IP Library Granted Patent US 12,079,274
Granted Patent B2
US 12,079,274 · App. 16/162,212 · Granted Sep 3, 2024

Systems and methods for identifying scene changes in video files

Inventor: Qiang Fu (Sunnyvale, CA)
Assignee: NBCUniversal Studios LLC
G06F16/7847G06F16/745G06V10/462G06V20/41G06V20/46G06V20/48G06V20/49G11B27/036H04N5/278
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,079,274
App. No.
16/162,212
Granted
Sep 3, 2024
Kind
B2
Abstract

Systems and methods including one or more processing modules and one or more non-transitory storage modules storing computing instructions configured to run on the one or more processing modules and perform acts of: receiving at least two consecutive frames of a video file; determining a level of difference between the at least two consecutive frames of the video file; receiving a subtitle file associated with the video file; analyzing the subtitle file to identify a gap in conversation in the video file; and identifying a scene change in the video file when: (1) the level of difference between the at least two consecutive frames of the video file is above a predefined threshold; and (2) the level of difference between the at least two consecutive frames of the video file occurs during the gap in the conversation. Other embodiments are disclosed herein.

Claims (54)

1. A system comprising:

one or more processors; and

one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:

receiving at least two consecutive frames of a video file;

determining a level of difference between the at least two consecutive frames of the video file;

receiving a subtitle file associated with the video file;

analyzing the subtitle file to identify a gap in conversation in the video file; and

identifying a scene change in the video file when:

the level of difference between the at least two consecutive frames of the video file breaches a predefined similarity threshold during an identified gap in conversation; and

otherwise, refrain from identifying a scene change in the video file when: the level of difference between the at least two consecutive frames of the video file breaches the predefined similarity threshold outside of an identified gap in the conversation;

wherein a media file is inserted into the video file when the scene change occurs.

2. The system of claim 1 , wherein the computing instructions are further configured to perform:

identifying a minimum time between two media files; and

when a second scene change occurs within the minimum time after the media file, not displaying a second media file when the second scene change occurs.

3. The system of claim 1 , wherein when the scene change occurs during an end credit sequence, the media file is not inserted into the video file at the scene change.

4. The system of claim 1 , wherein:

the step of determining the level of difference between the at least two consecutive frames of the video file is performed on a standard definition version of the video file; and

the media file is inserted into a high definition version of the video file.

5. The system of claim 1 , wherein determining the level of difference between the at least two consecutive frames of the video file occurs only for frames of the video file that are associated with portions of the video file corresponding to the gap in the conversation in the video file.

6. A method being implemented via execution of computing instructions configured to run at one or more processors and configured to be stored at non-transitory computer-readable media, the method comprising:

receiving at least two consecutive frames of a video file;

determining a level of difference between the at least two consecutive frames of the video file;

receiving a subtitle file associated with the video file;

analyzing the subtitle file to identify a gap in conversation in the video file; and

identifying a scene change in the video file when:

the level of difference between the at least two consecutive frames of the video file breaches a predefined similarity threshold during an identified gap in conversation; and

otherwise, refrain from identifying a scene change in the video file when:

the level of difference between the at least two consecutive frames of the video file breaches the predefined similarity threshold outside of the identified gap in the conversation;

wherein a media file is inserted into the video file when the scene change occurs.

7. The method of claim 6 further comprising:

identifying a minimum time between two media files; and

when a second scene change occurs within the minimum time after the media file, not displaying a second media file when the second scene change occurs.

8. The method of claim 6 , wherein when the scene change occurs during an end credit sequence, the media file is not inserted into the video file at the scene change.

9. The method of claim 6 , wherein:

the step of determining the level of difference between the at least two consecutive frames of the video file is performed on a standard definition version of the video file; and

the media file is inserted into a high definition version of the video file.

10. The method of claim 6 , wherein determining the level of difference between the at least two consecutive frames of the video file occurs only for frames of the video file that are associated with portions of the video file corresponding to the gap in the conversation in the video file.

11. A tangible, non-transitory, computer-readable medium, comprising computer-readable instructions that, when executed by one or more processors of one or more computers, cause the one or more computers to:

receive at least two consecutive frames of a video file;

determine a level of difference between the at least two consecutive frames of the video file;

receive a subtitle file associated with the video file;

analyze the subtitle file to identify a gap in conversation in the video file; and

identify a scene change in the video file when:

the level of difference between the at least two consecutive frames of the video file breaches a predefined similarity threshold during an identified gap in conversation; and

otherwise, refrain from identifying a scene change in the video file when: the level of difference between the at least two consecutive frames of the video file breaches the predefined similarity threshold outside of an identified gap in the conversation;

wherein a media file is inserted into the video file when the scene change occurs.

12. The tangible, non-transitory, computer-readable medium of claim 11 , comprising computer-readable instructions that, when executed by the one or more processors of the one or more computers, cause the one or more computers to:

identify a minimum time between two media files; and

when a second scene change occurs within the minimum time after the media file, not display a second media file when the second scene change occurs.

13. The tangible, non-transitory, computer-readable medium of claim 11 , wherein when the scene change occurs during an end credit sequence, the media file is not inserted into the video file at the scene change.

14. The tangible, non-transitory, computer-readable medium of claim 11 , wherein:

the step of determining the level of difference between the at least two consecutive frames of the video file is performed on a standard definition version of the video file; and

the media file is inserted into a high definition version of the video file.

15. The tangible, non-transitory, computer-readable medium of claim 11 , wherein determining the level of difference between the at least two consecutive frames of the video file occurs only for frames of the video file that are associated with portions of the video file corresponding to the gap in the conversation in the video file.

Assignments (4)
CORRECTIVE ASSIGNMENT TO CORRECT THE COVERSHEET TO EXCLUDE APP. NO. 11368308, WHICH WAS INADVERTENTLY ADDED AT THE TIME OF RECORDING THE ASSIGNMENT PREVIOUSLY RECORDED AT REEL: 053609 FRAME: 0302. ASSIGNOR(S) HEREBY CONFIRMS THE ASSIGNMENT. Recorded Jan 18, 2022
From: VUDU, LLC
To: NBCUNIVERSAL MEDIA LLC
Reel/Frame 058756/0244 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Aug 26, 2020
From: VUDU, LLC
To: NBCUNIVERSAL MEDIA LLC
Reel/Frame 053609/0302 →
CHANGE OF NAME Recorded Aug 24, 2020
From: VUDU, INC.
To: VUDU, LLC
Reel/Frame 053585/0162 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 22, 2018
From: FU, QIANG
To: VUDU, INC.
Reel/Frame 047267/0978 →
Continuity (1)
Related Publication 20200118593A1 · Apr 16, 2020