WO2024011926A1 - 基于5g的安防监控系统、方法、电子设备及存储介质 - Google Patents

基于5g的安防监控系统、方法、电子设备及存储介质 Download PDF

Info

Publication number
WO2024011926A1
WO2024011926A1 PCT/CN2023/080249 CN2023080249W WO2024011926A1 WO 2024011926 A1 WO2024011926 A1 WO 2024011926A1 CN 2023080249 W CN2023080249 W CN 2023080249W WO 2024011926 A1 WO2024011926 A1 WO 2024011926A1
Authority
WO
WIPO (PCT)
Prior art keywords
edge cloud
security monitoring
module
video stream
stream data
Prior art date
Application number
PCT/CN2023/080249
Other languages
English (en)
French (fr)
Inventor
刘鹏英
王勇
杜召娟
胡明臣
Original Assignee
卡奥斯工业智能研究院(青岛)有限公司
卡奥斯物联科技股份有限公司
海尔数字科技(青岛)有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 卡奥斯工业智能研究院(青岛)有限公司, 卡奥斯物联科技股份有限公司, 海尔数字科技(青岛)有限公司 filed Critical 卡奥斯工业智能研究院(青岛)有限公司
Publication of WO2024011926A1 publication Critical patent/WO2024011926A1/zh

Links

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
    • G08B13/00—Burglar, theft or intruder alarms
    • G08B13/18—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength
    • G08B13/189—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems
    • G08B13/194—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems
    • G08B13/196—Actuation by interference with heat, light, or radiation of shorter wavelength; Actuation by intruding sources of heat, light, or radiation of shorter wavelength using passive radiation detection systems using image scanning and comparing systems using television cameras
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
    • 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

Definitions

  • This application relates to the field of security technology, and in particular to a 5G-based security monitoring system, method, electronic device and storage medium.
  • the current common solution is to transfer the intelligent analysis module to the cloud for processing, transforming the video surveillance system from traditional civil air defense to intelligent. Specifically, it refers to connecting the video stream collected by the camera to the public network through wired/wireless connections, then transmitting the video stream to the cloud server for calculation, storage and analysis, and finally displaying the feedback results through terminal devices such as large screens.
  • the currently adopted intelligent monitoring solution has a long delay due to the long transmission path of the video stream, making some real-time video analysis functions lagging and meaningless.
  • some real-time video analysis functions lagging and meaningless.
  • factories, etc. Special application environments have high confidentiality requirements for video stream data.
  • the implementation of this solution requires connection to the public network, so it is not conducive to data protection. It can be seen that existing intelligent monitoring solutions have shortcomings such as lagging analysis functions and insufficient data confidentiality.
  • This application provides a 5G-based security monitoring system, method, electronic equipment and storage medium to solve the technical problems of lagging analysis functions and insufficient data confidentiality in existing industrial park intelligent monitoring solutions.
  • this application provides a 5G-based security monitoring system, including: collection terminal, 5G base station and edge cloud systems;
  • the collection terminal is communicatively connected to the 5G base station, and the collection terminal is used to collect video stream data in the target area;
  • the 5G base station is communicatively connected to the edge cloud system.
  • the edge cloud system is used to obtain detection results based on the video stream data.
  • the detection results are used to characterize whether there is security abnormality in the target area.
  • the edge cloud system includes a UPF module, an edge cloud control server, and an edge cloud management server;
  • the UPF module is used to forward the video stream data from the collection terminal to the edge cloud control server through the 5G network;
  • the edge cloud control server is used to store the received video stream data, and perform scene-based detection on the video stream data to obtain the detection result;
  • the edge cloud management server is used to configure a target application program for the edge cloud control server, and the target application program is used to implement the scene-based detection.
  • the security monitoring system also includes: an SMF module and an encrypted virtual network module;
  • the SMF module is connected to the UPF module through the N3 interface and the N4 interface.
  • the SMF module is connected to the encrypted virtual network module through the N2 interface.
  • the encrypted virtual network module is also connected to the core network.
  • the security monitoring system further includes a display module connected to the edge cloud system;
  • the display module is used to display the detection results forwarded by the UPF module.
  • the collection terminal and the 5G base station are communicated through a 5G module;
  • the 5G module includes a 5G module built into the collection terminal or a 5G gateway added between the collection terminal and the 5G base station.
  • the security monitoring system further includes an alarm module connected to the display module;
  • the alarm module is used to trigger an alarm device and generate alarm information
  • the display module is also used to display the alarm information
  • the scene-based detection includes any one or more of: pedestrian-vehicle diversion scene detection, personnel recognition scene detection, personnel post recognition scene detection, and safety equipment scene detection.
  • this application provides a 5G-based security monitoring method, which can be applied to any possible security monitoring system as provided in the first aspect.
  • the security monitoring system includes a communication-connected collection terminal and a 5G base station. and edge cloud system; the method includes:
  • the collection terminal collects video stream data of the target area
  • the edge cloud system receives the video stream data based on the 5G network provided by the 5G base station, and obtains detection results based on the video stream data.
  • the detection results are used to characterize whether there is security abnormality in the target area.
  • this application provides an electronic device, including: a processor, and a memory communicatively connected to the processor;
  • the memory stores computer execution instructions
  • the processor executes the computer execution instructions stored in the memory to implement the possible security monitoring method as provided in the second aspect.
  • the present application provides a computer-readable storage medium on which computer-executable instructions are stored.
  • the computer-executable instructions are executed by a processor, the possible security monitoring method provided in the second aspect is implemented.
  • the security monitoring system includes a collection terminal, a 5G base station and an edge cloud system.
  • the collection terminal is connected to the 5G base station for communication, wherein the collection terminal is used to
  • the target area collects video stream data, and the 5G base station communicates with the edge cloud system.
  • the edge cloud system is configured in the target area to obtain detection results based on the video stream data. The detection results are used to characterize whether there are security abnormal behaviors in the target area, thereby
  • a 5G-based security monitoring system is formed by constructing a 5G virtual private network through 5G and edge computing technology.
  • the path thereby reduces the delay, overcomes the lagging defect of the video analysis function in the existing technology, and does not require a public network connection, which is conducive to data protection.
  • Figure 1 is a schematic diagram of an application scenario provided by an embodiment of the present application.
  • Figure 2 is a schematic structural diagram of a security monitoring system provided by an embodiment of the present application.
  • Figure 3 is a schematic flow chart of a security monitoring method provided by an embodiment of the present application.
  • Figure 4 is a schematic flow chart of another security monitoring method provided by an embodiment of the present application.
  • Figure 5 is a schematic diagram of the implementation of scene-based detection provided by the embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • connection should be understood in a broad sense.
  • it can be a fixed connection or a detachable connection. , or integrally connected; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be an internal connection between the two components.
  • connection should be understood in a broad sense.
  • it can be a fixed connection or a detachable connection. , or integrally connected; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be an internal connection between the two components.
  • this application provides a 5G-based security monitoring system, method, electronic device and storage medium.
  • the inventive concept of this application is to construct a security monitoring system including a collection terminal, a 5G base station and an edge cloud system.
  • the collection terminal is communicated with the 5G base station, and the 5G base station is communicated with the edge cloud system.
  • the edge cloud system is configured in the target area, which includes any area with video security monitoring requirements, such as industrial parks, factory areas, etc.
  • the edge cloud system can receive video stream data through the 5G network provided by the 5G base station, and obtain detection results based on the video stream data that can indicate whether there are security abnormal behaviors in the target area, thus building a 5G virtual private network based on 5G and edge technology.
  • a 5G-based security monitoring system is formed. Through this security monitoring system, it is possible to detect whether there are security abnormal behaviors in the target area.
  • the configured edge cloud system can ensure that the video stream data can be detected based on the video stream data without leaving the factory. This is in line with the existing Compared with other technologies, the transmission path of video stream data is shortened, thereby reducing the delay and overcoming the lagging defect of the video analysis function in the existing technology.
  • the security monitoring system does not need to be connected to the public network, ensuring the confidentiality of video streaming data and conducive to data protection.
  • FIG 1 is a schematic diagram of an application scenario provided by an embodiment of the present application.
  • the security monitoring system 100 is deployed in a target area.
  • the target area in Figure 1 takes an industrial park as an example.
  • the security monitoring system 100 includes a collection terminal 101, a 5G base station 102, and an edge cloud system 103.
  • the collection terminal 101 may be, for example, a camera, used to collect video stream data in a target area.
  • the 5G base station 102 is used to provide a 5G network.
  • the edge cloud system 103 obtains video stream data through the 5G network, and then performs scene-based detection on the video stream data to obtain detection results that can indicate whether there is security abnormality in the target area. Based on 5G and edge technology, it ensures that the video stream data does not leave the factory. Detect whether there are abnormal security behaviors in the target area.
  • the 5G-based security monitoring system provided by the embodiments of this application includes but is not limited to the above illustrative application scenarios.
  • FIG 2 is a schematic structural diagram of a security monitoring system provided by an embodiment of the present application.
  • the 5G-based security monitoring system 200 provided by the embodiment of this application includes: a collection terminal 201, a 5G base station 202, and an edge cloud system 203.
  • the collection terminal 201 can be, for example, a camera, and is communicated with the 5G base station 202 to collect video stream data in the target area.
  • the number of collection terminals 201 can be multiple, and the location of the target area can be set according to actual working conditions.
  • the setting principle is to facilitate the capture of moving targets in the target area, thereby collecting video stream data.
  • the moving targets in the target area can be people, vehicles, etc.
  • the collected video stream data refers to video frames containing moving targets.
  • the 5G base station 202 is used to provide a 5G network, and is connected to the edge cloud system 203 for communication, so that the edge cloud system 203 can obtain video stream data through the 5G network, and then obtain detection results based on the video stream data, and use the detection results to characterize whether the target area exists. Security anomalies.
  • the edge cloud system 203 is configured in the target area, so that the 5G-based security monitoring system 200 provided in the embodiment of the present application can detect whether the target area exists based on the video stream data without leaving the factory. Security exception. Compared with the existing technology, it not only shortens the transmission path of video stream data and reduces the delay, but also overcomes the lagging defect of the video analysis function in the existing technology. In addition, the 5G-based security monitoring system 200 does not need to be connected to the public network, ensuring the confidentiality of video streaming data and conducive to data protection.
  • the 5G-based security monitoring system includes a collection terminal, a 5G base station and an edge cloud system.
  • the collection terminal is communicated with the 5G base station.
  • the collection terminal is used to collect video stream data in the target area, and the 5G base station is communicated with the edge cloud system.
  • the edge cloud system is configured in the target area to obtain detection results based on the video stream data. , the detection results are used to characterize whether there are security abnormal behaviors in the target area, thereby forming a 5G-based security monitoring system by constructing a 5G virtual private network through 5G and edge computing technology, which can be detected without ensuring that the video stream data does not leave the factory.
  • the transmission path of the streaming data thus reduces the delay, overcomes the lagging defect of the video analysis function in the existing technology, and does not need to be connected to the public network, which is conducive to data protection.
  • the edge cloud system 203 may include a UPF module 2031, an edge cloud control server 2032, and an edge cloud management server 2033.
  • the UPF module 2031 is used to forward the video stream data from the collection terminal 201 to the edge cloud control server 2032 through the 5G network provided by the 5G base station 202, so as to divert the video stream data and ensure that the video stream data in the factory is not It leaves the factory and effectively reduces latency.
  • the edge cloud control server 2032 can store the video stream data it receives, and then perform scene-based detection on the video stream data to obtain corresponding detection results.
  • the scene-based detection is determined based on the scene where the video stream data is located.
  • the scene-based detection can include: any one of the following: pedestrian-vehicle diversion scene detection, person recognition scene detection, person post recognition scene detection, and safety equipment scene detection, or Several kinds.
  • video stream data can be collected in a pedestrian-vehicle diversion scene, and the scene-based detection of the video stream data in this scene is the pedestrian-vehicle diversion scene detection.
  • the pedestrian-vehicle diversion scene can occur on roads in factory areas, etc.
  • video stream data can be collected in a scene that requires face recognition, and the scene-based detection of the video stream data collected in this scene is person recognition scene detection.
  • the scene of face recognition can occur at an access control point.
  • video stream data can be collected in a scene that requires human post recognition.
  • the scene-based detection of the video stream data collected in this scene is human post recognition scene detection.
  • the human post recognition scenario is such as people on an assembly line station. Job matching, etc.
  • safety equipment scene detection may also include one or more of helmet scene detection, safety clothing scene detection, reflective clothing scene detection, area delineation scene detection, location scene detection, etc.
  • helmet scene detection safety clothing scene detection
  • reflective clothing scene detection area delineation scene detection, location scene detection, etc.
  • the above-mentioned safety equipment scene detection can be understood as any scene-based detection related to safety production scenarios.
  • the embodiments of this application do not limit the specific content of the safety production scenario.
  • the edge cloud control server (Multi-access Edge Computing, MEC) 2032 has computing power and storage capabilities. It can perform AI analysis, that is, scene-based detection of video stream data, and the corresponding analysis results obtained are also detection result.
  • the edge cloud management server 2033 is the management platform of the edge cloud control server 2032 and can be responsible for allocating resources such as computing power, GPU, storage space, and network for SAAS applications deployed in the edge cloud control server 2032.
  • the edge cloud management server 2033 is used to configure the target application deployed therein for the edge cloud control server 2032.
  • the target application is a SAAS-based application that can be used to implement scenario-based detection.
  • the edge cloud control server 2032 can form an AI algorithm integration library through plug-ins. Multiple SAAS applications are deployed in the algorithm integration library, and the multiple SAAS applications are collectively referred to as target applications.
  • the edge cloud management server 2033 implements the scheduling and policy distribution of multiple AI algorithms by configuring target applications for the edge cloud control server 2032, in other words, by scheduling multiple SAAS applications.
  • the security monitoring system 200 may also include a display module 204 connected to the edge cloud system 203.
  • the display module 204 can visually display the detection results.
  • the UPF module 2031 in the edge cloud system 203 will forward the detection results to the display module 204 for visual display, thereby realizing the scene
  • the visualization of chemical detection is conducive to the timely discovery and processing of abnormal security behaviors.
  • the security monitoring system 200 may also include an SMF (Session Management Function) module 205 and an encrypted virtual network (Secret Private Network, SPN) module 206.
  • SMF Session Management Function
  • SPN Synthetic Private Network
  • the SMF module 205 is connected to the UPF module 2031 through the N3 interface and the N4 interface.
  • the SMF module 205 is also connected to the encrypted virtual network module 206 through the N2 interface, and the encrypted virtual network module 206 is also connected to the core network 300. .
  • the IP address of the collection terminal 201 can be allocated through the SMF module 205, so that the 5G network traffic can be forwarded to the UPF module 2031 via the 5G base station 202, and then the UPF module 2031 forwards it to the edge cloud control server 2032 to realize the network traffic.
  • the edge cloud control server 2032 Distribute and direct traffic to the edge cloud system 203.
  • the encrypted virtual network module 206 is used to establish physical or logical business area isolation, build a security system that conforms to the business processes in the factory, and improve the security of the security monitoring system 200.
  • the encrypted virtual module 206 is connected to the core network 300 through the transmission network 400, so that the core network 300 can distribute the detection results and/or video stream data according to the actual working conditions of the factory.
  • the detection results and/or The video stream data is distributed to other network systems according to requirements.
  • the other network systems can be, for example, any network system in the factory except the security monitoring system 200.
  • the functions of other network systems are determined by actual working conditions, and are not limited in the embodiments of this application.
  • the transmission network 400 is used for information transmission between the security monitoring system 200 and the core network 300 .
  • the edge cloud system 203 can also be connected to the Internet through the N6 interface.
  • the collection terminal 201 can be, for example, a camera, and is communicatively connected to the 5G base station 202. Specifically, the collection terminal 201 and the 5G base station 202 can be connected through 5G module communication.
  • the 5G module can be a 5G module built into the collection terminal 201 or a 5G gateway added between the collection terminal 201 and the 5G base station 202.
  • some cameras have 5G modules themselves, through which they can access the 5G network.
  • the 5G module can add a 5G gateway between the collection terminal 201 and the 5G base station 202 to allow the collection terminal 201 that does not have a 5G module to access the 5G network through the 5G gateway.
  • the added 5G gateway and the collection terminal 201 can be connected through wired or wireless connections.
  • the security monitoring system 200 may also include an alarm module 207 connected to the display module 204 .
  • the alarm module 207 can trigger the alarm device and generate alarm information, so that the alarm device can alert the site where the abnormal safety behavior occurs, and can also use the display module to 204 visually displays alarm information, thereby achieving active early warning for abnormal safety behaviors occurring in the factory area.
  • the video stream data can be collected from different scenes in the target area to perform scene-based detection corresponding to the scene, so that the 5G-based security monitoring system provided by the embodiment of the present application can be used in the target area. No blind spot monitoring.
  • FIG 3 is a schematic flow chart of a security monitoring method provided by an embodiment of the present application.
  • the 5G-based security monitoring method provided by an embodiment of the present application is applied to the 5G-based security monitoring system provided by the above embodiments.
  • the security monitoring system includes Communication connection collection terminals, 5G base stations and edge cloud systems.
  • the 5G-based security monitoring method provided by the embodiment of this application includes:
  • the collection terminal collects video stream data of the target area.
  • the collection terminal is connected to the 5G base station for communication, and the collection terminal is set up in the area where security monitoring is required, that is, the target area, to collect video stream data in the target area.
  • the collection terminal can be, for example, a camera, and can be connected to the 5G base station through a 5G module.
  • the 5G module can be a 5G module built into the collection terminal, or, for a collection terminal that does not come with a 5G module, the 5G module can be a 5G gateway added between the collection terminal and the 5G base station. Both the 5G network group and the 5G gateway are used to enable the collection terminal to access the 5G network provided by the 5G base station and achieve communication connections with the 5G base station.
  • the edge cloud system receives video stream data based on the 5G network provided by the 5G base station, and obtains detection results based on the video stream data.
  • the detection results are used to characterize whether there are safety abnormal behaviors in the target area.
  • the edge cloud system is configured in the target area and communicates with the 5G base station, equipped with edge cloud computing functions. Therefore, the edge cloud system can obtain the video stream data collected by the collection terminal based on the 5G network provided by the 5G base station, and can perform AI analysis on the video stream data to obtain the corresponding analysis results, that is, detection results, to determine whether there are security anomalies in the target area. Detection of behavior. In other words, the edge cloud system can obtain detection results based on video stream data, and the detection results are used to characterize whether there are security abnormal behaviors in the target area.
  • the target area can be learned based on the video stream data without leaving the factory. Whether there is any abnormal security behavior in the domain, and realize intelligent monitoring of the target area.
  • the transmission path of the video stream data is shortened, the delay is reduced, and the lagging defect of the video analysis function in the existing technology can be overcome.
  • the security monitoring system provided by the embodiments of this application does not need to be connected to the public network, so it can ensure the confidentiality of video stream data and is conducive to data protection.
  • the 5G-based security monitoring method provided by the embodiments of this application is applied to a 5G-based security monitoring system.
  • the security monitoring system includes a communication-connected collection terminal, a 5G base station, and an edge cloud system.
  • the acquisition terminal collects video stream data of the target area.
  • the edge cloud system obtains video stream data from the acquisition terminal based on the 5G network provided by the 5G base station, and obtains detection results based on the video stream data. The detection results are used to characterize whether there is security in the target area.
  • the 5G-based security monitoring system implements security monitoring methods and detects whether there are security abnormalities in the target area based on the video stream data when the video stream data does not leave the factory, thereby realizing monitoring of the target area and shortening the processing time of the video stream data.
  • the transmission path reduces the delay and can overcome the lagging defect of the video analysis function in the existing technology. It also ensures the confidentiality of the video stream data and is conducive to data protection.
  • FIG 4 is a schematic flow chart of another security monitoring method provided by an embodiment of the present application.
  • the 5G-based security monitoring method provided by the embodiments of this application is applied to the 5G-based security monitoring system provided by the above embodiments.
  • the security monitoring system includes a communication-connected collection terminal, a 5G base station, and an edge cloud system.
  • the security monitoring method provided by the embodiment of the present application includes:
  • S201 The collection terminal collects video stream data of the target area.
  • step S201 and step S101 are similar. For details, please refer to the description of the foregoing embodiments and will not be described again here.
  • the UPF module forwards the video stream data from the collection terminal to the edge cloud control server through the 5G network.
  • the edge cloud control server stores the received video stream data.
  • the edge cloud management server configures the target application for the edge cloud control server, and the edge cloud control server runs the target application to perform scene-based detection of the video stream data and obtain detection results.
  • the edge cloud system includes the UPF module, edge cloud control server and edge cloud management server, and the target application is used to implement scene-based detection.
  • the UPF module in the edge cloud system forwards the video stream data from the collection terminal to the edge cloud control server through the 5G network provided by the 5G base station, which plays a role in diverting the video stream data.
  • the edge cloud control server receives the video stream data and stores it, and uses its computing power to perform scene-based detection of the video stream data to obtain corresponding detection results.
  • the edge cloud control server realizes its computing power by running the target application. .
  • the scene-based detection includes any one or more of pedestrian-vehicle diversion scene detection, personnel recognition scene detection, personnel post recognition scene detection, and safety equipment scene detection.
  • scene-based detection includes but is not limited to the listed scene detection.
  • the edge cloud management server is the management platform of the edge cloud control server and is responsible for allocating computing power, GPU, storage space, network and other resources of SAAS applications deployed in the edge cloud control server.
  • FIG. 5 is a schematic diagram of an implementation of scene-based detection provided by an embodiment of the present application.
  • the UPF module in the edge cloud system forwards the video stream data to the edge cloud control server in the edge cloud system through the 5G network provided by the 5G base station.
  • the cloud control server adopts a plug-in method to form an AI algorithm integration library.
  • Multiple SAAS applications are deployed in the AI algorithm integration library, such as algorithm A, algorithm B, etc. in Figure 5.
  • algorithm A is used to perform face recognition. Identification, human-machine identification, person identification, etc.
  • Algorithm B is used for safety clothing identification, hard hat identification, reflective clothing identification, etc.
  • Algorithm C is used for person tracking algorithm
  • algorithm D is used for location detection, etc. (not shown in Figure 5 Show C algorithm and D algorithm, etc.).
  • the respective applications of various algorithms are SAAS applications and are collectively referred to as target applications.
  • algorithm A is application A in the target application program
  • algorithm B is application B in the target application program
  • Various algorithms and corresponding applications are connected through service interfaces.
  • the target application is used to implement scene-based detection.
  • the edge cloud management server can schedule the corresponding algorithm required for scene detection of the video stream data for the edge cloud control server based on the video picture of the video stream data.
  • the corresponding algorithm dispatched is the corresponding application in the target application.
  • the edge cloud management server implements intelligent scheduling and policy distribution of AI algorithms by configuring each application in the target application for the edge cloud control server.
  • the edge cloud management server schedules the edge cloud control server from the AI algorithm integration library based on the video images of the video stream data collected in the pedestrian-vehicle diversion scenario.
  • the face recognition algorithm, human-machine recognition algorithm, electronic area delimitation algorithm, location detection algorithm, and person tracking algorithm are developed and superimposed to form a pedestrian-vehicle diversion scene detection, which is used to determine whether pedestrians are on the sidewalk. and whether the vehicle is in a motor vehicle lane. After judgment, if the detection result obtained is that pedestrians are not on the sidewalk and/or the vehicle is not on the motor vehicle lane, it means that there is abnormal safety behavior in the target area where the pedestrian-vehicle diversion scenario is performed.
  • the edge cloud management server schedules the corresponding applications of the face recognition algorithm, human-computer recognition algorithm, electronic area delineation algorithm, location detection algorithm, and personnel tracking algorithm, that is, configuring the target application for the edge cloud control server to utilize the configured
  • the target application realizes the separation of people and vehicles in the current pedestrian-vehicle diversion scenario. Divert scene detection and obtain corresponding detection results.
  • S203a The UPF module forwards the detection results to the display module, and the display module displays the detection results.
  • the 5G-based security monitoring system can also include a display module connected to the edge cloud system. After obtaining the detection results, the UPF module in the edge cloud system forwards the detection results to the display module for visual display, realizing the visualization of scene-based detection. It is conducive to the timely detection and handling of abnormal security behaviors.
  • S203b When the detection result indicates that there is abnormal security behavior in the target area, the alarm module triggers the alarm device and generates alarm information, and the display module displays the alarm information.
  • the 5G-based security monitoring system can also include an alarm module connected to the display module.
  • the alarm module can trigger the alarm device and generate alarm information.
  • the display module can visually display all
  • the alarm device can be a warning light, broadcast and other equipment.
  • the alarm information can be notified by lighting up lights and voice broadcasts to achieve active early warning for abnormal safety behaviors that occur in the factory area.
  • the 5G-based security monitoring method provided by the embodiments of this application is applied to a 5G-based security monitoring system.
  • the security monitoring system includes a communication-connected collection terminal, a 5G base station, and an edge cloud system.
  • the UPF module in the edge cloud system forwards the video stream data to the edge cloud control server in the edge cloud system through the 5G network provided by the 5G base station.
  • the edge cloud control server processes the video stream data.
  • the edge cloud management server in the edge cloud system configures the target application for the edge cloud control server, and the edge cloud control server runs the target application to perform scene-based detection of video stream data and obtain detection results.
  • the UPF module in the edge cloud system forwards the detection results to the display module, and the display module displays the detection results visually.
  • the alarm module connected to the display module triggers the alarm device and generates alarm information, and the display module visually displays the alarm information.
  • the analysis function has the disadvantage of lag, but it also ensures the confidentiality of video stream data, which is conducive to data protection.
  • active early warning of abnormal security behaviors in the target area can be realized, automatic monitoring without blind spots can be realized, and the digital transformation capability of the security monitoring system can be improved.
  • FIG. 6 is a schematic structural diagram of an electronic device provided by an embodiment of the present application.
  • the electronic device 500 may include: a processor 501 and a memory 502 communicatively connected to the processor 501 .
  • Memory 502 is used to store programs.
  • the program may include program code, which includes computer-executable instructions.
  • Memory 502 may include high-speed RAM memory and may also include non-volatile memory (NoN-volatile memory), such as at least one disk memory.
  • NoN-volatile memory such as at least one disk memory.
  • the processor 501 is used to execute computer execution instructions stored in the memory 502 to implement a 5G-based security monitoring method.
  • the processor 501 may be a central processing unit (Central Processing Unit, referred to as CPU), or a specific integrated circuit (Application Specific Integrated Circuit, referred to as ASIC), or a device configured to implement the embodiments of the present application. Multiple integrated circuits.
  • CPU Central Processing Unit
  • ASIC Application Specific Integrated Circuit
  • the memory 502 can be independent or integrated with the processor 501 .
  • the electronic device 500 may also include:
  • Bus 503 is used to connect the processor 501 and the memory 502.
  • the bus can be an industry standard architecture (industry standard architecture, ISA) bus, a peripheral component (PCI) bus or an extended industry standard architecture (EISA) bus, etc.
  • the bus can be divided into address bus, data bus, control bus, etc., but it does not mean that there is only one bus or one type of bus.
  • the memory 502 and the processor 501 can communicate through an internal interface.
  • This application also provides a computer-readable storage medium, which can include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random AccessMemory) , magnetic disks or optical disks and other media that can store program codes.
  • ROM read-only memory
  • RAM random access memory
  • the computer-readable storage medium stores computer execution instructions, and the computer execution instructions are used for the 5G-based security monitoring method in the above embodiment.
  • This application also provides a computer program product, which includes computer execution instructions.
  • the computer instructions are executed by a processor, the 5G-based security monitoring method in the above embodiment is implemented.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Alarm Systems (AREA)

Abstract

一种基于5G的安防监控系统（200）、方法、电子设备及存储介质，安防监控系统（200）包括采集终端（201）、5G基站（202）以及边缘云系统（203），采集终端（201）与5G基站（202）通信连接，其中，采集终端（201）用于在目标区域采集视频流数据，而5G基站（202）与边缘云系统（203）通信连接，边缘云系统（203）配置于目标区域内以用于根据视频流数据获得检测结果，检测结果用于表征目标区域是否存在安全异常行为，从而通过5G与边缘计算技术构建5G虚拟专网的方式形成基于5G的安防监控系统（203），在保障视频流数据不出厂的情况下即可检测出目标区域是否存在安全异常行为，缩短了视频流数据的传输路径从而降低了时延，克服了现有技术中视频分析功能存在滞后性的缺陷，且无需连接公网有利于数据保护。

Description

基于5G的安防监控系统、方法、电子设备及存储介质
本申请要求于2022年07月11日提交中国专利局、申请号为202210810701.6、申请名称为“基于5G的安防监控系统、方法、电子设备及存储介质”的中国申请专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及安防技术领域，尤其涉及一种基于5G的安防监控系统、方法、电子设备及存储介质。
背景技术
随着人们对工业生产安全防护意识的不断提高，工业园区视频安全防护系统的重要性也愈发突出。对于工业园区的视频安全防护系统而言，普遍使用的传统视频监控对所发生事件只具备记录功能，并且在很大程度上还依赖于人的判断，而人又受制于精力和注意力有限，因而采用传统的视频监控可能会导致漏报现象发生，进而会带来安全隐患。另外，传统视频监控在布线过程易受监控地域等诸多物理条件的限制，且由于网络布线架构的复杂性会使得后期监控系统的维护费用居高不下。
针对传统视频监控的不足，目前普遍的解决方案是将智能化分析模块转移到云端处理，使得视频监控系统由传统人防转化到智能化。具体是指将摄像头采集的视频流通过有线/无线与公网相连，进而将视频流传输到云服务器进行计算、存储和分析，最后将得到的反馈结果通过大屏等终端设备进行显示。
然而，目前所采用的这种智能化监控解决方案一方面由于视频流的传送路径长而导致时延较长，使得一些实时的视频分析功能存在滞后性而失去意义，另一方面，比如工厂等特殊的应用环境对视频流数据保密性要求高，此方案的实现需连接公网，因此不利于数据保护。可见，现有的智能化监控解决方案存在分析功能滞后以及数据保密性不足的缺陷。
发明内容
本申请提供一种基于5G的安防监控系统、方法、电子设备及存储介质，用以解决现有的工业园区智能化监控方案存在的分析功能滞后以及数据保密性不足的技术问题。
第一方面，本申请提供一种基于5G的安防监控系统，包括：采集终端、5G基站 以及边缘云系统；
所述采集终端与所述5G基站通信连接，所述采集终端用于在目标区域采集视频流数据；
所述5G基站与所述边缘云系统通信连接，所述边缘云系统用于根据所述视频流数据获得检测结果，所述检测结果用于表征所述目标区域是否存在安全异常行为。
在一种可能的设计中，所述边缘云系统包括UPF模块、边缘云控制服务器以及边缘云管理服务器；
所述UPF模块用于通过5G网络将所述视频流数据从所述采集终端转发至所述边缘云控制服务器；
所述边缘云控制服务器用于存储接收到的所述视频流数据，并对所述视频流数据进行场景化检测，得到所述检测结果；
所述边缘云管理服务器用于为所述边缘云控制服务器配置目标应用程序，所述目标应用程序用于实现所述场景化检测。
在一种可能的设计中，所述安防监控系统，还包括：SMF模块和加密虚拟网络模块；
所述SMF模块通过N3接口和N4接口与所述UPF模块连接，所述SMF模块通过N2接口与所述加密虚拟网络模块连接，所述加密虚拟网络模块还连接至核心网端。
在一种可能的设计中，所述安防监控系统，还包括与所述边缘云系统连接的显示模块；
所述显示模块用于显示所述UPF模块转发的所述检测结果。
在一种可能的设计中，所述采集终端与所述5G基站之间通过5G模块通信连接；
其中，所述5G模块包括内置于所述采集终端的5G模组或增设于所述采集终端与所述5G基站之间的5G网关。
在一种可能的设计中，所述安防监控系统，还包括与所述显示模块连接的报警模块；
当所述目标区域存在安全异常行为时，所述报警模块用于触发警报装置以及生成警报信息，所述显示模块还用于显示所述警报信息。
在一种可能的设计中，所述场景化检测包括：人车分流场景检测、人员识别场景检测、人岗识别场景检测以及安全装备场景检测中的任意一种或几种。
第二方面，本申请提供一种基于5G的安防监控方法，应用于如第一方面提供的任意一种可能的安防监控系统，所述安防监控系统包括通信连接的采集终端、5G基站 以及边缘云系统；所述方法，包括：
所述采集终端采集目标区域的视频流数据；
所述边缘云系统基于5G基站提供的5G网络接收所述视频流数据，并根据所述视频流数据获得检测结果，所述检测结果用于表征所述目标区域是否存在安全异常行为。
第三方面，本申请提供一种电子设备，包括：处理器，以及与所述处理器通信连接的存储器；
所述存储器存储计算机执行指令；
所述处理器执行所述存储器存储的计算机执行指令，以实现如第二方面提供的可能的安防监控方法。
第四方面，本申请提供一种计算机可读存储介质，其上存储有计算机执行指令，所述计算机执行指令被处理器执行时实现第二方面提供的可能的安防监控方法。
本申请提供一种基于5G的安防监控系统、方法、电子设备及存储介质，该安防监控系统包括采集终端、5G基站以及边缘云系统，采集终端与5G基站通信连接，其中，采集终端用于在目标区域采集视频流数据，而5G基站与边缘云系统通信连接，边缘云系统配置于目标区域内以用于根据视频流数据获得检测结果，检测结果用于表征目标区域是否存在安全异常行为，从而通过5G与边缘计算技术构建5G虚拟专网的方式形成基于5G的安防监控系统，在保障视频流数据不出厂的情况下即可检测出目标区域是否存在安全异常行为，缩短了视频流数据的传输路径从而降低了时延，克服了现有技术中视频分析功能存在滞后性的缺陷，且无需连接公网有利于数据保护。
附图说明
图1为本申请实施例提供的一种应用场景示意图；
图2为本申请实施例提供的一种安防监控系统的结构示意图；
图3为本申请实施例提供的一种安防监控方法的流程示意图；
图4为本申请实施例提供的另一种安防监控方法的流程示意图；
图5为本申请实施例提供的一种场景化检测的实现示意图；
图6为本申请实施例提供的一种电子设备的结构示意图。
具体实施方式
首先，本领域技术人员应当理解的是，这些实施方式仅仅用于解释本申请的技术原理，并非旨在限制本申请的保护范围。本领域技术人员可以根据需要对其做出调整，以便适应具体的应用场合。
其次，需要说明的是，在本申请的描述中，术语“内”、“外”等指示的方向或 位置关系的术语是基于附图所示的方向或位置关系，这仅仅是为了便于描述，而不是指示或暗示装置或构件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。
此外，还需要说明的是，在本申请的描述中，除非另有明确的规定和限定，术语“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接，或一体地连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个构件内部的连通。对于本领域技术人员而言，可根据具体情况理解上述术语在本申请中的具体含义。
随着人们对工业生产安全防护意识的不断提高，工业园区视频安全防护系统的重要性也愈发突出。而对于工业园区的视频安全防护系统而言，传统的视频监控会导致漏报现象发生，并且布线过程易受监控地域等诸多物理条件的限制，另外还由于网络布线架构的复杂性会使得后期监控系统的维护费用居高不下。针对传统视频监控的不足，目前普遍的解决方案是将智能化分析模块转移到云端处理，使得视频监控系统由传统人防转化到智能化。然而，这种智能化监控解决方案会由于视频流的传送路径长而导致时延较长，使得一些实时的视频分析功能存在滞后性而失去意义，另外，此方案的实现需连接公网，不利于数据保护，缺乏数据保密性。
针对现有技术存在的上述问题，本申请提供一种基于5G的安防监控系统、方法、电子设备及存储介质。本申请的发明构思在于：构建包括采集终端、5G基站以及边缘云系统的安防监控系统，采集终端与5G基站通信连接，5G基站与边缘云系统通信连接。边缘云系统配置于目标区域内，目标区域包括存在视频安防监控需求的任意区域，例如工业园区、厂房区等等。边缘云系统可以通过5G基站提供的5G网络接收到视频流数据，并根据视频流数据得到能够表征目标区域内是否存在安全异常行为的检测结果，从而基于5G与边缘技术构建5G虚拟专网的方式形成基于5G的安防监控系统，通过该安防监控系统实现对目标区域是否存在安全异常行为的检测，配置的边缘云系统可以保障视频流数据不出厂即可根据视频流数据得到检测结果，与现有技术相比，缩短了视频流数据的传输路径，从而可以降低时延，并能够克服现有技术中视频分析功能存在滞后性的缺陷。另外，该安防监控系统无需连接公网，保证了视频流数据的保密性，有利于数据保护。
图1为本申请实施例提供的一种应用场景示意图。如图1所示，例如工业园区、厂房区等目标区域为了提高安全防护意识，需要对该目标区域内的移动目标进行实时监控，以检测目标区域内是否存在安全异常行为。本申请实施例提供的基于5G的安 防监控系统100部署于目标区域，图1中的目标区域以工业园区为例示出，该安防监控系统100包括采集终端101、5G基站102以及边缘云系统103。采集终端101可以例如摄像头，用于在目标区域采集视频流数据。5G基站102用于提供5G网络。边缘云系统103通过5G网络获得视频流数据，进而对视频流数据进行场景化检测得到可以表征目标区域是否存在安全异常行为的检测结果，基于5G与边缘技术在保证视频流数据不出厂的情况下实现对目标区域是否存在安全异常行为的检测。
需要说明的是，本申请实施例提供的基于5G的安防监控系统包括但不限于上述示意的应用场景。
图2为本申请实施例提供的一种安防监控系统的结构示意图。如图2所示，本申请实施例提供的基于5G的安防监控系统200，包括：采集终端201、5G基站202以及边缘云系统203。
采集终端201可以例如摄像头，并与5G基站202通信连接，用于在目标区域采集视频流数据，采集终端201的数量可以为多个，在目标区域的位置可以根据实际工况中需要进行设置，设置原则为便于捕获目标区域内的移动目标，从而采集到视频流数据。需要说明的时，目标区域内的移动目标可以为人、车辆等。所采集到的视频流数据是指包含有移动目标的视频画面。
5G基站202用于提供5G网络，其与边缘云系统203通信连接，使得边缘云系统203可以通过5G网络获得视频流数据，进而可以根据视频流数据得到检测结果，通过检测结果表征目标区域是否存在安全异常行为。
另外，边缘云系统203被配置于目标区域，因而可以使得本申请实施例提供的基于5G的安防监控系统200，在视频流数据不出厂的情况下便可根据视频流数据检测出目标区域是否存在安全异常。与现有技术相比，不但缩短了视频流数据的传输路径，降低了时延，并能够克服现有技术中视频分析功能存在滞后性的缺陷。此外，该基于5G的安防监控系统200还无需连接公网，保证了视频流数据的保密性，有利于数据保护。
本申请实施例提供的基于5G的安防监控系统，包括采集终端、5G基站以及边缘云系统。采集终端与5G基站通信连接，其中，采集终端用于在目标区域采集视频流数据，而5G基站与边缘云系统通信连接，边缘云系统配置于目标区域内以用于根据视频流数据获得检测结果，检测结果用于表征目标区域是否存在安全异常行为，从而通过5G与边缘计算技术构建5G虚拟专网的方式形成基于5G的安防监控系统，在保障视频流数据不出厂的情况下即可检测出目标区域是否存在安全异常行为，缩短了视 频流数据的传输路径从而降低了时延，克服了现有技术中视频分析功能存在滞后性的缺陷，且无需连接公网有利于数据保护。
在一种可能的设计中，边缘云系统203可以包括UPF模块2031、边缘云控制服务器2032以及边缘云管理服务器2033。
其中，UPF模块2031用于通过5G基站202提供的5G网络将视频流数据从采集终端201转发至边缘云控制服务器2032，以对视频流数据起到分流作用，可以保证厂区内的视频流数据不出厂且有效降低时延。
边缘云控制服务器2032则可以存储其接收到的视频流数据，进而对视频流数据进行场景化检测，得到对应的检测结果。其中场景化检测是根据视频流数据所在的场景决定的，例如，场景化检测可以包括：人车分流场景检测、人员识别场景检测、人岗识别场景检测以及安全装备场景检测中的任意一种或几种。
比如，视频流数据可以采集于人车分流场景，则此场景的该视频流数据进行的场景化检测即为人车分流场景检测，人车分流场景可发生于厂区内的道路等。
又比如，视频流数据可以采集于需要进行人脸识别的场景，则对该场景采集的视频流数据所进行的场景化检测即为人员识别场景检测，人脸识别的场景可以发生于门禁处。
再比如，视频流数据可以采集于需要进行人岗识别的场景，则对该场景采集的视频流数据所进行的场景化检测即为人岗识别场景检测，人岗识别场景例如流水线工位上的人岗匹配等。
可选地，安全装备场景检测还可以包括安全帽场景检测、安全服场景检测、反光服场景检测、区域划定场景检测、位置场景检测等其中的一个或多个。上述安全装备场景检测可以理解为与安全生产场景相关的任意场景化检测。本申请实施例对于安全生产场景的具体内容不作限定。
需要说明的是，边缘云控制服务器(Multi-access Edge Computing，MEC)2032具备算力以及存储能力，其可以进行AI分析，即对视频流数据进行场景化检测，得到的对应分析结果也就是检测结果。
而边缘云管理服务器2033为边缘云控制服务器2032的管理平台，可以负责分配部署在边缘云控制服务器2032中SAAS化应用的算力、GPU、存储空间以及网络等资源。换言之，边缘云管理服务器2033用于为边缘云控制服务器2032配置其内已部署的目标应用程序，目标应用程序为SAAS化的可以用于实现场景化检测的应用。
例如，边缘云控制服务器2032中可以通过插件的方式形成AI算法集成库，该AI 算法集成库中部署有多个SAAS化应用，该多个SAAS应用被统称为目标应用程序。边缘云管理服务器2033通过为边缘云控制服务器2032配置目标应用程序，换言之，通过对多个SAAS化应用进行调度实现多种AI算法的调度和策略分发。
可选地，安防监控系统200，还可以包括有与边缘云系统203连接的显示模块204。边缘云系统203根据视频流数据得到检测结果后，显示模块204可以对检测结果进行可视化显示，例如，边缘云系统203中的UPF模块2031会转发检测结果至显示模块204进行可视化显示，从而实现场景化检测的可视化，有利于安全异常行为的及时发现和处理。
在一种可能的设计中，安防监控系统200还可以包括SMF(Session Management Function，会话管理功能)模块205和加密虚拟网络(Secret Private Network，SPN)模块206。
如图2所示，SMF模块205通过N3接口和N4接口与UPF模块2031连接，另外，SMF模块205还通过N2接口与加密虚拟网络模块206连接，而加密虚拟网络模块206还连接至核心网300。
其中，采集终端201的IP地址可以通过SMF模块205进行分配，从而可以经由5G基站202将5G网络流量转发至UPF模块2031，进而又UPF模块2031转发至边缘云控制服务器2032，以实现将网络流量分发并导流至边缘云系统203。
另外，加密虚拟网络模块206用于建立业务物理或逻辑区域隔离，建成符合厂区内业务流程的安全体系，提高安防监控系统200的安全性。
此外，加密虚拟模块206通过传输网400与核心网300连接，以使得核心网300可以将检测结果和/或视频流数据根据厂区的实际工况的需求进行分发，例如可以将检测结果和/或视频流数据按照需求分发至其他网络系统，其他网络系统可以例如厂区内除安防监控系统200之外的任意网络系统，其他网络系统的功能由实际工况决定，本申请实施例对此不作限定。显然，传输网400则用于安防监控系统200与核心网300之间的信息传送。
可选地，边缘云系统203还可以通过N6接口连接至互联网。
如前述实施例所描述，采集终端201可以例如摄像头，并与5G基站202通信连接。具体地，采集终端201与5G基站202之间可以通过5G模块通信连接。
在一种可能的设计中，5G模块可以为内置于采集终端201的5G模组或者增设于采集终端201与5G基站202之间的5G网关。比如，有些摄像头自身具备5G模组，通过5G模组可接入5G网络。而对于有些传统摄像头而言，可能自身不具备能够接入 5G网络的5G模组，因而5G模块可以通过在采集终端201与5G基站202之间增设5G网关的方式，以通过5G网关使得自身不具备5G模组的采集终端201接入5G网络。
可以理解的是，增设的5G网关与采集终端201之间可通过有线或者无线连接。
在一种可能的设计中，安防监控系统200还可以包括与显示模块204连接的报警模块207。在当边缘云系统203根据视频流数据确定目标区域存在安全异常行为时，报警模块207可以触发警报装置并生成警报信息，使得警报装置对发生安全异常行为的现场进行告警，进而还可以通过显示模块204对警报信息进行可视化显示，从而对厂区内所发生的安全异常行为实现主动预警。
另外，需要说明的是，视频流数据可以采集自目标区域内的不同场景以进行该场景所对应的场景化检测，从而使得本申请实施例提供的基于5G的安防监控系统可以做到在目标区域的无盲点监控。
图3为本申请实施例提供的一种安防监控方法的流程示意图，本申请实施例提供的基于5G的安防监控方法应用于上述各实施例提供的基于5G的安防监控系统，该安防监控系统包括通信连接的采集终端、5G基站以及边缘云系统。如图3所示，本申请实施例提供的基于5G的安防监控方法，包括：
S101：采集终端采集目标区域的视频流数据。
其中，采集终端与5G基站通信连接，在需要进行安防监控的区域即目标区域设置采集终端，用来采集目标区域的视频流数据。
可选地，采集终端可以例如摄像头，可以通过5G模块与5G基站通信连接。5G模块可以是采集终端内置的5G模组，或者，对于未自带5G模组的采集终端而言，5G模块可以为增设于采集终端与5G基站之间的5G网关。5G网组和5G网关均用于使得采集终端接入5G基站提供的5G网络，与5G基站实现通信连接。
S102：边缘云系统基于5G基站提供的5G网络接收视频流数据，并根据视频流数据获得检测结果。
其中，检测结果用于表征目标区域是否存在安全异常行为。
边缘云系统被配置于目标区域，并与5G基站通信连接，具备边缘云计算功能。因此，边缘云系统可以基于5G基站提供的5G网络获得采集终端所采集的视频流数据，并可以对视频流数据进行AI分析，得到对应分析结果也即检测结果，实现对目标区域是否存在安全异常行为的检测。换言之，边缘云系统可以根据视频流数据获得检测结果，检测结果用于表征目标区域是否存在安全异常行为。
通过边缘云系统则可在视频流数据不出厂的情况下，根据视频流数据获知目标区 域是否存在安全异常行为，实现对目标区域的智能监控。与现有技术相比，缩短了视频流数据的传输路径，降低了时延，能够克服现有技术中视频分析功能存在滞后性的缺陷。本申请实施例提供的安防监控系统无需连接公网，因而可以保证视频流数据的保密性，有利于数据保护。
本申请实施例提供的基于5G的安防监控方法应用于基于5G的安防监控系统，安防监控系统包括通信连接的采集终端、5G基站以及边缘云系统。首先采集终端采集目标区域的视频流数据，然后边缘云系统基于5G基站提供的5G网络从采集终端处获得视频流数据，并根据视频流数据获得检测结果，检测结果用于表征目标区域是否存在安全异常行为，基于5G的安全监控系统通过执行安全监控方法，在视频流数据不出厂的情况下根据视频流数据检测出目标区域是否存在安全异常，实现对目标区域的监控，缩短了视频流数据的传输路径，降低了时延，并能够克服现有技术中视频分析功能存在滞后性的缺陷，还保证了视频流数据的保密性，有利于数据保护。
图4为本申请实施例提供的另一种安防监控方法的流程示意图。本申请实施例提供的基于5G的安防监控方法应用于上述各实施例提供的基于5G的安防监控系统，该安防监控系统包括通信连接的采集终端、5G基站以及边缘云系统。如图4所示，本申请实施例提供的安防监控方法，包括：
S201：采集终端采集目标区域的视频流数据。
步骤S201与步骤S101的实现方式、原理及技术效果相类似，详细内容可参考前述实施例描述，在此不再赘述。
S202a：UPF模块通过5G网络将视频流数据从采集终端转发至边缘云控制服务器。
S202b：边缘云控制服务器存储接收到的视频流数据。
S202c：边缘云管理服务器为边缘云控制服务器配置目标应用程序，边缘云控制服务器运行目标应用程序以对视频流数据进行场景化检测，得到检测结果。
其中，边缘云系统包括UPF模块、边缘云控制服务器以及边缘云管理服务器，而目标应用程序用于实现场景化检测。
边缘云系统中的UPF模块通过5G基站提供的5G网络将视频流数据从采集终端转发给边缘云控制服务器，对视频流数据起到分流作用。边缘云控制服务器接收到视频流数据后进行存储，并利用其具备的算力对视频流数据进行场景化检测得到对应的检测结果，边缘云控制服务器通过运行目标应用程序实现其所具备的算力。
可选地，场景化检测包括人车分流场景检测、人员识别场景检测、人岗识别场景检测以及安全装备场景检测中的任意一种或几种。
对于场景化检测的具体描述可参考前述实施例，在此不再赘述。另外，场景化检测包括但不仅限于所列举的各场景检测。
边缘云控制服务器进行的场景化检测是通过边缘云管理服务器为边缘云控制服务器配置的目标应用程序得以实现。其中，边缘云管理服务器为边缘云控制服务器的管理平台，负责分配已部署在边缘云控制服务器中的SAAS化应用的算力、GPU、存储空间以及网络等资源。
图5为本申请实施例提供的一种场景化检测的实现示意图。如图5所示，采集终端采集目标区域的视频流数据后，边缘云系统中的UPF模块通过5G基站提供的5G网络将视频流数据转发至边缘云系统中的边缘云控制服务器，其中，边缘云控制服务器采用插件的方式形成有AI算法集成库，该AI算法集成库中部署有多个SAAS化应用，如图5中的A算法、B算法等等，比如，A算法用于进行人脸识别、人机识别、人员识别等，B算法用于进行安全服识别、安全帽识别、反光服识别等，C算法用于进行人员追踪算法，D算法用于进行位置检测等(图5中未示出C算法和D算法等)。诸类算法各自的应用程序均为SAAS化应用，被统称为目标应用程序。如图5所示，A算法为目标应用程序中的应用A，B算法为目标应用程序中的应用B等。各类算法与对应的应用之间通过服务接口连接。其中，目标应用程序用于实现场景化检测。比如，边缘云管理服务器可以根据视频流数据的视频画面，为边缘云控制服务器调度该视频流数据进行场景化检测所需的对应算法，通过调度出的相应算法也即目标应用程序中的对应应用对视频流数据进行AI分析，也就是对视频流数据进行采集该视频流数据的当前场景下的场景化检测，分析结果即为检测结果。另外，调度出的算法可进行叠加。边缘云管理服务器通过为边缘云控制服务器配置目标应用程序中的各应用，实现AI算法的智能调度与策略分发。
例如，在进行人车分流场景下的人车分流场景检测时，边缘云管理服务器根据人车分流场景下所采集到的视频流数据的视频画面，从AI算法集成库中为边缘云控制服务器调度出人脸识别算法、人机识别算法、电子区域划定算法、位置检测算法以及人员追踪算法等，并进行叠加，形成人车分流场景下的人车分流场景检测，用于判断行人是否处于人行道以及车辆是否处于机动车道。经过判断，若得到的检测结果为行人未处于人行道和/或车辆未处于机动车道，则表示进行人车分流场景的该目标区域存在安全异常行为。其中，边缘云管理服务器调度人脸识别算法、人机识别算法、电子区域划定算法、位置检测算法以及人员追踪算法各自对应的应用，即为边缘云控制服务器配置目标应用程序，以利用所配置的目标应用程序实现当前人车分流场景下的人车 分流场景检测，得到对应的检测结果。
S203a：UPF模块转发检测结果至显示模块，显示模块显示检测结果。
基于5G的安防监控系统中还可以包括有与边缘云系统连接的显示模块，在得到检测结果后，边缘云系统中的UPF模块转发检测结果至显示模块进行可视化显示，实现场景化检测的可视化，有利于安全异常行为的及时发现和处理。
可选地，S203b：当检测结果表示目标区域存在安全异常行为，报警模块触发警报装置并生成警报信息，显示模块显示警报信息。
基于5G的安防监控系统中还可以包括有与显示模块连接的报警模块，在当检测结果中表示目标区域存在安全异常行为时，报警模块可以触发警报装置并生成警报信息，显示模块可以可视化显示所生成的警报信息，警报装置可以为警灯、广播等设备，可以通过亮灯、语音播报的方式通报警报信息，对厂区内所发生的安全异常行为实现主动预警。
本申请实施例提供的基于5G的安防监控方法应用于基于5G的安防监控系统，安防监控系统包括通信连接的采集终端、5G基站以及边缘云系统。采集终端采集目标区域的视频流数据后，边缘云系统中的UPF模块通过5G基站提供的5G网络将视频流数据转发至边缘云系统中的边缘云控制服务器，边缘云控制服务器对视频流数据进行存储，边缘云系统中的边缘云管理服务器为边缘云控制服务器配置目标应用程序，边缘云控制服务器运行目标应用程序以对视频流数据进行场景化检测，得到检测结果。之后，边缘云系统中的UPF模块转发检测结果至显示模块，显示模块对检测结果进行可视化显示。并还可以当检测结果中表示目标区域存在安全异常行为时，与显示模块连接的报警模块触发警报装置并生成警报信息，显示模块可视化显示警报信息。在视频流数据不出厂的情况下根据视频流数据检测出目标区域是否存在安全异常，实现对目标区域的监控，缩短视频流数据的传输路径，降低了时延，并能够克服现有技术中视频分析功能存在滞后性的缺陷，还保证了视频流数据的保密性，有利于数据保护。同时，通过显示模块以及报警模块可以实现对目标区域内所存在的安全异常行为的主动预警，实现无盲点自动监控，提升了安防监控系统的数字化转型能力。
图6为本申请实施例提供的一种电子设备的结构示意图。如图6所示，该电子设备500可以包括：处理器501，以及与处理器501通信连接的存储器502。
存储器502，用于存放程序。具体地，程序可以包括程序代码，程序代码包括计算机执行指令。
存储器502可能包含高速RAM存储器，也可能还包括非易失性存储器 (NoN-volatile memory)，例如至少一个磁盘存储器。
处理器501用于执行存储器502存储的计算机执行指令，以实现基于5G的安防监控方法。
其中，处理器501可能是一个中央处理器(Central Processing Unit，简称为CPU)，或者是特定集成电路(Application Specific Integrated Circuit，简称为ASIC)，或者是被配置成实施本申请实施例的一个或多个集成电路。
可选地，存储器502既可以是独立的，也可以跟处理器501集成在一起。当存储器502是独立于处理器501之外的器件时，电子设备500，还可以包括：
总线503，用于连接处理器501以及存储器502。总线可以是工业标准体系结构(industry standard architecture，简称为ISA)总线、外部设备互连(peripheral component，PCI)总线或扩展工业标准体系结构(extended industry standard architecture，EISA)总线等。总线可以分为地址总线、数据总线、控制总线等，但并不表示仅有一根总线或一种类型的总线。
可选的，在具体实现上，如果存储器502和处理器501集成在一块芯片上实现，则存储器502和处理器501可以通过内部接口完成通信。
本申请还提供了一种计算机可读存储介质，该计算机可读存储介质可以包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random AccessMemory)、磁盘或者光盘等各种可以存储程序代码的介质，具体的，该计算机可读存储介质中存储有计算机执行指令，计算机执行指令用于上述实施例中的基于5G的安防监控方法。
本申请还提供了一种计算机程序产品，包括计算机执行指令，该计算机指令被处理器执行时实现上述实施例中的基于5G的安防监控方法。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本申请的其它实施方案。本申请旨在涵盖本申请的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本申请的一般性原理并包括本申请未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本申请的真正范围和精神由权利要求书指出。
应当理解的是，本申请并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本申请的范围仅由所附的权利要求书来限制。

Claims (10)

  1. 一种基于5G的安防监控系统，其特征在于，包括：采集终端、5G基站以及边缘云系统；
    所述采集终端与所述5G基站通信连接，所述采集终端用于在目标区域采集视频流数据；
    所述5G基站与所述边缘云系统通信连接，所述边缘云系统用于根据所述视频流数据获得检测结果，所述检测结果用于表征所述目标区域是否存在安全异常行为。
  2. 根据权利要求1所述的安防监控系统，其特征在于，所述边缘云系统包括UPF模块、边缘云控制服务器以及边缘云管理服务器；
    所述UPF模块用于通过5G网络将所述视频流数据从所述采集终端转发至所述边缘云控制服务器；
    所述边缘云控制服务器用于存储接收到的所述视频流数据，并对所述视频流数据进行场景化检测，得到所述检测结果；
    所述边缘云管理服务器用于为所述边缘云控制服务器配置目标应用程序，所述目标应用程序用于实现所述场景化检测。
  3. 根据权利要求2所述的安防监控系统，其特征在于，所述安防监控系统，还包括：SMF模块和加密虚拟网络模块；
    所述SMF模块通过N3接口和N4接口与所述UPF模块连接，所述SMF模块通过N2接口与所述加密虚拟网络模块连接，所述加密虚拟网络模块还连接至核心网端。
  4. 根据权利要求3所述的安防监控系统，其特征在于，所述安防监控系统，还包括与所述边缘云系统连接的显示模块；
    所述显示模块用于显示所述UPF模块转发的所述检测结果。
  5. 根据权利要求2-4任一项所述的安防监控系统，其特征在于，所述采集终端与所述5G基站之间通过5G模块通信连接；
    其中，所述5G模块包括内置于所述采集终端的5G模组或增设于所述采集终端与所述5G基站之间的5G网关。
  6. 根据权利要求4所述的安防监控系统，其特征在于，所述安防监控系统，还包括与所述显示模块连接的报警模块；
    当所述目标区域存在安全异常行为时，所述报警模块用于触发警报装置以及生成警报信息，所述显示模块还用于显示所述警报信息。
  7. 根据权利要求6所述的安防监控系统，其特征在于，所述场景化检测包括：人车分流场景检测、人员识别场景检测、人岗识别场景检测以及安全装备场景检测中的任意一种或几种。
  8. 一种基于5G的安防监控方法，其特征在于，应用于如权利要求1-7任一项所述的安防监控系统，所述安防监控系统包括通信连接的采集终端、5G基站以及边缘云系统；所述方法，包括：
    所述采集终端采集目标区域的视频流数据；
    所述边缘云系统基于5G基站提供的5G网络接收所述视频流数据，并根据所述视频流数据获得检测结果，所述检测结果用于表征所述目标区域是否存在安全异常行为。
  9. 一种电子设备，其特征在于，包括：处理器，以及与所述处理器通信连接的存储器；
    所述存储器存储计算机执行指令；
    所述处理器执行所述存储器存储的计算机执行指令，以实现如权利要求8所述的安防监控方法。
  10. 一种计算机可读存储介质，其上存储有计算机执行指令，其特征在于，所述计算机执行指令被处理器执行时实现权利要求8所述的安防监控方法。
PCT/CN2023/080249 2022-07-11 2023-03-08 基于5g的安防监控系统、方法、电子设备及存储介质 WO2024011926A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210810701.6A CN115188148A (zh) 2022-07-11 2022-07-11 基于5g的安防监控系统、方法、电子设备及存储介质
CN202210810701.6 2022-07-11

Publications (1)

Publication Number Publication Date
WO2024011926A1 true WO2024011926A1 (zh) 2024-01-18

Family

ID=83517373

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/080249 WO2024011926A1 (zh) 2022-07-11 2023-03-08 基于5g的安防监控系统、方法、电子设备及存储介质

Country Status (2)

Country Link
CN (1) CN115188148A (zh)
WO (1) WO2024011926A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118506287A (zh) * 2024-07-17 2024-08-16 江西博微新技术有限公司 区域安全监控方法、系统、可读存储介质及计算机

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115188148A (zh) * 2022-07-11 2022-10-14 卡奥斯工业智能研究院(青岛)有限公司 基于5g的安防监控系统、方法、电子设备及存储介质
CN115883789B (zh) * 2022-11-30 2023-12-01 中国铁道科学研究院集团有限公司 一种基于5g的铁路基础设施监测及信息安全防护的系统
CN115866717B (zh) * 2023-02-28 2023-08-11 广州市高科通信技术股份有限公司 一种基于5g专网的移动终端事务程序管理方法及系统

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111131794A (zh) * 2020-01-17 2020-05-08 软通动力信息技术有限公司 具备视频ai分析及5g通讯的边缘智慧终端设备
US20210133468A1 (en) * 2018-09-27 2021-05-06 Beijing Sensetime Technology Development Co., Ltd. Action Recognition Method, Electronic Device, and Storage Medium
CN112969057A (zh) * 2021-03-23 2021-06-15 中国大唐集团科学技术研究院有限公司华东电力试验研究院 一种5g mec分流的电力系统人员行为自动识别系统
CN214338041U (zh) * 2021-02-22 2021-10-01 郭义华 一种基于5g物联网的智能城市监控系统
CN113497832A (zh) * 2021-07-14 2021-10-12 中国联合网络通信集团有限公司 远程维护系统、方法及服务器
WO2021258195A1 (en) * 2020-06-22 2021-12-30 Canscan Softwares And Technologies Inc. Image-based system and method for shipping container management with edge computing
CN113989625A (zh) * 2021-12-13 2022-01-28 上海华谊信息技术有限公司 基于边缘计算的图像识别方法、装置、设备及存储介质
CN115188148A (zh) * 2022-07-11 2022-10-14 卡奥斯工业智能研究院(青岛)有限公司 基于5g的安防监控系统、方法、电子设备及存储介质

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3843438A4 (en) * 2018-10-30 2021-09-22 Huawei Technologies Co., Ltd. KEY PRODUCTION PROCESS, DEVICE AND SYSTEM
WO2020127148A1 (en) * 2018-12-21 2020-06-25 Telefonaktiebolaget Lm Ericsson (Publ) User data traffic handling
CN112422701B (zh) * 2019-08-20 2022-05-24 华为技术有限公司 域名系统查询的方法和通信装置
CN113541989B (zh) * 2020-04-17 2023-05-09 中国移动通信有限公司研究院 一种网络切片检测方法、装置和存储介质
CN111698470B (zh) * 2020-06-03 2021-09-03 中科民盛安防(河南)有限公司 一种基于云边协同计算的安防视频监控系统及其实现方法
CN112040189B (zh) * 2020-09-01 2022-06-24 浙江大华技术股份有限公司 前端设备的监控方法及系统、存储介质
CN112907867B (zh) * 2021-01-22 2022-10-25 深圳英飞拓科技股份有限公司 一种基于图像识别的预警方法、装置及服务器

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20210133468A1 (en) * 2018-09-27 2021-05-06 Beijing Sensetime Technology Development Co., Ltd. Action Recognition Method, Electronic Device, and Storage Medium
CN111131794A (zh) * 2020-01-17 2020-05-08 软通动力信息技术有限公司 具备视频ai分析及5g通讯的边缘智慧终端设备
WO2021258195A1 (en) * 2020-06-22 2021-12-30 Canscan Softwares And Technologies Inc. Image-based system and method for shipping container management with edge computing
CN214338041U (zh) * 2021-02-22 2021-10-01 郭义华 一种基于5g物联网的智能城市监控系统
CN112969057A (zh) * 2021-03-23 2021-06-15 中国大唐集团科学技术研究院有限公司华东电力试验研究院 一种5g mec分流的电力系统人员行为自动识别系统
CN113497832A (zh) * 2021-07-14 2021-10-12 中国联合网络通信集团有限公司 远程维护系统、方法及服务器
CN113989625A (zh) * 2021-12-13 2022-01-28 上海华谊信息技术有限公司 基于边缘计算的图像识别方法、装置、设备及存储介质
CN115188148A (zh) * 2022-07-11 2022-10-14 卡奥斯工业智能研究院(青岛)有限公司 基于5g的安防监控系统、方法、电子设备及存储介质

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118506287A (zh) * 2024-07-17 2024-08-16 江西博微新技术有限公司 区域安全监控方法、系统、可读存储介质及计算机

Also Published As

Publication number Publication date
CN115188148A (zh) 2022-10-14

Similar Documents

Publication Publication Date Title
WO2024011926A1 (zh) 基于5g的安防监控系统、方法、电子设备及存储介质
US20220215748A1 (en) Automated camera response in a surveillance architecture
EP3867841B1 (en) System for controlling and managing a process within an environment using artificial intelligence techniques and relative method
CN202772924U (zh) 智能云卡口系统
CN103578240B (zh) 一种基于物联网的安防服务网
WO2019052266A1 (zh) 一种智能物联网管理系统、方法以及服务器
WO2020019818A1 (zh) 一种数据传输方法和装置
CN203260195U (zh) 基于智能终端的交通违章公众监督系统
CN105187771A (zh) 一种厂级综合监管平台
EP2834776A1 (en) Recognition-based security
KR102119721B1 (ko) 지능형 에지장치 및 그 장치의 구동방법
SG191954A1 (en) An integrated intelligent server based system and method/systems adapted to facilitate fail-safe integration and /or optimized utilization of various sensory inputs
CN110288837B (zh) 一种多摄像机协同的违停车牌识别方法及装置
GB2455837A (en) Co-operative camera surveillance method
CN103853143A (zh) 一种应用于供电系统输电线路的远程无线监测网络系统
CN102281431A (zh) 交互式智能视频分析与应急指挥调度系统
CN203849870U (zh) 基于无线网络的车流监测与信号灯智能控制系统
CN110033601A (zh) 一种基于WF-IoT的物联网消防报警系统和方法
CN111371895A (zh) 一种高速公路隧道用机电设备管理系统及其方法
WO2013131189A1 (en) Cloud-based video analytics with post-processing at the video source-end
CN110568834A (zh) 基于物联网与大数据运营的智慧建筑集成管理平台
CN106412127A (zh) 一种IPv6与IPv4双栈兼容的道路监控视频分析系统
CN106506589A (zh) 一种机器人集群方法及系统
CN102457483A (zh) 一种视频监控前端及其向物联网上报数据的方法
CN212463305U (zh) 边缘计算装置以及边缘计算系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23838428

Country of ref document: EP

Kind code of ref document: A1