Granted Patent B2

US 12,744,911 · App. 19/049,062 · Granted Sep 22, 2026

Inventor: Brian Hardy (Atlanta, GA)

Assignee: EDG, LLC

H04N19/139H04N19/119H04N19/14

Abstract

Claims (46)

1 . A computer-implemented method for processing a video, the method comprising:

identifying a plurality of still images from an original video;

identifying, based on a framework applicable to respective ones of the plurality of still images, a first area within a first still image of the plurality of still images;

identifying, based on the framework, a second area within a second still image of the plurality of still images, the second area corresponding to the first area;

determining a quantitative score associated with an extent to which a difference between the first area of the first still image and the second area of the second still image is frameable within a first subframe of the framework, wherein a size of the first subframe is smaller than a size of the framework;

determining, based on the quantitative score, a second subframe of the framework that improves upon the extent to which the difference between the first area of the first still image and the second area of the second still image is frameable within the first subframe, wherein a size of the second subframe is smaller than the size of the framework and different from the size of the first subframe;

modifying, based on the second subframe, the second still image through one or more of (i) a cropping process, (ii) a zooming process, or (iii) a panning process to create a modified second still image; and

including the modified second still image in a new video.

2 . The method of claim 1 , wherein the quantitative score is a first quantitative score, the method further comprising:

identifying, based on the framework, a third area within a third still image of the plurality of still images, the third area corresponding to the second area;

determining a second quantitative score associated with an extent to which a difference between the second area of the second still image and the third area of the third still image is frameable within the second subframe of the framework;

determining, based on the second quantitative score, a third subframe of the framework that improves upon the extent to which the difference between the second area of the second still image and the third area of the third still image is frameable within the second subframe, wherein a size of the third subframe is smaller than the size of the framework and different from the size of the second subframe;

modifying, based on the third subframe, the third still image through one or more of (i) a cropping process, (ii) a zooming process, or (iii) a panning process to create a modified third still image; and

including the modified third still image in the new video.

3 . The method of claim 1 , wherein the original video also includes audio.

4 . The method of claim 1 , wherein respective ones of the plurality of still images from the original video are separated by a same time interval within a time period of the original video.

5 . The method of claim 1 , wherein the difference between the first area of the first still image and the second area of the second still image is determined based on a motion vector.

6 . The method of claim 1 , wherein the difference between the first area of the first still image and the second area of the second still image is determined based on a pixel delta.

7 . The method of claim 1 , wherein the difference between the first area of the first still image and the second area of the second still image is determined using computer vision techniques.

8 . The method of claim 1 , wherein the first area corresponds to a location of an object in the first still image.

9 . The method of claim 1 , wherein the size of the second subframe is equal to or larger than a predetermined minimum subframe size.

10 . The method of claim 1 , wherein size of the second subframe is proportional to the size of the framework.

11 . A system configured to process a video, the system comprising:

memory including machine-readable instructions; and

one or more processors configured, in response to executing the machine-readable instructions, to perform operations comprising:

identifying a plurality of still images from an original video;

identifying, based on a framework applicable to respective ones of the plurality of still images, a first area within a first still image of the plurality of still images;

identifying, based on the framework, a second area within a second still image of the plurality of still images, the second area corresponding to the first area;

determining a quantitative score associated with an extent to which a difference between the first area of the first still image and the second area of the second still image is frameable within a first subframe of the framework, wherein a size of the first subframe is smaller than a size of the framework;

determining, based on the quantitative score, a second subframe of the framework that improves upon the extent to which the difference between the first area of the first still image and the second area of the second still image is frameable within the first subframe, wherein a size of the second subframe is smaller than the size of the framework and different from the size of the first subframe;

modifying, based on the second subframe, the second still image through one or more of (i) a cropping process, (ii) a zooming process, or (iii) a panning process to create a modified second still image; and

including the modified second still image in a new video.

12 . The system of claim 11 , wherein the quantitative score is a first quantitative score, wherein the operations further comprise:

identifying, based on the framework, a third area within a third still image of the plurality of still images, the third area corresponding to the second area;

determining a second quantitative score associated with an extent to which a difference between the second area of the second still image and the third area of the third still image is frameable within the second subframe of the framework;

determining, based on the second quantitative score, a third subframe of the framework that improves upon the extent to which the difference between the second area of the second still image and the third area of the third still image is frameable within the second subframe, wherein a size of the third subframe is smaller than the size of the framework and different from the size of the second subframe;

modifying, based on the third subframe, the third still image through one or more of (i) a cropping process, (ii) a zooming process, or (iii) a panning process to create a modified third still image; and

including the modified third still image in the new video.

13 . The system of claim 11 , wherein the original video also includes audio.

14 . The system of claim 11 , wherein respective ones of the plurality of still images from the original video are separated by a same time interval within a time period of the original video.

15 . The system of claim 11 , wherein the difference between the first area of the first still image and the second area of the second still image is determined based on a motion vector.

16 . The system of claim 11 , wherein the difference between the first area of the first still image and the second area of the second still image is determined based on a pixel delta.

17 . The system of claim 11 , wherein the difference between the first area of the first still image and the second area of the second still image is determined using computer vision techniques.

18 . The system of claim 11 , wherein the first area corresponds to a location of an object in the first still image.

19 . The system of claim 11 , wherein the size of the second subframe is equal to or larger than a predetermined minimum subframe size.

20 . The system of claim 11 , wherein size of the second subframe is proportional to the size of the framework.

Assignments (1)

Continuity (5)

References Cited (43)