , further comprising:
obtaining a plurality of video inputs, each of the video inputs associated with one of the camera views;
processing each of the video inputs for at least one facial characteristic; and
determining which of the video inputs has a greatest likelihood of framing a human face based on the processing,
wherein selecting the camera view is based at least in part on the camera view associated with the video input having the greatest likelihood.
9. The method of claim 8 , wherein the at least one facial characteristic is selected from the group consisting of a human facial feature, a tone indicative of human skin, a motion indicative of a human, and a combination thereof.
10. The method of claim 1 , wherein the camera views are associated with a plurality of arbitrarily arranged cameras.
11. The method of claim 10 , wherein each of the audio inputs comprise one or more microphones associated by proximity to at least one of the cameras.
12. The method of claim 1 , wherein the camera views are associated with at least one controllable camera.
13. A program storage device having program instructions stored thereon for causing a programmable control device to perform a videoconference camera selection method, the method comprising:
obtaining a plurality of audio inputs for a videoconference, each of the audio inputs associated with one of a plurality of camera views;
processing each of the audio inputs into first audio energy for a first frequency range and into second audio energy for a second frequency range, the first frequency range being higher than the second frequency range;
determining which of the audio inputs has a greatest ratio of the first audio energy relative to the second audio energy;
selecting the camera view associated with the audio input having the greatest ratio; and
outputting video of the selected camera view for the videoconference.
14. A videoconferencing apparatus, comprising:
a video interface receiving video inputs of a plurality of camera views;
an audio interface receiving audio inputs, each of the audio inputs associated with one of the camera views;
a network interface communicatively coupling to a network; and
a processing unit operatively coupled to the video, audio, and network interfaces, the processing unit programmed to:
process each of the audio inputs into a first audio energy for a first frequency range and into a second audio energy for a second frequency range, the first frequency range being higher than the second frequency range,
determine which of the audio inputs has a greatest ratio of the first audio energy relative to the second audio energy,
select the camera view associated the audio input having the greatest ratio, and
output the video input of the selected camera view with the network interface.
15. The apparatus of claim 14 ,
wherein the processing unit is programmed to:
process each of the video inputs for at least one facial characteristic, and
determine which of the video inputs has a greatest likelihood of framing a human face based on the processing; and
wherein the selection of the camera view is based at least in part on the camera view associated with the video input having the greatest likelihood.
16. The apparatus of claim 14 , further comprising a plurality of arbitrarily arranged cameras communicatively coupled to the video interface and each associated with one of the camera views.
17. The method of claim 16 , further comprising a plurality of microphones communicatively coupled to the audio interface and each associated by proximity to at least one of the arbitrarily arranged cameras.
18. A videoconferencing apparatus, comprising:
at least one controllable camera for obtaining video with a directed view;
at least one microphone for obtaining audio; and
a processing unit operatively coupled to the at least one controllable camera and the at least one microphone, the processing unit programmed to:
process the audio from the at least one microphone into a first audio energy for a first frequency range and into a second audio energy for a second frequency range, the first frequency range being greater than the second frequency range,
determine a ratio of the first audio energy to the second audio energy, and
control the directed view of the at least one controllable camera based on the determined ratio.
19. The program storage device of claim 13 , wherein the first frequency range is greater than a threshold of about 2500 Hz, and wherein the second frequency range is less than the threshold.
20. The program storage device of claim 13 , wherein processing each of the audio inputs into the first audio energy for the first frequency range comprises using the first frequency range of about 4000 Hz to about 7000 Hz.
21. The program storage device of claim 20 , wherein processing each of the audio inputs into the second audio energy of the second frequency range comprises using the second frequency range of about 500 Hz to about 1000 Hz.
22. The program storage device of claim 13 , further comprising detecting audio indicative of speech as a prerequisite to processing each of the audio inputs.
23. The program storage device of claim 13 , wherein selecting the associated camera view comprises switching for output from one of the camera views to another of the camera views.
24. The program storage device of claim 13 , further comprising adjusting one or more of a pan, a tilt, and a zoom of the selected camera view.
25. The program storage device of claim 13 , further comprising:
obtaining a plurality of video inputs, each of the video inputs associated with one of the camera views;
processing each of the video inputs for at least one facial characteristic; and
determining which of the video inputs has a greatest likelihood of framing a human face based on the processing,
wherein selecting the camera view is based at least in part on the camera view associated with the video input having the greatest likelihood.
26. The program storage device of claim 25 , wherein the at least one facial characteristic is selected from the group consisting of a human facial feature, a tone indicative of human skin, a motion indicative of a human, and a combination thereof.
27. The apparatus of claim 14 , wherein the first frequency range is greater than a threshold of about 2500 Hz, and wherein the second frequency range is less than the threshold.
28. The apparatus of claim 14 , wherein to process each of the audio inputs into the first audio energy for the first frequency range, the processing unit is programmed to use the first frequency range of about 4000 Hz to about 7000 Hz.
29. The apparatus of claim 27 , wherein to process each of the audio inputs into the second audio energy of the second frequency range, the processing unit is programmed to use the second frequency range of about 500 Hz to about 1000 Hz.
30. The apparatus of claim 14 , wherein the processing unit is further programmed to detect audio indicative of speech as a prerequisite to processing each of the audio inputs.
31. The apparatus of claim 14 , wherein to select the associated camera view, the processing unit is programmed to switch for output from one of the camera views to another of the camera views.
32. The apparatus of claim 14 , wherein the processing unit is further programmed to adjust one or more of a pan, a tilt, and a zoom of the selected camera view.
33. The apparatus of claim 14 , wherein the at least one facial characteristic is selected from the group consisting of a human facial feature, a tone indicative of human skin, a motion indicative of a human, and a combination thereof.