Method for optimizing encoding through video category classification based on artificial intelligence, and device and system therefor
OwnerSeung Mo Kiminventor
Life of this patent
Estimating the term…
Abstract
Proposed are a method for optimizing encoding through video category classification based on artificial intelligence, and a device and a system therefor. A method for optimizing video encoding based on artificial intelligence includes dividing an input video file into groups of pictures (GOPs), performing classification of a category and extraction of feature information on each of the groups of pictures resulting from division, estimating, on the basis of the extracted feature information, a compression option value corresponding to the classified category, performing GOP-by-GOP encoding by applying the compression option value, and combining GOP-by-GOP encoded files to generate an entire video file transcoded.
Claims6
A method for optimizing video encoding based on artificial intelligence, the method comprising:
- dividing an input video file into groups of pictures (GOPs);
- performing classification of a category and extraction of feature information on each of the GOPs resulting from division;
- estimating, based on extraction of the feature information, an estimated optimal compression option value corresponding to the classification of the category by determining an optimal feature element to predict the estimated optimal compression option value for the classification of the category;
- analyzing GOP-by-GOP compression efficiency and video quality using artificial intelligence to generate an optimized compression option value;
- performing GOP-by-GOP encoding by applying the optimized compression option value for the classification of the category on the each of the GOPs to generate GOP-by-GOP encoded files;
- and
- combining the GOP-by-GOP encoded files to generate an entire video file transcoded,
- wherein the analyzing the GOP-by-GOP compression efficiency and video quality comprises re-calculating the estimated optimal compression option value using a pre-trained compression option optimization model on a basis of a result of analyzing the GOP-by-GOP compression efficiency and video quality, without physically encoding an entire video file to be generated by combining the GOP-by-GOP encoded files.
A computing device, comprising:
- a processor configured to execute instructions;
- and
- a memory configured to store the instructions,
- wherein the instructions are designed to divide an input video file into groups of pictures (GOPs), perform classification of a category and extraction of feature information on each of the GOPs resulting from division, estimate, based on extraction of the feature information, an estimated optimal compression option value corresponding to the classification of the category by determining an optimal feature element to predict the estimated optimal compression option value for the classification of the category, analyze GOP-by-GOP compression efficiency and video quality using artificial intelligence to generate an optimized compression option value, perform GOP-by-GOP encoding by applying the optimized compression option value for the classification of the category on the each of the GOPs to generate GOP-by-GOP encoded files, and combine the GOP-by-GOP encoded files to generate an entire video file transcoded, wherein the GOP-by-GOP compression efficiency and video quality is analyzed re-calculating the estimated optimal compression option value using a pre-trained compression option optimization model on a basis of a result of analyzing the GOP-by-GOP compression efficiency and video quality, without physically encoding an entire video file to be generated by combining the GOP-by-GOP encoded files.
Dependencies are inferred from the claim text.