Method and system for adapting a CP layout according to interaction between conferees
A system and method is disclosed for adapting a continuous presence videoconferencing layout according to interactions between conferees. Using regions of interest found in video images, the arrangement of images of conferees may be dynamically arranged as displayed by endpoints. Arrangements may be responsive to various metrics, including the position of conferees in a room and dominant conferees in the videoconference. Video images may be manipulated as part of the arrangement, including cropping and mirroring the video image. As interactions between conferees change, the layout may be automatically rearranged responsive to the changed interactions.
1. A method, comprising:
designing a continuous presence video image automatically for a first endpoint of a continuous presence videoconference responsive to an interaction between a plurality of conferees, comprising:
determining automatically an interaction between a first conferee and a second conferee of the plurality of conferees;
positioning a first video image corresponding to the first conferee in the continuous presence video image; and
positioning a second video image corresponding to the second conferee relative to the first video image in the continuous presence video image, responsive to the interaction between the first conferee and the second conferee; and
displaying the continuous presence video image at the first endpoint of the continuous presence videoconference.
2. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
receiving content from an endpoint corresponding to the first conferee; and
presenting the content in the continuous presence video image,
wherein the act of positioning a first video image comprises:
positioning the first video image on a first side of the content, and
wherein the act of positioning a second video image comprises:
positioning the second video image on a second side of the content.
3. The method of claim 2 , further comprising:
processing the first video image and the second video image such that the first conferee and the second conferee are presented looking toward the content.
4. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
generating instructions for a first endpoint of the continuous presence videoconference for creating the continuous presence video image at the first endpoint responsive to the interaction between the first conferee and the second conferee;
sending the instructions to the first endpoint of the continuous presence videoconference; and
creating the continuous presence video image at the first endpoint responsive to the instructions.
5. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
creating the continuous presence video image for the first endpoint responsive to the interaction between the first conferee and the second conferee; and
sending the continuous presence video image to the first endpoint.
6. The method of claim 1 , further comprising:
designing a continuous presence video image for a second endpoint of the continuous presence videoconference automatically responsive to the interaction between the plurality of conferees, the continuous presence video image for the second endpoint different from the continuous presence video image for the first endpoint; and
displaying the continuous presence video image for the second endpoint at the second endpoint of the continuous presence videoconference.
7. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
analyzing a first video image corresponding to the first conferee of the plurality of conferees; and
analyzing a second video image corresponding to the second conferee of the plurality of conferees; and
wherein determining automatically an interaction between the first conferee and the second conferee comprises determining the interaction responsive to the act of analyzing a first video image and the act of analyzing a second video image.
8. The method of claim 7 , further comprising:
sending the continuous presence video image for the first endpoint to the first endpoint.
9. The method of claim 7 , further comprising:
generating instructions for creating the continuous presence video image for the first endpoint; and
sending the instructions for creating the continuous presence video image for the first endpoint to the first endpoint.
10. The method of claim 7 , wherein the act of designing a continuous presence video image further comprises:
modifying the first video image responsive to the interaction between the first conferee and the second conferee.
11. The method of claim 10 , wherein the act of modifying the first video image comprises:
mirroring the first video image.
12. The method of claim 1 ,
wherein determining automatically an interaction between a first conferee and a second conferee comprises:
determining a dominant conferee of the plurality of conferees; and
determining a non-dominant conferee of the plurality of conferees; and
wherein positioning a first video image corresponding to the first conferee in the continuous presence video image comprises:
positioning automatically a first video image corresponding to the dominant conferee in the continuous presence video image, and
wherein positioning a second video image corresponding to the second conferee relative to the first video image comprises:
positioning automatically a second video image corresponding to the non-dominant conferee relative to the first video image in the continuous presence video image.
13. The method of claim 1 ,
wherein the act of designing a continuous presence video image further comprises:
designing a first continuous presence video image automatically responsive to a first interaction between the plurality of conferees; and
designing a second continuous presence video image automatically responsive to a second interaction between the plurality of conferees subsequent to the first interaction, and
wherein the act of displaying the continuous presence video image comprises:
displaying the first continuous presence video image; and
displaying the second continuous presence video image subsequent to the first continuous presence video image.
14. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
analyzing a first audio energy corresponding to the first conferee of the plurality of conferees;
analyzing a second audio energy corresponding to the second conferee of the plurality of conferees; and
wherein determining automatically an interaction between the first conferee and the second conferee comprises determining the interaction responsive to the act of analyzing a first audio energy and the act of analyzing a second audio energy.
15. The method of claim 1 , wherein the act of designing a continuous presence video image further comprises:
identifying a first relative location of a first region of interest within a first video image corresponding to the first conferee of the plurality of conferees;
identifying a second relative location of a second region of interest within a second video image corresponding to the second conferee of the plurality of conferees; and
wherein determining automatically an interaction between a first conferee and a second conferee comprises
determining an interaction between the first conferee and the second conferee responsive to the first relative location of the first region of interest within the first video image and the second relative location of the second region of interest within the second video image.
16. The method of claim 1 , wherein positioning a second video image corresponding to the second conferee relative to the first video image in the continuous presence video image comprises:
positioning a first video image corresponding to a first conferee relative to a second video image corresponding to a second conferee so that the first conferee and the second conferee appear to be facing each other.
17. The method of claim 16 , wherein the act of designing a continuous presence video image further comprises:
mirroring the first video image.
18. The method of claim 16 , further comprising:
designating a conferee of the plurality of conferees at a first site as an active conferee;
copying an image of the active conferee from a video image received from the first site; and
presenting the image of the active conferee and the video image received from the first site in the continuous presence video image.
19. The method of claim 16 , further comprising:
designating a conferee of the plurality of conferees at a first site as an active conferee;
copying an image of the active conferee from a video image received from the first site; and
presenting the image of the active conferee in the continuous presence video image instead of the video image received from the first site.
20. A videoconferencing system, comprising:
a plurality of endpoints, comprising:
a first endpoint, corresponding to a first conferee; and
a second endpoint, corresponding to a second conferee; and
a layout controller adapted to design a continuous presence video image responsive to an interaction between the first conferee and the second conferee, wherein the layout controller is adapted to:
determine automatically an interaction between the first conferee and the second conferee;
position a first video image corresponding to the first conferee in the continuous presence video image; and
position a second video image corresponding to the second conferee relative to the first video image in the continuous presence video image, responsive to the interaction between the first conferee and the second conferee.
21. The videoconferencing system of claim 20 , wherein the layout controller is a module of a multipoint control unit (MCU).
22. The videoconferencing system of claim 20 , further comprising:
an editor module adapted to manipulate a first video image received from the first endpoint and a second video image responsive to the layout controller.
23. The videoconferencing system of claim 20 , wherein the layout controller is further adapted to send instructions for displaying the continuous presence video image designed by the layout controller to the plurality of endpoints.
24. The videoconferencing system of claim 20 , further comprising:
a video module adapted to encode the continuous presence video image responsive to the layout controller.
25. The videoconferencing system of claim 20 , further comprising:
a video layout editor module, adapted to position in the continuous presence video image a first video image corresponding to the first conferee and a second video image corresponding to the second conferee relative to the first video image, responsive to the layout controller.
26. The videoconferencing system of claim 25 , wherein the video layout editor module is further adapted to manipulate the first video image.
27. The videoconferencing system of claim 25 , wherein the video layout editor module is further adapted to mirror the first video image.
28. The videoconferencing system of claim 20 , further comprising:
an interaction decoder, adapted to detect the interaction between the first conferee and the second conferee and to inform the layout controller of the interaction.
29. The videoconferencing system of claim 28 , wherein the interaction decoder comprises a video interaction decoder adapted to identify a relative location of a region of interest in a first video image corresponding to the first conferee.
30. The videoconferencing system of claim 28 , wherein the interaction decoder is adapted to detect that the first conferee is a dominant conferee.
31. The videoconferencing system of claim 28 , wherein the interaction decoder comprises an audio interaction decoder adapted to analyze audio energy and to inform the layout controller of the interaction responsive to the audio energy.
32. The videoconferencing system of claim 20 , wherein the layout controller is adapted to design the continuous presence video image so that the first conferee and the second conferee appear to be facing each other.
33. An apparatus for processing a first video image from a first endpoint corresponding to a first conferee in a continuous presence video conference and a second video image from a second endpoint corresponding to a second conferee in the continuous presence video conference, comprising:
a control module adapted to design a continuous presence video conference video image responsive to an interaction between the first conferee and the second conferee, wherein the control module is adapted to:
determine automatically an interaction between the first conferee and the second conferee;
position a first video image corresponding to the first conferee in the continuous presence video image; and
position a second video image corresponding to the second conferee relative to the first video image in the continuous presence video image, responsive to the interaction between the first conferee and the second conferee; and
a first video module adapted to create the continuous presence video conference video image designed by the control module.
34. The apparatus of claim 33 , further comprising:
an interaction decoder, adapted to detect the interaction between the first conferee and the second conferee and to inform the control module of the interaction.
35. The apparatus of claim 34 , wherein the interaction decoder is a video interaction decoder, adapted to identify a relative location of a region of interest in the first video image.
36. The apparatus of claim 34 , wherein the interaction decoder is an audio interaction decoder, adapted to analyze a first audio energy corresponding to the first conferee and a second audio energy corresponding to the second conferee.
37. The apparatus of claim 34 , wherein the interaction decoder is adapted to detect that the first conferee is a dominant conferee.
38. The apparatus of claim 33 , wherein the apparatus is a multipoint control unit.
39. The apparatus of claim 33 , wherein the first video module is associated with the first endpoint.
40. The apparatus of claim 33 , further comprising:
an editor module adapted to manipulate the first video image responsive to the control module.
41. The apparatus of claim 40 , wherein the editor module is adapted to mirror the first video image responsive to the control module.