Method and apparatus for face recognition enhanced video mixing

• US 8,184,141 B2
• Filed: 02/04/2008
• Issued: 05/22/2012
• Est. Priority Date: 02/04/2008
• Status: Active Grant

• Current Assignee: RingCentral Incorporated
• Original Assignee: Siemens Enterprise Communications, Inc. (Atos SE)
• Inventors: Caspi, Rami, Beyda, William J.
• Primary Examiner(s): Kuntz, Curtis
• Assistant Examiner(s): El-Zoobi, Maria
• Application Number:
  US12/012,622
• Publication Number:
  US 20090195638A1
• Time in Patent Office: 1,569 Days
• Field of Search: 348 1401- 1409, 348 1411- 1413, 382/118, 382/248, 358/85, 709/204, 370260-261, 725/135, 725/37, 725/141, 725/106, 725115-116
• US Class Current: 348/14.01
• CPC Class Codes: H04N 5/272 Means for inserting a foreground image in a background image, i.e. inlay, outlay
• CPC Class Codes: H04N 7/152 Multipoint control units therefor

Abstract

A telecommunications system includes a network; a plurality of user devices coupled to the network; a multipoint control unit coupled to the network and configured to supervise multipoint conferencing among the plurality of user devices, the multipoint control unit including a presentation mixer, the presentation mixer configured to remove one or more backgrounds from a presentation and mix a live video feed into the presentation as a substitute background; a screen for displaying a resulting mixed presentation such that a full area of the screen is used to display the mixed presentation; and a feature recognition system configured to identify a party from one or more features displayed on the screen and selectively adjust a transparency of said one or more features other than said party.

Claims

1. A telecommunications system, comprising:

a presentation server;

a plurality of user devices, each of the user devices associated with at least one conference participant of a plurality of conference participants and connected to the presentation server via a network; and

wherein the presentation server receives a presentation; and

wherein the presentation server receives at least one video feed from at least one of the conference participants; and

wherein the presentation server applies a first transparency level of a first portion of the at least one received video feed and a second transparency level of a second portion of the at least one received video feed, the first transparency level and the second transparency level being adjustable independent of each other; and

wherein the first transparency level adjusting how visible the first portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed to the conference participants and the second transparency level adjusting how visible the second portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed to the conference participants; and

wherein the presentation server mixes the at least one received video feed with the received presentation to form a mixed video presentation; and

wherein the presentation server provides the mixed video presentation to the plurality of user devices of the plurality of conference participants during a conference via the network.

2. The telecommunications system of claim 1 wherein the first portion of the at least one received video feed comprises a face of a conference participant that is currently speaking.

3. The telecommunications system of claim 1 wherein the first portion of the at least one received video feed comprises faces of all of the conference participants.

4. The telecommunications system of claim 1 wherein the presentation server applies the first transparency level and the second transparency level to the mixed video presentation based on a command received from a designated user device of the plurality of user devices and the presentation server provides the mixed video presentation with the first transparency level and the second transparency level to the user devices via the network.

5. The telecommunications system of claim 1 wherein the mixed video presentation being displayed on the user devices and the first transparency level and the second transparency level being adjustable by each of the user devices independent of the other user devices via a transparency control on each user device.

20. The telecommunication system of claim 1 wherein at least one of the server and the user devices recognize at least one face of a speaker during the conference and wherein the first portion of the at least one received video feed comprises the at least one recognized face.

6. A telecommunications system, comprising:

a presentation server;

a plurality of user devices, each of the user devices associated with at least one of a plurality of conference participants and connected to the presentation server via a network, each one of the plurality of user devices having a transparency level control; and

wherein the presentation server receives a presentation from a conference participant of the plurality of conference participants; and

wherein the presentation server determines if there is a background in the received presentation; and

wherein if the background is present in the received presentation, then the presentation server removes the background; and

wherein the presentation server receives a video feed from a participant of the plurality of conference participants; and

wherein the presentation server mixes the received video feed with the received presentation to form a mixed video presentation; and

wherein the presentation server provides the mixed video presentation to the user devices via the network; and

wherein a first transparency level of a first portion of the received video feed and a second transparency level of a second portion of the received video feed being adjustable by each of the user devices independent of the other user devices via the transparency level control of each user device;

wherein adjustment of the first transparency level adjusting how visible the first portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed to the conference participants and the second transparency level adjusting how visible the second portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed to the conference participants, the first transparency level and the second transparency level being adjustable independent of each other.

7. The telecommunications system of claim 6 wherein the first portion of the video feed comprises a face of a currently speaking participant in the received video feed.

8. The telecommunications system of claim 6 wherein the first transparency level adjusting how visible an image of a currently speaking participant in the received video feed portion of the mixed video presentation received from the presentation server is displayed to the conference participants during a conference and wherein the second transparency level adjusting how visible an image of a remaining portion of the video feed in the received video feed portion of the mixed video presentation received from the presentation server is displayed to the conference participants during the conference.

9. A telecommunications method, comprising:

uploading a presentation to a presentation server;

receiving at least one video feed from a participant of a plurality of conference participants;

mixing the at least one received video feed with the uploaded presentation to form a mixed video presentation;

providing the mixed video presentation to a plurality of user devices, each of the user devices associated with at least one of the plurality of conference participants, each user device displaying the mixed video presentation to the at least one conference participant associated with the user device; and

providing a first transparency level control and a second transparency level control, the first transparency level control controlling a first transparency level of a first portion of the at least one video feed in the mixed video presentation, the second transparency level control controlling a second transparency level of a second portion of the at least one video feed in the mixed video presentation; and

wherein adjustment of the first transparency level adjusting how visible the first portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed during a conference and adjustment of the second transparency level adjusting how visible the second portion of the at least one received video feed of the mixed video presentation received from the presentation server is displayed during the conference, the first transparency level and the second transparency level being adjustable independent of each other.

10. The telecommunications method of claim 9 wherein adjustment of the first transparency level adjusting how visible an image of a currently speaking participant in the received video feed portion of the mixed video presentation received from the presentation server is displayed to the at least one conference participant during the conference and wherein adjustment of the second transparency level adjusting how visible an image of a remaining portion of the video feed in the received video feed portion of the mixed video presentation received from the presentation server is displayed to the at least one conference participant during the conference.

11. The telecommunications method of claim 9 wherein each user device of the plurality of user devices comprises the first transparency level control and the second transparency level control, the first transparency level and the second transparency level of each user device being adjustable independent of other user devices.

12. The telecommunications method of claim 9 further comprising identifying a face of a currently speaking conference participant, the first portion of the at least one received video feed comprising the face.

13. The telecommunications method of claim 9 further comprising identifying faces of all of the conference participants, the first portion of the video feed comprising the identified faces.

14. A telecommunications method, comprising:

uploading a presentation to a presentation server;

determining if there is a background in the uploaded presentation;

if the background is present in the uploaded presentation, then removing the background;

receiving a video feed from a currently speaking participant of the plurality of conference participants;

mixing the received video feed with the uploaded presentation to form a mixed video presentation;

providing the mixed video presentation to a plurality of user devices, each of the user devices associated with at least one of the plurality of conference participants, each user device displaying the mixed video presentation to the at least one conference participant associated with that user device; and

providing a first transparency level control and a second transparency level control on each user device, the first transparency level control controlling a first transparency level of a first portion of the video feed in the mixed video presentation, the second transparency level control controlling a second transparency level of a second portion of the video feed in the mixed video presentation, the first transparency level and the second transparency level being adjustable independent of each other; and

wherein adjustment of the first transparency level adjusting how visible the first portion of the received video feed of the mixed video presentation received from the presentation server is displayed and adjustment of the second transparency level adjusting how visible the second portion of the received video feed of the mixed video presentation received from the presentation server is displayed, the first transparency level and the second transparency level of each user device being adjustable independent of other user devices via the first transparency level control and the second transparency level control on each user device.

15. The telecommunications method of claim 14 wherein adjustment of the first transparency level adjusting visibility of an image of the currently speaking participant in the received video feed portion of the mixed video presentation and wherein adjustment of the second transparency level adjusting visibility of an image of a remaining portion of the received video feed portion of the mixed video presentation.

16. The telecommunications method of claim 14 further comprising identifying a face of the currently speaking conference participant, and wherein the first portion of the at least one received video feed is comprised of the face of the currently speaking conference participant.

17. The telecommunications method of claim 14 wherein the first transparency level control and the second transparency level control are provided such that a control window having a first window that displays the mixed video presentation prior to an adjustment of at least one of the first transparency level and the second transparency level to the at least one conference participant via the user device associated with the at least one conference participant and a second window that displays the mixed video presentation following an adjustment of at least one of the first transparency level and the second transparency level to the at least one conference participant via the user device associated with the at least one conference participant.

18. The telecommunications method of claim 14 further comprising identifying faces of all of the conference participants, and wherein the first portion of the video feed comprises the faces of all of the conference participants.

19. The telecommunications method of claim 14 further comprising applying the first transparency level or the second transparency level to the received video feed prior to mixing the received video feed with the uploaded presentation.