Voice-following video system

• US 5,844,599 A
• Filed: 08/06/1997
• Issued: 12/01/1998
• Est. Priority Date: 06/20/1994
• Status: Expired due to Term

• Current Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Hildin, John J.
• Primary Examiner(s): Woo, Stella
• Application Number:
  US08/906,822
• Time in Patent Office: 482 Days
• Field of Search: 348/15, 348/14, 348/16, 348/17, 348/18, 348/19, 348/20, 348/169, 348/214, 348/162, 348/164, 379/202, 379/204, 379/205, 379/203, 379/93.17, 379/93.21
• US Class Current: 348/14.1
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display
• CPC Class Codes: H04N 7/15 Conference systems
• CPC Class Codes: H04N 7/18 Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast

Abstract

A voice-following video system for dynamically capturing the view of an active speaker includes a video camera, a position control system for the video camera, and one or more voice-activated emitters. A voice-activated emitter is associated with each potential speaker. As a person talks, the associated voice-activated emitter transmits a position signal. The position control system uses the position signal as a beacon to determine the location of the active speaker. The position control system then adjusts the pan and/or tilt of the video camera to bring the active speaker into the field of view and tracks that person'"'"'s movements. In this manner, as one person stops speaking and another starts, the video camera is automatically repositioned, capturing the view of the active speaker.

Claims

1. A system comprising:

a video camera;

a plurality of sound-activated position signal generators that indicate locations of the position signal generators by emitting respective position signals only when corresponding sound signals are detected, and not emitting the position signals when the corresponding sound signals are not detected, each of the position signal generators including;

a sound detector that detects a sound signal, and

a position signal emitter coupled to the sound detector that emits a position signal only when the sound detector detects the sound signal;

a position signal detector capable of detecting the position signals from any of the position signal generators; and

a video camera positioning device that points the video camera in a direction of a position signal detected by the position signal detector, the positioning device positioning the video camera to follow the locations of the position signal generators as the locations of the position signal generators change.

2. The system of claim 1, wherein the sound detector detects the sound signal by comparing a magnitude of the sound signal with a threshold value and by generating an active signal when the magnitude of the sound signal exceeds the threshold value, the active signal indicating that the sound signal is a voice signal, and the position signal emitter emitting the position signal when the active signal is generated.

3. The system of claim 2, wherein the sound detector comprises:

a microphone that receives the sound signal;

an amplifier coupled to the microphone that amplifies the received sound signal; and

a thresholding device coupled to the amplifier, wherein the thresholding device performs said comparing.

4. The system of claim 3, wherein the thresholding device includes a band pass filter that is tuned to select only sound signal frequencies in a human voice frequency band.

5. The system of claim 1, wherein said position signal emitter comprises an infrared light emitter emitting an infrared beam as the position signal.

6. The system of claim 1, wherein each of the position signal generators further includes a position signal modulator coupled to the sound detector and the position signal emitter, the modulator modulating the sound signal onto the position signal to generate a modulated position signal, the modulated position signal being emitted by the position signal emitter.

7. The system of claim 6, wherein the modulator modulates the position signal by first modulating a carrier signal based on the sound signal and then modulating the position signal based on the modulated carrier signal.

8. The system of claim 6 further comprising a demodulator coupled to the positioning device, the demodulator demodulating the modulated position signal received by the positioning device to reproduce the sound signal.

9. The system of claim 1, wherein each of the position signal generators further includes a position signal modulator coupled to the sound detector and the position signal emitter, the modulator modulating the sound signal and the position signal to generate a modulated position signal wherein the sound signal is carried by the position signal, the modulated position signal being emitted by the position signal emitter.

10. The system of claim 1, wherein the video camera positioning device comprises:

a controller coupled to the position signal detector that detects the locations of the position signal generators based on the position signals and generates a control signal based on the locations of the position signal generators; and

a servo-controller coupled to the controller that positions the video camera based on the control signal in such a way that when each of the position signal generators is attached to an object, that object is maintained in a field of view of the video camera.

11. A system for controlling a video camera, comprising:

a plurality of sound-activated position signal generators, the position signal generators emitting position signals to indicate locations of respective position signal generators only when corresponding sound signals are detected and not emitting the position signals when the corresponding sound signals are not detected, each of the position signal generators including;

a) a sound detector that detects the sound signal, and

b) a position signal emitter emitting the position signal only when the sound detector detects sound signal;

a position signal detector capable of detecting the position signals from any of the position signal generators; and

a video camera positioning device that points the video camera in a direction of a position signal detected by the position signal detector, the positioning device positioning the video camera to follow one of the locations of the position signal generators as the one of the locations of the position signal generators changes.

12. The system of claim 11, wherein the sound detector detects the sound signal by comparing a magnitude of the sound signal with a threshold value, when the magnitude of the sound signal exceeds the threshold value, the sound detector generating an active signal, and receiving the sound signal as a voice signal, the position signal emitter of each of the position signal generators emitting the position signal only when the active signal is generated.

13. The system of claim 11, wherein the positioning device selects one of the position signal generators based on the emitted position signals, the positioning device positioning the video camera to follow a location of the selected one of the position signal generators, the positioning device maintaining an object attached to the selected one of the position signal generators in a field of view of the video camera.

14. The system of claim 13, wherein the positioning device selects the one of the position signal generators based on a priority system.

15. The system of claim 14, wherein the positioning device filters the emitted position signals to remove short bursts of the emitted position signals, the priority system directing the positioning device to select one of the filtered emitted position signals that is first detected by the position signal detector.

16. The system of claim 11, wherein each of the position signal generators further includes a position signal modulator coupled to the sound detector, the modulator modulating the position signal based on the sound signal to generate a modulated position signal, the position signal emitter emitting the modulated position signal.

17. The system of claim 16 further comprising a demodulator coupled to the positioning device, the demodulator demodulating the modulated position signal emitted by the selected one of the position signal generators to reproduce a sound signal that corresponds to the selected one of the position signal generators.

18. The system of claim 16, wherein the modulator modulates the position signal by first modulating a carrier signal based on the sound signal and then modulating the position signal based on the modulated carrier signal.

19. The system of claim 11, wherein the position signal emitter comprises an infrared light emitting source for emitting the position signal.

20. A system that automatically positions a video camera to follow an active speaker, comprising:

position signal emitting means for emitting position signals only when corresponding voice signals of active speakers are detected and not emitting the position signals when the corresponding voice signals of the active speakers are not detected, the position signal emitting means including;

a) sound signal detecting means for detecting a voice signal of an active speaker,

b) emitting means coupled to the sound signal detecting means for emitting the position signals only when the sound signal detecting means detects the voice signal of the active speaker;

position signal detecting means for detecting any of the position signals; and

video camera positioning means for pointing the video camera in a direction of a position signal detected by the position signal detection means and for maintaining the active speaker in a field of view of the video camera by tracking the position signal as a location of the position signal changes.

21. A method for operating a system that controls a video camera, the method comprising:

receiving emitted position signals which were emitted by position signal generators only when the position signal generators detected sound signals;

detecting the emitted position signals emitted from any of the position signal generators; and

pointing the video camera in a direction of a position signal detected by the detecting step such that the video camera is positioned to follow a location of one of the position signal generators as the location of one of the position signal generators changes.

22. The method of claim 21, further comprising detecting the sound signals using sound detectors of the position signal generators, and emitting a position signal when a sound signal is detected by one of the position signal generators.

23. The method of claim 22, wherein the detecting step comprises:

comparing a magnitude of the sound signals with a threshold value;

generating an active signal corresponding to the sound signals that exceed the threshold value; and

characterizing the sound signals that exceed the threshold value as voice signals.

24. The method of claim 23, wherein the position signals correspond to the voice signals.

25. The method of claim 21, further comprising:

selecting one of the position signal generators based on the emitted position signals;

tracking a position signal emitted by the selected one of the position signal generators; and

maintaining an object attached to the selected one of the position signal generators in a field of view of the video camera.

26. The method of claim 25, wherein the selecting step comprises selecting the one of the position signal generators based on a priority system.

27. The method of claim 26, further comprising filtering the emitted position signals to remove short bursts of the emitted position signals, wherein the selecting step selects one of the position signal generators that 1) emitted a position signal, 2) corresponds to one of the filtered emitted position signals, and 3) corresponds to a position signal which is first detected by the detecting the emitted position signals step.

28. The method of claim 21, further comprising modulating position signals of the position signal generators to generate modulated position signals, and emitting the modulated position signals.

29. The method of claim 28, further comprising demodulating one of the modulated position signals that was emitted by a selected one of the position signal generators to reproduce a demodulated sound signal.

30. The method of claim 28, wherein the modulating step comprises:

modulating carrier signals based on the sound signals; and

modulating the position signals based on the modulated carrier signals.

31. The method of claim 21, wherein each of the position signal generators includes an infrared light emitting source for emitting the emitted position signals.

32. A system for use with a video camera, comprising:

a plurality of position signal generators that indicate locations of the position signal generators by emitting respective position signals only when sense signals are input to the position signal generators, each of the position signal generators including;

a detector that detects a sense signal, and

a position signal emitter coupled to the detector that emits a position signal only when the detector detects the sense signal;

a position signal detector capable of detecting position signals from any of the position signal generators; and

a video camera positioning device that points the video camera in a direction of one of the position signals detected by the position signal detector, the positioning device positioning the video camera to follow a location of one of the position signal generators as the location changes.

33. The system of claim 32, wherein the position signal emitter comprises an infrared light emitter emitting an infrared beam as the position signal.

34. The system of claim 32, wherein each of the position signal generators further includes a position signal modulator coupled to the detector and the position signal emitter, the modulator modulating the position signal based on the sense signal to generate a modulated position signal, the modulated position signal being emitted by the position signal emitter.

35. The system of claim 34, wherein the modulator modulates the position signal by first modulating a carrier signal based on the sense signal and then modulating the position signal based on the modulated carrier signal.

36. The system of claim 35, further comprising a demodulator coupled to the positioning device, the demodulator demodulating the modulated position signal received by the positioning device through the position signal detector to reproduce the sense signal.

37. The system of claim 32, wherein the video camera positioning device comprises:

a controller coupled to the position signal detector that determines the locations of the position signal generators based on the position signals and generates a control signal based on a location of one of the position signal generators; and

a servo-controller coupled to the controller that positions the video camera based on the control signal in such a way that when the one of the position signal generators is attached to an object, that object is maintained in a field of view of the video camera.

38. A method for operating a system that controls a video camera, the method comprising:

receiving emitted position signals which were emitted by position signal generators only when sensory inputs are detected;

detecting the emitted position signals from any of the position signal generators; and

pointing the video camera in a direction of a position signal detected by the detecting step such that the video camera is positioned to follow a location of one of the position signal generators as the location changes.

39. The method of claim 38, further comprising:

selecting one of the position signal generators based on the emitted position signals;

tracking a position signal emitted by the selected one of the position signal generators; and

maintaining an object attached to the selected one of the position signal generators in a field of view of the video camera.

40. The method of claim 38, further comprising modulating the position signals to generate modulated position signals, and emitting the modulated position signals.

41. The method of claim 40, further comprising demodulating one of the modulated position signals that was emitted by the selected one of the position signal generators to reproduce a demodulated sensory input signal.

42. The method of claim 38, wherein the position signal generators include an infrared light emitting source for emitting the position signals.