Volume adjustment based on listener position

1. A method of regulating volume, the method comprising:

receiving a stream of depth images generated by an arbitrarily-placed depth camera imaging a three-dimensional world space from a singular vantage point;

recognizing from the stream of depth images a position of a listener in the three-dimensional world space;

tracking a position of the listener within the three-dimensional world space in a plurality of depth images;

for each of one or more speakers within the three-dimensional world space, identifying in the plurality of depth images a three-dimensional position physically indicated by the listener and recognizing that three-dimensional position as the three-dimensional position of that speaker;

tracking a position of a listener relative to each of the one or more speakers within the three-dimensional world space;

for each of the one or more speakers, assessing a changing distance between that speaker and the listener in the three-dimensional world space; and

automatically adjusting a volume of each of the one or more speakers in real-time based on a current distance between each respective speaker and the listener.

2. The method of claim 1 , where assessing the changing distance between that speaker and the listener includes calculating a distance between the position of that speaker and the position of the listener at two or more different times.

3. The method of claim 1 , where automatically adjusting the volume of that speaker includes adjusting an audio output level as a function of the current distance.

4. The method of claim 3 , where automatically adjusting the volume of that speaker includes exponentially adjusting an audio output level as a function of the current distance.

5. The method of claim 3 , where automatically adjusting the volume of that speaker includes linearly adjusting an audio output level as a function of the current distance.

6. The method of claim 1 , where identifying the three-dimensional position for each of the one or more speakers includes, for each speaker:

emitting an audio signal configured to cause that speaker to produce a test sound;

tracking a position of a moving microphone within the three-dimensional world space in a plurality of depth images; and

for each of a plurality of different positions of the moving microphone, correlating that position with a volume of the test sound as perceived by the microphone at that position.

7. A method of regulating volume, the method comprising:

receiving a stream of depth images generated by an arbitrarily-placed depth camera imaging a three-dimensional world space from a singular vantage point of a scene;

recognizing from the stream of depth images a listener in the depth image;

tracking a position of the listener within the three-dimensional world space in a plurality of depth images;

for each of a plurality of surround sound speakers within the three-dimensional world space, identifying in the plurality of depth images a three-dimensional position physically indicated by the listener and recognizing that three-dimensional position as the three-dimensional position of that speaker;

assessing a distance between the three-dimensional position of the listener and the three-dimensional position of each of the plurality of surround sound speakers; and

automatically setting a volume of each of the plurality of surround sound speakers based on the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

8. The method of claim 7 , where automatically setting the volume of each of the plurality of surround sound speakers includes adjusting an audio output level for that speaker as a function of the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

9. The method of claim 7 , where automatically setting the volume of each of the plurality of surround sound speakers includes exponentially adjusting an audio output level for that speaker as a function of the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

10. The method of claim 7 , where automatically setting the volume of each of the plurality of surround sound speakers includes linearly adjusting an audio output level for that speaker as a function of the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

11. A computing system, comprising:

an audio output configured to send an audio signal to a speaker or amplifier;

a depth camera input configured to receive depth information useable to construct a depth image;

a logic subsystem operatively connected to the audio output and the depth camera; and

a data-holding subsystem holding instructions executable by the logic subsystem to:

receive a stream of depth images generated by an arbitrarily-placed depth camera imaging a three-dimensional world space from a singular vantage point;

recognize a listener in the stream of depth images;

identify from the stream of depth images a three-dimensional position of the listener in the three-dimensional world space;

for each of one or more speakers within the three-dimensional world space, identify from the plurality of depth images a three-dimensional position physically indicated by the listener and recognizing that three-dimensional position as the three-dimensional position of that speaker;

assess a distance between the three-dimensional position of the listener and the three-dimensional position of that speaker; and

automatically set a level of the audio signal based on the distance between the three-dimensional position of the listener and the three-dimensional position of the speaker.

12. The computing system of claim 11 , where the audio output is one of a plurality of surround sound audio outputs, each surround sound audio output configured to send an audio signal to a different surround sound speaker.

13. The computing system of claim 11 , where the data-holding subsystem holds instructions executable by the logic subsystem to automatically set the level of the audio signal as an exponential function of the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

14. The computing system of claim 11 , where the data-holding subsystem holds instructions executable by the logic subsystem to automatically set the level of the audio signal as a linear function of the distance between the three-dimensional position of that speaker and the three-dimensional position of the listener.

15. The computing system of claim 11 , further comprising a microphone, and where the data-holding subsystem holds instructions executable by the logic subsystem to cause the audio output to emit an audio signal configured to cause the speaker to produce a test sound; track a position in a three-dimensional world space of the microphone in a plurality of depth images from the depth camera; and for each of a plurality of positions of the microphone, correlate a perceived volume of the audio signal with the position of the microphone.

16. The computing system of claim 11 , where the depth camera includes a time-of-flight depth camera.

17. The computing system of claim 11 , where the depth camera includes a structured light depth camera.

18. The computing system of claim 11 , where the depth camera includes stereo depth cameras.