Composite video generation

1. A system for generating composite videos, the system comprising:

one or more physical processors configured by machine-readable instructions to:

obtain video information defining a video having a progress length, the video including video frames, the video frames including depiction of a person that moves during the progress length of the video, wherein the video frames include the depiction of the person at different locations within the video frames such that the video frames include a first video frame and a second video frame, the first video frame including the depiction of the person at a first location and the second video frame including the depiction of the person at a second location different from the first location;

determine the different locations of the depiction of the person within the video frames;

determine different portions of the video frames to be included in a composite video based on the different locations of the depiction of the person within the video frames, wherein determination of the different portions of the video frames to be included in the composite video includes determination of different locations of a mask for the video frames based on the different locations of the depiction of the person within the video frames such that the depiction of the person within the video frames is included within the mask;

generate a background image from the video frames based on the different locations of the depiction of the person within the video frames, the background image not including the depiction of the person; and

generate the composite video based on the different portions of the video frames and the background image, the composite video including composite video frames, wherein the composite video frames include multiple depictions of the person.

2. The system of claim 1 , wherein the background image is generated based on merging of two or more of the video frames, the two or more of the video frames selected for merging based on the different locations of the depiction of the person within the video frames.

3. The system of claim 1 , wherein the different locations of the depiction of the person within the video frames are determined based on body detection.

4. The system of claim 3 , wherein the different locations of the depiction of the person within the video frames are determined based on face detection responsive to failure of the body detection.

5. The system of claim 1 , wherein the composite video frames include the multiple depictions of the person based on merging of multiple ones of the depiction of the person included within multiple ones of the video frames and included within the mask into individual composite video frames.

6. The system of claim 5 , wherein determination of the different locations of the mask includes determination of different placements and/or different sizes of the mask.

7. The system of claim 6 , wherein the different placements and/or the different sizes of the mask are determined to prevent overlap of the mask for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames.

8. The system of claim 7 , wherein the multiple ones of the video frames are selected for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames based on matching of audio associated with the video frames.

9. The system of claim 7 , wherein the multiple ones of the video frames are selected for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames based on matching of poses of the person depicted within the video frames.

10. A method for generating composite videos, the method performed by a computing system including one or more processors, the method comprising:

obtaining, by the computing system, video information defining a video having a progress length, the video including video frames, the video frames including depiction of a person that moves during the progress length of the video, wherein the video frames include the depiction of the person at different locations within the video frames such that the video frames include a first video frame and a second video frame, the first video frame including the depiction of the person at a first location and the second video frame including the depiction of the person at a second location different from the first location;

determining, by the computing system, the different locations of the depiction of the person within the video frames;

determining, by the computing system, different portions of the video frames to be included in a composite video based on the different locations of the depiction of the person within the video frames, wherein determining the different portions of the video frames to be included in the composite video includes determining different locations of a mask for the video frames based on the different locations of the depiction of the person within the video frames such that the depiction of the person within the video frames is included within the mask;

generating, by the computing system, a background image from the video frames based on the different locations of the depiction of the person within the video frames, the background image not including the depiction of the person; and

generating, by the computing system, the composite video based on the different portions of the video frames and the background image, the composite video including composite video frames, wherein the composite video frames include multiple depictions of the person.

11. The method of claim 10 , wherein the background image is generated based on merging of two or more of the video frames, the two or more of the video frames selected for merging based on the different locations of the depiction of the person within the video frames.

12. The method of claim 10 , wherein the different locations of the depiction of the person within the video frames are determined based on body detection.

13. The method of claim 12 , wherein the different locations of the depiction of the person within the video frames are determined based on face detection responsive to failure of the body detection.

14. The method of claim 10 , wherein the composite video frames include the multiple depictions of the person based on merging of multiple ones of the depiction of the person included within multiple ones of the video frames and included within the mask into individual composite video frames.

15. The method of claim 14 , wherein determining the different locations of the mask includes determining different placements and/or different sizes of the mask.

16. The system of claim 14 , wherein the different placements and/or the different sizes of the mask are determined to prevent overlap of the mask for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames.

17. The system of claim 16 , wherein the multiple ones of the video frames are selected for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames based on matching of audio associated with the video frames.

18. The system of claim 16 , wherein the multiple ones of the video frames are selected for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames based on matching of poses of the person depicted within the video frames.

19. A system for generating composite videos, the system comprising:

one or more physical processors configured by machine-readable instructions to:

obtain video information defining a video having a progress length, the video including video frames, the video frames including depiction of a person that moves during the progress length of the video, wherein the video frames include the depiction of the person at different locations within the video frames such that the video frames include a first video frame and a second video frame, the first video frame including the depiction of the person at a first location and the second video frame including the depiction of the person at a second location different from the first location;

determine the different locations of the depiction of the person within the video frames;

determine different portions of the video frames to be included in a composite video based on the different locations of the depiction of the person within the video frames, wherein determination of the different portions of the video frames to be included in the composite video includes determination of different locations of a mask for the video frames based on the different locations of the depiction of the person within the video frames such that the depiction of the person within the video frames is included within the mask, wherein determination of the different locations of the mask includes determination of different placements and/or different sizes of the mask;

generate a background image from the video frames based on the different locations of the depiction of the person within the video frames, the background image not including the depiction of the person, wherein the background image is generated based on merging of two or more of the video frames, the two or more of the video frames selected for merging based on the different locations of the depiction of the person within the video frames; and

generate the composite video based on the different portions of the video frames and the background image, the composite video including composite video frames, wherein the composite video frames include multiple depictions of the person.

20. The system of claim 19 , wherein:

the composite video frames include the multiple depictions of the person based on merging of multiple ones of the depiction of the person included within multiple ones of the video frames and included within the mask into individual composite video frames; and

the different placements and/or the different sizes of the mask are determined to prevent overlap of the mask for the merging of the multiple ones of the depiction of the person included within the multiple ones of the video frames and included within the mask into the individual composite video frames.