Duplicate frames detection

Patent metadata

Field	Value
Publication number	US-11868441-B2
Application number	US-202117390321-A
Country	US
Kind code	B2
Filing date	Jul 30, 2021
Priority date	Sep 22, 2020
Publication date	Jan 9, 2024
Grant date	Jan 9, 2024

Abstract

Systems and methods for detecting duplicate frames is provided. An automated duplicate frames detection service may extract one or more frames from content and determine a hamming distance between each of the extracted one or more frames and adjacent frames. In response to determining the hamming distance is less than a threshold hamming distance, the duplicate frames detection service may determine duplicate frames. In turn, the duplicate frames detection service may determine the duplicate frames are created without intent in response to determining the average distance between the one or more duplicate frames meets threshold criteria and provide an indication of the one or more duplicate frames without intent to a client device.

First claim

The invention claimed is:

1. A method for detecting unintended duplicate frames in content, comprising:
identifying, via one or more processors, one or more duplicate frames within the content;
calculating, via the one or more processors, an average frame distance between the one or more duplicate frames;
determining, via the one or more processors, whether the one or more duplicate frames are generated without intent based on the average frame distance between the one or more duplicate frames; and
providing, via the one or more processors, an indication of whether the one or more duplicate frames are generated without intent to a client device.

2. The method of claim 1 , wherein identifying, via the one or more processors, the one or more duplicate frames within the content comprises:
receiving, via the one or more processors, the content;
extracting, via the one or more processors, one or more frames from the content;
determining, via the one or more processors, a hamming distance between each of the one or more frames and corresponding one or more adjacent frames; and
identifying, via the one or more processors, the one or more duplicate frames in response to determining that the hamming distance is less than a threshold hamming distance.

3. The method of claim 2 , further comprising generating, via the one or more processors, a binary array indicative of each of the one or more frames as duplicate or not duplicate based on the threshold hamming distance.

4. The method of claim 2 , wherein the threshold hamming distance comprises 6 bits.

5. The method of claim 1 , wherein the indication provided to the client device indicates that the one or more duplicate frames are generated without intent in response to determining, via the one or more processors, the average frame distance between the one or more duplicate frames meets a threshold frame distance.

6. The method of claim 1 , wherein the indication provided to the client device indicates that the one or more duplicate frames are generated with intent in response to determining, via the one or more processors, that the average frame distance between the one or more duplicate frames does not meet a threshold frame distance.

7. The method of claim 6 , wherein the threshold frame distance comprises between 4 and 7 frames.

8. The method of claim 1 , further comprising identifying, via the one or more processors, a frequency of the one or more duplicate frames in the content, one or more patterns associated with the one or more duplicate frames, or both.

9. A non-transitory, machine-readable medium, comprising machine-readable instructions that, when executed by one or more processors of a machine, cause the machine to:
identify one or more duplicate frames in content;
calculate an average frame distance between the one or more duplicate frames;
identify a frequency of the one or more duplicate frames in the content, one or more patterns associated with the one or more duplicate frames, or both; and
determine whether the one or more duplicate frames are generated with intent based on the average frame distance between the one or more duplicate frames.

10. The non-transitory, machine-readable medium of claim 9 , wherein the machine-readable instructions cause the machine to identify the one or more duplicate frames in the content based at least in part on:
receiving the content;
extracting one or more frames from the content;
determining a hamming distance between each of the one or more frames and corresponding one or more adjacent frames; and
identifying the one or more duplicate frames in response to determining that the hamming distance is less than a threshold hamming distance.

11. The non-transitory, machine-readable medium of claim 10 , wherein the machine-readable instructions further cause the machine to generate a binary array indicative of each of the one or more frames as duplicate or not duplicate based on the threshold hamming distance.

12. The non-transitory, machine-readable medium of claim 9 , wherein the machine-readable instructions further cause the machine to:
determine that the average frame distance does not meet a threshold criteria in response to determining that the average frame distance comprises 1 frame; and
determine that the one or more duplicated frames are generated with intent in response to determining that the average frame distance does not meet the threshold criteria.

13. The non-transitory, machine-readable medium of claim 12 , wherein the machine-readable instructions further cause the machine to provide a notification indicative of intentional duplicate frames to a client device based on determining that the average frame distance does not meet the threshold criteria.

14. The non-transitory, machine-readable medium of claim 9 , wherein the machine-readable instructions further cause the machine to:
determine that the average frame distance meets a threshold criteria in response to determining that the average frame distance comprises between 4 and 7 frames; and
determine that the one or more duplicated frames are generated without intent in response to determining that the average frame distance meets the threshold criteria.

15. The non-transitory, machine-readable medium of claim 14 , wherein the machine-readable instructions further cause the machine to provide a notification indicative of unintentional duplicate frames to a client device based on determining that the average frame distance meets the threshold criteria.

16. A duplicate frames detection system, comprising:
one or more processors; and
one or more memory devices configured to store instructions that, when executed by the one or more processors, cause the one or more processors to:
identify one or more duplicate frames;
calculate an average frame distance between the one or more duplicate frames; and
determine whether the one or more duplicate frames are generated without intent based on the average frame distance between the one or more duplicate frames.

17. The duplicate frames detection system of claim 16 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to provide an indication of whether the one or more duplicate frames are generated with intent to a client device.

18. The duplicate frames detection system of claim 16 , wherein the instructions, when executed by the one or more processors, further cause the one or more processors to determine that the one or more duplicate frames are generated without intent in response to determining the average frame distance between the one or more duplicate frames meets a threshold criteria.

19. The duplicate frames detection system of claim 16 , wherein the instructions, when executed by the one or more processors, cause the one or more processors to identify the one or more duplicate frames based at least in part on:
extracting one or more frames from content;
determining a hamming distance between each of the one or more frames and corresponding one or more adjacent frames; and
identifying the one or more duplicate frames in response to determining that the hamming distance is less than a threshold hamming distance.

Assignees

• Nbcuniversal Media Llc

Inventors

• Levin Michael S
• Lynn Christopher
• Paige Alexandra
• Hoppas Constantinos
• Nash Matthew
• Price Rachel A

Classifications

• G06F18/22 Primary

  Matching criteria, e.g. proximity measures · CPC title

• G06V20/41 Primary

  Higher-level, semantic clustering, classification or understanding of video scenes, e.g. detection, labelling or Markovian modelling of sport events or news items (segmenting video sequences G06V20/49) · CPC title

• G06V20/46

  Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames · CPC title

• G06V20/95

  Pattern authentication; Markers therefor; Forgery detection · CPC title

• G06V10/761

  Proximity, similarity or dissimilarity measures · CPC title