CAPTURE DEVICE MOVEMENT COMPENSATION FOR SPEAKER INDEXING

• US 20090002477A1
• Filed: 06/29/2007
• Published: 01/01/2009
• Est. Priority Date: 06/29/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Cutler, Ross G.
• Granted Patent: US 8,330,787 B2
• Time in Patent Office: Days
• US Class Current: 348/14.100
• CPC Class Codes: G06V 20/40 in video content extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44
• CPC Class Codes: H04N 23/6812 based on additional sensors, e.g. acceleration sensors
• CPC Class Codes: H04N 7/147 Communication arrangements, e.g. identifying the communication as a video-communication, intermediate storage of the signals selecting H04Q

Abstract

Embodiments of the invention compensate for the movement of a meeting capture device during a live meeting when performing speaker indexing of a recorded meeting. In one example, a first position of a capture device is determined. A second position of the capture device is determined after the capture device has been moved from the first position to the second position. The movement data associated with movement of the capture device from the first position to the second position is determined. The movement data is outputted and used in speaker indexing of the recorded meeting.

Claims

1. A method, comprising:

determining a first position of a capture device;

determining a second position of the capture device after the capture device has been moved from the first position to the second position;

determining movement data associated with movement of the capture device from the first position to the second position; and

outputting the movement data.

2. The method of claim 1 wherein the first and second positions are determined by comparing at least a portion of a first image captured at the first position by the capture device to at least a portion of a second image captured at the second position by the capture device.

3. The method of claim 2 wherein the first and second images are compared using stationary points in the first and second images.

4. The method of claim 2 wherein the first and second images are compared using stationary edges in first and second edge images corresponding to the first and second images.

5. The method of claim 2 wherein the first and second images are compared using object modeling in the first and second images.

6. The method of claim 1 wherein the first and second positions are determined using at least one of a magnetometer or an accelerometer at the capture device.

7. The method of claim 1, further comprising applying the movement data to speaker indexing of an audio/video recording captured by the capture device.

8. The method of claim 7 wherein applying the movement data includes correcting for at least one of azimuthal movement or translational movement of the capture device that occurred during the capture of the audio/video recording.

9. The method of claim 7 wherein applying the movement data includes restarting the speaker indexing at the time in the audio/video recording when the capture device movement is detected.

10. The method of claim 9 wherein applying the movement data includes merging a first speaker indexing determined before the capture device movement with a second speaker indexing determined after the capture device movement, wherein a speaker in the first speaker indexing is matched to the same speaker in the second speaker indexing.

11. The method of claim 7 wherein the speaker indexing is used to display speaker segmentation in a meeting timeline of a client user interface, wherein the meeting timeline includes a timeline for each speaker identified in the audio/video recording.

12. The method of claim 11 wherein play speed for each speaker in the timeline is individually selectable.

13. A method, comprising:

determining a first position of a capture device from an audio/video recording made with the capture device;

determining a second position of the capture device from the audio/video recording after the capture device has been moved from the first position to the second position;

determining movement data associated with movement of the capture device from the first position to the second position; and

outputting the movement data.

14. The method of claim 13 wherein the first and second positions are determined by comparing a first stationary point in the first image captured at the first position to a second stationary point, corresponding the first stationary point, in the second image captured at the second position.

15. The method of claim 13 wherein the first and second images are compared using stationary edges in first and second edge images corresponding to the first and second images.

16. The method of claim 13 wherein the first and second images are compared using a table model of a table in the first and second images, wherein the capture device is positioned on the table.

17. A method for detecting movement of a capture device for speaker indexing, comprising:

detecting movement of the capture device by an accelerometer at the capture device;

determining an amount of translational movement of the capture device by the accelerometer; and

outputting the amount of translational movement determined by the accelerometer.

18. The method of claim 17, further comprising:

measuring a first azimuth of the capture device by a magnetometer at the capture device when movement of the capture device is detected by the accelerometer;

measuring a second azimuth of the capture device by the magnetometer when the accelerometer detects the movement of the capture device has stopped; and

determining an amount of azimuthal movement between the first azimuth and the second azimuth.

19. The method of claim 18, further comprising:

determining an amount of azimuthal movement of the capture device by the accelerometer;

outputting the amount of azimuthal movement determined by the accelerometer when the amount of azimuthal movement determined by the magnetometer is not substantially equal to the amount of azimuthal movement determined by the accelerometer; and

outputting the amount of azimuthal movement determined by the magnetometer when the amount of azimuthal movement determined by the magnetometer is substantially equal to the amount of azimuthal movement determined by the accelerometer.

20. The method of claim 17, further comprising:

determining an amount of azimuthal movement of the capture device by the accelerometer; and

outputting the amount of azimuthal movement determined by the accelerometer.

21. The method of claim 17, further comprising:

applying the amount of translational movement to speaker indexing of an audio/video recording captured by the capture device.