CN109889781A - A kind of processing method and processing device regarding networked video - Google Patents
A kind of processing method and processing device regarding networked video Download PDFInfo
- Publication number
- CN109889781A CN109889781A CN201910108108.5A CN201910108108A CN109889781A CN 109889781 A CN109889781 A CN 109889781A CN 201910108108 A CN201910108108 A CN 201910108108A CN 109889781 A CN109889781 A CN 109889781A
- Authority
- CN
- China
- Prior art keywords
- view
- video
- networking
- view networking
- networked
- 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
Landscapes
- Compression Or Coding Systems Of Tv Signals (AREA)
Abstract
This application provides a kind of processing method and processing devices for regarding networked video.In this application, it is shown in view networked server or to after regarding networked terminals transmission provided with the view networking original video of rectangle frame, the view networking original video provided with rectangle frame can be stored in view networked server.In this way, user not only can check at that time the view networking original video provided with rectangle frame, the view networking original video provided with rectangle frame can also be obtained and checked from depending on networked server later, can be brought great convenience to user.
Description
Technical field
This application involves view networking technology fields, more particularly to a kind of processing method and processing device for regarding networked video.
Background technique
It is social now, in order to provide safety precautions and guarantee to the work and life of people, often set at critical positions
It is equipped with monitoring camera, the monitoring video flow at critical positions is recorded by monitoring camera, later, arrangement checks that personnel check
It whether there is suspicious figure in the monitoring video flow that monitoring camera is recorded, for example, checking whether that there are fugitive personnel etc..
Wherein, check that the monitoring video flow that terminal carrys out the recording of checking monitoring camera can be used in personnel, for example, monitoring is taken the photograph
As the monitoring video flow that the monitoring video flow being recorded to is sent to the terminal by head, and terminal reception monitoring camera is sent, and
Monitoring video flow is played on the screen, and the personnel of checking can check the monitoring video flow that the terminal plays on the screen.
Summary of the invention
To solve the above-mentioned problems, present application illustrates a kind of processing method and processing devices for regarding networked video.
In a first aspect, present application illustrates a kind of processing methods for regarding networked video, the processing applied to view networked video
System, the system comprises view networked video recording arrangement, view networked server and view networked terminals, the view networked videos
Recording arrangement and the view networked server are based on view networking protocol communication connection, and the view networked server and the view are networked
Based on view networking protocol communication connection between terminal, the method is applied in the view networked server, which comprises
Obtain view networking encoded video, it is described view networking encoded video be to view network original video encode after obtain;
Used coding mode when being determined according to view networking encoded video to view networking original video coding;
Target decoder mode corresponding with the coding mode is determined in a variety of default decoding processes;
View networking encoded video is decoded using the target decoder mode, obtains the view networking original video;
The target object in each frame picture in the view networking original video is identified using default neural network model,
The default neural network model includes the model combined by Darknet and YOLO (You Only Look Once), described pre-
If neural network model is obtained based on a plurality of types of sample objects and the training of the sample object of many attitude;
Rectangle frame is set in each frame picture depending in networking original video, so that each in each frame picture
A target object is respectively positioned in a different rectangle frame, and showing each frame in the view networking original video
The rectangle frame of setting can be shown when picture;
Display sends the view networking original video for being provided with rectangle frame to view networked terminals;
Storage is provided with the original view networked video of rectangle frame in the view networked server.
It is described to identify the view networking original video using default neural network model in an optional implementation
In each frame picture in target object, comprising:
Identify that the view joins by the graphics processor GPU in the view networked server using default neural network model
The target object in each frame picture in net original video.
It is described that square is set in each frame picture depending in networking original video in an optional implementation
Before shape frame, further includes:
For each frame picture in the view networking original video, the object identified in the picture is counted
The quantity is arranged in the quantity of body in the picture, so as to can show the warning message when showing the picture.
In an optional implementation, the method also includes:
Determine whether the quantity is greater than preset quantity;
If the quantity is greater than preset quantity, warning message is generated;
The warning message is set in the picture, so as to can show the alarm signal when showing the picture
Breath.
In an optional implementation, the acquisition view networking encoded video, comprising:
It obtains in the encoded video of networking depending on the view directly inputted in networked server;Or,
Receive view networking encoded video that the view networked video recording arrangement is sent, real-time recording, the view networking
It video recording device and is connected depending on point-to-point between networked server by data line direct communication;Or,
View networking encoded video is obtained by view networking network.
It is described determining original to view networking according to view networking encoded video in an optional implementation
Used coding mode when Video coding, comprising:
Code identification is searched in the preset field depending in networking encoded video;
The coding mode is determined according to the code identification.
In an optional implementation, the determination in a variety of default decoding processes is opposite with the coding mode
The target decoder mode answered, comprising:
In corresponding relationship between coding mode and the matched decoding process of coding mode, search and the coding mode
Corresponding decoding process, and as the target decoder mode.
Second aspect, present application illustrates a kind of processing units for regarding networked video, the processing applied to view networked video
System, the system comprises view networked video recording arrangement, view networked server and view networked terminals, the view networked videos
Recording arrangement and the view networked server are based on view networking protocol communication connection, and the view networked server and the view are networked
Based on view networking protocol communication connection between terminal, described device is applied in the view networked server, and described device includes:
Obtain module, for obtain view networking encoded video, it is described view networking encoded video be to view networking original video
It is obtained after coding;
First determining module, when for being determined according to view networking encoded video to view networking original video coding
Used coding mode;
Second determining module, for determining target solution corresponding with the coding mode in a variety of default decoding processes
Code mode;
Decoder module obtains the view for decoding using the target decoder mode to view networking encoded video
Networking original video;
Identification module, for using default neural network model to identify each frame picture in the view networking original video
In target object, the default neural network model includes being combined by Darknet and YOLO (You Only Look Once)
Model, the default neural network model be based on a plurality of types of sample objects and the sample object of many attitude training
It obtains;
First setup module, for rectangle frame to be arranged in each frame picture depending in networking original video, so that
Each of each frame picture target object is respectively positioned in a different rectangle frame, and showing the view networking
The rectangle frame of setting can be shown when each frame picture in original video;
Sending module is shown, for showing or sending to view networked terminals the view networking original video provided with rectangle frame;
Memory module, for original view networked video of the storage provided with rectangle frame in the view networked server.
In an optional implementation, the identification module is specifically used for using default neural network model by institute
State the object identified in each frame picture in the view networking original video depending on the graphics processor GPU in networked server
Body.
In an optional implementation, described device further include:
Statistical module, for counting in the picture for each frame picture in the view networking original video
The quantity of the target object identified, the second setup module, for the quantity to be arranged in the picture, so that in display institute
The warning message can be shown when stating picture.
In an optional implementation, described device further include:
Third determining module, for determining whether the quantity is greater than preset quantity;
Generation module generates warning message if being greater than preset quantity for the quantity;
Third setup module, for the warning message to be arranged in the picture, so that the energy when showing the picture
Enough show the warning message.
In an optional implementation, the acquisition module includes:
First acquisition unit, for obtaining in the encoded video of networking depending on the view directly inputted in networked server;Or,
Receiving unit, for receiving view networking coding view that the view networked video recording arrangement is sent, real-time recording
Frequently, described to be connected depending on networked video recording arrangement and depending on point-to-point between networked server by data line direct communication;Or,
Second acquisition unit, for obtaining view networking encoded video by view networking network.
In an optional implementation, first determining module includes:
Searching unit, for searching code identification in the preset field depending in networking encoded video;
Determination unit, for determining the coding mode according to the code identification.
In an optional implementation, second determining module is specifically used in coding mode and coding mode
In the corresponding relationship between decoding process matched, decoding process corresponding with the coding mode is searched, and as the mesh
Mark decoding process.
The application includes following advantages:
Under normal conditions, former in the view networking that view networked server is shown or is provided with rectangle frame to view networked terminals transmission
After beginning video, the view networking original video provided with rectangle frame can't be stored.In this way, user can only often check at that time
View networking original video provided with rectangle frame is that can not view the view networking original video provided with rectangle frame later,
This must user bring very big inconvenience.
And in this application, it shows in view networked server or sends the view provided with rectangle frame to view networked terminals and network
After original video, the view networking original video for being provided with rectangle frame can be stored in view networked server.In this way, user is not
It only can check at that time the view networking original video provided with rectangle frame, can also obtained from depending on networked server later
And check the view networking original video provided with rectangle frame, it can be brought great convenience to user.
In this application, depending on presetting in networked server, there are many different coding modes to distinguish matched decoding side
Formula, therefore, for the view networking encoded video encoded by any coding mode, the view networked server of the application
It can decode it, the view networking original video before being encoded, and use default neural network in view networking original video
The target object in each frame picture in model identification view networking original video, it is then each in view networking original video
Rectangle frame is set in frame picture, so that each of each frame picture target object is respectively positioned in a different rectangle frame,
And enables and show the rectangle frame of setting when display view networks each frame picture in original video.Therefore, the application
It can support to be decoded to what is encoded by any coding mode in a variety of coding modes depending on networking encoded video
And it handles.
Secondly, in this application, in advance in the default neural network model of training, technical staff acquires a large amount of figure
Piece, includes a plurality of types of sample objects in a large amount of picture, for example, automobile, people, pet, bicycle, motorcycle, rifle and
Cutter etc. includes the sample object of many attitude in a large amount of picture, for example, having stance, kneeling position, crouching for people
Appearance, appearance of lying prone and lying posture etc., lying posture further includes lying on one's side and just lying etc., so that default neural network mould used herein
Type can identify the object of a plurality of types of objects and many attitude in image, that is, can recognize that in picture
Object as much as possible, so as to improve the recognition accuracy of default neural network model.
Detailed description of the invention
Fig. 1 is a kind of networking schematic diagram of view networking of the application.
Fig. 2 is a kind of hardware structural diagram of node server of the application.
Fig. 3 is a kind of hardware structural diagram of access switch of the application.
Fig. 4 is that a kind of Ethernet association of the application turns the hardware structural diagram of gateway.
Fig. 5 is a kind of structural block diagram of the processing system of view networked video of the application.
Fig. 6 is a kind of step flow chart of the processing method of view networked video of the application.
Fig. 7 is a kind of structural block diagram of the processing unit of view networked video of the application.
Specific embodiment
In order to make the above objects, features, and advantages of the present application more apparent, with reference to the accompanying drawing and it is specific real
Applying mode, the present application will be further described in detail.
It is the important milestone of network Development depending on networking, is a real-time network, can be realized HD video real-time Transmission,
Push numerous Internet applications to HD video, high definition is face-to-face.
Real-time high-definition video switching technology is used depending on networking, it can be such as high in a network platform by required service
Clear video conference, Intellectualized monitoring analysis, emergency command, digital broadcast television, delay TV, the Web-based instruction, shows video monitoring
Field live streaming, VOD program request, TV Mail, individual character records (PVR), Intranet (manages) channel by oneself, intelligent video Broadcast Control, information publication
All be incorporated into a system platform etc. services such as tens of kinds of videos, voice, picture, text, communication, data, by TV or
Computer realizes that high-definition quality video plays.
To make those skilled in the art more fully understand the application, it is introduced below to depending on networking:
Depending on networking, applied portion of techniques is as described below:
Network technology (Network Technology)
Traditional ethernet (Ethernet) is improved depending on the network technology innovation networked, with potential huge on network
Video flow.(Circuit is exchanged different from simple network packet packet switch (Packet Switching) or lattice network
Switching), Streaming demand is met using Packet Switching depending on networking technology.Has grouping depending on networking technology
Flexible, the simple and low price of exchange, is provided simultaneously with the quality and safety assurance of circuit switching, it is virtually electric to realize the whole network switch type
The seamless connection of road and data format.
Switching technology (Switching Technology)
Two advantages of asynchronous and packet switch that Ethernet is used depending on networking eliminate Ethernet under the premise of complete compatible and lack
It falls into, has the end-to-end seamless connection of the whole network, direct user terminal, directly carrying IP data packet.User data is in network-wide basis
It is not required to any format conversion.It is the more advanced form of Ethernet depending on networking, is a real-time exchange platform, can be realized at present mutually
The whole network large-scale high-definition realtime video transmission that networking cannot achieve pushes numerous network video applications to high Qinghua, unitizes.
Server technology (Server Technology)
It is different from traditional server, its Streaming Media depending on the server technology in networking and unified video platform
Transmission be built upon it is connection-oriented on the basis of, data-handling capacity is unrelated with flow, communication time, single network layer energy
Enough transmitted comprising signaling and data.For voice and video business, handled depending on networking and unified video platform Streaming Media
Complexity many simpler than data processing, efficiency substantially increase hundred times or more than traditional server.
Reservoir technology (Storage Technology)
The ultrahigh speed reservoir technology of unified video platform in order to adapt to the media content of vast capacity and super-flow and
Using state-of-the-art real time operating system, the programme information in server instruction is mapped to specific hard drive space, media
Content is no longer pass through server, and moment is directly delivered to user terminal, and user waits typical time less than 0.2 second.It optimizes
Sector distribution greatly reduces the mechanical movement of hard disc magnetic head tracking, and resource consumption only accounts for the 20% of the internet ad eundem IP, but
The concurrent flow greater than 3 times of traditional disk array is generated, overall efficiency promotes 10 times or more.
Network security technology (Network Security Technology)
Depending on the structural design networked by servicing independent licence system, equipment and the modes such as user data is completely isolated every time
The network security problem that puzzlement internet has thoroughly been eradicated from structure, does not need antivirus applet, firewall generally, has prevented black
The attack of visitor and virus, structural carefree secure network is provided for user.
It services innovative technology (Service Innovation Technology)
Business and transmission are fused together by unified video platform, whether single user, private user or a net
The sum total of network is all only primary automatic connection.User terminal, set-top box or PC are attached directly to unified video platform, obtain rich
The multimedia video service of rich colorful various forms.Unified video platform is traditional to substitute with table schema using " menu type "
Complicated applications programming, considerably less code, which can be used, can be realized complicated application, realize the new business innovation of " endless ".
Networking depending on networking is as described below:
It is a kind of central controlled network structure depending on networking, which can be Tree Network, Star network, ring network etc. class
Type, but centralized control node is needed to control whole network in network on this basis.
As shown in Figure 1, being divided into access net and Metropolitan Area Network (MAN) two parts depending on networking.
The equipment of access mesh portions can be mainly divided into 3 classes: node server, access switch, terminal (including various machines
Top box, encoding board, memory etc.).Node server is connected with access switch, and access switch can be with multiple terminal phases
Even, and it can connect Ethernet.
Wherein, node server is the node that centralized control functions are played in access net, can control access switch and terminal.
Node server can directly be connected with access switch, can also directly be connected with terminal.
Similar, the equipment of metropolitan area mesh portions can also be divided into 3 classes: metropolitan area server, node switch, node serve
Device.Metropolitan area server is connected with node switch, and node switch can be connected with multiple node servers.
Wherein, node server is the node server for accessing mesh portions, i.e. node server had both belonged to access wet end
Point, and belong to metropolitan area mesh portions.
Metropolitan area server is the node that centralized control functions are played in Metropolitan Area Network (MAN), can control node switch and node serve
Device.Metropolitan area server can be directly connected to node switch, can also be directly connected to node server.
It can be seen that be entirely a kind of central controlled network structure of layering depending on networking, and node server and metropolitan area clothes
The network controlled under business device can be the various structures such as tree-shaped, star-like, cyclic annular.
Visually claim, access mesh portions can form unified video platform (part in virtual coil), and multiple unified videos are flat
Platform can form view networking;Each unified video platform can be interconnected by metropolitan area and wide area depending on networking.
Classify depending on networked devices
1.1 the application's can be mainly divided into 3 classes: server depending on the equipment in networking, interchanger (including Ethernet net
Close), terminal (including various set-top boxes, encoding board, memory etc.).Depending on networking can be divided on the whole Metropolitan Area Network (MAN) (or country
Net, World Wide Web etc.) and access net.
1.2 equipment for wherein accessing mesh portions can be mainly divided into 3 classes: node server, access switch (including ether
Net gateway), terminal (including various set-top boxes, encoding board, memory etc.).
The specific hardware structure of each access network equipment are as follows:
Node server:
As shown in Fig. 2, mainly including Network Interface Module 201, switching engine module 202, CPU module 203, disk array
Module 204;
Wherein, Network Interface Module 201, the Bao Jun that CPU module 203, disk array module 204 are come in enter switching engine
Module 202;Switching engine module 202 look into the operation of address table 205 to the packet come in, to obtain the navigation information of packet;
And the packet is stored according to the navigation information of packet the queue of corresponding pack buffer 206;If the queue of pack buffer 206 is close
It is full, then it abandons;All pack buffer queues of 202 poll of switching engine mould, are forwarded: 1) port if meeting the following conditions
It is less than to send caching;2) the queue package counting facility is greater than zero.Disk array module 204 mainly realizes the control to hard disk, including
The operation such as initialization, read-write to hard disk;CPU module 203 is mainly responsible between access switch, terminal (not shown)
Protocol processes, to address table 205 (including descending protocol packet address table, uplink protocol package address table, data packet addressed table)
Configuration, and, the configuration to disk array module 204.
Access switch:
As shown in figure 3, mainly including Network Interface Module (downstream network interface module 301, uplink network interface module
302), switching engine module 303 and CPU module 304;
Wherein, the packet (upstream data) that downstream network interface module 301 is come in enters packet detection module 305;Packet detection mould
Whether mesh way address (DA), source address (SA), type of data packet and the packet length of the detection packet of block 305 meet the requirements, if met,
It then distributes corresponding flow identifier (stream-id), and enters switching engine module 303, otherwise abandon;Uplink network interface mould
The packet (downlink data) that block 302 is come in enters switching engine module 303;The data packet that CPU module 204 is come in enters switching engine
Module 303;Switching engine module 303 look into the operation of address table 306 to the packet come in, to obtain the navigation information of packet;
If the packet into switching engine module 303 is that downstream network interface is gone toward uplink network interface, in conjunction with flow identifier
(stream-id) packet is stored in the queue of corresponding pack buffer 307;If the queue of the pack buffer 307 is close full,
It abandons;If the packet into switching engine module 303 is not that downstream network interface is gone toward uplink network interface, according to packet
Navigation information is stored in the data packet queue of corresponding pack buffer 307;If the queue of the pack buffer 307 is close full,
Then abandon.
All pack buffer queues of 303 poll of switching engine module, are divided to two kinds of situations in this application:
If the queue is that downstream network interface is gone toward uplink network interface, meets the following conditions and be forwarded: 1)
It is less than that the port sends caching;2) the queue package counting facility is greater than zero;3) token that rate control module generates is obtained;
If the queue is not that downstream network interface is gone toward uplink network interface, meets the following conditions and is forwarded:
1) it is less than to send caching for the port;2) the queue package counting facility is greater than zero.
Rate control module 208 is configured by CPU module 204, to all downlink networks in programmable interval
Interface generates token toward the pack buffer queue that uplink network interface is gone, to control the code rate of forwarded upstream.
CPU module 304 is mainly responsible for the protocol processes between node server, the configuration to address table 306, and,
Configuration to rate control module 308.
Ethernet association turns gateway:
As shown in figure 4, mainly including Network Interface Module (downstream network interface module 401, uplink network interface module
402), switching engine module 403, CPU module 404, packet detection module 405, rate control module 408, address table 406, Bao Huan
Storage 407 and MAC adding module 409, MAC removing module 410.
Wherein, the data packet that downstream network interface module 401 is come in enters packet detection module 405;Packet detection module 405 is examined
Ethernet mac DA, ethernet mac SA, Ethernet length or frame type, the view networking destination address of measured data packet
DA, whether meet the requirements depending on networking source address SA, depending on networking data Packet type and packet length, corresponding stream is distributed if meeting
Identifier (stream-id);Then, MAC DA, MAC SA, length or frame type are subtracted by MAC removing module 410
(2byte), and enter corresponding receive and cache, otherwise abandon;
Downstream network interface module 401 detects the transmission caching of the port, if there is Bao Ze is according to the view of packet networking purpose
Address D A knows the ethernet mac DA of corresponding terminal, adds the ethernet mac DA of terminal, Ethernet assists the MAC for turning gateway
SA, Ethernet length or frame type, and send.
The function that Ethernet association turns other modules in gateway is similar with access switch.
Terminal:
It mainly include Network Interface Module, Service Processing Module and CPU module;For example, set-top box mainly connects including network
Mouth mold block, video/audio encoding and decoding engine modules, CPU module;Encoding board mainly includes Network Interface Module, video encoding engine
Module, CPU module;Memory mainly includes Network Interface Module, CPU module and disk array module.
The equipment of 1.3 metropolitan area mesh portions can be mainly divided into 2 classes: node server, node switch, metropolitan area server.
Wherein, node switch mainly includes Network Interface Module, switching engine module and CPU module;Metropolitan area server mainly includes
Network Interface Module, switching engine module and CPU module are constituted.
2, networking data package definition is regarded
2.1 access network data package definitions
Access net data packet mainly include following sections: destination address (DA), source address (SA), reserve bytes,
payload(PDU)、CRC。
As shown in the table, the data packet for accessing net mainly includes following sections:
DA | SA | Reserved | Payload | CRC |
Wherein:
Destination address (DA) is made of 8 bytes (byte), and first character section indicates type (such as the various associations of data packet
Discuss packet, multicast packet, unicast packet etc.), be up to 256 kinds of possibility, the second byte to the 6th byte is metropolitan area net address,
Seven, the 8th bytes are access net address;
Source address (SA) is also to be made of 8 bytes (byte), is defined identical as destination address (DA);
Reserve bytes are made of 2 bytes;
The part payload has different length according to the type of different datagrams, is if it is various protocol packages
64 bytes are 32+1024=1056 bytes if it is single group unicast packets words, are not restricted to above 2 kinds certainly;
CRC is made of 4 bytes, and calculation method follows the Ethernet CRC algorithm of standard.
2.2 Metropolitan Area Network (MAN) packet definitions
The topology of Metropolitan Area Network (MAN) is pattern, may there is 2 kinds, connection even of more than two kinds, i.e. node switching between two equipment
It can all can exceed that 2 kinds between machine and node server, node switch and node switch, node switch and node server
Connection.But the metropolitan area net address of metropolitan area network equipment is uniquely, to close to accurately describe the connection between metropolitan area network equipment
System, introduces parameter in this application: label, uniquely to describe a metropolitan area network equipment.
(Multi-Protocol Label Switch, multiprotocol label are handed over by the definition of label and MPLS in this specification
Change) label definition it is similar, it is assumed that between equipment A and equipment B there are two connection, then data packet from equipment A to equipment B just
There are 2 labels, data packet also there are 2 labels from equipment B to equipment A.Label is divided into label, outgoing label, it is assumed that data packet enters
The label (entering label) of equipment A is 0x0000, and the label (outgoing label) when this data packet leaves equipment A may reform into
0x0001.The networking process of Metropolitan Area Network (MAN) is to enter network process under centralized control, also means that address distribution, the label of Metropolitan Area Network (MAN)
Distribution be all to be dominated by metropolitan area server, node switch, node server be all passively execute, this point with
The label distribution of MPLS is different, and the distribution of the label of MPLS is the result that interchanger, server are negotiated mutually.
As shown in the table, the data packet of Metropolitan Area Network (MAN) mainly includes following sections:
DA | SA | Reserved | Label | Payload | CRC |
That is destination address (DA), source address (SA), reserve bytes (Reserved), label, payload (PDU), CRC.Its
In, the format of label, which can refer to, such as gives a definition: label is 32bit, wherein high 16bit retains, only with low 16bit, its position
Set is between the reserve bytes and payload of data packet.
Based on the above-mentioned characteristic of view networking, one of core idea of the application is proposed, it then follows the agreement for regarding networking, at this
In application, after view networked server is shown or sends the view networking original video provided with rectangle frame to view networked terminals,
The view networking original video for being provided with rectangle frame can be stored in view networked server.In this way, user can not only work as
When check the view networking original video provided with rectangle frame, can also obtain and check from depending on networked server later and be provided with
The view networking original video of rectangle frame, it can be brought great convenience to user.
Referring to Fig. 5, a kind of structural block diagram of the processing system of view networked video of the application is shown, which includes:
Depending on networked video recording arrangement 01, view networked server 02 and view networked terminals 03, depending on networked video recording arrangement 01 and view
Networked server 02 is based on view networking protocol communication connection, depending on being based on view networking between networked server 02 and view networked terminals 03
Protocol communication connection.
Wherein, video recording device 01 includes monitoring camera head etc..It include mobile phone, tablet computer, pen depending on networked terminals 03
Remember this computer and desktop computer etc..
Referring to Fig. 6, a kind of step flow chart of the processing method of view networked video of the application is shown, this method can be with
Applied in view networked server 02 shown in fig. 5, this method can specifically include following steps:
In step s101, view networking encoded video is obtained, is to view networking original video coding depending on networking encoded video
It obtains afterwards;
The application can obtain view networking encoded video by three kinds of modes.
In one example, depending on the available view networking coding directly inputted in depending on networked server of networked server
Video;For example, user by USB (Universal Serial Bus, universal serial bus) directly to view networked server it is defeated
Enter view networking encoded video.
In another example, view networking encoded video that view networked video recording arrangement is sent, real-time recording is received,
Wherein, it is connected depending on networked video recording arrangement and depending on point-to-point between networked server by data line direct communication.Depending on networking
Then video recording device real-time recording view networking original video encodes to obtain view networking coding to view networking original video and regards
Frequently, view networking encoded video then is sent to view networked server.
In yet another example, by view networking network obtain view networking encoded video, for example, by view intranet network from its
He regards downloading view networking encoded video in networked devices.
In step s 102, used coding when being determined according to view networking encoded video to view networking original video coding
Mode;
Before view networks original video, in order to save Internet resources, generally require to encode to depending on networking original video
To view networking encoded video, in this application, various coding modes can be used to when encoding depending on networking original video, such as
MP4 (Moving Picture Experts Group 4, dynamic image expert group), AVI (Audio Video
Interleaved, Audio Video Interleaved format), H.265, H.264 and YUV (colour coding method) etc., and can will be made
The code identification of coding mode is stored in the preset field in view networking encoded video.The coding mark of different coding mode
Difference is known, in this way, in this step, code identification can be searched in depending on the preset field in networking encoded video, then root
Coding mode is determined according to the code identification.
In step s 103, target decoder side corresponding with the coding mode is determined in a variety of default decoding processes
Formula;
Each coding mode is all matched with decoding process, and coding mode and the matched decoding of coding mode has been locally stored
Corresponding relationship between mode is stored with various coding modes and its matched decoding process in the corresponding relationship.
It, can corresponding relationship between coding mode and the matched decoding process of coding mode in this way, in this step
In, decoding process corresponding with the coding mode is searched, and as target decoder mode.
In step S104, view networking encoded video is decoded using target decoder mode, obtains view networking original video;
In step s105, it is identified using default neural network model in each frame picture in view networking original video
Target object, default neural network model include the model combined by Darknet and YOLO (You Only Look Once), in advance
If neural network model is obtained based on a plurality of types of sample objects and the training of the sample object of many attitude;
Due to including more convolutional layers in YOLO, network is bigger, and the size that can be recognized accurately in picture is lesser
Therefore object the identification of the target object in identification picture can be improved using the default neural network model for including YOLO
Accuracy rate.
In addition, since highest measurement floating-point operation per second and GPU (Graphics may be implemented in YOLO
Processing Unit, graphics processor) it is more suitable for the acceleration of floating-point operation, thus that can accelerate to identify by GPU,
Such as using default neural network model by each frame figure in the GPU identification view networking original video in view networked server
Target object in piece improves the rate of identification.
In step s 106, rectangle frame is set in depending on each frame picture in networking original video, so that each frame figure
Each of piece target object is respectively positioned in a different rectangle frame, and to regard in networking original video in display
The rectangle frame of setting can be shown when each frame picture;
In step s 107, display or the view networking original video to the transmission of view networked terminals provided with rectangle frame;
The networking original video of the view provided with rectangle frame can be directly displayed depending on networked server, it can also be to view networking eventually
End sends the view networking original video for being provided with rectangle frame, so as to can be checked using the user depending on networked terminals provided with rectangle
The view networking original video of frame;
In step S108, storage is provided with the original view networked video of rectangle frame in view networked server.
Under normal conditions, former in the view networking that view networked server is shown or is provided with rectangle frame to view networked terminals transmission
After beginning video, the view networking original video provided with rectangle frame can't be stored.In this way, user can only often check at that time
View networking original video provided with rectangle frame is that can not view the view networking original video provided with rectangle frame later,
This must user bring very big inconvenience.
And in this application, it shows in view networked server or sends the view provided with rectangle frame to view networked terminals and network
After original video, the view networking original video for being provided with rectangle frame can be stored in view networked server.In this way, user is not
It only can check at that time the view networking original video provided with rectangle frame, can also obtained from depending on networked server later
And check the view networking original video provided with rectangle frame, it can be brought great convenience to user.
In this application, depending on presetting in networked server, there are many different coding modes to distinguish matched decoding side
Formula, therefore, for the view networking encoded video encoded by any coding mode, the view networked server of the application
It can decode it, the view networking original video before being encoded, and use default neural network in view networking original video
The target object in each frame picture in model identification view networking original video, it is then each in view networking original video
Rectangle frame is set in frame picture, so that each of each frame picture target object is respectively positioned in a different rectangle frame,
And enables and show the rectangle frame of setting when display view networks each frame picture in original video.Therefore, the application
It can support to be decoded to what is encoded by any coding mode in a variety of coding modes depending on networking encoded video
And it handles.
Secondly, in this application, in advance in the default neural network model of training, technical staff acquires a large amount of figure
Piece, includes a plurality of types of sample objects in a large amount of picture, for example, automobile, people, pet, bicycle, motorcycle, rifle and
Cutter etc. includes the sample object of many attitude in a large amount of picture, for example, having stance, kneeling position, crouching for people
Appearance, appearance of lying prone and lying posture etc., lying posture further includes lying on one's side and just lying etc., so that default neural network mould used herein
Type can identify the object of a plurality of types of objects and many attitude in image, that is, can recognize that in picture
Object as much as possible, so as to improve the recognition accuracy of default neural network model.
In another embodiment of the application, for any one frame picture in view networking original video, it can count
Then the quantity can be arranged in the quantity of the target object identified in the picture in the picture, so that when showing picture
It can show the warning message.
If the people in picture is more, such as people's quantity is more in a region, then illegal aggregation or bucket may occur
It the events such as beats up, and then can alarm, to prompt to check that the personnel of video can be with timely learning field condition and processing in time is live
Situation.For example, it may be determined that whether the quantity is greater than preset quantity;If the quantity is greater than preset quantity, alarm signal is generated
Breath;The warning message is set in the picture, so as to can show the warning message when showing the picture.
It is same for other each frame pictures in view networking original video.
It should be noted that for simple description, therefore, it is stated as a series of action groups for embodiment of the method
It closes, but those skilled in the art should understand that, the embodiment of the present application is not limited by the described action sequence, because according to
According to the embodiment of the present application, some steps may be performed in other sequences or simultaneously.Secondly, those skilled in the art also should
Know, the embodiments described in the specification are all preferred embodiments, and related movement not necessarily the application is implemented
Necessary to example.
Referring to Fig. 7, a kind of structural block diagram of the processing unit of view networked video of the application is shown, is applied to view networking
The processing system of video, it is described the system comprises view networked video recording arrangement, view networked server and view networked terminals
Be based on view networking protocol communication connection depending on networked video recording arrangement and the view networked server, the view networked server and
Based on view networking protocol communication connection between the view networked terminals, described device is applied in the view networked server, institute
Stating device includes:
Module 11 is obtained, for obtaining view networking encoded video, the view networking encoded video is to the original view of view networking
What frequency obtained after encoding;
First determining module 12, for being networked according to the view, encoded video is determining to encode view networking original video
When used coding mode;
Second determining module 13, for determining target corresponding with the coding mode in a variety of default decoding processes
Decoding process;
Decoder module 14 is obtained described for being decoded using the target decoder mode to view networking encoded video
Depending on original video of networking;
Identification module 15, for using default neural network model to identify each frame figure in the view networking original video
Target object in piece, the default neural network model include being tied by Darknet and YOLO (You Only Look Once)
The model of conjunction, the default neural network model are instructed based on a plurality of types of sample objects and the sample object of many attitude
It gets;
First setup module 16, for rectangle frame to be arranged in each frame picture depending in networking original video, with
It is respectively positioned on each of each frame picture target object in one different rectangle frame, and showing the view connection
The rectangle frame of setting can be shown when each frame picture in net original video;
Sending module 17 is shown, for showing or sending to view networked terminals the original view of view networking provided with rectangle frame
Frequently;
Memory module 18, for original view networked video of the storage provided with rectangle frame in the view networked server.
In an optional implementation, the identification module 15 be specifically used for using default neural network model by
The graphics processor GPU depending in networked server identifies the target in each frame picture in the view networking original video
Object.
In an optional implementation, described device further include:
Statistical module, for counting in the picture for each frame picture in the view networking original video
The quantity of the target object identified, the second setup module, for the quantity to be arranged in the picture, so that in display institute
The warning message can be shown when stating picture.
In an optional implementation, described device further include:
Third determining module, for determining whether the quantity is greater than preset quantity;
Generation module generates warning message if being greater than preset quantity for the quantity;
Third setup module, for the warning message to be arranged in the picture, so that the energy when showing the picture
Enough show the warning message.
In an optional implementation, the acquisition module 11 includes:
First acquisition unit, for obtaining in the encoded video of networking depending on the view directly inputted in networked server;Or,
Receiving unit, for receiving view networking coding view that the view networked video recording arrangement is sent, real-time recording
Frequently, described to be connected depending on networked video recording arrangement and depending on point-to-point between networked server by data line direct communication;Or,
Second acquisition unit, for obtaining view networking encoded video by view networking network.
In an optional implementation, first determining module 12 includes:
Searching unit, for searching code identification in the preset field depending in networking encoded video;
Determination unit, for determining the coding mode according to the code identification.
In an optional implementation, second determining module 13 is specifically used in coding mode and coding mode
In corresponding relationship between matched decoding process, decoding process corresponding with the coding mode is searched, and as described
Target decoder mode.
Under normal conditions, former in the view networking that view networked server is shown or is provided with rectangle frame to view networked terminals transmission
After beginning video, the view networking original video provided with rectangle frame can't be stored.In this way, user can only often check at that time
View networking original video provided with rectangle frame is that can not view the view networking original video provided with rectangle frame later,
This must user bring very big inconvenience.
And in this application, it shows in view networked server or sends the view provided with rectangle frame to view networked terminals and network
After original video, the view networking original video for being provided with rectangle frame can be stored in view networked server.In this way, user is not
It only can check at that time the view networking original video provided with rectangle frame, can also obtained from depending on networked server later
And check the view networking original video provided with rectangle frame, it can be brought great convenience to user.
In this application, depending on presetting in networked server, there are many different coding modes to distinguish matched decoding side
Formula, therefore, for the view networking encoded video encoded by any coding mode, the view networked server of the application
It can decode it, the view networking original video before being encoded, and use default neural network in view networking original video
The target object in each frame picture in model identification view networking original video, it is then each in view networking original video
Rectangle frame is set in frame picture, so that each of each frame picture target object is respectively positioned in a different rectangle frame,
And enables and show the rectangle frame of setting when display view networks each frame picture in original video.Therefore, the application
It can support to be decoded to what is encoded by any coding mode in a variety of coding modes depending on networking encoded video
And it handles.
Secondly, in this application, in advance in the default neural network model of training, technical staff acquires a large amount of figure
Piece, includes a plurality of types of sample objects in a large amount of picture, for example, automobile, people, pet, bicycle, motorcycle, rifle and
Cutter etc. includes the sample object of many attitude in a large amount of picture, for example, having stance, kneeling position, crouching for people
Appearance, appearance of lying prone and lying posture etc., lying posture further includes lying on one's side and just lying etc., so that default neural network mould used herein
Type can identify the object of a plurality of types of objects and many attitude in image, that is, can recognize that in picture
Object as much as possible, so as to improve the recognition accuracy of default neural network model.
For device embodiment, since it is basically similar to the method embodiment, related so being described relatively simple
Place illustrates referring to the part of embodiment of the method.
All the embodiments in this specification are described in a progressive manner, the highlights of each of the examples are with
The difference of other embodiments, the same or similar parts between the embodiments can be referred to each other.
It should be understood by those skilled in the art that, the embodiments of the present application may be provided as method, apparatus or calculating
Machine program product.Therefore, the embodiment of the present application can be used complete hardware embodiment, complete software embodiment or combine software and
The form of the embodiment of hardware aspect.Moreover, the embodiment of the present application can be used one or more wherein include computer can
With in the computer-usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) of program code
The form of the computer program product of implementation.
The embodiment of the present application is referring to according to the method for the embodiment of the present application, terminal device (system) and computer program
The flowchart and/or the block diagram of product describes.It should be understood that flowchart and/or the block diagram can be realized by computer program instructions
In each flow and/or block and flowchart and/or the block diagram in process and/or box combination.It can provide these
Computer program instructions are set to general purpose computer, special purpose computer, Embedded Processor or other programmable data processing terminals
Standby processor is to generate a machine, so that being held by the processor of computer or other programmable data processing terminal devices
Capable instruction generates for realizing in one or more flows of the flowchart and/or one or more blocks of the block diagram
The device of specified function.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing terminal devices
In computer-readable memory operate in a specific manner, so that instruction stored in the computer readable memory generates packet
The manufacture of command device is included, which realizes in one side of one or more flows of the flowchart and/or block diagram
The function of being specified in frame or multiple boxes.
These computer program instructions can also be loaded into computer or other programmable data processing terminal devices, so that
Series of operation steps are executed on computer or other programmable terminal equipments to generate computer implemented processing, thus
The instruction executed on computer or other programmable terminal equipments is provided for realizing in one or more flows of the flowchart
And/or in one or more blocks of the block diagram specify function the step of.
Although preferred embodiments of the embodiments of the present application have been described, once a person skilled in the art knows bases
This creative concept, then additional changes and modifications can be made to these embodiments.So the following claims are intended to be interpreted as
Including preferred embodiment and all change and modification within the scope of the embodiments of the present application.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that process, method, article or terminal device including a series of elements not only wrap
Those elements are included, but also including other elements that are not explicitly listed, or further includes for this process, method, article
Or the element that terminal device is intrinsic.In the absence of more restrictions, being wanted by what sentence "including a ..." limited
Element, it is not excluded that there is also other identical elements in process, method, article or the terminal device for including the element.
Above to a kind of processing method and processing device of view networked video provided herein, it is described in detail, this
Specific case is applied in text, and the principle and implementation of this application are described, the explanation of above example is only intended to
Help understands the present processes and its core concept;At the same time, for those skilled in the art, the think of according to the application
Think, there will be changes in the specific implementation manner and application range, in conclusion the content of the present specification should not be construed as pair
The limitation of the application.
Claims (10)
1. a kind of processing method for regarding networked video, which is characterized in that applied to the processing system of view networked video, the system
Including view networked video recording arrangement, view networked server and view networked terminals, the view networked video recording arrangement and institute
It states view networked server and is based on view networking protocol communication connection, it is described depending on networked server and described depending on being based between networked terminals
It is communicated to connect depending on networking protocol, the method is applied in the view networked server, which comprises
Obtain view networking encoded video, it is described view networking encoded video be to view network original video encode after obtain;
Used coding mode when being determined according to view networking encoded video to view networking original video coding;
Target decoder mode corresponding with the coding mode is determined in a variety of default decoding processes;
View networking encoded video is decoded using the target decoder mode, obtains the view networking original video;
The target object in each frame picture in the view networking original video is identified using default neural network model, it is described
Default neural network model includes the model combined by Darknet and YOLO (You Only Look Once), the default mind
It through network model is obtained based on a plurality of types of sample objects and the training of the sample object of many attitude;
Rectangle frame is set in each frame picture depending in networking original video, so that each of each frame picture mesh
Mark object is respectively positioned in a different rectangle frame, and showing each frame picture in the view networking original video
When can show the rectangle frame of setting;
Display sends the view networking original video for being provided with rectangle frame to view networked terminals;
Storage is provided with the original view networked video of rectangle frame in the view networked server.
2. the method according to claim 1, wherein described identify that the view joins using default neural network model
The target object in each frame picture in net original video, comprising:
Identify that the view networking is former by the graphics processor GPU in the view networked server using default neural network model
The target object in each frame picture in beginning video.
3. the method according to claim 1, wherein each frame figure in the view networking original video
It is arranged before rectangle frame in piece, further includes:
For each frame picture in the view networking original video, the target object identified in the picture is counted
The quantity is arranged in quantity in the picture, so as to can show the warning message when showing the picture.
4. according to the method described in claim 3, it is characterized in that, the method also includes:
Determine whether the quantity is greater than preset quantity;
If the quantity is greater than preset quantity, warning message is generated;
The warning message is set in the picture, so as to can show the warning message when showing the picture.
5. the method according to claim 1, wherein acquisition view networking encoded video, comprising:
It obtains in the encoded video of networking depending on the view directly inputted in networked server;Or,
Receive view networking encoded video that the view networked video recording arrangement is sent, real-time recording, the view networked video
It recording arrangement and is connected depending on point-to-point between networked server by data line direct communication;Or,
View networking encoded video is obtained by view networking network.
6. the method according to claim 1, wherein described determine according to view networking encoded video to described
Used coding mode when depending on networking original video coding, comprising:
Code identification is searched in the preset field depending in networking encoded video;
The coding mode is determined according to the code identification.
7. the method according to claim 1, wherein the determining and volume in a variety of default decoding processes
The corresponding target decoder mode of code mode, comprising:
In corresponding relationship between coding mode and the matched decoding process of coding mode, search opposite with the coding mode
The decoding process answered, and as the target decoder mode.
8. a kind of processing unit for regarding networked video, which is characterized in that applied to the processing system of view networked video, the system
Including view networked video recording arrangement, view networked server and view networked terminals, the view networked video recording arrangement and institute
It states view networked server and is based on view networking protocol communication connection, it is described depending on networked server and described depending on being based between networked terminals
It is communicated to connect depending on networking protocol, described device is applied in the view networked server, and described device includes:
Obtain module, for obtain view networking encoded video, it is described view networking encoded video be to view networking original video encode
It obtains afterwards;
First determining module, for according to it is described depending on networking encoded video determine to it is described view networking original video encode when made
Coding mode;
Second determining module, for determining target decoder side corresponding with the coding mode in a variety of default decoding processes
Formula;
Decoder module obtains the view networking for decoding using the target decoder mode to view networking encoded video
Original video;
Identification module, for using default neural network model to identify in each frame picture in the view networking original video
Target object, the default neural network model include the mould combined by Darknet and YOLO (You Only Look Once)
Type, the default neural network model are obtained based on a plurality of types of sample objects and the training of the sample object of many attitude
's;
First setup module, for rectangle frame to be arranged in each frame picture depending in networking original video, so that each
Each of frame picture target object is respectively positioned in a different rectangle frame, and showing that the view networking is original
The rectangle frame of setting can be shown when each frame picture in video;
Sending module is shown, for showing or sending to view networked terminals the view networking original video provided with rectangle frame;
Memory module, for original view networked video of the storage provided with rectangle frame in the view networked server.
9. device according to claim 8, which is characterized in that the identification module is specifically used for using default neural network
Model identifies each frame picture in the view networking original video by the graphics processor GPU depending in networked server
In target object.
10. device according to claim 8, which is characterized in that described device further include:
Statistical module, for for each frame picture in the view networking original video, statistics to identify in the picture
The quantity of target object out, the second setup module, for the quantity to be arranged in the picture, so that showing the figure
The warning message can be shown when piece.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910108108.5A CN109889781A (en) | 2019-02-02 | 2019-02-02 | A kind of processing method and processing device regarding networked video |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910108108.5A CN109889781A (en) | 2019-02-02 | 2019-02-02 | A kind of processing method and processing device regarding networked video |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109889781A true CN109889781A (en) | 2019-06-14 |
Family
ID=66928020
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910108108.5A Pending CN109889781A (en) | 2019-02-02 | 2019-02-02 | A kind of processing method and processing device regarding networked video |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109889781A (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3261017A1 (en) * | 2016-06-20 | 2017-12-27 | Delphi Technologies, Inc. | Image processing system to detect objects of interest |
CN107563387A (en) * | 2017-09-14 | 2018-01-09 | 成都掌中全景信息技术有限公司 | Frame method is selected in a kind of image object detection based on Recognition with Recurrent Neural Network |
CN108881818A (en) * | 2017-11-02 | 2018-11-23 | 北京视联动力国际信息技术有限公司 | A kind of transmission method and device of video data |
CN109063612A (en) * | 2018-07-19 | 2018-12-21 | 中智城信息技术有限公司 | City intelligent red line management method and machine readable storage medium |
US20200057904A1 (en) * | 2017-02-03 | 2020-02-20 | Siemens Aktiengesellschaf | Method and apparatus for detecting objects of interest in images |
-
2019
- 2019-02-02 CN CN201910108108.5A patent/CN109889781A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP3261017A1 (en) * | 2016-06-20 | 2017-12-27 | Delphi Technologies, Inc. | Image processing system to detect objects of interest |
US20200057904A1 (en) * | 2017-02-03 | 2020-02-20 | Siemens Aktiengesellschaf | Method and apparatus for detecting objects of interest in images |
CN107563387A (en) * | 2017-09-14 | 2018-01-09 | 成都掌中全景信息技术有限公司 | Frame method is selected in a kind of image object detection based on Recognition with Recurrent Neural Network |
CN108881818A (en) * | 2017-11-02 | 2018-11-23 | 北京视联动力国际信息技术有限公司 | A kind of transmission method and device of video data |
CN109063612A (en) * | 2018-07-19 | 2018-12-21 | 中智城信息技术有限公司 | City intelligent red line management method and machine readable storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108173804A (en) | It is a kind of to access the method for internet and regarding connection cat client by regarding networking | |
CN109788232A (en) | A kind of summary of meeting recording method of video conference, device and system | |
CN107959819A (en) | A kind of method and apparatus for realizing video conferencing system Dispatching monitor and control system | |
CN108063745B (en) | A kind of video call method and its system based on Android device | |
CN110233984A (en) | A kind of monitoring system and method based on view networking | |
CN108965224A (en) | A kind of method and apparatus of video on demand | |
CN108206911A (en) | A kind of camera long-range control method and association turn server | |
CN109889373A (en) | A kind of transmission method of warning information, device and system | |
CN108989078A (en) | A kind of view networking interior joint equipment fault detection method and device | |
CN108881135A (en) | It is a kind of based on view networking information transferring method, device and system | |
CN108243343B (en) | A kind of point distribution statistical method and its server based on view networking | |
CN109218093A (en) | A kind of method and system obtaining alarm | |
CN108966018B (en) | Video broadcasting method, device, electronic equipment and storage medium based on view networking | |
CN108307212A (en) | A kind of file order method and device | |
CN109191808A (en) | A kind of alarm method and system based on view networking | |
CN108965930A (en) | A kind of method and apparatus of video data processing | |
CN109743555A (en) | A kind of information processing method and system based on view networking | |
CN109544879A (en) | A kind of processing method and system of alert data | |
CN109743284A (en) | A kind of method for processing video frequency and system based on view networking | |
CN109257615A (en) | A kind of method and apparatus that net cast is shown | |
CN109491783A (en) | A kind of acquisition methods and system of memory usage | |
CN109743537A (en) | Monitoring alarm treating method and apparatus | |
CN109617709A (en) | A kind of methods of exhibiting and system of warning information | |
CN109788222A (en) | A kind of processing method and processing device regarding networked video | |
CN108989831A (en) | A kind of network REC method and apparatus of multi-code stream |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |