Camera-view acoustic fence
Determining the angle of sound relative to the centerline of a microphone array. The angle of the centerline of a camera field-of-view (FoV) and the angle of the camera FoV is determined. Knowing the angle from the centerline of the microphone array of the particular sound and then the angle of the centerline of the camera FoV and angles of the camera FoV allows a determination if the sound is inside the FoV of the camera. If so, the microphones are unmuted. If not, the microphones are muted. As the camera zooms or pans, the changes in camera FoV and centerline angle are computed and used with the sound angle, so that the muting and unmuting occurs automatically as the camera zoom and pan angle change.
1. A method for selecting audio to be transmitted in a videoconference,
the method comprising:
reviewing, by a processing unit, an output of a microphone for sound;
providing, by the processing unit from a camera having a field-of-view (FoV), an image from the camera;
determining, by the processing unit, whether or not the sound originates from within the FoV of the camera;
muting, by the processor, the microphone when the processing unit determines that the sound does not originate from within the FoV of the camera; and
unmuting, by the processor, the microphone when the processing unit determines that the sound originates from within the FoV of the camera,
wherein the camera includes a centerline, and
wherein determining if whether or not the sound originates within the FoV of the camera includes:
using a microphone array and sound source localization (SSL) to determine an angle of the sound; and
determining whether or not the sound originates within the FoV of the camera based on the determined SSL sound angle and the centerline and the FoV of the camera.
2. The method of claim 1 , wherein the microphone array and the camera physically pan in synchronization.
3. The method of claim 1 , wherein the pan axes of the microphone array and the camera are displaced.
4. The method of claim 1 , wherein the microphone array and the camera are fixed in position and the camera uses electronic pan and zoom.
5. The method of claim 1 ,
wherein determining whether or not the sound originates within the FoV of the camera includes:
evaluating the image from the camera for the presence of individuals;
evaluating, in the image, each of the individuals for lip movement;
determining that the sound originates from within the FoV of the camera when lip movement is found for any of the individuals; and
determining that the sound does not originate from within the FoV of the camera when no lip movement is found for any of the individuals.
6. The method of claim 5 ,
wherein determining whether or not the sound originates within the FoV of the camera further includes:
determining that sound is present but no lip movement is found for any of the individuals;
using the microphone array and sound source localization (SSL) to determine the angle of the sound when sound is present but no lip movement is found for any of the individuals; and
determining when the sound originates within the FoV of the camera based on the determined SSL sound angle and the camera centerline and the FoV of the camera when sound is present but no lip movement is found for any of the individuals.
7. A videoconferencing device comprising:
a camera to provide an image, the camera having a field-of-view (FoV) and a centerline;
a microphone to receive sound and provide an audio signal to be transmitted in the videoconference;
a network interface to provide videoconference streams to at least one far site;
a processor coupled to the camera, the microphone and the network interface;
a microphone array, coupled to the processor, and providing audio output signals to the processor; and
memory coupled to the processor, the memory store programs executed by the processor,
wherein the processor is to perform, by executing programs and operations, videoconferencing operations of:
determining whether or not sound is present in the audio signal from the microphone;
determining whether or not the sound originates from within the FoV of the camera;
muting the microphone when the processor determines that the sound does not originate from within the FoV of the camera; and
unmuting the microphone when the processor determines that the sound originates from within the FoV of the camera,
wherein determining whether or not the sound originates within the FoV of the camera includes:
using the audio output signals from the microphone array to perform sound source localization (SSL) to determine an angle of the sound; and
determining when the sound originates within the FoV of the camera based on the determined SSL sound angle and the centerline and the FoV of the camera.
8. The videoconferencing device of claim 7 , wherein the microphone array and the camera physically pan in synchronization.
9. The videoconferencing device of claim 7 , wherein the pan axes of the microphone array and the camera are displaced.
10. The videoconferencing device of claim 7 , wherein the microphone array and the camera are fixed in position and the camera uses electronic pan and zoom.
11. The videoconferencing device of claim 7 ,
wherein determining whether or not the sound is within the FoV of the camera includes:
evaluating the image from the camera for the presence of individuals;
evaluating each individual for lip movement;
determining that the sound does originate within the FoV of the camera when lip movement is found for any individual; and
determining that the sound does not originate within the FoV of the camera when no lip movement is found for any individual.
12. The videoconferencing device of claim 11 , the videoconferencing device further comprising:
a microphone array providing audio output signals coupled to the processor,
wherein the camera includes a centerline, and
wherein determining whether or not the sound originates within the FoV of the camera further includes:
determining that sound is present but no lip movement is found for any individual;
using a microphone array and sound source localization (SSL) to determine an angle of the sound when sound is present but no lip movement is found for any individual; and
determining whether or not the sound originates within the FoV of the camera based on the determined SSL sound angle and the camera centerline and the FoV of the camera when sound is present but no lip movement is found for any individual.
13. A non-transitory processor readable memory containing programs that when executed cause a processor to perform the following method of selecting audio to be transmitted in a videoconference,
the method comprising:
reviewing an output of a microphone for sound;
providing an image from a camera, the camera having a field-of-view (FoV) and a centerline;
determining whether or not the sound originates from within the FoV of the camera;
muting the microphone when the processor determines that the sound does not originate from within the FoV of the camera; and
unmuting the microphone when the processor determines that the sound originate from within the FoV of the camera,
wherein determining whether or not the sound originates within the FoV of the camera includes:
using audio signal outputs from a microphone array and sound source localization (SSL) to determine an angle of the sound; and
determining whether or not the sound originates within the FoV of the camera based on the determined SSL sound angle and the centerline and the FoV of the camera.
14. The non-transitory processor readable memory of claim 13 , wherein the microphone array and the camera physically pan in synchronization.
15. The non-transitory processor readable memory of claim 13 , wherein the pan axes of the microphone array and the camera are displaced.
16. The non-transitory processor readable memory of claim 13 , wherein the microphone array and the camera are fixed in position and the camera uses electronic pan and zoom.
17. The non-transitory processor readable memory of claim 13 , wherein determining whether or not the sound originates within the FoV of the camera includes:
evaluating the image from the camera for the presence of individuals;
evaluating each individual for lip movement;
determining that the sound does originate within the FoV of the camera when lip movement is found for any individual; and
determining that the sound does not originate within the FoV of the camera when no lip movement is found for any individual.