CN106844727B - Mass image characteristic data distributed acquisition processing and grading application system and method - Google Patents
Mass image characteristic data distributed acquisition processing and grading application system and method Download PDFInfo
- Publication number
- CN106844727B CN106844727B CN201710073491.6A CN201710073491A CN106844727B CN 106844727 B CN106844727 B CN 106844727B CN 201710073491 A CN201710073491 A CN 201710073491A CN 106844727 B CN106844727 B CN 106844727B
- Authority
- CN
- China
- Prior art keywords
- target image
- database
- processing unit
- information
- information processing
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/71—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/70—Information retrieval; Database structures therefor; File system structures therefor of video data
- G06F16/78—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/783—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
- G06F16/7837—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content using objects detected or recognised in the video content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
- G06V10/507—Summing image-intensity values; Histogram projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
- G06V20/46—Extracting features or characteristics from the video content, e.g. video fingerprints, representative shots or key frames
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention provides a distributed acquisition processing and grading application system and method for mass image characteristic data, which comprises the following steps: image acquisition unit, at least one characteristic acquisition unit, at least one picture directory server, at least one subordinate information processing unit, at least one subordinate database, higher information processing unit and higher database, the subordinate information processing unit includes: the system comprises an information storage module, a memory updating module and a lower-level memory database. The invention realizes the integration of the processing capacity of a plurality of computers under the scene of multi-level networking, and improves the working efficiency of the feature extraction of video information and the further processing of data.
Description
Technical Field
The invention belongs to the technical field of image big data processing, and particularly relates to a distributed acquisition processing and grading application system and method for massive image characteristic data.
Background
With the great development of the related technical fields such as computers, digital images, artificial intelligence and the like in recent years, a large number of cameras for generating digital image information and software and hardware equipment for generating digital image data in the fields of security, medical treatment and the like are used in the social activity level including production and life, and the data bring great value to the work and life of people. With the gradual increase of the number of devices generating data, especially devices in some security and protection fields, the device has the attributes of long continuous operation time, high data generation frequency, strong real-time performance, huge data volume and the like in a certain application scene, which brings great technical problems for the feature extraction processing of digital image data and the subsequent data analysis and other applications.
In the face of these technical difficulties, the existing solutions generally adopt a high-configuration computer mode, and use high-performance single-machine hardware devices, especially high-frequency CPUs. The performance of computer hardware is continuously improved, and in order to pursue the upper limit of application performance, the comprehensive cost of data utilization is greatly increased only by continuously investing a larger amount of capital.
The other method also belongs to hardware performance improvement of a single machine level, mainly increases a GPU and other computing units except a CPU, has the same disadvantages as the method, and leads to continuous cost improvement.
Disclosure of Invention
The invention provides a distributed acquisition processing and grading application system and method for massive image characteristic data, and aims to solve the technical problems.
The invention relates to a distributed acquisition processing and grading application system for mass image characteristic data, which comprises the following components:
image acquisition unit, at least one characteristic acquisition unit, at least one picture directory server, at least one subordinate information processing unit, at least one subordinate database, higher information processing unit and higher database, the subordinate information processing unit includes: the system comprises an information storage module, a memory updating module and a lower-level memory database;
the image acquisition unit is used for acquiring videos and images and storing the videos and the images;
the characteristic acquisition unit is used for detecting a target image in the video or image, extracting a characteristic value corresponding to the target image, sending the characteristic value and the accessory information of the target image to the information storage module, and sending the target image to the picture directory server;
the picture directory server is used for storing the target image processed by the characteristic acquisition unit and supporting the data access of the superior information processing unit through FTP and HTTP communication protocols;
the information storage module is used for sending the characteristic value of the target image to the memory updating module and sending the attached information of the target image to a lower-level database;
the memory updating module is used for updating the characteristic value of the target image to the lower-level memory database;
the lower database is used for storing the auxiliary information of the target image;
the upper level information processing unit includes:
the upper-level memory database and the application service module;
the upper-level memory database is used for receiving and storing the characteristic value of the target image sent by the lower-level information processing unit;
the application service module is used for comparing or inquiring the eigenvalue of the target image characteristic stored in a superior memory database, and restoring the scene corresponding to the target image according to the target image accessory information stored in the superior database;
and the upper database is used for receiving and storing the auxiliary information of the target image sent by the lower information processing unit.
Further, the feature acquisition unit includes:
the system comprises a target detection module, a feature extraction module and an image storage management module;
the target detection module is used for receiving the video or the image sent by the image acquisition unit and detecting the video or the image according to the target requirement to determine a target image;
the feature extraction module is used for extracting features of the target image;
the picture storage management module is used for carrying out renaming, classifying, filtering and screening on the target image with the extracted characteristic value.
Further, the lower information processing unit further includes:
the information synchronization module is configured to update a feature value of the target image in a lower-level memory database to a higher-level memory database, and update attached information of the target image in the lower-level database to the higher-level database, and the information synchronization module is configured to receive a control instruction sent by the higher-level information processing unit, where the control instruction includes: deleting a characteristic value of a certain appointed target image stored in a lower-level memory database and accessory information stored in the lower-level database; the feature value and the attached information of a certain specified target image are updated from the upper information processing unit to the lower information processing unit.
The invention relates to a distributed acquisition processing and grading application method of mass image characteristic data, which comprises the following steps:
the image acquisition unit acquires videos and images and stores the videos and the images;
the characteristic acquisition module acquires the video and the image, detects a target image in the video or the image, extracts a characteristic value corresponding to the target image, sends the characteristic value and the accessory information of the target image to the information storage module, and sends the target image to a picture directory server;
the lower processing unit receives the characteristic value, stores the accessory information of the target image into a lower database, and updates the lower database in real time according to the characteristic value;
and the upper information processing unit receives and stores the characteristic value of the target image sent by the lower information processing unit.
Further, after the upper information processing unit receives and stores the feature value of the target image sent by the lower information processing unit, the method includes:
the directory server stores the target image after extracting the characteristic value corresponding to the target image and supports the data access of the superior information processing unit through FTP and HTTP communication protocols.
Further, after updating the lower level database in real time according to the feature value, the method further includes:
judging whether the state of the information synchronization module is synchronous, if so, updating the characteristic value of the target image in the lower memory database to the upper memory database, updating the auxiliary information of the target image in the lower database to the upper database, and receiving a control instruction sent by an upper information processing unit, wherein the control instruction comprises: deleting the characteristic value of the target image stored in a lower level memory database and the accessory information stored in a lower level database, updating the characteristic value and the accessory information of the target image from a higher level information processing unit to a lower level information processing unit, and if not, updating the characteristic value of the target image into the lower level memory database.
The invention realizes the integration of the processing capacity of a plurality of computers under the scene of multi-level networking, and improves the working efficiency of the feature extraction of video information and the further processing of data.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
FIG. 1 is a schematic diagram of a distributed acquisition processing and hierarchical application system for mass image characteristic data according to the present invention;
FIG. 2 is a flow chart of a distributed acquisition processing and hierarchical application method of the mass image characteristic data of the present invention;
FIG. 3 is a flow chart of image feature acquisition in accordance with the present invention;
FIG. 4 is a flow chart of the real-time update process of the subordinate information processing unit according to the present invention;
FIG. 5 is a flow chart of information synchronization between a lower information processing unit and an upper information processing unit according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Fig. 1 is a schematic diagram of a distributed acquisition processing and hierarchical application system for mass image characteristic data according to the present invention, as shown in fig. 1, the system of this embodiment includes:
an image acquisition unit 101, at least one feature acquisition unit 102, at least one picture directory server 103, at least one lower information processing unit 104, at least one lower database 105, an upper information processing unit 106, and an upper database 107, the lower information processing unit including: an information storage module 108, a memory update module 109, and a lower memory database 110, where the upper information processing unit includes: memory database 111, application service module 112, the feature acquisition unit includes: an object detection module 113, a feature extraction module 114, and a picture storage management 115, wherein the lower information processing unit includes: an information synchronization module 116;
the image acquisition unit is used for acquiring videos and images and storing the videos and the images;
the characteristic acquisition unit is used for detecting a target image in the video or image, extracting a characteristic value corresponding to the target image, sending the characteristic value and the accessory information of the target image to the information storage module, and sending the target image to the picture directory server;
the picture directory server is used for storing the target image processed by the characteristic acquisition unit and supporting the data access of the superior information processing unit through FTP and HTTP communication protocols;
the information storage module is used for sending the characteristic value of the target image to the memory updating module and sending the attached information of the target image to a lower-level database;
the memory updating module is used for updating the characteristic value of the target image to the lower-level memory database;
the lower database is used for storing the auxiliary information of the target image;
the upper level information processing unit includes:
the upper-level memory database and the application service module;
the upper-level memory database is used for receiving and storing the characteristic value of the target image sent by the lower-level information processing unit;
the application service module is used for comparing or inquiring the eigenvalue of the target image characteristic stored in a superior memory database, and restoring the scene corresponding to the target image according to the target image accessory information stored in the superior database;
and the upper database is used for receiving and storing the auxiliary information of the target image sent by the lower information processing unit.
Specifically, the image capturing unit in the system of this embodiment is a device for capturing videos and images of various service systems. There may be many in number, and the captured video and images typically appear in multiple paths or files.
The feature acquisition unit of the image acquisition unit corresponding to the same service detects a middle target image in a video file or a video stream, extracts a feature value corresponding to the target image, and stores the feature value into the picture directory server. Further, the feature acquisition unit includes: the system comprises a target detection module, a feature extraction module and an image storage management module; the target detection module is used for receiving the video or the image sent by the image acquisition unit and detecting the video or the image according to the target requirement to determine a target image; the feature extraction module is used for extracting features of the target image; the picture storage management module is used for carrying out renaming, classifying, filtering and screening on the target image with the extracted characteristic value. Specifically, the target detection module selects different detection algorithms for different target requirements. The target detection module of the embodiment establishes a background model based on colors and color gradients by using a statistical method, updates the background model in real time, and finally comprehensively considers the two background models to effectively detect the target. Similarly, the feature extraction module extracts the types of features according to specific business processing requirements. The feature extraction module of this embodiment first divides an image into small connected regions, then acquires a gradient or edge directional histogram of each pixel point in the region, performs contrast normalization on a local histogram in a larger range of the image, that is, calculates the density of each histogram in this region, then normalizes each connected region in the region according to this density, and finally combines these histograms to form a feature description. The object detection module and the feature extraction module allow flexible configuration according to specific business contents, which may be based on, but not limited to, the above.
The lower information processing unit is used for storing the structural information generated by the feature extraction module and further synchronously distributing the structural information. The data is stored in the lower-level database through the information storage module and is updated to the lower-level memory database in real time through the memory updating module. The memory updating module polls the change condition of the lower-level database through the timing device and transfers the latest data to the lower-level memory database. The lower memory data is a structured database system which is stored in the lower information processing unit and takes the memory as a storage and operation place. The lower database refers to a structured database based on physical disk storage existing in the lower information processing unit. And the information synchronization module is used for storing the unsynchronized data in the lower database and the lower memory database into the corresponding upper database and the upper memory database after receiving the synchronization instruction.
The upper information processing unit is a processing unit for providing data support for a plurality of application services, and the data source is a remote lower information processing unit. The upper-level memory database is a structured database which is stored in the upper-level information processing unit and takes the memory as a storage and operation place. The application service module is a structured database stored in the upper information processing unit based on physical disk storage.
Compared with a magnetic disk, the data read-write speed of the memory is higher by several orders of magnitude, and the application performance can be greatly improved by storing data in the memory compared with accessing from the magnetic disk. A subordinate database is a data warehouse built on computer storage devices that organizes, stores, and manages data according to a data structure. The system is a database management system stored in a physical disk and used for storing the structured characteristic values and other related structured data. The application service module refers to a specific service logic for solving a certain requirement by calling corresponding data through a superior database, a superior memory database and a picture directory server. The module provides a common interface for such services for the relevant data manipulation.
Further, the lower information processing unit further includes:
the information synchronization module is configured to update a feature value of the target image in a lower-level memory database to a higher-level memory database, and update attached information of the target image in the lower-level database to the higher-level database, and the information synchronization module is configured to receive a control instruction sent by the higher-level information processing unit, where the control instruction includes: deleting a characteristic value of a certain appointed target image stored in a lower-level memory database and accessory information stored in the lower-level database; the feature value and the attached information of a certain specified target image are updated from the upper information processing unit to the lower information processing unit. Specifically, the information synchronization module of the present embodiment copies and stores the processing result of the lower information processing unit in the upper information processing unit. The path is saved mainly from the data in the lower database and the lower memory database to the corresponding upper database and the upper memory database, and is generally completed through a network link.
The information synchronization module is used for finishing the two-way communication between the upper-level memory database of the upper-level information processing unit and the memory updating module of the lower-level information processing unit.
Fig. 2 is a flowchart of a distributed acquisition processing and hierarchical application method for mass image characteristic data according to the present invention, and as shown in fig. 2, the method of the present embodiment includes:
102, a feature acquisition module acquires the video and the image, detects a target image in the video or the image, extracts a feature value corresponding to the target image, sends the feature value and accessory information of the target image to an information storage module, and sends the target image to a picture directory server;
the specific workflow of the feature acquisition module is shown in fig. 3. For example, the feature acquisition module detects a moving object in a current video or image frame by using a moving object detection algorithm. It is also possible to identify a specific target person using a face recognition algorithm. The auxiliary information corresponding to the moving target or the target person is a feature vector and coding key value pair, image acquisition time, acquisition position, resolution, storage position and the like, and the features corresponding to the moving target or the specific person and the auxiliary information of the target image corresponding to the moving target or the specific person are sent to the information storage module. And the target image is sent to the picture directory server.
103, the lower processing unit receives the characteristic value, stores the accessory information of the target image into a lower database, and updates the lower database in real time according to the characteristic value;
the work flow of the lower information processing unit is shown in fig. 4. For example, the lower information processing unit converts the face recognition data into a face feature code matrix.
And 104, receiving the characteristic value of the target image sent by the lower information processing unit by the upper information processing unit and storing the characteristic value.
Further, after the upper information processing unit receives and stores the feature value of the target image sent by the lower information processing unit, the method includes:
the directory server stores the target image after extracting the characteristic value corresponding to the target image and supports the data access of the superior information processing unit through FTP and HTTP communication protocols.
Further, after updating the lower level database in real time according to the feature value, the method further includes:
judging whether the state of the information synchronization module is synchronous, if so, updating the characteristic value of the target image in the lower memory database to the upper memory database, updating the auxiliary information of the target image in the lower database to the upper database, and receiving a control instruction sent by an upper information processing unit, wherein the control instruction comprises: deleting the characteristic value of the target image stored in a lower level memory database and the accessory information stored in a lower level database, updating the characteristic value and the accessory information of the target image from a higher level information processing unit to a lower level information processing unit, and if not, updating the characteristic value of the target image into the lower level memory database.
As shown in fig. 5, the information synchronization flow between the lower information processing unit and the upper information processing unit of the present invention:
step 1: starting an information synchronization process;
step 2: judging whether the system is set to be in active synchronization or not, and entering an information synchronization waiting state in the step 5 when the judgment result is in an active synchronization mode;
and step 3: if the judgment result in the step 2 is the non-active synchronization mode, the mode is a timing polling mode, whether the polling time is reached is judged, and if the polling time is reached, the step 5 is executed;
and 4, step 4: if the polling time is not reached in the step 3, entering a step 5 after waiting for the polling time to reach;
and 5: entering a waiting information synchronization state;
step 6: judging whether the previous synchronous transaction is finished, if not, returning to the step 5 to continue waiting for the information synchronization state;
and 7: if the last synchronous transaction is finished, synchronizing the data which are marked as being unsynchronized in the lower database and the memory database to the upper database and the memory database;
and 8: after the synchronization is finished, updating the synchronization marks of the lower level database and the memory database as synchronized;
and step 9: the current information synchronization transaction is ended.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (6)
1. A distributed acquisition processing and grading application system for mass image characteristic data is characterized by comprising the following components:
image acquisition unit, at least one characteristic acquisition unit, at least one picture directory server, at least one subordinate information processing unit, at least one subordinate database, higher information processing unit and higher database, the subordinate information processing unit includes: the system comprises an information storage module, a memory updating module and a lower-level memory database;
the image acquisition unit is used for acquiring videos and images and storing the videos and the images;
the characteristic acquisition unit is used for detecting a target image in the video or image, extracting a characteristic value corresponding to the target image, sending the characteristic value and the accessory information of the target image to the information storage module, and sending the target image to the picture directory server;
the picture directory server is used for storing the target image processed by the characteristic acquisition unit and supporting the data access of the superior information processing unit through FTP and HTTP communication protocols;
the information storage module is used for sending the characteristic value of the target image to the memory updating module and sending the attached information of the target image to a lower-level database;
the memory updating module is used for updating the characteristic value of the target image to the lower-level memory database;
the lower database is used for storing the auxiliary information of the target image;
the upper level information processing unit includes:
the upper-level memory database and the application service module;
the upper-level memory database is used for receiving and storing the characteristic value of the target image sent by the lower-level information processing unit;
the application service module is used for comparing or inquiring the characteristic values of the target images stored in a superior memory database and restoring the scenes corresponding to the target images according to the accessory information of the target images stored in the superior database;
the upper database is used for receiving and storing the auxiliary information of the target image sent by the lower information processing unit;
the lower level database is a data warehouse established on a computer storage device and used for organizing, storing and managing data according to a data structure, and is a database system stored in a physical disk.
2. The system of claim 1, wherein the feature acquisition unit comprises:
the system comprises a target detection module, a feature extraction module and an image storage management module;
the target detection module is used for receiving the video or the image sent by the image acquisition unit and detecting the video or the image according to the target requirement to determine a target image;
the feature extraction module is used for extracting features of the target image;
the picture storage management module is used for carrying out renaming, classifying, filtering and screening on the target image with the extracted characteristic value.
3. The system according to claim 1 or 2, wherein the subordinate information processing unit further comprises:
an information synchronization module, configured to update a feature value of the target image in a lower-level memory database to a higher-level memory database, and update the attached information of the target image in the lower-level database to the higher-level database, where the information synchronization module is configured to receive a control instruction sent by the higher-level information processing unit, where the control instruction includes: deleting a characteristic value of a certain appointed target image stored in a lower-level memory database and accessory information stored in the lower-level database; the feature value and the attached information of a certain specified target image are updated from the upper information processing unit to the lower information processing unit.
4. A distributed acquisition processing and hierarchical application method of mass image characteristic data based on the system of any one of claims 1 to 3 is characterized by comprising the following steps:
the image acquisition unit acquires videos and images and stores the videos and the images;
the characteristic acquisition module acquires the video and the image, detects a target image in the video or the image, extracts a characteristic value corresponding to the target image, sends the characteristic value and the accessory information of the target image to the information storage module, and sends the target image to the picture directory server;
the lower processing unit receives the characteristic value, stores the accessory information of the target image into a lower database, and updates the lower database in real time according to the characteristic value;
the superior information processing unit receives and stores the characteristic value of the target image sent by the inferior information processing unit;
the lower level database is a data warehouse established on a computer storage device and used for organizing, storing and managing data according to a data structure, and is a database system stored in a physical disk.
5. The method according to claim 4, wherein after the upper information processing unit receives and stores the feature value of the target image transmitted by the lower information processing unit, the method comprises:
the directory server stores the target image after extracting the characteristic value corresponding to the target image and supports the data access of the superior information processing unit through FTP and HTTP communication protocols.
6. The method of claim 5, wherein after updating the subordinate database in real-time according to the eigenvalue, the method further comprises:
judging whether the state of the information synchronization module is synchronous, if so, updating the characteristic value of the target image in the lower memory database to the upper memory database, updating the auxiliary information of the target image in the lower database to the upper database, and receiving a control instruction sent by an upper information processing unit, wherein the control instruction comprises: deleting the characteristic value of the target image stored in a lower level memory database and the accessory information stored in a lower level database, updating the characteristic value and the accessory information of the target image from a higher level information processing unit to a lower level information processing unit, and if not, updating the characteristic value of the target image into the lower level memory database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710073491.6A CN106844727B (en) | 2017-02-10 | 2017-02-10 | Mass image characteristic data distributed acquisition processing and grading application system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710073491.6A CN106844727B (en) | 2017-02-10 | 2017-02-10 | Mass image characteristic data distributed acquisition processing and grading application system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106844727A CN106844727A (en) | 2017-06-13 |
| CN106844727B true CN106844727B (en) | 2020-07-10 |
Family
ID=59122304
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710073491.6A Active CN106844727B (en) | 2017-02-10 | 2017-02-10 | Mass image characteristic data distributed acquisition processing and grading application system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106844727B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111343209B (en) * | 2020-05-21 | 2020-08-25 | 浙江双视红外科技股份有限公司 | Picture processing method with temperature information |
| CN112799588B (en) * | 2020-12-31 | 2022-10-21 | 深圳软通动力信息技术有限公司 | Data storage method for loading container cluster application data by using external storage |
| CN113987089B (en) * | 2021-12-28 | 2022-08-26 | 北京力控元通科技有限公司 | System cascading method, data processing method and device |
| CN115062169A (en) * | 2022-06-09 | 2022-09-16 | 安徽英福泰克信息科技有限公司 | Image synchronous updating method based on image storage library shooting record |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102663053A (en) * | 2012-03-30 | 2012-09-12 | 上海博康智能信息技术有限公司 | Distributed server system based on image content search |
| JP2014178739A (en) * | 2013-03-13 | 2014-09-25 | Sony Corp | Image processor and image processing method and program |
| CN104156458B (en) * | 2014-08-20 | 2017-09-22 | 北京小度互娱科技有限公司 | The extracting method and device of a kind of information |
-
2017
- 2017-02-10 CN CN201710073491.6A patent/CN106844727B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106844727A (en) | 2017-06-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP6916895B2 (en) | Face image duplication deletion method and device, electronic device, storage medium, program | |
| US10891465B2 (en) | Methods and apparatuses for searching for target person, devices, and media | |
| CN106844727B (en) | Mass image characteristic data distributed acquisition processing and grading application system and method | |
| EP4156017A1 (en) | Action recognition method and apparatus, and device and storage medium | |
| CN107798354B (en) | Image clustering method and device based on face image and storage equipment | |
| US20190325198A1 (en) | Surveillance and monitoring system that employs automated methods and subsystems that identify and characterize face tracks in video | |
| WO2019080908A1 (en) | Image processing method and apparatus for implementing image recognition, and electronic device | |
| CN109948734B (en) | Image clustering method and device and electronic equipment | |
| CN110941978B (en) | Face clustering method and device for unidentified personnel and storage medium | |
| CN104391879B (en) | The method and device of hierarchical clustering | |
| KR20150015016A (en) | Searching for events by attendants | |
| CN111553327B (en) | Clothing identification method, device, equipment and medium | |
| CN106503112B (en) | Video retrieval method and device | |
| CN114973057A (en) | Video image detection method based on artificial intelligence and related equipment | |
| CN112883827A (en) | Method and device for identifying designated target in image, electronic equipment and storage medium | |
| CN111783677A (en) | Face recognition method, face recognition device, server and computer readable medium | |
| TW202018540A (en) | Method, apparatus and electronic device for database updating and computer storage medium thereof | |
| Noor et al. | ibuck: Reliable and secured image processing middleware for openstack swift | |
| CN112487943B (en) | Key frame de-duplication method and device and electronic equipment | |
| CN112669353B (en) | Data processing method, data processing device, computer equipment and storage medium | |
| CN114998599A (en) | Data processing method, device, equipment and computer readable medium | |
| CN115495606A (en) | Image gathering method and system | |
| CN111191612B (en) | Video image matching method, device, terminal equipment and readable storage medium | |
| CN108984614B (en) | Visual image rapid identification method based on big data environment | |
| US9361540B2 (en) | Fast image processing for recognition objectives system |
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 | ||
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20180621 Address after: 850700 Changsha Road, Gongga County, Shannan City, Tibet autonomous region 12 Applicant after: Shannan far macro Technology Co., Ltd. Address before: 116000 Yinhai Road 16 building, 701 Huangpu Road, hi tech park, Dalian, Liaoning Applicant before: Zhuhai Special Economic Zone Technology Co., Ltd. Dalian branch |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |