A distributed edge computing police video recognition security system and implementation method

Abstract

The present invention discloses a distributed edge computing police video recognition security system and an implementation method, wherein the security system is used for distributed networking installation in a community, and comprises a 5G routing terminal, a cloud data center and multiple edge computing security modules, wherein: the cloud data center is connected to the 5G routing terminal via a 5G communication link; each edge computing security module comprises an edge computing module, a storage disk array, a UPS power supply, a POE switch, multiple cameras and an AP wireless bridge; multiple edge computing security modules are connected via their respective AP wireless bridge data connections, and the 5G routing terminal is connected to the POE switch of one of the multiple edge computing security modules, so as to exchange data between all edge computing security modules and the cloud data center.

Description

Technical Field

[0001] The present invention relates to the field of security technology, and in particular to a distributed edge computing police video recognition security system and an implementation method thereof. Background Art

[0002] With the continuous development of information technology and the gradual advancement of smart city construction, more and more surveillance cameras are installed in the streets and alleys to monitor every corner of the city. The problem that follows is how to quickly analyze and process the massive video data generated every day. According to the traditional method, all surveillance cameras need to transmit the video data they generate in real time to the data center of the central monitoring system. Large-scale data centers are used to process and store massive amounts of data every day. For security reasons, data centers often need to occupy an independent space, and the construction of surveillance video networks requires the installation of a large number of network cables or high-power wireless communication equipment. The overall realization requires a lot of manpower and material resources in the construction of large-scale data centers and huge video transmission networks, which is a major challenge for smart city builders.

[0003] In addition, when investigating a case, the police usually need to retrieve a large amount of raw video surveillance data from the data center, and then manually screen it to find key information and clues. This is labor-intensive and time-consuming, and may lead to the loss of key opportunities for investigating the case. Currently, using AI algorithms to quickly search and identify video content can improve the efficiency and accuracy of video information retrieval, but searching through the massive data in the data center is also time-consuming and labor-intensive.

[0004] The application of edge computing technology can solve the various problems we are currently facing. Applying edge computing to the construction of security systems can greatly save infrastructure costs for the construction of smart cities and improve the timeliness and convenience of video information retrieval. Summary of the invention

[0005] In order to address the shortcomings of the prior art, the present invention provides a distributed edge computing police video recognition security system, which modularizes edge computing and flexibly networks and installs it to break through the distance limitations of traditional network cable transmission and reduce the manpower and material costs of initial infrastructure construction. At the same time, through distributed processing within the community and 5G transmission, the computing and storage pressure of the remote data center is reduced and the data transmission efficiency is improved.

[0006] In order to achieve the above-mentioned object, the present invention provides a distributed edge computing police video recognition security system for distributed networking installation in a community, which includes: a 5G routing terminal, a cloud data center and multiple edge computing security modules, wherein:

[0007] The cloud data center and the 5G routing terminal are connected via a 5G communication link;

[0008] Each edge computing security module includes an edge computing module, a storage disk array, a UPS power supply, a POE switch, multiple cameras and an AP wireless bridge, among which:

[0009] The edge computing module is connected to the storage disk array data, and is used to process and identify multiple channels of raw video data, and store the raw video data in the storage disk array in real time;

[0010] UPS power supply, electrically connected to the edge computing module, used to power the system during short-term power outages;

[0011] Each camera is connected to the POE switch via a network cable;

[0012] The POE switch is connected to the edge computing module via a Gigabit Ethernet cable and is used to transmit the video data collected by each camera to the edge computing module;

[0013] AP wireless bridge, connected to the POE switch via a network cable, for networking and transmitting data via wireless communication; and

[0014] Multiple edge computing security modules are connected through their respective AP wireless bridge data connections, and the 5G routing terminal is connected to the POE switch of one of the multiple edge computing security modules to exchange data between all edge computing security modules and the cloud data center.

[0015] In one embodiment of the present invention, the edge computing module performs processing and recognition specifically to capture effective information from the original video data collected by the camera, and transmits it to the cloud data center through the AP wireless bridge and the 5G routing terminal in the system, wherein the effective information includes facial information, license plate information and body feature information.

[0016] In one embodiment of the present invention, the storage disk array is a hard disk storage array having multiple large-capacity surveillance-grade hard disks built therein, and the storage capacity of the storage disk array is capable of storing video data for ≥30 days.

[0017] In one embodiment of the present invention, the POE switch is a monitoring network switch that supports POE power supply.

[0018] In one embodiment of the present invention, each camera is a network surveillance camera, and the network surveillance camera adopts POE network cable power supply technology. The POE switch simultaneously supplies power and transmits data to each camera through the network cable.

[0019] In one embodiment of the present invention, the AP wireless bridge adopts POE power supply technology, and the POE switch simultaneously supplies power and transmits data to the AP wireless bridge.

[0020] In one embodiment of the present invention, the 5G routing terminal adopts POE power supply technology, and the POE switch simultaneously supplies power and transmits data to the 5G routing terminal.

[0021] In one embodiment of the present invention, the 5G routing terminal is connected to a POE switch of one of the multiple edge computing security modules as follows: the edge computing security module connected to the 5G routing terminal is installed in an area where the 5G signal strength is high and the transmission rate is fast and has been determined through detection in the community where the system is located.

[0022] In one embodiment of the present invention, the data connection method between multiple edge computing security modules through their respective AP wireless bridges can be replaced by a wired network, 4G or 5G network connection method according to the actual networking environment, wherein the wired network connection method includes copper cable or optical fiber connection, and the 4G or 5G network connection method includes 4G or 5G router, 4G or 5G gateway device connection.

[0023] In order to achieve the above object, the present invention also provides a distributed edge computing police video recognition security implementation method, which includes the following steps:

[0024] S1: Set the number and location of edge computing security modules in the target community according to the needs of the community streets, and the number and location of cameras included in each edge computing security module, and install the network according to the determined number and location;

[0025] S2: After the system is enabled, multiple cameras of each edge computing security module transmit the collected raw video data to the corresponding edge computing module through the corresponding POE switch;

[0026] S3: Each edge computing module stores the raw video data collected by each camera connected to it into the corresponding storage disk array in real time;

[0027] S4: Each edge computing module processes the raw video data collected by each camera connected to it, identifies the valid information in the video data, and transmits the valid information to the cloud data center through the corresponding AP wireless bridge and the 5G routing terminal in the system. The valid information includes facial information, license plate information, body feature information, etc.

[0028] S5: The cloud data center stores and analyzes the effective information transmitted by S4. If the original video data needs to be retrieved, the cloud data center obtains the original video data content from the corresponding storage disk array in real time through the 5G routing terminal and the corresponding AP wireless bridge;

[0029] S6: During the execution of S2 to S5, if a short power outage occurs, the UPS power supply in the corresponding edge computing security module will automatically start and supply power to all components in the corresponding edge computing security module.

[0030] The present invention realizes distributed processing in the community through networking of AP wireless bridges, uses 5G communication technology to achieve connection with the cloud data center, and sets the processing and recognition of the original video data at the edge. Compared with the prior art, the present invention has the following advantages:

[0031] (1) Through wireless networking, the distance limitation of traditional network cable transmission is broken, and flexible networking and installation are achieved;

[0032] (2) Based on the concept of edge computing, there is no need to send a large amount of raw data to a remote data center, reducing the computing and storage pressure of the remote data center;

[0033] (3) Modular integrated installation reduces the construction difficulty of monitoring network construction and the cost of a large amount of initial infrastructure materials and manpower. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art are briefly introduced below.

[0035] Figure 1 This is the architecture diagram of the distributed edge computing security system of the present invention;

[0036] Figure 2 This is a schematic diagram of the structure of a single edge computing security module in one embodiment of the present invention. DETAILED DESCRIPTION

[0037] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings in the embodiments of the present invention.

[0038] Figure 1 This is the architecture diagram of the distributed edge computing security system of the present invention, as shown in Figure 1 As shown, the present invention provides a distributed edge computing police video recognition security system for distributed networking installation in a community, which includes a 5G routing terminal, a cloud data center and multiple edge computing security modules, wherein:

[0039] The cloud data center is connected to the 5G routing terminal through a 5G communication link. 5G (5th generation mobile networks or 5th-Generation) is the fifth generation of mobile communication technology, which has high transmission rate, short delay and large network capacity, and is suitable for the transmission of large amounts of data such as high-definition video.

[0040] Figure 2 FIG. 1 is a schematic diagram of the structure of a single edge computing security module in an embodiment of the present invention. Figure 2 As shown, each edge computing security module includes an edge computing module, a storage disk array, a UPS (Uninterruptible Power Supply) power supply (i.e., an uninterruptible power supply), a POE (Power Over Ethernet) switch (a network switch that can provide DC power supply), multiple cameras and an AP (Access Point) wireless bridge, wherein:

[0041] The edge computing module is connected to the storage disk array data, and is used to process and identify multiple channels of raw video data, and store the raw video data in the storage disk array in real time;

[0042] UPS power supply, electrically connected to the edge computing module, used to power the system during short-term power outages;

[0043] Each camera is connected to the POE switch via a network cable;

[0044] The POE switch is connected to the edge computing module via a Gigabit Ethernet cable and is used to transmit the video data collected by each camera to the edge computing module;

[0045] AP wireless bridge, connected to the POE switch via a network cable, is used to network and transmit data via wireless communication;

[0046] Multiple edge computing security modules are connected through their respective AP wireless bridge data connections, and the 5G routing terminal is connected to the POE switch of one of the multiple edge computing security modules to exchange data between all edge computing security modules and the cloud data center.

[0047] In this embodiment, the edge computing module performs processing and identification specifically to capture effective information from the original video data collected by the camera, and transmits it to the cloud data center through the AP wireless bridge and the 5G routing terminal in the system, where the effective information includes facial information, license plate information, body feature information, etc.

[0048] In this embodiment, the storage disk array is a hard disk storage array, which has multiple large-capacity monitoring-level hard disks built in. The storage capacity of the storage disk array is capable of storing video data for ≥30 days.

[0049] In this embodiment, the POE switch is a monitoring network switch that supports POE power supply.

[0050] In this embodiment, each camera is a network surveillance camera, which adopts POE network cable power supply technology, and the POE switch simultaneously supplies power and transmits data to each camera through the network cable.

[0051] In this embodiment, the AP wireless bridge adopts POE power supply technology, and the POE switch simultaneously supplies power and transmits data to the AP wireless bridge.

[0052] In this embodiment, the 5G routing terminal adopts POE power supply technology, and the POE switch simultaneously supplies power and transmits data to the 5G routing terminal to reduce wiring workload and save material costs and time costs.

[0053] In this embodiment, the 5G routing terminal is connected to a POE switch of one of the multiple edge computing security modules as follows: the connected edge computing security module is set in an area where the 5G signal strength is high and the transmission rate is fast and determined through detection within the cell where the system is located.

[0054] In this embodiment, the data connection method between multiple edge computing security modules through their respective AP wireless bridges can be replaced by a wired network, 4G (fourth-generation mobile communication technology) or 5G network connection method according to the actual networking environment, wherein the wired network connection method includes copper cable, optical fiber and other connections, and the 4G or 5G network connection method includes 4G or 5G routers, 4G or 5G gateways and other device connections.

[0055] In this embodiment, each edge computing module can process multiple video stream data at the same time, and an edge computing security module can cover several monitoring points. The number of each camera and the number of edge computing security modules in the community can be set according to the different monitoring placement requirements of the community streets. Each edge computing security module uses an AP wireless bridge connected by POE to achieve data intercommunication, forming a complete video surveillance communication network. Each AP wireless bridge can achieve a transmission distance of hundreds of meters to thousands of meters according to its different power and performance, which is enough to form a fully covered area. When all edge computing security systems in the area are networked, select an area with a good 5G signal and a high transmission rate to install a 5G routing terminal, and upload all valid information collected by the edge computing security module to the cloud server for storage and analysis through the 5G routing terminal. If the original video data needs to be retrieved, the cloud data center can access the original video data content in each storage disk array in real time through the 5G communication link. In addition, each edge computing security module is equipped with a UPS power supply as a backup power supply. If a short-term power outage occurs, the backup power supply is automatically enabled to ensure the normal operation of the system within a certain period of time.

[0056] The present invention also provides a method for implementing a distributed edge computing police video recognition security system, which comprises the following steps:

[0057] S1: Set the number and location of edge computing security modules in the target community according to the needs of the community streets, and the number and location of cameras included in each edge computing security module, and install the network according to the determined number and location;

[0058] S2: After the system is enabled, multiple cameras of each edge computing security module transmit the collected raw video data to the corresponding edge computing module through the corresponding POE switch;

[0059] S3: Each edge computing module stores the raw video data collected by each camera connected to it into the corresponding storage disk array in real time;

[0060] S4: Each edge computing module processes the raw video data collected by each camera connected to it, identifies the valid information in the video data, and transmits the valid information to the cloud data center through the corresponding AP wireless bridge and the 5G routing terminal in the system. The valid information includes facial information, license plate information, body feature information, etc.

[0061] S5: The cloud data center stores and analyzes the effective information transmitted by S4. If the original video data needs to be retrieved, the cloud data center obtains the original video data content from the corresponding storage disk array in real time through the 5G routing terminal and the corresponding AP wireless bridge;

[0062] S6: During the execution of S2 to S5, if a short power outage occurs, the UPS power supply in the corresponding edge computing security module will automatically start and supply power to all components in the corresponding edge computing security module.

[0063] The present invention converts the way of uniformly networking all cameras in the prior art and then using the data center to perform video processing into distributed processing within the community, and networks through wireless networks, which greatly reduces the construction difficulty of monitoring network construction and the computing pressure of cloud servers. Since the original video data of the present invention is stored at the edge, the processing and recognition of the original video data are also completed at the edge, which reduces the amount of data transmission compared to the prior art. At the same time, by using 5G communication technology and AP wireless bridges, the entire system networking mode is also flexible and has the ability to expand infinitely.

[0064] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A distributed edge computing police video recognition security system, used for distributed networking installation in a community, including a 5G routing terminal, a cloud data center and multiple edge computing security modules, in: Each edge computing security module includes an edge computing module, a storage disk array, a UPS power supply, a POE switch, multiple cameras and an AP wireless bridge, and is characterized by: The edge computing module is connected to the storage disk array data, and is used to process and identify multiple channels of original video data, and store the original video data in the storage disk array in real time. The storage disk array is a hard disk storage array, which has multiple large-capacity monitoring-level hard disks built in; The UPS power supply is electrically connected to the edge computing module and is used to power the system during a short power outage; Each camera is connected to the POE switch through a network cable, each camera is a network surveillance camera, the network surveillance camera adopts POE network cable power supply technology, and the POE switch simultaneously supplies power and transmits data to each camera through the network cable; The POE switch is a monitoring network switch that supports POE power supply, which is connected to the edge computing module via a gigabit network cable and is used to transmit the video data collected by each camera to the edge computing module; The 5G routing terminal adopts POE power supply technology, and the POE switch simultaneously supplies power and transmits data to the 5G routing terminal; The AP wireless bridge is connected to the POE switch via a network cable, and is used to form a network and transmit data via wireless communication. The AP wireless bridge adopts POE power supply technology, and the POE switch simultaneously supplies power to the AP wireless bridge and transmits data; and Multiple edge computing security modules are connected through their respective AP wireless bridge data to form a video surveillance communication network. The 5G routing terminal is connected to the POE switch of one of the multiple edge computing security modules. The cloud data center is connected to the 5G routing terminal through a 5G communication link to exchange data between all edge computing security modules and the cloud data center. This is achieved through the following steps: S1: Set the number and location of edge computing security modules in the target community according to the needs of the community streets, and the number and location of cameras included in each edge computing security module, and install the network according to the determined number and location; S2: After the system is enabled, multiple cameras of each edge computing security module transmit the collected raw video data to the corresponding edge computing module through the corresponding POE switch; S3: Each edge computing module stores the raw video data collected by each camera connected to it into the corresponding storage disk array in real time; S4: Each edge computing module processes the raw video data collected by each camera connected to it, identifies valid information in the video data, and transmits the valid information to the cloud data center through the corresponding AP wireless bridge and the 5G routing terminal in the system; S5: The cloud data center stores and analyzes the valid information transmitted by S4. If the original video data needs to be retrieved, the cloud data center obtains the original video data from the corresponding storage disk array in real time through the 5G routing terminal and the corresponding AP wireless bridge; S6: During the execution of S2 to S5, if a short power outage occurs, the UPS power supply in the corresponding edge computing security module will automatically start and supply power to all components in the corresponding edge computing security module.

2. The security system according to claim 1, It is characterized in that The edge computing module performs processing and identification specifically to capture valid information from the original video data collected by any camera, and transmits it to the cloud data center through the AP wireless bridge and the 5G routing terminal in the system, wherein the valid information includes facial information, license plate information and body feature information.

3. The security system according to claim 1, It is characterized in that The storage capacity of the storage disk array is capable of storing video data for ≥30 days.

4. The security system according to claim 1, It is characterized in that The 5G routing terminal is connected to the POE switch of one of the multiple edge computing security modules as follows: the edge computing security module connected to the 5G routing terminal is installed in an area where the 5G signal strength is high and the transmission rate is fast and has been determined through detection in the community where the system is located.

5. The security system according to claim 1, It is characterized in that The data connection method between multiple edge computing security modules through their respective AP wireless bridges can be replaced by a wired network, 4G or 5G network connection method according to the actual networking environment, wherein the wired network connection method includes copper cable or optical fiber connection, and the 4G or 5G network connection method includes 4G or 5G router, 4G or 5G gateway device connection.

Images