CN108269331A - A kind of intelligent video big data processing system - Google Patents
A kind of intelligent video big data processing system Download PDFInfo
- Publication number
- CN108269331A CN108269331A CN201711315531.XA CN201711315531A CN108269331A CN 108269331 A CN108269331 A CN 108269331A CN 201711315531 A CN201711315531 A CN 201711315531A CN 108269331 A CN108269331 A CN 108269331A
- Authority
- CN
- China
- Prior art keywords
- data
- video
- interface
- face
- big data
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07B—TICKET-ISSUING APPARATUS; FARE-REGISTERING APPARATUS; FRANKING APPARATUS
- G07B15/00—Arrangements or apparatus for collecting fares, tolls or entrance fees at one or more control points
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
Abstract
The present invention proposes a kind of intelligent video big data processing system, cloud service platform subsystem, client, management terminal, the video sensor being connect the system comprises integrated treatment subsystem and with the integrated treatment subsystem.Intelligent video big data processing system provided by the invention, based on public cloud, privately owned cloud platform, the data supporting provided by server and database carries out big data analysis, develop the Software Development Kit (SDK) and client of algorithm for encryption, it can carry out fingerprint recognition, recognition of face, iris recognition, Application on Voiceprint Recognition, In vivo detection, portrait is retrieved, Car license recognition, power line video transmission, intelligent thermal imaging, video analysis is (including identification, behavior/trajectory analysis, video frequency searching), cloud storage etc. practical application, in finance, internet, it is with a wide range of applications in the industries such as communication.
Description
Technical field
The present invention relates to technical field of data processing more particularly to a kind of intelligent video big data processing systems.
Background technology
It can be related to acquisition, transmission, processing, display and playback to vedio data etc. during Computer Vision
Process, these processes together form the integral cycle of a system, successional can operate.In video image processing technology
In the range of it is most important be exactly treatment technology for the compress technique and video image for including image etc..At present, mainstream in the market
Video image processing technology include:Intellectual analysis processing, technology that video Penetrating Fog is anti-reflection, wide dynamic processing, super-resolution processing.
Intelligent video analysis technology be solve the problems, such as field of video monitoring big data screening, retrieval technique important means.
Country's Intellectual Analysis Technology can be divided into two major class at present:One kind is the shifting to the object in picture the methods of passing through foreground extraction
It is dynamic to be detected, distinguish different behaviors by setting rule, such as mix line, article is left, circumference;Another kind of is to utilize mould
Formula identification technology targetedly models the object of monitoring required in picture, so as to reach to the certain objects in video
It is detected and related application, such as vehicle detection, stream of people's statistics, Face datection application.
Existing video acquisition is higher to dynamic requirements, the dynamic requirement height of entire video acquisition and entire video
The magnanimity big data of image causes data acquisition and is unable to real-time acquisition, and entire matching process is comparatively laborious, to dynamic data
The positioning of having differences of image is acquired, search difficulty is caused to increase, and collected video image and searching in whole image library
Rope matching primitives are cumbersome, cause search rate slow, it is impossible to good Adaptive matching search.
Have some domestic and international companies at present or personal handled for intelligent video big data has applied for some patents, such as
Chinese Patent Application No. 201610451008.9 discloses a kind of intelligent video analysis system, its key points of the technical solution are that utilizing
Centralized construction mode builds video big data cloud center, carries out big data retrieval, compares analysis, track of vehicle tracking etc.;It takes
Recognition of face or car plate Compare System are built, face is established or car plate captures database, by the way that face or license board information are filed, and
With personal identification or vehicle opening relationships.By increasing the deployment density of monitoring point, the video information of magnanimity, video information are brought
Real-time streams are subjected to multitask decomposition, and the regarding based on deep learning algorithm by the video file in video information through grid computing
Frequency architectural system is investigated to extract face face feature or vehicle license plate feature through being compared in face or vehicle database,
Finally determining suspect's identity or information of vehicles;And policeman can utilize rights management, be checked by characteristic key, video recording
Video carries out reanalysing retrieval, improves strick precaution effect of video monitoring, offender can not be stealthy.
However, above-mentioned patent is only capable of solving recognition of face, car plate than reciprocity technical problem, application range is very limited, no
The other technologies service such as charging, data exchange can be provided.
Invention content
To solve problem above, the purpose of the present invention is what is be achieved through the following technical solutions.
The system that the present invention proposes a kind of processing of intelligent video big data, the system comprises integrated treatment subsystem,
And cloud service platform subsystem, client, management terminal, the video sensor being connect with the integrated treatment subsystem.
Preferably, the cloud service platform subsystem uses HTTPS cryptographic protocols and user client communication, and data are with json lattice
Formula coding transmission realizes the certification to client using public key system.
Preferably, the cloud service platform subsystem includes following functions module:
Query interface module for providing Face Retrieval interface and data model tag queries interface, inputs name identity
Card number, exports corresponding face feature vector;Input face feature vector, the most matched top N face number of output.
Data trade interface module, for providing automaticdata transaction interface, the data being automatically performed between client are handed over
It changes and charging;
Modeling module, for providing the processing model and auxiliary Modeling Platform based on data;
Model release module, for providing data model automatic distribution platform, for upgrading intelligent video integrated treatment system
Service in system.
Preferably, the modeling module provides user interface, and all data available set lists are shown on interface, uses
Family input is used for the C dimension module description vectors of modeling, and is selected as the data acquisition system of mode input and is used as standard input set
Close, and selected well known algorithm is fitted calculatings, in error amount less than after specified data D, the corresponding N-dimensional of input model to
Amount.
Preferably, the data model is a N-dimensional vector, and a corresponding hashed value for being directed to N-dimensional vector.
Preferably, the model release module provides query interface, receives the model parameter of a M dimensional vectors description, defeated
Go out the hashed value of a corresponding model.
Preferably, the cloud processing platform subsystem accessed by data warehouse/management interface is come from multiple distributed numbers
According to access, management data in warehouse, and pass through the automatic issuing interface of data model and carry out service management and logical transaction, thus and
Interactive collaboration between third party's data service, while pass through identity service interface and extraneous authentication, identification demand pair
It connects.
Preferably, the integrated treatment subsystem provides value-added service by accessing cloud service for client, and provides API and connect
Mouth and client's original system slitless connection, the integrated treatment subsystem include following function module:
Access Management, for managing the access of video sensor;Access Management is on LAN designated port
Broadcast query notifies, after video sensor listens to this broadcast, the configuration information of response oneself;After Access Management receives
It is stored in database;
Data management module for managing the tidal data recovering of non-video sensors, performs protocol conversion function, by various biographies
The Data Format Transform of sensor output is unified internal representation;
Processing is identified for comprehensive video sensor and non-video sensors data in data identification module;
Integrated interface management module, for managing system integration interface.
Preferably, the basic procedure that the video of the integrated treatment subsystem is handled in real time is as follows:It is first after video flowing input
Motion detection is first carried out, starts recording function if moving object is detected and preserves initial data, and export the company of moving object
Continuous shearing picture forms Moving Objects stream;The face shearing picture that the output of Face datection algorithm detects, forms face object data stream;
Recognition of face processing merges identical face, forms human face target stream;Identification handles human face target stream, from initialized data base
The corresponding identity information of face is found out, forms target identities stream;Target following synthesis object coordinates, identification result form mesh
Target movement locus stream.
Preferably, the multidate information of the multiple sensors input in the real-time analysis monitoring region of the client, and at analysis
Reason according to handling result, is realized and is included to the real-time positioning of interested object, in time real-time tracking, identification.
Intelligent video big data processing system provided by the invention, based on public cloud, privately owned cloud platform, by server and
The data supporting that database provides carries out big data analysis, develops the Software Development Kit (SDK) and client of algorithm for encryption,
It can carry out fingerprint recognition, recognition of face, iris recognition, Application on Voiceprint Recognition, In vivo detection, portrait retrieval, Car license recognition, power line
Transmission of video, intelligent thermal imaging, video analysis (including identification, behavior/trajectory analysis, video frequency searching), cloud storage etc. are practical
Using being with a wide range of applications in the industries such as finance, internet, communication.
Description of the drawings
By reading the detailed description of hereafter preferred embodiment, it is various other the advantages of and benefit it is common for this field
Technical staff will become clear.Attached drawing is only used for showing the purpose of preferred embodiment, and is not considered as to the present invention
Limitation.And throughout the drawings, the same reference numbers will be used to refer to the same parts.In the accompanying drawings:
Attached drawing 1 shows the intelligent video big data processing system structure chart according to embodiment of the present invention.
Attached drawing 2 shows the work-based logic schematic diagram of cloud service platform subsystem.
Attached drawing 3 shows the configuration diagram of integrated treatment subsystem.
Attached drawing 4 shows the core process flow figure of intelligent video big data processing system of the present invention.
Attached drawing 4a is the basic flow chart that video is handled in real time.
Attached drawing 5 shows the intelligent safety and defence system schematic diagram using the present invention.
Attached drawing 6 shows the wisdom cell schematic diagram using the present invention.
Attached drawing 7 shows the wisdom marketing principle figure using the present invention.
Specific embodiment
The illustrative embodiments of the disclosure are more fully described below with reference to accompanying drawings.Although this public affairs is shown in attached drawing
The illustrative embodiments opened, it being understood, however, that may be realized in various forms the disclosure without the reality that should be illustrated here
The mode of applying is limited.It is to be able to be best understood from the disclosure, and can be by this public affairs on the contrary, providing these embodiments
The range opened completely is communicated to those skilled in the art.
Specifically, as shown in Figure 1, the present invention proposes a kind of system of intelligent video big data processing, the system packet
Include integrated treatment subsystem and the cloud service platform subsystem being connect with the integrated treatment subsystem, client, management eventually
End, video sensor.
The cloud service platform subsystem is deployed in service cloud, is offering customers service by internet.Cloud service is put down
Platform uses HTTPS cryptographic protocols and user client communication, and data are transmitted with json said shanks.It is realized using public key system to client
The certification at end.The cloud service platform subsystem mainly includes following functions module:
Query interface module, for providing Face Retrieval interface and data model tag queries interface.Input name identity
Card number, exports corresponding face feature vector;Input face feature vector, the most matched top N face number of output.
Data trade interface module, for providing automaticdata transaction interface, the data being automatically performed between client are handed over
It changes and charging.Data trade interface module provides following service:
1st, client account balance and other attributes (such as rate, client's term of validity etc.) are inquired;
2nd, inquire transaction record, including purchase data record number and sell data recording number and communication records number and
Time of origin;
3rd, account charging;
4th, data upload interface is submitted for user and sells data.Server counts the data that user uploads automatically, enters
Account.
Modeling module, for providing the processing model and auxiliary Modeling Platform based on data.Modeling module provides user behaviour
Make interface.All data available set lists are shown on interface, user's input is used for the C dimension module description vectors of modeling, and selects
It selects as the data acquisition system of mode input and as standard input set, and selected well known algorithm is fitted calculating, accidentally
After difference is less than specified data D, the corresponding N-dimensional vector of input model.
Model release module, for providing data model automatic distribution platform, for upgrading intelligent video integrated treatment system
Service in system.So-called model is a N-dimensional vector, and a corresponding hashed value for being directed to N-dimensional vector.Model issues mould
Block provides query interface, receives the model parameter of a M dimensional vectors description, exports the hashed value of a corresponding model.Client
Hashed value is inputted, the corresponding N-dimensional vector field homoemorphism type data of hashed value are downloaded from server end.
As shown in Fig. 2, the work-based logic schematic diagram for above-mentioned cloud service platform subsystem.As seen from the figure, cloud of the invention
Processing platform subsystem accessed by data warehouse/and management interface accesses from multiple Distributed Data Warehouses, manages data,
And pass through the automatic issuing interface of data model and carry out service management and logical transaction, so as to the interaction between third party's data service
Cooperation, while docked by identity service interface with extraneous authentication, identification demand.User passes through service cloud management field
Face controls the above-mentioned logical operation of entire cloud service platform subsystem and result displaying.
The integrated treatment subsystem is deployed in customers' place or separate server, is offering customers service;In addition by connecing
Enter cloud service to provide value-added service for client and api interface and client's original system slitless connection are provided.Including following function mould
Block:
Access Management, for managing the access of video sensor.Access Management is on LAN designated port
Broadcast query notifies, after sensor assembly listens to this broadcast, the configuration information of response oneself.Management module is stored in after receiving
Database;Management module is persistently broadcasted at set time intervals.
Data management module, for managing the tidal data recovering of non-video sensors.Protocol conversion function is performed, by various biographies
The Data Format Transform of sensor output is unified internal representation.
Processing is identified for comprehensive sensor data in data identification module;
Integrated interface management module, for managing system integration interface.
As shown in figure 3, the configuration diagram for above-mentioned integrated treatment subsystem.As seen from the figure, integrated treatment subsystem is
Using the real-time distributed big data computing platforms of the Storm of Apache as backbone, storage system SCYLLADB is provided in a distributed manner
Storage service realizes the video flow processing of flexibly intelligence by different interfaces and algorithm groupware, and passes through B/S frameworks and provide use
Family operate interface and for system integration API Calls interface.Storm is a distributed real-time streaming that is free and increasing income
Computing system frame can be easily done using Storm and reliably handle wireless data flow, real-time processing data.
SCYLLA is that the high-performance of famous distributed NoSQL Database Systems Apache Cassandra databases is real
Existing, using the data model of the BigTable of Google designs, data are directly resident locally and log type database, i.e. handle
The data being newly written are stored in the Memtable of memory and do persistence by the CommitLog in disk.This system
The characteristics of be write-in than read faster because write-in a data be sequence be included in commit log, do not need to random read take
Disk and search.
SCYLLA system architectures inherit Cassandra characteristics, are easy to extending transversely, and with high availability, never fall
Line, zero failure recovery time, can be across data center deployment.It is the complete P2P frameworks based on consistency Hash, each row of data
By Hash come determine should there are in which or which node.All nodes of cluster are all same roles, are thoroughly avoided
Unstability caused by the single-point problem of whole system, the state synchronized between cluster carry out the logical of P2P by Gossip agreements
Letter.Each node stores data in local, and each node receives the request from client.Each client is selected at random
It selects in cluster node and carrys out request data, the corresponding node for receiving request is by corresponding key on the ring of consistency Hash
Positioning is which node should store this data, is forwarded requests on corresponding node, and looking into several nodes of correspondence
It askes feedback and returns to client.
In addition, Scylla has used efficient language to realize, and using newest operation system technology and without lock processing side
Case, therefore have than Cassandra in performance ten times of promotion;System read-write postpones in the millisecond order of magnitude, and single node can reach
To per second million operations.The Scylla throughput of system of one 3 node of actual measurement and the Cassandra systems of 30 nodes are suitable,
Significantly reduce system TOC.
As shown in figure 4, the core process flow figure for intelligent video big data processing system of the present invention.It can by figure
See, first, integrated treatment subsystem obtains video flowing or other initial data from multiple sensors, wherein the sensor includes
High definition camera, thermal imaging system, smoke sensor etc..Then, integrated treatment subsystem taken out from original data stream concern when
Between feature.Finally, integrated treatment subsystem according to processing rule process temporal characteristics stream and is exported as a result, showing or generating newly
Event.
The basic procedure that video is handled in real time is as shown in Figure 5.Motion detection is carried out first after video flowing input to come out, if inspection
It measures moving object and then starts recording function preservation initial data, and the continuous shear stress picture for exporting moving object forms movement pair
As stream;The face shearing picture that the output of Face datection algorithm detects, forms face object data stream;Recognition of face processing merges identical
Face forms human face target stream;Identification handles human face target stream, and the corresponding identity letter of face is found out from initialized data base
Breath forms target identities stream;Target following synthesis object coordinates, identification result form the movement locus stream of target.Above
The flow of event of the formation can preserve in the database, form perdurable data.
In video is handled in real time, in addition to video flowing, image data is not transmitted in other flows of event, only includes image data
Reference, image data is stored in itself in memory or database.
The video sensor is other than with traditional camera function, also with wireless automatic positioning function, in room
It is positioned by the GPS/ Big Dippeves, is automatically positioned indoors by wireless networks such as WiFi/ZigBee/RFID outside.
The client can the multiple sensors input in analysis monitoring region in real time multidate information, and analyze and process.
According to handling result, can realize including to the real-time positioning of interested object, in time real-time tracking, the functions such as identification.Such as
Fruit identifies the personage of monitoring area, not only can with tracking object by camera shooting head region, for video monitoring all standing
The movement locus for identifying object can also be depicted on the map of monitoring area by region.
Intelligent video big data processing system provided by the invention, based on public cloud, privately owned cloud platform, by server and
The data supporting that database provides carries out big data analysis, develops the Software Development Kit (SDK) and client of algorithm for encryption,
It can carry out fingerprint recognition, recognition of face, iris recognition, Application on Voiceprint Recognition, In vivo detection, portrait retrieval, Car license recognition, power line
Transmission of video, intelligent thermal imaging, video analysis (including identification, behavior/trajectory analysis, video frequency searching), cloud storage etc. are practical
Using being with a wide range of applications in the industries such as finance, internet, communication.
Multinomial Preprocessing Technique has been arrived in present invention use in video processing, including but not limited to:Portrait deblurring
Technology, light field are given comments and criticisms, face is become a full member, low resolution turns high-resolution, image enhancement, image defogging etc..
Three application examples of the intelligent video big data processing system of the present invention are exemplified below, to further illustrate this
The technical solution of invention, the technical issues of solving and technique effect.
1 intelligent security guard of embodiment
As shown in figure 5, the intelligent safety and defence system schematic diagram for the application present invention.
Within the system, utilize recognition of face host that each use is taken on site by biological characteristic library typing/build library first
The digital photograph that photo or computer the identification user oneself at family submit, establishes biological attribute data library.When needing dynamic human face
During identification, crawl first needs the human face image information detected, is sent to authentication/veritification platform after processing and is tested
Card.During verification, video big data processing system of the invention is according to living things feature recognition as a result, the facial image of such as crawl
Data in the human face image information of scene crawl and the biological attribute data library established in advance are carried out retrieval comparison by information.
If belonging to biological characteristic library white list, allow personnel by or carry out other operation etc..If it is black to belong to biological characteristic library
List is then alarmed.
In this way, the intelligent safety and defence system of embodiment 1 realizes following three functions:
(1) identity typing+identity veritifies (bad investigation).Establish resident personnel's information bank:Identity card+portrait+educational background/
Nationality+cell-phone number+other.Establish the interim personal information that comes in and goes out:Identity card+portrait+cell-phone number+other.It carries out authority and veritifies information:
Such as identity information veritifies (name, identity card, cell-phone number ... ...);People is compared to (collection in worksite portrait photo's Vs. identity cards
Portrait photo);Personal record of bad behavior verifies (case-involving/to be involved in drug traffic).
(2) recognition of face+intelligent video monitoring.Realize dynamic human face identification (in/out mouth, key area are deployed to ensure effective monitoring and control of illegal activities), and
Typing portrait is compared, and confirms identity.Intelligent monitoring:Zone of action is divided, sets warning line;Dynamic ID (face) is known
Not, cross the border automatic alarm;Unusual checking/analysis.
(3) log analysis, report generation.The personal information statistics that comes in and goes out is carried out, draws personnel activity track of marching into the arena.
2 wisdom cell of embodiment
As shown in fig. 6, the wisdom cell schematic diagram for the application present invention.
Intelligent video big data processing system of the wisdom cell based on the present invention, is divided into four levels:
Phy-aware layer:Including recognition of face video camera, recognition of face gate, Car license recognition gate, recognition of face gate inhibition
Deng.
Transport network layer:Including wire transmission or wireless transmission.
Plateform system layer:Including privately owned cloud service platform, vehicle identification service platform, dynamic portrait compare service platform,
Big data analysis service platform.
Application layer:Including recognition of face gate inhibition, resident family come in and go out intelligent management, blacklist automatic alarm, recognition of face gate,
Visitor's discrepancy intelligent management, people's vehicle correlation inquiry, vehicle identification gate, visitor's Vehicular intelligent management etc..
3 wisdom of embodiment is marketed
As shown in fig. 7, the wisdom marketing principle figure for the application present invention.
As seen from the figure, the intelligent video big data processing system of the wisdom marketing based on the present invention, realizes client identity
Veritification, Customer Credit Risk Rating, consuming capacity analysis, VIP client's examination, the push of client's Identification of Images, marketing message, personalized clothes
Business customization etc..
Those skilled in the art will also be appreciated that the various illustrative components, blocks that the embodiment of the present invention is listed
(illustrative logical block), unit and step can pass through the knot of electronic hardware, computer software, or both
Conjunction is realized.To clearly show that the replaceability (interchangeability) of hardware and software, above-mentioned various explanations
Property component (illustrative components), unit and step universally describe their function.Such work(
Can be that specific application and the design requirement of whole system are depended on to realize by hardware or software.Those skilled in the art
Can be for each specific function of applying, the realization of various methods can be used described, but this realization is understood not to
Beyond the range of protection of the embodiment of the present invention.
Various illustrative logical blocks or unit described in the embodiment of the present invention can by general processor,
Digital signal processor, application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic devices,
Described function is realized or is operated in the design of discrete gate or transistor logic, discrete hardware components or any of the above described combination.
General processor can be microprocessor, optionally, the general processor may be any traditional processor, controller,
Microcontroller or state machine.Processor can also be realized by the combination of computing device, such as digital signal processor and micro-
Processor, multi-microprocessor, one or more microprocessors combine a digital signal processor core or any other like
Configuration realize.
The step of method or algorithm described in the embodiment of the present invention can be directly embedded into hardware, processor perform it is soft
The combination of part module or the two.Software module can be stored in RAM memory, flash memory, ROM memory, EPROM storages
Other any form of storaging mediums in device, eeprom memory, register, hard disk, moveable magnetic disc, CD-ROM or this field
In.Illustratively, storaging medium can be connect with processor, so that processor can read information from storaging medium, and
It can be to storaging medium stored and written information.Optionally, storaging medium can also be integrated into processor.Processor and storaging medium can
To be set in ASIC, ASIC can be set in user terminal.Optionally, processor and storaging medium can also be set to use
In different components in the terminal of family.
In one or more illustrative designs, the described above-mentioned function of the embodiment of the present invention can be in hardware, soft
Part, firmware or the arbitrary of this three combine to realize.If realized in software, these functions can store and computer-readable
It is transmitted on the medium of computer-readable on medium or with one or more instruction or code form.Computer readable medium includes electricity
Brain storaging medium and convenient for allow computer program to be transferred to from a place telecommunication media in other places.Storaging medium can be with
It is that any general or special computer can be with the useable medium of access.For example, such computer readable media can include but
It is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disc storage, disk storage or other magnetic storage devices or other
What can be used for carrying or store with instruct or data structure and it is other can be by general or special computer or general or specially treated
The medium of the program code of device reading form.In addition, any connection can be properly termed computer readable medium, example
Such as, if software is to pass through a coaxial cable, fiber optic cables, double from a web-site, server or other remote resources
Twisted wire, Digital Subscriber Line (DSL) are defined with being also contained in for the wireless way for transmitting such as example infrared, wireless and microwave
In computer readable medium.The disk (disk) and disk (disc) includes compress disk, radium-shine disk, CD, DVD, floppy disk
And Blu-ray Disc, disk is usually with magnetic duplication data, and disk usually carries out optical reproduction data with laser.Combinations of the above
It can also be included in computer readable medium.
The foregoing is only a preferred embodiment of the present invention, but protection scope of the present invention be not limited thereto,
Any one skilled in the art in the technical scope disclosed by the present invention, the change or replacement that can be readily occurred in,
It should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be with the protection model of the claim
Subject to enclosing.
Claims (10)
1. a kind of system of intelligent video big data processing, it is characterised in that:
The cloud service platform subsystem being connect the system comprises integrated treatment subsystem and with the integrated treatment subsystem
System, client, management terminal, video sensor.
2. a kind of system of intelligent video big data processing according to claim 1, it is characterised in that:
The cloud service platform subsystem uses HTTPS cryptographic protocols and user client communication, and data are transmitted with json said shanks,
Certification to client is realized using public key system.
3. a kind of system of intelligent video big data processing according to claim 1 or 2, it is characterised in that:
The cloud service platform subsystem includes following functions module:
Query interface module for providing Face Retrieval interface and data model tag queries interface, inputs name identification card number,
Export corresponding face feature vector;Input face feature vector, the most matched top N face number of output.
Data trade interface module, for providing automaticdata transaction interface, be automatically performed data exchange between client and
Charging;
Modeling module, for providing the processing model and auxiliary Modeling Platform based on data;
Model release module, for providing data model automatic distribution platform, for upgrading in intelligent video total system
Service.
4. a kind of system of intelligent video big data processing according to claim 3, it is characterised in that:
The modeling module provides user interface, and all data available set lists are shown on interface, and user's input is used for
The C dimension module description vectors of modeling, and be selected as the data acquisition system of mode input and gather as standard input, and selected public affairs
The algorithm known is fitted calculating, after error amount is less than specified data D, the corresponding N-dimensional vector of input model.
5. a kind of system of intelligent video big data processing according to claim 3, it is characterised in that:
The data model is a N-dimensional vector, and a corresponding hashed value for being directed to N-dimensional vector.
6. a kind of system of intelligent video big data processing according to claim 3, it is characterised in that:
The model release module provides query interface, receives the model parameter of a M dimensional vectors description, exports a corresponding mould
The hashed value of type.
7. a kind of system of intelligent video big data processing according to claim 1, it is characterised in that:
The cloud processing platform subsystem accessed by data warehouse/and management interface deposits from multiple Distributed Data Warehouses
It takes, manage data, and pass through the automatic issuing interface of data model and carry out service management and logical transaction, thus and third party's data
Interactive collaboration between service, while docked by identity service interface with extraneous authentication, identification demand.
8. a kind of system of intelligent video big data processing according to claim 1, it is characterised in that:
The integrated treatment subsystem provides value-added service by accessing cloud service for client, and provides api interface and client's original
There is system slitless connection, the integrated treatment subsystem includes following function module:
Access Management, for managing the access of video sensor;Access Management is broadcasted on LAN designated port
Inquiry notice, after video sensor listens to this broadcast, the configuration information of response oneself;Access Management is stored in after receiving
Database;
Data management module for managing the tidal data recovering of non-video sensors, performs protocol conversion function, by various sensors
The Data Format Transform of output is unified internal representation;
Processing is identified for comprehensive video sensor and non-video sensors data in data identification module;
Integrated interface management module, for managing system integration interface.
9. a kind of system of intelligent video big data processing according to claim 8, it is characterised in that:
The basic procedure that the video of the integrated treatment subsystem is handled in real time is as follows:Movement inspection is carried out first after video flowing input
It surveys, starts recording function if moving object is detected and preserve initial data, and export the continuous shear stress picture shape of moving object
Into Moving Objects stream;The face shearing picture that the output of Face datection algorithm detects, forms face object data stream;Recognition of face is handled
Merge identical face, form human face target stream;Identification handles human face target stream, and face correspondence is found out from initialized data base
Identity information, formed target identities stream;Target following synthesis object coordinates, identification result form the movement locus of target
Stream.
10. a kind of system of intelligent video big data processing according to claim 1, it is characterised in that:
The multidate information of the multiple sensors input in the real-time analysis monitoring region of client, and analyze and process, according to processing
Include as a result, realizing to the real-time positioning of interested object, in time real-time tracking, identification.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711315531.XA CN108269331A (en) | 2017-12-12 | 2017-12-12 | A kind of intelligent video big data processing system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711315531.XA CN108269331A (en) | 2017-12-12 | 2017-12-12 | A kind of intelligent video big data processing system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108269331A true CN108269331A (en) | 2018-07-10 |
Family
ID=62771829
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711315531.XA Withdrawn CN108269331A (en) | 2017-12-12 | 2017-12-12 | A kind of intelligent video big data processing system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108269331A (en) |
Cited By (13)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214303A (en) * | 2018-08-14 | 2019-01-15 | 北京工商大学 | A kind of multithreading dynamic human face based on cloud API is registered method |
CN109522433A (en) * | 2018-10-18 | 2019-03-26 | 广州市勤思网络科技有限公司 | A kind of long-range check method of crewman based on recognition of face and system |
CN110007905A (en) * | 2019-04-17 | 2019-07-12 | 安徽省希灵科技服务有限公司 | A kind of generation method and system of the software development scheme based on big data |
CN110782558A (en) * | 2019-10-08 | 2020-02-11 | 一汽解放汽车有限公司 | Differentiated GPS vehicle locking control method |
CN111177469A (en) * | 2019-12-20 | 2020-05-19 | 国久大数据有限公司 | Face retrieval method and face retrieval device |
CN111212264A (en) * | 2019-12-27 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Image processing method and device based on edge calculation and storage medium |
CN111506914A (en) * | 2020-04-26 | 2020-08-07 | 段懿容 | Big data encryption method and device, server and readable storage medium |
CN111653024A (en) * | 2020-06-10 | 2020-09-11 | 创新奇智(成都)科技有限公司 | Warehouse management system, identification method, camera and readable storage medium |
CN111815831A (en) * | 2020-06-19 | 2020-10-23 | 安徽超清科技股份有限公司 | Intelligent community security system based on Internet of things |
CN111881727A (en) * | 2020-06-16 | 2020-11-03 | 深圳数联天下智能科技有限公司 | Live body discrimination method, device and equipment based on thermal imaging and storage medium |
CN112669966A (en) * | 2020-12-14 | 2021-04-16 | 北京易华录信息技术股份有限公司 | Behavior analysis system based on monitoring data |
CN113596104A (en) * | 2021-07-05 | 2021-11-02 | 武汉理工大学 | Data transmission method and device for mobile robot and cloud server |
CN117035853A (en) * | 2023-10-09 | 2023-11-10 | 销生客(北京)数字科技有限公司 | Potential customer identity marking system based on big data |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101216885A (en) * | 2008-01-04 | 2008-07-09 | 中山大学 | Passerby face detection and tracing algorithm based on video |
US20150032886A1 (en) * | 2011-11-23 | 2015-01-29 | Shen Wang | Remote Real-Time Monitoring System based on cloud computing |
CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
CN105184940A (en) * | 2015-08-31 | 2015-12-23 | 湖南长宜物联科技有限公司 | Vehicle barrier gate machine passing system based on intelligent cloud |
CN105975948A (en) * | 2016-05-23 | 2016-09-28 | 南京甄视智能科技有限公司 | Cloud service platform architecture for face identification |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
-
2017
- 2017-12-12 CN CN201711315531.XA patent/CN108269331A/en not_active Withdrawn
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101216885A (en) * | 2008-01-04 | 2008-07-09 | 中山大学 | Passerby face detection and tracing algorithm based on video |
US20150032886A1 (en) * | 2011-11-23 | 2015-01-29 | Shen Wang | Remote Real-Time Monitoring System based on cloud computing |
CN104731964A (en) * | 2015-04-07 | 2015-06-24 | 上海海势信息科技有限公司 | Face abstracting method and video abstracting method based on face recognition and devices thereof |
CN105184940A (en) * | 2015-08-31 | 2015-12-23 | 湖南长宜物联科技有限公司 | Vehicle barrier gate machine passing system based on intelligent cloud |
CN105975948A (en) * | 2016-05-23 | 2016-09-28 | 南京甄视智能科技有限公司 | Cloud service platform architecture for face identification |
CN106375721A (en) * | 2016-09-14 | 2017-02-01 | 重庆邮电大学 | Smart video monitoring system based on cloud platform |
Non-Patent Citations (1)
Title |
---|
高菲菲: "基于多样性的人脸图像提取及识别", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
Cited By (18)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109214303B (en) * | 2018-08-14 | 2021-10-01 | 北京工商大学 | Multithreading dynamic face sign-in method based on cloud API |
CN109214303A (en) * | 2018-08-14 | 2019-01-15 | 北京工商大学 | A kind of multithreading dynamic human face based on cloud API is registered method |
CN109522433A (en) * | 2018-10-18 | 2019-03-26 | 广州市勤思网络科技有限公司 | A kind of long-range check method of crewman based on recognition of face and system |
CN110007905A (en) * | 2019-04-17 | 2019-07-12 | 安徽省希灵科技服务有限公司 | A kind of generation method and system of the software development scheme based on big data |
CN110782558A (en) * | 2019-10-08 | 2020-02-11 | 一汽解放汽车有限公司 | Differentiated GPS vehicle locking control method |
CN110782558B (en) * | 2019-10-08 | 2021-10-08 | 一汽解放汽车有限公司 | Differentiated GPS vehicle locking control method |
CN111177469A (en) * | 2019-12-20 | 2020-05-19 | 国久大数据有限公司 | Face retrieval method and face retrieval device |
CN111212264A (en) * | 2019-12-27 | 2020-05-29 | 中移(杭州)信息技术有限公司 | Image processing method and device based on edge calculation and storage medium |
CN111506914A (en) * | 2020-04-26 | 2020-08-07 | 段懿容 | Big data encryption method and device, server and readable storage medium |
CN111506914B (en) * | 2020-04-26 | 2023-10-13 | 深圳市华智世纪科技有限公司 | Big data encryption method, device, server and readable storage medium |
CN111653024A (en) * | 2020-06-10 | 2020-09-11 | 创新奇智(成都)科技有限公司 | Warehouse management system, identification method, camera and readable storage medium |
CN111881727A (en) * | 2020-06-16 | 2020-11-03 | 深圳数联天下智能科技有限公司 | Live body discrimination method, device and equipment based on thermal imaging and storage medium |
CN111881727B (en) * | 2020-06-16 | 2024-02-06 | 深圳数联天下智能科技有限公司 | Living body screening method, device, equipment and storage medium based on thermal imaging |
CN111815831A (en) * | 2020-06-19 | 2020-10-23 | 安徽超清科技股份有限公司 | Intelligent community security system based on Internet of things |
CN112669966A (en) * | 2020-12-14 | 2021-04-16 | 北京易华录信息技术股份有限公司 | Behavior analysis system based on monitoring data |
CN113596104A (en) * | 2021-07-05 | 2021-11-02 | 武汉理工大学 | Data transmission method and device for mobile robot and cloud server |
CN117035853A (en) * | 2023-10-09 | 2023-11-10 | 销生客(北京)数字科技有限公司 | Potential customer identity marking system based on big data |
CN117035853B (en) * | 2023-10-09 | 2024-02-02 | 销生客(北京)数字科技有限公司 | Potential customer identity marking system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108269331A (en) | A kind of intelligent video big data processing system | |
Laufs et al. | Security and the smart city: A systematic review | |
US7617167B2 (en) | Machine vision system for enterprise management | |
CN115272037B (en) | Smart city based on Internet of things regional public security management early warning method and system | |
CN104240342B (en) | Access control method and device based on identity authentication | |
CN106846577A (en) | Personnel's discrepancy authority control method and device based on recognition of face | |
CN112562161A (en) | Based on 5G thing networking and AI intelligent entrance guard integrated management system | |
CN102187336B (en) | Method for identifying an object in a video archive | |
JPWO2014132841A1 (en) | Person search method and home staying person search device | |
KR102295660B1 (en) | System for providing internet of things device sharing service for one-person households | |
CN109492604A (en) | Faceform's characteristic statistics analysis system | |
KR102333143B1 (en) | System for providing people counting service | |
CN108509502A (en) | The speech interface of monitoring system for view-based access control model | |
CN110807117B (en) | User relation prediction method and device and computer readable storage medium | |
Alhamed et al. | Building construction based on video surveillance and deep reinforcement learning using smart grid power system | |
CN101790717B (en) | Machine vision system for enterprise management | |
CN113158771B (en) | Community personnel information acquisition method, system and application | |
Yin | Public security video image detection system construction platform in cloud computing environment | |
CN112925899A (en) | Ranking model establishing method, case clue recommending device and medium | |
di Bella et al. | Smart Security: Integrated systems for security policies in urban environments | |
KR20210065764A (en) | System for providing non face-to-face vehicle utilization rate management service using artificial intelligence on shared economy platform | |
CN110569715A (en) | Face recognition system based on convolutional neural network | |
CN115761614A (en) | Abnormal behavior target detection system based on multi-view deep learning algorithm | |
Liang et al. | Soft multimedia anomaly detection based on neural network and optimization driven support vector machine | |
Liu et al. | Big Data and Smart Service Systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
WW01 | Invention patent application withdrawn after publication | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20180710 |