CN106657069A - Image data processing system - Google Patents

Image data processing system Download PDF

Info

Publication number
CN106657069A
CN106657069A CN201611210864.1A CN201611210864A CN106657069A CN 106657069 A CN106657069 A CN 106657069A CN 201611210864 A CN201611210864 A CN 201611210864A CN 106657069 A CN106657069 A CN 106657069A
Authority
CN
China
Prior art keywords
image data
data
image
processing system
face image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN201611210864.1A
Other languages
Chinese (zh)
Inventor
伍波
钟斌
张立峰
王健
王成
钟攀攀
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shenzhen Intellifusion Technologies Co Ltd
Original Assignee
Shenzhen Intellifusion Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shenzhen Intellifusion Technologies Co Ltd filed Critical Shenzhen Intellifusion Technologies Co Ltd
Priority to CN201611210864.1A priority Critical patent/CN106657069A/en
Publication of CN106657069A publication Critical patent/CN106657069A/en
Pending legal-status Critical Current

Links

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06VIMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168Feature extraction; Face representation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L63/00Network architectures or network communication protocols for network security
    • H04L63/10Network architectures or network communication protocols for network security for controlling access to devices or network resources

Landscapes

  • Engineering & Computer Science (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Hardware Design (AREA)
  • Computer Security & Cryptography (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Processing Or Creating Images (AREA)

Abstract

The embodiment of the invention discloses an image data processing system. The image data processing system is used for a multilevel image processing system; the image processing system further comprises a plurality of image data acquisition devices, an image data access device and a service application device; the image data processing system comprises an image database and an image data processing module; the image database is used for storing face image data; and the image data processing module is used for carrying out processing on the face image data. By implementing communication of data between different levels of systems and between different modules at the same level, uniform management on the data is implemented, the utilization value of the data is improved, and mutual isolation of the data between secondary image processing systems is also prevented; and the image data processing system adopts a distributed architecture, so that data processing requests from different levels of image systems can be stably and efficiently processed, integral efficiency of the system is improved.

Description

A kind of image data processing system
Technical field
The present invention relates to artificial intelligence field, and in particular to a kind of image data processing system.
Background technology
Portrait recognition technology is referred to and utilizes image processing techniquess, by camera acquisition facial image, then to facial image It is analyzed to obtain a kind of technology of the information of needs, current portrait recognition technology has been applied to various scenes In, for example, one-level management department carries out carrying out personal identification management to diode reason department using portrait recognition technology.
At present, when one-level management department carries out personal management using portrait recognition technology to diode reason department, can be with Photographic head is disposed by managing the level image processing system of department in each diode, then people again by capturing to photographic head Face image is analyzed to carry out personal identification management, but in prior art, and the image processing system of different region arrangements is only Vertical, when realizing that cooperation carries out personal management between one-level management department and each diode reason department, cooperate high cost, difficulty Greatly.
The content of the invention
A kind of image data processing system is embodiments provided, image real time transfer efficiency can be improved, can be with Improve the data sharing level in each hierarchical system, it is possible to achieve the flexible business structure of layering.
In a first aspect, the embodiment of the present invention provides a kind of described image data handling system, described image data processing system Unite for the image processing system of multi-layer, described image processing system also includes multiple images data acquisition unit, picture number According to access device, and traffic application device, described image data acquisition unit is used to gather destination image data, described image DAA is used to realize the plurality of image data acquiring device, described image data handling system and the business Data communication between application apparatus, the data processing equipment is used for the facial image number obtained to described image harvester Traffic application device according to being processed, described is provided based on the higher layer applications in described image processing meanss, described image number Distributed structure/architecture, described image data handling system is adopted to include according to processing system:Image data base and image real time transfer Module;
Described image data base is used to store face image data, the face image data include facial image and with The corresponding structural data of the facial image;
Described image data processing module is used to process the face image data, to obtain and the face figure As corresponding facial image structural data and based on the face image data on the basis of the facial image structural data Compare search, data mining results.
As can be seen that in the technical scheme that provided of the embodiment of the present invention, by realizing to various level system and With the connection of data between level disparate modules, it is achieved thereby that the unified management to data, improves data separate value, also prevent Data only between each level image processing system are mutually isolated, and image data processing system adopts distributed structure/architecture, Ke Yiwen Fixed and efficient process improve the overall efficiency of system from the data processing request of different picture systems at different levels.
Description of the drawings
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing The accompanying drawing to be used needed for having technology description is briefly described, it should be apparent that, drawings in the following description are only this Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is a kind of configuration diagram of image processing system provided in an embodiment of the present invention;
Fig. 2 is a kind of structural representation of image data processing system provided in an embodiment of the present invention;
Fig. 3 is a kind of structural representation of image data processing system provided in an embodiment of the present invention.
Specific embodiment
A kind of image data processing system is embodiments provided, to image real time transfer efficiency can be improved, The data sharing level in each hierarchical system can be improved, it is possible to achieve the flexible business structure of layering.
In order that those skilled in the art more fully understand the present invention program, below in conjunction with the embodiment of the present invention Accompanying drawing, is clearly and completely described to the technical scheme in the embodiment of the present invention, it is clear that described embodiment is only The embodiment of a part of the invention, rather than the embodiment of whole.Based on the embodiment in the present invention, ordinary skill people The every other embodiment that member is obtained under the premise of creative work is not made, should all belong to the model of present invention protection Enclose.
Term " first ", " second " and " the 3rd " in description and claims of this specification and above-mentioned accompanying drawing etc. is For distinguishing different objects, not for description particular order.Additionally, term " including " and their any deformations, it is intended that Non-exclusive include in covering.For example containing process, method, system, product or the equipment of series of steps or unit does not have The step of listing or unit are defined in, but alternatively also include the step of not listing or unit, or alternatively also included Other steps intrinsic for these processes, method, product or equipment or unit.
Referring first to Fig. 1, Fig. 1 is a kind of configuration diagram of image processing system 100 provided in an embodiment of the present invention, institute Image processing system is stated including multiple images data acquisition unit 110, view data access device 120, image real time transfer dress 130 are put, traffic application device 140, described image data acquisition unit 110 is used to gather destination image data, described image number According to access device 120 be used for realize the plurality of image data acquiring device 110, described image data handling system 130 and Data communication between the traffic application device 140, described image data handling system 130 is used to fill described image collection The face image data for putting acquisition is processed, described traffic application device 140 is provided based in described image processing meanss Higher layer applications, described image data processing equipment 130 adopts distributed structure/architecture.
The plurality of image data acquiring device 110 is in the layout of respectively multiple level image processing systems, for gathering people Face image data simultaneously send the face image data to the data processing equipment by the DAA 120 130;
Described image data handling system 130 is used for the face image data to getting and is processed to obtain people Face image data processed result, then again sends the face image data result to the traffic application device 140;
The traffic application device 140 shows for carrying out service application result based on the face image data result Show.
In embodiments of the present invention, in order to complete to making top layer images processing system complete to each level image processing system The data for collecting are managed, it is possible to realize connecting each level image processing system by the image processing system 100 Lead to.
Alternatively, in one embodiment of the invention, the top layer images processing system may be considered certain general headquarters of group, Level image processing system may be considered certain branch of group, and top layer images processing system is carried out to each level image processing system Unified management.
In embodiments of the present invention, by setting up multiple images data acquisition unit 110 in level image processing system, It is used to gather facial image by setting up image data acquiring device 110 in each level image processing system, for example, two Image data acquiring device 110 is set up in the region that level picture system is managed.Then image data acquiring device 110 adopted again The face image data for collecting is linked into the image real time transfer of top layer images processing system by view data access device 120 System 130 goes unification to be processed view data and analyzed with traffic application device 140.
View data of the image data processing system provided in an embodiment of the present invention as based on the image processing system 100 Processing system 130, by gathering distributed system framework is carried out, and be can be used in real time to the Pang from each level image processing system Big view data carries out real-time processing, improves image processing efficiency.
Other devices of the image processing system 100 are illustrated first below, to understand that the embodiment of the present invention is provided Image data processing system application background.Certainly the facial image processing device that the embodiment of the present invention is provided is not limited to be applied to The image processing system, it is also possible to in other image processing systems.
Wherein, the data acquisition unit 110 include multiple video cameras, by the camera acquisition to image can include Panorama sketch and portrait figure.For example, image data acquiring can respectively be set up in each chain-supermarket of the different places in an area Device 110, and each image data acquiring device 110 can with the multiple front-end cameras of framework be used for gather image.Then The image is in the server for collecting region two-stage image processing system.
Wherein, view data access device 120 is referred to realize the data communication between each device and top level diagram As the data communication between processing system and level image processing system, and a device of uniform data interface is provided, passed through By each level image processing system by a unified interface and data processing equipment 130 and traffic application device 140 It is attached, so that the unified management to each level image processing system data can be realized, improves data-handling efficiency, And by the way that data are managed collectively, namely the shared of each level image processing system data is realized, improve data profit With value.
Alternatively, in one embodiment of the invention, described image DAA 120 is included with lower interface It is at least one:
Picture uploads interface, emphasis personal management interface, result communication interface and inter-layer data and reports and shared interface;
Wherein, the picture uploads interface and obtains from the plurality of data acquisition module for described image data processing equipment Take the face image data;
The emphasis personal management interface is used to increase default emphasis personnel portrait to described image data base;
The result communication interface is used to send out the default face image data result of the data processing equipment 130 Deliver to default client;
The inter-layer data is reported and processed from the top layer images for the level image processing system with shared interface System obtains data.
In embodiments of the present invention, data access layer defines form, agreement, system structure of data input output etc., Such that it is able to realize the data communication between each device by data access layer.
In embodiments of the present invention, image data base includes top layer images data base and level image data base, described Top layer images data base carries out the transmission of data and shares with the level image data base by DAA.
It is appreciated that in embodiments of the present invention, filled by arranging view data access device, and accessing in view data Different interfaces are centered, such that it is able to realize by the data interchange between disparate modules, from for region, it is possible to achieve no With the data interchange between level image processing system and top layer images processing system, to reach the unified pipe to view data Reason, improves image real time transfer efficiency.
Wherein, the traffic application device 140 referred to installed in client, for the module directly docked with user.The industry Business application apparatus 140 indicates the concrete function that can be realized by the image processing system 100.When traffic application device 140 When triggering certain functional module, then the functional module is by calling image capture module, DIU data interface unit and view data Face image data result is exported to traffic application device 140 and shown realizing by processing system 130, for User checks.
The traffic application device includes following at least one:Retrieval module, Real time identification notification module, statistical module, digging Pick module, system management module and map display module.For realizing different functions.
The retrieval module is used to be based on image data base, and according to default facial image facial image retrieval result is obtained, The face image data result includes the facial image retrieval result;
The Real time identification notification module is used to recognize goal-selling portrait in real time and message informing;
The statistical module is used to count the face result data;
The excavation module is used to that at least one in data below to be counted and analyzed:Face image data, people Face structural data or face result data are carried out;
The system management module is used to be managed described image processing system 100;
The map display module is used to carry out the corresponding goal activitiess track of the default facial image on map Show.
Alternatively, the traffic application device 140 can also include other functional modules, for realizing other functions.
As can be seen that the embodiment of the present invention provide image processing system 100 by realizing to various level system and With the connection of data between level disparate modules, it is achieved thereby that the unified management to data, improves data separate value, also prevent Data only between each level image processing system are mutually isolated, and image data processing system adopts distributed structure/architecture, Ke Yiwen Fixed and efficient process improve the overall efficiency of system from the data processing request of different picture systems at different levels.
Image data processing system provided in an embodiment of the present invention is discussed in detail again below.
Referring to Fig. 2, Fig. 2 is a kind of structural representation of image data processing system 130 provided in an embodiment of the present invention.Such as Shown in Fig. 2, described image data handling system includes:Image data base 131 and image data processing module 132;
Described image data base 131 is used to store face image data, the face image data include facial image with And structural data corresponding with the facial image;
Described image data processing module 132 is used to process the face image data, to obtain and the people The corresponding facial image structural data of face image and based on the facial image on the basis of the facial image structural data Comparing is searched for, data mining results.
In embodiments of the present invention, the image data processing system adopts distributed structure/architecture, to improve image real time transfer Efficiency.
Wherein, image data base 131 refers to the data base for storing various facial images, at subsequent image data When reason system carries out recognition of face, by being contrasted to obtain face with the face image data in the image data base 131 Image data processing result.
Specifically, the image data base 131 can include face image data, and be obtained based on the face image data Accessed structural data, for example, when a facial image is got from image capturing system, can preserve the face View data, while facial image feature can be extracted based on the facial image, for example, textural characteristics, color characteristic point, then will These features are stored in simultaneously all together in image data base 131, during in order to subsequently carrying out image recognition, can directly utilize the knot Structure data are identified, and improve image recognition efficiency.By preserving face image data, and and face image data simultaneously Corresponding structural data, can improve image processing efficiency.
Alternatively, in one embodiment of the invention, image data base includes emphasis figure database and non-emphasis Figure database, static identity database and dynamic acquisition data base;
The emphasis figure database pays close attention to who object data for storage;
The non-emphasis figure database is used to store non-to pay close attention to who object data;
Described static identity data is used for storage and levies the related data of part to the identity of personage;
Described dynamic acquisition data are used to be stored in the portrait data gathered in actual monitors environment.
Specifically, in one embodiment of the invention, the emphasis figure database pays close attention to people for storage The data of member, the non-emphasis figure database is used for the data of the personnel for storing general concern.For example, this pay close attention to personnel can Being crime habitual offender of member, or market etc..
Specifically, in one embodiment of the invention, each face image data in the static database can also be wrapped People information corresponding with each face image data is included, for example, personage's sex, birthplace, permanent residence, identification card number, if having The information such as criminal history, and the also Jing of the personage often actively, panorama sketch link, camera position information, acquisition time etc..
Specifically, in one embodiment of the invention, what is stored in the dynamic portrait data base is in monitors environment The figure for collecting, the figure is the figure of the real-time grasp shoot for including facial image place scene.
Alternatively, in one embodiment of the invention, described image data base 131 include top layer images data base and Level image data base, the top layer images data base is carried out by described data access layer with the level image data base Data exchange, so as to form a totality.
Alternatively, in one embodiment of the invention, the top layer images data base manages picture number with the diode Row data communication is entered by data access layer according to storehouse.In embodiments of the present invention, the default communication interface is view data access The top layer images processing system data acquisition interface of device.
Wherein, in embodiments of the present invention, top layer images data base may refer to the image data base 131 of office of city, and this two Level image data base may refer to the image data base 131 of each level image processing system.It is appreciated that by arranging top level diagram As data base and level image data base, and face image data is shared, to improve each level image processing system The value of the face image data for getting, and can synchronous each level image processing system face image data, So that office of city is managed collectively to the face image data of level image processing system.
Alternatively, in one embodiment of the invention, described image data processing module 132 includes following at least one Kind:
Structuring engine, contrast engine, data mining engine and image storage engine;
The structuring engine is used to carry out feature extraction to the face image data to obtain facial image structuring Data;
The contrast engine is used to that the facial image structural data to be processed to obtain at face image data Reason result;
Described image storage engines are used to carry out the face image data and the facial image structural data Storage.
Referring to Fig. 3, Fig. 3 is a kind of structural representation of image data processing module 132 provided in an embodiment of the present invention.Such as Shown in Fig. 3, needed for performing different image real time transfers by the way that image data processing module 132 is distinguished into into different engines Will, and described image data processing module 132 adopts distributed structure/architecture by the structuring engine 1321, the contrast engine 1322nd, the data mining engine 1323 and described image storage engines 1324 are built in different image procossings as distributed Server group into cluster on.So that for different tasks needs, the task can be needed by distributed structure/architecture It is distributed on different servers, to realize the quick process to task.For example, when needing real-time grasp shoot and retrieve certain face Whether image is particular persons, now needs constantly to be input into retrieval tasks, and the internal memory consumed due to image procossing is big, such as The frequency of fruit real-time grasp shoot is big, is now accomplished by ceaselessly performing image recognition tasks, if by continuous image recognition tasks collection In on a server, recall precision will necessarily be now affected, so arriving different share tasks by distributed structure/architecture On different servers, the identification retrieval frequency of every server will be reduced, to improve recall precision, it is ensured that issued transaction is imitated Rate and reliability.
Alternatively, in one embodiment of the invention, the composition of described image data server cluster takes including physics Business device or virtual machine.So that above-mentioned framework is more flexible.
Alternatively, in one embodiment of the invention, described image data server safeguards component including cluster management, The cluster management safeguards component for being managed to server cluster.It is appreciated that, it is also possible to which group is safeguarded by cluster management Part carrys out each task of distribution process, and safeguards component by cluster management to realize unified management, adopts between each cluster server Load balancing ensureing reliability so that each image data processing tasks are more reliable.
Each function engine is described in detail below.
Specifically, in an embodiment of the invention, the structuring engine 1321 is used for each level image processing system The dynamic portrait picture of upload, office of city static image data are modeled, by the structural data and level image of modeling acquisition The portrait data that processing system is uploaded are preserved, and set up corresponding relation, to export people in subsequent calls static image data Face image result.In embodiments of the present invention, because data volume is very huge, and the data volume of a day must be little 24 When it is interior complete transmission and structured work amount, the structuring engine should realize possessing following characteristic by distributed structure/architecture: 1st, high concurrent, high PC cluster framework in real time;2nd, the high reliability of business is calculated, supports that multimachine is mutually standby, service dynamic migration Recover;3rd, dynamic equalization of all calculating in whole cluster is supported;4th, by stackable aggregated structure, high flexible is realized Structural extended and business dilatation.
Specifically, in an embodiment of the invention, the contrast engine 1322 is used to realize working as have individual contrast demand to be input into When, for example can be that traffic application device calls retrieval module or examining to certain facial image of sending of real-time identification module Rope, needs are first modeled processs to the facial image, then by the structured data entry of the facial image of acquisition to right Than engine, contrast engine compares it with the structural data in image data base 131, and will be more defeated than middle portrait data Go out.Because contrast needs high-timeliness, second level output comparing result because contrast engine can adopt distributed structure/architecture, with Lower characteristic:1st, High Availabitity is supported, can be rapidly switched between engine;2nd, holding load balancing cluster, it is ensured that load balancing can use; 3rd, machine state monitor in real time is supported;4th, holding load equilibrium, failure transfer;5th, high-performance buffer service, acceleration request are provided Process, support caching distributed deployment.
Specifically, in an embodiment of the invention, the data mining engine 1323 is used to work as individual data mining demand During input, for example, can be that traffic application device calls excavation module to send the moving position for inquiring about certain facial image, need Process is first modeled to it, then by the structured data entry for obtaining to data mining engine, engine is by itself and structuring Data are compared, and will be than middle portrait data output.Because the data volume of data mining is very big, therefore the data mining draws Hold up and adopt distributed structure/architecture, with following characteristic:1st, High Availabitity is supported, can be rapidly switched between engine;2nd, holding load is equal Weighing apparatus cluster, it is ensured that load balancing can use;3rd, machine state monitor in real time is supported;4th, holding load equilibrium, failure transfer;5th, provide Caching distributed deployment is supported in high-performance buffer service, acceleration request process.
Specifically, in one embodiment of the invention, the image storage engine 1324 can be in image real time transfer System triggers when receiving facial image and face image data is stored, and in structuring engine to facial image number According to carrying out after structuring, then store to obtaining rear facial image structural data.
It is appreciated that in embodiments of the present invention, by by face image processing module be divided into image data base 131 and Image processing module, and image processing module is divided into into different functional modules carries out framework, so that different functions Can be with distributed structure/architecture on a different server, and by the division of above-mentioned functions module between module so that each function Coupling can be better achieved between module with decoupling.
Wherein, face image data result refers to that image processing apparatus call corresponding function according to traffic application device When, this pair of face image data or call image data base 131 perform carry out respective handling, obtain user needs facial image Data processed result, is then shown by service application layer, to meet the service application demand of user.
Specifically, the face image data result includes following at least one:
The facial image related to default face image data and the default face in described image data base 131 The related goal activitiess region of view data goal activitiess time related to the default face image data and described pre- If the related goal activitiess track of face image data go together portrait data, the institute related to the default face image data State the corresponding biological information of default face image data and non-biometric information;The biological information include but It is not limited to following at least one:Sex and age etc.;The non-biometric information is including but not limited to following at least one: Glasses attachment feature and clothing enclosing characteristic and the portable article characteristics of other people.
Specifically, illustrate, in an example of the present invention, when user retrieves in the triggering of traffic application device 140 When module executor is as search function, obtain so as to image data processing system 130 can enter line retrieval to output to pre-set image The facial image related to the pre-set image;
Specifically, illustrate, in another example of the present invention, when user triggers reality in traffic application device 140 When identification notification module when performing in real time identification and informing function, for example, increase some target person to object library, so as to Increase the view data of the personnel in emphasis demographic data storehouse first, then image data processing system 130 is again to connecing in real time The facial image for receiving enters line retrieval, when similar face image is retrieved, then sends and notifies.
Specifically, illustrate, in an example of the present invention, when user counts in the triggering of traffic application device 140 During module, now by the relevant interface of data access layer the data of data analysis layer can be called to be counted, for example, can be with Jing is counted often actively in the personage in certain place by face image data.
Specifically, illustrate, in an example of the present invention, when user calls excavation in traffic application device 140 When module performs data mining capability, for example, the activity venue of someone's picture, the activity time of someone's picture, with certain are excavated Colleague's portrait data of personage, and the event trace of someone's picture etc., can now pass through the relevant interface of data access layer The data in image data processing system 130 in static database are called to obtain correlated results.
Alternatively, in other embodiments of the present invention, the face image data result can be answered according to business Trigger other functional modules with device to generate other different face image processing results.
Alternatively, in other embodiments of the present invention, described device 130 also includes view data AM access module 133, The top layer images data database obtains level image data by view data access device from described image harvester Face image data in storehouse, the secondary data data base can access being total to for top layer images data base by data access layer Enjoy data.
Alternatively, described image DAA is additionally operable to provide the passage of data input output to external data.
As can be seen that image processing system 100 by realize to various level system and with level disparate modules it Between data connection, it is achieved thereby that the unified management to data, improve data separate value, be also prevented from each level image and process Data between system are mutually isolated, and image data processing system adopts distributed structure/architecture, can stablize and efficient process from The data processing request of different picture systems at different levels, improves the overall efficiency of system.
The embodiment of the present invention also provides a kind of computer-readable storage medium, wherein, the computer-readable storage medium can be stored with journey Sequence, including the part or all of step of any method described in above-described embodiment during the program performing.
It should be noted that for aforesaid each method embodiment, in order to be briefly described, therefore it is all expressed as a series of Combination of actions, but those skilled in the art should know, the present invention do not limited by described sequence of movement because According to the present invention, some steps can adopt other orders or while carry out.Secondly, those skilled in the art also should know Know, embodiment described in this description belongs to preferred embodiment, involved action and module is not necessarily of the invention It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, without the portion described in detail in certain embodiment Point, may refer to the associated description of other embodiment.
In several embodiments provided herein, it should be understood that disclosed device, can be by another way Realize.For example, device embodiment described above is only schematic, such as division of described unit, is only one kind Division of logic function, can there is an other dividing mode when actually realizing, such as multiple units or component can with reference to or can To be integrated into another system, or some features can be ignored, or not perform.It is another, it is shown or discussed each other Coupling or direct-coupling or communication connection can be INDIRECT COUPLING or communication connection by some interfaces, device or unit, Can be electrical or other forms.
The unit as separating component explanation can be or may not be it is physically separate, it is aobvious as unit The part for showing can be or may not be physical location, you can with positioned at a place, or can also be distributed to multiple On NE.Some or all of unit therein can according to the actual needs be selected to realize the mesh of this embodiment scheme 's.
In addition, each functional unit in various embodiments of the present invention can be integrated in a processing unit, also may be used Being that unit is individually physically present, it is also possible to which two or more units are integrated in a unit.It is above-mentioned integrated Unit both can be realized in the form of hardware, it would however also be possible to employ the form of SFU software functional unit is realized.
If the integrated unit is realized using in the form of SFU software functional unit and as independent production marketing or used When, during a computer read/write memory medium can be stored in.Based on such understanding, technical scheme is substantially The part for contributing to prior art in other words or all or part of the technical scheme can be in the form of software products Embody, the computer software product is stored in a storage medium, including some instructions are used so that a computer Equipment (can be personal computer, server or network equipment etc.) perform the whole of each embodiment methods described of the invention or Part steps.And aforesaid storage medium includes:USB flash disk, read only memory (ROM, Read-Only Memory), random access memory are deposited Reservoir (RAM, Random Access Memory), portable hard drive, magnetic disc or CD etc. are various can be with store program codes Medium.
The above, above example only to illustrate technical scheme, rather than a limitation;Although with reference to front State embodiment to be described in detail the present invention, it will be understood by those within the art that:It still can be to front State the technical scheme described in each embodiment to modify, or equivalent is carried out to which part technical characteristic;And these Modification is replaced, and does not make the scope of the essence disengaging various embodiments of the present invention technical scheme of appropriate technical solution.

Claims (10)

1. a kind of image data processing system, it is characterised in that described image data handling system is used at the image of multi-layer Reason system, described image processing system also includes that multiple images data acquisition unit, view data access device, and business should With device, for gathering destination image data, described image DAA is used to realize described image data acquisition unit The plurality of image data acquiring module, the data between described image data handling system and the traffic application device are led to Letter, described image data handling system be used for described image harvester obtain face image data processed, it is described Traffic application device provide based on the higher layer applications in described image processing meanss, described image data processing module using point Cloth framework, described image data handling system includes:Image data base and image data processing module;
Described image data base is used to store face image data, the face image data include facial image and with it is described The corresponding structural data of facial image;
Described image data processing module is used to process the face image data, to obtain and the facial image pair The facial image structural data answered and compared based on the face image data on the basis of the facial image structural data Search, data mining results.
2. device according to claim 1, it is characterised in that described image data processing module includes following at least Kind:
Structuring engine, contrast engine, data mining engine and image storage engine;
The structuring engine is used to carry out feature extraction to the face image data to obtain facial image structural data;
The contrast engine is used to that the facial image structural data to be processed to obtain face image data process knot Really;
Described image storage engines are used to store the face image data and the facial image structural data.
3. method according to claim 1, it is characterised in that described image data base include top layer images data base and Level image data base, the top layer images data base carries out data with the level image data base by DAA Transmission and shared.
4. method according to claim 3, it is characterised in that the top layer images data base and the level image data Storehouse is carried out data transmission by data access layer.
5. the method according to claim 3 or 4, it is characterised in that described image data base includes emphasis figure database And non-emphasis figure database, static identity database and dynamic acquisition data base;
The emphasis figure database pays close attention to who object data for storage;
The non-emphasis figure database is used to store non-to pay close attention to who object data;
Described static identity data is used for storage and levies the related data of part to the identity of personage;
Described dynamic acquisition data are used to be stored in the portrait data gathered in actual monitors environment.
6. method according to claim 4, it is characterised in that described image data processing equipment will using distributed structure/architecture The structuring engine, the contrast engine, the data mining engine and described image storage engines point press distributed structure It build on the cluster of different image processing server compositions.
7. method according to claim 6, it is characterised in that the composition of described image data server cluster includes physics Server or virtual machine.
8. method according to claim 7, it is characterised in that described image data server includes cluster management maintenance group Part.
9. the method according to any one of claim 1 to 8, it is characterised in that the face image data result bag Include following at least one:
The Search Results of the facial image related to default face image data and the default people in described image data base The related goal activitiess region of face image data goal activitiess time related to the default face image data and described The related goal activitiess track of default face image data the go together portrait data related to the default face image data, The corresponding biological information of the default face image data and non-biometric information;The biological information includes But it is not limited to following at least one:Sex and age;The non-biometric information is including but not limited to following at least one: Glasses attachment feature, clothing enclosing characteristic and the portable article characteristics of other pedestrians.
10. method according to claim 9, it is characterised in that described device also includes view data AM access module, described Top layer images data database is obtained in level image data base by view data access device from described image harvester Face image data, the secondary data data base can by data access layer access top layer images data base shared number According to.
CN201611210864.1A 2016-12-24 2016-12-24 Image data processing system Pending CN106657069A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611210864.1A CN106657069A (en) 2016-12-24 2016-12-24 Image data processing system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611210864.1A CN106657069A (en) 2016-12-24 2016-12-24 Image data processing system

Publications (1)

Publication Number Publication Date
CN106657069A true CN106657069A (en) 2017-05-10

Family

ID=58827635

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611210864.1A Pending CN106657069A (en) 2016-12-24 2016-12-24 Image data processing system

Country Status (1)

Country Link
CN (1) CN106657069A (en)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109150969A (en) * 2018-07-13 2019-01-04 北京旷视科技有限公司 Data transmission method, sorter, terminating machine and data transmission system
CN109871456A (en) * 2018-12-27 2019-06-11 深圳云天励飞技术有限公司 A kind of detention house personnel relationship analysis method, device and electronic equipment
CN110704660A (en) * 2019-09-29 2020-01-17 北京市商汤科技开发有限公司 Data processing method, device, equipment and computer storage medium
CN110799972A (en) * 2017-07-21 2020-02-14 北京市商汤科技开发有限公司 Dynamic human face image storage method and device, electronic equipment, medium and program
CN113569645A (en) * 2021-06-28 2021-10-29 广东技术师范大学 Track generation method, device and system based on image detection

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8891835B2 (en) * 2008-12-12 2014-11-18 At&T Intellectual Property I, L.P. System and method for matching faces
CN104794458A (en) * 2015-05-07 2015-07-22 北京丰华联合科技有限公司 Fuzzy video person identifying method
CN104978550A (en) * 2014-04-08 2015-10-14 上海骏聿数码科技有限公司 Face recognition method and system based on large-scale face database
CN105975964A (en) * 2016-07-01 2016-09-28 恒东信息科技无锡有限公司 Intelligent comprehensive application platform based on perceptive channel

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8891835B2 (en) * 2008-12-12 2014-11-18 At&T Intellectual Property I, L.P. System and method for matching faces
CN104978550A (en) * 2014-04-08 2015-10-14 上海骏聿数码科技有限公司 Face recognition method and system based on large-scale face database
CN104794458A (en) * 2015-05-07 2015-07-22 北京丰华联合科技有限公司 Fuzzy video person identifying method
CN105975964A (en) * 2016-07-01 2016-09-28 恒东信息科技无锡有限公司 Intelligent comprehensive application platform based on perceptive channel

Cited By (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110799972A (en) * 2017-07-21 2020-02-14 北京市商汤科技开发有限公司 Dynamic human face image storage method and device, electronic equipment, medium and program
CN109150969A (en) * 2018-07-13 2019-01-04 北京旷视科技有限公司 Data transmission method, sorter, terminating machine and data transmission system
CN109871456A (en) * 2018-12-27 2019-06-11 深圳云天励飞技术有限公司 A kind of detention house personnel relationship analysis method, device and electronic equipment
CN109871456B (en) * 2018-12-27 2021-05-11 深圳云天励飞技术有限公司 Method and device for analyzing relationship between watchmen and electronic equipment
CN110704660A (en) * 2019-09-29 2020-01-17 北京市商汤科技开发有限公司 Data processing method, device, equipment and computer storage medium
CN113569645A (en) * 2021-06-28 2021-10-29 广东技术师范大学 Track generation method, device and system based on image detection
CN113569645B (en) * 2021-06-28 2024-03-22 广东技术师范大学 Track generation method, device and system based on image detection

Similar Documents

Publication Publication Date Title
CN106657069A (en) Image data processing system
CN104519316B (en) Monitoring system, monitoring method and recording medium
US9342594B2 (en) Indexing and searching according to attributes of a person
CN101510205B (en) Method for implementing automatically clustering photographs, apparatus and system
CN107370983A (en) Acquisition methods and device for the whereabouts track of video monitoring system
CN107018042A (en) Method for tracing and tracing system for online service system
CN108345854A (en) Information processing method, device, system based on image analysis and storage medium
CN109783685A (en) A kind of querying method and device
CN108683877A (en) Distributed massive video resolution system based on Spark
CN104966006A (en) Intelligent face identification system based on cloud variation platform
CN107844524A (en) Data processing method, data processing equipment, computer equipment and storage medium
CN101489116A (en) Video surveillance system and method using ip-based networks
CN106650589A (en) Real-time face recognition system and method
CN109977758A (en) A kind of face identification system and method based on cloud platform management
CN108304428A (en) Information recommendation method and device
CN112818149A (en) Face clustering method and device based on space-time trajectory data and storage medium
CN110827164A (en) Intelligent aquaculture management system and method based on edge cloud
CN204926080U (en) System for video can be retrieveed with target to discernment people's face or video recording of license plate target
CN106844727B (en) Mass image characteristic data distributed acquisition processing and grading application system and method
CN106777215A (en) A kind of image searching result display methods and device
CN207589029U (en) A kind of intelligent mobile full-view video image monitoring system
CN110119456A (en) Retrieve the method and device of image
CN109120896B (en) Security video monitoring guard system
CN115114236A (en) Management system and management method for photos and/or videos
CN111275583A (en) Service method based on face recognition and database

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20170510