Electric meter box fire early warning method, device and system

Abstract

The invention relates to an electric meter box fire early warning method, device and system. The electric meter box fire early warning method comprises the following steps: if fire early warning information of an electric meter box is received, calling electric meter box environment image data acquired by an image data acquisition module; determining the credibility of the fire early warning information according to the electric meter box environment image data; and when the credibility exceeds a preset fire hazard judgment threshold, sending the fire hazard early warning information to a fire hazard monitoring platform. According to the scheme provided by the invention, the fire early warning information sent to the fire monitoring platform can be ensured to be credible, and the accuracy of fire early warning and the effectiveness of fire rescue are improved.

Description

Technical Field

[0001] The present application relates to the technical field of electric meter boxes, and in particular to an electric meter box fire early warning method, device and system. Background Art

[0002] The electric meter box is a common electrical equipment widely used in industry and households. It can provide protection for vulnerable equipment such as electrical switches, thereby ensuring the safety of the circuit. However, when the electricity is overloaded, the circuit of the electric meter box may generate a lot of heat, which may cause a fire hazard. Therefore, the electric meter box needs to be equipped with a corresponding safety monitoring mechanism.

[0003] However, the traditional safety monitoring mechanism of the meter box is not perfect and is highly dependent on temperature sensors and smoke sensors to detect whether a fire has occurred. This monitoring method may result in false alarms. Summary of the invention

[0004] Based on this, it is necessary to provide a meter box fire warning method, device and system that can accurately provide meter box fire alarm in response to the above technical problems.

[0005] In a first aspect, the present application provides a fire warning method for an electric meter box, comprising:

[0006] If fire warning information of the electric meter box is received, the environmental image data of the electric meter box obtained by the image data acquisition module is called;

[0007] Determine the credibility of fire warning information based on the environmental image data of the meter box;

[0008] When the credibility exceeds the preset fire judgment threshold, the fire warning information is sent to the fire monitoring platform.

[0009] In one of the embodiments, the fire warning information includes at least one of an ambient temperature and humidity alarm message, a meter terminal temperature alarm message, and an equipment overload alarm message.

[0010] In one of the embodiments, each alarm message in the fire warning information is communicated in a message queue communication manner.

[0011] In one embodiment, determining the credibility of fire warning information based on the environmental image data of the electric meter box includes the following steps:

[0012] Binarization is performed on the environmental image data of the electric meter box to obtain a binary image;

[0013] According to the binary image, smoke monitoring information, light perception change information and image motion change information are obtained; the smoke monitoring information represents whether there is smoke in the meter box environment; the light perception change information represents the change of light intensity in the meter box environment; the image motion change information represents the change of the motion state of the object in the image;

[0014] The credibility of the fire warning information is obtained based on the smoke monitoring information, light perception change information and image motion change information.

[0015] In one embodiment, obtaining smoke monitoring information, light perception change information and image motion change information according to a binary image includes the following steps:

[0016] According to the proportion of white pixels in the binary image, determine whether there is fire smoke and obtain smoke monitoring information;

[0017] Determine the average illumination intensity of the binary image, and obtain light perception change information based on the difference in the average illumination intensity of the binary image at multiple moments;

[0018] The frame difference method is used to process binary images at multiple moments to obtain image motion change information.

[0019] In one embodiment, obtaining the credibility of fire warning information according to smoke monitoring information, light perception change information, and image motion change information includes the following steps:

[0020] Determine the fire credibility score based on smoke monitoring information, light perception change information, and image motion change information;

[0021] The credibility of the fire warning information is determined according to the fire credibility determination range in which the fire credibility score falls.

[0022] In one embodiment, the fire warning information includes a pile warning message, and the method further includes:

[0023] Acquire the meter box environment image data collected by the image data acquisition module;

[0024] Grayscale processing of the meter box environment image data to obtain a grayscale image;

[0025] Analyze the grayscale image and the initial installation environment image by image comparison method to obtain the environmental deposit analysis results;

[0026] When the environmental accumulation analysis results confirm the presence of combustible accumulation, an accumulation warning message is sent to the fire monitoring platform.

[0027] In one embodiment, the grayscale image and the initial installation environment image are analyzed by an image comparison method to obtain an environmental deposit analysis result, including:

[0028] Using at least two image comparison algorithms to compare and analyze the grayscale image and the initial installation environment image, and obtaining a comparison and analysis result corresponding to each image comparison algorithm, the comparison and analysis result including the presence of combustible accumulation and the absence of combustible accumulation;

[0029] If the proportion of combustible accumulation in the multiple comparison and analysis results is greater than or equal to the preset proportion, it is determined that combustible accumulation exists around the electric meter box;

[0030] If the proportion of combustible accumulation in multiple comparison and analysis results is less than a preset proportion, it is determined that there is no combustible accumulation around the electric meter box.

[0031] In one of the embodiments, the image comparison algorithm includes at least two of an image mean algorithm, a perceptual hash algorithm, a SSIM structural similarity algorithm, and a histogram comparison algorithm.

[0032] In a second aspect, the present application also provides a fire warning device for an electric meter box, the device comprising:

[0033] An image data calling module is used to call the environmental image data of the electric meter box acquired by the image data acquisition module if fire warning information of the electric meter box is received;

[0034] A credibility confirmation module is used to determine the credibility of the fire warning information based on the environmental image data of the electric meter box;

[0035] The warning information sending module is used to send fire warning information to the fire monitoring platform when the credibility exceeds the preset fire judgment threshold.

[0036] In a third aspect, the present application further provides a controller including a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the computer program, the steps of the meter box fire warning method of the first aspect are implemented.

[0037] In a fourth aspect, the present application also provides a fire warning system for an electric meter box, the system comprising: an image data acquisition module and a controller.

[0038] An image data acquisition module is used to obtain environmental image data of the electric meter box;

[0039] The controller is the controller described in the third aspect, and the controller is connected to the image data acquisition module.

[0040] In one embodiment, the system further comprises:

[0041] Environmental temperature and humidity sensor, used to collect temperature and humidity data of the environment around the meter box;

[0042] The meter terminal temperature sensor is used to monitor the temperature of the meter terminal in the meter box.

[0043] The above-mentioned electric meter box fire warning method, device and system, when receiving fire warning information from the electric meter box, in order to avoid false alarms, call the electric meter box environmental image data obtained by the image data acquisition module, and combine the electric meter box environmental image data to determine the credibility of the fire warning information. When the credibility reaches the preset fire judgment threshold, it is considered that there is indeed a fire risk in the electric meter box or a fire has occurred, and a warning is needed. Based on this method, it can ensure that the fire warning information sent to the fire monitoring platform is credible, thereby improving the accuracy of fire warnings and the effectiveness of fire rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the conventional technology, the drawings required for use in the embodiments or the conventional technology descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] FIG1 is a schematic flow chart of a fire warning method for an electric meter box according to an embodiment;

[0046] FIG2 is a schematic diagram of a process for determining the credibility of fire warning information according to the environmental image data of the electric meter box in one embodiment;

[0047] FIG3 is a schematic diagram of a process for obtaining smoke monitoring information, light perception change information, and image motion change information in one embodiment;

[0048] FIG4 is a schematic diagram of a process for determining the credibility of fire warning information in one embodiment;

[0049] FIG5 is a comparison table of fire credibility determination ranges and credibility of fire warning information in one embodiment;

[0050] FIG6 is a schematic diagram of a process for generating a deposit warning message in one embodiment;

[0051] FIG7 is a schematic diagram of a fire warning device for an electric meter box in one embodiment;

[0052] Figure 8 FIG. 1 is a schematic diagram of a fire warning system for an electric meter box in one embodiment. DETAILED DESCRIPTION

[0053] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.

[0054] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0055] It should be noted that when an element is considered to be "connected" to another element, it can be directly connected to the other element, or connected to the other element through an intermediate element. In addition, the "connection" in the following embodiments should be understood as "electrical connection", "communication connection", etc. if there is transmission of electrical signals or data between the connected objects.

[0056] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.

[0057] The present application provides a fire warning method for an electric meter box, as shown in FIG1 , the method comprises the following steps:

[0058] S102, if fire warning information of the electric meter box is received, then the electric meter box environment image data acquired by the image data acquisition module is called;

[0059] The fire warning information of the meter box is collected by a data monitoring module arranged inside or around the meter box. The data monitoring module may include a temperature sensor, a humidity sensor, a smoke sensor, an image data acquisition module, etc. The meter box environment image data may include image data of the meter box and the environment around the meter box. For example, the image data of the meter box may include but is not limited to an image of the front of the meter box.

[0060] S104, determining the credibility of the fire warning information according to the environmental image data of the electric meter box.

[0061] S106, when the credibility exceeds the preset fire determination threshold, send fire warning information to the fire monitoring platform. The preset fire determination threshold can be set based on the specific application scenario. For example, it can be configured differently according to the environment where the meter box is located. For example, for some areas with disordered and dense cable layout and high degree of aging of meter boxes, the fire determination threshold can be set lower than the area where the meter box has been renovated. Exemplarily, in one application environment, the fire determination threshold can be set to 65%.

[0062] Specifically, when a fire warning message is received, it indicates that a fire may have occurred in the electric meter box or the environment around the electric meter box. At this time, the image data acquisition module is further called to collect the electric meter box environment image data for analysis to confirm whether the received warning information is credible, thereby reducing the possibility of misjudgment and improving the accuracy and reliability of the fire warning.

[0063] After receiving the fire warning information, the fire monitoring platform can initiate emergency response actions, such as calling the emergency unmanned fire extinguishing device installed near the meter box, activating the buzzer on the meter box to alarm, etc. Given that the fire warning information sent to the fire monitoring platform is credible, the effectiveness of subsequent fire rescue actions is guaranteed.

[0064] In one embodiment, after step S106, the method further includes:

[0065] If the fire warning information fails to be sent, the fire warning information will be sent to the fire monitoring platform again.

[0066] Among them, the method for determining the failure of sending the fire warning information may be that a feedback message from the fire monitoring platform is not received. The feedback message is generated and sent by the fire monitoring platform when the fire warning information is successfully received.

[0067] In one embodiment, if the fire warning information fails to be sent, the fire warning information is sent to the fire monitoring platform again, including:

[0068] If no feedback signal is received within a preset time after the fire warning information, the fire warning information is sent to the fire monitoring platform again. The feedback signal is generated and sent by the fire monitoring platform when the fire warning information is successfully received.

[0069] The preset duration can be configured according to the adopted communication protocol and the communication distance between the execution subject and the fire monitoring platform. By monitoring whether there is a feedback signal within the preset duration, the secondary sending of fire warning information due to communication delay can be avoided.

[0070] In one embodiment, the fire warning information includes: at least one of an ambient temperature and humidity alarm message, a meter terminal temperature alarm message, and an equipment overload alarm message.

[0071] Among them, the ambient temperature and humidity alarm message includes the ambient temperature and humidity data collected by the ambient temperature and humidity data monitoring module, and the ambient temperature and humidity alarm message is generated when the ambient temperature and humidity data is greater than or equal to the preset temperature and humidity thresholds. For the preset temperature and humidity thresholds, it can be understood that the corresponding thresholds are set in the two dimensions of temperature and humidity respectively. Compare the collected ambient temperature data and ambient humidity data with the thresholds of the above two dimensions. When the ambient temperature data is greater than or equal to the corresponding temperature threshold and the ambient humidity data is less than or equal to the humidity threshold, that is, the current ambient humidity decreases and the temperature increases significantly, indicating that there may be a fire point in the environment around the meter box at this time, the currently monitored abnormal ambient temperature and humidity data is written into the fire warning information as the ambient temperature and humidity alarm information.

[0072] The meter terminal temperature alarm message includes the temperature data of the meter box terminal collected by the meter terminal temperature data acquisition module. When the temperature data of the meter box terminal exceeds a certain threshold, it indicates that the meter box may be overloaded or even ignited the meter terminal. At this time, the current abnormal temperature data of the meter box terminal is written into the fire warning information as the meter terminal temperature alarm message.

[0073] The equipment overload alarm message includes the current and voltage data collected by the current and voltage data acquisition module. When the current and voltage data exceed the corresponding current threshold / voltage threshold, it indicates that the equipment is overloaded and there is a great fire hazard. At this time, the abnormal current and voltage data is written into the fire warning information as an equipment overload alarm message. It can be understood that the above current and voltage data can also be measured by the meter body in the meter box, without the need to install other current and voltage monitoring components in the meter box.

[0074] It is understandable that the fire warning information may also include other monitoring information for indicating the possibility of fire, such as smoke warning data detected by smoke sensors, etc., as long as it can characterize the risk of fire. Judging whether a fire has occurred based on multiple types of alarm messages can provide reference data in multiple dimensions. Combined with the analysis method, the accuracy or timeliness of fire identification can be improved. For example, the fire warning information includes environmental temperature and humidity alarm messages, meter terminal temperature alarm messages, and equipment overload alarm messages. When any alarm message is received, it is considered that there is a fire risk, which can improve the timeliness of the fire warning and avoid missed detection caused by single sensor data collection. In addition, it can also be considered that there is a fire risk when more than two alarm messages are received. At this time, false alarms caused by unreasonable settings of temperature and humidity thresholds under single sensor data can be avoided, thereby effectively improving the accuracy of fire identification.

[0075] In one embodiment, each alarm message in the fire warning information is communicated in a message queue communication manner.

[0076] Among them, the message queue is a communication mechanism between tasks or threads, and can exchange message data in an asynchronous manner.

[0077] Specifically, since the data collection between sensors is relatively independent, a message queue communication method can be used to achieve timely communication between tasks or threads. Exemplarily, when the data monitoring module (which may include but is not limited to the environmental temperature and humidity data monitoring module, the meter terminal temperature data acquisition module, and the current and voltage data acquisition module in the above embodiment) generates the above-mentioned various warning messages, the corresponding warning message can be written into the message queue for sending, and the recipient can obtain the specific warning message by parsing the message queue. Furthermore, data exchange between processes can be carried out by setting a data center on the process: the tcp_server of the data center maintains the tcp connection between processes, and receives and sends tcp data (including message queues); the data_cache_server of the data center manages the query and modification of tcp data; the callback_server is responsible for subscribing to data notifications and managing the registration and subscription of notifications.

[0078] In one embodiment, as shown in FIG2 , determining the credibility of fire warning information according to the environmental image data of the electric meter box includes the following steps:

[0079] S202, performing binarization processing on the electric meter box environment image data to obtain a binary image;

[0080] S204, obtaining smoke monitoring information, light perception change information and image motion change information according to the binary image;

[0081] S206, obtaining the credibility of the fire warning information according to the smoke monitoring information, the light perception change information and the image motion change information.

[0082] Among them, the smoke monitoring information represents whether there is smoke in the meter box environment; the light perception change information represents the change in the light intensity of the meter box environment; and the image motion change information represents the change in the motion state of the object in the image. Optionally, binarization processing can be performed by means of color threshold. The light perception change information and the image motion change information are both information determined based on binary images at multiple moments before and after. The smoke monitoring information can be determined based on the binary image corresponding to the current moment.

[0083] Specifically, a binary image can be obtained based on the binary processed meter box environment image data. Based on the binary image, smoke monitoring information, light perception change information and image motion change information can be obtained based on the pixel data distribution in the binary image; based on the smoke monitoring information, light perception change information and image motion change information, it is possible to understand whether there is smoke around the meter box, the change in the size of the flame brightness (characterized by the change in light intensity), and the swing and diffusion of the flame. Based on the above information, the credibility of the fire warning information can be further calculated.

[0084] In one embodiment, as shown in FIG3 , obtaining smoke monitoring information, light perception change information, and image motion change information according to a binary image may include the following steps:

[0085] S302, according to the proportion of white pixels in the binary image, smoke monitoring information is obtained. The smoke monitoring information may include a judgment result on whether there is fire smoke. Optionally, according to the range of the HSV (also known as Hue, Saturation, Brightness) color space, the inRange function in the open source project opencv can be used to extract a specific color area from the binary image. It can be understood that after obtaining the color area proportion of white pixels, it is compared with the preset smoke judgment threshold. When the color area proportion of white pixels exceeds the preset smoke judgment threshold, it indicates that there is fire smoke in the environmental image data. If the color area proportion of white pixels is less than the preset smoke judgment threshold, it is determined that there is no fire smoke.

[0086] S304, determine the average illumination intensity of the binary image, and obtain light perception change information based on the difference in the average illumination intensity of the binary image at multiple moments. The light perception change information may include a judgment result of whether an abnormal light intensity change occurs in the binary image. Exemplarily, the average illumination intensity of the binary image may be determined based on the binary image, and the light perception change information may be obtained based on the difference in the average illumination intensity of the binary image at multiple moments. It is understandable that when a fire occurs, the change in the average illumination intensity in the image at different moments is significantly different from the change in the average illumination intensity in a normal environment. When the difference in the average illumination intensity of the binary image at multiple moments exceeds a preset threshold value for the change in the average illumination intensity, it indicates that an abnormal light intensity change occurs in the image, and a fire may have occurred.

[0087] S306, using the frame difference method to process the binary images at multiple moments to obtain image motion change information. The image motion change information includes the judgment result of whether there is a moving object in the binary image. Exemplarily, the difference between adjacent frame images can be obtained by subtracting adjacent frames, thresholding, and removing noise according to two or three adjacent binary images, so as to judge whether there is a moving target in the image, such as a leaping flame in a fire or a component of an electric meter box that falls off due to the high temperature of the flame. It can be understood that other image moving object detection methods can also be used in the present application, such as optical flow method, background subtraction method, etc., and the embodiments of the present application are not limited, as long as it can meet the needs of detecting moving objects in the image. It can be understood that in order to ensure the safety of the equipment, generally speaking, there are fewer active moving objects in the electric meter box and its surrounding environment. When a more active moving object appears in the image data, it may be that the electric meter box or its surrounding environment has an abnormal situation, and the image data acquired by the environmental image data acquisition module contains active moving flames or environmental debris that is burned and deformed.

[0088] Specifically, the meter box fire warning method provided in the embodiment of the present application can understand whether the image contains fire smoke, whether there is a sudden increase in ambient light intensity caused by the flame, and whether there is object movement caused by the flame or the falling off of components of the meter box, by analyzing the binary image based on the above steps. The credibility of the fire warning information is determined based on the changes in physical quantities that may be caused in multiple dimensions when a fire occurs, which is conducive to improving the accuracy of the meter box fire warning method.

[0089] In one embodiment, as shown in FIG4 , obtaining the credibility of fire warning information according to smoke monitoring information, light perception change information, and image motion change information may include the following steps:

[0090] S402, determining a fire credibility score based on smoke monitoring information, light perception change information, and image motion change information.

[0091] S404: Determine the credibility of the fire warning information according to the fire credibility determination range in which the fire credibility score is located.

[0092] The fire credibility determination range is used to define a numerical interval to ultimately determine the credibility of the fire warning information, and a mapping relationship exists between multiple fire credibility determination ranges and the credibility of multiple fire warning information.

[0093] For example, in an analysis result of environmental image data, when the analysis result of smoke monitoring information is that there is fire smoke, the fire credibility score is increased by one; when the difference in average illumination intensity exceeds the preset average illumination intensity change threshold, that is, the analysis result of light perception change information is that there is an abnormal illumination intensity change, the fire credibility score is increased by one; when the analysis result of image motion change information is that there is a moving object in the image, the fire credibility score is increased by one. Obtaining a fire credibility score based on a multi-factor structure can effectively improve the accuracy of fire judgment.

[0094] In a specific implementation, as shown in FIG5 , the fire credibility determination range can be divided into five numerical intervals. When the obtained fire credibility score falls into one of the intervals, the credibility of the fire warning information at this time can be obtained accordingly. For example, when the fire credibility score is 4, it is within the numerical interval (0, 5) of the fire credibility determination range, and the credibility of the fire warning information at this time is 50%; when the fire credibility score is 25, it is within the numerical interval (20, N) of the fire credibility determination range, N represents a value above 20, and the credibility of the fire warning information at this time is 99%. It can be understood that the division of the fire credibility determination range in this embodiment is only used as a specific example. When the technical solution of this application is specifically implemented, the division of the fire credibility determination range can be determined according to specific application scenarios and requirements.

[0095] In one embodiment, as shown in FIG6 , the fire warning method for the electric meter box further includes the following steps:

[0096] S602, acquiring the electric meter box environment image data collected by the image data collection module;

[0097] S604, gray-scale processing of the electric meter box environment image data to obtain a gray-scale image;

[0098] S606, analyzing the grayscale image and the initial installation environment image by an image comparison method to obtain an environmental deposit analysis result;

[0099] S608: When the environmental deposit analysis result confirms the presence of combustible deposits, a deposit warning message is sent to the fire monitoring platform.

[0100] Specifically, the environmental deposit analysis results, i.e., the newly added deposits around the environment, can be determined by graying the environmental image data of the meter box and comparing it with the initial installation environmental image. When the environmental deposit analysis results confirm that there is a deposit of combustibles, a deposit warning message is sent to the fire monitoring platform to prompt the operation and maintenance personnel to clean up the deposits around the meter box and eliminate fire hazards.

[0101] Optionally, the identification of combustibles can use machine learning to identify objects in image data. For example, a decision tree is used to extract image features and a K-nearest neighbor algorithm is used to classify image features to determine the category of the object. Alternatively, the grayscale image can be compared with the grayscale image of combustibles in the database to determine whether combustibles exist.

[0102] In one embodiment, analyzing the grayscale image and the initial installation environment image by an image comparison method to obtain the environmental deposit analysis result may include the following steps:

[0103] S802, using at least two image comparison algorithms to compare and analyze the grayscale image and the initial installation environment image, and obtaining a comparison and analysis result corresponding to each image comparison algorithm, the comparison and analysis result including the presence of combustible accumulation and the absence of combustible accumulation;

[0104] S804, if the proportion of combustible accumulation in the multiple comparison and analysis results is greater than or equal to a preset proportion, it is determined that combustible accumulation exists;

[0105] S806: If the proportion of combustible accumulation in the multiple comparison and analysis results is less than a preset proportion, it is determined that there is no combustible accumulation.

[0106] Among them, the initial installation environment image can be used to collect image data when the installation of the meter box is completed. At this time, the surrounding environment of the meter box generally has less accumulation. By comparing the image with the above-mentioned initial installation environment image, the accumulation of combustible materials in the surrounding environment of the meter box can be known.

[0107] Exemplarily, at least two image comparison algorithms are used to compare and analyze the grayscale image and the initial installation environment image to obtain the comparison and analysis results corresponding to each image comparison algorithm. When the proportion of combustible accumulation in multiple comparison and analysis results is greater than or equal to a preset proportion, it is determined that there is combustible accumulation. If the proportion of combustible accumulation in multiple comparison and analysis results is less than a preset proportion, it is determined that there is no combustible accumulation. When it is determined that there is combustible accumulation, the controller reports an accumulation warning message to the fire monitoring platform, prompting the operation and maintenance personnel to clean up the accumulation in the environment around the meter box and eliminate fire hazards in a timely manner.

[0108] In one embodiment, the image comparison algorithm includes: at least two of an image mean algorithm, a perceptual hash algorithm, a SSIM structural similarity algorithm, and a histogram comparison algorithm.

[0109] The image mean algorithm compares the grayscale of each pixel of the image with the grayscale average of the image. When the grayscale of each pixel is greater than or equal to the average, the pixel position is recorded as 1, and when it is less than the average, the pixel position is recorded as 0, so that an integer consisting of 0 and 1 can be finally formed. This integer is the image fingerprint obtained by the image mean algorithm. Specifically, the similarity between the two images can be evaluated by comparing the image fingerprints of the grayscale image of the current environment and the grayscale image of the initial installation environment. Optionally, the similarity between images can be evaluated by comparing the Hamming distance or Manhattan distance of different image fingerprints. The smaller the distance, the more similar the two images are.

[0110] The perceptual hashing algorithm can use the dct() method provided in Opencv to perform discrete cosine transform (DCT) of grayscale images to obtain the fingerprint of the image. The similarity between the grayscale image of the current environment and the grayscale image of the initial installation environment can be evaluated by comparing the image fingerprints.

[0111] The SSIM structural similarity algorithm (Structural Similarity Index) can use a sliding window to divide the image into blocks, and use Gaussian weighting to calculate the mean, variance, and covariance of each window, and then calculate the structural similarity SSIM of the corresponding block, and finally use the average value as the structural similarity measure of the two images, that is, the average structural similarity SSIM. The average structural similarity SSIM can measure image similarity from three aspects: brightness, contrast, and structure.

[0112] The histogram comparison algorithm provides information about the color characteristics of the image by counting the distribution of each color value in the image. Based on the characteristic information, the similarity of the color distribution of two images can be measured, which can then be used to compare the similarity of images. The comparison object of the histogram comparison algorithm is usually a one-dimensional array constructed from image data (depending on the number of channels used), where each element of the array represents the number of pixels with a specific color or intensity value in the image. Optionally, the similarity between the current environment image and the installation environment image can be measured by the correlation coefficient, chi-square coefficient, intersection coefficient, and Buffett coefficient of the histogram of the two.

[0113] Exemplarily, the image mean algorithm, perceptual hash algorithm, SSIM structural similarity algorithm and histogram comparison algorithm are used to compare and analyze the grayscale image and the initial installation environment image, respectively, to obtain the comparison and analysis results corresponding to each image comparison algorithm. When the proportion of combustible accumulation in multiple comparison and analysis results is greater than or equal to a preset proportion, it is determined that there is combustible accumulation. For example, the preset proportion may be 50%. At this time, when the comparison and analysis results determined by more than two algorithms are that there are combustibles, it is considered that there is combustible accumulation around the meter box. If the proportion of combustible accumulation in multiple comparison and analysis results is less than the preset proportion, it is determined that there is no combustible accumulation. When it is determined that there is combustible accumulation, the controller reports an accumulation warning message to the fire monitoring platform, prompting the operation and maintenance personnel to clean up the accumulation in the environment around the meter box and eliminate fire hazards in time.

[0114] It should be understood that the various steps in the flow chart are displayed in sequence according to the indication of the arrows, but these steps are not necessarily executed in sequence in the order indicated by the arrows. Unless there is a clear description in this article, there is no strict order restriction on the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the figure may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0115] In one embodiment, as shown in FIG. 7 , the present application further provides a fire warning device 700 for an electric meter box, the device comprising:

[0116] The image data calling module 702 is used to call the environmental image data of the electric meter box acquired by the image data acquisition module if fire warning information of the electric meter box is received;

[0117] Credibility confirmation module 704, used to determine the credibility of fire warning information based on the meter box environment image data;

[0118] The warning information sending module 706 is used to send fire warning information to the fire monitoring platform when the credibility exceeds the preset fire determination threshold.

[0119] For the specific definition of the fire warning device for the meter box, please refer to the definition of the fire warning method for the meter box above, which will not be repeated here. The various modules in the above-mentioned fire warning device for the meter box can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation.

[0120] In one embodiment, the fire warning information includes: at least one of an ambient temperature and humidity alarm message, a meter terminal temperature alarm message, and an equipment overload alarm message.

[0121] In one embodiment, each alarm message in the fire warning information is communicated in a message queue communication manner.

[0122] In one embodiment, the credibility confirmation module 704 includes:

[0123] A binary processing unit, used for performing binary processing on the environmental image data of the electric meter box to obtain a binary image;

[0124] The information acquisition unit is used to obtain smoke monitoring information, light perception change information and image motion change information according to the binary image; the smoke monitoring information indicates whether there is smoke in the meter box environment; the light perception change information indicates the change of light intensity in the meter box environment; the image motion change information indicates the change of motion state of the object in the image;

[0125] The credibility acquisition unit is used to obtain the credibility of the fire warning information according to the smoke monitoring information, the light perception change information and the image motion change information.

[0126] In one embodiment, the information acquisition unit includes:

[0127] A smoke monitoring information determination unit, used to determine whether there is fire smoke according to the proportion of white pixels in the binary image, and obtain smoke monitoring information;

[0128] A light sensitivity change information determination unit, used to determine the average light intensity of the binary image, and obtain light sensitivity change information based on the difference in the average light intensity of the binary image at multiple moments;

[0129] The image motion change information determination unit is used to process binary images at multiple moments using a frame difference method to obtain image motion change information.

[0130] In one embodiment, the credibility acquisition unit includes:

[0131] A fire credibility scoring unit, used to determine a fire credibility score based on smoke monitoring information, light perception change information, and image motion change information;

[0132] The fire warning information credibility acquisition unit is used to determine the credibility of the fire warning information according to the fire credibility determination range in which the fire credibility score is located.

[0133] In one embodiment, the fire warning device for the electric meter box further includes:

[0134] The deposit image data acquisition module is used to obtain the meter box environment image data collected by the image data acquisition module.

[0135] A grayscale processing module is used for grayscale processing of the meter box environment image data to obtain a grayscale image;

[0136] An image comparison and analysis module is used to analyze the grayscale image and the initial installation environment image by an image comparison method to obtain an environmental deposit analysis result;

[0137] The accumulation warning module is used to generate an accumulation warning message when the environmental accumulation analysis result determines that there is a accumulation of combustibles;

[0138] The accumulation warning module is used to send an accumulation warning message to the fire monitoring platform when the environmental accumulation analysis result determines that there is combustible accumulation.

[0139] In one embodiment, the image comparison and analysis module includes:

[0140] A combustible accumulation discrimination unit is used to compare and analyze the grayscale image and the initial installation environment image using at least two image comparison algorithms to obtain a comparison and analysis result corresponding to each image comparison algorithm, wherein the comparison and analysis result includes the presence of combustible accumulation and the absence of combustible accumulation;

[0141] The combustible accumulation discrimination unit is further used to determine that combustible accumulation exists in the environment around the electric meter box when the proportion of combustible accumulation in the multiple comparison and analysis results is greater than or equal to a preset proportion;

[0142] The combustible accumulation determination unit is also used to determine that there is no combustible accumulation in the environment around the meter box when the proportion of combustible accumulation in multiple comparison and analysis results is less than a preset proportion.

[0143] In one embodiment, the image comparison algorithm in the combustible accumulation determination unit includes: at least two of an image mean algorithm, a perceptual hash algorithm, a SSIM structural similarity algorithm, and a histogram comparison algorithm.

[0144] In one embodiment, the present application further provides a controller, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the fire warning method for the electric meter box in the above embodiment when executing the computer program. The implementation process of the method steps executed in the controller can refer to the introduction in the above method embodiment, and the controller can correspondingly implement the beneficial effects in the above method embodiment.

[0145] In one embodiment, Figure 8 As shown, the present application also provides a meter box fire warning system 20, the system comprising: an image data acquisition module 22, and the above-mentioned controller (not shown).

[0146] Among them, the image data acquisition module 22 is used to obtain the environmental image data of the electric meter box. The controller is used to execute the steps of the electric meter box fire warning method in the above embodiment. The electric meter box fire warning system 20 provided in the embodiment of the present application, its controller can achieve the beneficial effects of the above method embodiment by executing the steps of the above electric meter box fire warning method, which will not be repeated here.

[0147] In one embodiment, the image data acquisition module 22 may include a dual-channel camera. The dual-channel camera is connected to the controller. The image data acquisition range of the dual-channel camera includes the front of the meter box and the surrounding environment of the meter box, and can monitor the on-site environment of the meter box and capture the image data of the meter box environment according to the controller instruction, and provide it for the controller to call.

[0148] In one embodiment, the meter box fire warning system 20 further includes: an ambient temperature and humidity sensor 24 and a meter terminal temperature sensor 26. The ambient temperature and humidity sensor 24 is used to collect temperature and humidity data of the environment around the meter box; the meter terminal temperature sensor 26 is used to monitor the meter terminal temperature of the meter box.

[0149] For example, the ambient temperature and humidity sensor 24 can be set in the environment around the meter box to collect temperature and humidity data of the environment around the meter box; the meter terminal temperature sensor 26 can be a dot matrix infrared sensor, which can be set near the meter terminal to monitor the meter terminal temperature data in real time. In addition, according to the monitoring data of the dot matrix infrared sensor, the access control status of the meter box can also be monitored by the dot matrix infrared sensor.

[0150] In one embodiment, the controller can adopt a blocking loop operation logic. When the system starts normally, the initial value of the loop flag defaults to true. At this time, the controller jumps out of the originally executed loop judgment program and executes the steps of the meter box fire warning method in the above embodiment. Through this method, fire warning monitoring can be performed after the meter box fire warning system 20 is started, and the triggering is simple and quick.

[0151] In one embodiment, the present application further provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the electric meter box fire warning method in the above embodiment are implemented.

[0152] In one embodiment, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the electric meter box fire warning method in the above embodiment.

[0153] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), tape, floppy disk, flash memory or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM).

[0154] In the description of this specification, the description with reference to the terms "some embodiments", "other embodiments", "ideal embodiments", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic descriptions of the above terms do not necessarily refer to the same embodiment or example.

[0155] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0156] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A fire warning method for an electric meter box, characterized in that: The following steps are involved: If fire warning information of the electric meter box is received, the environmental image data of the electric meter box obtained by the image data acquisition module is called; Determining the credibility of the fire warning information according to the electric meter box environment image data; When the credibility exceeds a preset fire determination threshold, the fire warning information is sent to a fire monitoring platform.

2. The method according to claim 1, characterized in that The fire warning information includes: at least one of an environmental temperature and humidity alarm message, a meter terminal temperature alarm message, and an equipment overload alarm message.

3. The method according to claim 2, characterized in that Each alarm message in the fire warning information is communicated in a message queue communication manner.

4. The method according to claim 1, characterized in that: Determining the credibility of the fire warning information according to the electric meter box environment image data comprises the following steps: Binarizing the electric meter box environment image data to obtain a binary image; According to the binary image, smoke monitoring information, light perception change information and image motion change information are obtained; the smoke monitoring information indicates whether there is smoke in the meter box environment; the light perception change information indicates changes in the light intensity of the meter box environment; the image motion change information indicates changes in the motion state of objects in the image; The credibility of the fire warning information is obtained according to the smoke monitoring information, the light perception change information and the image motion change information.

5. The method according to claim 4, characterized in that The method of obtaining smoke monitoring information, light perception change information and image motion change information according to the binary image comprises the following steps: Obtaining the smoke monitoring information according to the proportion of white pixels in the binary image; Determining the average illumination intensity of the binary image, and obtaining the light perception change information based on the difference in the average illumination intensity of the binary image at multiple moments; The binary images at multiple moments are processed using a frame difference method to obtain the image motion change information.

6. The method according to any one of claims 4-5, characterized in that: The step of obtaining the credibility of the fire warning information according to the smoke monitoring information, the light perception change information and the image motion change information comprises the following steps: Determining a fire credibility score according to the smoke monitoring information, the light perception change information, and the image motion change information; The credibility of the fire warning information is determined according to the fire credibility determination range in which the fire credibility score is located.

7. The method according to claim 1, characterized in that The method further comprises: Acquire the meter box environment image data collected by the image data collection module; Grayscale processing of the electric meter box environment image data to obtain a grayscale image; Analyze the grayscale image and the initial installation environment image by an image comparison method to obtain an environmental deposit analysis result; When the environmental deposit analysis result determines that there is a deposit of combustibles, a deposit warning message is sent to the fire monitoring platform.

8. The method according to claim 7, characterized in that The step of analyzing the grayscale image and the initial installation environment image by an image comparison method to obtain an environmental deposit analysis result includes: Using at least two image comparison algorithms to compare and analyze the grayscale image and the initial installation environment image, and obtaining comparison and analysis results corresponding to each of the image comparison algorithms, wherein the comparison and analysis results include the presence of combustible accumulation and the absence of combustible accumulation; If the proportion of combustible accumulation in the plurality of comparison and analysis results is greater than or equal to a preset proportion, it is determined that combustible accumulation exists around the electric meter box; If the proportion of combustible accumulation in the plurality of comparison and analysis results is less than the preset proportion, it is determined that there is no combustible accumulation around the electric meter box.

9. The method according to claim 8, characterized in that The image comparison algorithm includes: at least two of an image mean algorithm, a perceptual hash algorithm, a SSIM structural similarity algorithm and a histogram comparison algorithm.

10. A fire warning device for an electric meter box, characterized in that: The device comprises: An image data calling module is used to call the environmental image data of the electric meter box acquired by the image data acquisition module if fire warning information of the electric meter box is received; A credibility confirmation module, used to determine the credibility of the fire warning information according to the environmental image data of the electric meter box; The warning information sending module is used to send the fire warning information to the fire monitoring platform when the credibility exceeds a preset fire determination threshold.

11. A controller, comprising a memory and a processor, wherein a computer program is stored in the memory, characterized in that: When the processor executes the computer program, the steps of the electric meter box fire warning method according to any one of claims 1 to 9 are implemented.

12. A fire warning system for an electric meter box, characterized in that: The system comprises: An image data acquisition module is used to obtain environmental image data of the electric meter box; The controller according to claim 11, wherein the controller is connected to the image data acquisition module.

13. The system according to claim 12, characterized in that Also includes: Environmental temperature and humidity sensor, used to collect temperature and humidity data of the environment around the meter box; The meter terminal temperature sensor is used to monitor the temperature of the meter terminal in the meter box.

Images