CN115604462A - Video compression method and system applying component analysis - Google Patents

Abstract

The invention provides a video compression method and a video compression system applying component analysis, which form a double video key frame screening mechanism by adopting a principal component analysis algorithm to screen video key frames and combining frame difference operation, thereby minimizing the correlation of video subspaces, further realizing video compression to the maximum extent and overcoming the problems of low compression ratio and serious information loss in the prior art.

Description

A video compression method and system using component analysis

technical field

The present application relates to the field of network multimedia, in particular to a video compression method and system using component analysis.

Background technique

As the length of existing video is getting larger and larger, common video compression methods focus more on data volume compression, that is, there are problems of low compression rate and serious loss of information. How to retain as much redundant information as possible while compressing while taking into account different degrees of compression according to the video content is a problem that those skilled in the art need to consider.

Therefore, there is an urgent need for a targeted method and system for video compression using component analysis.

Contents of the invention

The purpose of the present invention is to provide a video compression method and system using component analysis, which uses principal component analysis algorithm to screen video key frames, and combines frame difference calculations to form a screening mechanism for double video key frames, making the video subspace The correlation is minimized, so as to realize the maximum video compression.

In a first aspect, the present application provides a video compression method using component analysis, the method comprising:

Acquiring video data streams of a plurality of different platforms according to the acquisition strategy, and performing frame division processing on the video data streams to obtain first data in units of frames;

Performing a difference calculation between each frame of the first data and a reference frame, and estimating the difference, if the difference is within a preset range, it indicates that the frame is not much different from the reference frame and is not a key frame, removing the frame from the first data;

Input the frame by frame of the first data after the difference operation into the semantic analysis model to obtain the meaning of the word, calculate the similarity between the meaning of the word and the keyword, and when the similarity value is higher than the first threshold, give the current frame assign the first coefficient;

The first data is input into the vector matrix template to obtain the first vector matrix P1, and the transposition matrix T1 of the first vector matrix P1 is calculated; the reference frame is input into the vector matrix template to obtain the reference matrix P2, Calculating a transpose matrix T2 of the reference matrix P2, calculating the correlation between T1 and T2, and removing frames whose correlation value is higher than a second threshold to obtain second data;

generating a compression coefficient according to the first coefficient, performing compression coding on the second data to obtain a transmission data stream, and using the compression coefficient as a parameter in the compression coding;

Receive the compressed data stream sent by the other party's equipment, obtain the redundant information of the mapped data stream, which contains keywords, input the keywords into the semantic analysis model, obtain the meaning of the second word, and query to obtain the second coefficient of the corresponding category; The second coefficient generates a second compression coefficient for decompressing the compressed data stream.

In a second aspect, the present application provides a video compression system using component analysis, the system comprising:

An acquisition unit, configured to acquire a plurality of video data streams of different platforms according to an acquisition strategy, and perform frame processing on the video data streams to obtain first data in units of frames;

A preprocessing unit, configured to perform a difference operation on each frame of the first data and a reference frame, and estimate the difference, and if the difference is within a preset range, it indicates that the difference between the frame and the reference frame is the same Large, not a key frame, this frame is removed from the first data; the first data after the difference operation is input into the semantic analysis model frame by frame to obtain the meaning of the word, and the meaning of the word is combined with the keyword Perform similarity calculation, when the similarity value is higher than the first threshold, assign the first coefficient to the current frame;

A reprocessing unit, configured to input the first data into the vector matrix template to obtain the first vector matrix P1, and calculate the transposition matrix T1 of the first vector matrix P1; input the reference frame into the vector matrix template , obtain the reference matrix P2, calculate the transpose matrix T2 of the reference matrix P2, calculate the correlation between T1 and T2, and eliminate the frames whose correlation value is higher than the second threshold, and obtain the second data;

A compression unit, configured to generate a compression coefficient according to the first coefficient, and compress and encode the second data to obtain a transmission data stream, and the compression encoding uses the compression coefficient as a parameter;

The decompression unit is used to receive the compressed data stream sent by the other device, and obtain the redundant information of the mapped data stream, which contains keywords, and input the keywords into the semantic analysis model to obtain the meaning of the second word, and obtain the corresponding category of second coefficient; generating a second compression coefficient according to the second coefficient, and decompressing the compressed data stream.

In a third aspect, the present application provides a video compression system using component analysis, the system includes a processor and a memory:

The memory is used to store program codes and transmit the program codes to the processor;

The processor is configured to execute the method described in any one of the four possibilities in the first aspect according to instructions in the program code.

In a fourth aspect, the present application provides a computer-readable storage medium, where the computer-readable storage medium is used to store program code, and the program code is used to execute the method described in any one of the four possibilities in the first aspect.

Beneficial effect

The present invention provides a video compression method and system using component analysis. By adopting a principal component analysis algorithm to screen video key frames and combining frame difference calculations, a dual video key frame screening mechanism is formed, so that the correlation of video subspaces The performance is minimized, thereby realizing video compression to the greatest extent, and overcoming the problems of low compression rate and serious loss of information in the prior art.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings that need to be used in the embodiments will be briefly introduced below. Obviously, for those of ordinary skill in the art, without paying creative work Below, other drawings can also be obtained from these drawings.

Fig. 1 is a flow chart of a video compression method using component analysis of the present invention;

FIG. 2 is a structural diagram of a video compression system applying component analysis according to the present invention.

detailed description

The preferred embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, so as to define the protection scope of the present invention more clearly.

Fig. 1 is the flow chart of the video compression method of application component analysis provided by the present application, including:

Acquiring video data streams of a plurality of different platforms according to the acquisition strategy, and performing frame division processing on the video data streams to obtain first data in units of frames;

Performing a difference calculation between each frame of the first data and a reference frame, and estimating the difference, if the difference is within a preset range, it indicates that the frame is not much different from the reference frame and is not a key frame, removing the frame from the first data;

Input the frame by frame of the first data after the difference operation into the semantic analysis model to obtain the meaning of the word, calculate the similarity between the meaning of the word and the keyword, and when the similarity value is higher than the first threshold, give the current frame assign the first coefficient;

The first data is input into the vector matrix template to obtain the first vector matrix P1, and the transposition matrix T1 of the first vector matrix P1 is calculated; the reference frame is input into the vector matrix template to obtain the reference matrix P2, Calculating a transpose matrix T2 of the reference matrix P2, calculating the correlation between T1 and T2, and removing frames whose correlation value is higher than a second threshold to obtain second data;

generating a compression coefficient according to the first coefficient, performing compression coding on the second data to obtain a transmission data stream, and using the compression coefficient as a parameter in the compression coding;

Receive the compressed data stream sent by the other party's equipment, obtain the redundant information of the mapped data stream, which contains keywords, input the keywords into the semantic analysis model, obtain the meaning of the second word, and query to obtain the second coefficient of the corresponding category; The second coefficient generates a second compression coefficient for decompressing the compressed data stream.

In some preferred embodiments, different platforms preset different acquisition strategies, and the acquisition strategies are updated according to the correction records of the video features and popularity information.

In some preferred embodiments, the acquiring video data streams of multiple different platforms includes encoding and decoding the video data streams.

In some preferred embodiments, said compression encoding comprises quantization encoding.

Fig. 2 is the architectural diagram of the video compression system of application component analysis that the application provides, and described system comprises:

An acquisition unit, configured to acquire a plurality of video data streams of different platforms according to an acquisition strategy, and perform frame processing on the video data streams to obtain first data in units of frames;

A preprocessing unit, configured to perform a difference operation on each frame of the first data and a reference frame, and estimate the difference, and if the difference is within a preset range, it indicates that the difference between the frame and the reference frame is the same Large, not a key frame, this frame is removed from the first data; the first data after the difference operation is input into the semantic analysis model frame by frame to obtain the meaning of the word, and the meaning of the word is combined with the keyword Perform similarity calculation, when the similarity value is higher than the first threshold, assign the first coefficient to the current frame;

A reprocessing unit, configured to input the first data into the vector matrix template to obtain the first vector matrix P1, and calculate the transposition matrix T1 of the first vector matrix P1; input the reference frame into the vector matrix template , obtain the reference matrix P2, calculate the transpose matrix T2 of the reference matrix P2, calculate the correlation between T1 and T2, and eliminate the frames whose correlation value is higher than the second threshold, and obtain the second data;

A compression unit, configured to generate a compression coefficient according to the first coefficient, and compress and encode the second data to obtain a transmission data stream, and the compression encoding uses the compression coefficient as a parameter;

The decompression unit is used to receive the compressed data stream sent by the other device, and obtain the redundant information of the mapped data stream, which contains keywords, and input the keywords into the semantic analysis model to obtain the meaning of the second word, and obtain the corresponding category of second coefficient; generating a second compression coefficient according to the second coefficient, and decompressing the compressed data stream.

The present application provides a video compression system using component analysis, the system includes: the system includes a processor and a memory:

The memory is used to store program codes and transmit the program codes to the processor;

The processor is configured to execute the method in any one of the embodiments of the first aspect according to instructions in the program code.

The present application provides a computer-readable storage medium, where the computer-readable storage medium is used to store program code, and the program code is used to execute the method described in any one of the embodiments of the first aspect.

In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and the program may include part or all of the steps in the various embodiments of the present invention when executed. The storage medium may be a magnetic disk, an optical disk, a read-only memory (referred to as ROM) or a random access memory (referred to as RAM), and the like.

Those skilled in the art can clearly understand that the technologies in the embodiments of the present invention can be implemented by means of software plus a necessary general-purpose hardware platform. Based on this understanding, the essence of the technical solutions in the embodiments of the present invention or the part that contributes to the prior art can be embodied in the form of software products, and the computer software products can be stored in storage media, such as ROM/RAM, A magnetic disk, an optical disk, etc., include several instructions to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in various embodiments or some parts of the embodiments of the present invention.

For the same and similar parts in the various embodiments of this specification, refer to each other. In particular, as for the embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and for relevant parts, please refer to the description in the method embodiments.

The embodiments of the present invention described above are not intended to limit the protection scope of the present invention.

Claims (7)

1. A video compression method using component analysis, characterized in that the method comprises: Acquiring video data streams of a plurality of different platforms according to the acquisition strategy, and performing frame division processing on the video data streams to obtain first data in units of frames; Performing a difference calculation between each frame of the first data and a reference frame, and estimating the difference, if the difference is within a preset range, it indicates that the frame is not much different from the reference frame and is not a key frame, removing the frame from the first data; Input the frame by frame of the first data after the difference operation into the semantic analysis model to obtain the meaning of the word, calculate the similarity between the meaning of the word and the keyword, and when the similarity value is higher than the first threshold, give the current frame assign the first coefficient; The first data is input into the vector matrix template to obtain the first vector matrix P1, and the transposition matrix T1 of the first vector matrix P1 is calculated; the reference frame is input into the vector matrix template to obtain the reference matrix P2, Calculating a transpose matrix T2 of the reference matrix P2, calculating the correlation between T1 and T2, and removing frames whose correlation value is higher than a second threshold to obtain second data; generating a compression coefficient according to the first coefficient, performing compression coding on the second data to obtain a transmission data stream, and using the compression coefficient as a parameter in the compression coding; Receive the compressed data stream sent by the other party's equipment, obtain the redundant information of the mapped data stream, which contains keywords, input the keywords into the semantic analysis model, obtain the meaning of the second word, and query to obtain the second coefficient of the corresponding category; The second coefficient generates a second compression coefficient for decompressing the compressed data stream. 2. The method according to claim 1, characterized in that: different platforms preset different acquisition strategies, and the acquisition strategies are updated according to the correction records of the video features and popularity information. 3. The method according to claim 2, characterized in that: said acquiring multiple video data streams of different platforms comprises encoding and decoding the video data streams. 4. The method according to claim 3, wherein said compression coding comprises quantization coding. 5. A video compression system using component analysis, characterized in that the system comprises: An acquisition unit, configured to acquire a plurality of video data streams of different platforms according to an acquisition strategy, and perform frame processing on the video data streams to obtain first data in units of frames; A preprocessing unit, configured to perform a difference operation on each frame of the first data and a reference frame, and estimate the difference, and if the difference is within a preset range, it indicates that the difference between the frame and the reference frame is the same Large, not a key frame, this frame is removed from the first data; the first data after the difference operation is input into the semantic analysis model frame by frame to obtain the meaning of the word, and the meaning of the word is combined with the keyword Perform similarity calculation, when the similarity value is higher than the first threshold, assign the first coefficient to the current frame; A reprocessing unit, configured to input the first data into the vector matrix template to obtain the first vector matrix P1, and calculate the transposition matrix T1 of the first vector matrix P1; input the reference frame into the vector matrix template , obtain the reference matrix P2, calculate the transpose matrix T2 of the reference matrix P2, calculate the correlation between T1 and T2, and eliminate the frames whose correlation value is higher than the second threshold, and obtain the second data; A compression unit, configured to generate a compression coefficient according to the first coefficient, and compress and encode the second data to obtain a transmission data stream, and the compression encoding uses the compression coefficient as a parameter; The decompression unit is used to receive the compressed data stream sent by the other device, and obtain the redundant information of the mapped data stream, which contains keywords, and input the keywords into the semantic analysis model to obtain the meaning of the second word, and obtain the corresponding category of a second coefficient; generating a second compression coefficient according to the second coefficient, and decompressing the compressed data stream. 6. A video compression system using component analysis, characterized in that the system includes a processor and a memory: The memory is used to store program codes and transmit the program codes to the processor; The processor is configured to implement the method according to any one of claims 1-4 according to instructions in the program code. 7. A computer-readable storage medium, wherein the computer-readable storage medium is used to store program codes, and the program codes are used to implement the method according to any one of claims 1-4.

Images