Fire risk early warning method and apparatus

Abstract

Provided in the present application are a fire risk early warning method and apparatus. The method comprises: inputting, into a pre-trained material recognition model, color image feature values corresponding to an appearance color image of an article to be subjected to detection, so as to obtain material properties of said article; inputting environmental parameters of said article, an infrared feature value corresponding to a thermal infrared image and the material properties into a pre-established temperature interference analysis model, so as to obtain a temperature interference coefficient; and on the basis of the temperature interference coefficient, a predetermined heat diffusion value and a preset fire risk threshold value, determining the risk of said article causing a fire. The present application can determine, by taking temperature interference factors of a surrounding environment into consideration, the risk of a fire being caused by an article to be subjected to detection.

Description

Fire risk early warning method and device

[0001] Related applications

[0002] This application claims priority to the Chinese invention patent application with application number 202311188433.X filed on September 14, 2023, and cites the entire contents disclosed in the above patent application as part of this application. Technical Field

[0003] The present application relates to the field of intelligent early warning for aviation warehousing, and specifically to a fire risk early warning method and device. Background Art

[0004] Aviation warehouse fires pose a serious threat to the operational safety of aviation systems. With the widespread adoption of smart electronic devices, fires are becoming increasingly frequent. While existing technologies utilize infrared thermal imaging cameras to monitor the temperature of stored cargo for fire warning, these methods fail to fully consider factors beyond the cargo's own temperature.

[0005] Currently, there is no solution that can automatically identify fire risk cargo, and there is no method for regularly checking the temperature of stored cargo in aviation management standard procedures.

[0006] Summary of the Invention

[0007] In response to the problems in the prior art, the present application provides a fire risk warning method and device that can take into account the temperature interference factors of the surrounding environment and determine the risk of fire caused by the object to be detected.

[0008] To solve the above technical problems, this application provides the following technical solutions:

[0009] In a first aspect, the present application provides a fire risk early warning method, comprising:

[0010] Inputting the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material properties of the object to be detected;

[0011] Inputting the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0012] The risk of the object to be detected causing a fire is determined based on the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold.

[0013] Furthermore, the step of predetermining the heat dissipation value includes:

[0014] determining a vector field corresponding to the thermal infrared image;

[0015] The vector field is input into a pre-established heat distribution analysis model to obtain the heat distribution value.

[0016] Furthermore, the step of pre-training the material recognition model includes:

[0017] Obtain historical material properties of historical inspection objects and historical color image feature values ​​corresponding to historical appearance color images;

[0018] Grouping the historical material attributes and the corresponding historical color image feature values ​​according to a preset ratio to obtain a color image training set and a color image test set;

[0019] According to preset model training parameters, the historical material attributes and the color image training set are input into a convolutional neural network model for training to obtain a material recognition model;

[0020] Furthermore, determining the risk of the object to be detected causing a fire based on the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold includes:

[0021] Determining a temperature interference weight according to a preset temperature interference weight and the temperature interference coefficient;

[0022] Determine the heat spread weight according to the preset heat spread weight and the heat spread;

[0023] The risk is determined according to the temperature interference weight, the heat dissipation weight, and the fire risk threshold.

[0024] In a second aspect, the present application provides a fire risk warning device, comprising:

[0025] A material property determination unit is used to input the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material property of the object to be detected;

[0026] an interference coefficient determination unit, configured to input the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0027] The fire risk determination unit is used to determine the risk of the object to be detected causing a fire based on the temperature interference coefficient, a predetermined heat dissipation value and a preset fire risk threshold.

[0028] Furthermore, the fire risk warning device further includes:

[0029] a vector field determining unit, configured to determine a vector field corresponding to the thermal infrared image;

[0030] The heat spread value calculation unit is used to input the vector field into a pre-established heat distribution analysis model to obtain the heat spread value.

[0031] Furthermore, the fire risk warning device further includes:

[0032] A historical feature acquisition unit, used to obtain historical color image feature values ​​corresponding to historical material properties and historical appearance color images of historical inspection objects;

[0033] Grouping the historical material attributes and the corresponding historical color image feature values ​​according to a preset ratio to obtain a color image training set and a color image test set;

[0034] An initial model building unit is used to input the historical material attributes and the color image training set into a convolutional neural network model for training according to preset model training parameters to obtain an initial model for material recognition;

[0035] The recognition model establishing unit is used to adjust the material recognition initial model using the color picture test set to obtain the material recognition model.

[0036] Furthermore, the fire risk determination unit includes:

[0037] An interference weight determination module is used to determine a temperature interference weight according to a preset temperature interference weight and the temperature interference coefficient;

[0038] A heat spread weight determination module, configured to determine a heat spread weight according to a preset heat spread weight and the heat spread value;

[0039] The fire risk determination module is used to determine the risk according to the temperature interference weight, the heat dissipation weight and the fire risk threshold.

[0040] In a third aspect, the present application provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the fire risk warning method when executing the program.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the fire risk warning method when executed by a processor.

[0042] In a fifth aspect, the present application provides a computer program product, comprising a computer program / instruction, which implements the steps of the fire risk warning method when executed by a processor.

[0043] In response to the problems in the existing technology, the fire risk warning method and device provided by this application can take into account the temperature interference factors of the surrounding environment and determine the risk of fire caused by the objects to be tested; by collecting the appearance and environmental data of the objects to be tested and combining them with thermal imaging images, external factors unrelated to the heat energy generated by the heat source are separated from the analysis, thereby increasing the possibility of the inspection system to find objects with abnormal temperatures, which is beneficial to improving the safety level of the logistics industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0045] FIG1 is a flow chart of a fire risk early warning method according to an embodiment of the present application;

[0046] FIG2 is a flow chart of the steps of determining heat dispersion values ​​in an embodiment of the present application;

[0047] FIG3 is a flow chart of the steps of pre-training a material recognition model in an embodiment of the present application;

[0048] FIG4 is a flow chart of determining the risk of a fire caused by an object to be detected according to an embodiment of the present application;

[0049] FIG5 is a structural diagram of a fire risk warning device according to an embodiment of the present application;

[0050] FIG6 is a second structural diagram of the fire risk warning device according to an embodiment of the present application;

[0051] FIG7 is a third structural diagram of the fire risk warning device according to an embodiment of the present application;

[0052] FIG8 is a structural diagram of a fire risk determination unit in an embodiment of the present application;

[0053] FIG9 is a schematic structural diagram of an electronic device in an embodiment of the present application;

[0054] FIG10 is a diagram of the overall system structure in an embodiment of the present application. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0056] The acquisition, storage, use and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0057] Temperature is a manifestation of the thermal energy of an object, and the thermal energy inside an object will be affected by the surrounding environmental factors. Some of these environmental factors have nothing to do with whether there is a heat source inside the object, and some environmental factors may affect the speed and efficiency of the transfer of internal thermal energy to the surface of the object. The following are a few examples of factors that affect the surface temperature of an object: for example, the material of the object, the ambient temperature and the ambient humidity, etc. The method provided in this application analyzes the above points and separates the factors related to the analysis of the fire risk of cargo from the factors that are not related to it, so as to improve the reliability of the analysis. The location of the heat source and the fire risk are analyzed based on the relationship between the data points of the surface temperature of multiple objects, thereby improving the accuracy and reliability of judging the fire risk.

[0058] Under normal circumstances, an object containing a heat source will be warmer than its surroundings. In this situation, the object exchanges heat with the surrounding environment, losing heat to it. The formula for heat loss is: Q = U × A × ΔT, where A is the area of ​​the heat loss surface, ΔT is the temperature difference between the object and the surrounding environment, and U is the thermal conductivity, calculated as 1 / (material thickness / thermal conductivity). Therefore, different surface materials have different thermal conductivity properties, and under the same environment and heat source, the surface temperature will also vary.

[0059] Furthermore, the ambient temperature:

[0060] When an object is in an environment, its surface comes into contact with the air, causing heat to transfer from the object to the air. According to the aforementioned heat loss formula, assuming the object and the heat source within it remain constant, in a high-temperature environment, the temperature difference is smaller, so the rate of heat loss is slower. Conversely, in a low-temperature environment, the temperature difference is larger, so the rate of heat loss is faster. Furthermore, if the object's temperature is lower than the ambient temperature, heat energy will transfer from the environment to the object until the two temperatures reach the same level. Therefore, the ambient temperature also affects the object's base temperature.

[0061] Furthermore, the ambient humidity:

[0062] Studies have shown that the humidity of the environment will also affect the efficiency of heat convection heat transfer. Air with high humidity has poor heat transfer capacity, while air with low humidity has relatively good heat transfer capacity.

[0063] To sum up, if we ignore these environmental factors and simply use traditional methods to detect the surface temperature of objects and judge the fire risk based on this, we often cannot achieve relatively accurate results.

[0064] In one embodiment, referring to FIG1 , in order to consider the temperature interference factor of the surrounding environment and determine the risk of fire caused by the detected object, the present application provides a fire risk warning method, including:

[0065] S101: Inputting the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material properties of the object to be detected;

[0066] Referring to FIG. 3 , the steps for pre-training the material recognition model include: obtaining historical material attributes of historically inspected items and historical color image feature values ​​corresponding to historical appearance color images (S301); wherein material attributes are used to classify and label different objects to train feature maps for deep learning. The historical material attributes and corresponding historical color image feature values ​​are grouped according to a preset ratio to obtain a color image training set and a color image test set (S302); according to preset model training parameters, the historical material attributes and the color image training set are input into a convolutional neural network model for training to obtain an initial material recognition model (S303); and the initial material recognition model is adjusted using the color image test set to obtain the material recognition model (S304).

[0067] Among them, an AI material recognition model developed based on instance segmentation detection methods or equivalent AI detection methods (including but not limited to object detection and semantic segmentation) is used to identify the actual location of cargo / baggage and identify the type of aviation cargo / baggage material based on its texture and appearance. The results provided by the AI ​​material recognition model are crucial because it can help the system estimate the thermal properties of objects, including infrared emissivity, thermal resistance, and reflectivity. It also enables the system to implement background filtering to improve the detection accuracy of other subsystems.

[0068] S102: Inputting the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0069] It can be understood that this step corresponds to the interference analysis module. This module obtains input from the weather sensor, material identification unit, and infrared camera to calculate a dynamic scale for temperature assessment. The temperature information of the cargo / baggage is compared with this dynamic scale (also known as the threshold) to check whether the overall surface temperature is within the acceptable range. Based on this result, a risk factor is generated and provided to the fire risk assessment module.

[0070] S103: Determine the risk of the object to be detected causing a fire according to the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold.

[0071] It should be noted that, referring to FIG10 , the image of the object to be inspected can generally be acquired in the following manner:

[0072] Color camera (RGB-based images): A standard IP surveillance camera can be used. In this application scenario, it can be placed next to the thermal imaging camera (to alleviate the problem of position and angle differences that can hinder the identification of pixels in subsequent images that belong to the same object). This camera can be used to capture images of the goods' exterior and obtain the data needed for material analysis.

[0073] Thermal imaging: A thermal imaging lens is required to obtain thermal distribution data of an object. Existing thermal imaging lenses typically output a 16-bit grayscale image, where the grayscale of each pixel is determined by the average surface temperature of the object corresponding to that pixel. In this application scenario, the thermal imaging lens can be mounted on a bracket and pointed at the object to be measured to obtain the surface temperature distribution of the object.

[0074] Weather sensors: These sensors consist of at least three sensors that monitor environmental parameters. The collected data includes at least temperature, humidity, and wind speed. These digital data are used as inputs for the environmental and material interference analysis model (also known as the interference analysis model).

[0075] It is understood that in the embodiment of the present application, the specific method of obtaining the appearance color image, thermal infrared image and environmental parameters is as follows:

[0076] Data is first extracted from standard color RGB cameras, thermal imaging cameras, and sensors that collect environmental parameters. The standard color RGB camera outputs an RGB-based image. The material recognition model receives this data and then feeds it into a deep learning model. This deep learning model consists of multiple layers of neurons, each weighted by a number in a weight file. After the raw image is input into the neural network, it undergoes a step-by-step convolution and pooling process to produce the final feature map. This feature map is then used to identify locations and classify objects. This location and classification data is then fed into the interference analysis model for further analysis.

[0077] The thermal imaging camera outputs a 16-bit grayscale image. The thermal pattern analysis model and the interference analysis model each utilize this data. The thermal pattern analysis system uses the grayscale data to generate a system of vectors. The vector data is used to calculate the gradient, and then the gradient is used to calculate the divergence. The intensity of the divergence can be used to estimate the fire risk of an object and can also be used to subsequently determine the location of the heat source. The thermal pattern analysis model outputs the value to the fire risk calculator (corresponding to steps S401 to S403).

[0078] The 16-bit grayscale output from the thermal imaging camera can also be used to calculate temperature values. This temperature value can also be used in interference analysis models.

[0079] Finally, environmental parameter sensors capture current ambient temperature, humidity, wind speed, and other parameters. The interference analysis model then processes this data, performing calculations and outputting the resulting values ​​to the fire risk calculator.

[0080] In one embodiment, referring to FIG. 2 , the step of predetermining the heat spread value includes: determining a vector field corresponding to the thermal infrared image ( S201 ); and inputting the vector field into a pre-established heat distribution analysis model to obtain the heat spread value ( S202 ).

[0081] Among them, the heat distribution analysis model is a system that retrieves input from a thermal camera to determine whether thermal signatures suggest an active heat source within the container itself. This is based on the assumption that, in the absence of a fire within the container, the primary heat source will be from the surroundings, which will uniformly heat the container surface. In the case of a cargo fire, however, the heat source will originate from within the container, resulting in uneven heating of the container surface, depending on the heat source's distance from the surface point.

[0082] Furthermore, the heat distribution analysis module detects fire risks by processing the video stream from the thermal camera and identifying concentrated heat areas as areas on the object's surface close to certain heat sources. To assess the fire risk of the object under test, the module first calculates the gradient along the x- and y-dimensions, converts the relevant frames of the video stream into a vector field, and then calculates the divergence of each point in the vector field:

[0083] Among them, V(x,y) is the value of the vector field, that is, the gradient of the heat distribution, is the divergence of the vector field, V x (x,y) is the x value at the vector field point (x,y), V y (x,y) is the y value at the vector field point (x,y). As the vector flow accelerates away from a point, the divergence at that point increases, and vice versa. Areas of concentrated heat will exhibit gradient vectors that converge toward the center of those areas. Therefore, this module detects fire hazard areas as areas with high negative divergence on thermal images.

[0084] For example, given an image with these pixel values:

[0085] Let V(x,y)=(I(x+1,y)-I(x,y),I(x,y+1)-I(x,y)),

[0086] make

[0087] From this example, we can observe that if the index starts from (0,0), then from (4,1) to (3,2) is the area with the largest negative divergence value, that is, where the temperature value converges at I(x,y).

[0088] The heat distribution analysis module also filters out transient active heat sources, such as temporary contact between an object's surface and an external heat source (e.g., a human hand). By calculating the divergence over a series of frames in a video stream, it can determine if a strongly negative divergence value decreases within a short period of time. This indicates that the area is attributed to a transient heat source and is not considered a fire risk.

[0089] In one embodiment, referring to FIG4 , determining the risk of the detected object causing a fire based on the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold includes:

[0090] S401: Determine a temperature interference weight according to a preset temperature interference weight and the temperature interference coefficient;

[0091] S402: Determine a heat spread weight according to a preset heat spread weight and the heat spread;

[0092] S403: Determine the risk according to the temperature interference weight, the heat dissipation weight, and the fire risk threshold.

[0093] It is understood that the temperature assessment module receives the material type, several environmental variables (ambient temperature, humidity, light intensity) and the thermal statistics of the relevant object (minimum, maximum and average temperature), and returns a binary classification of whether there is a fire risk. It uses the Naive Bayes classifier To calculate the given input x1,…,x n .

[0094] in,

[0095] Where p(C k ) is event class C k The prior probability of whether there is a fire risk, p(x i |C k ) is a given event class Ck The parameter x i The likelihood of x, i.e., the probability of receiving the input value x given the presence or absence of a fire risk. The prior probability is inferred from historical data on fire events at a given location. The likelihood is calculated based on data from controlled experiments.

[0096] Since the material type is a discrete variable, its probability can be calculated by computing the histogram of materials that are or are not associated with fire risk. The other input parameters are continuous and their probabilities are modeled assuming a Gaussian distribution:

[0097] Where, is the parameter x i In event class C k In the equation, the probability density of the observation v, μ ik is x i In event class C k The average value in is x i In event class C k Bessel-corrected variance in .

[0098] For example, suppose the probability of fire risk is 0.01 if the fire is present and 0.99 otherwise. Assume there are only two input parameters: the material type and the average temperature of the object. Assume there are only two material types: aluminum and paper. Assume the following are the fire risk probabilities associated with different material types:

[0099] Here are the parameters of the Gaussian distribution of the average temperature of an object that are relevant to the fire risk:

[0100] If the material type is aluminum and the average temperature of the object is 15°C, the posterior probability of fire risk is:

[0101] The posterior probability that there is no fire risk is:

[0102] Since the posterior probability of no fire risk is greater than the posterior probability of fire risk, aluminum-wrapped objects with an average temperature of 15°C are unlikely to pose a fire risk.

[0103] From the above description, it can be seen that the fire risk warning method and device provided by this application can take into account the temperature interference factors of the surrounding environment and determine the risk of fire caused by the objects to be tested; by collecting the appearance and environmental data of the objects to be tested and combining them with thermal imaging images, external factors unrelated to the heat energy generated by the heat source are separated from the analysis, thereby increasing the possibility of the inspection system finding objects with abnormal temperatures, which is beneficial to improving the safety level of the logistics industry.

[0104] Based on the same inventive concept, the embodiments of the present application also provide a fire risk warning device, which can be used to implement the method described in the above embodiments, as described in the following embodiments. Since the principle of solving the problem by the fire risk warning device is similar to that of the fire risk warning method, the implementation of the fire risk warning device can refer to the implementation of the method based on the software performance benchmark, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements the predetermined function. Although the system described in the following embodiments is preferably implemented in software, implementation in hardware, or a combination of software and hardware, is also possible and conceived.

[0105] In one embodiment, referring to FIG5 , in order to consider the temperature interference factor of the surrounding environment and determine the risk of fire caused by the object to be detected, the present application provides a fire risk warning device, including:

[0106] The material property determination unit 501 is used to input the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material property of the object to be detected;

[0107] The interference coefficient determination unit 502 is configured to input the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0108] The fire risk determination unit 503 is configured to determine the risk of the object to be detected causing a fire based on the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold.

[0109] In one embodiment, referring to FIG6 , the fire risk warning device further includes:

[0110] A vector field determining unit 601 is configured to determine a vector field corresponding to the thermal infrared image;

[0111] The heat spread value calculation unit 602 is used to input the vector field into a pre-established heat distribution analysis model to obtain the heat spread value.

[0112] In one embodiment, referring to FIG7 , the fire risk warning device further includes:

[0113] The historical feature acquisition unit 701 is used to obtain historical color image feature values ​​corresponding to historical material properties and historical appearance color images of historical inspection objects;

[0114] A training set test set generating unit 702 is configured to group the historical material attributes and the corresponding historical color image feature values ​​according to a preset ratio to obtain a color image training set and a color image test set;

[0115] The initial model building unit 703 is used to input the historical material attributes and the color image training set into the convolutional neural network model for training according to the preset model training parameters to obtain an initial model for material recognition;

[0116] The recognition model establishing unit 704 is configured to adjust the material recognition initial model using the color image test set to obtain the material recognition model.

[0117] In one embodiment, referring to FIG8 , the fire risk determination unit 503 includes:

[0118] The interference weight determination module 801 is configured to determine the temperature interference weight according to a preset temperature interference weight and the temperature interference coefficient;

[0119] Heat spread weight determination module 802, configured to determine a heat spread weight according to a preset heat spread weight and the heat spread;

[0120] The fire risk determination module 803 is configured to determine the risk according to the temperature interference weight, the heat dissipation weight, and the fire risk threshold.

[0121] From a hardware perspective, in order to consider the temperature interference factors of the surrounding environment and determine the risk of fire caused by the detected object, the present application provides an embodiment of an electronic device for implementing all or part of the content of the fire risk warning method. The electronic device specifically includes the following content:

[0122] Processor, memory, communication interface, and bus; wherein the processor, memory, and communication interface communicate with each other via the bus; the communication interface is used to transmit information between the fire risk warning device and related equipment such as the core business system, user terminals, and related databases; the logic controller can be a desktop computer, a tablet computer, a mobile terminal, etc., but this embodiment is not limited thereto. In this embodiment, the logic controller can be implemented with reference to the embodiment of the fire risk warning method and the embodiment of the fire risk warning device in the embodiment, and their contents are incorporated herein, and repeated parts are not repeated.

[0123] It is understandable that the user terminal may include a smart phone, a tablet electronic device, a network set-top box, a portable computer, a desktop computer, a personal digital assistant (PDA), a vehicle-mounted device, a smart wearable device, etc. Among them, the smart wearable device may include smart glasses, a smart watch, a smart bracelet, etc.

[0124] In practical applications, portions of the fire risk warning method may be executed on the electronic device as described above, or all operations may be performed on the client device. The specific method may be selected based on the processing capabilities of the client device and the limitations of the user's usage scenario. This application does not impose any restrictions on this. If all operations are performed on the client device, the client device may also include a processor.

[0125] The client device may include a communication module (i.e., a communication unit) that can establish a communication connection with a remote server to implement data transmission with the server. The server may include a server on the task scheduling center side, and in other implementation scenarios, may also include a server on an intermediate platform, such as a server on a third-party server platform that has a communication link with the task scheduling center server. The server may include a single computer device, a server cluster consisting of multiple servers, or a server structure of a distributed device.

[0126] Figure 9 is a schematic block diagram of the system architecture of an electronic device 9600 according to an embodiment of the present application. As shown in Figure 9 , the electronic device 9600 may include a central processing unit 9100 and a memory 9140; the memory 9140 is coupled to the central processing unit 9100. It should be noted that Figure 9 is exemplary; other types of structures may be used to supplement or replace this structure to implement telecommunications or other functions.

[0127] In one embodiment, the fire risk warning method function may be integrated into the central processing unit 9100. The central processing unit 9100 may be configured to perform the following control:

[0128] S101: Inputting the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material properties of the object to be detected;

[0129] S102: Inputting the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0130] S103: Determine the risk of the object to be detected causing a fire according to the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold.

[0131] From the above description, it can be seen that the fire risk warning method provided by this application can take into account the temperature interference factors of the surrounding environment and determine the risk of fire caused by the objects to be tested; by collecting the appearance and environmental data of the objects to be tested and combining them with thermal imaging images, external factors unrelated to the heat energy generated by the heat source are separated from the analysis, thereby increasing the possibility of the inspection system finding objects with abnormal temperatures, which is beneficial to improving the safety level of the logistics industry.

[0132] In another embodiment, the fire risk warning device can be configured separately from the central processing unit 9100. For example, the data composite transmission device fire risk warning device can be configured as a chip connected to the central processing unit 9100, and the function of the fire risk warning method can be realized through the control of the central processing unit.

[0133] As shown in FIG9 , the electronic device 9600 may further include: a communication module 9110, an input unit 9120, an audio processor 9130, a display 9160, and a power supply 9170. It is worth noting that the electronic device 9600 does not necessarily include all of the components shown in FIG9 ; in addition, the electronic device 9600 may also include components not shown in FIG9 , for which reference may be made to the prior art.

[0134] As shown in FIG9 , the central processing unit 9100 is sometimes also referred to as a controller or an operation control unit, and may include a microprocessor or other processor device and / or logic device. The central processing unit 9100 receives input and controls the operation of various components of the electronic device 9600 .

[0135] Memory 9140 can be, for example, one or more of a cache, flash memory, hard drive, removable media, volatile memory, non-volatile memory, or other suitable devices. It can store the aforementioned failure-related information and also store programs that execute the relevant information. The CPU 9100 can execute the programs stored in memory 9140 to implement information storage or processing.

[0136] The input unit 9120 provides input to the central processing unit 9100. The input unit 9120 may be, for example, a keypad or touch input device. The power supply 9170 is used to provide power to the electronic device 9600. The display 9160 is used to display objects such as images and text. The display may be, for example, an LCD display, but is not limited thereto.

[0137] The memory 9140 may be a solid-state memory, such as a read-only memory (ROM), a random access memory (RAM), or a SIM card. Alternatively, it may be a memory that retains information even when power is off, can be selectively erased, and is provided with more data. Examples of such memory are sometimes referred to as EPROMs. The memory 9140 may also be some other type of device. The memory 9140 includes a buffer memory 9141 (sometimes referred to as a buffer). The memory 9140 may include an application / function storage unit 9142 for storing application programs and function programs or processes for executing the operation of the electronic device 9600 by the central processing unit 9100.

[0138] The memory 9140 may also include a data storage unit 9143 for storing data, such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. The driver storage unit 9144 of the memory 9140 may include various driver programs for the electronic device's communication functions and / or for executing other functions of the electronic device (such as messaging applications, address book applications, etc.).

[0139] The communication module 9110 is a transmitter / receiver 9110 that sends and receives signals via an antenna 9111. The communication module (transmitter / receiver) 9110 is coupled to the central processor 9100 to provide input signals and receive output signals, which may be the same as in a conventional mobile communication terminal.

[0140] Based on different communication technologies, multiple communication modules 9110 can be provided in the same electronic device, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module. The communication module (transmitter / receiver) 9110 is also coupled to a speaker 9131 and a microphone 9132 via an audio processor 9130 to provide audio output via the speaker 9131 and receive audio input from the microphone 9132, thereby implementing common telecommunication functions. The audio processor 9130 may include any suitable buffer, decoder, amplifier, etc. In addition, the audio processor 9130 is also coupled to the central processing unit 9100, enabling local recording via the microphone 9132 and playback of stored audio via the speaker 9131.

[0141] Embodiments of the present application also provide a computer-readable storage medium capable of implementing all steps of the fire risk early warning method in the above-mentioned embodiment, where the execution subject is a server or a client. The computer-readable storage medium stores a computer program. When the computer program is executed by a processor, the computer program implements all steps of the fire risk early warning method in the above-mentioned embodiment, where the execution subject is a server or a client. For example, when the processor executes the computer program, the following steps are implemented:

[0142] S101: Inputting the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material properties of the object to be detected;

[0143] S102: Inputting the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient;

[0144] S103: Determine the risk of the object to be detected causing a fire according to the temperature interference coefficient, a predetermined heat dissipation value, and a preset fire risk threshold.

[0145] From the above description, it can be seen that the fire risk warning method provided by this application can take into account the temperature interference factors of the surrounding environment and determine the risk of fire caused by the objects to be tested; by collecting the appearance and environmental data of the objects to be tested and combining them with thermal imaging images, external factors unrelated to the heat energy generated by the heat source are separated from the analysis, thereby increasing the possibility of the inspection system finding objects with abnormal temperatures, which is beneficial to improving the safety level of the logistics industry.

[0146] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, apparatus, or computer program products. Thus, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0147] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (apparatus), and computer program products according to embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device produce a device for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0148] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction device that implements the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0149] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, so that the instructions executed on the computer or other programmable device provide steps for implementing the functions specified in one or more processes in the flowchart and / or one or more boxes in the block diagram.

[0150] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

Claims

1. A fire risk early warning method, characterized in that: include: Inputting the color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material properties of the object to be detected; Input the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image, and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient; The risk of the object to be detected causing a fire is determined according to the temperature interference coefficient, the heat dissipation value and a preset fire risk threshold.

2. The fire risk early warning method according to claim 1, characterized in that: The step of predetermining the heat dissipation value comprises: Determining a vector field corresponding to the thermal infrared image; The vector field is input into a pre-established heat distribution analysis model to obtain the heat dissipation value.

3. The fire risk early warning method according to claim 1, characterized in that: The step of pre-training the material recognition model comprises: Obtain historical material properties of historical inspection objects and historical color image feature values ​​corresponding to historical appearance color images; Grouping the historical material attributes and the corresponding historical color picture feature values ​​according to a preset ratio to obtain a color picture training set and a color picture test set; According to preset model training parameters, the historical material attributes and the color image training set are input into a convolutional neural network model for training to obtain an initial material recognition model; The material recognition model is obtained by adjusting the initial material recognition model using the color picture test set.

4. The fire risk early warning method according to claim 1, characterized in that: The determining the risk of the object to be detected causing a fire according to the temperature interference coefficient, the heat dissipation value and a preset fire risk threshold value includes: Determine the temperature interference weight according to the preset temperature interference weight and the temperature interference coefficient; Determine the heat spread weight according to the preset heat spread weight and the heat spread; The risk is determined according to the temperature interference weight, the heat dissipation weight and the fire risk threshold.

5. A fire risk warning device, characterized in that: include: A material property determination unit, used for inputting a color image feature value corresponding to the appearance color image of the object to be detected into a pre-trained material recognition model to obtain the material property of the object to be detected; An interference coefficient determination unit, used for inputting the environmental parameters of the object to be detected, the infrared characteristic values ​​corresponding to the thermal infrared image and the material properties into a pre-established temperature interference analysis model to obtain a temperature interference coefficient; The fire risk determination unit is used to determine the risk of the object to be detected causing a fire according to the temperature interference coefficient, a predetermined heat dissipation value and a preset fire risk threshold.

6. The fire risk warning device according to claim 5, characterized in that: Also includes: A vector field determination unit, used to determine the vector field corresponding to the thermal infrared image; The heat dissipation value calculation unit is used to input the vector field into a pre-established heat distribution analysis model to obtain the heat dissipation value.

7. The fire risk warning device according to claim 5, characterized in that: Also includes: A historical feature acquisition unit, used to acquire historical material properties of historical inspection objects and historical color image feature values ​​corresponding to historical appearance color images; A training set test set generating unit, used for grouping the historical material attributes and the corresponding historical color image feature values ​​according to a preset ratio to obtain a color image training set and a color image test set; An initial model building unit is used to input the historical material attributes and the color image training set into a convolutional neural network model for training according to preset model training parameters to obtain an initial model for material recognition; The recognition model building unit is used to adjust the material recognition initial model using the color picture test set to obtain the material recognition model.

8. The fire risk warning device according to claim 5, characterized in that: Fire risk determination unit, including: An interference weight determination module, used to determine a temperature interference weight according to a preset temperature interference weight and the temperature interference coefficient; A heat dissipation weight determination module, used to determine a heat dissipation weight according to a preset heat dissipation weight and the heat dissipation; The fire risk determination module is used to determine the risk according to the temperature interference weight, the heat dissipation weight and the fire risk threshold.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the fire risk warning method according to any one of claims 1 to 4 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the fire risk warning method according to any one of claims 1 to 4 are implemented.

Images