CN109561324A - The processing system for video and processing method of software definition - Google Patents

The processing system for video and processing method of software definition Download PDF

Info

Publication number
CN109561324A
CN109561324A CN201811234417.9A CN201811234417A CN109561324A CN 109561324 A CN109561324 A CN 109561324A CN 201811234417 A CN201811234417 A CN 201811234417A CN 109561324 A CN109561324 A CN 109561324A
Authority
CN
China
Prior art keywords
video
information
terminal
unit
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.)
Granted
Application number
CN201811234417.9A
Other languages
Chinese (zh)
Other versions
CN109561324B (en
Inventor
纪雯
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Institute of Computing Technology of CAS
Original Assignee
Institute of Computing Technology of CAS
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Institute of Computing Technology of CAS filed Critical Institute of Computing Technology of CAS
Priority to CN201811234417.9A priority Critical patent/CN109561324B/en
Publication of CN109561324A publication Critical patent/CN109561324A/en
Application granted granted Critical
Publication of CN109561324B publication Critical patent/CN109561324B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/238—Interfacing the downstream path of the transmission network, e.g. adapting the transmission rate of a video stream to network bandwidth; Processing of multiplex streams
    • H04N21/23805—Controlling the feeding rate to the network, e.g. by controlling the video pump
    • 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
    • H04N19/436—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 using parallelised computational arrangements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/23—Processing of content or additional data; Elementary server operations; Server middleware
    • H04N21/238—Interfacing the downstream path of the transmission network, e.g. adapting the transmission rate of a video stream to network bandwidth; Processing of multiplex streams
    • H04N21/2385—Channel allocation; Bandwidth allocation
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/251—Learning process for intelligent management, e.g. learning user preferences for recommending movies
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/262—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists
    • H04N21/26208—Content or additional data distribution scheduling, e.g. sending additional data at off-peak times, updating software modules, calculating the carousel transmission frequency, delaying a video stream transmission, generating play-lists the scheduling operation being performed under constraints
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/20—Servers specifically adapted for the distribution of content, e.g. VOD servers; Operations thereof
    • H04N21/25—Management operations performed by the server for facilitating the content distribution or administrating data related to end-users or client devices, e.g. end-user or client device authentication, learning user preferences for recommending movies
    • H04N21/266—Channel or content management, e.g. generation and management of keys and entitlement messages in a conditional access system, merging a VOD unicast channel into a multicast channel
    • H04N21/2662—Controlling the complexity of the video stream, e.g. by scaling the resolution or bitrate of the video stream based on the client capabilities
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N21/00—Selective content distribution, e.g. interactive television or video on demand [VOD]
    • H04N21/40—Client devices specifically adapted for the reception of or interaction with content, e.g. set-top-box [STB]; Operations thereof
    • H04N21/45—Management operations performed by the client for facilitating the reception of or the interaction with the content or administrating data related to the end-user or to the client device itself, e.g. learning user preferences for recommending movies, resolving scheduling conflicts
    • H04N21/466—Learning process for intelligent management, e.g. learning user preferences for recommending movies

Abstract

The present invention provides a kind of processing system for video and processing method based on software definition.The system includes: isomerous environment sensing module, for obtaining the video terminal information of video terminal；Video information preprocessing module, for being video terminal selection delay and/or Bandwidth Allocation Policy according to the channel state information in the video terminal information and/or video processing procedure；Video processing duties are decomposed into the multiple subtasks executed by multiple processing units for determining the decomposition strategy of video processing duties based on the channel state information in the video terminal information and/or video processing procedure by resource scheduling management module.The control plane of video processing procedure and data surface can be separated using processing system for video of the invention, and more flexible video processing architecture is provided, to meet diversified user demand.

Description

The processing system for video and processing method of software definition
Technical field
The present invention relates to multimedia technology field more particularly to a kind of processing system for video and processing based on software definition Method.
Background technique
Increasingly developed with multimedia communication technology, the various applications based on video are grown rapidly, but due to The diversity of user terminal and the isomerism of network need Video service end to provide the service of differentiation, accordingly, it is desirable to be able to obtain It takes real-time user terminal and the network information and coding-control can be carried out to video information.
However, current video encoder generallys use hybrid encoding frame, by adjusting coding parameter, such as regulated quantity Change parameter and generate different code rate outputs, adjust frame per second and generate different time resolutions, and if to generate SD, it is super it is clear, When HD video, it would be desirable to a variety of coder structures.It, can only be according to being previously set and based on current video coding framework Good coding parameter or encryption algorithm is forwarded data packet, and control plane is together with data surface close-coupled, logical decision Face and distributed hardware facility combination tension.Therefore, the hybrid coding structure of the prior art lacks flexibility, cannot be sufficiently sharp With the efficient computing resource such as cloud computing, and the diversified demand of unsuitable current user and various types of visual Equipment.
To solve the above problems, software definition video technique comes into being, it is a kind of realization unrelated with infrastructure Flexibly, expansible and can be easily scalable video architecture, this mode allows video provider software deployment in privately owned and public There are the customization of optimum organization and virtualization resource in data center, video provider is made to exempt the limitation of equipment for customizing, it will be best Framework and processor combination for specifically apply, even if the application changes over time.To the branch of new demand servicing and video format Holding can be by simple software upgrading Seamless integration-.Although there has been proposed the concepts of software video technology at present, for tool There are no mature schemes for the framework of realizing of body.
Therefore, in view of the above-mentioned problems, the present invention provides the processing system for video or framework of a kind of software definition.
Summary of the invention
The present invention is to overcome the defect of the above-mentioned prior art, provides a kind of processing system for video based on software definition and place Reason method needs to provide the Video service of differentiation can be directed to a plurality of types of video terminals and different users.
According to the first aspect of the invention, a kind of processing system for video based on software definition is provided.The system includes:
Isomerous environment sensing module: for obtaining the video terminal information of video terminal, wherein the video terminal information The preference of video is watched including video terminal type, the attribute information of video terminal, the resource state information of video terminal, user At least one of in；
Video information preprocessing module: for according to the channel in the video terminal information and/or video processing procedure Status information is video terminal selection delay and/or Bandwidth Allocation Policy；
Resource scheduling management module: for based on the channel shape in the video terminal information and/or video processing procedure State information determines the decomposition strategy of video processing duties, video processing duties are decomposed into executed by multiple processing units it is more A subtask.
In one embodiment, the isomerous environment sensing module includes that low latitude terminal device sension unit, ground are fixed At least one of terminal sension unit, terrestrial mobile terminal sension unit and user's sension unit, wherein
The low latitude terminal device sension unit is used to perceive the video terminal information that type is low latitude equipment, the ground Fixed terminal sension unit is used to perceive the video terminal information that type is ground fixed terminal, the terrestrial mobile terminal perception Unit is used to perceive the video terminal information that type is terrestrial mobile terminal, and user's sension unit is for obtaining user's viewing The preference of video.
In one embodiment, the video information preprocessing module includes resource status collector unit, video information knowledge Not and filter element, policy management element, isomery video information perceive fusion calculation unit, isomery video information timing management list Member, in which:
The resource status collector unit is used to obtain channel state information in video processing procedure and/or from described different Structure environmental perception module receives the video terminal information；
The video information identification and filter element are used to carry out video information content recognition and extract key frame Characteristics of image；
The policy management element be used for according to from the resource status collector unit video terminal information and/or Channel state information in video processing procedure is the suitable delay of each video information selection or Bandwidth Allocation Policy；
The isomery video information perception fusion calculation unit is used to calculate the amalgamation mode of multiple video informations；
The isomery video information timing management unit is used to manage the processing sequence of multiple video informations.
In one embodiment, the resource scheduling management module includes Task-decomposing computing unit, multitask decision list Member, equipment of more dwelling Topology Management unit, user interface unit, dwell equipment collaboration scheduling unit, performance evaluation and tracking more Unit, performance prediction unit and feedback unit, in which:
The Task-decomposing computing unit is multiple subtasks for video information process Task-decomposing, multiple to be distributed to Processing unit executes；
The multitask decision package is used for based on the channel shape in the video terminal information and/or video processing procedure State information decision goes out the video terminal scheduling strategy optimized；
The equipment Topology Management unit of dwelling for providing the connection relationship of video terminal more；
The user interface unit is for receiving user to the quality requirement of vision signal；
The equipment collaboration scheduling unit of dwelling whole for going out the video optimized based on the multitask decision package decision more End scheduling strategy carrys out schedule video information；
The performance evaluation and tracking cell are used to monitor the performance of each processing unit in video processing procedure, to be supervised Survey results of property；
The performance prediction unit is used for the decision to the multitask decision package and the Task-decomposing computing unit It is predicted, to obtain estimated performance result.
The feedback unit is used to feed back the prison to the multitask decision package and the Task-decomposing computing unit Survey results of property and the estimated performance result.
In one embodiment, the multitask decision package is also used to the video image quality information required according to user Or the Monitoring Performance result or the estimated performance result decision go out the video terminal scheduling strategy optimized.
In one embodiment, the attribute information of the video terminal include movement speed, processing capacity, current electric quantity, At least one of connection type.
In one embodiment, the video terminal type includes low latitude terminal device, ground fixed terminal, ground moving At least one of terminal.
According to the second aspect of the invention, a kind of method for processing video frequency based on software definition is provided.This method includes Following steps:
Step 1: different types of video terminal information is obtained, wherein the video terminal information includes video terminal class Type, the attribute information of video terminal, the resource state information of video terminal, user watch video preference at least one of；
Step 2: being the video according to the channel state information in the video terminal information and/or video processing procedure Terminal selection delay and/or Bandwidth Allocation Policy；
Step 3: being determined at video based on the channel state information in the video terminal information and/or video processing procedure Video processing duties are decomposed into the multiple subtasks executed by multiple processing units by the decomposition strategy of reason task.
Compared with the prior art, the advantages of the present invention are as follows: it, can be by video by the processing system for video of software definition The control plane of information process is separated with data surface, to realize visual information/video information from acquisition, pretreatment to volume The flexible control of the operations such as code generates the video of arbitrary resolution, any code stream；In addition, the present invention can be realized visual information Flexible encoding and decoding and acquisition, sufficiently dispatch the resources such as cloud computing, realize visual information processing rapidly and efficiently.
Detailed description of the invention
The following drawings only makees schematical description and interpretation to the present invention, is not intended to limit the scope of the present invention, in which:
Fig. 1 shows a kind of signal of processing system for video based on software definition according to an embodiment of the invention Figure；
Fig. 2 shows the structural schematic diagrams of the isomerous environment sensing module in Fig. 1 system；
Fig. 3 shows the structural schematic diagram of the video information preprocessing module in Fig. 1 system；
Fig. 4 shows the structural schematic diagram of the resource scheduling management module in Fig. 1 system；
Fig. 5 shows the schematic diagram of the video information process process based on processing system for video of the invention.
Specific embodiment
It is logical below in conjunction with attached drawing in order to keep the purpose of the present invention, technical solution, design method and advantage more clear Crossing specific embodiment, the present invention is described in more detail.It should be appreciated that specific embodiment described herein is only to explain The present invention is not intended to limit the present invention.
According to one embodiment of present invention, a kind of processing system for video (or software based on software definition is provided Controller), which can be realized the control plane function in video coding process, the specific coding realized for guide data face Process will introduce the function of the modules and unit of processing system herein, and to the encoded of general various standards Cheng Buzai is introduced.
Shown in Figure 1, which includes isomerous environment sensing module 110,120 and of video information preprocessing module Resource scheduling management module 130.
Isomerous environment sensing module 110 is used to perceive the relevant information of video terminal, including terminal type, video terminal Attribute information and the resource state information of video terminal etc., wherein terminal type is related to geographical location locating for terminal, example Such as include low latitude terminal device, terrestrial mobile terminal equipment, ground fixed terminal equipment, attribute information include movement speed, Processing capacity, current electric quantity, connection type etc., resource state information include such as the available resources situation of video terminal.It is different Structure environmental perception module 110 establishes the location index of each video frequency terminal apparatus, and to video information preprocessing module 120 and resource Dispatching management module 130 provides required video terminal information.
Video information preprocessing module 120 is used for according to the video terminal information from isomerous environment sensing module 110 And/or the channel state information in the video processing procedure obtained in real time to the delay of video information, bandwidth and timing etc. into Row management and pretreatment, to provide differentiation according to the type of video terminal, resource state information or channel state information etc. Delay, timing strategy etc..Collected channel state information etc. can be also supplied to resource by video information preprocessing module 120 Dispatching management module 130.
Resource scheduling management module 130 be used for according to from isomerous environment sensing module 110 video terminal information and/ Or video processing duties are decomposed from the channel state information of video information preprocessing module 120, it is formed optimal Multitask decision.Resource scheduling management module 130 can merge various optical signal resources and video terminal information, finally establish Optimal visual task decomposition strategy or a variety of optimizing decisions.
Video processing architecture to further describe the present invention, Fig. 2 shows isomeries according to an embodiment of the invention The structural schematic diagram of environmental perception module 110 comprising low latitude terminal device sension unit 1101, the perception of ground fixed terminal are single Member 1102, terrestrial mobile terminal sension unit 1103 and user's sension unit 1104.
Low latitude terminal device sension unit 1101 can perceive all low latitude terminal devices in the presence of more dwelling network, record Its ID, and store Termination ID, terminal attributive information and terminal resource status information etc., terminal attributive information is for example including mobile speed Degree, processing capacity and electricity etc..In the present invention.Low latitude terminal device includes but is not limited to low-altitude unmanned vehicle etc..
Ground fixed terminal sension unit 1102 can perceive all ground fixed terminals in the presence of more dwelling network, and deposit Termination ID, terminal attributive information and terminal resource status information etc. are stored up, terminal attribute is for example including position, connection type, processing Ability and electricity etc..In the present invention, ground fixed terminal includes but is not limited to smart television, video conference terminal etc..
Terrestrial mobile terminal sension unit 1103 can perceive all terrestrial mobile terminals in the presence of more dwelling network, and deposit Store up Termination ID, terminal attributive information and terminal resource status information etc., terminal attribute for example including connection type (for example, wifi, Mobile network etc.), movement speed, processing capacity and electricity etc..In the present invention, earth moving equipment includes but is not limited to flat Plate computer, smart phone etc..
User's sension unit 1104 can perceive all users in the presence of more dwelling network, and record the attribute of user, institute User property is stated for example including terminal type, connection type, processing capacity and electricity, the user preference etc. used, user's sense Know that unit 1104 usually stores customer attribute information with the mode of specific data structure.In order to obtain user preference, user's sense Know that unit 1104 also stores historical behavior information type, the viewing time etc. of video (such as viewing) of user, and for example, by The method of machine learning obtains user preference analysis.
It should be noted that low latitude terminal device sension unit 1101, ground fixed terminal sension unit 1102, ground shifting Dynamic terminal sension unit 1103 and user's sension unit 1104 usually store relevant information with the mode of specific data structure and (deposit Store up Termination ID and terminal attributive information etc.), for example, knowledge mapping, table or tree structure etc. can be used, as long as can be clearly Storage terminal device information enables processing system for video 100 to obtain.
To sum up, isomerous environment sensing module 110 can perceive a plurality of types of video terminals, each terminal attribute information and Resource state information etc., and by these information be supplied to video information preprocessing module 120 and resource scheduling management module 130 with Strategy or coding parameter for its decision Video coding etc..
Fig. 3 shows the structural schematic diagram of video information preprocessing module 120 according to an embodiment of the invention, packet Include resource status collector unit 1201, video information identification and filter element 1202, policy management element 1203, isomery video letter Breath perception fusion calculation unit 1204 and isomery video information timing management unit 1205.
Resource status collector unit 1201 be used for obtain from isomerous environment sensing module 110 video terminal information or The feedback information of other modules or processing unit, channel state information etc. in person itself real-time collecting video processing procedure.
Video information identification is used to carry out content recognition to video information with filter element 1202, extracts the image of key frame Feature, then, the correlation of analysis and the video information of user demand, and further filter it is some with user demand correlation compared with Low signal.
Policy management element 1203 is used for according to video terminal information and/or channel state information etc., for each visual letter The suitable delay of breath selection or Bandwidth Allocation Policy.Video terminal information may be from isomerous environment sensing module 110, can also come From in resource status collector unit 1201, channel state information may be from resource status collector unit 1201.
Isomery video information perception fusion calculation unit 1204 is used to calculate the optimal visual letter of multiple isomery video informations Number amalgamation mode.
The visual information that isomery video information timing management unit 1205 is used to be provided according to policy management element 1203 Delaying policy manages the processing sequence etc. of vision signal.
Fig. 4 shows the structural schematic diagram of resource scheduling management module 130 according to an embodiment of the invention comprising Task-decomposing computing unit 1301, multitask decision package 1302, equipment of more dwelling Topology Management unit 1303, user interface Unit 1304, equipment collaboration scheduling unit 1305 of more dwelling, performance evaluation and tracking cell 1306, performance prediction unit 1307 and anti- Present unit 1308.
Task-decomposing computing unit 1301 is used to decompose complicated visual information processing task according to system resource condition For suitable multiple tasks, it is then dispensed for each processing unit and is handled, for example, for typical Video coding, task point These Video coding tasks can be divided and then be distributed to different types of processing unit by block by solution computing unit 1301, be drawn Block after point can be decoded independently, these processing units can be the processing unit of processing unit or terminal positioned at cloud.
Equipment Topology Management units 1303 dwell for providing the connection relationship of video terminal more, such as (be connected to vlan or Mobile network etc.).
User interface (UI) boundary element 1304 is used to receive the video signal quality that the needs that user specifies generate, such as Resolution requirement etc..
Multitask decision package 1302 goes out optimal video terminal scheduling strategy for decision and feeds back to equipment association of more dwelling With scheduling unit 1305, for example, according to dwell more equipment Topology Management unit 1303 offer video terminal connection relationship and From the received user of user interface (UI) boundary element 1304 requirement and from the video of isomerous environment sensing module 110 The decisions such as end message and/or the channel state information in the video processing procedure of resource status collector unit 1201 go out The vision signal of which video terminal of priority processing.
Performance prediction unit 1307 is used for the result to multitask decision package 1302 and Task-decomposing computing unit 1301 It is predicted, and prediction result can further be fed back to multitask decision package 1302 and Task-decomposing computing unit 1301, Multitask Optimal Management is optimized so as to subsequent.
Performance evaluation and tracking cell 1306 are used for multitask decision package 1302 and Task-decomposing computing unit 1301 Result tracked and analyzed, and calculated by the feedback of feedback unit 1308 to multitask decision package 1302 and Task-decomposing Unit 1301 optimizes multitask Optimal Management so as to subsequent.
To sum up, in multitask decision package 1302 and Task-decomposing computing unit 1301 and resource scheduling management module 130 Other units can all have connection, with according to the performance of the information of user's needs, video terminal and video processing procedure supervise The case where various aspects such as survey, carries out suitable tactic adjustment, to instruct actual video coding process, for example, setting interframe Every the processing list of, period of frame per second, key frame, code rate type (e.g., dynamic code rate and cbr (constant bit rate)) and each subtask scheduling Member etc..
, can be according to the type of mobile terminal and locating scene etc. using processing system for video of the invention, decision is suitable When coding strategy, can satisfy mobile terminal computing capability and transmission environment situation.
For example, the Video service of facing moving terminal include online short and small video on demand, various instant messagings video chat It etc. can reduce video frame rate when monitoring that network bandwidth changes and lead to that entire code stream cannot be transmitted with suitable Answer bandwidth.
For another example, suitable code rate is set, but according to the movement speed of video terminal when movement speed is fast, is arranged lower Code rate.
Processing system for video of the invention is accomplished that the control plane in video processing procedure, for example, scheduling of resource, selection Optimal policy etc., and the dedicated or General Porcess Unit of the prior art can be used in actual data surface, i.e., specific cataloged procedure It realizes, control plane and data surface can be separated in this way, thus realize flexible coding and the acquisition of visual information, And calculating and the communication resource of the nodes such as cloud computing, edge calculations can be sufficiently dispatched, and processing system uses modularization Design, Each performs its own functions for each module or unit, can be realized rapidly and efficiently visual information processing.
In order to further be clearly understood from the present invention, by taking an actual encoding tasks as an example, illustrate resource scheduling management The function of module 130.
It suppose there is a frame video sequence, resolution ratio is 4k (3840*2160), and for encoding tasks are rapidly completed, the present invention will The Task-decomposing is multiple subtasks, is then delivered to parallel processing in terminal, at this moment, each to compile according to N number of coding nodes of terminal Code node parameter are as follows: processor speed: A={ A1,A2,…,AN, downlink transfer speed: UL={ UL1,UL2,…,ULN, uplink Transmission speed, DL={ DL1,DL2,…,DLN, each subtask is a block, has independent decoding capability, data length are as follows: Block={ Block1,Block2,…,BlockN, the data length after coding is h={ h1,h2,…,hN, then it is complete with task For the encoding tasks are decomposed into multiple subtasks at the time, execution time of the subtask i in corresponding encoded node are as follows:
Wherein, TiTime, when the subtask multiple by parallel processing, required time are handled for subtask are as follows:
Then it may be expressed as: using handling the time as the encoding tasks majorized function of target
Wherein,Fr is the total length of a frame encoding tasks.
In order to further decrease the computation complexity of optimization aim, delay, optionally, resource scheduling management module are reduced 130 can be by carrying out pair the result of performance evaluation and tracking cell 1306 and feedback unit 1308 and performance prediction unit 1307 Than then to amendment subtask partition strategy, so that system performance is more excellent.
For example, being modified using feedback time, it is assumed that Feedback={ Feedback1,Feedback2,…, FeedbackNIt is the time needed for the completion subtask of feedback, then performance prediction unit 1307 can be estimated needed for each node Processing capacity are as follows:It calculatesIt, can to complete each subtask in minimum time Length optimization is decomposed into subtask are as follows:
After the completion of group Task-decomposing, it can be transmitted directly to the coding nodes of required terminal, when transmission, should be added in data Piecemeal ID, to identify corresponding subtask.
Fig. 5 illustrates video processing procedure according to the present invention, wherein solid line is data surface, and dotted line is control plane, works as end When the request video content of end, video sequence is transferred to processing system for video 100 of the invention, according to isomerous environment sensing module The demand information that the information such as the position of 110 heterogeneous terminals obtained and type, video information preprocessing module 120 obtain, by Resource scheduling management module 130 generates matched multiple subtasks according to the information of fusion, then by multiple subtask information shapes It is transferred to interchanger at flow chart, interchanger is multiple terminals (terminal 1, terminal 2, terminal 3 and terminal 4) transmission according to flow chart Matched subtask.
In conclusion the processing system for video of software definition of the invention can make video provider exempt equipment for customizing Limitation provides optimal scheduling of resource for specific application and processor combines, even if the application changes over time, to new demand servicing Support with video format can pass through simple software upgrading Seamless integration-.It can be to consumer demand using system of the invention Variation is made a response immediately.Further, since processing system for video of the invention realizes control plane function, software definition video according to Rely general processor, specific video processing function can be virtualized or be resided in facility based on cloud, therefore using ground Upper and resource based on cloud.
It should be noted that, although each step is described according to particular order above, it is not intended that must press Each step is executed according to above-mentioned particular order, in fact, some in these steps can concurrently execute, or even is changed suitable Sequence, as long as can be realized required function.
The present invention can be system, method and/or computer program product.Computer program product may include computer Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer readable storage medium can be to maintain and store the tangible device of the instruction used by instruction execution equipment. Computer readable storage medium for example can include but is not limited to storage device electric, magnetic storage apparatus, light storage device, electromagnetism and deposit Store up equipment, semiconductor memory apparatus or above-mentioned any appropriate combination.The more specific example of computer readable storage medium Sub (non exhaustive list) include: portable computer diskette, hard disk, random access memory (RAM), read-only memory (ROM), Erasable programmable read only memory (EPROM or flash memory), static random access memory (SRAM), Portable compressed disk are read-only Memory (CD-ROM), memory stick, floppy disk, mechanical coding equipment, is for example stored thereon with instruction at digital versatile disc (DVD) Punch card or groove internal projection structure and above-mentioned any appropriate combination.
Various embodiments of the present invention are described above, above description is exemplary, and non-exclusive, and It is not limited to disclosed each embodiment.Without departing from the scope and spirit of illustrated each embodiment, for this skill Many modifications and changes are obvious for the those of ordinary skill in art field.The selection of term used herein, purport In principle, the practical application or to the technological improvement in market for best explaining each embodiment, or make the art its Its those of ordinary skill can understand each embodiment disclosed herein.

Claims (10)

1. a kind of processing system for video based on software definition, comprising:
Isomerous environment sensing module: for obtaining the video terminal information of video terminal, wherein the video terminal information includes Video terminal type, the attribute information of video terminal, the resource state information of video terminal, user watch in the preference of video At least one of；
Video information preprocessing module: for according to the channel status in the video terminal information and/or video processing procedure Information is video terminal selection delay and/or Bandwidth Allocation Policy；
Resource scheduling management module: for based on the channel status letter in the video terminal information and/or video processing procedure The decomposition strategy for determining video processing duties is ceased, video processing duties are decomposed into the multiple sons executed by multiple processing units Task.
2. system according to claim 1, which is characterized in that the isomerous environment sensing module includes low latitude terminal device At least one of sension unit, ground fixed terminal sension unit, terrestrial mobile terminal sension unit and user's sension unit, Wherein,
The low latitude terminal device sension unit is used to perceive the video terminal information that type is low latitude equipment, and the ground is fixed Terminal sension unit is used to perceive the video terminal information that type is ground fixed terminal, the terrestrial mobile terminal sension unit For perceiving the video terminal information that type is terrestrial mobile terminal, user's sension unit watches video for obtaining user Preference.
3. system according to claim 1, which is characterized in that the video information preprocessing module includes that resource status is received Collect unit, video information identification and filter element, policy management element, isomery video information and perceives fusion calculation unit, isomery Video information timing management unit, in which:
The resource status collector unit is used to obtain channel state information in video processing procedure and/or from the isomery ring Border sensing module receives the video terminal information；
The video information identification and filter element are used to carry out content recognition to video information and extract the image of key frame Feature；
The policy management element is used for according to the video terminal information and/or video from the resource status collector unit Channel state information in treatment process is the suitable delay of each video information selection or Bandwidth Allocation Policy；
The isomery video information perception fusion calculation unit is used to calculate the amalgamation mode of multiple video informations；
The isomery video information timing management unit is used to manage the processing sequence of multiple video informations.
4. system according to claim 1, which is characterized in that the resource scheduling management module includes that Task-decomposing calculates Unit, multitask decision package, equipment of more dwelling Topology Management unit, user interface unit, equipment collaboration of more dwelling scheduling are single Member, performance evaluation and tracking cell, performance prediction unit and feedback unit, in which:
The Task-decomposing computing unit is multiple subtasks for video information process Task-decomposing, to be distributed to multiple processing Unit executes；
The multitask decision package is used for based on the channel status letter in the video terminal information and/or video processing procedure It ceases decision and goes out the video terminal scheduling strategy optimized；
The equipment Topology Management unit of dwelling for providing the connection relationship of video terminal more；
The user interface unit is for receiving user to the quality requirement of vision signal；
The equipment collaboration scheduling unit of dwelling for going out the video terminal tune optimized based on the multitask decision package decision more Degree strategy carrys out schedule video information；
The performance evaluation and tracking cell are used to monitor the performance of each processing unit in video processing procedure, to obtain monitoring It can result；
The performance prediction unit is used to carry out the decision of the multitask decision package and the Task-decomposing computing unit Prediction, to obtain estimated performance result.
The feedback unit is used to feed back the monitoring to the multitask decision package and the Task-decomposing computing unit It can result and the estimated performance result.
5. system according to claim 4, which is characterized in that the multitask decision package is also used to be required according to user Video image quality information or the Monitoring Performance result or the estimated performance result decision go out the video terminal tune optimized Degree strategy.
6. system according to claim 1, which is characterized in that the attribute information of the video terminal include movement speed, At least one of processing capacity, current electric quantity, connection type.
7. system according to claim 1, which is characterized in that the video terminal type include low latitude terminal device, At least one of face fixed terminal, terrestrial mobile terminal.
8. a kind of method for processing video frequency based on software definition, comprising the following steps:
Step 1: different types of video terminal information is obtained, wherein the video terminal information includes video terminal type, view The attribute information of frequency terminal, the resource state information of video terminal, user watch video preference at least one of；
Step 2: being the video terminal according to the channel state information in the video terminal information and/or video processing procedure Selection delay and/or Bandwidth Allocation Policy；
Step 3: determining that video processing is appointed based on the channel state information in the video terminal information and/or video processing procedure Video processing duties are decomposed into the multiple subtasks executed by multiple processing units by the decomposition strategy of business.
9. a kind of computer readable storage medium, is stored thereon with computer program, wherein real when the program is executed by processor Now according to claim 8 method the step of.
10. a kind of computer equipment, including memory and processor, be stored on the memory to transport on a processor Capable computer program, which is characterized in that the processor realizes the step of method according to any one of claims 8 when executing described program Suddenly.
CN201811234417.9A 2018-10-23 2018-10-23 Software defined video processing system and method Active CN109561324B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811234417.9A CN109561324B (en) 2018-10-23 2018-10-23 Software defined video processing system and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811234417.9A CN109561324B (en) 2018-10-23 2018-10-23 Software defined video processing system and method

Publications (2)

Publication Number Publication Date
CN109561324A true CN109561324A (en) 2019-04-02
CN109561324B CN109561324B (en) 2020-12-29

Family

ID=65865180

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811234417.9A Active CN109561324B (en) 2018-10-23 2018-10-23 Software defined video processing system and method

Country Status (1)

Country Link
CN (1) CN109561324B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100166068A1 (en) * 2002-12-10 2010-07-01 Perlman Stephen G System and Method for Multi-Stream Video Compression Using Multiple Encoding Formats
CN104349178A (en) * 2014-11-21 2015-02-11 赛特斯信息科技股份有限公司 System and method for required real-time transcoding and self-adaptive code rate stream media playing
CN104980752A (en) * 2015-06-11 2015-10-14 武汉大千信息技术有限公司 Method for realizing multipath self-adaptive parallel transcoding through CPU and GPU and system thereof
CN105516636A (en) * 2015-11-25 2016-04-20 南京邮电大学 Heterogeneous network multi-access resource distribution method based on video communication
CN106851336A (en) * 2017-02-07 2017-06-13 上海网达软件股份有限公司 The audio-video document code-transferring method and system of a kind of Dynamic Resource Allocation for Multimedia
CN108012163A (en) * 2017-12-19 2018-05-08 希诺麦田技术（深圳）有限公司 The bit rate control method and device of Video coding

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100166068A1 (en) * 2002-12-10 2010-07-01 Perlman Stephen G System and Method for Multi-Stream Video Compression Using Multiple Encoding Formats
CN104349178A (en) * 2014-11-21 2015-02-11 赛特斯信息科技股份有限公司 System and method for required real-time transcoding and self-adaptive code rate stream media playing
CN104980752A (en) * 2015-06-11 2015-10-14 武汉大千信息技术有限公司 Method for realizing multipath self-adaptive parallel transcoding through CPU and GPU and system thereof
CN105516636A (en) * 2015-11-25 2016-04-20 南京邮电大学 Heterogeneous network multi-access resource distribution method based on video communication
CN106851336A (en) * 2017-02-07 2017-06-13 上海网达软件股份有限公司 The audio-video document code-transferring method and system of a kind of Dynamic Resource Allocation for Multimedia
CN108012163A (en) * 2017-12-19 2018-05-08 希诺麦田技术（深圳）有限公司 The bit rate control method and device of Video coding

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
DEMÓSTENES ZEGARRA RODRÍGUEZ: "Video Quality Assessment in Video Streaming Services Considering User Preference for Video Content", 《IEEE TRANSACTIONS ON CONSUMER ELECTRONICS》 *

Also Published As

Publication number Publication date
CN109561324B (en) 2020-12-29

Similar Documents

Publication Publication Date Title
US11362918B2 (en) Intelligent analytics virtual network orchestration system and method
Hu et al. Ready player one: UAV-clustering-based multi-task offloading for vehicular VR/AR gaming
US11960976B2 (en) Decomposing tasks through artificial intelligence chaining
KR101595763B1 (en) Method for mapping media components employing machine learning
Wei et al. Reinforcement learning-empowered mobile edge computing for 6G edge intelligence
CN111444014A (en) Ocean observation network system and method based on EC-REST system structure
CN112673593A (en) Improvements in and relating to telecommunications networks
Guevara et al. Class of service in fog computing
CN109656685A (en) Container resource regulating method and system, server and computer readable storage medium
Jung et al. Adaptive and stabilized real-time super-resolution control for UAV-assisted smart harbor surveillance platforms
Chiang et al. Management and orchestration of edge computing for iot: A comprehensive survey
Shen et al. Edgematrix: A resource-redefined scheduling framework for sla-guaranteed multi-tier edge-cloud computing systems
CN116402318B (en) Multi-stage computing power resource distribution method and device for power distribution network and network architecture
US11075817B1 (en) Context aware network capacity augmentation using a flying device
CN109561324A (en) The processing system for video and processing method of software definition
Ling et al. A case for distributed multilevel storage infrastructure for visual surveillance in intelligent transportation networks
CN116456496A (en) Resource scheduling method, storage medium and electronic equipment
US20230068437A1 (en) Using user-side contextual factors to predict cellular radio throughput
CN113794756B (en) Multi-video-stream unloading method and system supporting mobile equipment
Zhang et al. Toward 6g-enabled mobile vision analytics for immersive extended reality
Makaya et al. Cost-effective machine learning inference offload for edge computing
CN105915910A (en) Video transcoding method and device based on cloud platform
Zhang et al. Evaluation of an Intelligent Task Scheduling Algorithm for 6G 3D Networking
CN110784512A (en) Airborne dynamic cloud system and real-time response resource allocation method thereof
Filip et al. EdgeMQ: Towards a message queuing processing system for cloud-edge computing:(Use cases on water and forest monitoring)

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
GR01 Patent grant
GR01 Patent grant