CN114201640A - Garden management method and system based on video acquisition and related equipment - Google Patents
Garden management method and system based on video acquisition and related equipment Download PDFInfo
- Publication number
- CN114201640A CN114201640A CN202111316733.2A CN202111316733A CN114201640A CN 114201640 A CN114201640 A CN 114201640A CN 202111316733 A CN202111316733 A CN 202111316733A CN 114201640 A CN114201640 A CN 114201640A
- Authority
- CN
- China
- Prior art keywords
- picture
- data
- server
- database
- small
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 55
- 238000004458 analytical method Methods 0.000 claims abstract description 67
- 230000006399 behavior Effects 0.000 claims description 39
- 238000000034 method Methods 0.000 claims description 27
- 238000001514 detection method Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 14
- 230000006870 function Effects 0.000 claims description 11
- 238000013459 approach Methods 0.000 claims description 2
- 238000012800 visualization Methods 0.000 abstract description 3
- 238000013528 artificial neural network Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 6
- 230000005540 biological transmission Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000000391 smoking effect Effects 0.000 description 4
- 238000012545 processing Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 2
- 230000009545 invasion Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 229910052799 carbon Inorganic materials 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
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
- G06F16/70—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
- G06F16/784—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 the detected or recognised objects being people
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5005—Allocation of resources, e.g. of the central processing unit [CPU] to service a request
- G06F9/5027—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals
- G06F9/505—Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resource being a machine, e.g. CPUs, Servers, Terminals considering the load
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5083—Techniques for rebalancing the load in a distributed system
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/54—Interprogram communication
- G06F9/546—Message passing systems or structures, e.g. queues
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2209/00—Indexing scheme relating to G06F9/00
- G06F2209/54—Indexing scheme relating to G06F9/54
- G06F2209/548—Queue
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Library & Information Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Analysis (AREA)
- Processing Or Creating Images (AREA)
Abstract
The invention is suitable for the field of picture analysis, and provides a park management method, a park management system and related equipment based on video acquisition, wherein the park management method comprises the following steps: acquiring big image data and small image data through a data acquisition unit, and sending the big image data and the small image data to a data receiving server; the data receiving server sends the big image data and the small image data to a search engine server and sends the small image data to a message queue; the analysis server analyzes the picture information of the message queue and stores the picture information into a database; the analysis server analyzes the early warning information in the queue and stores the early warning information in a database; the analysis server identifies the human face, the human figure and the vehicle, and stores the identified human face, the human figure and the vehicle picture into a database; the analysis server carries out behavior recognition on the recognized face picture and stores the recognized face behavior data into a database; and reading other servers and databases through the application server, and sending the pictures in the databases to the front end for display. The invention realizes the management efficiency improvement and the information visualization of the park management.
Description
Technical Field
The invention belongs to the field of picture analysis, and particularly relates to a park management method and system based on video acquisition and related equipment.
Background
The concept of the intelligent park is that through an informatization tool and a management means, the park resource management and enterprise service are more intelligent, efficient, low-carbon and environment-friendly. Various gardens are because the facility is imperfect, lack the modern management rule of the garden of unified specialty, from the aspect of garden management, because different garden information establishment process system of forming oneself, lead to the information level low, lack long-range, centralized control mode, secondly, several aspects such as garden management limitation and security protection, garden consumption, do not cover fields such as personnel management, space management of garden, make the garden management mode be in passive state, the personnel of implementing the management can't adjust the management strategy to the all kinds of circumstances of garden.
In the existing park management system, as the park only observes videos captured by the cameras, all conditions in the park need to be observed manually; or the park workers are managed only in a manual card punching mode, and the park intruders are managed in a monitoring mode to manage all matters of the park. The above approaches belong to traditional campus management, and lack management efficiency and information visualization.
Disclosure of Invention
The embodiment of the invention provides a park management method, a park management system and related equipment based on video acquisition, and aims to solve the problems that the traditional park management is lack of management efficiency and information visualization.
In a first aspect, an embodiment of the present invention provides a campus management method based on video capture, where the method includes:
acquiring large graph data and small graph data in real time through a video acquisition unit, and sending the large graph data and the small graph data to a data receiving server in a load balancing cluster mode; the small image data is obtained by amplifying and/or cutting the large image data;
the data receiving server sends the big image data and the small image data to a search engine server, and simultaneously sends the small image data to a message queue;
consuming the message queue through a resolution server, resolving picture information of the consumed small picture data, and storing each resolved picture information into a database, wherein the picture information comprises attributes and characteristic values of pictures;
carrying out face, human shape and vehicle identification on the small image data in the message queue through the analysis server, and storing the identified face picture and/or human shape picture and/or vehicle picture into the database;
performing behavior recognition on the face picture through the analysis server, and storing recognized face behavior data into the database;
the analysis server analyzes the small image data in the message queue, marks the early warning information of the images in the small image data according to a preset rule, and stores the early warning information into the database;
and reading the search engine server and the database through an application server, sending the pictures meeting the preset requirements to a front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
Further, the load balancing clustering manner is based on miniO.
Further, the step of consuming the message queue by the parsing server, parsing the picture information of the consumed thumbnail data, and storing each parsed picture information in the database, wherein the picture information includes attributes and feature values of pictures, specifically includes:
the analysis server consumes the small graph data in the message queue according to the sequence of the message queue, performs feature detection on each small graph data by using a trained feature detection network to obtain the picture information of each small graph data, wherein the picture information comprises the attribute and the feature value of a picture, and then stores the picture information into the database.
Still further, the database is based on My SQL.
Further, the step of recognizing the human face, the human figure and the vehicle of the small image data in the data receiving server through the analysis server and storing the recognized human face picture and/or the human figure picture and/or the vehicle picture into the database specifically comprises the following steps:
and the analysis server respectively identifies the human face, the human shape and the vehicle of the small image data by using a trained target detection network, and stores the identified human face picture, the human shape picture and the vehicle picture into the database.
Furthermore, the step of performing behavior recognition on the face picture through the analysis server and storing the recognized face behavior data into the database specifically includes:
and the analysis server performs behavior detection on the face picture by using a trained behavior detection network, and stores the recognized face behavior as the additional attribute of the face picture into the database.
Furthermore, the step of analyzing the small graph data in the data receiving server by the analysis server, marking the early warning information on the picture in the small graph data according to a preset rule, and storing the early warning information in a database, wherein the preset rule is as follows:
and if any one of preset early warning features exists in the pictures in the small picture data, marking the early warning features according to types.
In a second aspect, an embodiment of the present invention further provides a park management system, including:
the data acquisition module is used for controlling the video acquisition unit to acquire large graph data and small graph data in real time and sending the large graph data and the small graph data to the data receiving server in a load balancing cluster mode; the small image data is obtained by amplifying and/or cutting the large image data;
the data receiving module is used for sending the large graph data and the small graph data to a search engine server and sending the small graph data to a message queue;
the picture information analysis module is used for controlling an analysis server to consume the message queue, analyzing the picture information of the consumed small picture data and storing each analyzed picture information into the search engine server, wherein the picture information comprises the attribute and the characteristic value of a picture;
the image type analysis module is used for controlling the analysis server to identify faces, human shapes and vehicles of the small image data in the data receiving server and store the identified face images and/or human shape images and/or vehicle images into a database;
the behavior analysis module is used for controlling the analysis server to perform behavior identification on the face picture and storing the identified face behavior data into the database;
the early warning information analysis module is used for controlling the analysis server to analyze the small picture data in the data receiving server, marking early warning information on pictures in the small picture data according to a preset rule and storing the early warning information into the database;
and the application service module is used for controlling an application server to read the search engine server and the database, sending the pictures meeting the preset requirements to the front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
In a third aspect, an embodiment of the present invention further provides a computer device, including: a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the video capture-based campus management method according to any one of the above embodiments when executing the computer program.
In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements the steps in the method for managing a campus based on video capture as described in any one of the above embodiments.
The beneficial effect achieved by the invention is that the park management system is constructed by adopting the storage design of load balance and the message queue based on Pulsar, so that the operation efficiency of the management system can be improved, and the rapid management of personnel and early warning events in the park can be realized.
Drawings
Fig. 1 is a block flow diagram of a campus management method based on video capture according to an embodiment of the present invention;
fig. 2 is a block diagram of a campus management system 200 according to the present invention;
fig. 3 is a schematic structural diagram of a computer device 300 according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Referring to fig. 1, fig. 1 is a block flow diagram of a campus management method based on video capture according to an embodiment of the present invention, where the method specifically includes the following steps:
s101, acquiring large graph data and small graph data in real time through a video acquisition unit, and sending the large graph data and the small graph data to a data receiving server in a load balancing cluster mode, wherein the small graph data is obtained through amplification and/or cutting of the large graph data.
In the embodiment of the present invention, the data acquisition unit may be an intelligent camera having functions of image pickup, snapshot, and data transmission, the data acquisition unit has a plurality of data acquisition units, and is disposed in different areas of a campus, the data acquisition unit can transmit acquired image data to corresponding receiving devices through data transmission methods such as a wired network and a wireless local area network, the data acquisition unit has an image processing function, and when acquiring an image, the image data is divided into large image data and small image data through a segmentation method, wherein the small image data is obtained by amplifying and/or cropping the large image data, in the embodiment of the present invention, the data receiving server is used to receive the large image data and the small image data acquired by the data acquisition unit in real time, and the data receiving server is implemented in an minIO method, in the embodiment of the invention, the data receiving server is realized by a plurality of minIO clusters, and a plurality of data acquisition units realize data transmission with the data receiving server in a load balancing cluster mode, that is, when the data acquisition units send the large image data and the small image data to the data receiving server, the data volume of the large image data and the small image data can be differentiated according to the performance of a transmission channel and the response condition in the group of the data receiving server and the large image data and the small image data can be stored in the data receiving server in a balanced mode.
S102, the data receiving server sends the big image data and the small image data to a search engine server, and meanwhile, sends the small image data to a message queue.
Specifically, in the embodiment of the present invention, the message queue is implemented based on pulser, which is a message system, and queue management of data to be processed by pulser can improve processing efficiency of the system, and the search engine server is an application server with an index search function, and a large data volume can be quickly retrieved by using the search engine server.
S103, consuming the message queue through a resolution server, resolving picture information of the consumed small picture data, and storing each resolved picture information into a database, wherein the picture information comprises attributes and characteristic values of pictures.
Specifically, the analysis server is composed of a plurality of neural network modules, and the neural network modules are used for realizing various image recognition functions. In this step, the parsing server consumes the message queue, acquires the thumbnail data therein, and parses the thumbnail information, using the neural network module capable of identifying the thumbnail information, where the consumption refers to an operation of acquiring and processing queue information in the message queue Pulsar, and the thumbnail information includes attributes of resolution, number of channels, and the like of the thumbnail data, and characteristic values of a figure or a vehicle picture type, a figure or a vehicle picture, and the like in the picture, and then stores the thumbnail information in the database. Specifically, the database is implemented based on My SQL, which is a commonly used database building and management software platform, the My SQL used in the embodiment of the present invention uses the thumbnail data as a main attribute of the database, and the picture information is written as an additional attribute of the thumbnail data when written into the database.
S104, recognizing human faces, human shapes and vehicles of the small image data in the message queue through the analysis server, and storing recognized human face pictures and/or human shape pictures and/or vehicle pictures into the database.
In this step, the parsing server performs face, human shape and vehicle recognition on the thumbnail data in the message queue, uses the neural network module capable of recognizing whether a target object of a face, a human shape and a vehicle exists in an object picture, and classifies the target object according to the categories of the face, the human shape and the vehicle, performs face, human shape and vehicle recognition on the thumbnail data through the neural network module to obtain a face picture, a human shape picture and a vehicle picture, and stores the face picture, the human shape picture and the vehicle picture in the database as new entries of the main attributes of the database.
And S105, performing behavior recognition on the face picture through the analysis server, and storing the recognized face behavior data into the database.
In this step, the parsing server performs behavior recognition on the face picture in step S104, uses the neural network module capable of recognizing whether the corresponding face target in the face picture has smoking behavior, performs smoking tagging on the face target having smoking behavior, obtains face behavior data corresponding to the smoking tagging and the corresponding face picture in a picture additional attribute form, and stores the face behavior data in the database in a field form as the additional attribute of the face picture.
S106, the small image data in the message queue is analyzed through the analysis server, the pictures in the small image data are marked with early warning information according to a preset rule, and the early warning information is stored in the database.
The analysis server analyzes the small pictures in the message queue and acquires early warning information in the small picture data, specifically, the analysis server analyzes the pictures in the small picture data by using a trained early warning information identification model and acquires the early warning information therein, the early warning information can identify that the early warning information exists in the small picture data according to picture characteristics used by the early warning information identification model in a training stage and by combining the analyzed face picture, the human figure picture and the vehicle picture, and specifically, the preset early warning information identified by the analysis server in the embodiment of the invention comprises messy objects, smoke and fire in the pictures, and information of whether fence invasion, abnormal invasion, prevention and control personnel, prevention and control vehicles and the like exist, and if any one of the early warning information in the pictures in the small picture data can be identified by the analysis server And if so, the analysis server takes the early warning information as an additional attribute of the small graph data and stores the additional attribute into the database in a field mode.
S107, reading the search engine server and the database through an application server, sending the pictures meeting preset requirements to a front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
The application server is configured to implement data communication with the front end, and read contents of the search engine server and the database to obtain a picture displayed in the front end according to a preset requirement, specifically, the preset requirement in the embodiment of the present invention is that all the large image data and the small image data stored in the search engine server, and the face picture, the human figure picture, the vehicle picture and the face behavior data, which are obtained by storing the corresponding small image data in the database, are read, and the warning information is displayed at a corresponding position of the front end, where the pictures and the information are displayed to a user in a visual manner.
Preferably, the front end still includes and searches for the picture module with the picture and patrols more card module, through with the picture search module be in search engine server can in according to big picture data is to including the same content little picture data search, it can according to patrolling more card module can according to the people's face picture is according to preset route of checking the card and time of checking the card, to the target that the people's face picture corresponds marks of checking the card, and can through the people's face picture with associative relation between people's face and the human shape reaches and retrieves corresponding with the mode retrieval human shape the effect of people's face picture to realize the personnel management in garden.
The method and the system have the advantages that the park management system is constructed by adopting the storage design of load balance and the message queue based on Pulsar, so that the operation efficiency of the management system can be improved, and the rapid management of personnel and early warning events in the park can be realized.
Referring to fig. 2, fig. 2 is a block diagram of a structure of a campus management system 200 according to the present invention, where the campus management system 200 includes a data acquisition module 201, a data receiving module 202, a picture information analysis module 203, a picture category analysis module 204, a behavior analysis module 205, an early warning information analysis module 206, and an application service module 207, where:
the data acquisition module 201 is configured to control a video acquisition unit to acquire large graph data and small graph data in real time, and send the large graph data and the small graph data to a data receiving server in a load balancing cluster manner; the small image data is obtained by amplifying and/or cutting the large image data;
a data receiving module 202, configured to control the data receiving server to send the big image data and the small image data to a search engine server, and send the small image data to a message queue;
the picture information analysis module 203 is used for controlling an analysis server to consume the message queue, analyzing the picture information of the consumed small picture data, and storing each analyzed picture information into a database, wherein the picture information comprises the attribute and the characteristic value of a picture;
the image type analysis module 204 is used for controlling the analysis server to identify faces, human shapes and vehicles of the small image data in the message queue, and storing the identified face images and/or human shape images and/or vehicle images into the database;
a behavior analysis module 205, configured to control performing behavior identification on the face picture through the analysis server, and store the identified face behavior data in the database;
the early warning information analysis module 206 is configured to control the analysis server to analyze the thumbnail data in the message queue, mark early warning information on a picture in the thumbnail data according to a preset rule, and store the early warning information in the database;
and the application service module 207 is used for controlling an application server to read the search engine server and the database, sending the pictures meeting the preset requirements to the front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
The campus management system 200 can implement the steps in the video capture-based campus management method in the above embodiment, and can implement the same technical effects, which are not described herein again with reference to the description in the above embodiment.
Referring to fig. 3, fig. 3 is a schematic structural diagram of a computer device 300 according to an embodiment of the present invention, where the computer device 300 includes: a memory 302, a processor 301, and a computer program stored on the memory 302 and executable on the processor 301.
The processor 301 calls the computer program stored in the memory 302 to execute the steps of the method for managing a campus based on video capture according to the embodiment of the present invention, and with reference to fig. 1, the method specifically includes:
s101, acquiring large graph data and small graph data in real time through a video acquisition unit, and sending the large graph data and the small graph data to a data receiving server in a load balancing cluster mode; and the small image data is obtained by amplifying and/or cutting the large image data.
Further, the load balancing clustering manner is based on miniO.
S102, the data receiving server sends the big image data and the small image data to a search engine server, and meanwhile, the small image data is sent to a message queue.
S103, consuming the message queue through a resolution server, resolving picture information of the consumed small picture data, and storing each resolved picture information into a database, wherein the picture information comprises attributes and characteristic values of pictures.
Further, the step of consuming the message queue by the parsing server, parsing the picture information of the consumed thumbnail data, and storing each parsed picture information in the database, wherein the picture information includes attributes and feature values of pictures, specifically includes:
the analysis server consumes the small graph data in the message queue according to the sequence of the message queue, performs feature detection on each small graph data by using a trained feature detection network to obtain the picture information of each small graph data, wherein the picture information comprises the attribute and the feature value of a picture, and then stores the picture information into the database.
Still further, the database is based on My SQL.
S104, recognizing human faces, human shapes and vehicles of the small image data in the message queue through the analysis server, and storing recognized human face pictures and/or human shape pictures and/or vehicle pictures into the database.
Further, the step of recognizing the human face, the human figure and the vehicle of the small image data in the data receiving server through the analysis server and storing the recognized human face picture and/or the human figure picture and/or the vehicle picture into the database specifically comprises the following steps:
and the analysis server respectively identifies the human face, the human shape and the vehicle of the small image data by using a trained target detection network, and stores the identified human face image, the human shape image and the vehicle image into the database.
And S105, performing behavior recognition on the face picture through the analysis server, and storing the recognized face behavior data into the database.
Furthermore, the step of performing behavior recognition on the face picture through the analysis server and storing the recognized face behavior data into the database specifically includes:
and the analysis server performs behavior detection on the face picture by using a trained behavior detection network, and stores the recognized face behavior as the additional attribute of the face picture into the database.
S106, analyzing the small graph data in the message queue through the analysis server, marking the early warning information on the pictures in the small graph data according to a preset rule, and storing the early warning information into the database.
Furthermore, the step of analyzing the small graph data in the data receiving server by the analysis server, marking the early warning information on the picture in the small graph data according to a preset rule, and storing the early warning information in a database, wherein the preset rule is as follows:
and if any one of preset early warning features exists in the small graph data, marking the early warning features according to types.
S107, reading the search engine server and the database through an application server, sending the pictures meeting preset requirements to a front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
The computer device 300 according to the embodiment of the present invention can implement the steps in the video capture-based campus management method according to the above embodiment, and can achieve the same technical effects, and reference is made to the description in the above embodiment, which is not described herein again.
The embodiment of the present invention further provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the computer program implements each process and step in the video acquisition-based campus management method provided in the embodiment of the present invention, and can implement the same technical effects, and in order to avoid repetition, the details are not repeated here.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which is stored in a storage medium (such as ROM/RAM, magnetic disk, optical disk) and includes instructions for enabling a terminal (such as a mobile phone, a computer, a server, an air conditioner, or a network device) to execute the method according to the embodiments of the present invention.
While the present invention has been described with reference to the preferred embodiments, it is to be understood that the invention is not limited to the disclosed embodiments, which are illustrative, but not restrictive, and that various changes may be made therein by those skilled in the art without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (10)
1. A campus management method based on video capture, the method comprising:
acquiring large graph data and small graph data in real time through a video acquisition unit, and sending the large graph data and the small graph data to a data receiving server in a load balancing cluster mode; the small image data is obtained by amplifying and/or cutting the large image data;
the data receiving server sends the big image data and the small image data to a search engine server, and simultaneously sends the small image data to a message queue;
consuming the message queue through a resolution server, resolving picture information of the consumed small picture data, and storing each resolved picture information into a database, wherein the picture information comprises attributes and characteristic values of pictures;
carrying out face, human shape and vehicle identification on the small image data in the message queue through the analysis server, and storing the identified face picture and/or human shape picture and/or vehicle picture into the database;
performing behavior recognition on the face picture through the analysis server, and storing recognized face behavior data into the database;
analyzing the small graph data in the message queue through the analysis server, marking early warning information on pictures in the small graph data according to a preset rule, and storing the early warning information into the database;
and reading the search engine server and the database through an application server, sending the pictures meeting the preset requirements to a front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
2. The method for campus management based on video acquisition of claim 1 wherein said load balancing clustering approach is based on minIO.
3. The campus management method based on video capture as claimed in claim 1, wherein said step of consuming said message queue by a parsing server, parsing picture information of said consumed thumbnail data, and storing each parsed picture information in a database, wherein said picture information includes attributes and feature values of pictures, specifically:
the analysis server consumes the small graph data in the message queue according to the sequence of the message queue, performs feature detection on each small graph data by using a trained feature detection network to obtain the picture information of each small graph data, wherein the picture information comprises the attribute and the feature value of a picture, and then stores the picture information into the database.
4. The method for video capture based campus management of claim 3 wherein said database is based on My SQL.
5. The campus management method based on video collection as claimed in claim 4 wherein, said step of performing face, human figure and vehicle recognition on said small graph data in said data receiving server through said parsing server, and storing the recognized face picture and/or human figure picture and/or vehicle picture in said database specifically comprises:
and the analysis server respectively identifies the human face, the human shape and the vehicle of the small image data by using a trained target detection network, and stores the identified human face picture, the human shape picture and the vehicle picture into the database.
6. The campus management method based on video capture as claimed in claim 5 wherein said step of performing behavior recognition on said human face picture by said parsing server and storing the recognized human face behavior data in said database comprises:
and the analysis server performs behavior detection on the face image by using a trained behavior detection network, and stores the recognized face behavior data as the additional attribute of the face image into the database.
7. The campus management method based on video collection as claimed in claim 6, wherein in the step of parsing the thumbnail data in the data receiving server by the parsing server, marking the pre-warning information of the pictures in the thumbnail data according to a preset rule, and storing the pre-warning information in a database, the preset rule is:
and if any one of preset early warning features exists in the pictures in the small picture data, marking the early warning features according to types.
8. A park management system, comprising:
the data acquisition module is used for controlling the video acquisition unit to acquire large graph data and small graph data in real time and sending the large graph data and the small graph data to the data receiving server in a load balancing cluster mode; the small image data is obtained by amplifying and/or cutting the large image data;
the data receiving module is used for controlling the data receiving server to send the big image data and the small image data to a search engine server and simultaneously send the small image data to a message queue;
the picture information analysis module is used for controlling an analysis server to consume the message queue, analyzing the picture information of the consumed small picture data and storing each analyzed picture information into a database, wherein the picture information comprises the attribute and the characteristic value of a picture;
the image category analysis module is used for controlling the analysis server to identify faces, human shapes and vehicles of the small image data in the message queue and store the identified face images and/or human shape images and/or vehicle images into the database;
the behavior analysis module is used for controlling the analysis server to perform behavior identification on the face picture and storing the identified picture face behavior data into the database;
the early warning information analysis module is used for controlling the analysis server to analyze the small image data in the message queue, marking early warning information on the image in the small image data according to a preset rule, and storing the early warning information into the database;
and the application service module is used for controlling an application server to read the search engine server and the database, sending the pictures meeting the preset requirements to the front end and displaying the pictures, and providing a function of searching the small picture data by using the large picture data through the search engine server.
9. A computer device, comprising: memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of the video capture based campus management method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, having stored thereon a computer program which, when being executed by a processor, carries out the steps of the method for video-capture-based campus management of any one of claims 1 to 7.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111316733.2A CN114201640A (en) | 2021-11-08 | 2021-11-08 | Garden management method and system based on video acquisition and related equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111316733.2A CN114201640A (en) | 2021-11-08 | 2021-11-08 | Garden management method and system based on video acquisition and related equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114201640A true CN114201640A (en) | 2022-03-18 |
Family
ID=80647102
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111316733.2A Pending CN114201640A (en) | 2021-11-08 | 2021-11-08 | Garden management method and system based on video acquisition and related equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114201640A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114419522A (en) * | 2022-03-29 | 2022-04-29 | 以萨技术股份有限公司 | Target object structured analysis method, device and equipment |
CN115118754A (en) * | 2022-08-29 | 2022-09-27 | 中国汽车技术研究中心有限公司 | Remote monitoring test system and monitoring test method for electric vehicle |
-
2021
- 2021-11-08 CN CN202111316733.2A patent/CN114201640A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114419522A (en) * | 2022-03-29 | 2022-04-29 | 以萨技术股份有限公司 | Target object structured analysis method, device and equipment |
CN115118754A (en) * | 2022-08-29 | 2022-09-27 | 中国汽车技术研究中心有限公司 | Remote monitoring test system and monitoring test method for electric vehicle |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210191979A1 (en) | Distributed video storage and search with edge computing | |
US20220092881A1 (en) | Method and apparatus for behavior analysis, electronic apparatus, storage medium, and computer program | |
CN108197565A (en) | Target based on recognition of face seeks track method and system | |
CN114201640A (en) | Garden management method and system based on video acquisition and related equipment | |
US20210357624A1 (en) | Information processing method and device, and storage medium | |
CN110619277A (en) | Multi-community intelligent deployment and control method and system | |
CN111930868A (en) | Big data behavior trajectory analysis method based on multi-dimensional data acquisition | |
CN111241305A (en) | Data processing method and device, electronic equipment and computer readable storage medium | |
WO2021114985A1 (en) | Companionship object identification method and apparatus, server and system | |
KR102296274B1 (en) | Method for providing object recognition with deep learning using fine tuning by user | |
CN111222373A (en) | Personnel behavior analysis method and device and electronic equipment | |
CN109766821A (en) | Vehicle driving law analytical method, system, computer equipment and storage medium | |
CN112001443A (en) | Network behavior data monitoring method and device, storage medium and electronic equipment | |
CN113971821A (en) | Driver information determination method and device, terminal device and storage medium | |
CN116483810A (en) | Data management method based on public security big data processing technical guidelines | |
CN111666263A (en) | Method for realizing heterogeneous data management in data lake environment | |
CN110443187A (en) | The recording method of characteristic information and device | |
CN111159190A (en) | Campus risk analysis system and method based on cloud platform | |
CN113128294B (en) | Road event evidence obtaining method and device, electronic equipment and storage medium | |
CN114863364A (en) | Security detection method and system based on intelligent video monitoring | |
WO2021102760A1 (en) | Method and apparatus for analyzing behavior of person, and electronic device | |
CN113591620A (en) | Early warning method, device and system based on integrated mobile acquisition equipment | |
CN113012006A (en) | Intelligent investigation and research method, system, computer equipment and storage medium | |
CN118097198B (en) | Automatic dressing compliance management and control system and method based on artificial intelligence | |
WO2023281897A1 (en) | Video surveillance system and video surveillance method |
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 |