Systems and methods for embedding a foreground video into a background feed based on a control input

• US 9,628,722 B2
• Filed: 03/30/2011
• Issued: 04/18/2017
• Est. Priority Date: 03/30/2010
• Status: Active Grant

• Current Assignee: Personify Incorporated (Wilson Human Capital Group, Inc.)
• Original Assignee: Personify Incorporated (Wilson Human Capital Group, Inc.)
• Inventors: Nguyen, Quang Il., Do, Minh N., Lin, Dennis, Patel, Sanjay I.
• Primary Examiner(s): Holder, Anner
• Assistant Examiner(s): Adrovel, William
• Application Number:
  US13/076,264
• Publication Number:
  US 20110242277A1
• Time in Patent Office: 2,211 Days
• Field of Search: None
• CPC Class Codes: G02B 27/00 Optical systems or apparatus not provided for by any of the groups G02B1/00 - G02B26/00, G02B30/00
• CPC Class Codes: G02B 27/0093 with means for monitoring data relating to the user, e.g. head-tracking, eye-tracking
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06F 3/017 Gesture based interaction, e.g. based on a set of recognized hand gestures interaction based on gestures traced on a digitiser G06F3/04883
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10028 Range image; Depth image; 3D point clouds
• CPC Class Codes: G06T 2207/20221 Image fusion; Image merging
• CPC Class Codes: G06T 5/20 using local operators
• CPC Class Codes: G06T 5/50 using two or more images, e.g. averaging or subtraction
• CPC Class Codes: G06T 5/70 Denoising; Smoothing
• CPC Class Codes: G06T 7/11 Region-based segmentation
• CPC Class Codes: G06T 7/194 involving foreground-background segmentation
• CPC Class Codes: G06T 7/90 Determination of colour characteristics
• CPC Class Codes: H04N 1/00336 with an apparatus performing pattern recognition, e.g. of a face or a geographic feature image or video recognition or understanding of scenes G06V20/00
• CPC Class Codes: H04N 13/30 Image reproducers optical systems for producing stereoscopic or other three-dimensional effects G02B30/00
• CPC Class Codes: H04N 13/366 using viewer tracking
• CPC Class Codes: H04N 5/144 Movement detection for video coding H04N19/503; analysis of motion in general G06T7/20
• CPC Class Codes: H04N 5/2226 Determination of depth image, e.g. for foreground/background separation determining depth by image analysis in general G06T7/50; segmentation by image analysis in general G06T7/10
• CPC Class Codes: H04N 5/272 Means for inserting a foreground image in a background image, i.e. inlay, outlay

Abstract

A color image and a depth image of a live video are received. Each of the color image and the depth image are processed to identify the foreground and the background of the live video. The background of the live video is removed in order to create a foreground video that comprises the foreground of the live video. A control input may be received to control the embedding of the foreground video into a second background from a background feed. The background feed may also comprise virtual objects such that the foreground video may interact with the virtual objects.

Claims

1. A method for selectively embedding a foreground video into a background feed, the method comprising:

receiving, using a computer, depth and color information of a first video from at least one camera;

creating a foreground video by identifying a foreground portion and a background portion of the first video based on the depth and color information of the first video, the creation of the foreground video comprising an inclusion of the foreground portion of the first video and a removal of the background portion of the first video;

receiving the background feed comprising a second background;

detecting, in the foreground video, a control input from a user;

determining, based on the control input, whether or not to embed the foreground video into the second background;

in response to a determination to embed the foreground video, creating an output video by embedding the foreground video into the second background; and

in response to a determination to not embed the foreground video, creating the output video by using the second background without embedding the foreground video.

2. The method as set forth in claim 1, wherein the control input comprises a gesture from the user, the gesture detected by using the depth information of the first video.

3. The method as set forth in claim 1, wherein the control input comprises a depth of the foreground portion of the first video, the foreground portion is embedded into the background feed if the depth of the foreground portion is below a threshold value, the foreground portion is not embedded into the background feed if the depth of the foreground portion is above the threshold value.

4. The method as set forth in claim 1, wherein the control input comprises body motion of the user, the body motion comprising at least one of the user'"'"'s horizontal movement, depth movement, and entering of a hot spot, the depth movement comprising the user moving forwards or backwards, the hot spot comprising a two dimensional (2D) or a three dimensional (3D) placement of the user, the 2D placement comprising a defined horizontal positioning of the user, the 3D placement comprising a defined horizontal and depth placement of the user.

5. The method as set forth in claim 1, wherein the background feed comprises a virtual object for changing the background feed to a third background, a placement of a user hand from the foreground video on the virtual object in the background feed changes the background feed to the third background.

6. The method as set forth in claim 1, further comprising adding, from a virtual object authoring module, a virtual object to the second background, the virtual object added is assigned a required user action and a virtual object effect.

7. The method as set forth in claim 1, wherein the background feed comprises at least one virtual object, each virtual object comprises a required user action and a virtual object effect, the foreground portion comprises a depiction of the user such that if the user from the foreground portion performs the required user action, the virtual object effect is activated in the output video.

8. The method as set forth in claim 1, wherein the second background comprises at least one of a presentation slide, video, shared computer desktop, and virtual scene.

9. The method as set forth in claim 1, wherein the depth information comprises a depth image for providing a distance of each pixel from the at least one camera.

10. A system for selectively embedding a foreground video into a background feed, the system comprising:

at least one computer; and

a non-transitory computer readable medium having stored thereon one or more programs, which when executed by the at least one computer, cause the at least one computer to;

receive depth and color information of a first video from at least one camera;

create a foreground video by identifying a foreground portion and a background portion of the first video based on the depth and color information of the first, the creation of the foreground video comprising an inclusion of the foreground portion of the first video and a removal of the background portion of the first video;

receive the background feed comprising a second background;

detect, in the foreground video, a control input from a user;

determine, based on the control input, whether or not to embed the foreground video into the second background;

in response to a determination to embed the foreground video, create an output video by embedding the foreground video into the second background; and

in response to a determination to not embed the foreground video create the output video by using the second background without embedding the foreground video.

11. The system as set forth in claim 10, wherein the control input comprises a gesture from the user, the gesture detected by using the depth information of the first video.

12. The system as set forth in claim 10, wherein the control input comprises a depth of the foreground portion of the first video, the foreground portion is embedded into the background feed if the depth of the foreground portion is below a threshold value, the foreground portion is not embedded into the background feed if the depth of the foreground portion is above the threshold value.

13. The system as set forth in claim 10, wherein the control input comprises body motion of the user, the body motion comprising at least one of the user'"'"'s horizontal movement, depth movement, and entering of a hot spot, the depth movement comprising the user moving forwards or backwards, the hot spot comprising a two dimensional (2D) or a three dimensional (3D) placement of the user, the 2D placement comprising a defined horizontal positioning of the user, the 3D placement comprising a defined horizontal and depth placement of the user.

14. The system as set forth in claim 10, wherein the background feed comprises a virtual object for changing the background feed to a third background, a placement of a user hand from the foreground video on the virtual object in the background feed changes the background feed to the third background.

15. The system as set forth in claim 10, further comprising a virtual object authoring module for adding a virtual object to the second background, the virtual object added is assigned a required user action and a virtual object effect.

16. The system as set forth in claim 10, wherein the background feed comprises at least one virtual object, each virtual object comprises a required user action and a virtual object effect, the foreground portion comprises a depiction of the user such that if the user from the foreground portion performs the required user action, the virtual object effect is activated in the output video.

17. The system as set forth in claim 10, wherein the second background comprises at least one of a presentation slide, video, shared computer desktop, and virtual scene.

18. The system as set forth in claim 10, wherein the depth information comprises a depth image for providing a distance of each pixel from the at least one camera.

19. A non-transitory computer readable medium carrying one or more instructions for selectively embedding a foreground video into a background feed, wherein the one or more instructions, when executed by one or more processors, cause the one or more processors to perform the steps of:

receiving depth and color information of a first video from at least one camera;

creating a foreground video by identifying a foreground portion and a background portion of the first video based on the depth and color information of the first video, the creation of the foreground video comprising an inclusion of the foreground portion of the first video and a removal of the background portion of the first video;

receiving the background feed comprising a second background;

detecting, in the foreground video, a control input from a user;

determining, based on the control input, whether or not to embed the foreground video into the second background;

in response to a determination to embed the foreground video, creating an output video by embedding the foreground video into the second background; and

in response to a determination to not embed the foreground video, creating the output video by using the second background without embedding the foreground video.

20. The non-transitory computer readable medium as set forth in claim 19, wherein the control input comprises a gesture from the user, the gesture detected by using the depth information of the first video.

21. The non-transitory computer readable medium as set forth in claim 19, wherein the control input comprises a depth of the foreground portion of the first video, the foreground portion is embedded into the background feed if the depth of the foreground portion is below a threshold value, the foreground portion is not embedded into the background feed if the depth of the foreground portion is above the threshold value.

22. The non-transitory computer readable medium as set forth in claim 19, wherein the control input comprises body motion of the user, the body motion comprising at least one of the user'"'"'s horizontal movement, depth movement, and entering of a hot spot, the depth movement comprising the user moving forwards or backwards, the hot spot comprising a two dimensional (2D) or a three dimensional (3D) placement of the user, the 2D placement comprising a defined horizontal positioning of the user, the 3D placement comprising a defined horizontal and depth placement of the user.

23. The non-transitory computer readable medium as set forth in claim 19, wherein the background feed comprises a virtual object for changing the background feed to a third background, a placement of a user hand from the foreground video on the virtual object in the background feed changes the background feed to the third background.

24. The non-transitory computer readable medium as set forth in claim 19, further comprising adding, from a virtual object authoring module, a virtual object to the second background, the virtual object added is assigned a required user action and a virtual object effect.

25. The non-transitory computer readable medium as set forth in claim 19, wherein the background feed comprises at least one virtual object, each virtual object comprises a required user action and a virtual object effect, the foreground portion comprises a depiction of the user such that if the user from the foreground portion performs the required user action, the virtual object effect is activated in the output video.

26. The non-transitory computer readable medium as set forth in claim 19, wherein the second background comprises at least one of a presentation slide, video, shared computer desktop, and virtual scene.