Enhancement of audio captured by multiple microphones at unspecified positions
Embodiments disclosed herein provide systems, methods, and computer readable media for steering a camera and enhancing audio captured by microphones at unspecified positions. In a particular embodiment, a method provides receiving audio captured by the plurality of microphones at a location and receiving video captured of a scene that includes the plurality of microphones captured by a first camera at a first camera position. The method further provides identifying the plurality of microphones in the scene and determining physical positions of the plurality of microphones at the location relative to the first camera position. The method then provides adjusting the audio based on the physical positions of the plurality of microphones.
1. A method of determining positions of a plurality of microphones, the method comprising:
receiving audio captured by the plurality of microphones at a location;
receiving video captured of a scene that includes the plurality of microphones captured by a first camera at a first camera position, wherein the plurality of microphones each include a visual feature with known dimensions;
identifying the plurality of microphones in the scene using image recognition on the video to identify the visual feature of each microphone of the plurality of microphones;
determining physical positions of the plurality of microphones at the location relative to the first camera position by, at least in part, calculating a distance from the first camera for each of the plurality of microphones based on movement of the visual feature and the known dimensions; and
adjusting the audio based on the physical positions of the plurality of microphones.
2. The method of claim 1 , further comprising:
identifying a speaker in the audio;
determining a first physical position of the speaker based on the physical positions of the plurality of microphones; and
adjusting a video camera to feature the first physical position.
3. The method of claim 2 , wherein determining a first physical position of the speaker comprises:
determining a time difference between when each of the plurality of microphones captured a portion of the audio from the speaker.
4. The method of claim 1 , wherein the movement comprises rotational movement.
5. The method of claim 4 , wherein the visual feature comprises a T shaped element and the rotational movement comprises a spinning of the T shaped element.
6. The method of claim 1 , wherein the first camera comprises a three dimensional (3D) camera, and wherein determining the physical positions of the plurality of microphones comprises:
deriving the physical positions of the plurality of microphones from depth information provided by the 3D camera.
7. The method of claim 1 , further comprising:
determining second physical positions of the plurality of microphones at the location; and
adjusting the audio based on the second physical positions of the plurality of microphones.
8. The method of claim 1 further comprising:
receiving second video captured of a second scene that includes the plurality of microphones captured by a second camera at a second camera position;
identifying the plurality of microphones in the second scene;
determining second physical positions of the plurality of microphones at the location relative to the second camera position; and
adjusting the audio based on the second physical positions of the plurality of microphones.
9. An audio management system for determining positions of a plurality of microphones, the audio management system comprising:
a communication interface configured to receive audio captured by the plurality of microphones at a location and receive video captured of a scene that includes the plurality of microphones captured by a first camera at a first camera position, wherein the plurality of microphones each include a visual feature with known dimensions;
a processing system configured to identify the plurality of microphones in the scene using image recognition on the video to identify the visual feature of each microphone of the plurality of microphones, determine physical positions of the plurality of microphones at the location relative to the first camera position by, at least in part, calculating a distance from the first camera for each of the plurality of microphones based on movement of the visual feature and the known dimensions, and adjust the audio based on the physical positions of the plurality of microphones.
10. The audio management system of claim 9 , further comprising:
the processing system configured to identify a speaker in the audio, determine a first physical position of the speaker based on the physical positions of the plurality of microphones, and adjust a video camera to feature the first physical position.
11. The audio management system of claim 10 , wherein the processing system configured to determine a first physical position of the speaker comprises:
the processing system configured to determine a time difference between when each of the plurality of microphones captured a portion of the audio from the speaker.
12. The audio management system of claim 9 , wherein the movement comprises rotational movement.
13. The audio management system of claim 12 , wherein the visual feature comprises a T shaped element and the rotational movement comprises a spinning of the T shaped element.
14. The audio management system of claim 9 , wherein the first camera comprises a three dimensional (3D) camera, and wherein the processing system configured to determine the physical positions of the plurality of microphones comprises:
the processing system configured to derive the physical positions of the plurality of microphones from depth information provided by the 3D camera.
15. The audio management system of claim 9 , further comprising:
the processing system configured to determine second physical positions of the plurality of microphones at the location and adjust the audio based on the second physical positions of the plurality of microphones.
16. The audio management system of claim 9 further comprising:
receiving second video captured of a second scene that includes the plurality of microphones captured by a second camera at a second camera position;
identifying the plurality of microphones in the second scene;
determining second physical positions of the plurality of microphones at the location relative to the second camera position; and
adjusting the audio based on the second physical positions of the plurality of microphones.