CN106504540A - A kind of analysis method of information of vehicles and device - Google Patents
A kind of analysis method of information of vehicles and device Download PDFInfo
- Publication number
- CN106504540A CN106504540A CN201611141098.8A CN201611141098A CN106504540A CN 106504540 A CN106504540 A CN 106504540A CN 201611141098 A CN201611141098 A CN 201611141098A CN 106504540 A CN106504540 A CN 106504540A
- Authority
- CN
- China
- Prior art keywords
- analysis
- picture
- headend equipment
- information
- vehicle region
- 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
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/08—Detecting or categorising vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
This application discloses a kind of analysis method of information of vehicles, the method is generated by Analysis server and end equipment issues analysis rule forward, Analysis server receiving front-end equipment sends vehicle region picture, the vehicle region picture is that headend equipment is generated according to analysis rule, Analysis server determines information of vehicles according to vehicle region picture, and information of vehicles is sent to client.The preanalysis for crossing car information are processed by headend equipment, alleviate the burden of Analysis server, further improve the real-time that information of vehicles shows in client.
Description
Technical field
The application is related to field of traffic control, more particularly to a kind of analysis method of information of vehicles and device.
Background technology
When case is related to motor vehicles, the key point that vehicle is that whole case breaks through, existing bayonet system is locked
Machine recognition is carried out to car plate, can have been captured from magnanimity according to car plate and searched in picture automatically vehicle, but suspected vehicles are often
The tracking and identification of bayonet system can be escaped using modes such as false-trademark, deck, unlicensed and multiple replacing car plates, also give case
Detection work bring very big difficulty, meanwhile, numerous relate to car case car plate relevant information can not be provided, also just make vehicle
Lookup thoroughly without foundation.
Therefore, the characteristic in order to overcome car plate easily to pretend, and when without license board information, moreover it is possible to vehicle is carried out
Identification and lookup, it is necessary to using the information of vehicle itself, rather than car plate.Model recognition system is that vehicle self-information is carried out
Identification, can automatically identify the brand of car according to face before vehicle, and the information such as car system and age, by information of vehicles with structurized
Data storage is in data base, and the client-side program by specialty is presented, and completes to inquire about, the function such as detection.
But traditional model recognition system includes that bayonet socket camera, in interior headend equipment, the information package for collecting is sent out
Back end media server is delivered to, Partial key information is parsed and analyzed by back end media server, then back end media
Server retransmits analysis result to model analysis server, by model analysis server by logo, car system, time, vehicle
Analyze out Deng structured message, final result is forwarded to client through back end media server again then, so that client
The structured messages such as the logo of vehicle, car system, time, vehicle are shown.Rear end during whole information of vehicles displaying
Media server parses and forwards data message, takes a lot of times, causes client data and shows the excessive problem of delay.
Content of the invention
The main purpose of the application is to provide a kind of analysis method of information of vehicles and device, in order to solve prior art
Model recognition system in headend equipment collection data message parse through back end media server and forward, take excessive when
Between, cause client data to show and postpone excessive problem.
To achieve these goals, the embodiment of the present application provides a kind of analysis method of information of vehicles and device.Foundation
The one side of the embodiment of the present application, there is provided a kind of analysis method of information of vehicles, the method are applied to model recognition system
In Analysis server, the model recognition system includes the Analysis server, headend equipment and client, methods described bag
Include：
Analysis rule is generated, and the analysis rule is issued to the headend equipment；
Receive the vehicle region picture that the headend equipment sends, the vehicle region picture be the headend equipment according to
The analysis rule is generated；
According to the information of vehicles that vehicle region picture determines, and the information of vehicles is sent to the client.
Preferably, the vehicle region picture is that the headend equipment is generated according to the analysis rule, specifically includes：
The analysis rule includes multiple picture zonings；
The vehicle region picture is the headend equipment by the original vehicle picture that captures according to the picture dividing regions
Regional partition；
The vehicle region picture is corresponding with the picture zoning.
Preferably, also include：
Receive the resource request information that the headend equipment sends；
According to the idle state of other Analysis servers in the server cluster, select corresponding with the headend equipment
Second Analysis server；
The address information of second Analysis server is obtained, and the resource request information is forwarded to described second point
Analysis server；
Response message of the analysis rule with the address information will be carried to send to the headend equipment, so that institute
State headend equipment to send the vehicle region picture to second Analysis server.
According to the another aspect of the embodiment of the present application, the embodiment of the present application proposes a kind of information of vehicles analysis method,
The method is applied to the headend equipment in model recognition system, and the model recognition system includes analyzing the headend equipment, clothes
Business device and client, methods described include：
Obtain the analysis rule that the Analysis server sends；
Vehicle region picture is generated according to the analysis rule；
The vehicle region picture is sent to the Analysis server, so that the Analysis server is according to the vehicle area
Domain picture determines corresponding information of vehicles and sends the information of vehicles to client.
Preferably, the headend equipment generates vehicle region picture according to the analysis rule, specially：
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
Accordingly, based on technical thought same as described above, the embodiment of the present application also proposed a kind of information of vehicles analysis
Server, the Analysis server are applied in the model recognition system for include the Analysis server, headend equipment and client,
The Analysis server includes：
Configuration module, generates analysis rule, and issues the analysis rule to the headend equipment；
Receiver module, receives the vehicle region picture that the headend equipment sends, before the vehicle region picture is described
End equipment is generated according to the analysis rule；
Analysis module, according to the information of vehicles that vehicle region picture determines, and the information of vehicles is sent to the visitor
Family end.
Preferably, the vehicle region picture is that the headend equipment is generated according to the analysis rule, specifically includes：
The analysis rule includes multiple picture zonings；
The vehicle region picture is that the original vehicle picture that itself captures is drawn by the headend equipment according to the picture
Subregion is split to form；
The vehicle region picture is corresponding with the picture zoning.
Preferably, also include：
Receive the resource request information that the headend equipment sends；
According to the idle state of other Analysis servers in the server cluster, select corresponding with the headend equipment
Second Analysis server；
The address information of second Analysis server is obtained, and the resource request information is forwarded to described second point
Analysis server；
Response message of the analysis rule with the address information will be carried to send to the headend equipment, so that institute
State headend equipment to send the vehicle region picture to second Analysis server.
Accordingly, the embodiment of the present application also proposed a kind of information of vehicles analysis headend equipment,
It is applied in the model recognition system for include the Analysis server, headend equipment and client, it is characterised in that
Side's headend equipment includes：
Acquisition module, obtains the analysis rule that the Analysis server sends；
Processing module, generates vehicle region picture according to the analysis rule；
Sending module, the Analysis server send the vehicle region picture, so that the Analysis server is according to institute
State vehicle region picture to determine corresponding information of vehicles and send the information of vehicles to client.
Preferably, the processing module specifically for：
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
The analysis method of the information of vehicles that the embodiment of the present application is provided and device, the method are generated simultaneously by Analysis server
End equipment issues analysis rule forward, and Analysis server receiving front-end equipment sends vehicle region picture, the vehicle region picture
Being headend equipment generates according to analysis rule, and Analysis server determines information of vehicles according to vehicle region picture, and by vehicle
Information is sent to client.The preanalysis for crossing car information are processed by headend equipment, alleviate the burden of Analysis server, more
The real-time that information of vehicles shows is further increased in client.
Description of the drawings
Fig. 1 is a kind of information of vehicles analysis method schematic flow sheet that the embodiment of the present application one is provided；
Fig. 2 is a kind of structural representation of model recognition system that the embodiment of the present application one is provided；
Fig. 3 is a kind of information of vehicles analysis method schematic flow sheet that the application implements two offers；
A kind of information of vehicles analysis method schematic flow sheet that Fig. 4 is provided for the application specific embodiment；
Fig. 5 is a kind of structural representation of Analysis server that the embodiment of the present application three is provided；
A kind of structural representation of headend equipment that Fig. 6 positions the embodiment of the present application four is provided.
Specific embodiment
As stated in the Background Art, traditional model analysis, have first been analyzed after car plate by front-end camera, by with the complete of vehicle
Scape photo is stored in dedicated storage equipment, then reads picture by vehicle server from storage device, after the completion of analysis, then by car
The structured messages such as mark, car system, vehicle are write in data base, in the process the reception of data, parsing and forward all be
Analysis server is carried out, and causes the load excessive of Analysis server, and the partial properties of headend equipment are idle so that waste, this
Outward due to having carried out whole processing procedures in Analysis server, time-consuming more, model analysis process of the prior art is real-time
Property is relatively low.
In view of above technical problem, present applicant proposes a kind of information of vehicles analysis method and device, are taken by analysis
Business device generates the analysis rule of headend equipment previously according to user's request, and analysis rule is sent to headend equipment, analysis clothes
The headend equipment that business device receiving front-end equipment sends generates vehicle region picture according to analysis rule, and Analysis server is according to vehicle
Region picture determines information of vehicles, and information of vehicles is sent to client, in the technical scheme of the application, by headend equipment
The analysis rule issued according to Analysis server is analyzed acquisition vehicle region come the vehicle artwork for carrying out headend equipment candid photograph
Picture, by vehicle region picture and crosses car information and sends to Analysis server, save for by original at Analysis server end
Diagram analysis becomes the process of the vehicle region picture of requirement, reduces the load of Analysis server, while before also taking full advantage of
The performance of end equipment, and then improve the real-time of information of vehicles analysis.
Purpose, technical scheme and excellent device for making the embodiment of the present invention is clearer, below in conjunction with present invention enforcement
Example in accompanying drawing, to the embodiment of the present invention in technical scheme be clearly and completely described, it is clear that described embodiment
It is a part of embodiment of the embodiment of the present invention, rather than whole embodiments.Embodiment in based on the present invention, this area are general
The every other embodiment obtained on the premise of creative work is not made by logical technical staff, belongs to protection of the present invention
Scope.
Embodiment one
Before the present embodiment one is introduced, first the application scenarios of the technical scheme of the application are illustrated, the application
Technical scheme be applied in the model recognition system for include headend equipment, Analysis server and client, wherein headend equipment
For the image capture device for itself possessing analysis module, itself possess certain analysis ability, such as web camera IPC, prison
Control photographing unit etc., belongs to the protection domain of the application
As shown in figure 1, the embodiment of the present application one provides a kind of analysis method of information of vehicles, the analysis of the information of vehicles
Method includes：
Step 101, generation analysis rule, and end equipment issues analysis rule forward.
It should be noted that be described above, headend equipment itself possesses certain analysis ability, but its analysis ability
Hardware limitation is received, corresponding service device end is weaker, in order to alleviate the processing pressure of Analysis server, makes full use of the property of headend equipment
Can, therefore in the technical scheme of the application, the preliminary information of vehicles analysis i.e. segmentation of picture is carried out by headend equipment.
A kind of concrete networking diagram structural representation of model recognition system as shown in Figure 2, wherein IPSAN memorizeies mainly enter
The storage of row picture, forwarding media stream server mainly perform the forwarding of the information such as picture, and video management server is main
The scheduling of signaling and issuing for administration order is executed, client presents information to user.
When headend equipment on startup or when reconnecting network to Analysis server requirement analysis rule or by Analysis server
Actively issue analysis rule, equally in the preferred embodiment of the application, headend equipment newly reach the standard grade or restart and
After network recovery, need to contact with Analysis server foundation again, sending resource from headend equipment to Analysis server first please
Ask, when Analysis server receives the resource request, according to information and use such as the numberings and location of headend equipment
The demand at family for example only needs to logo, car plate of collection vehicle etc., according to user's need determining the analysis rule of the headend equipment
Asking and setting the picture region for needing collection, analysis rule is generated according to multiple picture zonings, server is by the analysis rule
Be encapsulated in response message and be back to headend equipment, headend equipment in the follow-up course of work, to the candid photograph of vehicle during,
Capturing to after original image, to original image in logo and the position such as car plate carry out scratching figure, obtain the picture corresponding
The vehicle region picture such as logo picture and car plate picture, then by vehicle region picture, original image and other information send to
Analysis server is analyzed.
In the foregoing description, the analysis rule of headend equipment is issued by Analysis server, issues analysis rule this process
Cause can be arranged by practical experience with promoter, and be not limited in procedure described above.
Step 102, the vehicle region picture that receiving front-end equipment sends.
It should be noted that after Analysis server receives the first protocol information of headend equipment transmission, wherein including
Vehicle region picture and excessively car information, cross car information and contain position, numbering and candid photograph picture time of headend equipment etc.
Information, vehicle region picture are that headend equipment is generated according to analysis rule.
Vehicle pictures how to be generated to headend equipment below to illustrate, headend equipment is receiving Analysis server transmission
Analysis rule after, according to the picture zoning included in analysis rule, itself is captured the original vehicle picture that arrives according to
Picture zoning is split, and obtains multiple vehicle region pictures corresponding with each picture zoning, by multiple vehicles
Region picture is transmitted to Analysis server.Specifically, set in headend equipment in advance by the technical scheme of foregoing description
The analysis rule that puts, headend equipment after vehicle pictures (big scheme) are captured, can pass through to the vehicle pictures according to point
Analysis rule carries out scratching figure (carrying out picture segmentation according to picture zoning), obtains corresponding vehicle region picture in analysis rule
(little figure), then according to the information of headend equipment itself, the such as Information encapsulation such as track number, time, device numbering becomes the first association
View information, sends to forwarding Analysis server.
And in specific application scenarios, so that headend equipment is as IPC as an example, separate unit model analysis server can typically be located
The picture amount of reason 100-200 platform IPC, but a lot of practical applications, often have thousands of or even thousand of front end IPC equipment, therefore
Analysis server generally requires to configure multiple stage, and server can be bound by traditional method with front end IPC equipment, such as
IPC1-IPC100 is processed by server 1, and IPC101-IPC200 is processed by server 2, the like, but this can bring one
Problem, i.e., as front end is crossed, car frequency is different, and some server process pressure is big, and some server process pressure is little, causes
Server resource distribution is uneven, and is difficult to accomplish in reliability that the server of redundancy, i.e., is delayed after machine, and the server is corresponding
Front end IPC equipment cannot just be analyzed.
Based on the problems referred to above, in the preferred embodiment of the application, propose a kind of side that cluster is carried out to Analysis server
Method, carries out cluster to model analysis server, the sub- Analysis servers of each slave is carried out by the main Analysis server of master
State and the management of computing resource, and virtualization operations are carried out to resource, an IP resource pool is formed, is united by master servers
One scheduling, therefore when Analysis server receive headend equipment transmission resource request information after, according in server cluster its
The idle state of his Analysis server, selects the second Analysis server corresponding with headend equipment, by the second Analysis server point
Analysis processes picture and the information that headend equipment subsequently sends, while obtain the address information of the second Analysis server, and by resource
Solicited message is forwarded to the second Analysis server, on the other hand will carry analysis rule and the second Analysis server address information
Response message send to headend equipment so that headend equipment sends follow-up vehicle region picture and other information to
Two Analysis servers, to realize the load balancing between server.
Hereinafter above-mentioned server cluster load sharing schemes are specifically described：
After headend equipment is captured to vehicle pictures, money is sent to model analysis server admin node (master)
Source solicited message, Analysis server management node master is according to the relation between each slave Analysis servers and respectively
The idle state of slave Analysis servers, determines current priority highest salve Analysis server, notifies the salve point
Analysis server receiving front-end equipment task, while master Analysis servers return headend equipment analysis rule with corresponding
The address of slave Analysis servers, follow-up headend equipment are sent to corresponding after the vehicle pictures to capturing are analyzed
Slave Analysis servers, so that slave Analysis servers do and further analyze.
Step 103, determines information of vehicles according to vehicle region picture, and information of vehicles is sent to client.
It should be noted that i.e. demand of the Analysis server according to user.Such as logo, vehicle, car money, car system etc. are entered
Row independent assortment, after selection is one or several, carries out Algorithm Analysis for the analysis item that wherein chooses, and mainly choice is given birth to
Into analysis rule, analysis rule is sent to headend equipment, the picture for carrying out concrete position according to analysis rule by headend equipment
Split and be identified, after Analysis server receives the vehicle region picture of headend equipment transmission and crosses car information, according to
Analysis rule carries out corresponding vehicle region picture recognition analysis, then according to analysis rule carries out Algorithm Analysis, analysis draws
Corresponding information of vehicles, by information of vehicles and excessively, car information etc. is encapsulated into second protocol information to Analysis server.
It should also be noted that Analysis server sends second protocol information to the circulation of picture forwarding media sends out service
Device, and vehicle original image and the corresponding vehicle region picture that splits according to analysis rule are stored to picture memory
Structured message, after forwarding media stream server parses corresponding vehicle region picture, is transmitted to video management service by IPSAN
Device is put in storage, and model data and picture are sent in real time to client.
Embodiment two
Above-described embodiment one is illustrated with the angle of Analysis server, based on identical technical thought, real below
Apply example two to illustrate information of vehicles analysis method with the angle of headend equipment, as shown in figure 3, propose for embodiment two
A kind of schematic flow sheet of information of vehicles analysis method, the method are applied to the headend equipment in model recognition system, the car
Type identifying system includes analyzing the headend equipment, server and client side, comprise the following steps that：
S301, obtains the analysis rule that the Analysis server sends.
In a preferred embodiment, the analysis rule, the headend equipment are pre-set in the Analysis server
The analysis rule that the Analysis server sends is obtained, specially：
The headend equipment sends resource request information to the Analysis server, and obtains the Analysis server return
Response message；
Carry in the analysis rule and Analysis server place server cluster in the response message its
His secondary analysis server address.
S302, generates vehicle region picture according to the analysis rule.
In the preferred embodiment of the application,
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
S303, sends the vehicle region picture to the Analysis server.
It should be noted that the vehicle region picture is sent to the Analysis server, so that the Analysis server
Corresponding information of vehicles is determined according to the vehicle region picture and the information of vehicles is sent to client.
The analysis method of the information of vehicles proposed by embodiment one and embodiment two,
The method is generated by Analysis server and end equipment issues analysis rule forward, and Analysis server receiving front-end sets
Preparation send vehicle region picture, and the vehicle region picture is headend equipment to be generated according to analysis rule, Analysis server according to
Vehicle region picture determines information of vehicles, and information of vehicles is sent to client.By headend equipment to crossing the pre- of car information
Analyzing and processing, alleviates the burden of Analysis server, further improves the real-time that information of vehicles shows in client.
In order to further illustrate the technical scheme of the application, carry out the technical scheme to the application below in conjunction with corresponding accompanying drawing
It is described further.
As shown in Figure 4, be the application specific embodiment propose a kind of information of vehicles analysis method schematic flow sheet,
Same based on Fig. 2, in this specific embodiment, headend equipment is by taking IPC as an example, the vehicle point of Analysis server and client
In analysis system, wherein in the model analysis system, possesses server cluster, server cluster includes a master analysis
Server and multiple slave Analysis servers, the method are comprised the following steps that：
S401, IPC send resource request to Analysis server；
Specifically, after IPC is captured to vehicle pictures, to model analysis server admin node, (master is analyzed
Server) computing resource request.
S402, master Analysis server determines slave Analysis servers corresponding with IPC in own resource pond；
Specifically, master Analysis servers select idle condition according to the keep-alive relation with each slave Analysis servers
Higher slave Analysis servers, notify the task of slave Analysis server receiving front-end IPC, slave Analysis servers to return
Return response message.
S403, master Analysis server returns IPC answer messages；
Specifically, IP address and the analysis rule of slave Analysis servers are contained in answer message, while containing
IPC is notified to send picture to specified slave Analysis servers and cross the instruction of car data.
After S404, IPC receive message, picture is sent to slave Analysis servers with car data is crossed；
Specifically, IPC carries out picture segmentation according to analysis rule and generates vehicle region picture to original vehicle picture, by phase
The original image that answers and vehicle region picture, and cross car data send to slave Analysis servers.
S405, slave Analysis server replys IPC Request information after receiving information, to notify IPC to receive accordingly
Information.
S406, slave Analysis server is analyzed according to task；
Specifically, slave Analysis servers are analyzed to vehicle region picture according to corresponding analysis rule, obtain which
In structural data.
Analysis result is reported picture forwarding server by S407, slave Analysis server.
S408, picture forwarding server decompose message, and the structural datas such as vehicle are stored in data base；
Picture is write IPSAN by S409, picture forwarding server.
As can be seen here, by the technical scheme of application the application, Analysis server is generated and end equipment issues analysis forward
Rule, Analysis server receiving front-end equipment send vehicle region picture, and the vehicle region picture is headend equipment according to analysis
Rule is generated, and Analysis server determines information of vehicles according to vehicle region picture, and information of vehicles is sent to client.Logical
Cross headend equipment to process the preanalysis for crossing car information, alleviate the burden of Analysis server, further improve vehicle letter
The real-time that breath shows in client.
Embodiment three
Based on the angle with one identical technical thought of embodiment and Analysis server, the embodiment of the present application three is proposed
A kind of Analysis server device, is applied in the model recognition system for include the Analysis server, headend equipment and client, such as
Shown in accompanying drawing 5, it is a kind of Analysis server structural representation that the embodiment of the present application three is proposed, the Analysis server includes：
Configuration module 51, generates analysis rule, and issues the analysis rule to the headend equipment；
Receiver module 52, receives the vehicle region picture that the headend equipment sends, and the vehicle region picture is described
Headend equipment is generated according to the analysis rule；
Analysis module 53, according to the information of vehicles that vehicle region picture determines, and the information of vehicles is sent to described
Client.
In specific application scenarios, the vehicle region picture is that the headend equipment is generated according to the analysis rule
, specifically include：
The analysis rule includes multiple picture zonings；
The vehicle region picture is the headend equipment by the original vehicle picture that captures according to the picture dividing regions
Regional partition；
The vehicle region picture is corresponding with the picture zoning.
In specific application scenarios, also include：
Receive the resource request information that the headend equipment sends；
According to the idle state of other Analysis servers in the server cluster, select corresponding with the headend equipment
Second Analysis server；
The address information of second Analysis server is obtained, and the resource request information is forwarded to described second point
Analysis server；
Response message of the analysis rule with the address information will be carried to send to the headend equipment, so that institute
State headend equipment to send the vehicle region picture to second Analysis server.
Example IV
Based on the angle with two identical technical thought of embodiment and headend equipment, the embodiment of the present application four proposes one
Headend equipment is planted, it is applied in the model recognition system for include the Analysis server, headend equipment and client, such as accompanying drawing 6
Shown, it is a kind of headend equipment structural representation that the embodiment of the present application three is proposed, the headend equipment includes：
Acquisition module 61, obtains the analysis rule that the Analysis server sends；
Processing module 62, generates vehicle region picture according to the analysis rule；
Sending module 63, the Analysis server send the vehicle region picture so that the Analysis server according to
The vehicle region picture determines corresponding information of vehicles and sends the information of vehicles to client.
In specific application scenarios, the processing module 62 specifically for：
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
By the technical scheme for applying the application to propose, Analysis server is generated and end equipment issues analysis rule forward,
Analysis server receiving front-end equipment sends vehicle region picture, and the vehicle region picture is that headend equipment is given birth to according to analysis rule
Into, Analysis server determines information of vehicles according to vehicle region picture, and information of vehicles is sent to client.By front end
Equipment is processed to the preanalysis for crossing car information, is alleviated the burden of Analysis server, is further improve information of vehicles in visitor
The real-time that family end shows.
Finally illustrated is：Various embodiments above only in order to technical scheme to be described, rather than a limitation；Although
The present invention is described in detail with reference to foregoing embodiments, it will be understood by those within the art that；Which is still
Technical scheme described in foregoing embodiments can be modified, or which part or all technical characteristic are carried out
Equivalent；And these modifications or replacement, do not make the essence of appropriate technical solution depart from the claims in the present invention and limited
Scope.
Claims (10)
1. a kind of analysis method of information of vehicles, the Analysis server being applied in model recognition system, the vehicle cab recognition system
System includes the Analysis server, headend equipment and client, it is characterised in that methods described includes：
Analysis rule is generated, and the analysis rule is issued to the headend equipment；
Receive the vehicle region picture that the headend equipment sends, the vehicle region picture is the headend equipment according to described
Analysis rule is generated；
Information of vehicles is determined according to vehicle region picture, and the information of vehicles is sent to the client.
2. the method for claim 1, it is characterised in that the vehicle region picture is the headend equipment according to described
Analysis rule is generated, and is specifically included：
The analysis rule includes multiple picture zonings；
The vehicle region picture is that the original vehicle picture that captures is divided by the headend equipment according to the picture zoning
Cut；
The vehicle region picture is corresponding with the picture zoning.
3. the method for claim 1, it is characterised in that also include：
Receive the resource request information that the headend equipment sends；
According to the idle state of other Analysis servers in the server cluster, corresponding with the headend equipment second is selected
Analysis server；
The address information of second Analysis server is obtained, and the resource request information is forwarded to the second analysis clothes
Business device；
Response message of the analysis rule with the address information will be carried to send to the headend equipment, so that before described
End equipment sends the vehicle region picture to second Analysis server.
4. a kind of analysis method of information of vehicles, the headend equipment being applied in model recognition system, the model recognition system
Including analyzing the headend equipment, server and client side, it is characterised in that methods described includes：
Obtain the analysis rule that the Analysis server sends；
Vehicle region picture is generated according to the analysis rule；
The vehicle region picture is sent to the Analysis server, so that the Analysis server is according to the vehicle region figure
Piece determines corresponding information of vehicles and sends the information of vehicles to client.
5. method as claimed in claim 4, it is characterised in that vehicle region picture is generated according to the analysis rule, specifically
For：
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
6. a kind of information of vehicles Analysis server, is applied to the vehicle for including the Analysis server, headend equipment and client
In identifying system, it is characterised in that the Analysis server includes：
Configuration module, generates analysis rule, and issues the analysis rule to the headend equipment；
Receiver module, receives the vehicle region picture that the headend equipment sends, and the vehicle region picture is that the front end sets
For generated according to the analysis rule；
Analysis module, according to the information of vehicles that vehicle region picture determines, and the information of vehicles is sent to the client.
7. Analysis server as claimed in claim 6, it is characterised in that the vehicle region picture is the headend equipment root
Generate according to the analysis rule, specifically include：
The analysis rule includes multiple picture zonings；
The vehicle region picture is that the original vehicle picture that captures is divided by the headend equipment according to the picture zoning
Cut；
The vehicle region picture is corresponding with the picture zoning.
8. Analysis server as claimed in claim 6, also includes：
Receive the resource request information that the headend equipment sends；
According to the idle state of other Analysis servers in the server cluster, corresponding with the headend equipment second is selected
Analysis server；
The address information of second Analysis server is obtained, and the resource request information is forwarded to the second analysis clothes
Business device；
Response message of the analysis rule with the address information will be carried to send to the headend equipment, so that before described
End equipment sends the vehicle region picture to second Analysis server.
9. a kind of information of vehicles analyzes headend equipment, is applied to the car for including the Analysis server, headend equipment and client
In type identifying system, it is characterised in that side's headend equipment includes：
Acquisition module, obtains the analysis rule that the Analysis server sends；
Processing module, generates vehicle region picture according to the analysis rule；
Sending module, the Analysis server send the vehicle region picture, so that the Analysis server is according to the car
Region picture determines corresponding information of vehicles and sends the information of vehicles to client.
10. headend equipment as claimed in claim 9, it is characterised in that the processing module specifically for：
The analysis rule includes multiple picture zonings；
The original vehicle picture of candid photograph is partitioned into vehicle region picture according to each picture zoning；
The vehicle region picture is corresponding with each picture zoning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611141098.8A CN106504540B (en) | 2016-12-12 | 2016-12-12 | Vehicle information analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611141098.8A CN106504540B (en) | 2016-12-12 | 2016-12-12 | Vehicle information analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106504540A true CN106504540A (en) | 2017-03-15 |
| CN106504540B CN106504540B (en) | 2020-10-20 |
Family
ID=58329813
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611141098.8A Active CN106504540B (en) | 2016-12-12 | 2016-12-12 | Vehicle information analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106504540B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832158A (en) * | 2017-10-16 | 2018-03-23 | 深圳市中钞信达金融科技有限公司 | Face identification method and device |
| CN109598940A (en) * | 2018-09-27 | 2019-04-09 | 浙江宇视科技有限公司 | Belisha beacon timing method and device |
| CN113408559A (en) * | 2020-03-17 | 2021-09-17 | 杭州萤石软件有限公司 | Vehicle brand identification method and device and storage medium |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1928892A (en) * | 2006-09-20 | 2007-03-14 | 王枚 | Method and device for license plate location recognition, vehicle-logo location recognition and vehicle type |
| CN200976204Y (en) * | 2006-09-20 | 2007-11-14 | 王枚 | License plate positioning recognition, vehicle tag positioning recognition and vehicle shaped recognition device |
| CN102982311A (en) * | 2012-09-21 | 2013-03-20 | 公安部第三研究所 | Vehicle video characteristic extraction system and vehicle video characteristic extraction method based on video structure description |
| CN103065144A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
| CN103646546A (en) * | 2013-11-23 | 2014-03-19 | 安徽蓝盾光电子股份有限公司 | An intelligent traffic system with a large-scale vehicle passing-forbidding function |
| CN104573680A (en) * | 2015-02-10 | 2015-04-29 | 深圳市哈工大交通电子技术有限公司 | Image detection method, image detection device and traffic violation detection system |
| CN104778444A (en) * | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN105426896A (en) * | 2015-11-16 | 2016-03-23 | 成都神州数码索贝科技有限公司 | Car logo automatic identification method and system |
| CN105469078A (en) * | 2015-12-30 | 2016-04-06 | 厦门大学 | Feature selection method for vehicle type recognition |
| CN105608441A (en) * | 2016-01-13 | 2016-05-25 | 浙江宇视科技有限公司 | Vehicle type identification method and system |
| CN105654733A (en) * | 2016-03-08 | 2016-06-08 | 博康智能网络科技股份有限公司 | Front and back vehicle license plate recognition method and device based on video detection |
-
2016
- 2016-12-12 CN CN201611141098.8A patent/CN106504540B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1928892A (en) * | 2006-09-20 | 2007-03-14 | 王枚 | Method and device for license plate location recognition, vehicle-logo location recognition and vehicle type |
| CN200976204Y (en) * | 2006-09-20 | 2007-11-14 | 王枚 | License plate positioning recognition, vehicle tag positioning recognition and vehicle shaped recognition device |
| CN102982311A (en) * | 2012-09-21 | 2013-03-20 | 公安部第三研究所 | Vehicle video characteristic extraction system and vehicle video characteristic extraction method based on video structure description |
| CN103065144A (en) * | 2012-12-30 | 2013-04-24 | 信帧电子技术（北京）有限公司 | Automobile logo identification method and device |
| CN103646546A (en) * | 2013-11-23 | 2014-03-19 | 安徽蓝盾光电子股份有限公司 | An intelligent traffic system with a large-scale vehicle passing-forbidding function |
| CN104573680A (en) * | 2015-02-10 | 2015-04-29 | 深圳市哈工大交通电子技术有限公司 | Image detection method, image detection device and traffic violation detection system |
| CN104778444A (en) * | 2015-03-10 | 2015-07-15 | 公安部交通管理科学研究所 | Method for analyzing apparent characteristic of vehicle image in road scene |
| CN105426896A (en) * | 2015-11-16 | 2016-03-23 | 成都神州数码索贝科技有限公司 | Car logo automatic identification method and system |
| CN105469078A (en) * | 2015-12-30 | 2016-04-06 | 厦门大学 | Feature selection method for vehicle type recognition |
| CN105608441A (en) * | 2016-01-13 | 2016-05-25 | 浙江宇视科技有限公司 | Vehicle type identification method and system |
| CN105654733A (en) * | 2016-03-08 | 2016-06-08 | 博康智能网络科技股份有限公司 | Front and back vehicle license plate recognition method and device based on video detection |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832158A (en) * | 2017-10-16 | 2018-03-23 | 深圳市中钞信达金融科技有限公司 | Face identification method and device |
| CN109598940A (en) * | 2018-09-27 | 2019-04-09 | 浙江宇视科技有限公司 | Belisha beacon timing method and device |
| CN113408559A (en) * | 2020-03-17 | 2021-09-17 | 杭州萤石软件有限公司 | Vehicle brand identification method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106504540B (en) | 2020-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9990306B2 (en) | Inter-manycore communications method and system | |
| CN111131544B (en) | Method for realizing NAT traversal | |
| CN108964962B (en) | Method and system for controlling video network terminal | |
| CN106504540A (en) | A kind of analysis method of information of vehicles and device | |
| CN101785283B (en) | Methods and devices for communicating diagnosis data in a real time communication network | |
| CN112698838B (en) | Multi-cloud container deployment system and container deployment method thereof | |
| CN109376053A (en) | Data processing method, device and mobile terminal | |
| CN114024972A (en) | Long connection communication method, system, device, equipment and storage medium | |
| CN102984015A (en) | Method of gateway equipment for automatically identifying access equipment type and optimizing service | |
| CN112632124B (en) | Multimedia information acquisition method, device, system, storage medium and electronic device | |
| CN115348126A (en) | Network target range entity equipment access method, device and implementation system | |
| CN106559236B (en) | Equipment resource management method and device of service board, main control board and frame type equipment | |
| CN111177281B (en) | Access control method, device, equipment and storage medium | |
| US11258939B2 (en) | System, method and apparatus for networking independent synchronized generation of a series of images | |
| CN111010290B (en) | Service log processing method and device, electronic equipment and storage medium | |
| CN103369308B (en) | OSD superposition management and superposition execution method and device | |
| CN113542092A (en) | Openstack-based automatic drainage method | |
| CN106612193A (en) | Network deployment configuration method and device in virtualization technology | |
| CN111953749A (en) | Message distribution method and device for distributed equipment | |
| CN111600929A (en) | Transmission line detection method, route strategy generation method and proxy server | |
| CN103780434A (en) | Unattended operation automatic networking method of large-type distribution type system | |
| CN105939278B (en) | Traffic processing method and device | |
| CN106453118B (en) | Flow control method and flow control system | |
| CN115689610A (en) | Credit card marketing customer-obtaining method and device based on big data | |
| CN113596105B (en) | Content acquisition method, edge node and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20221103 Address after: 15 / F, Zhongchuang Plaza, 385 Hangtian Middle Road, national civil aerospace industrial base, Xi'an City, Shaanxi Province 710100 Patentee after: Xi'an Yu vision Mdt InfoTech Ltd. Address before: 2 / F, South Block, building 10, wanlun Science Park, 88 Jiangling Road, Binjiang District, Hangzhou City, Zhejiang Province, 310051 Patentee before: ZHEJIANG UNIVIEW TECHNOLOGIES Co.,Ltd. |
|
| TR01 | Transfer of patent right |