Early warning method and system for intelligently detecting afterheat recombustion of fire scene based on AR glasses

Abstract

The invention discloses an early warning method and system for intelligently detecting fire scene waste heat reburning based on AR glasses, and relates to the technical field of fire safety intelligent monitoring. The early warning method comprises the following steps: scanning a conical area in front of a visual field in real time based on AR glasses, capturing temperature matrix data and collecting environmental parameter data, and identifying afterheat hot spots in the visual field and associated article types based on a YOLOv8s model; based on edge AI comprehensive temperature matrix data and environmental parameter data, risk indexes of residual heat hot spots are calculated in real time and visualized into low, medium and high risks; locking and analyzing the temperature change of the medium-high risk article, dynamically correcting the safety coefficient in combination with an article material database, and visualizing the detailed information, the real-time temperature and the risk index of the article; and spraying and cooling the high-risk target based on the guidance of AR glasses, and judging whether the risk is relieved or not according to the temperature attenuation rate and the risk index. By implementing the technical scheme provided by the invention, the fire scene afterheat after-combustion hidden danger can be quickly, comprehensively and intuitively detected.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent monitoring of fire safety, more specifically, to a warning method and system for intelligent detection of fire field afterglow reburning based on AR glasses. BACKGROUND

[0002] Fire field cleaning and safety inspection after fire extinguishing is of great importance, and residual high-temperature cinder (afterglow hot spot) is the main hidden danger leading to reburning accidents, which seriously threatens the safety of firefighters and subsequent disposal personnel, and may cause secondary property loss. At present, fire field afterglow detection mainly relies on the experience judgment of firefighters and manual investigation by handheld thermal imaging instruments or point temperature guns. However, this method has significant limitations: in a complex fire field environment, especially in the presence of a large amount of debris, obstacle shielding or insufficient light, firefighters have difficulty in quickly and accurately locating afterglow hot spots covered by coverings or in the deep structure with naked eyes; at the same time, operating handheld devices requires firefighters to frequently look down to check the screen or operate the instrument, which not only is inefficient, but also distracts their attention in dangerous environments, increases the risk of action, and makes it difficult to form an intuitive and overall understanding of the overall afterglow distribution of the fire field.

[0003] Although augmented reality (AR) technology has been preliminarily explored and applied in the field of firefighting, such as for route planning or information superimposition, its deep integration with afterglow detection technology to realize real-time visual warning of potential reburning points and directly present hidden afterglow information in the field of vision of firefighters in an intuitive and non-interfering manner is still a blank.

[0004] Therefore, there is an urgent need to provide a solution to quickly, comprehensively and intuitively detect fire field afterglow reburning hidden dangers and improve the limitations of fire field afterglow detection relying on the experience judgment of firefighters to significantly reduce the risk of reburning and ensure the safety of personnel life. SUMMARY

[0005] The purpose of the present application is to provide a warning method and system for intelligent detection of fire field afterglow reburning based on AR glasses, which improves the convenience of fire field afterglow hidden danger investigation.

[0006] The warning method for intelligent detection of fire field afterglow reburning based on AR glasses provided by the present application adopts the following technical solution:

[0007] The AR glasses are activated, a cone-shaped area in front of the field of view is scanned in real time based on the AR glasses, temperature matrix data and environmental parameter data are captured, and YOLOv8s model is used to identify afterglow hot spots and their associated item types in the field of view;

[0008] Based on edge AI, the temperature matrix data and the environmental parameter data are comprehensively calculated to obtain the risk index of the afterglow hot spots in real time, and the risk index is visualized as low, medium and high risks.

[0009] Lock and analyze the temperature change of high-risk goods, dynamically correct the safety factor combined with the material database of the goods, and visualize the detailed information, real-time temperature and risk index of the goods;

[0010] Based on AR glasses, guide to spray cooling on high-risk targets, and judge whether to remove the risk through temperature decay rate and risk index.

[0011] Preferably, the process of activating the AR glasses includes:

[0012] The fire residual temperature afterburning intelligent detection mode of the activated AR glasses automatically loads the afterburning risk assessment algorithm, presets the temperature threshold and risk parameter weight based on the fire type, simultaneously activates the visible light camera, thermal imaging camera, air pressure sensor, humidity sensor and oxygen concentration sensor integrated in the glasses, all sensors perform synchronous data acquisition at a frequency of 10Hz, and the AR glasses can be controlled by voice instructions or gestures or buttons when activated.

[0013] Preferably, during the process of real-time scanning the front conical area of the field of view based on the AR glasses, capturing temperature matrix data and collecting environmental parameter data, it includes:

[0014] Based on the visible light camera integrated in the AR glasses, the front conical area of the field of view is scanned in real time, the conical area is 120° in front of the field of view, the distance is 0.5 to 5 meters, the temperature matrix data is captured based on the thermal imaging camera integrated in the AR glasses, and the environmental parameter data is collected based on multiple sensors, including air pressure, humidity and oxygen concentration.

[0015] Preferably, during the process of real-time calculation of the risk index of the residual temperature hot spot based on the edge AI comprehensive temperature matrix data and environmental parameter data, the afterburning risk assessment algorithm is used for calculation, and the calculation formula is as follows:

[0016] R=(α·T_level)×(β / S_c)×e (γ·T) ×(1+δ·C_type)×(1-η·H)×(1+θ·D)×[1+k·(O2-O0) / O0]×(1+λ·ΔP / P0);

[0017] Wherein, R is a risk index, a is a temperature classification weight, T_level is a temperature level, b is a safety factor inverse amplification factor, S_c is a safety factor based on the carbonization state of the object, g is a temperature index growth coefficient, T is a heat source temperature, d is a flammability enhancement coefficient, C_type is an object type, h is a humidity suppression coefficient, H is an environmental humidity, q is a time accumulation coefficient, D is a high-temperature duration, k is an oxygen sensitivity coefficient, O2 is the real-time detected environmental oxygen content, O0 is the standard atmospheric oxygen content, l is a gas pressure coefficient, AP is a gas pressure difference, P0 is a reference gas pressure.

[0018] Preferably, the visualization of the low, medium and high risk processes includes:

[0019] When the risk index is less than 100, it is a low risk, and the display screen of the AR glasses penetrates and displays a blue box containing the real-time temperature in the residual heat spot area;

[0020] When the risk index is greater than or equal to 100 and less than or equal to 500, it is a medium risk, and the display screen of the AR glasses penetrates and displays an orange warning box containing the real-time temperature in the residual heat spot area and flashes;

[0021] When the risk index is greater than 500, it is a high risk, and the display screen of the AR glasses penetrates and displays a red warning box containing the real-time temperature in the residual heat spot area and flashes.

[0022] Preferably, the process of determining whether to remove the risk by the temperature decay rate and the risk index includes:

[0023] After spraying cooling on the high-risk target, the global temperature distribution map penetrated and displayed is switched to a single high-risk heat spot detail by command, and a 3-second gaze on the area triggers a verification scan;

[0024] When the temperature decay rate is less than or equal to -2℃ / s, and the risk index is less than 100, a green safety mark is penetrated and displayed, and a voice prompt is given to remove the risk; otherwise, the warning is intensified, the red warning box flashes at double the frequency, and an optimized disposal scheme is superimposed and displayed.

[0025] Preferably, the early warning method further includes:

[0026] The AR glasses integrated gas pressure sensor monitors the gas pressure change in real time, the AR glasses integrated GPS obtains real-time positioning information, and the motion state and floor change information of the firefighter are obtained based on the gas pressure change and real-time positioning.

[0027] The second aspect of the application provides an early warning system for intelligent detection of residual heat rekindling in a fire scene based on AR glasses, including a data acquisition module, a data processing module, a real-time analysis module and a risk processing module, wherein:

[0028] A data acquisition module is configured to activate the AR glasses, scan a conical area in front of a field of view in real time based on the AR glasses, capture temperature matrix data and collect environmental parameter data, and identify residual heat spots and associated item types in the field of view based on a YOLOv8s model;

[0029] A data processing module is configured to calculate a risk index of the residual heat spots in real time based on the edge AI comprehensive temperature matrix data and the environmental parameter data, and visualize the risk index as low, medium and high risks.

[0030] A real-time analysis module is configured to lock and analyze temperature changes of the medium and high risk items, dynamically correct a safety factor in combination with an item material database, and visualize detailed information, real-time temperature and the risk index of the items.

[0031] A risk processing module is configured to guide spraying cooling on the high risk target based on the AR glasses, and determine whether to remove the risk based on a temperature decay rate and the risk index.

[0032] A third aspect of the present application provides an electronic device, characterized in that the electronic device comprises:

[0033] at least one processor; and

[0034] a memory connected in communication with the at least one processor; wherein

[0035] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the method of any one of the above aspects.

[0036] A fourth aspect of the present application provides a computer readable storage medium comprising a storage data area and a storage program area, the storage data area stores created data, and the storage program area stores a computer program; wherein the computer program is executed by a processor to implement the method of any one of the above aspects.

[0037] The early warning method for intelligent detection of residual heat reburning in a fire scene based on AR glasses has the beneficial effects that:

[0038] 1、The present application scans the fire scene environment in real time through the AR glasses, and displays the detected residual heat spot position, temperature distribution and danger level information in a visual augmented reality graphic superimposed on the real fire scene viewed by the user through the glasses through the penetration display function of the AR glasses, so that the deep residual heat spots that are blocked or cannot be identified by the naked eye can be quickly, comprehensively and intuitively found without interference.

[0039] 2、The application can improve the efficiency and accuracy of residual heat spot rekindling detection, significantly reduce the risk of fire rekindling, and ensure personnel safety by using the rekindling risk assessment algorithm to calculate the risk index based on the comprehensive environment of the article. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 A flowchart of the early warning method for intelligent detection of fire field residual heat rekindling based on AR glasses is provided for the embodiments of the application.

[0041] Figure 2 A structural diagram of an electronic device is provided for the embodiments of the application. DETAILED DESCRIPTION

[0042] In order to make the technical problems, technical solutions and beneficial effects of the present application clearer, the following will further describe the present application in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0043] It should be noted that when a component is referred to as "fixed" or "set" or "connected" to another component, it can be directly or indirectly located on the other component. The terms "up", "down", "left", "right", "front", "back", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc. indicate the orientation or position based on the orientation or position shown in the drawings, and are only for convenience of description, and cannot be understood as a limitation on the technical solutions. The terms "first", "second", etc. are only for the purpose of convenient description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features. The meaning of "multiple" is two or more, unless otherwise specifically limited. The meaning of "several" is one or more, unless otherwise specifically limited.

[0044] The embodiments of the present application provide an early warning method for intelligent detection of fire field residual heat rekindling based on AR glasses, referring to Figure 1 , comprising:

[0045] S1, activate the AR glasses, scan the front conical area of the field of view based on the AR glasses in real time, capture temperature matrix data and collect environmental parameter data, identify the residual heat spot and its associated article type in the field of view based on the YOLOv8s model;

[0046] S2, based on edge AI, comprehensively calculate the risk index of the residual heat spot based on the temperature matrix data and the environmental parameter data, and visualize it as low, medium and high risk;

[0047] S3, lock and analyze the temperature change of high-risk items, dynamically correct the safety factor combined with the material database of the item, and visualize the detailed information, real-time temperature and risk index of the item;

[0048] S4, based on AR glasses, guide to spray cooling on high-risk targets, and judge whether to remove the risk through temperature decay rate and risk index.

[0049] In some embodiments, during the execution of step S1, the following steps are included:

[0050] S1.1, activate the AR glasses;

[0051] S1.2, based on the AR glasses, real-time scan the conical area in front of the field of view, capture temperature matrix data and collect environmental parameter data;

[0052] S1.3, based on the YOLOv8s model, identify the residual heat spots in the field of view and their associated item types.

[0053] Specifically, during the execution of step S1.1, activating the AR glasses, the following steps are included:

[0054] After the firefighter wears the AR glasses, the fire scene residual heat reignition intelligent detection mode of the AR glasses is activated, the reignition risk assessment algorithm is automatically loaded, the temperature threshold and risk parameter weight are preset based on the fire scene type, and the visible light camera, thermal imaging camera, air pressure sensor, humidity sensor and oxygen concentration sensor integrated in the AR glasses are activated. All sensors perform synchronous data acquisition at a frequency of 10Hz. When the AR glasses are activated, voice instructions, gesture control or button control can be used.

[0055] Further, during the execution of step S1.2, based on the AR glasses, real-time scan the conical area in front of the field of view, capture temperature matrix data and collect environmental parameter data, the following steps are included:

[0056] The firefighter maintains a natural standing posture, the visible light camera integrated in the AR glasses real-time scans the conical area in front of the field of view, the conical area is 120° in front of the field of view, the distance is 0.5 to 5 meters, the thermal imaging camera integrated in the AR glasses captures temperature matrix data, and the multiple sensors collect environmental parameter data, including air pressure, humidity and oxygen concentration.

[0057] In fact, during the real-time scanning of the conical area in front of the field of view, the visible light camera synchronously collects RGB images and performs preprocessing, extracts the outline and material type characteristics of the item.

[0058] Specifically, during the execution of step S1.3, based on the YOLOv8s model, identifying the residual heat spots in the field of view and their associated item types, the following steps are included:

[0059] The edge AI engine synchronizes and aligns the temperature matrix data with the visible light image in space-time, encodes the environmental parameters (oxygen concentration, air pressure, humidity) into a 3-channel tensor and splices it with the temperature matrix into a multi-channel thermal feature map, simultaneously fuses the contour information of the visible light image into the thermal feature map through an attention mechanism, and generates a fusion feature tensor containing temperature, contour, material and environmental information.

[0060] Further, the YOLOv8s receives the fusion feature tensor, and the backbone network of the YOLOv8s extracts the fusion feature in layers, wherein the shallow layer feature retains the detail information of temperature and contour, such as local hotspot edge and item texture, and the deep layer feature fuses multi-scale semantic information, such as item category and temperature distribution pattern, through cross-stage partial connection. In the feature pyramid network stage, a bidirectional feature fusion module is introduced to dynamically weight and fuse the deep layer semantic feature and the shallow layer detail feature, and at the same time, a channel attention mechanism is used to enhance the feature channels related to the residual temperature detection and suppress irrelevant noise. In the detection head part, a decoupling head design is adopted to regress and classify the residual temperature hotspot and the item type respectively; for the residual temperature hotspot, a temperature perception regression branch is used to predict the hotspot bounding box coordinates, and a temperature threshold constraint is introduced, and the contour feature is combined to optimize the adhesion of the bounding box; for the item type, the classification branch uses the material feature and the environmental parameter to assist in judgment, and a multi-label classification strategy is used to process the multiple attributes of the associated items. Finally, the non-maximum suppression is used to merge the overlapping detection boxes, and the detection result containing the fusion temperature, position and item type information is output, so as to display the residual temperature hotspot and its associated item type.

[0061] In some embodiments, in the process of performing step S2, the following steps are included:

[0062] S2.1, based on edge AI, integrating temperature matrix data and environmental parameter data, real-time calculating the risk index of residual temperature hotspot;

[0063] S2.2, visualizing the risk index of residual temperature hotspot as low, medium and high risk;

[0064] Specifically, in the process of performing step S2.1, the calculation is performed using a reburning risk assessment algorithm, and the calculation formula is as follows:

[0065] R=(α·T_level)×(β / S_c)×e (γ·T) ×(1+δ·C_type)×(1-η·H)×(1+θ·D)×[1+κ·(O2-O0) / O0]×(1+λ·ΔP / P0);

[0066] Wherein, R is the risk index, a is the temperature classification weight, T_level is the temperature level, β is the safety factor inverse amplification factor, S_c is the safety factor based on the carbonization state of the object, γ is the temperature index growth coefficient, T is the heat source temperature, δ is the flammability enhancement coefficient, C_type is the object type, η is the humidity inhibition coefficient, H is the environmental humidity, θ is the time accumulation coefficient, D is the high temperature duration, κ is the oxygen sensitivity coefficient, O2 is the real-time detected environmental oxygen content, O0 is the standard atmospheric oxygen content, λ is the air pressure coefficient, ΔP is the air pressure difference, P0 is the reference air pressure.

[0067] In fact, T_level is divided into 3 levels, T_level is 1 for low temperature, temperature ≤ 100℃, T_level is 2 for medium temperature, temperature is 100-300℃, T_level is 3 for high temperature, temperature > 300℃, S_c is linearly decreased from 1.0 for new objects to 0.1 for carbonized damaged objects, C_type is 0.1 for non-flammable materials such as metals, C_type is 0.3 for flammable materials such as wood, and C_type is 0.5 for flammable materials such as chemicals.

[0068] Further, the temperature classification weight a = 0.8, the safety factor inverse amplification factor β = 1.5, the temperature index growth coefficient γ = 0.015, the flammability enhancement coefficient δ = 0.7, the humidity inhibition coefficient η = 0.005, the time accumulation coefficient θ = 0.01, the oxygen sensitivity coefficient κ = 1.5, and the air pressure coefficient λ = 0.8. The weight coefficients can be adjusted in the background according to actual conditions.

[0069] Specifically, in the process of executing step S2.2, it includes: when the risk index is less than 100, it is low risk, the display screen of the AR glasses penetrates and displays a blue square box containing real-time temperature in the residual heat spot area; when the risk index is greater than or equal to 100 and less than or equal to 500, it is medium risk, the display screen of the AR glasses penetrates and displays an orange warning box containing real-time temperature in the residual heat spot area and flashes; when the risk index is greater than 500, it is high risk, the display screen of the AR glasses penetrates and displays a red warning box containing real-time temperature in the residual heat spot area and flashes.

[0070] In fact, all warning graphics can be accurately superimposed on the actual object position in the firefighter's field of view through the waveguide optical system.

[0071] In some embodiments, in the process of executing step S3, it includes:

[0072] When a medium-high risk target is detected, the firefighter locks the item through voice instructions or gesture control or key control, and the AR glasses built-in system automatically starts a deep scanning mode: the visible light camera analyzes the type and state of the item, the thermal imaging camera focuses on analyzing temperature changes, and the item material database is combined to dynamically correct the safety factor S_c according to the item type and carbonization degree, and the detailed information of the item, the real-time temperature and the risk index are generated in the AR field of view.

[0073] Further, the data is uploaded to the background, and when the firefighter cannot make independent judgment according to the information, the background will be consulted for decision-making.

[0074] In some embodiments, during the execution of step S4, the following steps are included:

[0075] After spraying and cooling the high-risk target based on the AR glasses guidance, the global temperature distribution graph displayed through the instruction is switched to the details of a single high-risk hotspot, and the area is kept under observation for 3 seconds to trigger the verification scan.

[0076] Further, when the temperature decay rate is less than or equal to -2℃ / s, and the risk index is less than 100, a green safety mark is displayed through penetration, and a voice prompt is given that the risk has been eliminated; otherwise, the warning is intensified, the red warning box flashes at double the frequency, and an optimized disposal scheme is generated and displayed.

[0077] In fact, all detection data during the scanning process automatically generates a timestamped electronic report, including temperature distribution, risk value, disposal record, etc. At the end of the inspection, a text file is exported through voice instructions or gesture control or key control, and is transmitted to the command center through WIFI or 4G wireless transmission. Finally, the "mode end" instruction is executed to return to standby state.

[0078] In some embodiments, during the execution of the pre-warning method, the following steps are further included: real-time monitoring of air pressure changes based on the air pressure sensor integrated in the AR glasses, obtaining real-time positioning information based on the GPS integrated in the AR glasses, and obtaining the motion state and floor change information of the firefighter based on the air pressure changes and real-time positioning.

[0079] Further, the motion state is divided into three types:

[0080] State 1 is floor plane motion: Z-axis motion is small, XY-axis motion is large, and air pressure change is small and not continuous, and the person moves within the current floor. At this time, the air pressure sensor is zeroed, the current floor is confirmed, and the floor number is updated;

[0081] ∣A Z (t)-g∣<θ Z ;

[0082]

[0083] |P(t)-P(t-Δ t )|<θ P , and P(t) is discontinuous;

[0084] wherein, A Z (t) is the Z-axis acceleration of the gyroscope, g is the acceleration of gravity, θ Z is the Z-axis acceleration threshold, A X (t) is the X-axis acceleration, A Y (t) is the Y-axis acceleration, θ XY is the XY-axis acceleration threshold, P(t) is the real-time air pressure, Δ t is the time change value, θ P is the air pressure change threshold.

[0085] State 2 is going up and down the stairs: the Z-axis moves a lot, the XY-axis also moves and has a repeated motion phenomenon, and the air pressure changes a lot and continuously, and the personnel is going up and down the stairs. The air pressure value changes, the air pressure change is calculated all the time until entering state 1, the number of floors is confirmed according to the change, and the number of floors is updated;

[0086] |A Z (t)-g|>θ Z ;

[0087] and the signs of A X (t) and A Y (t) change many times;

[0088] |P(t)-P(t-Δ t |>θ P , and P(t) continuously changes.

[0089] State 3 is vertical up and down the stairs (such as elevator): the Z-axis moves a lot, the XY-axis changes a little, and the air pressure changes a lot and continuously, and the personnel is vertically moving. The air pressure value changes, the air pressure change is calculated all the time until entering state 1, the number of floors is confirmed according to the change, and the number of floors is updated.

[0090] |A Z (t)-g|>θ Z ;

[0091]

[0092] |P(t)-P(t-Δ t |>θ P , and P(t) continuously changes.

[0093] Further, according to the above three motion modes, the floor change is determined, and the determination formula is as follows:

[0094] ΔPtotal = ∑(P(t) - P(t-Δ t ));

[0095]

[0096] current floor = current floor + Δfloor;

[0097] wherein ΔP total is a cumulative value of air pressure change, Δfloor is a floor change value, P per is a difference value of air pressure between each floor, current floor is a current floor value.

[0098] The embodiment of the present application also provides a warning system for intelligently detecting fire field residual temperature afterburning based on AR glasses, comprising a data acquisition module, a data processing module, a real-time analysis module and a risk processing module, wherein:

[0099] The data acquisition module is used for activating the AR glasses, scanning a conical area in front of a field of view based on the AR glasses in real time, capturing temperature matrix data and collecting environmental parameter data, and identifying residual temperature hot spots and their associated article types in the field of view based on a YOLOv8s model.

[0100] The data processing module is used for comprehensively processing the temperature matrix data and the environmental parameter data based on edge AI, calculating a risk index of the residual temperature hot spots in real time, and visualizing the risk index as low, medium and high risks.

[0101] The real-time analysis module is used for locking and analyzing temperature changes of medium and high risk articles, dynamically correcting a safety coefficient in combination with an article material database, and visualizing detailed information of the articles, real-time temperatures and the risk index.

[0102] The risk processing module guides spraying and cooling on a high risk target based on the AR glasses, and judges whether to release the risk through a temperature decay rate and the risk index.

[0103] The embodiment also discloses an electronic device, referring to Figure 2 The electronic device can comprise a processor 10, a memory 11, a communication bus 12 and a communication interface 13, and can further comprise a computer program stored in the memory 11 and executable on the processor 10, such as a warning program for intelligently detecting fire field residual temperature afterburning based on AR glasses.

[0104] The processor 10 may, in some embodiments, be composed of integrated circuits, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits of the same or different functions, including one or more combinations of central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and various control chips. The processor 10 is the control unit of the electronic device, connects various components of the electronic device through various interfaces and lines, executes programs or modules stored in the memory 11 (for example, executes the early warning program for intelligent detection of fire scene residual temperature rekindling based on AR glasses), and calls data stored in the memory 11 to perform various functions and process data of the electronic device.

[0105] The memory 11 includes at least one type of readable storage medium, including flash memories, mobile hard disks, multimedia cards, card-type memories (for example, SD or DX memories, etc.), magnetic memories, magnetic disks, optical disks, etc. The memory 11 may, in some embodiments, be an internal storage unit of the electronic device, for example, a mobile hard disk of the electronic device. The memory 11 may, in other embodiments, also be an external storage device of the electronic device, for example, a plug-in mobile hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. Further, the memory 11 may include both an internal storage unit and an external storage device of the electronic device. The memory 11 can be used not only to store application software and various data installed in the electronic device, for example, the code of the early warning program for intelligent detection of fire scene residual temperature rekindling based on AR glasses, but also to temporarily store data that has been or will be output.

[0106] The communication bus 12 can be a peripheral component interconnect (PCI) bus or an extended industry standard architecture (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize the connection and communication between the memory 11, the processor 10, etc.

[0107] The communication interface 13 is used for communication between the electronic device and other devices, including a network interface and a user interface. Optionally, the network interface can include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is usually used to establish a communication connection between the electronic device and other electronic devices. The user interface can be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface can also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display can be an LED display, a liquid crystal display, a touch liquid crystal display, and an OLED (Organic Light-Emitting Diode) touch screen, etc. Among them, the display can also be appropriately called a display screen or a display unit, which is used to display information processed in the electronic device and to display a visualized user interface.

[0108] Figure 2 Only the electronic device with components is shown, and those skilled in the art can understand that, Figure 2 The structure shown does not constitute a limitation on the electronic device, and can include fewer or more components than shown, or combine certain components, or different component arrangements.

[0109] For example, although not shown, the electronic device can also include a power source (such as a battery) to power each component. Preferably, the power source can be logically connected to the at least one processor 10 through a power management system, so that functions such as charge management, discharge management, and power consumption management can be realized through the power management system. The power source can also include one or more direct current or alternating current power sources, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and any other components. The electronic device can also include various sensors, Bluetooth modules, Wi-Fi modules, etc., which are not described here.

[0110] It should be understood that the embodiments are only for illustration and are not limited in the scope of the patent application by this structure.

[0111] The combination of the warning program for AR glasses intelligent detection of fire residual temperature afterburning stored in the memory 11 in the electronic device can realize:

[0112] S1, activate the AR glasses, based on the AR glasses, scan the front conical area of the field of view in real time, capture temperature matrix data and collect environmental parameter data, and identify the residual temperature hot spots and their associated object types in the field of view based on the YOLOv8s model;

[0113] S2, based on edge AI, integrate temperature matrix data and environmental parameter data, real-time calculate the risk index of residual temperature hot spot, and visualize as low, medium and high risk;

[0114] S3, lock and analyze the temperature change of the medium and high risk goods, dynamically correct the safety factor combined with the goods material database, and visualize the detailed information, real-time temperature and risk index of the goods;

[0115] S4, based on AR glasses, guide to spray cooling for high-risk targets, and judge whether to remove the risk through temperature attenuation rate and risk index.

[0116] Specifically, the specific implementation method of the processor 10 to the above computer program can refer to Figure 1 The description of the related steps in the corresponding embodiment is not repeated here.

[0117] Further, the modules / units integrated in the electronic device, if realized in the form of software function units and sold or used as independent products, can be stored in a non-volatile computer readable storage medium. The computer readable storage medium can be volatile or non-volatile. For example, the computer readable medium can include any entity or system, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory).

[0118] The embodiment of the application also discloses a computer readable storage medium, the readable storage medium stores a computer program, when the computer program is executed by the processor of the electronic device, can realize:

[0119] S1, activate the AR glasses, based on the real-time scanning of the AR glasses in the conical area in front of the field of view, capture temperature matrix data and collect environmental parameter data, identify the residual temperature hot spot and its associated goods type in the field of view based on YOLOv8s model;

[0120] S2, based on edge AI, integrate temperature matrix data and environmental parameter data, real-time calculate the risk index of residual temperature hot spot, and visualize as low, medium and high risk;

[0121] S3, lock and analyze the temperature change of the medium and high risk goods, dynamically correct the safety factor combined with the goods material database, and visualize the detailed information, real-time temperature and risk index of the goods;

[0122] S4, based on AR glasses, guide to spray cooling for high-risk targets, and judge whether to remove the risk through temperature attenuation rate and risk index.

[0123] In several embodiments provided by the present application, it should be understood that the disclosed devices, systems and methods can be implemented in other manners. For example, the system embodiments described above are merely illustrative. For example, the division of the modules is merely logical function division. In actual implementation, other division manners can be adopted.

[0124] The modules illustrated as separated components can or can not be physically separated, and the components illustrated as modules can or can not be physical units, that is, can be located in one place, or can be distributed on multiple network units. Part or all of the modules can be selected according to actual needs to achieve the purpose of the embodiments.

[0125] In addition, each function module in each embodiment of the present application can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of hardware plus software function modules.

[0126] It is obvious for those skilled in the art that the present application is not limited to the details of the above exemplary embodiments, and the present application can be implemented in other specific forms without departing from the spirit or essential characteristics of the present application.

[0127] Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting, and the scope of the present application is defined by the appended claims rather than the above description, and therefore all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present application. Any additional reference signs in the claims should not be considered as limiting the claims involved.

[0128] The blockchain referred to in the present application is a new application mode of distributed data storage, peer-to-peer transmission, consensus mechanism, encryption algorithm and other computer technologies. Blockchain, in essence, is a decentralized database, a series of data blocks associated using cryptography. Each data block contains information about a batch of network transactions, used to verify the validity (anti-fake) of the information and generate the next block. The blockchain can include a blockchain underlying platform, a platform product service layer, and an application service layer.

[0129] The embodiments of the present application can acquire and process related data based on artificial intelligence technology. Among them, artificial intelligence (Artificial Intelligence, AI) is to use digital computers or digital computer controlled machines to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results. Theory, method, technology and application system.

[0130] Furthermore, the word "comprising" does not exclude other elements or steps, and the singular does not exclude the plural and vice-versa, unless the context clearly requires these exclusions. The mere fact that different features are recited in mutually different dependent claims does not indicate that the

[0131] Finally, it should be noted that the above-mentioned embodiments illustrate rather than limit the application, since the skilled person, having regard to the above-mentioned teaching, will be able to carry out equivalent modifications or alternative techniques without departing from the scope of the application.

Claims

1. An early warning method for intelligent detection of fire residual temperature afterglow based on AR glasses, characterized in that, The method comprises the following steps: activating the AR glasses, capturing temperature matrix data and collecting environmental parameter data based on real-time scanning of a conical area in front of the field of view of the AR glasses, identifying residual heat spots and their associated item types in the field of view based on a YOLOv8s model; based on edge AI, integrating the temperature matrix data and the environmental parameter data, real-time calculation of the risk index of the residual heat spot, and visualization as low, medium and high risk; locking and analyzing the temperature change of the medium and high risk items, dynamically correcting the safety factor in combination with the item material database, and visualizing the detailed information, real-time temperature and risk index of the items; based on the AR glasses, guiding the spraying cooling of the high-risk target, and judging whether to remove the risk through the temperature decay rate and the risk index.

2. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 1, characterized in that, In the process of activating the AR glasses, it includes: activating the fire residual temperature afterglow intelligent detection mode of the AR glasses, automatically loading the afterglow risk assessment algorithm, presetting the temperature threshold and risk parameter weight based on the fire type, and simultaneously activating the visible light camera, thermal imaging camera, air pressure sensor, humidity sensor and oxygen concentration sensor integrated in the AR glasses, all sensors synchronously collect data at a frequency of 10 Hz, and the AR glasses can be controlled by voice instructions or gestures or buttons when activated.

3. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 2, characterized in that, In the process of capturing temperature matrix data and collecting environmental parameter data based on real-time scanning of a conical area in front of the field of view of the AR glasses, it includes: based on the visible light camera integrated in the AR glasses, real-time scanning of a conical area in front of the field of view, the conical area is 120° in front of the field of view, the distance is 0.5 to 5 meters, based on the thermal imaging camera integrated in the AR glasses, capturing temperature matrix data, based on multiple sensors, collecting environmental parameter data, including air pressure, humidity and oxygen concentration.

4. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 3, characterized in that, In the process of real-time calculation of the risk index of the residual heat spot based on edge AI, integrating the temperature matrix data and the environmental parameter data, the afterglow risk assessment algorithm is used for calculation, and the calculation formula is as follows: R = (a • T_level) x (b / S_c) x e (γ·T) x (1 + d • C_type) x (1 - h • H) x (1 + 0 • D) x [1 + K • (O2- O0) / O0] x (1 + l • A P / P0); wherein R is the risk index, a is the temperature grading weight, T_level is the temperature level, β is the safety factor inverse amplification factor, S_c is the safety factor based on the carbonization state of the item, γ is the temperature index growth coefficient, T is the heat source temperature, δ is the flammability enhancement coefficient, C_type is the item type, η is the humidity suppression coefficient, H is the environmental humidity, θ is the time accumulation coefficient, D is the high temperature duration, κ is the oxygen sensitivity coefficient, O2 is the real-time detected environmental oxygen content, O0 is the standard atmospheric oxygen content, λ is the air pressure coefficient, ΔP is the air pressure difference, and P0 is the reference air pressure.

5. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 1, characterized in that, In the process of visualizing as low, medium and high risk, it includes: when the risk index is less than 100, it is low risk, the display screen of the AR glasses penetrates and displays a blue box containing real-time temperature in the residual heat spot area; when the risk index is greater than or equal to 100 and less than or equal to 500, it is medium risk, the display screen of the AR glasses penetrates and displays an orange warning box containing real-time temperature in the residual heat spot area and performs flashing; when the risk index is greater than 500, it is high risk, the display screen of the AR glasses penetrates and displays a red warning box containing real-time temperature in the residual heat spot area and performs flashing.

6. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 1, characterized in that, The process of determining whether to remove the risk by temperature decay rate and risk index includes: After spraying the high-risk target to reduce the temperature, the global temperature distribution map displayed by the penetration is switched to the details of the focused single high-risk hotspot through the instruction, and the gaze at the area is maintained for 3 seconds to trigger the verification scan; When the temperature decay rate is less than or equal to-2℃ / s, and the risk index is less than 100, the penetration displays a green safety mark and voice prompts the risk removal; otherwise, the warning is intensified, the red warning box flashes at double the frequency, and an optimized disposal scheme is superimposed and displayed.

7. The early warning method for detecting fire residual temperature afterglow based on AR glasses according to claim 1, characterized in that, The early warning method further includes: Based on the air pressure sensor integrated in the AR glasses, the air pressure change is monitored in real time, based on the GPS integrated in the AR glasses, the real-time positioning information is obtained, and based on the air pressure change and the real-time positioning, the motion state and floor change information of the firefighter are obtained.

8. An early warning system for intelligent detection of fire scene afterglow reburning based on AR glasses, characterized in that, It includes a data acquisition module, a data processing module, a real-time analysis module and a risk processing module, wherein: The data acquisition module is used to activate the AR glasses, scan the conical area in front of the field of view based on the AR glasses in real time, capture temperature matrix data and collect environmental parameter data, and identify residual heat spots and their associated item types in the field of view based on the YOLOv8s model; The data processing module is used to integrate the temperature matrix data and the environmental parameter data based on the edge AI, to calculate the risk index of the residual heat spot in real time, and to visualize it as low, medium and high risk; The real-time analysis module is used to lock and analyze the temperature change of the medium and high risk items, dynamically correct the safety factor in combination with the item material database, and visualize the detailed information, real-time temperature and risk index of the items; The risk processing module guides the spraying of the high-risk target to reduce the temperature based on the AR glasses, and determines whether to remove the risk by the temperature decay rate and the risk index.

9. An electronic device, comprising: The electronic device includes: At least one processor; and The memory is in communication connection with the at least one processor; wherein The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the early warning method for intelligent detection of residual heat rekindling in a fire scene based on AR glasses according to any one of claims 1 to 7.

10. A computer readable storage medium comprising a storage data area and a storage program area, the storage data area storing created data, the storage program area storing a computer program; wherein, The computer program is executed by the processor to implement the early warning method for intelligent detection of residual heat rekindling in a fire scene based on AR glasses according to any one of claims 1 to 7.

Images