Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Implementation method of mosaic detection based on fixed video

An implementation method and mosaic technology, applied in the field of image recognition, can solve the problems of missed mosaic detection, high cost, complex final image of video images, etc., and achieve high detection efficiency, low missed detection and false detection rates, and effective software and hardware quality detection. Effect

Active Publication Date: 2020-12-29
SICHUAN CHANGHONG ELECTRIC CO LTD
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Researchers have used the edge detection method of straight lines and rectangles to judge mosaics, but due to the limitations of edge detection itself, regular images such as straight lines, chessboards, and windows in video content are easy to be misjudged. Mosaic is easy to be missed
There are also mosaic feature pre-analysis and deep learning methods to classify and learn mosaic feature values, but due to the complexity of the video image and the final image formed after the mosaic is superimposed, the final image is more complex, so the features learned in advance are completely incompatible.
[0004] Therefore, at present, the video mosaic test is basically performed by manual judgment in the industry, which has low efficiency, high cost, and high missed and false detection rates.

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Implementation method of mosaic detection based on fixed video
  • Implementation method of mosaic detection based on fixed video

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] Such as figure 1 As shown, the implementation method of mosaic detection based on fixed video in this embodiment includes the following steps:

[0052] 1. Prepare a video;

[0053] In this step, the video is an ordinary video, and no information needs to be added to the video;

[0054] 2. Extract and store the feature values ​​of each frame image in the video to form a standard feature library;

[0055] In this step, the process of extracting the feature values ​​of each frame image is as follows:

[0056] 21. Reduce the size: reduce the image to 8*8, thereby simplifying the amount of calculation;

[0057] 22. Simplify color: convert the image into a grayscale image, further simplifying the amount of calculation;

[0058] 23. Calculate DCT: Calculate the DCT transformation of the picture to obtain a 32*32 DCT coefficient matrix;

[0059] 24. Reduce the DCT: only retain the 8*8 scale DCT coefficient matrix in the upper left corner of the DCT coefficient matrix, this p...

Embodiment 2

[0070] The implementation method of mosaic detection based on fixed video in this embodiment is as follows figure 2 As shown, it includes the following steps:

[0071] 1. Prepare a video;

[0072] 2. Preprocess the video: add a time stamp to each frame of the video; set a QR code for each second of video, so that each frame of each second of video has the same QR code;

[0073] 3. Extract and store the feature values ​​of each frame image in the video to form a standard feature library;

[0074] In this step, the process of extracting the feature values ​​of each frame image is as follows:

[0075] 31. Reduce the size: reduce the image to 8*8, thereby simplifying the amount of calculation;

[0076] 32. Simplify color: convert the image into a grayscale image, further simplifying the amount of calculation;

[0077] 33. Calculate DCT: Calculate the DCT transformation of the picture to obtain a 32*32 DCT coefficient matrix;

[0078] 34. Reduce the DCT: only retain the 8*8 s...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of image recognition, which discloses a mosaic detection realization method based on fixed video, which realizes automatic detection of video mosaic with high efficiency and accuracy. The method comprises the following steps of: a. preparing a preprocessed video, wherein the preprocessed video is that a time stamp is added to each frame image of the video; setting a two-dimensional code for each second video so that each frame image in each second video has the same two-dimensional code; b. extracting the eigenvalues of each frame image in the video and storing the eigenvalues to form a standard feature library; c. when that mosaic detection is carry out,playing the video by the equipment to be tested, and the video image is captured in real time by a computer for image acquisition; d. calculating the eigenvalues of the captured images and comparing the eigenvalues with the eigenvalues in the standard feature library to judge whether the video has mosaic or not.

Description

technical field [0001] The invention relates to the field of image recognition, in particular to a method for realizing mosaic detection based on fixed video. Background technique [0002] In traditional set-top boxes, the main basis for TUNER performance testing is video mosaic. In OTT and IPTV set-top boxes, video playback mosaic is an important test basis for checking the memory performance and software reliability of set-top boxes. Therefore, video mosaic detection is very important. However, due to the random timing and irregular graphics of the mosaic, especially for set-top boxes with post-processing functions, the shape of the mosaic after image restoration is more complicated. As a result, automated mosaic detection has always been a pain point and difficulty in the industry. [0003] Researchers have used the edge detection method of straight lines and rectangles to judge mosaics, but due to the limitations of edge detection itself, regular images such as straigh...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): H04N21/44H04N21/8547G06K19/06
CPCG06K19/06037H04N21/44008H04N21/8547
Inventor 靳国荣昝元宝邹书强
Owner SICHUAN CHANGHONG ELECTRIC CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products