CN113676729A - Video coding method and device, computer equipment and storage medium - Google Patents
Video coding method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN113676729A CN113676729A CN202110786709.9A CN202110786709A CN113676729A CN 113676729 A CN113676729 A CN 113676729A CN 202110786709 A CN202110786709 A CN 202110786709A CN 113676729 A CN113676729 A CN 113676729A
- Authority
- CN
- China
- Prior art keywords
- coding
- video
- encoding
- original video
- analysis processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 108
- 238000003860 storage Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 113
- 238000004458 analytical method Methods 0.000 claims abstract description 67
- 230000008569 process Effects 0.000 claims abstract description 53
- 238000013468 resource allocation Methods 0.000 claims description 15
- 238000009826 distribution Methods 0.000 claims description 2
- 230000006835 compression Effects 0.000 abstract description 13
- 238000007906 compression Methods 0.000 abstract description 13
- 238000013486 operation strategy Methods 0.000 abstract description 3
- 230000006870 function Effects 0.000 description 10
- 238000005192 partition Methods 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 230000003044 adaptive effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000012805 post-processing Methods 0.000 description 3
- 238000000638 solvent extraction Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 2
- 238000003703 image analysis method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012827 research and development Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000008901 benefit Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/90—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using coding techniques not provided for in groups H04N19/10-H04N19/85, e.g. fractals
- H04N19/96—Tree coding, e.g. quad-tree coding
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/10—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding
- H04N19/134—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using adaptive coding characterised by the element, parameter or criterion affecting or controlling the adaptive coding
- H04N19/142—Detection of scene cut or scene change
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/42—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N19/00—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
- H04N19/85—Methods or arrangements for coding, decoding, compressing or decompressing digital video signals using pre-processing or post-processing specially adapted for video compression
Abstract
The invention provides a video coding method, a video coding device, computer equipment and a storage medium. The method comprises the following steps: reading an original video to be coded, and performing at least one time of preanalysis processing on the original video to generate a coding strategy parameter through the preanalysis processing; and coding the original video according to the coding strategy parameters to obtain the coding result of the original video. The device comprises a video reading module, a pre-analysis processing module and a coding processing module. The invention can determine the coding strategy of the current video according to the needs based on the pre-analysis processing process, and different coding strategy parameters are often available for different types of videos, thereby better overcoming the problems of difficult realization of performance and area resource balance, higher complexity and the like of a common hardware encoder. The invention does not need to deeply adjust the operation strategy of the internal tool of the encoder according to the experience, ensures the reliability and the stability of the operation of the encoder and thoroughly exerts the compression performance of the encoder.
Description
Technical Field
The present invention relates to the field of video coding technologies, and in particular, to a method and an apparatus for video coding, a computer device, and a storage medium.
Background
Currently, conventional video encoder designs divide processing units by function; for a certain maximum size Coding Tree Unit (CTU), each main function is often completed correspondingly in different stages, that is, a pipeline processing architecture with processing function priority is formed. For the research and development personnel, in order to make each function reach the basic speed requirement, the responsible function module is generally realized according to the research and development experience and algorithm constraint. However, the conventional encoder schemes targeting speed requirements often suffer from some problems of excessive design of functions and waste of computational resources, resulting in excessive resource occupation by some non-critical functional modules, while insufficient resources are available for functional modules that need to improve performance.
Disclosure of Invention
In order to solve the problems of excessive design of certain functions and waste of computing resources in the conventional encoder scheme, one or more embodiments of the present invention can provide a method, an apparatus, a computer device, and a storage medium for video encoding, so as to achieve the technical purposes of optimizing an encoder, improving the performance of the encoder, and the like.
To achieve the above technical objects, the present invention can provide a method of video encoding, which may include, but is not limited to, one or more of the following steps.
And reading the original video to be coded.
And performing at least one time of pre-analysis processing on the original video to generate coding strategy parameters through the pre-analysis processing.
And coding the original video according to the coding strategy parameters to obtain a coding result of the original video.
Further, the performing at least one pre-analysis process on the original video to generate the encoding strategy parameters through the pre-analysis process includes:
and acquiring content information contained in the original video through the pre-analysis processing.
And identifying the content information to determine the target scene category of the original video according to the identification result.
And generating the coding strategy parameters according to the target scene category.
Further, the encoding policy parameter comprises a resource allocation parameter; the encoding the original video according to the encoding strategy parameters comprises:
and distributing hardware resources for each sub-processing process included in the coding processing process according to the resource distribution parameters.
Further, the encoding strategy parameters also comprise an execution strategy parameter; the encoding the original video according to the encoding strategy parameters comprises:
and setting or selecting an execution mode for each sub-processing process contained in the coding processing process according to the execution strategy parameters.
Further, the method further comprises:
receiving basic configuration information before reading an original video to be coded; the basic configuration information is used for determining a first default execution mode of the pre-analysis processing process and a second default execution mode of the encoding processing process.
Further, the method further comprises:
and recording historical encoding information, wherein the historical encoding information comprises historical encoding process information and historical encoding result information.
And feeding back and adjusting the pre-analysis processing process according to the historical coding information.
Further, the at least one pre-analysis processing on the original video comprises:
and performing pre-analysis processing on the original video by using the trained video recognition model.
To achieve the above technical objects, the present invention can also provide a video encoding apparatus, which may include, but is not limited to, a video reading module, a pre-analysis processing module, and an encoding processing module.
And the video reading module is used for reading the original video to be coded.
And the pre-analysis processing module is used for performing at least one time of pre-analysis processing on the original video so as to generate the coding strategy parameters through the pre-analysis processing.
And the coding processing module is used for coding the original video according to the coding strategy parameters to obtain a coding result of the original video.
To achieve the above technical object, the present invention can also provide a computer device, which includes a memory and a processor, wherein the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the method for video encoding according to any embodiment of the present invention.
To achieve the above technical objects, the present invention may also provide a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the steps of the method for video encoding according to any one of the embodiments of the present invention.
The invention has the beneficial effects that:
the invention can determine the coding strategy of the current video according to the needs based on the pre-analysis processing process, and different coding strategies can be provided for different types of videos, thereby better overcoming the problems of difficult realization of performance and area resource balance, higher complexity and the like of a common hardware encoder.
The invention does not need to deeply adjust the operation strategy of the internal tool of the encoder according to the experience, thereby effectively ensuring the working reliability and stability of the encoder. The invention can adjust the resources and algorithm execution strategies in the encoder according to different scene requirements, actual user requirements and the like as required, supports self-adaptive intelligent parameter configuration and user requirement parameter configuration, and can fully and thoroughly exert the compression encoding performance of the encoder equipment.
The intelligent coding technical scheme provided by the invention is beneficial to improving the compression coding efficiency and the compression coding quality of the video image, can reduce the cost of video image storage and network transmission, and has higher market value.
Drawings
Fig. 1 is a flow diagram illustrating a method of video encoding in one or more embodiments of the invention.
Fig. 2 is a block diagram illustrating an intelligent hardware video encoder framework in one or more embodiments of the invention.
FIG. 3 is a schematic diagram illustrating the circuit composition of a flexible hardware video encoder according to one or more embodiments of the invention.
Detailed Description
The following describes a method, an apparatus, a computer device and a storage medium for video encoding according to the present invention in detail with reference to the accompanying drawings.
As shown in fig. 1, and in conjunction with fig. 2 and 3, one or more embodiments of the present invention provide a method of video encoding. More specifically, the method of video encoding may include, but is not limited to, one or more of the following steps.
First, an original video to be subjected to encoding processing is read. It is understood that the original video, such as a surveillance video, a live video or a video of a television program, is determined according to the specific source scene of the original video to be processed, or according to the purpose of the original video, which is not limited by the present invention.
As shown in fig. 2, the method for video encoding according to some embodiments of the present invention further includes: receiving basic configuration information before reading an original video to be coded; and the basic configuration information is used for determining a first default execution mode of the pre-analysis processing process and a second default execution mode of the encoding processing process. The first default execution mode in this embodiment may include, but is not limited to, the operation mode of the video pre-analysis processor determined according to the analysis optimization configuration information; the second default implementation may include, but is not limited to, the flexible hardware video encoder mode of operation determined from the encoding default configuration information. Specifically, the basic configuration information in this embodiment includes, but is not limited to, top-level configuration parameters directly related to the coding performance, such as the code rate, the frame rate, and the resolution, and it can be seen that the present invention does not need to deeply adjust the operation policy of the internal tool of the encoder. In addition, the invention can also meet the requirement that the user configures the parameters determined based on the existing experience or data to the video pre-analysis processor, and the parameters include but are not limited to 2-pass (secondary) or N-pass (N times) coding results, down-sampling results, illumination information, noise intensity information and the like, so as to better analyze the content characteristics of the original video, and further, the subsequent video encoder operation strategy can be better adjusted and optimized, so as to realize performance optimization. Therefore, the invention can meet the requirement of user-defined basic requirement configuration according to the original video content scene, and is beneficial to improving the execution efficiency and compression performance of the encoder.
Secondly, at least one time of preanalysis processing is carried out on the original video, so as to generate the coding strategy parameters through the at least one time of preanalysis processing.
As shown in fig. 2, the present invention enables a video pre-analysis processor hardware to pre-analyze the raw video before it enters the hardware video encoder. Generating the encoding policy parameters through the pre-analysis process in one or more embodiments of the invention may include: acquiring content information contained in an original video through pre-analysis processing, and identifying the content information to determine a target scene category to which the original video belongs according to an identification result; and generating coding strategy parameters according to the target scene category. Specifically, the content information in the embodiment of the present invention includes, but is not limited to, an important area, a motion characteristic, a gradient, a variance, and the like of a video image, and the target scene category includes, but is not limited to, a monitoring conference scene category, a competition scene category, a live tv scene category, and the like. It can be seen that the present invention can sufficiently analyze the relevant characteristics of the original video according to the video content characteristics and/or the user target requirements before the original video enters the video encoder, so as to generate the encoding strategy parameters for guiding the encoder to adjust and optimize accordingly.
Optionally, some embodiments of the present invention perform at least one pre-analysis process on the original video, including: and performing pre-analysis processing on the original video by using the trained video recognition model. The video identification model may be generated based on a machine learning manner, or generated based on a deep learning manner, or may be obtained based on a video image analysis method, and the like, which is not limited in the present invention. On the basis, the invention can also utilize the coded result information and the process information to feed back and train or adjust the video recognition model.
Optionally, the pre-analysis processing process of the present invention may further include performing optimization processing such as pre-processing filtering according to bandwidth requirements, so as to reduce the complexity of the video image. In this way, the complexity of the original video image coding compression can be reduced, so that the video fed into the coder can be coded and compressed more easily.
Finally, the invention can carry out coding processing on the original video according to the currently generated coding strategy parameters so as to obtain the coding result of the original video. The original video may be optimized or non-optimized video, and the encoding result is compressed video, as shown in fig. 2.
As shown in fig. 3, the encoding process of the present invention includes, but is not limited to, an obtaining (Fetch) step, an Integer pixel motion estimation (IME) step, a Fractional pixel motion estimation (FME) step, a Mode Decision (MD) step, an Intra Mode Pre-Decision (PreIP) step, a Deblocking (DBK) step, a Sample Adaptive Offset (SAO) step, and an Arithmetic Entropy Coding (AEC) step. The acquiring step is realized by an acquiring module and is used for acquiring coding information from a memory (such as DDR (Double Data Rate)); the integer pixel motion estimation step is realized by an integer pixel motion estimation module and is used for performing integer pixel search on a Coding Tree Unit (CTU); the sub-pixel motion estimation step is realized by a sub-pixel motion estimation module and is used for carrying out sub-pixel search on the coding tree unit; the mode decision step is realized by a mode decision module and is used for selecting which mode to divide the macro block and realizing the mode decision step by a traditional mode decision circuit; the step of the intra-frame mode pre-decision is realized by an intra-frame mode pre-decision module and can be used for quickly pre-selecting the intra-frame mode; the deblocking step is realized by a deblocking module and can be used for performing post-processing of deblocking filtering; the sample self-adaptive bias step is realized by a sample self-adaptive bias module and is used for post-processing filtering; the step of arithmetic entropy coding is realized by an arithmetic entropy coding module and is used for performing entropy coding compression and residual calculation. Each module (i.e., encoding tool) in fig. 3 of the present invention can output the intermediate result, so as to implement more optional configurations for each module, and thoroughly break through the problem that the conventional encoder is difficult to adjust the internal hardware resource allocation and further optimize the overall performance, which means that the encoder of the present invention has very high flexibility.
In addition, the encoding process in some embodiments of the present invention may further include a SKIP (implemented by an inter-frame prediction SKIP module, which may be used to select an inter-frame prediction SKIP mode) step, so as to implement the function of the encoder, which is not described in this embodiment again.
Optionally, the encoding policy parameter in the embodiment of the present invention may include a resource allocation parameter. The encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and according to the resource allocation parameters, allocating hardware resources for each sub-processing process included in the coding processing process. For the encoder internal tools, the present embodiment can allocate hardware resources as needed for one or more of the encoder internal tools in the acquisition module, the integer-pixel motion estimation module, the sub-pixel motion estimation module, the mode decision module, the intra-mode pre-decision module, the deblocking module, the sample adaptive bias module, and the arithmetic entropy coding module according to the resource allocation parameters. Taking the monitoring of the conference scene category as an example, the motion of the object is relatively slow, i.e. only a small range needs to be searched, in this embodiment, more resources can be allocated to the Mode Decision (MD) module through the resource allocation parameters, so as to increase the intra-frame mode of the MD without excessive integer pixel motion estimation (IME) processing and sub-pixel motion estimation (FME) processing, i.e. reduce the computational resources allocated to the IME and FME. By means of the mode of distributing computing resources according to scenes, the invention can utilize the hardware of the encoder to the maximum extent, and obviously improves the performance of the whole video encoder.
Optionally, the encoding policy parameters may further include an execution policy parameter; the encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and setting or selecting an execution mode for each sub-processing procedure contained in the coding processing procedure according to the execution strategy parameters. Taking the coding tree unit partitioning process as an example, the present embodiment can select the coding tree unit partitioning manner used this time from a plurality of preset partitioning manners according to the execution policy parameters; the preset partition modes include, but are not limited to, quadtree partition (QT), binary tree partition (BT), extended quadtree partition (EQT), and the like. For example, by analyzing the original video, if it is determined that the coding speed and quality can be improved by the quadtree partition, the implementation policy parameter includes information for selecting the quadtree partition to code the current video. The embodiment specifically can set or select an execution mode for at least one of the acquisition module, the integer pixel motion estimation module, the sub-pixel motion estimation module, the mode decision module, the intra-frame mode pre-decision module, the deblocking module, the sample adaptive bias module and the arithmetic entropy coding module according to the execution strategy parameters, that is, the invention can better perform the processes of intra-frame prediction, inter-frame prediction, mode decision and the like so as to generate an optimal decision result and perform post-processing and entropy coding on the optimal decision result.
Optionally, the video encoding method of the present invention may further include: and recording historical encoding information. The historical coding information comprises historical coding process information and historical coding result information, and the pre-analysis processing process is fed back and adjusted according to the historical coding information, namely the pre-analysis processing process is fed back and adjusted according to the historical coding process information and/or the historical coding result information. The principle of the invention adopting the mode is as follows: the video images have continuity, which indicates that the video content in a period of time often has a certain correlation, and then the compression result information generated by the video images which have been subjected to encoding and compression can be used as an important reference for adjusting the encoding effect of future video images, and the compression result information includes, but is not limited to, information such as image quality and distortion, code rate fluctuation and size. Therefore, the embodiment of the invention can train and verify the video identification model by utilizing the historical coding process information and/or the historical coding result information so as to improve the identification performance of the video identification model, further improve the performance of the encoder and form a benign video processing feedback loop.
The invention also provides a video coding device based on the same technical concept as the video coding method. The apparatus may include, but is not limited to, a video reading module, a pre-analysis processing module, and an encoding processing module.
The video reading module can be used for reading the original video to be coded. The original video may be, for example, a surveillance video, a live video, a television program video, or the like.
The pre-analysis processing module can be used for performing at least one time of pre-analysis processing on the original video so as to generate the coding strategy parameters through the pre-analysis processing. The pre-analysis processing module can be integrated into the video pre-analysis processor. The pre-analysis processing module is specifically used for acquiring content information contained in the original video through pre-analysis processing, identifying the content information, determining a target scene category to which the original video belongs according to an identification result, and generating an encoding strategy parameter according to the target scene category. It can be seen that the present invention can sufficiently analyze the relevant characteristics of the original video according to the video content characteristics and/or the user target requirements before the original video enters the video encoder, so as to generate the encoding strategy parameters for guiding the encoder to adjust and optimize accordingly.
Optionally, the pre-analysis processing module may be configured to perform pre-analysis processing on the original video by using the trained video recognition model. The video identification model can be generated based on a machine learning mode, or generated based on a deep learning mode, or obtained based on a video image analysis method and the like.
The encoding policy parameters in the embodiment of the present invention include, but are not limited to, resource allocation parameters and execution policy parameters.
The encoding processing module can be used for encoding the original video according to the encoding strategy parameters to obtain the encoding result of the original video. The encoding processing module in the embodiment of the invention can be integrated in a flexible hardware video encoder.
The encoding processing module is specifically configured to allocate hardware resources to each sub-processing procedure included in the encoding processing procedure according to the resource allocation parameter, and to set or select an execution mode for each sub-processing procedure included in the encoding processing procedure according to the execution policy parameter.
Optionally, the video coding apparatus further includes a top-level configuration module. The top configuration module is used for receiving basic configuration information before the video reading module reads an original video to be coded; the basic configuration information is used to determine a first default execution mode of the pre-analysis processing procedure and a second default execution mode of the encoding processing procedure. The first default execution mode includes but is not limited to the operation mode of the video pre-analysis processor determined according to the analysis optimization configuration information; the second default implementation includes, but is not limited to, the flexible hardware video encoder mode of operation determined from the encoding default configuration information.
Optionally, the apparatus for video encoding further comprises a feedback adjustment module. The feedback adjusting module is used for recording historical coding information and feeding back and adjusting the pre-analysis processing process according to the historical coding information, and the historical coding information comprises historical coding process information and historical coding result information.
Therefore, the embodiment of the invention can provide an intelligent hardware video encoder framework, and can be applied to flexible and configurable hardware encoders such as an FPGA (field programmable gate array) to balance resource allocation and compression performance, thereby effectively solving one or more technical problems in the prior art.
In conclusion, the invention can provide a brand-new intelligent hardware video encoder framework, and thoroughly solves the problems of unreasonable module computing resource allocation and unbalanced performance benefit of the traditional hardware encoder framework. Through the pre-analysis processing, the invention can allocate more resources to the modules which are more beneficial to improving the performance of the encoder. The intelligent hardware video encoder framework based on the video compression method meets the user-defined setting requirements, meets the requirements that a user flexibly adopts basic experience configuration and a self-adaptive strategy mode to optimize and improve the performance of the encoder according to the scene type of the video, and realizes better encoding and compression of the video.
Based on the same technical concept as the video encoding method of the present invention, the present invention can also provide a computer device, where the computer device includes a memory and a processor, and the memory stores computer readable instructions, and the computer readable instructions, when executed by the processor, cause the processor to execute the steps of the video encoding method in any embodiment of the present invention. The method of video encoding includes, but is not limited to, the steps of: first, an original video to be subjected to encoding processing is read. Optionally, the video encoding method of the present invention further includes: receiving basic configuration information before reading an original video to be coded; the basic configuration information is used to determine a first default execution mode of the pre-analysis processing procedure and a second default execution mode of the encoding processing procedure. Secondly, at least one time of preanalysis processing is carried out on the original video so as to generate the coding strategy parameters through the preanalysis processing. In some embodiments of the present invention, generating the encoding policy parameter through the pre-analysis process includes: acquiring content information contained in an original video through pre-analysis processing, and identifying the content information to determine a target scene category to which the original video belongs according to an identification result; and generating coding strategy parameters according to the target scene category. Optionally, some embodiments of the present invention perform at least one pre-analysis process on the original video, including: and performing pre-analysis processing on the original video by using the trained video recognition model. And finally, coding the original video according to the coding strategy parameters to obtain a coding result of the original video. Optionally, the encoding policy parameter comprises a resource allocation parameter; the encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and according to the resource allocation parameters, allocating hardware resources for each sub-processing process included in the coding processing process. Optionally, the encoding policy parameters further include an execution policy parameter; the encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and setting or selecting an execution mode for each sub-processing procedure contained in the coding processing procedure according to the execution strategy parameters. Optionally, the video encoding method of the present invention further includes: recording historical encoding information, wherein the historical encoding information comprises historical encoding process information and historical encoding result information; and feeding back and adjusting the pre-analysis processing process according to the historical coding information.
The present invention also provides a storage medium storing computer-readable instructions, which when executed by one or more processors, cause the one or more processors to perform the steps of the method for video encoding according to any of the embodiments of the present invention. The method of video encoding includes, but is not limited to, the steps of: first, an original video to be subjected to encoding processing is read. Optionally, the video encoding method of the present invention further includes: receiving basic configuration information before reading an original video to be coded; the basic configuration information is used to determine a first default execution mode of the pre-analysis processing procedure and a second default execution mode of the encoding processing procedure. Secondly, at least one time of preanalysis processing is carried out on the original video so as to generate the coding strategy parameters through the preanalysis processing. In some embodiments of the present invention, generating the encoding policy parameter through the pre-analysis process includes: acquiring content information contained in an original video through pre-analysis processing, and identifying the content information to determine a target scene category to which the original video belongs according to an identification result; and generating coding strategy parameters according to the target scene category. Optionally, some embodiments of the present invention perform at least one pre-analysis process on the original video, including: and performing pre-analysis processing on the original video by using the trained video recognition model. And finally, coding the original video according to the coding strategy parameters to obtain a coding result of the original video. Optionally, the encoding policy parameter comprises a resource allocation parameter; the encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and according to the resource allocation parameters, allocating hardware resources for each sub-processing process included in the coding processing process. Optionally, the encoding policy parameters further include an execution policy parameter; the encoding processing of the original video according to the encoding strategy parameters comprises the following steps: and setting or selecting an execution mode for each sub-processing procedure contained in the coding processing procedure according to the execution strategy parameters. Optionally, the video encoding method of the present invention further includes: recording historical encoding information, wherein the historical encoding information comprises historical encoding process information and historical encoding result information; and feeding back and adjusting the pre-analysis processing process according to the historical coding information.
The logic and/or steps represented in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable storage medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer cartridge (magnetic device), a Random Access Memory (RAM), a Read-Only Memory (ROM), an Erasable Programmable Read-Only Memory (EPROM-Only Memory, or flash Memory), an optical fiber device, and a portable Compact Disc Read-Only Memory (CDROM). Additionally, the computer-readable storage medium may even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic Gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic Gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "the present embodiment," "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents and simplifications made in the spirit of the present invention are intended to be included in the scope of the present invention.
Claims (10)
1. A method of video encoding, comprising:
reading an original video to be coded;
performing at least one time of pre-analysis processing on the original video to generate a coding strategy parameter through the pre-analysis processing;
and coding the original video according to the coding strategy parameters to obtain a coding result of the original video.
2. The method of claim 1, wherein the performing at least one pre-analysis process on the original video to generate the encoding strategy parameters through the pre-analysis process comprises:
acquiring content information contained in the original video through the pre-analysis processing;
identifying the content information to determine the target scene category of the original video according to an identification result;
and generating the coding strategy parameters according to the target scene category.
3. The method of claim 1 or 2, wherein the encoding policy parameters comprise resource allocation parameters; the encoding the original video according to the encoding strategy parameters comprises:
and distributing hardware resources for each sub-processing process included in the coding processing process according to the resource distribution parameters.
4. The method of claim 3, wherein the encoding strategy parameters further comprise an enforcement strategy parameter; the encoding the original video according to the encoding strategy parameters comprises:
and setting or selecting an execution mode for each sub-processing process contained in the coding processing process according to the execution strategy parameters.
5. The method of video coding according to claim 1 or 2, further comprising:
receiving basic configuration information before reading an original video to be coded; the basic configuration information is used for determining a first default execution mode of the pre-analysis processing process and a second default execution mode of the encoding processing process.
6. The method of video coding according to claim 1, further comprising:
recording historical encoding information, wherein the historical encoding information comprises historical encoding process information and historical encoding result information;
and feeding back and adjusting the pre-analysis processing process according to the historical coding information.
7. The method of claim 1 or 2, wherein the at least one pre-analysis processing on the original video comprises:
and performing pre-analysis processing on the original video by using the trained video recognition model.
8. An apparatus for video encoding, comprising:
the video reading module is used for reading an original video to be coded;
the pre-analysis processing module is used for performing at least one time of pre-analysis processing on the original video so as to generate a coding strategy parameter through the pre-analysis processing;
and the coding processing module is used for coding the original video according to the coding strategy parameters to obtain a coding result of the original video.
9. A computer device comprising a memory and a processor, the memory having stored therein computer-readable instructions which, when executed by the processor, cause the processor to carry out the steps of the method of video encoding according to any one of claims 1 to 7.
10. A storage medium having computer-readable instructions stored thereon, which, when executed by one or more processors, cause the one or more processors to perform the steps of the method of video encoding as claimed in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110786709.9A CN113676729A (en) | 2021-07-12 | 2021-07-12 | Video coding method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110786709.9A CN113676729A (en) | 2021-07-12 | 2021-07-12 | Video coding method and device, computer equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113676729A true CN113676729A (en) | 2021-11-19 |
Family
ID=78538978
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110786709.9A Pending CN113676729A (en) | 2021-07-12 | 2021-07-12 | Video coding method and device, computer equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113676729A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925226A (en) * | 2022-06-22 | 2022-08-19 | 上海威固信息技术股份有限公司 | Image storage method, system, image storage device and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190028741A1 (en) * | 2017-07-21 | 2019-01-24 | Cisco Technology, Inc. | Distributed learning video encoder/decoder |
| CN110312131A (en) * | 2019-07-01 | 2019-10-08 | 杭州当虹科技股份有限公司 | A kind of content-adaptive Online Video coding method based on deep learning |
| CN111787319A (en) * | 2020-07-22 | 2020-10-16 | 腾讯科技（深圳）有限公司 | Video information processing method, multimedia information processing method and device |
| CN112738511A (en) * | 2021-04-01 | 2021-04-30 | 杭州微帧信息科技有限公司 | Fast mode decision method and device combined with video analysis |
-
2021
- 2021-07-12 CN CN202110786709.9A patent/CN113676729A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190028741A1 (en) * | 2017-07-21 | 2019-01-24 | Cisco Technology, Inc. | Distributed learning video encoder/decoder |
| CN110312131A (en) * | 2019-07-01 | 2019-10-08 | 杭州当虹科技股份有限公司 | A kind of content-adaptive Online Video coding method based on deep learning |
| CN111787319A (en) * | 2020-07-22 | 2020-10-16 | 腾讯科技（深圳）有限公司 | Video information processing method, multimedia information processing method and device |
| CN112738511A (en) * | 2021-04-01 | 2021-04-30 | 杭州微帧信息科技有限公司 | Fast mode decision method and device combined with video analysis |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114925226A (en) * | 2022-06-22 | 2022-08-19 | 上海威固信息技术股份有限公司 | Image storage method, system, image storage device and storage medium |
| CN114925226B (en) * | 2022-06-22 | 2023-03-10 | 上海威固信息技术股份有限公司 | Image storage method, system, image storage device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110300977B (en) | Method for image processing and video compression | |
| US10200687B2 (en) | Sample adaptive offset for high dynamic range (HDR) video compression | |
| CN104885455B (en) | A kind of computer implemented method and device for Video coding | |
| JP5606591B2 (en) | Video compression method | |
| US9350990B2 (en) | Systems and methods of encoding multiple video streams with adaptive quantization for adaptive bitrate streaming | |
| CN105308960A (en) | Adaptive color space transform coding | |
| CN112351280B (en) | Video encoding method, video encoding device, electronic equipment and readable storage medium | |
| CN113545063B (en) | Method and device for intra-frame prediction by using linear model | |
| CN110199524A (en) | Noise inhibiting wave filter | |
| WO2014190308A1 (en) | Systems and methods of encoding multiple video streams with adaptive quantization for adaptive bitrate streaming | |
| CN106031177A (en) | Host encoder for hardware-accelerated video encoding | |
| US9451271B2 (en) | Adaptive filtering based on pattern information | |
| CN101779465A (en) | Method and apparatus for improved video encoding using region of interest (roi) information | |
| DE102016125604A1 (en) | Intelligent sorting of recursive block partitioning for advanced intra-prediction in video coding | |
| Viitanen et al. | From HEVC to VVC: the first development steps of a practical intra video encoder | |
| CN113676729A (en) | Video coding method and device, computer equipment and storage medium | |
| CN112087624A (en) | Coding management method based on high-efficiency video coding | |
| US9736485B2 (en) | Encoding apparatus, encoding method, and image capture apparatus | |
| US8687710B2 (en) | Input filtering in a video encoder | |
| US20140362927A1 (en) | Video codec flashing effect reduction | |
| Wang et al. | Region-of-interest based dynamical parameter allocation for H. 264/AVC encoder | |
| JP2024511084A (en) | Multidistribution entropy modeling of latency features in image and video coding using neural networks | |
| US8265141B2 (en) | System and method for open loop spatial prediction in a video encoder | |
| Jubran et al. | Sequence-level reference frames in video coding | |
| CN110611815A (en) | Video output method and device and storage device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |