Method, electronic apparatus and storage medium for detecting a static logo of a video

Patent metadata

Field	Value
Publication number	US-11710315-B2
Application number	US-202117443843-A
Country	US
Kind code	B2
Filing date	Jul 28, 2021
Priority date	Jul 30, 2020
Publication date	Jul 25, 2023
Grant date	Jul 25, 2023

Abstract

A method for detecting a static logo of a video, an electronic apparatus and a storage medium. The method includes: calculating a pixel grayscale flag value, an edge gradient flag value and an edge direction flag value; calculating, in a preset neighborhood centered on the pixel at each pixel position of the current video frame, a first local confidence degree of the pixel grayscale flag value, a second local confidence degree of the edge gradient flag value, and a third local confidence degree of the edge direction flag value respectively; calculating a contribution score of each local confidence degree and a total contribution score of each pixel position; and gathering the total contribution score of each pixel position of the current video frame, and determining a static logo in the current video frame according to the total contribution score of each pixel position.

First claim

The invention claimed is:

1. A method for detecting a static logo of a video, comprising:
calculating an absolute value of a difference value between a pixel grayscale value of each pixel position in a current video frame and a pixel grayscale value of a corresponding pixel position in an immediately preceding video frame, and obtaining a pixel grayscale flag value of the each pixel position according to the absolute value;
calculating a grayscale gradient between a pixel at each pixel position in the current video frame and a pixel in a preset neighborhood of the pixel, and obtaining an edge gradient flag value of each pixel position according to the grayscale gradient;
determining a pixel position having an edge according to the grayscale gradient, and determining an edge direction of a pixel at the pixel position having the edge according to the grayscale gradient of the pixel at the pixel position having the edge;
calculating, in the preset neighborhood centered on the pixel at the pixel position having the edge in the current video frame, a local direction correlation coefficient between the edge direction of the pixel at the pixel position having the edge in the current video frame and an edge direction of a pixel at the corresponding pixel position of the immediately preceding video frame, and determining an edge direction flag value of the pixel at the pixel position having the edge according to the local direction correlation coefficient;
calculating, in a preset neighborhood centered on the pixel at each pixel position in the current video frame, a first local confidence degree of the pixel grayscale flag value, a second local confidence degree of the edge gradient flag value, and a third local confidence degree of the edge direction flag value respectively;
calculating a first contribution score of the first local confidence degree, a second contribution score of the second local confidence degree and a third contribution score of the third local confidence degree respectively, and calculating a total contribution score of the first contribution score, the second contribution score and the third contribution score; and
gathering the total contribution score of each pixel position of the current video frame, and determining a static logo in the current video frame according to the total contribution score of each pixel position.

2. The method for detecting a static logo of a video according to claim 1 , wherein said obtaining a pixel grayscale flag value of the each pixel position according to the absolute value comprises:
assigning a value of 1 to the pixel grayscale flag value when the absolute value is less than a grayscale difference threshold, and
assigning a value of 0 to the pixel grayscale flag value when the absolute value is greater than or equal to the grayscale difference threshold.

3. The method for detecting a static logo of a video according to claim 1 , wherein said calculating a grayscale gradient between a pixel at each pixel position in the current video frame and a pixel in a preset neighborhood of the pixel, and obtaining an edge gradient flag value of each pixel position according to the grayscale gradient comprises:
calculating a grayscale gradient between a current pixel of the current video frame and a pixel in the preset neighborhood of the current pixel using a gradient operator with a size of m*n;
assigning a value of 1 to the edge gradient flag value of the current pixel when the grayscale gradient is greater than a gradient threshold; and
assigning a value of 0 to the edge gradient flag value when the grayscale gradient is less than or equal to the gradient threshold.

4. The method for detecting a static logo of a video according to claim 1 , wherein said determining a pixel position having an edge according to the grayscale gradient, and determining an edge direction of a pixel at the pixel position having the edge according to the grayscale gradient of the pixel at the pixel position having the edge comprises:
determining the pixel position as the pixel position having the edge if the grayscale gradient is greater than a gradient threshold; and
determining an edge direction of the pixel at the pixel position having the edge according to the pixel position having the edge and a change trend of the grayscale gradient of a pixel at a pixel position within the preset neighborhood.

5. The method for detecting a static logo of a video according to claim 1 , wherein said calculating, in the preset neighborhood centered on the pixel at the pixel position having the edge in the current video frame, a local direction correlation coefficient between the edge direction of a pixel at the pixel position having the edge in the current video frame and an edge direction of the pixel at the corresponding pixel position of the immediately preceding video frame, and determining an edge direction flag value of the pixel at the pixel position having the edge according to the local direction correlation coefficient comprises:
obtaining, in the preset neighborhood centered on the pixel at the current pixel position having the edge, a local direction correlation coefficient between an edge direction of the pixel at the current pixel position having the edge and an edge direction of the pixel at the corresponding pixel position of an immediately preceding video frame according to any of a least squares correlative method, a mean-square error method and a structural similarity index method;
assigning a value of 1 to the edge direction flag value of the current pixel position having the edge when the local direction correlation coefficient is greater than a preset direction correlation coefficient threshold; and
assigning a value of 0 to the edge direction flag value of the current pixel position having the edge when the local direction correlation coefficient is less than or equal to the preset direction correlation coefficient threshold.

6. The method for detecting a static logo of a video according to claim 5 , wherein in the mean-square error (MSE) method, the local direction correlation coefficient is calculated according to

MSE
=

1

M
*
N

⁢

∑

i
=
1

N

⁢

∑

j
=
1

M

⁢

(



f
t

⁡

(

i
,
j

)

-

Assignees

• Amlogic Shanghai Co Ltd

Inventors

• Ji Tao
• He Zhihong
• Wang Chun
• Wang Dongjian
• Chen Xuyun

Classifications

• G06V20/40 Primary

  in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) · CPC title

• G06F18/22

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

• G06T7/73

  using feature-based methods · CPC title

• G06V10/44

  Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components · CPC title

• G06V20/46

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