CN114884842A - Visual security detection system and method for dynamically configuring tasks - Google Patents
Visual security detection system and method for dynamically configuring tasks Download PDFInfo
- Publication number
- CN114884842A CN114884842A CN202210385834.3A CN202210385834A CN114884842A CN 114884842 A CN114884842 A CN 114884842A CN 202210385834 A CN202210385834 A CN 202210385834A CN 114884842 A CN114884842 A CN 114884842A
- Authority
- CN
- China
- Prior art keywords
- detection
- detection algorithm
- module
- visual
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L43/00—Arrangements for monitoring or testing data switching networks
- H04L43/08—Monitoring or testing based on specific metrics, e.g. QoS, energy consumption or environmental parameters
- H04L43/0876—Network utilisation, e.g. volume of load or congestion level
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L47/00—Traffic control in data switching networks
- H04L47/10—Flow control; Congestion control
- H04L47/12—Avoiding congestion; Recovering from congestion
- H04L47/125—Avoiding congestion; Recovering from congestion by balancing the load, e.g. traffic engineering
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/10—Protocols in which an application is distributed across nodes in the network
- H04L67/1001—Protocols in which an application is distributed across nodes in the network for accessing one among a plurality of replicated servers
- H04L67/1004—Server selection for load balancing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Environmental & Geological Engineering (AREA)
- Alarm Systems (AREA)
Abstract
The invention provides a visual security detection system and a visual security detection method for dynamically configuring tasks, wherein the visual security detection system comprises the following steps: the visual detection system management module sends security detection visual detection system management configuration data to the user equipment management module and the server management module for system configuration management; the server management module issues algorithm data to the detection algorithm server; the user equipment management module manages equipment according to the equipment information; the visual detection scene configuration module performs correlation operation to acquire visual detection scene correlation information so as to acquire visual detection scene task data; and the system central control operation module captures the equipment and visual scene task data, the detection algorithm server processes the equipment and visual scene task data to obtain a detection algorithm return result, and the detection algorithm return result is filtered to obtain alarm information. The invention has the following advantages: by binding the detection algorithm in the detection algorithm server, the load balance of detection algorithm scheduling is automatically realized, parallel and rapid deployment of multiple projects is supported, and the product quality is ensured.
Description
Technical Field
The invention relates to a visual identification technology, in particular to a visual security detection method and a system for dynamically configuring tasks, which abstract, unify technical architecture and template development process on an industrial visual detection scene and respond to future customer items in a configuration mode.
Background
With the development of artificial intelligence technology, machine vision software and hardware products have been gradually applied to various production and manufacturing links. A set of machine vision recognition platform and an analysis application system are proposed and established in an industrial field, real-time detection and alarming are realized in key areas for detecting unsafe behaviors of people and unsafe states of objects, the aspects of safety helmets, safety ropes, dust emission, smoking, code spraying and the like are mainly included, machine vision is used for replacing artificial vision, working efficiency is improved, and safety management level is enhanced.
The invention patent with application number 202010298529.1, namely 'an automatic integrated construction development deployment platform and method', comprises an interface setting module, a version controller management module, an integrated construction management module, a deployment management module and a project integrated construction management module; various version controllers are connected with the version controller management module, various compilers are connected with the integrated construction management module, and various deployment servers and containers can be connected with the deployment management module by smartly using the universality of ssh instructions. The project integration construction management module schedules, integrates and constructs related instructions at regular time, and realizes automatic source code downloading, automatic compiling, automatic packing and automatic deployment. In the development process of the prior art, due to the fact that technical routes of different teams or personnel are inconsistent, each new project is accessed, the new project needs to be evaluated, designed, developed, tested and deployed from beginning, the delivery time is long, and the quality cannot be well guaranteed; the deployment of each new project needs developers to be completed in person, the deployment cost is high, and the situation of shortage of development manpower is easily caused; the delivery deadline can not be guaranteed when multiple projects are parallel, and the image of an enterprise is adversely affected; research personnel do too much repeated work, which is not beneficial to improving technical capability and carrying out innovative thinking; it is difficult to produce standardized products.
Disclosure of Invention
The invention aims to solve the technical problem of providing a visual security detection method capable of solving the dynamic configuration task of the technical problems in the prior art that the project research and development repetitive work is too much, the developed visual detection system is low in efficiency and the like.
The invention solves the technical problems through the following technical means: a visual security detection system for dynamically configuring tasks is applied to machine vision monitoring, and the system comprises: a visual detection system management module, a server management module, a user equipment management module, a visual detection scene configuration module and a system central control operation module,
the visual detection system management module is used for acquiring and sending security detection visual detection system management configuration data to the user equipment management module and the server management module for system configuration management;
the server management module is used for acquiring detection algorithm input and output logic parameters and detection algorithm server information from the security detection visual detection system management configuration data, and distributing the detection algorithm input and output logic parameters to the detection algorithm server by using the detection algorithm server information, and the server management module is connected with the visual detection system management module;
the user equipment management module is used for acquiring and storing equipment information from the management configuration data of the security detection visual detection system, and managing equipment according to the equipment information, wherein the user equipment management module is connected with the visual detection system management module;
the visual detection scene configuration module is used for acquiring visual detection scene data, performing association operation on a detection algorithm, the equipment and the visual detection scene data according to the visual detection scene data, the detection algorithm input and output logic parameters and the equipment information, acquiring visual detection scene association information according to the visual detection scene data, and processing the visual detection scene association information to acquire visual detection scene task data;
the system central control operation module is used for capturing equipment detection data and the visual detection scene task data according to the visual detection scene task data, sending the equipment detection data to the detection algorithm server for processing to obtain a detection algorithm return result, filtering the detection algorithm return result according to the visual detection scene task data, and accordingly acquiring and storing warning information. Based on the existing project and the future expected project, the industrial visual detection scene is abstracted, the technical architecture is unified, and the development process is templated. Visualization system device configuration: the number of the detection algorithm servers can be configured according to actual traffic, and load balance of detection algorithm scheduling is automatically realized in a mode of binding detection algorithms in the detection algorithm servers.
In a more specific aspect, the visual inspection system management module includes: a user management module, an alarm management module, a detection algorithm management module and a page configuration module,
the user management module is used for storing and managing user configuration information;
the alarm management module is used for acquiring and outputting alarm data;
the detection algorithm management module is used for storing and managing detection algorithm configuration data;
the page configuration module is used for configuring the page state of the system display end.
In a more specific technical solution, the server management module includes: a detection algorithm establishing module, a detection algorithm server module and a detection algorithm deployment module,
the detection algorithm establishing module is used for setting the input and output parameters of the detection algorithm, a detection algorithm deep learning model and detection algorithm internal logic data; the defining operation of the detection algorithm is set by a user at the front end and is stored in a database through the rear end;
the detection algorithm server module is used for adding a server IP and a port number for operating the detection algorithm into the visual security detection system of the dynamic configuration task so as to acquire the connection state of the server in real time;
and the detection algorithm deployment module is used for adding the server as the detection algorithm server so as to deploy the input and output parameters of the detection algorithm, the deep learning model of the detection algorithm and the internal logic data of the detection algorithm to the server. The files required by the detection algorithm are sent to the server, and the detection algorithm management program is responsible for receiving, analyzing and decompressing the files to form a dependent file packet required by the start of the detection algorithm service. The future customer projects are responded through a configuration mode, and the aim of ensuring the product quality while supporting the parallel and rapid deployment of multiple projects with minimized manpower is achieved.
In a more specific technical solution, the detection algorithm establishing module includes: a front-end detection algorithm setting module, a detection algorithm data storage module,
the front-end detection algorithm setting module is used for setting the input and output parameters of the detection algorithm, the detection algorithm deep learning model and the detection algorithm internal logic data at the front end;
and the detection algorithm data storage module is used for storing the input and output parameters, the detection algorithm deep learning model and the detection algorithm internal logic data in a database through a back-end memory. And (3) visualization system workflow configuration: the invention can self-define the detection algorithm according to the requirement, and realize the expansion capability of the detection algorithm under the detection task by specifying the detection algorithm model, the detection algorithm input and output data and the detection algorithm logic script.
In a more specific technical solution, the detection algorithm server module includes:
the detection algorithm server front-end configuration module is used for adding and configuring the detection algorithm server at the front end;
the server information storage module is used for storing the server information into a database through a back-end memory;
the detection algorithm server state back-end query module is used for regularly querying the connection state of the detection algorithm server at the back end;
and the detection algorithm heartbeat monitoring module is used for receiving the connection state, returning the connection state to the rear end and displaying the connection state at the front end.
In a more specific technical solution, the detection algorithm deployment module includes: a detection algorithm file issuing module, a dependent packet module and a detection algorithm service module,
the detection algorithm file issuing module is used for issuing a detection algorithm file to the detection algorithm server;
the dependent package module is used for receiving and decompressing the detection algorithm file by using a detection algorithm management program so as to obtain a dependent file package;
and the detection algorithm service module is used for starting detection algorithm service according to the dependent file packet.
In a more specific technical solution, the detection algorithm service initiation module includes: a front-end start command module and a back-end start request module,
the front end starting command module is used for executing a starting command at the front end;
and the rear-end starting request module is used for sending the passing request of the starting command to the central control service program at the rear end, the central control service program forwards the passing request to the detection algorithm management program, and the detection algorithm management program starts corresponding detection algorithm service in a container starting mode according to the received request instruction.
In a more specific technical solution, the visual inspection scene configuration module includes:
the input/output extraction module is used for extracting detection algorithm input parameters from the detection algorithm input/output logic parameters and extracting equipment output data from the equipment information;
the input and output association module is used for associating the detection algorithm input parameters with the equipment output data so as to acquire the visual detection scene association information;
and the detection algorithm detection processing module is used for acquiring data from the equipment by using a detection algorithm according to the visual detection scene correlation information so as to carry out detection and logical reasoning. The visual self-defined visual detection scene configuration can detect the binding association of the algorithm and the equipment in the visual detection scene according to the detection algorithm and the equipment added into the system, so that the equipment has the current binding detection algorithm capability.
In a more specific technical solution, the system central control operation module further includes:
the central control service module is used for capturing data from equipment, sending the data to the detection algorithm service module, processing the data to obtain detection result data and returning the detection result data to the central control service module;
the central control result filtering module is used for filtering the detection result data according to the current visual detection scene associated data so as to obtain a filtering detection alarm result and returning the filtering detection alarm result to the background;
and the management background module is used for storing and sending the filtering detection alarm result to the front end and displaying the filtering detection alarm result.
In a more specific technical scheme, a visual security detection method for dynamically configuring tasks is characterized by comprising the following steps:
acquiring and sending security detection visual detection system management configuration data to the user equipment management module and the server management module for system configuration management;
acquiring detection algorithm input and output logic parameters and detection algorithm server information from the security detection visual detection system management configuration data, and issuing and deploying the detection algorithm input and output logic parameters to a detection algorithm server by using the detection algorithm server information, wherein the server management module is connected with the visual detection system management module;
acquiring and storing equipment information from the security detection visual detection system management configuration data, and managing equipment according to the equipment information, wherein the user equipment management module is connected with the visual detection system management module;
acquiring visual detection scene data, and performing association operation on a detection algorithm, the equipment and the visual detection scene data according to the visual detection scene data, the detection algorithm input/output logic parameters and the equipment information to acquire visual detection scene associated information, and processing the visual detection scene associated information to acquire visual detection scene task data;
capturing equipment detection data and the visual detection scene task data according to the visual detection scene task data, sending the equipment detection data to the detection algorithm server for processing to obtain a detection algorithm return result, and filtering the detection algorithm return result according to the visual detection scene task data. Accordingly, the alarm information is obtained and stored.
Compared with the prior art, the invention has the following advantages:
the invention abstracts the industrial visual detection scene, unifies the technical architecture and templates the development process based on the existing project and the future expected project. Visualization system device configuration: the number of the detection algorithm servers can be configured according to actual traffic, and load balance of detection algorithm scheduling is automatically realized in a mode of binding detection algorithms in the detection algorithm servers. The files required by the detection algorithm are sent to the server, and the detection algorithm management program is responsible for receiving, analyzing and decompressing the files to form a dependent file packet required by the start of the detection algorithm service. The future customer projects are responded through a configuration mode, and the aim of ensuring the product quality while supporting the parallel and rapid deployment of multiple projects with minimized manpower is achieved. The invention can self-define the detection algorithm according to the requirement, and realize the expansion capability of the detection algorithm under the detection task by specifying the detection algorithm model, the detection algorithm input and output data and the detection algorithm logic script. The visual self-defined visual detection scene configuration can detect the binding association of the algorithm and the equipment in the visual detection scene according to the detection algorithm and the equipment added into the system, so that the equipment has the current binding detection algorithm capability.
Drawings
FIG. 1 is a schematic view of a detection algorithm set-up interface;
FIG. 2 is a schematic diagram of a detection algorithm server add interface;
FIG. 3 is a schematic view of a detection algorithm file delivery interface;
FIG. 4 is a schematic view of a detection algorithm service initiation interface;
FIG. 5 is a schematic view of a visual inspection scene creation interface;
FIG. 6 is a schematic diagram of a detection algorithm service body;
fig. 7 is a schematic diagram of data interaction in system operation processing.
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 embodiments of the present invention, and it is obvious that the described embodiments are some embodiments of the present invention, but not all embodiments. 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.
Example (b):
the system mainly comprises 5 modules which are respectively as follows:
1. visual inspection system management module: user management, alarm management, detection algorithm management and page configuration
2. A device management module: CRUD operation for devices
3. A server management module: the server adds CRUD for modifying and monitoring state, server and detection algorithm, and controls the start and stop of detection algorithm
4. Visual inspection scene configuration module: configuring a service visual detection scene, and binding a detection algorithm and equipment in the visual detection scene
5. A system operation module: camera real-time video streaming, alarm information push, operation log and resource supervision.
The invention is based on a business visual detection scene, dynamically configures a detection algorithm task, and equipment can realize data push according to a bound detection algorithm, and the specific functions and the flow are as follows:
1. establishing a detection algorithm
As shown in FIG. 1, the platform may define a detection algorithm, including input parameters, output parameters defining the detection algorithm, a deep learning model used by the detection algorithm, and processing logic within the detection algorithm. The defining operation of the detection algorithm is set by the user at the front end and is stored in the database through the back end.
2. Add detection algorithm server
As shown in fig. 2, the connection status of the server can be obtained in real time by adding the IP and port number of the server running the detection algorithm to the system. The addition of the server is configured by the user at the front end and is stored in the database through the back end; the back end can inquire the connection state of the server at regular time, the inquiry is transmitted through the central control system, and the inquiry is returned to the back end and displayed at the front end after being responded by the detection algorithm management module. And finally realizing the heartbeat monitoring of the detection algorithm server.
3. Deployment and start detection algorithm
With the addition of a detection algorithm server, as shown in fig. 3, a specified detection algorithm may be deployed to the server. The files required by the detection algorithm are sent to the server, and the detection algorithm management program is responsible for receiving, analyzing and decompressing the files to form a dependent file packet required by the start of the detection algorithm service.
As shown in fig. 4, the detection algorithm starts: the user executes a start command at the front end, the back end sends the start command to the central control service program through a request, the central control service program forwards the start command to the detection algorithm management program, and the detection algorithm management program starts corresponding detection algorithm service in a container starting mode according to the received request command.
4. Adding device
A user can fill and submit necessary equipment information through the operation of a front-end interface, and the back end records and puts in storage the equipment information to realize the adding action of the equipment.
5. Establishing a visual inspection scene
As shown in fig. 5, after the detection algorithm is established and the device is added, before the system runs, the input parameters of the detection algorithm need to be associated with the output data of the device, so that the detection algorithm can acquire data from the device for detection and logical inference. The step is completed by the operation of a user at the front end, visual detection scene information, a detection algorithm and equipment association relation are stored in a database by the rear end, and are simultaneously sent to a central control service module, and the data capture function of the equipment is realized by the central control service module.
6. Operation of the system
As shown in fig. 6 and 7, after the visual detection scene task is established, the corresponding task can be started, after the task is started, the central control service module starts to capture data from the equipment and sends the data to the detection algorithm service module, the detection algorithm service module performs logical reasoning and returns the result to the central control service module, and the central control service module performs certain filtering on the detection algorithm return result according to the alarm strategy associated with the current detection algorithm, returns the result to the management background, and performs alarm display through the front end. And the management background is responsible for storing and managing the alarm records.
Compared with the prior art, the visual security detection method and the system for dynamically configuring the tasks have the following beneficial effects that: the invention abstracts the industrial visual detection scene, unifies the technical architecture and templates the development process based on the existing project and the future expected project. Visualization system device configuration: the number of the detection algorithm servers can be configured according to actual traffic, and load balance of detection algorithm scheduling is automatically realized in a mode of binding detection algorithms in the detection algorithm servers. The files required by the detection algorithm are sent to the server, and the detection algorithm management program is responsible for receiving, analyzing and decompressing the files to form a dependent file packet required by the start of the detection algorithm service. The future customer projects are responded through a configuration mode, and the aim of ensuring the product quality while supporting the parallel and rapid deployment of multiple projects with minimized manpower is achieved. The invention can self-define the detection algorithm according to the requirement, and realize the expansion capability of the detection algorithm under the detection task by specifying the detection algorithm model, the detection algorithm input and output data and the detection algorithm logic script. The visual self-defined visual detection scene configuration can detect the binding association of the algorithm and the equipment in the visual detection scene according to the detection algorithm and the equipment added into the system, so that the equipment has the current binding detection algorithm capability.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A visual security detection system for dynamically configuring tasks is applied to machine vision monitoring, and the system comprises: a visual detection system management module, a server management module, a user equipment management module, a visual detection scene configuration module and a system central control operation module,
the visual detection system management module is used for acquiring and sending security detection visual detection system management configuration data to the user equipment management module and the server management module for system configuration management;
the server management module is used for acquiring detection algorithm input and output logic parameters and detection algorithm server information from the security detection visual detection system management configuration data, and distributing the detection algorithm input and output logic parameters to the detection algorithm server by using the detection algorithm server information, and the server management module is connected with the visual detection system management module;
the user equipment management module is used for acquiring and storing equipment information from the management configuration data of the security detection visual detection system, and managing equipment according to the equipment information, wherein the user equipment management module is connected with the visual detection system management module;
the visual detection scene configuration module is used for acquiring visual detection scene data, performing association operation on a detection algorithm, the equipment and the visual detection scene data according to the visual detection scene data, the detection algorithm input and output logic parameters and the equipment information, acquiring visual detection scene association information according to the visual detection scene data, and processing the visual detection scene association information to acquire visual detection scene task data;
the system central control operation module is used for capturing equipment detection data and the visual detection scene task data according to the visual detection scene task data, sending the equipment detection data to the detection algorithm server for processing to obtain a detection algorithm return result, filtering the detection algorithm return result according to the visual detection scene task data, and accordingly acquiring and storing warning information.
2. The visual security detection system for dynamically configuring tasks according to claim 1, wherein the visual detection system management module comprises: a user management module, an alarm management module, a detection algorithm management module and a page configuration module,
the user management module is used for storing and managing user configuration information;
the alarm management module is used for acquiring and outputting alarm data;
the detection algorithm management module is used for storing and managing detection algorithm configuration data;
the page configuration module is used for configuring the page state of the system display end.
3. The visual security detection system for dynamically configuring tasks according to claim 2, wherein the server management module comprises: a detection algorithm establishing module, a detection algorithm server module and a detection algorithm deployment module,
the detection algorithm establishing module is used for setting the input and output parameters of the detection algorithm, a detection algorithm deep learning model and detection algorithm internal logic data; the defining operation of the detection algorithm is set by a user at the front end and is stored in a database through the rear end;
the detection algorithm server module is used for adding the IP and the port number of the server running the detection algorithm into the visual security detection system of the dynamic configuration task so as to acquire the connection state of the server in real time. The addition of the server is configured by the user at the front end and is stored in the database through the back end; the back end can inquire the connection state of the server at regular time, the inquiry is transmitted through the central control system, and the inquiry is returned to the back end and displayed at the front end after being responded by the detection algorithm management module. Finally realizing heartbeat monitoring of the detection algorithm server;
and the detection algorithm deployment module is used for adding the server as the detection algorithm server so as to deploy the input and output parameters of the detection algorithm, the deep learning model of the detection algorithm and the internal logic data of the detection algorithm to the server. The files required by the detection algorithm are sent to the server, and the detection algorithm management program is responsible for receiving, analyzing and decompressing the files to form a dependent file packet required by the start of the detection algorithm service.
4. The visual security detection system for dynamically configuring tasks according to claim 3, wherein the detection algorithm establishing module comprises: a front-end detection algorithm setting module, a detection algorithm data storage module,
the front-end detection algorithm setting module is used for setting the input and output parameters of the detection algorithm, the detection algorithm deep learning model and the detection algorithm internal logic data at the front end;
and the detection algorithm data storage module is used for storing the input and output parameters, the detection algorithm deep learning model and the detection algorithm internal logic data in a database through a back-end memory.
5. The visual security detection system for dynamic configuration tasks according to claim 3, wherein the detection algorithm server module comprises:
the detection algorithm server front-end configuration module is used for adding and configuring the detection algorithm server at the front end;
the server information storage module is used for storing the server information into a database through a back-end memory;
the detection algorithm server state back-end query module is used for regularly querying the connection state of the detection algorithm server at the back end;
and the detection algorithm heartbeat monitoring module is used for receiving the connection state, returning the connection state to the rear end and displaying the connection state at the front end.
6. The visual security detection system for dynamic configuration tasks according to claim 5, wherein the detection algorithm deployment module comprises: a detection algorithm file issuing module, a dependent packet module and a detection algorithm service module,
the detection algorithm file issuing module is used for issuing a detection algorithm file to the detection algorithm server;
the dependent package module is used for receiving and decompressing the detection algorithm file by using a detection algorithm management program so as to obtain a dependent file package;
and the detection algorithm service module is used for starting detection algorithm service according to the dependent file packet.
7. The visual security detection system for dynamic configuration tasks according to claim 6, wherein the detection algorithm service initiation module comprises: a front-end start command module and a back-end start request module,
the front end starting command module is used for executing a starting command at the front end;
and the rear-end starting request module is used for sending the passing request of the starting command to the central control service program at the rear end, the central control service program forwards the passing request to the detection algorithm management program, and the detection algorithm management program starts corresponding detection algorithm service in a container starting mode according to the received request instruction.
8. The visual security detection system for dynamically configuring tasks according to claim 1, wherein the visual detection scene configuration module comprises:
the input/output extraction module is used for extracting detection algorithm input parameters from the detection algorithm input/output logic parameters and extracting equipment output data from the equipment information;
the input and output association module is used for associating the detection algorithm input parameters with the equipment output data so as to acquire the visual detection scene association information;
and the detection algorithm detection processing module is used for acquiring data from the equipment by using a detection algorithm according to the visual detection scene correlation information so as to carry out detection and logical reasoning.
9. The visual security detection system for dynamically configuring tasks according to claim 1, wherein the system central control operation module further comprises:
the central control service module is used for capturing data from equipment, sending the data to the detection algorithm service module, processing the data to obtain detection result data and returning the detection result data to the central control service module;
the central control result filtering module is used for filtering the detection result data according to the current visual detection scene associated data so as to obtain a filtering detection alarm result and returning the filtering detection alarm result to the background;
and the management background module is used for storing and sending the filtering detection alarm result to the front end and displaying the filtering detection alarm result.
10. A visual security detection method for dynamically configuring tasks is characterized by comprising the following steps:
acquiring and sending security detection visual detection system management configuration data to the user equipment management module and the server management module for system configuration management;
acquiring detection algorithm input and output logic parameters and detection algorithm server information from the security detection visual detection system management configuration data, and issuing and deploying the detection algorithm input and output logic parameters to a detection algorithm server by using the detection algorithm server information, wherein the server management module is connected with the visual detection system management module;
acquiring and storing equipment information from the security detection visual detection system management configuration data, and managing equipment according to the equipment information, wherein the user equipment management module is connected with the visual detection system management module;
acquiring visual detection scene data, and performing association operation on a detection algorithm, the equipment and the visual detection scene data according to the visual detection scene data, the detection algorithm input/output logic parameters and the equipment information to acquire visual detection scene associated information, and processing the visual detection scene associated information to acquire visual detection scene task data;
capturing equipment detection data and the visual detection scene task data according to the visual detection scene task data,
and sending the equipment detection data to the detection algorithm server for processing to obtain a detection algorithm return result, and filtering the detection algorithm return result according to the visual detection scene task data. Accordingly, the alarm information is obtained and stored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210385834.3A CN114884842B (en) | 2022-04-13 | 2022-04-13 | Visual security detection system and method for dynamic configuration task |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210385834.3A CN114884842B (en) | 2022-04-13 | 2022-04-13 | Visual security detection system and method for dynamic configuration task |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114884842A true CN114884842A (en) | 2022-08-09 |
| CN114884842B CN114884842B (en) | 2023-09-05 |
Family
ID=82669313
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210385834.3A Active CN114884842B (en) | 2022-04-13 | 2022-04-13 | Visual security detection system and method for dynamic configuration task |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114884842B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541911A (en) * | 2023-12-20 | 2024-02-09 | 烟台新韦达智慧科技有限公司 | Management server of cluster type AI detection equipment |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040030383A1 (en) * | 2002-06-06 | 2004-02-12 | Havey Gary David | Method and apparatus for sensory substitution, vision prosthesis, or low-vision enhancement utilizing thermal sensing |
| WO2006031988A2 (en) * | 2004-09-15 | 2006-03-23 | The Regents Of The University Of California | Privacy protection of data collection in pervasive environments |
| US20070011711A1 (en) * | 2005-06-24 | 2007-01-11 | Wayne Wolf | Method and apparatus for real-time distributed video analysis |
| US20090063431A1 (en) * | 2006-07-31 | 2009-03-05 | Berna Erol | Monitoring and analyzing creation and usage of visual content |
| US20100278420A1 (en) * | 2009-04-02 | 2010-11-04 | Siemens Corporation | Predicate Logic based Image Grammars for Complex Visual Pattern Recognition |
| US20140064578A1 (en) * | 2008-06-13 | 2014-03-06 | Raytheon Company | Visual detection system for identifying objects within a region of interest |
| US20160314351A1 (en) * | 2015-04-27 | 2016-10-27 | Xerox Corporation | Extending generic business process management with computer vision capabilities |
| US9526443B1 (en) * | 2013-01-19 | 2016-12-27 | Bertec Corporation | Force and/or motion measurement system and a method of testing a subject |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| US20190079536A1 (en) * | 2017-09-13 | 2019-03-14 | TuSimple | Training and testing of a neural network system for deep odometry assisted by static scene optical flow |
| CN110430260A (en) * | 2019-08-02 | 2019-11-08 | 哈工大机器人（合肥）国际创新研究院 | Robot cloud platform based on big data cloud computing support and working method |
| CN110443175A (en) * | 2019-07-29 | 2019-11-12 | 苏州维众数据技术有限公司 | Clean robot control system and control method based on separate type vision-based detection |
| US20200105111A1 (en) * | 2018-10-01 | 2020-04-02 | Digital Barriers Services Ltd | Video surveillance and object recognition |
| CN113065528A (en) * | 2021-05-08 | 2021-07-02 | 南京四维向量科技有限公司 | Embedded visual computing system for face recognition, counting and temperature measurement |
| CN113310897A (en) * | 2021-05-31 | 2021-08-27 | 广东骏亚电子科技股份有限公司 | AI visual inspection system application based on 5G algorithm |
| WO2021253961A1 (en) * | 2020-06-15 | 2021-12-23 | 北京世纪瑞尔技术股份有限公司 | Intelligent visual perception system |
| CN114005088A (en) * | 2021-11-03 | 2022-02-01 | 哈工大机器人（合肥）国际创新研究院 | Safety rope wearing state monitoring method and system |
-
2022
- 2022-04-13 CN CN202210385834.3A patent/CN114884842B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040030383A1 (en) * | 2002-06-06 | 2004-02-12 | Havey Gary David | Method and apparatus for sensory substitution, vision prosthesis, or low-vision enhancement utilizing thermal sensing |
| WO2006031988A2 (en) * | 2004-09-15 | 2006-03-23 | The Regents Of The University Of California | Privacy protection of data collection in pervasive environments |
| US20070011711A1 (en) * | 2005-06-24 | 2007-01-11 | Wayne Wolf | Method and apparatus for real-time distributed video analysis |
| US20090063431A1 (en) * | 2006-07-31 | 2009-03-05 | Berna Erol | Monitoring and analyzing creation and usage of visual content |
| US20140064578A1 (en) * | 2008-06-13 | 2014-03-06 | Raytheon Company | Visual detection system for identifying objects within a region of interest |
| US20100278420A1 (en) * | 2009-04-02 | 2010-11-04 | Siemens Corporation | Predicate Logic based Image Grammars for Complex Visual Pattern Recognition |
| US9526443B1 (en) * | 2013-01-19 | 2016-12-27 | Bertec Corporation | Force and/or motion measurement system and a method of testing a subject |
| US20160314351A1 (en) * | 2015-04-27 | 2016-10-27 | Xerox Corporation | Extending generic business process management with computer vision capabilities |
| US20190079536A1 (en) * | 2017-09-13 | 2019-03-14 | TuSimple | Training and testing of a neural network system for deep odometry assisted by static scene optical flow |
| CN108171748A (en) * | 2018-01-23 | 2018-06-15 | 哈工大机器人（合肥）国际创新研究院 | A kind of visual identity of object manipulator intelligent grabbing application and localization method |
| US20200105111A1 (en) * | 2018-10-01 | 2020-04-02 | Digital Barriers Services Ltd | Video surveillance and object recognition |
| CN110443175A (en) * | 2019-07-29 | 2019-11-12 | 苏州维众数据技术有限公司 | Clean robot control system and control method based on separate type vision-based detection |
| CN110430260A (en) * | 2019-08-02 | 2019-11-08 | 哈工大机器人（合肥）国际创新研究院 | Robot cloud platform based on big data cloud computing support and working method |
| WO2021253961A1 (en) * | 2020-06-15 | 2021-12-23 | 北京世纪瑞尔技术股份有限公司 | Intelligent visual perception system |
| CN113065528A (en) * | 2021-05-08 | 2021-07-02 | 南京四维向量科技有限公司 | Embedded visual computing system for face recognition, counting and temperature measurement |
| CN113310897A (en) * | 2021-05-31 | 2021-08-27 | 广东骏亚电子科技股份有限公司 | AI visual inspection system application based on 5G algorithm |
| CN114005088A (en) * | 2021-11-03 | 2022-02-01 | 哈工大机器人（合肥）国际创新研究院 | Safety rope wearing state monitoring method and system |
Non-Patent Citations (4)
| Title |
|---|
| BASTIAN HELLMANN 等: "Integrating visual analysis of network security and management of detection system configurations", 2017 9TH IEEE INTERNATIONAL CONFERENCE ON INTELLIGENT DATA ACQUISITION AND ADVANCED COMPUTING SYSTEMS: TECHNOLOGY AND APPLICATIONS (IDAACS) * |
| 王靖娜;: "一种基于机器视觉的铝管缺陷检测系统", 电子测试, no. 15 * |
| 裴善强: "大型锻件多目视觉测量识别系统研究", 硕士电子期刊 * |
| 郭晓丽;: "基于计算机视觉的目标检测和阴影检测算法的研究", 江西电力职业技术学院学报, no. 03 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117541911A (en) * | 2023-12-20 | 2024-02-09 | 烟台新韦达智慧科技有限公司 | Management server of cluster type AI detection equipment |
| CN117541911B (en) * | 2023-12-20 | 2024-05-17 | 烟台新韦达智慧科技有限公司 | Management server of cluster type AI detection equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114884842B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109684053B (en) | Task scheduling method and system for big data | |
| CN105653425B (en) | Monitoring system based on complex event processing engine | |
| CN106445817B (en) | Processing method, the device and system of test data | |
| US20120221279A1 (en) | Automatic Test System for Distributed Comprehensive Service and Method Thereof | |
| CN109634728A (en) | Job scheduling method, device, terminal device and readable storage medium storing program for executing | |
| CN110581773A (en) | automatic service monitoring and alarm management system | |
| CN104809030A (en) | Android-based exception handling system and method | |
| CN114884842A (en) | Visual security detection system and method for dynamically configuring tasks | |
| CN109144734A (en) | A kind of container resource quota distribution method and device | |
| CN107168844B (en) | Performance monitoring method and device | |
| WO2023004805A1 (en) | Workflow modeling implementation system and method, and storage medium | |
| CN109426597B (en) | Application performance monitoring method, device, equipment, system and storage medium | |
| CN113312165A (en) | Task processing method and device | |
| CN114090378A (en) | Custom monitoring and alarming method based on Kapacitor | |
| CN110968479B (en) | Service level full-link monitoring method and server for application program | |
| CN104486147A (en) | Method and device for updating monitoring data of equipment monitoring system | |
| CN112100239A (en) | Portrait generation method and apparatus for vehicle detection device, server and readable storage medium | |
| EP2908498B1 (en) | Integrated application generating system and method for internet of things terminal | |
| CN114968272A (en) | Algorithm operation method, device, equipment and storage medium | |
| CN111090558B (en) | Panel detection system | |
| CN113206867A (en) | Intelligent data acquisition monitoring system and method and timing acquisition service module | |
| CN115689277B (en) | Chemical industry garden risk early warning system under cloud edge cooperation technology | |
| CN111209007B (en) | Software implementation method for monitoring controllable equipment based on mobile environment | |
| CN116450305B (en) | SOAR platform assembly execution method and device based on distributed task scheduling | |
| CN117312101B (en) | Method and device for determining structure log, storage medium and electronic equipment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |