Automatic voice tracking camera system and method of operation

• US 6,731,334 B1
• Filed: 07/31/1995
• Issued: 05/04/2004
• Est. Priority Date: 07/31/1995
• Status: Expired due to Term

• Current Assignee: Cisco Technology, Inc. (Cisco Systems, Inc.)
• Original Assignee: Forgent Networks (Asure Software)
• Inventors: Maeng, Joonyoul, Williams, Errol R.
• Primary Examiner(s): MOE, AUNG SOE
• Application Number:
  US08/509,228
• Time in Patent Office: 3,200 Days
• Field of Search: H04/N.714, H04/N.715, 348/13, 348/14, 348/15, 348/211, 348/14.01, 348/14.07, 348/14.11, 348/14.08, 348/211.99, 348/211.1, 348/211.4, 348/211.9, 348/211.11, 348/211.12, 381/92
• US Class Current: 348/211.12
• CPC Class Codes: G01S 3/7864 T.V. type tracking systems
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display

Abstract

An automatic voice tracking camera system (12) is provided. System (12) includes a camera (18) operable to receive control signals for controlling a view of the camera (18). A microphone array (14) comprises a plurality of microphones. The microphone array (14) is operable to receive a voice of a speaker and to provide an audio signal representing the voice. A beamformer (30) coupled to the microphone array (14). The beamformer (30) is operable to receive the audio signal, to generate from the audio signal speaker position data representing a position of the speaker, and to provide the speaker position data. A camera controller (36) is coupled to the beamformer (30) and to the camera (18). The camera controller (36) is operable to receive the speaker position data and to determine an appropriate responsive camera movement The camera controller (36) is further operable to generate camera control signals and to provide the camera control signals to the camera (18) such that the view of the camera (18) automatically tracks the position of the speaker.

Claims

1. An automatic voice tracking camera system, comprising:

a first camera operable to receive control signals for controlling a view of the first camera;

a microphone array comprising a plurality of microphones, the microphone array operable to receive a voice of a speaker and to provide an audio signal representing the voice;

a beamformer coupled to the microphone array, the beamformer operable to receive the audio signal, to generate from the audio signal speaker position data representing a position of the speaker as coordinates for a point in space, and to provide the speaker position data; and

a camera controller coupled to the beamformer and to the first camera, the camera controller operable;

to receive the speaker position data,

to determine a responsive camera movement based upon changes of greater than a predetermined amount in the coordinates for the point in space indicative of sneaker position changes, to generate camera control signals based upon the responsive camera movement, and

to provide the camera control signals to the first camera such that the view of the first camera automatically tracks the position of the speaker.

2. The automatic voice tracking camera system of claim 1, further comprising a second camera coupled to the camera controller, the second camera operable to receive control signals for automatically controlling a view of the second camera.

3. The automatic voice tracking camera system of claim 2, wherein the camera controller is further operable to move the second camera to view a new speaker position at a new point in space while the first camera is active and to switch to the second camera after the new speaker is viewed by the second camera.

4. The automatic voice tracking camera system of claim 2, wherein the camera controller is further operable to move the first camera to view a new speaker position at a new point in space when the new speaker position is outside of a first window and inside of a second window defined with respect to a current speaker position.

5. The automatic voice tracking camera system of claim 2, wherein the camera controller is further operable to move the second camera to view a new speaker position at a new point in space when the new speaker position is outside of a first and second window defined with respect to a current speaker position.

6. The automatic voice tracking camera system of claim 2, wherein the camera controller is further operable to associate the first camera and the second camera each with one of a plurality of zones and to only move the first camera and the second camera to view the speaker position if the speaker position is in the associated zone.

7. The automatic voice tracking camera system of claim 6, wherein said camera controller is further operable to associate said first camera and said second camera each with said plurality of zones such that each of said plurality of zones is sized according to the zoom setting on said first camera and said second camera.

8. The automatic voice tracking camera system of claim 2, wherein said first camera comprises a wide-angle camera and said second camera comprises a pan-tilt-zoom camera and further wherein said camera controller further comprises a camera controlling mechanism for controlling the said wide-angle camera to move from a first object focus to a second object focus, and further for directing said pan-tilt-zoom camera to reach said second object focus.

9. The automatic voice tracking camera system of claim 1, wherein the camera controller is further operable to continue to view a new speaker position at a new point in space with the first camera when the new speaker position is inside of a first window defined with respect to a current speaker position.

10. The automatic voice tracking camera system of claim 1, wherein the camera controller is further operable to filter the speaker position data to delay movement of the first camera until a new speaker position is verified.

11. The automatic voice tracking camera system of claim 10, wherein the camera controller is operable to filter the speaker position data by storing and averaging a plurality of temporary speaker positions.

12. An automatic camera controller for automatically controlling a camera to track a position of a speaker, the automatic camera controller comprising:

a camera controller operable;

to receive speaker position data representing the position of the speaker as coordinates for a point in space,

to determine a speaker position change if changes in the coordinates exceed a predetermined amount;

to determine an appropriate responsive camera movement based upon the speaker position change determination,

to generate camera control signals based upon the appropriate responsive camera movement, and

to provide the camera control signals to at least one camera such that a view of the at least one camera automatically tracks the position of the speaker; and

an interface coupled to the camera controller, the interface operable to communicate with a host video conference system and with the camera controller.

13. The automatic camera controller of claim 12, wherein the camera controller is further operable to move a second camera to view a new speaker position at a new point in space while a first camera is active and to switch to the second camera after the new speaker is viewed by the second camera.

14. The automatic camera controller of claim 12, wherein the camera controller is further operable to continue to view a new speaker position at a new point in space with the first camera when the new speaker position is inside of a first window defined with respect to a current speaker position.

15. The automatic camera controller of claim 12, wherein the camera controller is further operable to move a first camera to view a new speaker position at a new point in space when the new speaker position is outside of a first window and inside of a second window, said first window and said second window defined with respect to a current speaker position.

16. The automatic camera controller of claim 12, wherein the camera controller is further operable to move a second camera to view the new speaker position when the new speaker position is outside of a first and a second window defined with respect to a current speaker position.

17. The automatic camera controller of claim 12, wherein the camera controller is further operable to filter the speaker position data to delay movement of a camera until a new speaker position is verified.

18. The automatic camera controller of claim 17, wherein the camera controller is operable to filter the speaker position data by storing and averaging a plurality of temporary speaker positions.

19. The automatic camera controller of claim 12, wherein the camera controller is further operable to associate a first camera and a second camera each with one of a plurality of zones and to only move the first camera and the second camera to view the speaker position if the speaker position is in the associated zone.

20. A method of automatically controlling a camera to track a position of a speaker using a voice of the speaker, comprising:

receiving a voice of the speaker and providing an audio signal representing the voice;

processing the audio signal to generate speaker position data representing the position of the speaker as coordinates for a point in space;

determining a speaker position change if changes in the coordinates exceed a predetermined amount;

determining an appropriate responsive camera movement from the speaker position data based upon the speaker position change determination;

generating camera control signals based upon the appropriate responsive camera movement; and

providing the camera control signals to a first camera such that a view of the first camera automatically tracks the position of the speaker.

21. The method of claim 20, further comprising:

generating camera control signals to move a second camera to view a new speaker position at a new point in space while the first camera is active; and

switching to the second camera after the new speaker position is viewed by the second camera.

22. The method of claim 20, wherein determining an appropriate responsive camera movement comprises moving the first camera to view a new speaker position at a new point in space only when the new speaker position is outside of a first window and inside of a second window, said first window and said second window each defined with respect to a current speaker position.

23. The method of claim 20, wherein determining an appropriate responsive camera movement further comprises moving a second camera to view a new speaker position when the new speaker position is outside of a first and a second window defined with respect to a current speaker position.

24. The method of claim 20, wherein determining an appropriate responsive camera movement comprises filtering the speaker position data to delay movement of the first camera until a new speaker position is verified.

25. The method of claim 24, wherein determining an appropriate responsive camera movement further comprises filtering the speaker position data by storing and averaging a plurality of temporary speaker positions.

26. The method of claim 25, wherein the plurality of temporary speaker positions comprises three temporary speaker positions.

27. The method of claim 20, wherein determining an appropriate responsive camera movement comprises associating the first camera and a second camera each with one of a plurality of zones and only moving the first camera and the second camera to view the speaker position if the speaker position is in the associated zone.

28. The method of claim 20, wherein generating camera control signals further comprises generating zoom control from a host computer as an altered zoom set up configuration for controlling the camera.

29. The method of claim 20, wherein processing the audio signal further comprises generating on and off control signals from a host computer for the automatic tracking control of the speaker.

30. The method of claim 20, further comprising processing the audio signal representing the voice and the speaker position data for determining an offset between the camera and the microphone array by capturing the speaker while talking.