Regional risk early warning method and device, electronic equipment and medium

Abstract

The embodiment of the invention discloses a regional risk early warning method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a real-time working state of early warning equipment associated with a network camera when there is a personnel abnormal behavior or an environment abnormal condition; determining whether the real-time working state of the early warning equipment is an early-warned state or not; and under the condition that the real-time working state of the early-warning equipment is a non-early-warning state, an early-warning trigger instruction is sent to the early-warning equipment, and local risk recording operation is executed. According to the scheme, the problems of single early-warning dimension, poor linkage, untimely early warning and difficult tracing of the network camera in the related technology can be solved.

Description

Technical Field

[0001] This application relates to the field of network camera surveillance technology, specifically to a regional risk early warning method, device, electronic equipment, and storage medium. Background Technology

[0002] With the increasing demand for security monitoring, network cameras have been widely used in various target areas such as industrial parks, office buildings, and warehousing centers, becoming one of the core devices for regional security management. However, the application of existing network cameras has obvious limitations: most only have single image acquisition functions, capable of visually monitoring personnel activities, and cannot link with environmental data to achieve multi-dimensional risk detection; at the same time, the anomaly judgment logic is relatively simple, only able to identify a few specific behaviors, making it difficult to cover complex personnel anomalies such as unauthorized lingering or unauthorized entry, and unable to detect environmental risks such as excessive temperature or smoke leakage; in addition, the linkage between network cameras and early warning devices is insufficient, often resulting in situations where early warning devices are not triggered in time after a risk event occurs, leading to the spread of risk, and the lack of a complete risk recording mechanism makes subsequent tracing and responsibility determination difficult. It is evident that current regional risk early warning solutions suffer from problems such as single warning dimensions, poor linkage, untimely warnings, and difficulty in tracing. Summary of the Invention

[0003] This application provides a regional risk early warning method, electronic device, apparatus, and storage medium, which can solve the problems of single early warning dimension, poor linkage, untimely early warning, and difficulty in tracing in related technologies.

[0004] In a first aspect, embodiments of this application provide a regional risk early warning method, including: Acquire target area monitoring images captured by at least two network cameras set within the target monitoring area, as well as target area environmental data collected by an environmental sensing device associated with the network cameras; Based on the surveillance images, determine whether there is any abnormal human behavior within the target area; Based on the environmental data, determine whether there are environmental anomalies in the target area; When there are abnormal human behaviors or environmental abnormalities, the real-time working status of the early warning devices associated with the network camera is obtained; Determine whether the real-time operating status of the early warning device is in an early warning state; When the real-time working status of the warning device is in a non-warning state, a warning trigger command is sent to the warning device, and a local risk recording operation is performed.

[0005] Optionally, in some embodiments of this application, determining whether there is abnormal human behavior within the target area based on the surveillance image includes: Extract the movement trajectory features and dwell time information of the personnel from the surveillance images; When the dwell time information shows that the duration of a person's stay in the target monitoring area exceeds a preset dwell time threshold, or when the movement trajectory characteristics show that a person enters the target area from an unauthorized entrance, it is determined that there is abnormal behavior by the person.

[0006] Optionally, in some embodiments of this application, determining whether there are environmental anomalies in the target area based on the environmental data includes: Temperature and smoke concentration values ​​are extracted from the environmental data and compared with preset safe temperature and safe smoke concentration thresholds, respectively. If the temperature value exceeds the safe temperature threshold or the smoke concentration value exceeds the safe smoke concentration threshold, an environmental anomaly is determined to exist.

[0007] Optionally, in some embodiments of this application, acquiring target area monitoring images collected by at least two network cameras set within the target monitoring area, and target area environmental data collected by an environmental sensing device associated with the network cameras, includes: Obtain the installation location of each network camera; Based on the installation location, each network camera is associated with a sub-region of the target monitoring area; The system receives real-time video streams transmitted by each network camera through a network communication protocol, and extracts frame images from the real-time video streams as initial images. Acquire real-time environmental data from environmental sensing devices that match the installation locations of each network camera; Based on the sub-region division results of the target monitoring area, the initial image is associated with the environmental data of the corresponding sub-region to form a monitoring data set with environmental attributes.

[0008] Optionally, in some embodiments of this application, the step of extracting frame images from the real-time video stream as initial images includes: For each frame of the real-time video stream, image sharpness is detected, and images with sharpness values ​​higher than a preset sharpness threshold are selected. Perform personnel contour recognition and environmental feature recognition on the filtered images; Images containing complete human silhouettes or unusual environmental features are selected as initial images.

[0009] Optionally, in some embodiments of this application, determining whether there is abnormal human behavior within the target area based on the surveillance image includes: Extract the human body feature information of the person entering from the surveillance image; The human body feature information is matched with a preset authorized personnel feature database to calculate the feature matching value. If the feature matching value is lower than the preset authorization threshold and the person entering the area has not been verified by the authorization verification device at the entrance of the area, it is determined that there is an unauthorized person who has broken in.

[0010] Optionally, in some embodiments of this application, determining whether the real-time operating status of the early warning device is in an early warning state includes: Send a status query command to each early warning device, the status query command including the device identifier and the query time range; Receive status response messages from each early warning device, and parse the operating parameters of the early warning device from the status response messages; If the operating parameters meet the preset conditions, the early warning device is determined to be in an early warning state.

[0011] Secondly, embodiments of this application provide a regional risk early warning device, comprising: The first acquisition module is used to acquire target area monitoring images collected by at least two network cameras set in the target monitoring area, as well as target area environmental data collected by environmental sensing devices associated with the network cameras. The first determining module is used to determine whether there is abnormal human behavior in the target area based on the monitoring image; The second determining module is used to determine whether there are environmental anomalies in the target area based on the environmental data; The second acquisition module is used to acquire the real-time working status of the early warning device associated with the network camera when there is abnormal human behavior or environmental abnormality. The third determining module is used to determine whether the real-time working status of the early warning device is an early warning state; The early warning module is used to send an early warning trigger command to the early warning device and perform local risk recording operations when the real-time working status of the early warning device is a non-early warning state.

[0012] Accordingly, this application also provides an electronic device, including a memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as described in any of the methods above.

[0013] This application also provides a storage medium storing a processor program that, when executed by a processor, implements any of the methods described above.

[0014] This application provides a regional risk early warning method, device, electronic device, and storage medium. After acquiring monitoring images of a target area collected by at least two network cameras located within the target monitoring area, and environmental data of the target area collected by an environmental sensing device associated with the network cameras, the method determines whether abnormal human behavior exists within the target area based on the monitoring images, and whether environmental anomalies exist based on the environmental data. When abnormal human behavior or environmental anomalies are present, the method acquires the real-time operating status of the early warning device associated with the network cameras. Then, it determines whether the real-time operating status of the early warning device is in an alerted state. If the real-time operating status of the early warning device is in an alert-free state, an early warning trigger command is sent to the early warning device, and a local risk recording operation is performed. In the regional risk early warning scheme provided in this application, monitoring images collected by at least two network cameras within the target monitoring area and environmental data from associated environmental sensing devices are acquired. Abnormal human behavior is identified based on the monitoring images, and environmental anomalies are determined based on the environmental data. A risk event is determined if either of these conditions is met. Furthermore, the real-time operating status of the early warning device is acquired, and an early warning is triggered and the risk is recorded when no warning is issued. By combining the detection of both human behavior and environmental status, and enabling the linkage between network cameras, early warning devices, and environmental sensing devices, the limitations of single-dimensional early warning are effectively avoided. This ensures timely early warning of risk events and complete recording of risk information. Therefore, it can solve the problems of single-dimensional early warning, poor linkage, untimely early warning, and difficulty in tracing in related technologies, and achieve the effects of comprehensive risk monitoring, accurate early warning, and convenient tracing. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating the regional risk early warning method provided in an embodiment of this application; Figure 2 This is a schematic diagram of the structure of the regional risk early warning device provided in the embodiments of this application; Figure 3 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0018] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes that element. Furthermore, components, features, and elements with the same names in different embodiments of this application may have the same meaning or different meanings, the specific meaning of which must be determined by its interpretation in that specific embodiment or further in conjunction with the context of that specific embodiment.

[0019] It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0020] In the following description, the use of suffixes such as "module," "part," or "unit" to denote elements is solely for the purpose of illustrative purposes and has no specific meaning in itself. Therefore, "module," "part," or "unit" may be used interchangeably.

[0021] The following describes in detail the embodiments involved in this application. It should be noted that the order of description of the embodiments in this application is not intended to limit the priority of the embodiments.

[0022] This application provides a regional risk warning method, apparatus, storage medium, and smart terminal. Specifically, the regional risk warning method of this application can be executed by a smart terminal or a server, wherein the smart terminal can be a terminal. The terminal can be a smartphone, tablet computer, laptop computer, touch screen, game console, personal computer (PC), personal digital assistant (PDA), or other smart terminal. The terminal may also include a client, which can be a media playback client or an instant regional risk warning client, etc.

[0023] An embodiment of the present application provides a regional risk warning method, which can be executed by an electronic device or a server. Taking the regional risk warning method executed by an electronic device as an example, the embodiment of the present application will be described. Among them, the electronic device includes a touch display screen and a processor. The touch display screen is used to present a graphical user interface and receive operation instructions generated by a user acting on the graphical user interface. When the user operates the graphical user interface through the touch display screen, the graphical user interface can control the content on the local side of the electronic device by responding to the received operation instructions, or can control the content on the server side by responding to the received operation instructions.

[0024] The regional risk warning solution provided by the present application acquires monitoring images collected by at least two network cameras in a target monitoring area and environmental data of an associated environmental perception device, identifies abnormal human behaviors based on the monitoring images, and determines environmental abnormalities based on the environmental data. If either of them is satisfied, a risk event is determined; furthermore, the real-time working state of a warning device is acquired, and when there is no warning, a warning is triggered and the risk is recorded. Since it combines the two-dimensional detection of human behavior and environmental state, and realizes the linkage of network cameras, warning devices, and environmental perception devices, it effectively avoids the limitations of single-dimensional warning, ensures timely warning of risk events, and completely records risk information at the same time. Therefore, it can solve the problems of single warning dimension, poor linkage, untimely warning, and difficult traceability in the related technology, and achieve the effects of full-range risk monitoring, accurate warning, and convenient traceability.

[0025] The following will be described in detail respectively. It should be noted that the description order of the following embodiments does not limit the priority order of the embodiments.

[0026] A regional risk warning method includes: acquiring target area monitoring images collected by at least two network cameras set in a target monitoring area, and target area environmental data collected by an environmental perception device associated with the network cameras; determining whether there are abnormal human behaviors in the target area based on the monitoring images; determining whether there are environmental abnormalities in the target area based on the environmental data; when there are abnormal human behaviors or environmental abnormalities, acquiring the real-time working state of a warning device associated with the network cameras; determining whether the real-time working state of the warning device is a warned state; in the case where the real-time working state of the warning device is an unwarned state, sending a warning trigger instruction to the warning device and performing a local risk recording operation.

[0027] Please refer to Figure 1 , Figure 1 The flowchart of the regional risk warning method provided by the embodiment of the present application. The specific process of the regional risk warning method can be as follows: 101. Acquire monitoring images of the target area collected by at least two network cameras set within the target monitoring area, as well as environmental data of the target area collected by environmental sensing devices associated with the network cameras.

[0028] Specifically, the target monitoring area is divided into sub-areas, such as the coverage area entrance, core control sub-area, and channel sub-area. Each sub-area should have at least one network camera installed. The shooting angle should be adjusted to ensure there are no blind spots. Then, the network camera's IP address, shooting resolution, frame rate, and encoding format should be configured.

[0029] Meanwhile, the environmental sensing devices in each sub-region are installed in the same location as the network cameras in the corresponding sub-region to ensure that the collected environmental data can accurately correspond to the images of the corresponding sub-region. The device address, data acquisition frequency and measurement range of the environmental sensing devices are configured.

[0030] Furthermore, it can receive real-time video streams from various network cameras, classify and store the video stream data according to sub-region identifiers, and optionally, use a frame interval interception strategy to capture images, thereby obtaining the target area monitoring image and target area environmental data.

[0031] Optionally, in some embodiments of this application, the step "acquiring target area monitoring images captured by at least two network cameras set within the target monitoring area, and target area environmental data collected by environmental sensing devices associated with the network cameras" may specifically include: Obtain the installation location of each network camera; Each network camera is associated with a sub-region of the target monitoring area based on its installation location; The system receives real-time video streams transmitted by each network camera through network communication protocols and extracts frame images from the real-time video streams as initial images. Acquire real-time environmental data from environmental sensing devices that match the installation locations of each network camera; Based on the sub-region division results of the target monitoring area, the initial image is associated with the environmental data of the corresponding sub-region to form a monitoring data set with environmental attributes.

[0032] The target monitoring area can be a production workshop in an industrial park, a computer room in an office building, or a hazardous materials storage area in a warehouse center—areas requiring key security control. Network cameras can be installed at area entrances, core control sub-areas, and passageway sub-areas. They can transmit video streams in real time via the RTSP protocol, facilitating the extraction of key frames for monitoring. Environmental sensing devices, including temperature sensors and smoke sensors, are associated with the network cameras and installed in the same sub-area, transmitting real-time environmental data to electronic devices via the Modbus protocol.

[0033] Optionally, in some embodiments of this application, the step "extracting frame images from the real-time video stream as initial images" may specifically include: For each frame of the real-time video stream, image sharpness is detected, and images with sharpness values ​​higher than a preset sharpness threshold are selected. Perform personnel contour recognition and environmental feature recognition on the filtered images; Images containing complete human silhouettes or unusual environmental features are selected as initial images.

[0034] Specifically, the variance of grayscale values ​​can be calculated for each captured image frame, and images with variances greater than or equal to a preset sharpness threshold can be selected. Then, images containing complete human outlines or abnormal environmental features are determined as initial images. Optionally, in some embodiments of this application, metadata tags, such as shooting timestamps, network camera device numbers, and sub-region identifiers, such as image types, are added to the selected initial images. For example, based on the sub-region type, the entrance area image is the first image, and the core control area image is the second image.

[0035] 102. Determine whether there is any abnormal human behavior within the target area based on surveillance images.

[0036] The determination of abnormal personnel behavior requires combining the temporal characteristics and feature matching results of surveillance images. For example, for core controlled sub-areas, the duration of personnel stay is calculated using the timestamp of the surveillance image and compared with a preset stay threshold; exceeding the threshold indicates an anomaly. For area entrances, the human body features of personnel in the surveillance images are extracted and matched with an authorized personnel feature database; failure to match and failure to pass access control verification indicates unauthorized entry. Environmental anomalies are determined by comparing temperature and smoke concentration values ​​in environmental data with preset safe temperature and safe smoke concentration thresholds, respectively; exceeding these thresholds indicates an anomaly. The presence of any one of these anomalies triggers a risk event determination.

[0037] Optionally, in some embodiments of this application, the step "determining whether there is abnormal human behavior in the target area based on surveillance images" may specifically include: Extract the movement trajectory features and dwell time information of the personnel from the surveillance images; When the dwell time information shows that the duration of a person's stay in the target monitoring area exceeds a preset dwell time threshold, or when the movement trajectory characteristics show that a person enters the target area from an unauthorized entrance, it is determined that there is abnormal behavior by the person.

[0038] Optionally, in some embodiments of this application, the step "determining whether there is abnormal human behavior in the target area based on surveillance images" may specifically include: Extract the movement trajectory features and dwell time information of the personnel from the surveillance images; When the dwell time information shows that the duration of a person's stay in the target monitoring area exceeds a preset dwell time threshold, or when the movement trajectory characteristics show that a person enters the target area from an unauthorized entrance, it is determined that there is abnormal behavior by the person.

[0039] For example, human body features such as facial features, clothing color features, and height proportion features can be extracted from surveillance images collected by network cameras at the area entrance to form a multi-dimensional feature vector.

[0040] Specifically, a lightweight deep learning model (such as MobileFaceNet) can be used to extract features from the preprocessed facial region to obtain a facial feature vector, which contains core information such as facial contours, relative positions of facial features, and skin texture.

[0041] The HSV color space quantization method is used to segment the clothing areas (shirts and pants) of individuals from surveillance images. These clothing areas are then converted to the HSV color space, and the H (hue), S (saturation), and V (lightness) channels are quantized separately. The pixel percentage of each color range is calculated to form a color feature vector. The facial feature vector, clothing color feature vector, and height proportion feature vector are normalized and then weighted and fused to form a human body feature vector, which serves as the unique identifier for each person entering the area.

[0042] Furthermore, by comparing feature vectors, the similarity between the entrant and authorized personnel is quantified. When the feature matching value is lower than a preset authorization threshold (e.g., 70%), it is determined that the entrant's human characteristics differ significantly from those of all personnel in the authorized personnel feature database, and no matching authorized personnel exist. Simultaneously, based on timestamp matching, the verification records of the corresponding authorization verification device are queried: if a successful verification record is found, it is determined that verification has passed and no intrusion judgment is triggered; if no verification record is found, or a failed verification record is found, it is determined that verification has failed; if the feature matching value is lower than the preset authorization threshold and verification has failed, it is determined that an unauthorized person has intruded.

[0043] 103. Determine whether there are environmental anomalies in the target area based on environmental data.

[0044] The target area refers to a specific physical space that requires security control through network cameras and environmental sensing devices. The target area can be functionally divided into sub-areas (such as entrance areas, core control areas, and passageways), each equipped with corresponding network cameras and environmental sensing devices. Environmental data refers to quantitative data collected by the environmental sensing devices associated with the network cameras, reflecting the physical environmental status of the target area. Environmental anomalies refer to environmental data exceeding the preset security threshold range of the target area, potentially causing security incidents or affecting the normal operation of the area.

[0045] Based on the sub-region identifier matching rules, real-time environmental data of the corresponding sub-region is obtained from the environmental sensing device associated with the network camera. Then, according to the preset calibration coefficient, the original real-time environmental data is converted into readable physical quantity data. If the converted physical quantity exceeds the sensor measurement range, it is determined that there is an environmental anomaly in the target area.

[0046] Optionally, in some embodiments of this application, the step "determining whether there is an environmental anomaly in the target area based on the environmental data" may specifically include: Temperature and smoke concentration values ​​are extracted from the environmental data and compared with preset safe temperature and safe smoke concentration thresholds, respectively. If the temperature value exceeds the safe temperature threshold or the smoke concentration value exceeds the safe smoke concentration threshold, an environmental anomaly is determined to exist.

[0047] From the environmental data set of the associated sub-regions, temperature and smoke concentration values ​​(physical quantities in units) are extracted, along with the corresponding collection timestamps, sub-region identifiers, and environmental sensing device numbers. Next, the extracted raw data undergoes noise reduction preprocessing, using a data moving average method to filter out instantaneous outliers. For example, if the raw temperature data is 25℃, 26℃, 60℃, 25℃, and 24℃, the calculated average is 32℃, which is used as the final valid temperature value for comparison. Smoke concentration data is processed using the same logic. Then, the valid temperature value is compared with the referenced threshold. If the valid temperature value is greater than the safe temperature threshold, it is determined that the temperature exceeds the threshold. Similarly, the valid smoke concentration value is compared with the referenced safe smoke concentration threshold. If the valid smoke concentration value is greater than the safe smoke concentration threshold, it is determined that the smoke concentration exceeds the threshold. If either the valid temperature value or the valid smoke concentration value is greater than the safe temperature threshold, or greater than the safe smoke concentration threshold, the environment is determined to be abnormal.

[0048] 104. When there are abnormal behaviors of personnel or abnormal situations in the environment, obtain the real-time working status of the early warning device associated with the network camera.

[0049] When abnormal human behavior or environmental anomalies are detected in the target area, the sub-area identifier corresponding to the anomaly is extracted. Then, based on the sub-area identifier, all early warning devices associated with the network camera in that area are located. Based on the type and communication address of the early warning device, bidirectional communication between the electronic device and the early warning device is established. Optionally, in some embodiments of this application, a status query command can be sent to each associated early warning device. After receiving the query command, the early warning device generates a status response message based on its own real-time operating status. Then, the core operating parameters of each early warning device are extracted, that is, the real-time operating status of the early warning device associated with the network camera is obtained.

[0050] 105. Determine whether the real-time working status of the early warning device is in an early warning state.

[0051] For example, specifically, a status query command is sent to each early warning device, the status query command including the device identifier and query time range; status response messages are received from each early warning device, and the operating parameters of the early warning device are parsed from the status response messages. The operating parameters of the audible and visual early warning device include whether it is activated and the warning volume; the operating parameters of the remote message push module include whether a message has been sent and the list of receiving terminals; the operating parameters of the area access control interceptor include the door status and whether interception has been executed; if the operating parameters show that the audible and visual early warning device is activated, the remote message push module has sent a message, or the area access control interceptor has executed interception, the early warning device is determined to be in an alerted state. In this embodiment, the sending interval of the status query command can be set to 1 second, and the status response message adopts JSON format, which facilitates the parsing of operating parameters and avoids misjudging the device status by a single parameter through multi-dimensional judgment of operating parameters.

[0052] Optionally, in some embodiments of this application, the step of "determining whether the real-time operating status of the early warning device is an early warning state" may specifically include: Send a status query command to each early warning device, the status query command including the device identifier and the query time range; Receive status response messages from each early warning device, and parse the operating parameters of the early warning device from the status response messages; If the operating parameters meet the preset conditions, the early warning device is determined to be in an early warning state.

[0053] For example, specifically, based on a list of early warning devices associated with abnormal areas, a status query command can be generated individually for each early warning device. Then, a communication protocol compatible with the early warning device is used to send the status query command. After the early warning device receives and verifies the command's validity, it sends back a status response message containing its own operational status. The electronic device receives the message according to device identification, checking whether the message's timestamp falls within the query time interval, whether the message format conforms to preset specifications, and whether the checksum matches. If any condition is not met, the message is deemed invalid, and the device is temporarily treated as not having received an early warning and the anomaly is recorded. For valid messages, parameter parsing is performed. The electronic device has built-in preset conditions for the warning status of each type of early warning device, and the parsed operating parameters are compared one by one according to the device type.

[0054] If the operating parameters of a certain early warning device fully meet the corresponding preset conditions, the device is directly determined to be in an early warning state; if the preset conditions are not met, such as the sound and light early warning device not being activated or the push module failing to send, the device is determined to be in an unwarranted state.

[0055] 106. When the real-time working status of the warning device is in a non-warning state, send a warning trigger command to the warning device and perform a local risk recording operation.

[0056] For devices marked as not in a warning state, personalized trigger commands are generated according to the warning device type. Then, using a communication protocol adapted to the device, the trigger commands are sent sequentially according to the device identifier. Optionally, in some embodiments of this application, the sending order can be configured such that the priority of the area access control interceptor is higher than that of the luminous warning device.

[0057] Next, the local storage module is activated to generate a risk log file, which records the anomaly type, sub-region, occurrence timestamp, anomaly data details, and warning device information, and the log file is encrypted.

[0058] Furthermore, let's take the target monitoring area as the production workshop of the industrial park and the core control sub-area as the equipment operation area as an example for explanation: Network cameras A, B, and C are installed at the entrance of the production workshop, the equipment operation area, and the passageway sub-area, respectively. Temperature sensors and smoke sensors (environmental sensing devices) are installed next to each network camera. Early warning equipment includes audible and visual alarms in the workshop, a remote message push module that pushes messages to the management personnel's mobile APP, and access control interceptors at the passageway entrances.

[0059] Network cameras A, B, and C transmit real-time video streams to the backend electronic device via the RTSP protocol, while the environmental sensing device transmits real-time temperature and smoke concentration data via the Modbus protocol. The electronic device obtains the device number and installation location of each network camera, establishes the association between the sub-area and the device, and binds the addresses of the network cameras and the environmental sensing device.

[0060] The electronic device captures frames from the real-time video stream. First, it filters images that meet the clarity standards using the variance method. Then, it identifies personnel outlines or abnormal environmental features using the YOLO model to determine the initial image and adds a timestamp, device number, and sub-area identifier. The initial image is then associated with the environmental data of the corresponding sub-area to form a monitoring data set.

[0061] The electronic device extracts a first image (image of people entering the entrance) and a second image (image of people in the equipment operation area) from the monitoring data set. It extracts human features from the first image and matches them with the authorized personnel feature database. At the same time, it queries the access control verification record. If the feature matching value is less than 70% and access control verification is not performed, it is determined to be unauthorized entry. Simultaneously, it calculates the difference in shooting timestamps for the second image to obtain the duration of the person's stay. If it exceeds 15 minutes, it is determined to be abnormal behavior. It extracts the temperature value and smoke concentration value from the environmental data and compares them with the thresholds of 50℃ and 0.3mg / m³, respectively. If the values ​​exceed the thresholds, it is determined to be an environmental anomaly.

[0062] When abnormal personnel behavior or environmental anomalies are detected, a risk event is determined to have occurred. The electronic device sends a status query command to the early warning equipment, analyzes the feedback operating parameters, and determines whether an early warning has been issued.

[0063] If no warning is issued, the electronic device sends a trigger command to activate the sound and light alarm and lights. The remote message push module sends warning information such as personnel staying in the equipment operation area of ​​the production workshop for more than 15 minutes or the temperature exceeding the standard to the mobile APP of the management personnel.

[0064] Managers can query logs, view monitoring images and environmental data through a remote platform, promptly rush to the scene to handle risks, and subsequently export logs from the platform for event review.

[0065] The regional risk early warning method provided in this application acquires monitoring images of the target area collected by at least two network cameras set within the target monitoring area, as well as environmental data of the target area collected by an environmental sensing device associated with the network cameras. Based on the monitoring images, it determines whether abnormal human behavior exists within the target area, and based on the environmental data, it determines whether environmental anomalies exist within the target area. When abnormal human behavior or environmental anomalies are present, the real-time operating status of the early warning device associated with the network cameras is acquired. Then, it is determined whether the real-time operating status of the early warning device is in an alerted state. If the real-time operating status of the early warning device is in an alert-free state, an early warning trigger command is sent to the early warning device, and a local risk recording operation is performed. In the regional risk early warning scheme provided in this application, monitoring images collected by at least two network cameras within the target monitoring area and environmental data from associated environmental sensing devices are acquired. Abnormal human behavior is identified based on the monitoring images, and environmental anomalies are determined based on the environmental data. A risk event is determined if either of these conditions is met. The real-time operating status of the early warning device is then acquired, and an early warning is triggered and the risk is recorded when no warning is issued. By combining the detection of both human behavior and environmental status, and enabling the linkage between network cameras, early warning devices, and environmental sensing devices, the limitations of single-dimensional early warning are effectively avoided. This ensures timely early warning of risk events and complete recording of risk information. Therefore, it can solve the problems of single-dimensional early warning, poor linkage, untimely early warning, and difficulty in tracing in related technologies, and achieve the effects of comprehensive risk monitoring, accurate early warning, and convenient tracing.

[0066] To facilitate better implementation of the regional risk early warning method of this application embodiment, this application embodiment also provides a regional risk early warning device. The meanings of the terms used are the same as those in the aforementioned regional risk early warning system, and specific implementation details can be found in the description of the system embodiment.

[0067] Please see Figure 2 , Figure 2 This is a schematic diagram of the structure of a regional risk early warning device provided in an embodiment of this application. Specifically, the regional risk early warning device may include a first acquisition module 201, a first determination module 202, a second determination module 203, a second acquisition module 204, a third determination module 205, and an early warning module 206, as follows: The first acquisition module 201 is used to acquire target area monitoring images collected by at least two network cameras set in the target monitoring area, as well as target area environmental data collected by environmental sensing devices associated with the network cameras. The first determining module 202 is used to determine whether there is abnormal human behavior in the target area based on the monitoring image; The second determining module 203 is used to determine whether there is an environmental anomaly in the target area based on the environmental data; The second acquisition module 204 is used to acquire the real-time working status of the early warning device associated with the network camera when there is abnormal human behavior or environmental abnormality. The third determining module 205 is used to determine whether the real-time working status of the early warning device is an early warning state; The early warning module 206 is used to send an early warning trigger command to the early warning device and perform local risk recording operations when the real-time working status of the early warning device is a non-early warning state.

[0068] Optionally, in some embodiments of this application, the first acquisition module 201 may specifically be used for: Obtain the installation location of each network camera; Based on the installation location, each network camera is associated with a sub-region of the target monitoring area; The system receives real-time video streams transmitted by each network camera through a network communication protocol, and extracts frame images from the real-time video streams as initial images. Acquire real-time environmental data from environmental sensing devices that match the installation locations of each network camera; Based on the sub-region division results of the target monitoring area, the initial image is associated with the environmental data of the corresponding sub-region to form a monitoring data set with environmental attributes.

[0069] Optionally, in some embodiments of this application, the first acquisition module 201 may specifically be used for: The system performs image sharpness detection on each frame of the real-time video stream and filters out images with sharpness values ​​higher than a preset sharpness threshold. Perform personnel contour recognition and environmental feature recognition on the filtered images; Images containing complete human silhouettes or unusual environmental features are selected as initial images.

[0070] Optionally, in some embodiments of this application, the first determining module 202 may specifically be used for: Extract the movement trajectory features and dwell time information of the personnel from the surveillance images; When the dwell time information shows that the duration of a person's stay in the target monitoring area exceeds a preset dwell time threshold, or when the movement trajectory characteristics show that a person enters the target area from an unauthorized entrance, it is determined that there is abnormal behavior by the person.

[0071] Optionally, in some embodiments of this application, the first determining module 202 may specifically be used for: Extract the human body feature information of the person entering from the surveillance image; The human body feature information is matched with a preset authorized personnel feature database to calculate the feature matching value. If the feature matching value is lower than the preset authorization threshold and the person entering the area has not been verified by the authorization verification device at the entrance of the area, it is determined that there is an unauthorized person who has broken in.

[0072] Optionally, in some embodiments of this application, the second determining module 203 may also be used for: Temperature and smoke concentration values ​​are extracted from the environmental data and compared with preset safe temperature and safe smoke concentration thresholds, respectively. If the temperature value exceeds the safe temperature threshold or the smoke concentration value exceeds the safe smoke concentration threshold, an environmental anomaly is determined to exist.

[0073] Optionally, in some embodiments of this application, the early warning module 206 may specifically be used for: Send a status query command to each early warning device, the status query command including the device identifier and the query time range; Receive status response messages from each early warning device, and parse the operating parameters of the early warning device from the status response messages; If the operating parameters meet the preset conditions, the early warning device is determined to be in an early warning state.

[0074] This application provides a regional risk early warning device. A first acquisition module 201 acquires monitoring images of the target area collected by at least two network cameras located within the target monitoring area, and environmental data of the target area collected by an environmental sensing device associated with the network cameras. A first determination module 202 determines whether abnormal human behavior exists within the target area based on the monitoring images. A second determination module 203 determines whether environmental anomalies exist within the target area based on the environmental data. When abnormal human behavior or environmental anomalies are present, the second acquisition module 204 acquires the real-time operating status of the early warning device associated with the network cameras. Then, a third determination module 205 determines whether the real-time operating status of the early warning device is in an alerted state. If the real-time operating status of the early warning device is not in an alerted state, the early warning module 206 sends an early warning trigger command to the early warning device and performs a local risk recording operation. In the regional risk early warning scheme provided in this application, monitoring images collected by at least two network cameras within the target monitoring area and environmental data from associated environmental sensing devices are acquired. Abnormal human behavior is identified based on the monitoring images, and environmental anomalies are determined based on the environmental data. A risk event is determined if either of these conditions is met. The real-time operating status of the early warning device is then acquired, and an early warning is triggered and the risk is recorded when no warning is issued. By combining the detection of both human behavior and environmental status, and enabling the linkage between network cameras, early warning devices, and environmental sensing devices, the limitations of single-dimensional early warning are effectively avoided. This ensures timely early warning of risk events and complete recording of risk information. Therefore, it can solve the problems of single-dimensional early warning, poor linkage, untimely early warning, and difficulty in tracing in related technologies, and achieve the effects of comprehensive risk monitoring, accurate early warning, and convenient tracing. Furthermore, embodiments of this application also provide an electronic device, such as... Figure 3 As shown, it illustrates a structural schematic diagram of the electronic device involved in the embodiments of this application, specifically: The electronic device may include components such as a processor 301 with one or more processing cores, a memory 302 with one or more processor-readable storage media, a power supply 303, and an input unit 304. Those skilled in the art will understand that... Figure 3 The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements. Wherein: The processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines, and performs various functions and processes data by running or executing software programs and / or modules stored in the memory 302, and by calling data stored in the memory 302, thereby providing overall monitoring of the electronic device. Optionally, the processor 301 may include one or more processing cores; preferably, the processor 301 may integrate an application processor and a modem processor, wherein the application processor mainly handles the operating system, user interface, and applications, and the modem processor mainly handles wireless area risk warning. It is understood that the aforementioned modem processor may also not be integrated into the processor 301.

[0075] The memory 302 can be used to store software programs and modules. The processor 301 executes various functional applications and regional risk warning methods by running the software programs and modules stored in the memory 302. The memory 302 may mainly include a program storage area and a data storage area. The program storage area may store the operating system, application programs required for at least one function (such as sound playback function, image playback function, etc.), etc.; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, the memory 302 may also include a memory controller to provide the processor 301 with access to the memory 302.

[0076] The electronic device also includes a power supply 303 that supplies power to various components. Preferably, the power supply 303 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system. The power supply 303 may also include one or more DC or AC power supplies, recharging systems, power fault detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0077] The electronic device may also include an input unit 304, which can be used to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function control.

[0078] Although not shown, the electronic device may also include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the electronic device loads the executable files corresponding to the processes of one or more applications into the memory 302 according to the following instructions, and the processor 301 runs the applications stored in the memory 302 to realize various functions, as follows: Acquire monitoring images of the target area from at least two network cameras set within the target monitoring area, as well as environmental data of the target area from environmental sensing devices associated with the network cameras; determine whether there is abnormal human behavior within the target area based on the monitoring images; determine whether there is environmental anomaly within the target area based on the environmental data; when there is abnormal human behavior or environmental anomaly, acquire the real-time operating status of the early warning device associated with the network camera; determine whether the real-time operating status of the early warning device is in an alerted state; if the real-time operating status of the early warning device is in an alert-free state, send an early warning trigger command to the early warning device and execute local risk recording operations.

[0079] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0080] This application embodiment acquires monitoring images of the target area collected by at least two network cameras set within the target monitoring area, as well as environmental data of the target area collected by an environmental sensing device associated with the network cameras. Based on the monitoring images, it determines whether there is abnormal human behavior in the target area, and based on the environmental data, it determines whether there is an environmental anomaly in the target area. When there is abnormal human behavior or an environmental anomaly, it acquires the real-time operating status of the early warning device associated with the network camera. Then, it determines whether the real-time operating status of the early warning device is in an alerted state. If the real-time operating status of the early warning device is in an alert-free state, it sends an early warning trigger command to the early warning device and performs a local risk recording operation. In the regional risk early warning scheme provided in this application, monitoring images collected by at least two network cameras within the target monitoring area and environmental data from associated environmental sensing devices are acquired. Abnormal human behavior is identified based on the monitoring images, and environmental anomalies are judged based on the environmental data. If either of the two conditions is met, a risk event is determined. Then, the real-time operating status of the early warning device is acquired, and an early warning is triggered and the risk is recorded when no warning is issued. By combining the detection of both human behavior and environmental status, and enabling the linkage between network cameras, early warning devices, and environmental sensing devices, the limitations of single-dimensional early warning are effectively avoided. This ensures timely early warning of risk events and complete recording of risk information. Therefore, it can solve the problems of single-dimensional early warning, poor linkage, untimely early warning, and difficulty in tracing in related technologies, and achieve the effects of comprehensive risk monitoring, accurate early warning, and convenient tracing.

[0081] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be performed by instructions, or by instructions controlling related hardware. These instructions can be stored in a processor-readable storage medium and loaded and executed by a processor.

[0082] Therefore, embodiments of this application provide a storage medium storing multiple instructions that can be loaded by a processor to execute steps in any of the regional risk warning methods provided in embodiments of this application. For example, the instructions can execute the following steps: Acquire monitoring images of the target area from at least two network cameras set within the target monitoring area, as well as environmental data of the target area from environmental sensing devices associated with the network cameras; determine whether there is abnormal human behavior within the target area based on the monitoring images; determine whether there is environmental anomaly within the target area based on the environmental data; when there is abnormal human behavior or environmental anomaly, acquire the real-time operating status of the early warning device associated with the network camera; determine whether the real-time operating status of the early warning device is in an alerted state; if the real-time operating status of the early warning device is in an alert-free state, send an early warning trigger command to the early warning device and execute local risk recording operations.

[0083] For details on the implementation of each of the above operations, please refer to the previous examples, which will not be repeated here.

[0084] The storage medium may include: read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0085] Since the instructions stored in the storage medium can execute the steps in any of the regional risk warning methods provided in the embodiments of this application, the beneficial effects that any of the regional risk warning methods provided in the embodiments of this application can achieve can be realized. For details, please refer to the previous embodiments, which will not be repeated here.

[0086] The above provides a detailed description of a regional risk warning method, device, electronic device, and storage medium provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A regional risk early warning method, characterized in that, include: Acquire target area monitoring images captured by at least two network cameras set within the target monitoring area, as well as target area environmental data collected by an environmental sensing device associated with the network cameras; Based on the surveillance images, determine whether there is any abnormal human behavior within the target area; Based on the environmental data, determine whether there are environmental anomalies in the target area; When there are abnormal human behaviors or environmental abnormalities, the real-time working status of the early warning devices associated with the network camera is obtained; Determine whether the real-time operating status of the early warning device is in an early warning state; When the real-time working status of the warning device is in a non-warning state, a warning trigger command is sent to the warning device, and a local risk recording operation is performed.

2. The regional risk early warning method according to claim 1, characterized in that, The step of determining whether there is abnormal human behavior in the target area based on the monitoring image includes: Extract the movement trajectory features and dwell time information of the personnel from the surveillance images; When the dwell time information shows that the duration of a person's stay in the target monitoring area exceeds a preset dwell time threshold, or when the movement trajectory characteristics show that a person enters the target area from an unauthorized entrance, it is determined that there is abnormal behavior by the person.

3. The regional risk early warning method according to claim 1, characterized in that, The step of determining whether there are environmental anomalies in the target area based on the environmental data includes: Temperature and smoke concentration values ​​are extracted from the environmental data and compared with preset safe temperature and safe smoke concentration thresholds, respectively. If the temperature value exceeds the safe temperature threshold or the smoke concentration value exceeds the safe smoke concentration threshold, an environmental anomaly is determined to exist.

4. The regional risk early warning method according to claim 1, characterized in that, The acquisition of target area monitoring images captured by at least two network cameras set within the target monitoring area, and target area environmental data collected by environmental sensing devices associated with the network cameras, includes: Obtain the installation location of each network camera; Based on the installation location, each network camera is associated with a sub-region of the target monitoring area; The system receives real-time video streams transmitted by each network camera through a network communication protocol, and extracts frame images from the real-time video streams as initial images. Acquire real-time environmental data from environmental sensing devices that match the installation locations of each network camera; Based on the sub-region division results of the target monitoring area, the initial image is associated with the environmental data of the corresponding sub-region to form a monitoring data set with environmental attributes.

5. The regional risk early warning method according to claim 4, characterized in that, Extracting frame images from the real-time video stream as initial images includes: For each frame of the real-time video stream, image sharpness is detected, and images with sharpness values ​​higher than a preset sharpness threshold are selected. Perform personnel contour recognition and environmental feature recognition on the filtered images; Images containing complete human silhouettes or unusual environmental features are selected as initial images.

6. The regional risk early warning method according to claim 1, characterized in that, The step of determining whether there is abnormal human behavior in the target area based on the monitoring image includes: Extract the human body feature information of the person entering from the surveillance image; The human body feature information is matched with a preset authorized personnel feature database to calculate the feature matching value. If the feature matching value is lower than the preset authorization threshold and the person entering the area has not been verified by the authorization verification device at the entrance of the area, it is determined that there is an unauthorized person who has broken in.

7. The regional risk early warning method according to claim 1, characterized in that, Determining whether the real-time operating status of the early warning device is in an early warning state includes: Send a status query command to each early warning device, the status query command including the device identifier and the query time range; Receive status response messages from each early warning device, and parse the operating parameters of the early warning device from the status response messages; If the operating parameters meet the preset conditions, the early warning device is determined to be in an early warning state.

8. A regional risk early warning device, characterized in that, include: The first acquisition module is used to acquire target area monitoring images collected by at least two network cameras set in the target monitoring area, as well as target area environmental data collected by environmental sensing devices associated with the network cameras. The first determining module is used to determine whether there is abnormal human behavior in the target area based on the monitoring image; The second determining module is used to determine whether there are environmental anomalies in the target area based on the environmental data; The second acquisition module is used to acquire the real-time working status of the early warning device associated with the network camera when there is abnormal human behavior or environmental abnormality. The third determining module is used to determine whether the real-time working status of the early warning device is an early warning state; The early warning module is used to send an early warning trigger command to the early warning device and perform local risk recording operations when the real-time working status of the early warning device is a no-early-warning state.

9. An electronic device, characterized in that, include: A memory, a processor, and a processor program stored in the memory and executable on the processor, wherein the processor executes the program as steps of the regional risk warning method as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The system contains a computer processing program that can be loaded by a processor and executed as described in any one of claims 1 to 7.

Images