Techniques for adding interactive features to videos

Patent metadata

Field	Value
Publication number	US-9330718-B2
Application number	US-201314106136-A
Country	US
Kind code	B2
Filing date	Dec 13, 2013
Priority date	Feb 20, 2013
Publication date	May 3, 2016
Grant date	May 3, 2016

Abstract

Techniques are disclosed for adding interactive features to videos to enable users to create new media using a dynamic blend of motion and still imagery. The interactive techniques can include allowing a user to change the starting time of one or more subjects in a given video frame, or only animate/play a portion of a given frame scene. The techniques may include segmenting each frame of a video to identify one or more subjects within each frame, selecting (or receiving selections of) one or more subjects within the given frame scene, tracking the selected subject(s) from frame to frame, and alpha-matting to play/animate only the selected subject(s). In some instances, segmentation, selection, and/or tracking may be improved and/or enhanced using pixel depth information (e.g., using a depth map).

First claim

What is claimed is:

1. A method comprising:
segmenting each frame of a video into its semantic components to identify one or more subjects within each frame scene based on a respective group of pixels, wherein the video is a part of media;
receiving a selection of one or more subjects within a given frame scene;
tracking the one or more subjects from frame to frame of the video to identify the respective group of pixels comprising the one or more subjects in each frame; and
alpha-matting the media to isolate the one or more selected subjects from frame to frame.

2. The method of claim 1 wherein alpha-matting the media comprises:
forming a transparency matte matching the shape of the one or more selected subjects from the given frame scene to allow playing the video through one or more holes created by the transparency matte, wherein the shape of the one or more holes in the given scene is updated for each frame of the video to match the shape of the one or more selected subjects in the frame being played; or
forming a transparency matte around the one or more selected subjects in each frame to allow playing the video by copying the one or more selected subjects in the frame being played on top of the given frame scene.

3. The method of claim 1 wherein segmenting each frame of the video is performed using an unattended graph cut method.

4. The method of claim 1 , further comprising pixel depth information to improve segmenting to identify one or more subjects within each frame.

5. The method of claim 4 , further comprising generating the pixel depth information using a stereo or array camera.

6. The method of claim 1 , further comprising receiving the selection of the one or more subjects from a user.

7. The method of claim 6 , further comprising receiving the user selection from a click or tap input performed on the one or more subjects in the given frame.

8. The method of claim 1 , further comprising receiving the selection of the one or more subjects prior to segmenting each frame, wherein only the selected one or more subjects are segmented.

9. The method of claim 1 , further comprising tracking the one or more subjects prior to receiving a selection of one or more of the tracked subjects.

10. The method of claim 1 , further comprising generating a still image, wherein the one or more selected subjects are from different frames than the given frame.

11. The method of claim 1 , further comprising generating a video, wherein the one or more selected subjects are started out of sequence relative to the given frame.

12. The method of claim 1 , further comprising generating a visual media, wherein only the one or more selected subjects are playing while the remaining portion of the given frame is still.

13. The method of claim 1 , further comprising generating a visual media, wherein one or more subjects in a specific frame of the video can be selected to animate the selected one or more subjects relative to the remainder of the specific frame.

14. A computing device comprising:
a processor;
memory accessible by the processor; and
an application stored on the memory and executable by the processor, the application configured to:
segment each frame of a video into its semantic components to identify one or more subjects within each frame scene based on a respective group of pixels, wherein the video is a part of media;
receive a selection of one or more subjects within a given frame scene;
track the one or more subjects from frame to frame of the video to identify the respective group of pixels comprising the one or more subjects in each frame; and
alpha-matte the media to isolate the one or more selected subjects from frame to frame.

15. The device of claim 14 wherein alpha-matte the media comprises:
forming a transparency matte matching the shape of the one or more selected subjects from the given frame scene to allow playing the video through one or more holes created by the transparency matte, wherein the shape of the one or more holes in the given scene is updated for each frame of the video to match the shape of the one or more selected subjects in the frame being played; or
forming a transparency matte around the one or more selected subjects in each frame to allow playing the video by copying the one or more selected subjects in the frame being played on top of the given frame scene.

16. The device of claim 14 , further comprising a display operatively coupled to the processor and at least one input device operatively coupled to the processor, wherein a user can use the at least one input device to select the one or more subjects within a given frame scene.

17. The device of claim 14 , further comprising a touch screen display coupled to the processor, wherein the touch screen is configured to receive the selection of the one or more subjects from user input.

18. At least one non-transitory computer program product encoded with instructions that, when executed by one or more processors, causes a process for adding interactive features to video to be carried out, the process comprising:
segmenting each frame of a video into its semantic components to identify one or more subjects within each frame scene based on a respective group of pixels, wherein the video is a part of media;
receiving a selection of one or more subjects within a given frame scene;
tracking the one or more subjects from frame to frame of the video to identify the respective group of pixels comprising the one or more subjects in each frame; and
alpha-matting the media to isolate the one or more selected subjects from frame to frame.

19. The at least one computer program product of claim 18 wherein alpha-matting the media comprises:
forming a transparency matte matching the shape of the one or more selected subjects from the given frame scene to allow playing the video through one or more holes created by the transparency matte, wherein the shape of the one or more holes in the given scene is updated for each frame of the video to match the shape of the one or more selected subjects in the frame being played; or
forming a transparency matte around the one or more selected subjects in each frame to allow playing the video by copying the one or more selected subjects in the frame being played on top of the given frame scene.

20. The at least one computer program product of claim 18 , further comprising receiving the selection of the one or more subjects from a user.

21. The at least one computer program product of claim 18 , further comprising tracking the one or more subjects prior to receiving a selection of one or more of the tracked subjects.

22. The at least one computer program product of claim 18 , further comprising generating a still image, wherein the one or more selected subjects are from different frames than the given frame.

23. The at least one computer program product of claim 18 , further comprising generating a video, wherein the one or more selected subjects are started out of sequence relative to the given frame.

24. The at least one computer program product of claim 18 , further comprising generating a visual media, wherein only the one or more selected subjects are playing while the remaining portion of the given frame is still.

25. The at least one computer program product of claim 18 , further comprising generating a visual media, wherein one or more subjects in a specific frame of the video can be

Assignees

• Intel Corp

Inventors

• Middleton Daniel C
• Nestares Oscar
• Ainsworth Lucas B

Classifications

• G11B27/031 Primary

  Electronic editing of digitised analogue information signals, e.g. audio or video signals · CPC title