Real-time intelligent video analysis system based on edge computing device

Abstract

The invention belongs to the technical field of intelligent security and protection. The invention provides a real-time intelligent video analysis system based on edge computing equipment. According to the embodiment of the invention, real-time processing and intelligent analysis of the video data are carried out on the edge computing intelligent box, so that the real-time performance and the response speed of the system are effectively improved, and the problems of network delay and bandwidth limitation in a traditional cloud computing architecture are solved; multi-protocol cooperative work is adopted, efficient transmission of video stream data, configuration information, control instructions and analysis results is achieved, and simplicity and convenience of data management are ensured by using a JSON data format; a plurality of built-in algorithm detection and recognition models can carry out target detection and behavior recognition in real time and generate an analysis result, so that the requirements on efficient and accurate analysis in intelligent security and industrial production are met; a user can select different transmission modes as required and configure an uploading target address, so that the data can be accurately transmitted to a specified platform in real time.

Description

Background Art

[0002] With the rapid development of computer vision technology, intelligent video analysis has gradually become one of the key applications in various industries, especially important in the fields of intelligent security and industrial production. In intelligent security, real-time analysis of surveillance videos can achieve personnel intrusion detection, abnormal behavior recognition, and fire and smoke warnings, effectively improving the efficiency of public security management; while in industrial production, intelligent video analysis can be used to monitor the operating status of equipment, quickly detect abnormalities, and real-time identify employees' safe behaviors (such as not wearing safety helmets or entering dangerous areas), ensuring production safety and efficiency. However, most traditional video analysis systems rely on cloud computing architectures, and video data needs to be transmitted over the network to the cloud for processing. Although this method has powerful computing capabilities, it is limited by issues such as network bandwidth, transmission latency, and data privacy, and it is difficult to meet the high requirements for real-time and reliability in the above scenarios.

[0003] In recent years, the rise of edge computing technology has provided a new solution for intelligent video analysis. By performing calculations and processing on edge devices close to the data source, edge computing can not only significantly reduce the burden of data transmission but also significantly improve real-time performance and response speed, especially suitable for intelligent security and industrial production scenarios with extremely high timeliness requirements. However, current edge computing systems still face challenges in terms of computing power, power consumption optimization, and flexibility of model deployment. For example, when running complex deep learning models, the hardware resource limitations of edge devices often become performance bottlenecks.

[0004] In addition, existing edge computing video analysis systems lack a unified model management and efficient task allocation mechanism. Especially in an environment with multiple cameras and multiple tasks, the performance drops significantly. At the same time, how to balance low power consumption and low cost while meeting the requirements of high-precision analysis remains a difficult point in the current technological development.

[0005] Therefore, it is necessary to improve one or more problems existing in the above-mentioned related technical solutions.

[0006] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of the present disclosure, and thus may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the embodiments of the present disclosure is to provide a real-time intelligent video analysis system based on edge computing devices, thereby at least to some extent overcoming one or more problems caused by the limitations and defects of related technologies.

[0008] According to the first aspect of the embodiments of the present disclosure, there is provided a real-time intelligent video analysis system based on edge computing devices, the system includes: A switch, an edge computing module, a video perception module, and an event analysis module; wherein, The video perception module is used to obtain the RTSP video stream data sent by the camera in real time, and transmit the RTSP video stream data to the edge computing module through the switch; The edge computing module is used to analyze and process the RTSP video stream data to obtain JSON data, and transmit the JSON data to the event analysis module through the switch; The event analysis module is used to perform event analysis on the JSON data to obtain an event video, and perform remote visual video management on the event video.

[0009] Furthermore, the system further includes: A data reporting module, which is used to select the data reporting transmission mode according to actual needs, and select the corresponding video stream for data reporting according to the camera.

[0010] Furthermore, the video perception module and the switch are interconnected through the RTSP protocol, the edge computing module and the switch are interconnected through the RTSP protocol, the HTTP protocol, and the WebSocket protocol, the event analysis module and the switch perform data transmission through the HTTP protocol, and the data reporting module and the switch are interconnected through the HTTP protocol and the WebSocket protocol.

[0011] Furthermore, the edge computing module includes: A number of edge computing intelligent boxes; wherein, Each of the edge computing intelligent boxes is built with a program running startup program and a monitoring script program. The program running startup program and the monitoring script are used to automatically start and monitor the running status of each program of the system, ensure that the system remains efficient and stable during operation, and can give an alarm or automatically recover in case of a failure; Each of the edge computing intelligent boxes is installed with an expandable hard disk, which is used to store the RTSP video stream data, the JSON data, and system logs, and supports storage expansion according to actual needs to meet the needs of large-scale video analysis and data storage.

[0012] Furthermore, the edge computing intelligent box obtains the real-time RTSP video stream data from the video perception module, and performs analysis and inference according to a preset algorithm model; wherein, the process of the analysis and inference includes performing object detection and behavior recognition analysis operations on the images in the RTSP video stream data to generate an analysis result in real time and perform decision-making processing.

[0013] Further, the edge computing intelligent box and the switch are interconnected through the RTSP protocol, the HTTP protocol, and the WebSocket protocol; among them, The RTSP protocol is used for the edge computing intelligent box to obtain the RTSP video stream data from the switch. The HTTP protocol and the WebSocket protocol are used for real-time transmission of configuration information, control instructions, and algorithm analysis results. Moreover, the data transmitted by the edge computing intelligent box to the switch is in the JSON data format.

[0014] According to the second aspect of the embodiments of the present disclosure, a real-time intelligent video analysis method based on an edge computing device is provided. The method includes: Obtain the RTSP video stream data sent by the camera in real time, and transmit the RTSP video stream data to the edge computing module through the switch; Analyze and process the RTSP video stream data to obtain JOSN data, and transmit the JOSN data to the event analysis module through the switch; Perform event analysis on the JOSN data to obtain an event video, and perform remote visual video management on the event video.

[0015] The technical solutions provided by the embodiments of the present disclosure may include the following beneficial effects: In the embodiments of the present disclosure, through the above real-time intelligent video analysis system based on an edge computing device, by performing real-time processing and intelligent analysis of video data on the edge computing intelligent box, the real-time performance and response speed of the system are effectively improved, and the problems of network latency and bandwidth limitation existing in the traditional cloud computing architecture are solved; multiple protocols work together, including RTSP, HTTP, and WebSocket protocols, to achieve efficient transmission of video stream data, configuration information, control instructions, and analysis results. Using the JSON data format ensures the simplicity of data management; the built-in multiple algorithm detection and recognition models can perform target detection and behavior recognition in real time and generate analysis results, meeting the requirements for efficient and accurate analysis in intelligent security and industrial production; users can select different transmission modes according to needs and configure the upload target address to ensure that data can be transmitted to the specified platform in real time and accurately.

[0016] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings here are incorporated into and form a part of this specification, showing embodiments consistent with the present disclosure, and are used together with the specification to explain the principles of the present disclosure. Obviously, the accompanying drawings in the following description are only some embodiments of the present disclosure, and for those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0018] Figure 1 Schematic diagram showing a real-time intelligent video analysis system based on an edge computing device in an exemplary embodiment of the present disclosure; Figure 2 Schematic diagram showing the module connection of a real-time intelligent video analysis system based on an edge computing device in an exemplary embodiment of the present disclosure; Figure 3 Step diagram showing a real-time intelligent video analysis method based on an edge computing device in an exemplary embodiment of the present disclosure; Figure 4 Schematic diagram showing a storage medium in an exemplary embodiment of the present disclosure; Figure 5 Schematic diagram showing an electronic product in an exemplary embodiment of the present disclosure. Detailed implementation manners

[0019] Example embodiments will now be described more fully with reference to the accompanying drawings. However, the example embodiments can be implemented in various forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided so that this disclosure will be more thorough and complete, and will fully convey the concept of the example embodiments to those skilled in the art. The features, structures, or characteristics described can be combined in any suitable manner in one or more embodiments.

[0020] In addition, the accompanying drawings are only schematic illustrations of the present disclosure and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0021] In this example embodiment, a real-time intelligent video analysis system based on an edge computing device is first provided. This system can be applied to a terminal device, such as a mobile terminal like a mobile phone, personal digital assistant, laptop computer, tablet computer, smart watch, etc.

Adjust flexibly according to the specific situation, such as if the terminal device is a server, etc.

[0022] Through the above real-time intelligent video analysis system based on edge computing devices, by performing real-time processing and intelligent analysis of video data on the edge computing intelligent box, the real-time performance and response speed of the system are effectively improved, and the problems of network latency and bandwidth limitation existing in the traditional cloud computing architecture are solved; multiple protocols are used to work together, including RTSP, HTTP, and WebSocket protocols, to achieve efficient transmission of video stream data, configuration information, control instructions, and analysis results, and the use of the JSON data format ensures the simplicity of data management; built-in multiple algorithm detection and recognition models can perform target detection and behavior recognition in real time and generate analysis results to meet the requirements of efficient and accurate analysis in intelligent security and industrial production; users can select different transmission modes according to needs and configure the upload target address to ensure that data can be transmitted to the specified platform in real time and accurately.

[0023] Next, reference will be made to Figures 1 to 2 to describe each step of the above method in the exemplary embodiment in more detail.

[0024] In one embodiment, the real-time intelligent video analysis system based on edge computing devices includes a switch, a video perception module, an edge computing module, an event analysis module, and a data reporting module. The video perception module is connected to the switch through the RTSP protocol, the edge computing module is connected to the switch through the RTSP protocol, HTTP protocol, and WebSocket protocol, the event analysis module transmits data to the switch through the HTTP protocol, and the data reporting module is connected to the switch through the HTTP protocol and WebSocket protocol.

[0025] In one embodiment, the video perception module includes a network bullet camera, a network dome camera, and a network PTZ camera. The video perception module has the RTSP protocol built in, and is configured to obtain RTSP video stream data sent by a camera in real time, and transmit the obtained video stream data to the edge computing module through the switch for intelligent analysis and processing.

[0026] In one embodiment, the edge computing module includes an edge computing intelligent box. The edge intelligent box is built-in with programs such as a program running startup and monitoring script. The program running startup and monitoring script is used to automatically start and monitor the running status of various programs in the system, ensure the system remains efficient and stable during operation, and be able to give an alarm or automatically recover in case of a failure; The edge computing intelligent box is installed with an expandable hard disk, which is used to store information such as video stream data, analysis results, and system logs, supports storage expansion according to actual needs, and meets the requirements of large-scale video analysis and data storage.

[0027] In one embodiment, the edge computing intelligent box obtains real-time RTSP video stream data from the video perception module and performs analysis and inference according to a preset algorithm model. The analysis and inference process includes operations such as object detection and behavior recognition analysis on the images in the video stream, and generates analysis results in real time and performs decision-making processing.

[0028] In one embodiment, the edge computing box is interconnected with the switch through the RTSP protocol, HTTP protocol, and WebSocket protocol. The RTSP protocol is used for the edge computing intelligent box to obtain RTSP video stream data from the switch. The HTTP protocol and WebSocket protocol are used for real-time transmission of configuration information, control instructions, and algorithm analysis results. And the data transmitted by the edge computing box to the switch is in the JSON data format.

[0029] In one embodiment, the event analysis module is remotely accessed and data is transmitted with the switch through the HTTP protocol. The event analysis module is used for remote visual video management, specifically including video management, algorithm management, and alarm query. Video management allows users to preview and edit multiple video streams in real time; Algorithm management allows users to configure and schedule preset detection and recognition models. Users can draw polygon detection areas on the video interface, set the algorithm analysis extraction frame rate and model detection threshold for each video stream; Alarm query allows users to query historical alarm records and analyze them to determine the type, time, and camera information of the alarm.

[0030] In one embodiment, the data reporting module is interconnected with the switch through the HTTP protocol and the WebSocket protocol. Users can select the data reporting transmission mode according to actual needs and select the corresponding video stream for data reporting according to specific cameras. Users can configure the WebSocket address and HTTP address and report data to the specified third business platform through these addresses.

[0031] In a specific embodiment, refer to Figure 1 and Figure 2As shown in the figure, a real-time intelligent video analysis system based on edge computing devices includes a switch 1, an edge computing module 2, a video perception module 3, an event analysis module 4, and a data reporting module 5. The video perception module 2 is connected to the switch 1 through the RTSP protocol. The edge computing module 2 is connected to the switch 1 through the RTSP protocol, the HTTP protocol, and the WebSocket protocol. The event analysis module 4 transmits data to the switch 1 through the HTTP protocol. The data reporting module 5 is interconnected with the switch 1 through the HTTP protocol and the WebSocket protocol.

[0032] The video perception module 3 includes different types of camera devices such as network bullet cameras, network dome cameras, and network PTZ cameras. It has the RTSP protocol built-in and is used to obtain the RTSP video stream data sent by the cameras in real time. These cameras can provide high-definition video surveillance images and support real-time monitoring from multiple angles and wide fields of view. The obtained video stream data is efficiently transmitted through the switch 1 and finally sent to the edge computing module 2 for intelligent analysis and processing. During the transmission process, the RTSP protocol ensures the low latency, high reliability, and real-time nature of the video data, guaranteeing the stability and response speed of the system when processing high-definition video streams. In this way, the video perception module 3 can provide accurate real-time video data support in various application scenarios, providing a reliable data source for subsequent intelligent analysis and decision-making.

[0033] The edge computing module 2 includes an edge computing intelligent box. This intelligent box has programs such as program running startup and monitoring scripts built-in. It can ensure the high efficiency and stability of the system during long-term operation by automatically starting and real-time monitoring the running status of various programs in the system. The program running startup and monitoring scripts have a self-repair function. Once a system failure or abnormality is detected, it can issue an alarm in a timely manner and take automatic recovery measures to ensure the continuity and reliability of the system. In addition, the edge computing intelligent box is also equipped with an expandable hard disk for storing a large amount of real-time video stream data, analysis results, system logs, and other information. The expandable design of the hard disk enables the system to flexibly expand the storage capacity according to actual needs, meeting the requirements of large-scale video analysis and massive data storage, especially suitable for scenarios that require processing and storing long-term video surveillance data. With this configuration, the edge computing module 2 not only has powerful data processing capabilities but also can achieve efficient intelligent video analysis and storage management while ensuring data security and integrity.

[0034] The edge computing intelligent box included in the edge computing module 2 can obtain real-time RTSP video stream data from the video perception module 3 and perform intelligent analysis and inference based on preset deep learning algorithm models (YOLO series, OpenPose). The analysis and inference process includes performing object detection and behavior recognition analysis operations on the images in the received video stream. During the object detection process, the system can identify key objects in the video stream, such as personnel, vehicles, or other targets; during the behavior recognition process, the system can analyze the actions and behaviors of the targets to determine whether they conform to preset safety rules or abnormal behavior patterns. For example, the system can identify whether a person is wearing a safety helmet or whether an emergency has occurred. By generating analysis results in real time, the edge computing intelligent box can make quick decision-making processes based on the analysis conclusions, thus realizing rapid feedback and intelligent decision-making for real-time monitoring data, ensuring that the system can provide timely and accurate response measures while processing efficiently.

[0035] The detection and recognition scenarios of the edge computing module 2 are shown in Table 1: Table 1

[0036] The edge computing intelligent box in the edge computing module 2 and the switch 1 achieve interconnection and interoperability through the RTSP protocol, HTTP protocol, and WebSocket protocol. The RTSP protocol is used for the edge computing intelligent box to obtain real-time RTSP video stream data from the switch 1 to ensure low-latency and efficient transmission of the video stream; the HTTP protocol and WebSocket protocol are used to transmit the configuration information, control instructions, and algorithm analysis results of the system in real time to ensure rapid data update and feedback. All data are in JSON data format during the transmission process to simplify data processing and management and ensure more efficient and consistent data exchange between systems. Through the collaborative work of these multi-protocols, the edge computing intelligent box can achieve stable, fast, and flexible data interaction with the switch 1 to meet the system requirements of high real-time and high reliability.

[0037] The event analysis module 4 and the switch 1 achieve remote access and data transmission through the HTTP protocol. The event analysis module 4 is used to provide remote visual video management functions, specifically including modules such as video management, algorithm management, and alarm query. Through the video management function, users can preview and manage multiple video streams in real time, and perform video editing and adjustment; in the algorithm management module, users can configure and schedule pre-set detection and recognition models, and can also draw polygon detection areas on the video interface, set the detection and recognition frame rate of each video stream, and adjust the detection threshold of the model to meet the precise analysis requirements in different scenarios; the alarm query function allows users to query historical alarm records and provides detailed analysis functions to help users analyze the type of alarm, the occurrence time, and the relevant camera information, so as to manage the security events of the system more efficiently and take corresponding measures. Through flexible configuration and management, this module enhances the operability and intelligent management level of the system.

[0038] The data reporting module 5 and the switch 1 are connected bidirectionally through the HTTP protocol and the WebSocket protocol. Users can flexibly select the data reporting transmission mode according to actual needs, and select the corresponding video stream for data reporting according to specific cameras. By configuring the WebSocket address and the HTTP address, users can report real-time analysis results, video stream data, or other key information to a specified third-party business platform. This flexible data upload mechanism ensures that the system can adapt to different data transmission requirements, and guarantees that data can be transmitted to the external platform efficiently and stably for further processing, analysis, and storage.

[0039] In a specific embodiment, the system solves the deficiencies of traditional cloud computing-based video analysis systems in terms of network latency, bandwidth limitation, and data privacy by performing real-time processing and intelligent analysis of video data on edge computing devices. The system includes a switch, a video perception module, an edge computing module, an event analysis module, and a data reporting module, and uses protocols such as RTSP, HTTP, and WebSocket for data transmission, supporting efficient real-time processing in a multi-camera, multi-task environment. The video perception module collects video stream data in real time through network cameras and transmits it to the edge computing module through the switch. The edge computing module uses deep learning models for object detection and behavior recognition to achieve intelligent analysis and decision-making for scenarios such as safe production, campus monitoring, and perimeter protection. The system provides remote visual management functions through the event analysis module, including video management, algorithm configuration, and alarm query, ensuring the efficiency and stability of the system. The data reporting module supports a flexible data upload mechanism to ensure that real-time analysis results and key data can be accurately transmitted to the third-party platform.

[0040] Regarding the device in the above embodiments, the specific manner in which each module performs operations has been described in detail in the embodiments related to the method, and will not be elaborated here.

[0041] It should be noted that although several modules or units of the device for action execution are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of the two or more modules or units described above can be embodied in one module or unit. Conversely, the features and functions of one module or unit described above can be further divided and embodied by multiple modules or units. The components shown as modules or units may or may not be physical units, that is, they may be located in one place, or may be distributed over multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of the present disclosure. Those of ordinary skill in the art can understand and implement it without creative work.

[0042] Furthermore, in this exemplary embodiment, a real-time intelligent video analysis method based on an edge computing device is also provided. Refer to Figure 3 shown in, this method includes: Step S101: Real-time obtain the RTSP video stream data sent by the camera, and transmit the RTSP video stream data to the edge computing module through the switch; Step S102: Analyze and process the RTSP video stream data to obtain JOSN data, and transmit the JOSN data to the event analysis module through the switch; Step S103: Perform event analysis on the JOSN data to obtain an event video, and perform remote visual video management on the event video.

[0043] Through the above real-time intelligent video analysis method based on an edge computing device, by performing real-time processing and intelligent analysis of video data on the edge computing intelligent box, the real-time performance and response speed of the system are effectively improved, and the problems of network latency and bandwidth limitation existing in the traditional cloud computing architecture are solved; multiple protocols work together, including RTSP, HTTP, and WebSocket protocols, to achieve efficient transmission of video stream data, configuration information, control instructions, and analysis results, and the use of the JSON data format ensures the simplicity of data management; built-in multiple algorithm detection and recognition models can perform target detection and behavior recognition in real time and generate analysis results to meet the requirements of efficient and accurate analysis in intelligent security and industrial production; users can select different transmission modes according to needs and configure the upload target address to ensure that data can be transmitted to the specified platform in real time and accurately.

[0044] It should be noted that although the steps of the methods in the present disclosure are described in a specific order in the accompanying drawings, this does not require or imply that these steps must be performed in that specific order, or that all the steps shown must be performed to achieve the desired result. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into one step for execution, and / or one step may be decomposed into multiple steps for execution, etc. Moreover, it is also easy to understand that these steps may be executed synchronously or asynchronously, for example, in multiple modules / processes / threads.

[0045] In an exemplary embodiment of the present disclosure, there is also provided a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the steps of the real-time intelligent video analysis method based on an edge computing device described in any one of the above embodiments can be implemented. In some possible implementation manners, various aspects of the present invention can also be implemented in the form of a program product, which includes program code, and when the program product runs on a terminal device, the program code is used to cause the terminal device to execute the steps according to various exemplary embodiments of the present invention described in the above part of the real-time intelligent video analysis method based on an edge computing device in this specification.

[0046] Referring Figure 4 As shown, a program product 300 for implementing the above method according to an embodiment of the present invention is described, which may be a portable compact disc read-only memory (CD-ROM) and includes program code, and can run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, a readable storage medium may be any tangible medium that contains or stores a program, and the program can be used by or in combination with an instruction execution system, apparatus, or device.

[0047] The program product may adopt any combination of one or more readable media. The readable media may be a readable signal medium or a readable storage medium. The readable storage medium may, for example, but not be limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (a non-exhaustive list) of the readable storage medium include: an electrical connection having one or more wires, a portable disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above.

[0048] The computer-readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, which carries the readable program code. Such a propagated data signal may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the foregoing. The readable storage medium may also be any readable medium other than the readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the readable storage medium may be transmitted using any appropriate medium, including but not limited to wireless, wired, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0049] The program code for performing the operations of the present invention may be written in any combination of one or more programming languages, including object-oriented programming languages such as Java, C++, etc., and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, executed as a stand-alone software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In the case of a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., by connecting through the Internet using an Internet service provider).

[0050] In an exemplary embodiment of the present disclosure, there is also provided an electronic device, which may include a processor and a memory for storing executable instructions of the processor. Wherein, the processor is configured to execute the steps of the real-time intelligent video analysis method based on an edge computing device described in any one of the foregoing embodiments by executing the executable instructions.

[0051] Those skilled in the art can understand that various aspects of the present invention can be implemented as a system, a method, or a program product. Therefore, various aspects of the present invention can be specifically implemented in the following forms, namely: a complete hardware implementation, a complete software implementation (including firmware, microcode, etc.), or an implementation combining hardware and software aspects, which can be collectively referred to as "circuitry", "module", or "system" here.

[0052] The following refers to Figure 5 to describe the electronic device 600 according to this embodiment of the present invention. Figure 5 The electronic device 600 shown is only an example and should not impose any limitation on the functions and usage scope of the embodiments of the present invention.

[0053] AsFigure 5 As shown, the electronic device 600 is presented in the form of a general-purpose computing device. The components of the electronic device 600 may include, but are not limited to: at least one processing unit 610, at least one storage unit 620, a bus 630 connecting different system components (including the storage unit 620 and the processing unit 610), a display unit 640, etc.

[0054] Among them, the storage unit stores program code, and the program code can be executed by the processing unit 610, so that the processing unit 610 executes the steps according to various exemplary embodiments of the present invention described in the above part of the real-time intelligent video analysis method based on edge computing devices in this specification. For example, the processing unit 610 can execute steps as shown in Figure 1 shown in.

[0055] The storage unit 620 may include a readable medium in the form of a volatile storage unit, such as a random access storage unit (RAM) 6201 and / or a cache storage unit 6202, and may further include a read-only storage unit (ROM) 6203.

[0056] The storage unit 620 may also include a program / utility 6204 having a set (at least one) of program modules 6205. Such program modules 6205 include, but are not limited to: an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include the implementation of a network environment.

[0057] The bus 630 may represent one or more of several types of bus structures, including a storage unit bus or a storage unit controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any bus structure in a variety of bus structures.

[0058] The electronic device 600 may also communicate with one or more external devices 700 (such as a keyboard, a pointing device, a Bluetooth device, etc.), and may also communicate with one or more devices that enable a user to interact with the electronic device 600, and / or communicate with any device that enables the electronic device 600 to communicate with one or more other computing devices (such as a router, a modem, etc.). Such communication may be carried out through the input / output (I / O) interface 650. Moreover, the electronic device 600 may also communicate with one or more networks (such as a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through the network adapter 660. The network adapter 660 may communicate with other modules of the electronic device 600 through the bus 630. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 600, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, etc.

[0059] From the description of the above embodiments, those skilled in the art can easily understand that the example embodiments described herein can be implemented by software, or by a combination of software and necessary hardware. Therefore, the technical solutions according to the embodiments of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing device (which can be a personal computer, a server, or a network device, etc.) to execute the above real-time intelligent video analysis method based on an edge computing device according to the embodiments of the present disclosure.

[0060] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present disclosure. This application is intended to cover any variations, uses, or adaptations of the present disclosure, which follow the general principles of the present disclosure and include known common knowledge or conventional technical means in the technical field not disclosed by the present disclosure. The specification and examples are only regarded as exemplary, and the true scope and spirit of the present disclosure are pointed out by the appended claims.

Claims

1. A real-time intelligent video analysis system based on edge computing devices, characterized in that: The system includes: Switch, edge computing module, video perception module and event analysis module; among them, The video perception module is used to obtain the RTSP video stream data sent by the camera in real time, and transmit the RTSP video stream data to the edge computing module through the switch; The edge computing module is used to analyze and process the RTSP video stream data to obtain JOSN data, and transmit the JOSN data to the event analysis module through the switch; The event analysis module is used to perform event analysis on the JOSN data to obtain event videos, and to perform remote visual video management on the event videos.

2. The real-time intelligent video analysis system based on edge computing devices according to claim 1, characterized in that: The system also includes: The data reporting module is used to select the transmission mode of data reporting according to actual needs, and select the corresponding video stream according to the camera for data reporting.

3. The real-time intelligent video analysis system based on edge computing device according to claim 2, characterized in that: The video perception module is interactively connected to the switch via the RTSP protocol, the edge computing module is interactively connected to the switch via the RTSP protocol, the HTTP protocol and the WebSocket protocol, the event analysis module transmits data to the switch via the HTTP protocol, and the data reporting module is interactively connected to the switch via the HTTP protocol and the WebSocket protocol.

4. The real-time intelligent video analysis system based on edge computing devices according to claim 1, characterized in that: The edge computing module includes: Several edge computing smart boxes; among them, Each of the edge computing smart boxes has a built-in program running startup program and a monitoring script program. The program running startup program and the monitoring script are used to automatically start and monitor the running status of various programs of the system to ensure that the system remains efficient and stable during operation, and can promptly alarm or automatically recover when a fault occurs; Each of the edge computing smart boxes is installed with an expandable hard disk for storing the RTSP video stream data, the JOSN data and system logs, and supports storage expansion according to actual needs to meet the needs of large-scale video analysis and data storage.

5. The real-time intelligent video analysis system based on edge computing device according to claim 4, characterized in that: The edge computing smart box obtains the real-time RTSP video stream data from the video perception module, and performs analysis and reasoning according to a preset algorithm model; wherein the analysis and reasoning process includes performing target detection and behavior recognition analysis operations on the images in the RTSP video stream data, so as to generate analysis results in real time and perform decision processing.

6. The real-time intelligent video analysis system based on edge computing device according to claim 4, characterized in that: The edge computing smart box and the switch are connected to each other via RTSP protocol, HTTP protocol and WebSocket protocol; wherein, The RTSP protocol is used by the edge computing smart box to obtain the RTSP video stream data from the switch, the HTTP protocol and the WebSocket protocol are used to transmit configuration information, control instructions and algorithm analysis results in real time, and the data transmitted by the edge computing smart box to the switch is in JSON data format.

7. A real-time intelligent video analysis method based on edge computing equipment, characterized in that: The method includes: Acquire the RTSP video stream data sent by the camera in real time, and transmit the RTSP video stream data to the edge computing module through the switch; Analyze and process the RTSP video stream data to obtain JOSN data, and transmit the JOSN data to the event analysis module through the switch; Event analysis is performed on the JOSN data to obtain event videos, and remote visual video management is performed on the event videos.

Images