Control method, system and equipment of distributed monitoring system and storage medium

Through the control method of the distributed monitoring system, the target model of camera video streaming is received and matched in real time, and the problem of low camera management complexity and analysis accuracy in the prior art is solved, and flexible and efficient video stream management is achieved.

CN118972519APending Publication Date: 2024-11-15BEIJING CHINASOFT INT INFORMATION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410967876.7
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2024-07-05
Filing Date
2024-07-18
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The existing surveillance camera management system is complex in operation and low analysis accuracy and lacks flexibility when connecting to new cameras and analyzing diverse scenarios.

Method used

Through the control method of the distributed monitoring system, the server receives the client's access request in real time, establishes a communication connection, acquires video streams, and matches the target model from multiple candidate models, deploys the target model for detection, and returns the detection results.

Benefits of technology

It improves the flexibility of the monitoring system, can adapt to different scenarios, simplifies the access process of the new camera, and improves the accuracy and management efficiency of video stream analysis.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118972519A_ABST
    Figure CN118972519A_ABST
Patent Text Reader

Abstract

The invention relates to the field of video monitoring, and provides a distributed monitoring system control method, device and equipment and a computer storage medium, and the method comprises the steps: building communication connection with at least one client according to a received access request sent by the at least one client, the client is in communication connection with a camera and is used for acquiring a video stream of the camera; acquiring a video stream sent by the client, and matching a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream; obtaining a corresponding model file according to the target model, and deploying the target model based on the model file; and in the process of obtaining the video stream sent by the client, detecting the video stream based on the target model, and returning a detection result to the client.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of video surveillance, and in particular to a control method, system, device, computer equipment and storage medium for a distributed surveillance system. Background Art

[0002] With the development of technology, the application of surveillance cameras is becoming more and more common. The existing surveillance camera management system usually connects to a certain number of surveillance cameras and analyzes the video streams obtained by the surveillance cameras based on a pre-set model. However, this method requires more complicated operations when new cameras need to be connected, and the accuracy of analyzing diverse scenes through a single model is low. A more flexible and effective method is urgently needed in the existing technology to manage surveillance cameras. Summary of the invention

[0003] The main purpose of this application is to provide a control method, device, equipment and computer storage medium for a distributed monitoring system, aiming to improve the flexibility of monitoring system management.

[0004] In a first aspect, the present application provides a control method for a distributed monitoring system, the control method for the distributed monitoring system comprising the following steps:

[0005] Establishing a communication connection with at least one client according to an access request received from at least one client, wherein the client is in communication connection with a camera and is used to obtain a video stream of the camera;

[0006] Acquire a video stream sent by the client, and match a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream;

[0007] Acquire a corresponding model file according to the target model, and deploy the target model based on the model file;

[0008] In the process of acquiring the video stream sent by the client, the video stream is detected based on the target model, and the detection result is returned to the client.

[0009] In a second aspect, the present application also provides a distributed monitoring system, which includes multiple cameras, a client for connecting to the cameras, and a server, and the server is used to execute the control method of the distributed monitoring system as described in any one of the embodiments of the present application.

[0010] In a third aspect, the present application also provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the control method of the distributed monitoring system as described above is implemented.

[0011] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the control method of the distributed monitoring system as described above is implemented.

[0012] The present application provides a control method, system, device and storage medium for a distributed monitoring system, wherein the present application establishes a communication connection with at least one client according to an access request received from at least one client, wherein the client is connected to a camera for obtaining the video stream of the camera; obtains the video stream sent by the client, and matches a target model corresponding to the video stream of the client from multiple candidate models according to the video stream; obtains a corresponding model file according to the target model, and deploys the target model based on the model file; in the process of obtaining the video stream sent by the client, detects the video stream based on the target model, and returns the detection result to the client. Since the server accesses a new camera by obtaining the access request of the client in real time, and matches different target models for the newly connected camera, the distributed monitoring system can adapt to different scenarios, thereby improving the flexibility of the distributed monitoring system. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 A schematic diagram of a flow chart of a control method of a distributed monitoring system provided in one embodiment of the present application;

[0015] Figure 2 A usage scenario diagram of a control method for a distributed monitoring system provided in one embodiment of the present application;

[0016] Figure 3 A communication logic diagram of a distributed monitoring system provided in one embodiment of the present application;

[0017] Figure 4 A schematic block diagram of a distributed monitoring system provided in one embodiment of the present application;

[0018] Figure 5 A schematic block diagram of a distributed monitoring system provided in one embodiment of the present application;

[0019] Figure 6 The present invention is a block diagram showing the structure of a computer device according to an embodiment of the present application. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0021] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0022] Embodiments of the present application provide a control method, system, device, and storage medium for a distributed monitoring system.

[0023] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0024] Please refer to Figure 1 , Figure 1 A flow chart of a control method for a distributed monitoring system provided in an embodiment of the present application. The control method for the distributed monitoring system can be used in a server to obtain and analyze video streams captured by multiple cameras in a distributed monitoring system. The server can be an independent server, a server cluster, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (CDNs), and big data and artificial intelligence platforms.

[0025] Please refer to Figure 2 , Figure 2 This is a usage scenario diagram provided by an embodiment of the present application. Figure 2As shown, the distributed monitoring system includes multiple cameras, each of which is connected to the corresponding client in communication, wherein multiple clients can run on the same terminal device or on different terminal devices, which is not limited here; each client is connected to the server in communication, and is used to transmit the video stream acquired by the camera to the server so that the server can detect and analyze the video stream. Specifically, the terminal device running the client can be an electronic device running on the open source Hongmeng operating system, such as a mobile phone, tablet computer, laptop computer, desktop computer, personal digital assistant, wearable device and other electronic devices; the control method of the distributed monitoring system provided in the embodiment of the present application can be run in the graphics card of the server.

[0026] like Figure 1 As shown, the control method of the distributed monitoring system includes steps S101 to S104.

[0027] Step S101: establishing a communication connection with at least one client according to an access request received from at least one client, wherein the client is in communication connection with a camera and is used to obtain a video stream of the camera.

[0028] Exemplarily, multiple cameras are connected to the client through a local area network to obtain the video stream of the camera, each camera corresponds to a client, and the camera sends the video stream to the server based on RTSP (Real Time Streaming Protocol). Among them, the client runs on the terminal device, and the client can be a thread in the terminal device. The interrupt device creates a new thread when a new camera is connected. The embodiment of the present application does not limit the number of clients running in the terminal device.

[0029] Exemplarily, the client may send an access request to the server according to actual demand or a trigger operation of the user, and the server obtains the video stream sent by the client in response to the access request.

[0030] In some implementations, establishing a communication connection with at least one of the clients includes:

[0031] Performing a handshake connection with the client, and establishing the communication connection with the client through a local area network based on the result of the handshake connection; or,

[0032] The communication connection is established based on the peripheral interface and the client through a peripheral component interconnection fast bus.

[0033] For example, the client and the server can be connected to each other through a local area network. Before establishing a communication connection between the client and the server, a handshake connection is used to confirm whether the network is available and the reliability of the connection. Alternatively, if a corresponding peripheral interface exists between the terminal device running the client and the server, a communication connection can also be established between the client and the server through PCIE (Peripheral Component Interconnect Express), which is not limited here.

[0034] Exemplarily, the diverse connection modes enable the embodiments of the present application to be applicable to different devices, thereby improving the flexibility of usage scenarios.

[0035] In some implementations, establishing a communication connection with at least one client according to a received access request sent by at least one client includes:

[0036] Parsing the access request to obtain a client identifier in the access request;

[0037] Based on the client identifier, determining a message queue corresponding to the client;

[0038] The target instruction sent by the client is obtained based on the message queue, and the thread corresponding to the client is controlled to perform a corresponding operation according to the target instruction, wherein the target instruction includes the client identifier.

[0039] Exemplarily, when a communication connection is established between a client and a server, a client identifier corresponding to a video stream needs to be transmitted so that the client indicated by the target instruction can be subsequently determined according to the client identifier in the target instruction.

[0040] Exemplarily, a message queue for receiving target instructions is provided in the server. Specifically, multiple clients may correspond to the same message queue, and target instructions in the message queue may be distinguished according to the client identifier; when there are a large number of clients, the clients may be grouped according to a preset number, for example, every 20 clients may be grouped into a group, and a group of clients may correspond to a message queue, but this is not limited to this and is not limited here.

[0041] A message queue is established in the server according to the client ID, so that the video stream can be obtained based on the client ID and independent communication with the client can be carried out based on the message queue, ensuring the independence of the processing flow of video streams of different clients in the server and improving the stability of the distributed monitoring system.

[0042] Exemplarily, the client can send its own client identifier to the server through an access request. After the server parses the access request to obtain the client identifier, it establishes a corresponding message queue according to the client identifier. The subsequent instructions sent by the client to the server also include the client identifier of the client. The server processes the instructions sent by the client based on the message queue corresponding to the client identifier. The client identifier can be, for example, an rtsp address.

[0043] In some implementations, the target instruction includes: at least one of: an initialization instruction, a start instruction, a pause instruction, and a disconnect instruction; the acquiring the target instruction sent by the client based on the message queue, and controlling the thread corresponding to the client to perform a corresponding operation according to the target instruction, includes:

[0044] In the case where the target instruction is an initialization instruction, initializing the target model corresponding to the client; or,

[0045] When the target instruction is a start instruction, controlling the target model to start detection of the video stream;

[0046] When the target instruction is a pause instruction, controlling the target model to pause detection of the video stream;

[0047] When the target instruction is a disconnect instruction, the communication connection with the client is disconnected.

[0048] Exemplarily, after the camera is connected to the server through the client, the server's processing flow for the video stream can be adjusted according to actual needs. For example, the server can be instructed to initialize, start, pause or disconnect the processing flow of the video stream. In this way, when the video stream does not need to be processed, the detection of the video stream can be paused through a pause instruction or the connection with the client corresponding to the camera can be disconnected through a disconnect instruction, thereby improving the flexibility of the distributed monitoring system and avoiding unnecessary consumption of server computing resources.

[0049] Please refer to Figure 3 , Figure 3 A communication logic diagram of a distributed monitoring system provided in one embodiment of the present application.

[0050] like Figure 3As shown, in the SDK communication protocol between the server and the client, target instructions such as init, initmode, start, stop, and deinit are predefined, and the corresponding feedback returned by the server based on the instructions is defined. The target instruction can carry the rtsp address corresponding to the client, so that the server adds the target instruction to the message queue corresponding to the client for processing. Among them, the init instruction is used to initialize the connection between the client and the server, the initmode instruction is used to initialize the target model, the start instruction is used to start the detection and analysis of the video stream, the stop instruction is used to pause the detection and analysis of the target model, and the deinit instruction is used to disconnect the communication connection with the client. Other instructions can also be defined, and the name and type of the instruction are not limited here.

[0051] Exemplarily, initializing the target model corresponding to the client includes transferring the RTSP address corresponding to the video stream to the corresponding target model, so that the target model continuously obtains the video stream to be detected according to the RTSP address.

[0052] Step S102: Acquire the video stream sent by the client, and match the target model corresponding to the video stream of the client from multiple candidate models according to the video stream.

[0053] Exemplarily, the server obtains a video stream sent by the client in h264 format. Existing monitoring systems can usually only analyze video streams through a single model. The control method of the distributed monitoring system provided in the embodiment of the present application can pre-set multiple candidate models and determine a target model matching the video stream from the multiple candidate models according to the video stream sent by the client.

[0054] In some implementations, matching a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream includes:

[0055] Inputting the video stream into a preset intelligent matching engine;

[0056] Performing scene analysis on the video stream based on the intelligent matching engine to determine a target scene corresponding to the video stream, and determining a first candidate model set corresponding to the video stream from a plurality of candidate models according to the target scene;

[0057] Evaluating each first candidate model in the first candidate model set based on the video stream by the intelligent matching engine to obtain a model score for each first candidate model;

[0058] The target model is determined from the first candidate model set according to the model score.

[0059] Exemplarily, different models are trained for different application scenarios. Therefore, by performing scene analysis on the video stream, the target scene of the video stream is determined. For example, key frames in the video stream are obtained and scene analysis is performed on the key frames. Thus, at least one first candidate model corresponding to the target scene of the video stream can be determined from multiple candidate models to obtain a first candidate model set.

[0060] Exemplarily, the first candidate model set can be a class of models applicable to the corresponding type of scenario, but the computing resources and accuracy required by different models for the video stream may differ. Therefore, the video stream can be detected separately by multiple first candidate models, and each first candidate model can be evaluated separately based on indicators such as the computing resources consumed and accuracy of the detection to obtain the model score corresponding to each first candidate model, and then the first candidate model with the highest model score is determined as the target model.

[0061] In some implementations, performing scene analysis on the video stream based on the intelligent matching engine to determine a target scene corresponding to the video stream, and determining a first candidate model set corresponding to the video stream from a plurality of candidate models according to the target scene, includes:

[0062] Based on a preset classification model, determining whether the target scene captured by the video stream belongs to a vehicle area, a pedestrian area, or a fire-prone area;

[0063] According to the type of the target scene, the vehicle recognition model, the pedestrian recognition model or the fire alarm recognition model in the candidate models is determined as the first candidate model in the first candidate model set.

[0064] Exemplarily, the candidate models may include multiple types of models such as vehicle recognition models, pedestrian recognition models, and fire alarm recognition models. The intelligent matching engine includes a classification model. In order to determine which type of candidate model the video stream needs to be processed by, the target scene captured in the video stream is classified according to the type of the candidate model based on the classification model, and the target scene is determined to be any one of a vehicle area, a pedestrian area, or a high-incidence fire area. Of course, it is not limited to this, and the types of candidate models and target scenes are not limited here.

[0065] Exemplarily, according to the type described in the target scenario, a set of candidate models corresponding to the type is determined as the first candidate model.

[0066] In some implementations, the step of evaluating each first candidate model in the first candidate model set based on the video stream by the intelligent matching engine to obtain a model score for each first candidate model includes:

[0067] Inputting the video stream into each of the first candidate models and a preset standard model respectively, and determining a standard detection result according to the standard model;

[0068] Comparing the first detection result of each of the first candidate models with the standard detection result to obtain the recall rate and precision rate of each of the first detection models, and obtaining the resource occupation index during the operation of each of the first candidate models;

[0069] A model score of each of the first candidate models is determined according to the recall rate, the precision rate, and the resource occupancy index.

[0070] Exemplarily, the intelligent matching engine also includes a standard model set for each type of candidate model. The standard model can be a preset model with higher accuracy but higher computing resources required during operation. Each first candidate model is evaluated based on the operating results of the standard model.

[0071] Specifically, the video stream is input into each first candidate model and the standard model respectively, and the first detection result corresponding to each first candidate model and the standard detection result corresponding to the standard model are obtained, so as to evaluate the accuracy and recall rate of each first detection result according to the standard detection result, wherein the accuracy rate refers to the probability that the target object detected by the first detection model is accurate, which can be determined by the ratio of the number of first detection results consistent with the standard detection results and the first detection result; the recall rate refers to the recognition ability of the first candidate model for the target object compared with the standard detection result, which can be determined by the ratio of the number of target objects in the first detection result to the number of target objects in the standard detection result. The video streams input into each first candidate model are the same video streams.

[0072] Exemplarily, the memory usage indicator is used to quantify the computing resources occupied by each first candidate model.

[0073] Exemplarily, the model score is obtained by taking a weighted sum of the recall rate, precision rate, and resource occupancy index.

[0074] Step S103: Obtain a corresponding model file according to the target model, and deploy the target model based on the model file.

[0075] Exemplarily, the model files of each candidate model are pre-stored in a terminal device running the client. After determining the target model, the server can send a model file request to the terminal device according to the model identifier of the target model, so that the terminal device sends the model file to the server.

[0076] Exemplarily, the model file may also be stored in other devices, such as a server or a distributed storage device that is communicatively connected to the server, but this is certainly not limited to this and is not limited here.

[0077] Exemplarily, after obtaining the model file of the target model, a container for deploying and running the target model is set in the server, and the target model is deployed in the container to improve the independence of the operation of each model in the server. When setting the container, the container can be configured accordingly according to various parameters such as the operating memory of the target model.

[0078] Step S104: In the process of acquiring the video stream sent by the client, the video stream is detected based on the target model, and the detection result is returned to the client.

[0079] Exemplarily, after the target model is deployed, the target model in the server continuously identifies and detects the video stream sent by the client, and returns corresponding detection results, such as an alarm prompt light, to the client.

[0080] It should be understood that the client referred to in this application is a software abstraction, not an actual device. For example, the client can be a software object running in a terminal device. Specifically, one or more clients can run in a terminal device.

[0081] The control method of the distributed monitoring system provided in the above embodiment establishes a communication connection with at least one client according to an access request received from at least one client, wherein the client is connected to the camera for obtaining the video stream of the camera; obtains the video stream sent by the client, and matches the target model corresponding to the video stream of the client from multiple candidate models according to the video stream; obtains the corresponding model file according to the target model, and deploys the target model based on the model file; in the process of obtaining the video stream sent by the client, detects the video stream based on the target model, and returns the detection result to the client. Since the server accesses a new camera by obtaining the access request of the client in real time, and matches different target models for the newly connected camera, the distributed monitoring system can adapt to different scenarios, thereby improving the flexibility of the distributed monitoring system.

[0082] See also Figure 4 , 5 , Figure 4 , 5 It is a schematic diagram of a distributed monitoring system provided in one embodiment of the present application.

[0083] like Figure 4 , 5As shown, the control device of the distributed monitoring system includes: the distributed monitoring system includes multiple cameras, a client and a server for connecting to the cameras, and the server is used to execute:

[0084] Establishing a communication connection with at least one client according to an access request received from at least one client, wherein the client is in communication connection with a camera and is used to obtain a video stream of the camera;

[0085] Acquire a video stream sent by the client, and match a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream;

[0086] Acquire a corresponding model file according to the target model, and deploy the target model based on the model file;

[0087] In the process of acquiring the video stream sent by the client, the video stream is detected based on the target model, and the detection result is returned to the client.

[0088] Among them, multiple cameras can be connected to the same terminal device, and multiple clients corresponding to each camera can be run in the terminal device, or the camera and the terminal device can also correspond one to one, which is not limited here.

[0089] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and modules and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0090] The method and apparatus of the present application can be used in many general or special computing system environments or configurations. For example: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, etc. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in distributed computing environments, in which tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0091] Exemplarily, the above method and apparatus may be implemented in the form of a computer program. The computer program may be implemented in Figure 6Runs on the computer device shown.

[0092] See also Figure 6 , Figure 6 A schematic block diagram of the structure of a computer device provided in an embodiment of the present application. The computer device may be a server or a terminal.

[0093] like Figure 6 As shown, the computer device includes a processor, a memory, and a network interface connected via a system bus, wherein the memory may include a storage medium and an internal memory.

[0094] The storage medium can store an operating system and a computer program. The computer program includes program instructions, and when the program instructions are executed, the processor can execute any control method of a distributed monitoring system.

[0095] The processor is used to provide computing and control capabilities and support the operation of the entire computer equipment.

[0096] The internal memory provides an environment for the operation of the computer program in the storage medium. When the computer program is executed by the processor, the processor can execute any control method of the distributed monitoring system.

[0097] The network interface is used for network communication, such as sending assigned tasks, etc. Those skilled in the art will appreciate that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0098] It should be understood that the processor may be a central processing unit (CPU), and the processor may also be other general-purpose processors, graphics processing units (GPU), digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Specifically, the processor in the terminal device of the embodiment of the present application may be a CPU, and the processor in the server may be at least one of a CPU and a parallel computing unit such as a GPU or a DSP.

[0099] In one embodiment, the processor is used to run a computer program stored in the memory to implement the following steps:

[0100] Establishing a communication connection with at least one client according to an access request received from at least one client, wherein the client is in communication connection with a camera and is used to obtain a video stream of the camera;

[0101] Acquire a video stream sent by the client, and match a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream;

[0102] Acquire a corresponding model file according to the target model, and deploy the target model based on the model file;

[0103] In the process of acquiring the video stream sent by the client, the video stream is detected based on the target model, and the detection result is returned to the client.

[0104] In one embodiment, when the processor establishes a communication connection with at least one client according to an access request received from at least one client, the processor is configured to implement:

[0105] Parsing the access request to obtain a client identifier in the access request;

[0106] Based on the client identifier, determining a message queue corresponding to the client;

[0107] The target instruction sent by the client is obtained based on the message queue, and the thread corresponding to the client is controlled to perform a corresponding operation according to the target instruction, wherein the target instruction includes the client identifier.

[0108] In one embodiment, the target instruction includes: at least one of an initialization instruction, a start instruction, a pause instruction, and a disconnection instruction. When the processor obtains the target instruction sent by the client based on the message queue and controls the thread corresponding to the client to perform a corresponding operation according to the target instruction, it is used to implement:

[0109] In the case where the target instruction is an initialization instruction, initializing the target model corresponding to the client; or,

[0110] When the target instruction is a start instruction, controlling the target model to start detection of the video stream;

[0111] When the target instruction is a pause instruction, controlling the target model to pause detection of the video stream;

[0112] When the target instruction is a disconnect instruction, the communication connection with the client is disconnected.

[0113] In one embodiment, when implementing the establishing of a communication connection with at least one of the clients, the processor is configured to implement:

[0114] Performing a handshake connection with the client, and establishing the communication connection with the client through a local area network based on the result of the handshake connection; or,

[0115] The communication connection is established based on the peripheral interface and the client through a peripheral component interconnection fast bus.

[0116] In one embodiment, when implementing the matching of the target model corresponding to the video stream of the client from multiple candidate models according to the video stream, the processor is used to implement:

[0117] Inputting the video stream into a preset intelligent matching engine;

[0118] Performing scene analysis on the video stream based on the intelligent matching engine to determine a target scene corresponding to the video stream, and determining a first candidate model set corresponding to the video stream from a plurality of candidate models according to the target scene;

[0119] Evaluating each first candidate model in the first candidate model set based on the video stream by the intelligent matching engine to obtain a model score for each first candidate model;

[0120] The target model is determined from the first candidate model set according to the model score.

[0121] In one embodiment, when the processor performs scene analysis on the video stream based on the intelligent matching engine to determine the target scene corresponding to the video stream, and determines the first candidate model set corresponding to the video stream from the plurality of candidate models according to the target scene, it is configured to implement:

[0122] Based on a preset classification model, determining whether the target scene captured by the video stream belongs to a vehicle area, a pedestrian area, or a fire-prone area;

[0123] According to the type of the target scene, the vehicle recognition model, the pedestrian recognition model or the fire alarm recognition model in the candidate models is determined as the first candidate model in the first candidate model set.

[0124] In one embodiment, when the processor implements the step of evaluating each first candidate model in the first candidate model set based on the intelligent matching engine according to the video stream to obtain a model score for each first candidate model, the processor is used to implement:

[0125] Inputting the video stream into each of the first candidate models and a preset standard model respectively, and determining a standard detection result according to the standard model;

[0126] Comparing the first detection result of each of the first candidate models with the standard detection result to obtain the recall rate and precision rate of each of the first detection models, and obtaining the resource occupation index during the operation of each of the first candidate models;

[0127] A model score of each of the first candidate models is determined according to the recall rate, the precision rate, and the resource occupancy index.

[0128] It should be noted that technical personnel in the relevant field can clearly understand that, for the convenience and conciseness of description, the specific working process of the control of the distributed monitoring system described above can refer to the corresponding process in the control method embodiment of the aforementioned distributed monitoring system, and will not be repeated here.

[0129] An embodiment of the present application also provides a computer-readable storage medium, on which a computer program is stored. The computer program includes program instructions. The method implemented when the program instructions are executed can refer to the various embodiments of the control method of the distributed monitoring system of the present application.

[0130] The computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiment, such as a hard disk or memory of the computer device. The computer-readable storage medium may also be an external storage device of the computer device, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc., equipped on the computer device.

[0131] It should be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0132] It should also be understood that the term "and / or" used in the specification of this application and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, including these combinations. It should be noted that, in this article, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "including a..." does not exclude the presence of other identical elements in the process, method, article or system including the element.

[0133] The serial numbers of the embodiments of the present application are for description only and do not represent the advantages and disadvantages of the embodiments. The above description is only a specific implementation mode of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A control method for a distributed monitoring system, characterized in that: The method is applied to a server and comprises: Establishing a communication connection with at least one client according to an access request received from at least one client, wherein the client is in communication connection with a camera and is used to obtain a video stream of the camera; Acquire a video stream sent by the client, and match a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream; Acquire a corresponding model file according to the target model, and deploy the target model based on the model file; In the process of acquiring the video stream sent by the client, the video stream is detected based on the target model, and the detection result is returned to the client.

2. The control method of the distributed monitoring system according to claim 1, characterized in that: The step of establishing a communication connection with at least one client according to the received access request sent by at least one client comprises: Parsing the access request to obtain a client identifier in the access request; Based on the client identifier, determining a message queue corresponding to the client; The target instruction sent by the client is obtained based on the message queue, and the thread corresponding to the client is controlled to perform a corresponding operation according to the target instruction, wherein the target instruction includes the client identifier.

3. The control method of the distributed monitoring system according to claim 5, characterized in that: The target instruction includes: at least one of an initialization instruction, a start instruction, a pause instruction, and a disconnection instruction; the acquiring the target instruction sent by the client based on the message queue, and controlling the thread corresponding to the client to perform a corresponding operation according to the target instruction, includes: In the case where the target instruction is an initialization instruction, initializing the target model corresponding to the client; or, When the target instruction is a start instruction, controlling the target model to start detection of the video stream; When the target instruction is a pause instruction, controlling the target model to pause detection of the video stream; When the target instruction is a disconnect instruction, the communication connection with the client is disconnected.

4. The control method of the distributed monitoring system according to claim 1, characterized in that: The establishing a communication connection with at least one of the clients comprises: Performing a handshake connection with the client, and establishing the communication connection with the client through a local area network based on the result of the handshake connection; or, The communication connection is established based on the peripheral interface and the client through a peripheral component interconnection fast bus.

5. The control method of the distributed monitoring system according to claim 1, characterized in that: The step of matching a target model corresponding to the video stream of the client from a plurality of candidate models according to the video stream comprises: Inputting the video stream into a preset intelligent matching engine; Performing scene analysis on the video stream based on the intelligent matching engine to determine a target scene corresponding to the video stream, and determining a first candidate model set corresponding to the video stream from a plurality of candidate models according to the target scene; Evaluating each first candidate model in the first candidate model set based on the video stream by the intelligent matching engine to obtain a model score for each first candidate model; The target model is determined from the first candidate model set according to the model score.

6. The control method of the distributed monitoring system according to claim 5, characterized in that: The performing scene analysis on the video stream based on the intelligent matching engine to determine a target scene corresponding to the video stream, and determining a first candidate model set corresponding to the video stream from a plurality of candidate models according to the target scene, comprises: Based on a preset classification model, determining whether the target scene captured by the video stream belongs to a vehicle area, a pedestrian area, or a fire-prone area; According to the type of the target scene, the vehicle recognition model, the pedestrian recognition model or the fire alarm recognition model in the candidate models is determined as the first candidate model in the first candidate model set.

7. The control method of the distributed monitoring system according to claim 5, characterized in that: The step of evaluating each first candidate model in the first candidate model set based on the intelligent matching engine according to the video stream to obtain a model score for each first candidate model includes: Inputting the video stream into each of the first candidate models and a preset standard model respectively, and determining a standard detection result according to the standard model; Comparing the first detection result of each of the first candidate models with the standard detection result to obtain the recall rate and precision rate of each of the first detection models, and obtaining the resource occupation index during the operation of each of the first candidate models; A model score of each of the first candidate models is determined according to the recall rate, the precision rate, and the resource occupancy index.

8. A distributed monitoring system, characterized in that: The distributed monitoring system includes multiple cameras, a terminal device for running a client, and a server, wherein the cameras are respectively communicatively connected to the terminal devices, the terminal devices are communicatively connected to the server, and the server is used to execute the control method of the distributed monitoring system described in any one of claims 1 to 7 of the present application.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the steps of the distributed monitoring system control method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the steps of the distributed monitoring system control method according to any one of claims 1 to 7 are implemented.