Electrical equipment fire extinguishing method based on image recognition and related equipment

Abstract

The invention provides an electrical equipment fire extinguishing method based on image recognition. The method comprises the following steps: acquiring a monitoring image in electrical equipment; performing fire source identification on the monitoring image to obtain a fire source identification result; determining the position of the fire source in the internal space of the electrical equipment based on the fire source identification result; determining a target fire extinguishing sheet in the plurality of fire extinguishing sheets based on the fire source position and the fire extinguishing range of the fire extinguishing sheets; and the target fire extinguishing piece is controlled to be triggered, and fire extinguishing at the fire source position is achieved. Fire source identification is carried out on a monitoring image in the electrical equipment to obtain a fire source identification result, a fire source position is determined in the internal space of the electrical equipment according to the fire source identification result, and a target fire extinguishing piece is determined in a plurality of fire extinguishing pieces according to the fire source position and the fire extinguishing range of the fire extinguishing pieces, so that the target fire extinguishing piece is controlled to be triggered. Therefore, the fire fighting work intensity of the electrical equipment is effectively improved, and the work risk of firefighters is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an electrical equipment fire extinguishing method based on image recognition and related equipment. Background Art

[0002] At present, the most common firefighting method in my country is for firefighters to enter the fire scene and spray water guns on an area that needs to be extinguished. This method has many disadvantages: 1. In some places where the fire is extremely large, firefighters cannot enter to extinguish the fire, causing the fire to spread and intensify; 2. It takes a certain amount of time for firefighters to arrive at the fire scene, but the fire needs to be discovered and extinguished in time. In many cases, small fires are turned into fires because they are not extinguished in time; 3. The fire situation is complex and changeable, and firefighters are in danger of their lives; this is because the smoke in the fire scene is very thick, and the toxic gas is very harmful to the firefighters' bodies, and firefighters are likely to lose their lives due to gas poisoning. Summary of the invention

[0003] The embodiment of the present invention provides an electrical equipment fire extinguishing method based on image recognition, aiming to provide an efficient and intelligent electrical equipment fire extinguishing method to improve the fire fighting intensity of electrical equipment. The fire source is identified by the monitoring image inside the electrical equipment to obtain the fire source identification result, and the fire source position is determined in the internal space of the electrical equipment according to the fire source identification result, and the target fire extinguishing piece is determined among several fire extinguishing pieces by using the fire source position and the fire extinguishing range of the fire extinguishing piece, so as to control the triggering of the target fire extinguishing piece to achieve fire extinguishing at the fire source position, thereby effectively improving the fire fighting intensity of the electrical equipment and reducing the work risk of firefighters.

[0004] In a first aspect, an embodiment of the present invention provides an electrical equipment fire extinguishing method based on image recognition, wherein an image device and a plurality of distributed fire extinguishing sheets are installed in the electrical equipment, and the image device is used to collect images inside the electrical equipment, and the method comprises the following steps:

[0005] Acquiring a monitoring image inside the electrical equipment;

[0006] Performing fire source identification on the monitoring image to obtain a fire source identification result;

[0007] Based on the fire source identification result, determining the fire source location in the internal space of the electrical equipment;

[0008] Determining a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece;

[0009] The target fire extinguishing piece is controlled to be triggered to extinguish the fire at the fire source location.

[0010] Optionally, the performing fire source identification on the monitoring image to obtain a fire source identification result includes:

[0011] Performing target recognition processing on the monitoring image through the trained fire source recognition model to obtain a target recognition result, wherein the target recognition result includes a target detection frame and a confidence level corresponding to the target detection frame, and the target recognition result includes at least one of an electric spark recognition result, a flame recognition result, and a smoke recognition result;

[0012] Based on the target identification result, a fire source identification result is determined.

[0013] Optionally, determining to obtain a recognition result based on the target recognition result includes:

[0014] If the target recognition result includes multiple target detection frames;

[0015] The target detection frame whose confidence is greater than or equal to a preset confidence threshold is determined as a fire source target frame;

[0016] The fire source identification result is determined based on the fire source target frame.

[0017] Optionally, determining the fire source identification result based on the fire source target frame includes:

[0018] If the number of the fire source target frames is one, the fire source identification result is directly determined based on the fire source target frame, and the fire source identification result includes the fire source target frame;

[0019] If the number of the fire source target frames is two or more, merging and fusing the two or more fire source target frames to obtain a fused target frame;

[0020] The fire source identification result is determined based on the fusion target frame, and the fire source identification result includes the fusion target frame.

[0021] Optionally, determining the location of the fire source in the internal space of the electrical equipment based on the fire source identification result includes:

[0022] If the fire source identification result includes the fire source target frame, determining a first image area in the monitoring image based on the fire source target frame;

[0023] Based on the first image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

[0024] Optionally, determining the location of the fire source in the internal space of the electrical equipment based on the fire source identification result includes:

[0025] If the fire source identification result includes the fused target frame, then based on the fused target frame, determining a thermal map corresponding to the fused target frame in the monitoring image;

[0026] In the thermal map, a region whose thermal value is greater than or equal to a thermal value threshold is screened out to obtain the second image region;

[0027] Based on the second image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

[0028] Optionally, the determining a target fire extinguishing piece from a plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece includes:

[0029] Calculating the distance between the fire source position and each of the fire extinguishing plates;

[0030] Determine the fire extinguishing piece whose distance is smaller than the fire extinguishing range as a candidate fire extinguishing piece;

[0031] Among the candidate fire extinguishing sections, the target fire extinguishing section is determined with the goal of maximizing the coverage and selecting the least fire extinguishing section.

[0032] In a second aspect, an embodiment of the present invention further provides an electrical equipment fire extinguishing device based on image recognition, the electrical equipment fire extinguishing device based on image recognition comprising:

[0033] An acquisition module, used for acquiring a monitoring image of the interior of the electrical device;

[0034] A fire source identification module is used to identify the source of goods on the monitoring image and obtain a fire source identification result;

[0035] A first determination module, configured to determine a fire source location in an internal space of the electrical device based on the fire source identification result;

[0036] A second determination module is used to determine a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece;

[0037] The control module is used to control the target fire extinguishing piece to be triggered to extinguish the fire at the fire source location.

[0038] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the electrical equipment fire extinguishing method based on image recognition provided in an embodiment of the present invention are implemented.

[0039] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps of the electrical equipment fire extinguishing method based on image recognition provided in an embodiment of the invention are implemented.

[0040] In the embodiment of the present invention, a monitoring image of the interior of the electrical equipment is obtained; a fire source identification result is obtained by performing fire source identification on the monitoring image to obtain a fire source identification result; based on the fire source identification result, the fire source position is determined in the internal space of the electrical equipment; based on the fire source position and the fire extinguishing range of the fire extinguishing piece, a target fire extinguishing piece is determined from a plurality of fire extinguishing pieces; and the target fire extinguishing piece is controlled to be triggered to extinguish the fire at the fire source position. Fire source identification is performed on the monitoring image of the interior of the electrical equipment to obtain a fire source identification result, and based on the fire source identification result, the fire source position is determined in the internal space of the electrical equipment, and the fire extinguishing range of the fire extinguishing piece is used to determine the target fire extinguishing piece from a plurality of fire extinguishing pieces, thereby controlling the target fire extinguishing piece to be triggered to extinguish the fire at the fire source position, thereby effectively improving the fire fighting intensity of the electrical equipment and reducing the work risk of firefighters. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. 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 creative work.

[0042] Figure 1 is a flow chart of an electrical equipment fire extinguishing method based on image recognition provided by an embodiment of the present invention;

[0043] Figure 2 is a structural schematic diagram of an electrical equipment fire extinguishing device based on image recognition provided by an embodiment of the present invention;

[0044] Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] like Figure 1 As shown, Figure 1 It is a flow chart of an electrical equipment fire extinguishing method based on image recognition provided by an embodiment of the present invention.

[0047] In an embodiment of the present invention, an imaging device and a plurality of fire extinguishing plates arranged in a distributed manner are installed in the electrical equipment, and the imaging device is used to collect images inside the electrical equipment. The electrical equipment fire extinguishing method based on image recognition includes the following steps:

[0048] 101. Obtain monitoring images of the interior of electrical equipment.

[0049] In an embodiment of the present invention, the above-mentioned electrical equipment fire extinguishing method based on image recognition can be applied to a task scheduling system, the above-mentioned task scheduling system includes at least one electrical equipment, multiple fire extinguishing devices and a task scheduling module, the above-mentioned task scheduling module can be a task scheduling platform or an electronic device, the above-mentioned electronic device can be an intelligent gateway, an intelligent networking device or a server, etc., and the above-mentioned task scheduling platform can be constructed based on a server or a distributed server. The above-mentioned task scheduling platform or electronic device may include an electrical equipment interface, a fire extinguishing device interface, a task processing program, etc., wherein the task scheduling platform or electronic device can communicate with the electrical equipment through the electrical equipment interface, so as to receive the status data of the electrical equipment and send tasks to the fire extinguishing device, and the task scheduling platform can communicate with the fire extinguishing device through the electrical equipment interface, so as to receive the status data of the electrical equipment and send tasks to the fire extinguishing device.

[0050] The above-mentioned imaging device is used to capture real-time images inside the shooting device so as to provide visual information when any abnormality is discovered in time, which is helpful for diagnosis or maintenance. The fire extinguishing piece device interface is connected to the above-mentioned fire extinguishing piece, and an electric heating component (such as a heating wire, a heating piece, etc.) may be provided inside the above-mentioned fire extinguishing piece, and the fire extinguishing piece is triggered by controlling the electric heating component for heating. The above-mentioned fire extinguishing piece may be composed of a silica gel substrate and perfluorohexanone microcapsules, and is used to respond quickly in the event of a fire or other emergency. When a fire extinguishing instruction is received, the electric heating component is powered on for heating. When the heat reaches a certain temperature or encounters an open flame, the perfluorohexanone microcapsules of the fire extinguishing piece rupture, releasing perfluorohexanone, quickly absorbing heat and isolating the air, so that the temperature is reduced to below the flame point temperature to achieve automatic fire extinguishing, so as to control the fire and prevent it from spreading.

[0051] The above monitoring images are visual information monitored in real time inside the equipment. The above monitoring images can be understood as image data that needs to be analyzed to find out whether there is a fire source, including the operating status of the equipment, temperature change status, smoke generation, signs of fire or other possible indications of abnormal conditions.

[0052] It should be noted that by obtaining monitoring images of electrical equipment, fire sources or other potential problems can be discovered in a timely manner, and corresponding fire-fighting measures can be taken.

[0053] 102. Perform fire source identification on the monitoring image to obtain a fire source identification result.

[0054] In the embodiment of the present invention, the fire source recognition model can be used to perform fire source recognition on the monitoring image to obtain a fire source recognition result.

[0055] The above-mentioned fire source identification is a process of detecting fire sources from monitoring images.

[0056] The fire source recognition model can be a fire source recognition model based on deep learning or machine learning, such as a convolutional neural network (CNN), a recurrent neural network (RNN), etc. The fire source recognition model is trained by a sample image training data set, and the sample image training data set includes image data of the fire source and corresponding fire source label data. The training can be supervised training, which can be understood as adjusting the parameters of the model by using a set of samples of known categories to achieve the required performance.

[0057] The fire source recognition result includes a fire source target frame, which can be understood as a detection frame marked in an image or video for identifying a potential fire source area, including information such as the location and size of the fire source.

[0058] 103. Based on the fire source identification result, the fire source location is determined in the internal space of the electrical equipment.

[0059] In the embodiment of the present invention, the location of the fire source can be determined in the internal space of the electrical equipment according to the fire source identification result.

[0060] The above-mentioned fire source location can be understood as the place where the flame originates.

[0061] In a possible embodiment, the fire source location may be determined in the internal space of the electrical device based on the image area of ​​the fire source target frame in the monitoring image and the spatial mapping relationship between the monitoring image and the internal space of the electrical device.

[0062] The above spatial mapping relationship can be understood as a process of mapping elements in one space to another space. The above spatial mapping relationship between the monitoring image and the internal space of the electrical device can be understood as associating the monitoring image with the internal space of the electrical device to establish a mapping relationship between the two.

[0063] It should be noted that, through the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment, the fire source location can be determined in the internal space of the electrical equipment according to the image area of ​​the fire source target frame in the monitoring image.

[0064] 104. Based on the location of the fire source and the fire extinguishing range of the fire extinguishing piece, a target fire extinguishing piece is determined from among the plurality of fire extinguishing pieces.

[0065] In the embodiment of the present invention, the fire extinguishing range of the fire extinguishing piece can be understood as the spraying distance and coverage area of ​​the fire extinguishing piece. The fire extinguishing range of the fire extinguishing piece determines the size of the space in which it can extinguish the fire.

[0066] Specifically, the distance between the fire source location and each fire extinguishing plate can be calculated according to the fire source location and the fire extinguishing range of the fire extinguishing plate. Then, according to the fire extinguishing range of the fire extinguishing plate, the fire extinguishing plate whose distance from the fire source location is less than its fire extinguishing range is determined as the candidate fire extinguishing plate. Among the candidate fire extinguishing plates, the most suitable extinguishing plate is selected as the target fire extinguishing plate with the goal of maximizing the coverage range and using the least number of fire extinguishing plates. This ensures that the least number of fire extinguishing plates can be used during fire extinguishing and maximizes its fire extinguishing effect, which can effectively cover the area that needs to be extinguished without wasting resources.

[0067] 105. Control the target fire extinguishing piece to trigger and extinguish the fire at the fire source location.

[0068] In an embodiment of the present invention, after the target fire extinguishing plates are determined, the controller of the electrical equipment will trigger and activate these target fire extinguishing plates, and the electric heating components inside the fire extinguishing plates will be energized for heating. When the heat reaches a certain temperature or encounters an open flame, the perfluorohexanone microcapsules of the fire extinguishing plates will rupture, releasing perfluorohexanone, rapidly absorbing heat and isolating the air, thereby reducing the temperature to below the flame point temperature and achieving automatic fire extinguishing.

[0069] In the embodiment of the present invention, the present invention effectively improves the firefighting intensity of electrical equipment and reduces the work risks of firefighters by accurately locating the fire source, intelligently selecting appropriate firefighting resources, and efficiently performing firefighting operations.

[0070] In the embodiment of the present invention, a monitoring image of the interior of the electrical equipment is obtained; a fire source is identified on the monitoring image to obtain a fire source identification result; based on the fire source identification result, the fire source position is determined in the internal space of the electrical equipment; based on the fire source position and the fire extinguishing range of the fire extinguishing piece, a target fire extinguishing piece is determined from a plurality of fire extinguishing pieces; and the target fire extinguishing piece is controlled to be triggered to extinguish the fire at the fire source position. By identifying the fire source of the monitoring image inside the electrical equipment to obtain a fire source identification result, and according to the fire source identification result, the fire source position is determined in the internal space of the electrical equipment, and the fire source position is used to determine the target fire extinguishing piece from a plurality of fire extinguishing pieces with the fire source extinguishing range, so as to control the target fire extinguishing piece to be triggered, and extinguish the fire at the fire source position, the fire source can be quickly and accurately located and effectively extinguished, which effectively improves the fire fighting intensity of the electrical equipment and reduces the work risk of firefighters.

[0071] It is understandable that in the specific implementation of this application, related data such as electrical equipment data, image data, task data, etc. are involved. When the embodiments in this application are applied to specific products or technologies, user permission or consent is required, and the collection, use and processing of relevant data, as well as the training, deployment and calling of large language models, must comply with relevant laws, regulations and standards of relevant countries and regions.

[0072] Optionally, in the step of performing fire source identification on the monitoring image to obtain the fire source identification result, the monitoring image can be subjected to target recognition processing by a trained fire source identification model to obtain the target recognition result; and the fire source identification result is determined based on the target recognition result.

[0073] In an embodiment of the present invention, the target recognition result includes a target detection frame and a confidence score corresponding to the target detection frame, and the target recognition result includes at least one of a spark recognition result, a flame recognition result, and a smoke recognition result. The target can be understood as a fire-related phenomenon such as a spark, a flame, or smoke. The target recognition result includes information on all potential fire source locations detected in the image and corresponding confidence scores.

[0074] The monitoring images mentioned above are image data that need to be analyzed to find out whether there is a fire source.

[0075] The trained fire source recognition model can be a fire source recognition model based on deep learning or machine learning, for example, a convolutional neural network (CNN), a recurrent neural network (RNN), etc. The trained fire source recognition model is obtained by training the fire source recognition model to be trained with a sample image training data set, and the sample image training data set includes image data of the fire source and corresponding fire source label data.

[0076] Specifically, the fire source label data may include spark labels, flame labels or smoke labels, and the sample image is input into the fire source recognition model to be trained. The fire source recognition result corresponding to the sample image is output by the recognition model to be trained. The error loss between the fire source recognition result corresponding to the sample image and the fire source label data corresponding to the sample image is calculated by the loss function. The model parameters of the recognition model to be trained are adjusted with minimizing the error loss as the optimization goal, and the adjustment process of the model parameters is iterated. When the number of iterations or the error loss converges, the training is stopped to obtain a trained fire source recognition model. The fire source label data may include spark labels, flame labels and smoke labels, wherein the spark label may be a spark labeling box, the flame label may be a flame labeling box, and the smoke label may be a smoke box. The fire source recognition result output by the recognition model to be trained may include spark recognition result, flame recognition result and smoke recognition result. The spark recognition result is a spark target box, the flame recognition result is a flame target box, and the smoke recognition result is a smoke target box.

[0077] The above loss function can be calculated as follows:

[0078]

[0079] LOSS=γ 1 LOSS1+γ 2 LOSS2+γ 3 LOSS3

[0080] Among them, the above LOSS represents the error loss between the fire source recognition result corresponding to the sample image and the fire source label data corresponding to the sample image, the above LOSS1 represents the error loss between the electric spark recognition result and the electric spark label, LOSS2 represents the error loss between the flame recognition result and the flame label, LOSS3 represents the error loss between the smoke recognition result and the smoke label, N A Indicates the number of EDM annotation boxes corresponding to the sample image, M A Indicates the number of spark target frames corresponding to the fire source recognition results of the sample image. represents the i-th EDM annotation box, represents the jth EDM target frame, N B Indicates the number of flame annotation boxes corresponding to the sample image, M B Indicates the number of flame target boxes corresponding to the fire source recognition results of the sample image. represents the i-th flame labeling box, represents the jth flame target frame, N C Indicates the number of smoke annotation boxes corresponding to the sample image, M C Indicates the number of smoke target boxes corresponding to the fire source recognition results of the sample image. represents the i-th smoke annotation box, represents the jth smoke target frame, γ 1 , γ 2 , γ 3 is an artificially set empirical coefficient, γ 1 , γ 2 , γ 3 The sum of the three is 1.

[0081] The target recognition process can be understood as a process of analyzing the monitoring image to identify the fire source characteristics. The fire source characteristics include electric sparks, flames or smoke.

[0082] Optionally, in the step of determining the fire source identification result based on the target identification result, if the target identification result includes multiple target detection frames, the target detection frame whose confidence is greater than or equal to a preset confidence threshold is determined as the fire source target frame; and the fire source identification result is determined based on the fire source target frame.

[0083] In the embodiment of the present invention, the above-mentioned preset confidence threshold is a confidence threshold preset by the system.

[0084] The fire source target frame may be understood as a detection frame marked in an image or video for identifying a potential fire source area.

[0085] It is understandable that when multiple target detection frames are detected, the target detection frames whose confidence that the detection frames contain the fire source is greater than or equal to the preset threshold are screened out and determined as the fire source target frames. Only when the confidence of the detection frame is higher than the preset confidence threshold, the detection frame will be considered as a valid fire source target frame.

[0086] Optionally, in the step of determining the fire source identification result based on the fire source target frame, if the number of fire source target frames is one, the fire source identification result is directly determined based on the fire source target frame; if the number of fire source target frames is two or more, two or more fire source target frames are merged and fused to obtain a fused target frame; and the fire source identification result is determined based on the fused target frame.

[0087] In the embodiment of the present invention, the fire source identification result includes a fire source target frame.

[0088] The above fire source recognition results include a fused target frame.

[0089] The fire source target frame is a rectangular frame marked in an image or video to identify a potential fire source area.

[0090] The above-mentioned merging and fusion can be understood as a processing process of combining multiple similar objects or fire source target frames into an overall process to improve the recognition accuracy.

[0091] The above-mentioned fire source identification results include confirmation that a fire source does exist in a certain area, as well as information such as the specific location and size of the fire source.

[0092] It should be noted that when only one fire source target frame is detected, the fire source recognition result can be directly determined based on the fire source target frame; when there are two or more fire source target frames, these target frames need to be merged and fused to form a fused target frame; finally, the fire source recognition result is determined based on the fused target frame. The above merging and fusion can be to connect the boundaries of multiple target frames to form a minimum rectangular frame, thereby obtaining a fused target frame.

[0093] Optionally, in the step of determining the fire source location in the internal space of the electrical equipment based on the fire source identification result, if the fire source identification result includes a fire source target box, a first image area is determined in the monitoring image based on the fire source target box; based on the first image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment, the fire source location is determined in the internal space of the electrical equipment.

[0094] In the embodiment of the present invention, the fire source target frame is a marking frame used to indicate the location and size of the existing fire source.

[0095] The above-mentioned spatial mapping relationship can be understood as a process of mapping elements in one space to another space.

[0096] The spatial mapping relationship between the above-mentioned monitoring image and the internal space of the electrical equipment can be to associate the image data obtained by monitoring with the internal structure or spatial layout of the electrical equipment to establish a mapping relationship between the two. Specifically, it is necessary to extract key feature points, edges, textures and other information from the monitoring image. A three-dimensional model can be pre-defined in the internal space of the electrical equipment to describe the geometric structure and component layout of the equipment. By matching and aligning the feature points in the monitoring image with the corresponding points or areas in the internal space model of the electrical equipment, a mapping relationship between the image space and the internal space of the equipment is established. The spatial mapping relationship between the monitoring image and the internal space of the electrical equipment can be used to locate the location of the fire source or other abnormal conditions in the internal space of the electrical equipment. For example, if the monitoring image shows that the temperature in a certain area is abnormally high, the exact location of this hot spot inside the equipment can be determined through the mapping relationship.

[0097] It should be noted that after the fire source target frame is identified, the fire source target frame can be used to mark the first image area, and the specific location of the fire source can be accurately determined in the internal space of the electrical equipment by using the spatial mapping relationship between the first image area and the monitoring image and the internal space of the electrical equipment.

[0098] Optionally, in the step of determining the location of the fire source in the internal space of the electrical equipment based on the fire source identification result, if the fire source identification result includes a fusion target box, then based on the fusion target box, a thermal map corresponding to the fusion target box is determined in the monitoring image; in the thermal map, areas with thermal values ​​greater than or equal to the thermal value threshold are screened out to obtain a second image area; based on the second image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment, the location of the fire source is determined in the internal space of the electrical equipment.

[0099] In an embodiment of the present invention, the above-mentioned fused target frame can improve the accuracy of target detection by combining information of multiple detection frames. The above-mentioned imaging device can have an infrared module to collect infrared images inside the electrical equipment, thereby obtaining a monitoring thermal map of the electrical equipment. The monitoring thermal map is the same size as the monitoring image, so the thermal map corresponding to the fused target frame can be found in the monitoring thermal map.

[0100] The above heat map shows the density or value of data through color changes. In the heat map, higher value areas are represented by warm colors (such as red) and lower value areas are represented by cold colors (such as blue). The above heat map can reflect information such as the temperature distribution or flame intensity of the fused target frame.

[0101] The above-mentioned thermal value threshold is a pre-set thermal value threshold.

[0102] Specifically, each pixel or area in the thermal map is compared according to its thermal value. If the thermal value of a pixel or area is greater than or equal to the thermal value threshold, then the area greater than or equal to the thermal value threshold is used as the second image area. This can more intuitively identify which parts of the image are hot spots or high-energy areas, such as the location of the fire source in fire monitoring.

[0103] By using the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment, it is possible to locate the location of the fire source or other abnormal conditions in the internal space of the electrical equipment. For example, if the monitoring image shows that the temperature in a certain area is abnormally high, the mapping relationship can be used to determine the exact location of this hot spot inside the equipment.

[0104] Optionally, in the step of determining a target fire extinguishing piece among several fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece, the distance between the fire source location and each fire extinguishing piece can be calculated; the fire extinguishing piece whose distance is less than the fire extinguishing range is determined as a candidate fire extinguishing piece; and among the candidate fire extinguishing pieces, the target fire extinguishing piece is determined with the largest coverage and the least fire extinguishing piece as the goal.

[0105] In the embodiment of the present invention, when determining which fire extinguishing pieces to use to deal with a certain fire source, it is necessary to calculate the distance between the position of each fire extinguishing piece and the fire source. If the distance between a certain fire extinguishing piece and the fire source is less than its effective fire extinguishing range, then the fire extinguishing piece is considered to be a valid candidate fire extinguishing piece and can be considered to be used to extinguish the fire.

[0106] Furthermore, among multiple candidate fire extinguishing pieces, the one with the largest coverage should be selected, and the number of pieces used should be as small as possible. Specifically, it is necessary to find a balance point that can effectively cover the area that needs to be extinguished without wasting resources.

[0107] In an embodiment of the present invention, the distance between the fire source location and each fire extinguishing piece is calculated, and then, according to the fire extinguishing range of the fire extinguishing piece, the fire extinguishing piece whose distance from the fire source location is smaller than its fire extinguishing range is determined as a candidate fire extinguishing piece, and among the candidate fire extinguishing pieces, the most suitable extinguishing piece is selected as the target fire extinguishing piece with the goal of maximizing the coverage range and using the least number of fire extinguishing pieces. This is to ensure that the least number of fire extinguishing pieces can be used when extinguishing a fire, and the fire extinguishing effect is maximized, so as to effectively cover the area that needs to be extinguished without wasting resources.

[0108] like Figure 2 As shown, an embodiment of the present invention provides an electrical equipment fire extinguishing device based on image recognition, and the electrical equipment fire extinguishing device based on image recognition includes:

[0109] An acquisition module 201 is used to acquire a monitoring image inside the electrical device;

[0110] The fire source identification module 202 is used to identify the fire source of the monitoring image and obtain a fire source identification result;

[0111] A first determination module 203, configured to determine the location of a fire source in the internal space of the electrical device based on the fire source identification result;

[0112] A second determination module 204 is used to determine a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece;

[0113] The control module 205 is used to control the target fire extinguishing piece to be triggered to extinguish the fire at the fire source location.

[0114] Optionally, the fire source identification module 202 is also used to perform target recognition processing on the monitoring image through a trained fire source recognition model to obtain a target recognition result, wherein the target recognition result includes a target detection frame and a confidence level corresponding to the target detection frame, and the target recognition result includes at least one of an electric spark recognition result, a flame recognition result and a smoke recognition result; based on the target recognition result, a fire source recognition result is determined.

[0115] Optionally, the fire source identification module 202 is also used to, if the target identification result includes multiple target detection frames, determine the target detection frame with a confidence greater than or equal to a preset confidence threshold as a fire source target frame; and determine the fire source identification result based on the fire source target frame.

[0116] Optionally, the fire source identification module 202 is also used to directly determine the fire source identification result based on the fire source target frame if the number of the fire source target frames is one, and the fire source identification result includes the fire source target frame; if the number of the fire source target frames is two or more, merge and fuse the two or more fire source target frames to obtain a fused target frame; determine the fire source identification result based on the fused target frame, and the fire source identification result includes the fused target frame.

[0117] Optionally, the first determination module 203 is also used to determine a first image area in the monitoring image based on the fire source target box if the fire source identification result includes the fire source target box; and determine the fire source position in the internal space of the electrical equipment based on the first image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment.

[0118] Optionally, the first determination module 203 is also used to determine, based on the fusion target box, a thermal map corresponding to the fusion target box in the monitoring image if the fire source identification result includes the fusion target box; in the thermal map, screen out areas whose thermal values ​​are greater than or equal to a thermal value threshold to obtain the second image area; based on the second image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical equipment, determine the fire source location in the internal space of the electrical equipment.

[0119] Optionally, the second determination module 204 is also used to calculate the distance between the fire source location and each of the fire extinguishing pieces; determine the fire extinguishing pieces whose distance is less than the fire extinguishing range as candidate fire extinguishing pieces; and among the candidate fire extinguishing pieces, determine the target fire extinguishing piece with the largest coverage and the least fire extinguishing piece as the goal.

[0120] like Figure 3 As shown, an embodiment of the present invention further provides an electronic device, including a processor, and the processor can execute any one of the above-mentioned electrical equipment fire extinguishing methods based on image recognition.

[0121] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing an electrical equipment fire extinguishing method based on image recognition, which is stored in the memory 302 and can be run on the processor 301, wherein:

[0122] The processor 301 runs the computer program of the electrical equipment fire extinguishing method based on image recognition stored in the memory 302, and performs the following steps:

[0123] Acquiring a monitoring image inside the electrical equipment;

[0124] Performing fire source identification on the monitoring image to obtain a fire source identification result;

[0125] Based on the fire source identification result, determining the fire source location in the internal space of the electrical equipment;

[0126] Determining a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece;

[0127] The target fire extinguishing piece is controlled to be triggered to extinguish the fire at the fire source location.

[0128] Optionally, the processor 301 performs fire source identification on the monitoring image to obtain a fire source identification result, including:

[0129] Performing target recognition processing on the monitoring image through the trained fire source recognition model to obtain a target recognition result, wherein the target recognition result includes a target detection frame and a confidence level corresponding to the target detection frame, and the target recognition result includes at least one of an electric spark recognition result, a flame recognition result, and a smoke recognition result;

[0130] Based on the target identification result, a fire source identification result is determined.

[0131] Optionally, the determining to obtain a recognition result based on the target recognition result performed by the processor 301 includes:

[0132] If the target recognition result includes multiple target detection frames;

[0133] The target detection frame whose confidence is greater than or equal to a preset confidence threshold is determined as a fire source target frame;

[0134] The fire source identification result is determined based on the fire source target frame.

[0135] Optionally, the determining of the fire source identification result based on the fire source target frame performed by the processor 301 includes:

[0136] If the number of the fire source target frames is one, the fire source identification result is directly determined based on the fire source target frame, and the fire source identification result includes the fire source target frame;

[0137] If the number of the fire source target frames is two or more, merging and fusing the two or more fire source target frames to obtain a fused target frame;

[0138] The fire source identification result is determined based on the fusion target frame, and the fire source identification result includes the fusion target frame.

[0139] Optionally, the determining of the fire source location in the internal space of the electrical device based on the fire source identification result performed by the processor 301 includes:

[0140] If the fire source identification result includes the fire source target frame, determining a first image area in the monitoring image based on the fire source target frame;

[0141] Based on the first image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

[0142] Optionally, the determining of the fire source location in the internal space of the electrical device based on the fire source identification result performed by the processor 301 includes:

[0143] If the fire source identification result includes the fused target frame, then based on the fused target frame, determining a thermal map corresponding to the fused target frame in the monitoring image;

[0144] In the thermal map, a region whose thermal value is greater than or equal to a thermal value threshold is screened out to obtain the second image region;

[0145] Based on the second image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

[0146] Optionally, the processor 301 determines a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source position and the fire extinguishing range of the fire extinguishing piece, including:

[0147] Calculating the distance between the fire source position and each of the fire extinguishing plates;

[0148] Determine the fire extinguishing piece whose distance is smaller than the fire extinguishing range as a candidate fire extinguishing piece;

[0149] Among the candidate fire extinguishing sections, the target fire extinguishing section is determined with the goal of maximizing the coverage and selecting the least fire extinguishing section.

[0150] An embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the computer program implements the various processes of the electrical equipment fire extinguishing method based on image recognition or the electrical equipment fire extinguishing method based on image recognition on the application side provided by the embodiment of the present invention, and can achieve the same technical effect. To avoid repetition, it will not be repeated here.

[0151] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0152] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A method for extinguishing fire of electrical equipment based on image recognition, wherein an image device and a plurality of fire extinguishing plates arranged in a distributed manner are installed in the electrical equipment, wherein the image device is used to collect images inside the electrical equipment, and wherein: The method comprises the following steps: Acquiring a monitoring image inside the electrical equipment; Performing fire source identification on the monitoring image to obtain a fire source identification result; Based on the fire source identification result, determining the fire source location in the internal space of the electrical equipment; Determining a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece; The target fire extinguishing piece is controlled to be triggered to extinguish the fire at the fire source location.

2. The electrical equipment fire extinguishing method based on image recognition according to claim 1, characterized in that: The performing fire source identification on the monitoring image to obtain a fire source identification result includes: Performing target recognition processing on the monitoring image through the trained fire source recognition model to obtain a target recognition result, wherein the target recognition result includes a target detection frame and a confidence level corresponding to the target detection frame, and the target recognition result includes at least one of an electric spark recognition result, a flame recognition result, and a smoke recognition result; Based on the target identification result, a fire source identification result is determined.

3. The electrical equipment fire extinguishing method based on image recognition according to claim 2, characterized in that: The determining of the fire source identification result based on the target identification result includes: If the target recognition result includes multiple target detection frames; The target detection frame whose confidence is greater than or equal to a preset confidence threshold is determined as a fire source target frame; The fire source identification result is determined based on the fire source target frame.

4. The electrical equipment fire extinguishing method based on image recognition according to claim 3, characterized in that: The determining the fire source identification result based on the fire source target frame includes: If the number of the fire source target frames is one, the fire source identification result is directly determined based on the fire source target frame, and the fire source identification result includes the fire source target frame; If the number of the fire source target frames is two or more, merging and fusing the two or more fire source target frames to obtain a fused target frame; The fire source identification result is determined based on the fusion target frame, and the fire source identification result includes the fusion target frame.

5. The electrical equipment fire extinguishing method based on image recognition according to claim 4, characterized in that: The step of determining the location of the fire source in the internal space of the electrical equipment based on the fire source identification result includes: If the fire source identification result includes the fire source target frame, determining a first image area in the monitoring image based on the fire source target frame; Based on the first image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

6. The electrical equipment fire extinguishing method based on image recognition according to claim 4, characterized in that: The step of determining the location of the fire source in the internal space of the electrical equipment based on the fire source identification result includes: If the fire source identification result includes the fused target frame, then based on the fused target frame, determining a thermal map corresponding to the fused target frame in the monitoring image; In the thermal map, a region whose thermal value is greater than or equal to a thermal value threshold is screened out to obtain the second image region; Based on the second image area and the spatial mapping relationship between the monitoring image and the internal space of the electrical device, the fire source position is determined in the internal space of the electrical device.

7. The electrical equipment fire extinguishing method based on image recognition according to any one of claims 1 to 6, characterized in that: The step of determining a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source position and the fire extinguishing range of the fire extinguishing piece comprises: Calculating the distance between the fire source position and each of the fire extinguishing plates; Determine the fire extinguishing piece whose distance is smaller than the fire extinguishing range as a candidate fire extinguishing piece; Among the candidate fire extinguishing sections, the target fire extinguishing section is determined with the goal of maximizing the coverage and selecting the least fire extinguishing section.

8. An electrical equipment fire extinguishing device based on image recognition, characterized in that: The electrical equipment fire extinguishing device based on image recognition comprises: An acquisition module, used to acquire a detection image inside the electrical device; A fire source identification module is used to identify the fire source of the monitoring image and obtain a fire source identification result; A first determination module, configured to determine the location of a fire source in the internal space of the electrical device based on the fire source identification result; A second determination module is used to determine a target fire extinguishing piece from among the plurality of fire extinguishing pieces based on the fire source location and the fire extinguishing range of the fire extinguishing piece; The control module is used to control the target fire extinguishing piece to be triggered to extinguish the fire at the fire source location.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the electrical equipment fire extinguishing method based on image recognition as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the electrical equipment fire extinguishing method based on image recognition as described in any one of claims 1 to 7 are implemented.

Images