Normalized images for cameras

• US 20070019066A1
• Filed: 06/30/2005
• Published: 01/25/2007
• Est. Priority Date: 06/30/2005
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Cutler, Ross
• Granted Patent: US 7,576,766 B2
• Time in Patent Office: Days
• US Class Current: 348/14.80
• CPC Class Codes: H04N 23/698 for achieving an enlarged field of view, e.g. panoramic image capture
• CPC Class Codes: H04N 5/2628 Alteration of picture size, shape, position or orientation, e.g. zooming, rotation, rolling, perspective, translation
• CPC Class Codes: H04N 7/142 Constructional details of the terminal equipment, e.g. arrangements of the camera and the display

Abstract

A method and system for producing normalized images of conference participants so that the participants appear to be approximately the same size when the images are displayed is provided. The normalizing system normalizes the size of images based on constraints relating to the distance of participants from the location of the camera. To normalize the image of a participant, the system zooms the camera to account for the distance of the participant from the camera.

Claims

1. A method in a computer system for normalizing the size of images of participants in a video comprising:

providing a set of constraints relating to the locations of participants; and

generating an image of a participant having a size adjusted to account for the location of the participant as indicated by the provided constraints.

2. The method of claim 1 wherein the constraints describe a table around which the participants are located.

3. The method of claim 1 wherein generating the image includes factoring in a change in the orientation of the camera after the constraints are provided.

4. The method of claim 1 wherein the camera is a virtual camera.

5. The method of claim 4 wherein the virtual camera operates on a panoramic image of the participants received from a panoramic camera.

6. The method of claim 5 wherein the generated image is a subset of the panoramic image created by at least one of cropping or scaling the panoramic image.

7. The method of claim 1 wherein the camera is a non-panoramic camera.

8. The method of claim 7 wherein generating the image includes at least one of panning, tilting, or zooming the camera.

9. The method of claim 1 including automatically positioning the camera to point to a participant who is currently speaking.

10. The method of claim 9 wherein the speaking participant is detected by using a microphone.

11. The method of claim 1 wherein positioning the camera includes detecting an edge of the table and using the edge as the bottom position of the generated image.

12. The method of claim 1 wherein receiving the set of constraints includes automatically detecting the constraints.

13. A computer-readable medium containing instructions for controlling a computer system to perform a method for normalizing the size of images of participants in a video conference by a method comprising:

capturing a first image from a panoramic camera; and

generating a second image from the first image of a participant having a size based on a layout of a table on which the panoramic camera is located.

14. The computer-readable medium of claim 13 wherein the layout of the table describes the distance from the camera to an edge of the table.

15. The computer-readable medium of claim 13 wherein the method includes automatically positioning the camera to point to a participant who is currently speaking.

16. The computer-readable medium of claim 15 wherein the speaking participant is detected by using a microphone.

17. The computer-readable medium of claim 15 wherein positioning the camera includes detecting an edge of the table and sizing the second image to exclude the edge.

18. The computer-readable medium of claim 13 wherein generating the second image includes factoring in a change in the orientation of the camera after the table layout is determined.

19. A data signal conveying an image generated by positioning a camera on a participant and generating an image of the participant having a size adjusted to account for an estimated location of the participant as indicated by constraints on the location of the participant.

20. The data signal of claim 19 wherein the participant is a participant who is currently speaking.