Mountain fire point positioning method and device for power transmission line, equipment and storage medium

Abstract

The embodiment of the invention discloses a forest fire point positioning method and device for a power transmission line, equipment and a storage medium, and the method comprises the steps: obtaining the image data of the power transmission line, the image data being used for reflecting the current environment of the power transmission line; and inputting the image data into a pre-trained Kanbambala distance learning model for forest fire point positioning processing to obtain a forest fire point positioning result of the power transmission line, the forest fire point positioning result being used for reflecting whether a forest fire point exists in the current environment of the power transmission line, the Kanbazier distance learning model is obtained based on historical image data training of a plurality of power transmission lines with forest fire points; and when the forest fire point positioning result reflects that the forest fire point exists in the current environment of the power transmission line, outputting a forest fire prompt including the geographic position information of the forest fire point and the fire information of the forest fire point. The method can quickly respond to the forest fire event, improves the emergency response efficiency, and reduces the damage of the forest fire to the power transmission line. The method can be widely applied to the power transmission line safety monitoring and maintenance field.

Description

Technical Field

[0001] The present invention relates to the technical field of wildfire positioning, and in particular to a wildfire point positioning method and device, equipment and storage medium for a power transmission line. Background Art

[0002] With the continuous development of power systems and the increase in electricity demand, the safety monitoring and maintenance of transmission lines have become particularly important. However, the timely positioning and identification of transmission line wildfires has always been a challenging problem. Traditional wildfire detection methods usually rely on manual processing or simple image processing algorithms, which cannot meet the requirements of real-time and accuracy. Therefore, an efficient and accurate transmission line wildfire positioning device and method is needed. Summary of the invention

[0003] The main purpose of the present invention is to provide a method and device, equipment and storage medium for locating wildfire points on a power transmission line, which can solve the problems of inaccurate and low efficiency in locating wildfire points in the prior art.

[0004] To achieve the above object, the present invention provides a method for locating a wildfire point on a power transmission line in a first aspect, the method comprising:

[0005] Acquiring image data of the power transmission line, wherein the image data is used to reflect the current environment of the power transmission line;

[0006] The image data is input into a pre-trained Canberra distance learning model to perform wildfire point location processing, and a wildfire point location result of the transmission line is obtained, wherein the wildfire point location result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points;

[0007] When the wildfire point positioning result reflects that a wildfire point exists in the current environment of the power transmission line, a wildfire prompt is output, and the wildfire prompt includes at least the geographical location information of the wildfire point and the fire condition information of the wildfire point.

[0008] In a feasible implementation, the inputting the image data into a pre-trained Canberra distance learning model to perform wildfire point location processing to obtain a wildfire point location result of the transmission line includes:

[0009] Extracting feature vectors from the image data to obtain vectors to be located of the image data;

[0010] Determine a target Canberra distance between the vector to be located and a model vector pre-learned by the Canberra distance learning model based on a preset Canberra distance algorithm, wherein the vector to be located is used to reflect the image features of the image data, the model vector is used to reflect the image features of the image data where a wildfire point exists, and the Canberra distance is used to indicate the degree of difference between the vector to be located and the model vector;

[0011] If the target Canberra distance is less than or equal to a preset threshold, determining that the wildfire point positioning result of the transmission line is that a wildfire point exists;

[0012] If the target Canberra distance is greater than a preset threshold, it is determined that the wildfire point positioning result of the transmission line is that there is no wildfire point.

[0013] In one possible implementation, the Canberra distance algorithm includes the following mathematical expression:

[0014]

[0015] Wherein, p and q are the vector to be located and the model vector respectively, both of which are n-dimensional vectors, k is the kth component of the vector to be located and the model vector, and d is the target Canberra distance.

[0016] In a feasible implementation, the image data is input into a pre-trained Canberra distance learning model for wildfire location processing to obtain a wildfire location result of the transmission line, and the method further includes:

[0017] The image data is preprocessed to obtain preprocessed image data.

[0018] In a feasible implementation, preprocessing the image data to obtain preprocessed image data includes:

[0019] The image data is denoised using a preset denoising algorithm to obtain denoised image data, wherein the denoising algorithm includes at least one of median filtering, Gaussian filtering and bilateral filtering, and the preprocessed image data includes the denoised image data.

[0020] In a feasible implementation, the preprocessing the image data to obtain preprocessed image data further includes:

[0021] The denoised image data is subjected to image enhancement processing using a preset image enhancement algorithm to obtain enhanced image data, wherein the image enhancement algorithm includes at least one of histogram equalization, adaptive histogram equalization and contrast enhancement, and the preprocessed image data includes the enhanced image data.

[0022] In a feasible implementation, the preprocessing the image data to obtain preprocessed image data further includes:

[0023] The enhanced image data is subjected to image segmentation processing using a preset image segmentation algorithm to obtain segmented image data, wherein the image segmentation algorithm includes at least one of threshold segmentation, edge segmentation, and region segmentation, and the preprocessed image data includes the segmented image data.

[0024] To achieve the above-mentioned purpose, the second aspect of the present invention provides a device for locating a mountain fire point of a power transmission line, the device comprising:

[0025] Data acquisition module: used to obtain image data of the transmission line, and the image data is used to reflect the current environment of the transmission line;

[0026] Positioning module: used to input the image data into a pre-trained Canberra distance learning model to perform wildfire point positioning processing, and obtain a wildfire point positioning result of the transmission line, wherein the wildfire point positioning result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points;

[0027] Prompt module: used for outputting a wildfire prompt when the wildfire point positioning result reflects that there is a wildfire point in the current environment of the transmission line. The wildfire prompt at least includes the geographical location information of the wildfire point and the fire information of the wildfire point.

[0028] To achieve the above-mentioned purpose, the third aspect of the present invention provides a computer-readable storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the method shown in the first aspect and any feasible implementation method.

[0029] To achieve the above-mentioned purpose, the fourth aspect of the present invention provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method shown in the first aspect and any feasible implementation method.

[0030] The embodiments of the present invention have the following beneficial effects:

[0031] The present invention provides a method for locating a wildfire point of a power transmission line, the method comprising: acquiring image data of the power transmission line, the image data being used to reflect the current environment of the power transmission line; inputting the image data into a pre-trained Canberra distance learning model for wildfire point positioning processing, obtaining a wildfire point positioning result of the power transmission line, the wildfire point positioning result being used to reflect whether there is a wildfire point in the current environment of the power transmission line, the Canberra distance learning model being trained based on historical image data of several power transmission lines with wildfire points; when the wildfire point positioning result reflects that there is a wildfire point in the current environment of the power transmission line, a wildfire prompt is output, and the wildfire prompt at least includes geographical location information of the wildfire point and fire information of the wildfire point. The image is classified and located by collecting the image of the power transmission line and integrating the Canberra distance learning model (hereinafter referred to as the Canberra model) to improve the detection efficiency and accuracy of the wildfire point, thereby outputting a wildfire prompt. The present invention can quickly respond to wildfire events, improve emergency response efficiency, and reduce the damage of wildfires to power transmission lines. It can be widely used in the field of safety monitoring and maintenance of power transmission lines. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] 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.

[0033] in:

[0034] Figure 1 It is a flow chart of a method for locating a wildfire point on a power transmission line according to an embodiment of the present invention;

[0035] Figure 2 It is a structural block diagram of a wildfire point locating device for a power transmission line in an embodiment of the present invention;

[0036] Figure 3 4 is a structural block diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0037] 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.

[0038] It should be noted that in recent years, the model training method has powerful image feature extraction and classification capabilities. The use of the Canberra distance learning algorithm to locate and identify wildfire points on transmission lines can improve the accuracy and efficiency of positioning, better handle nonlinear classification problems, have stronger data fitting capabilities, and have better robustness to noise and abnormal data.

[0039] In summary, a transmission line wildfire location method based on Canberra distance learning and a device thereof are proposed to solve the problems existing in the traditional method and improve the location accuracy and real-time performance of the wildfire point, as follows.

[0040] See also Figure 1 , Figure 1 This is a flow chart of a method for locating a wildfire point on a power transmission line in an embodiment of the present invention. The method can be applied to both a terminal and a server. The terminal can be a desktop terminal or a mobile terminal. The mobile terminal can be at least one of a mobile phone, a tablet computer, a laptop computer, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers. This embodiment is described by applying to a terminal as an example. Figure 1 The method comprises the following steps:

[0041] 101. Acquire image data of the power transmission line, where the image data is used to reflect the current environment of the power transmission line;

[0042] In order to locate wildfire points on power transmission lines, it is necessary to monitor the surrounding environment of the power transmission lines in real time to promptly discover and locate wildfire points. Specifically, images of the transmission lines are collected in real time, and the image data is used for subsequent wildfire location. The image data collection methods include but are not limited to drone collection, surveillance camera collection, timed shooting, handheld camera collection and other methods, which are not limited here. When collecting images, it is necessary to determine the collection equipment, plan the collection route, set the collection parameters, and perform data collection, etc., which are not repeated here. The collected image data will be used as input for subsequent data preprocessing and wildfire location.

[0043] In order to improve the image quality and the separation effect of the wildfire points, the collected transmission line images can be preprocessed. The preprocessing methods include but are not limited to denoising, image enhancement and image segmentation operations. Among them, the denoising operation can reduce the noise interference in the image, the enhancement operation can enhance the contrast and details of the image, and the segmentation operation can separate the wildfire points from the background.

[0044] In a feasible implementation, the image data is input into a pre-trained Canberra distance learning model for wildfire point location processing to obtain the wildfire point location result of the transmission line, and the image data is pre-processed before obtaining the pre-processed image data.

[0045] Wherein, the preprocessing at least includes denoising processing, specifically, the image data is denoised using a preset denoising algorithm to obtain denoised image data, the denoising algorithm includes at least one of median filtering, Gaussian filtering and bilateral filtering, and the preprocessed image data includes the denoised image data. The preprocessing may also include image enhancement processing, specifically, image enhancement may be performed on the denoised image, that is, image enhancement may be performed on the denoised image data using a preset image enhancement algorithm to obtain enhanced image data, the image enhancement algorithm includes at least one of histogram equalization, adaptive histogram equalization and contrast enhancement, and the preprocessed image data includes the enhanced image data. The preprocessing may also include image segmentation processing, specifically, image segmentation may be performed on the enhanced image, that is, image segmentation may be performed on the enhanced image data using a preset image segmentation algorithm to obtain segmented image data, the image segmentation algorithm includes at least one of threshold segmentation, edge segmentation and region segmentation, and the preprocessed image data includes the segmented image data.

[0046] It should be noted that the image quality and the separation effect of wildfire spots can be improved by processing the collected transmission line images with denoising, enhancement and segmentation. Denoising is to remove the noise and interference in the image, making the wildfire spots more visible. Methods such as median filtering, Gaussian filtering and bilateral filtering can be used; enhancement aims to improve the visual effects and features of the image, making the wildfire spots more obvious. Methods such as histogram equalization, adaptive histogram equalization, contrast enhancement can be used; segmentation divides the image into different regions or objects, with the purpose of separating the wildfire spots from the background. Methods such as threshold segmentation, edge-based segmentation and region-based segmentation can be used.

[0047] Exemplarily, in the denoising process, median filtering uses a filter to replace the value of each pixel with the median of its surrounding pixels, which is suitable for removing discrete noise such as salt and pepper noise; Gaussian filtering uses a Gaussian kernel to smooth the image and reduce high-frequency noise, which is suitable for continuous noise such as Gaussian noise; bilateral filtering combines information in the spatial domain and the grayscale value domain, and can remove noise while maintaining edge information.

[0048] In image enhancement, histogram equalization adjusts the distribution of image pixel values ​​to enhance image contrast and details, making wildfire spots more prominent; adaptive histogram equalization divides the image into small blocks and performs histogram equalization on each block to avoid over-enhancement caused by global equalization; contrast enhancement highlights the details of wildfire spots by adjusting the contrast and brightness of the image, and linear or nonlinear adjustment methods can be used.

[0049] In image segmentation, threshold segmentation compares the grayscale value of pixels with the preset threshold value to divide pixels into foreground and background. It is suitable for situations where the grayscale difference between wildfire points and background is large; edge-based segmentation separates wildfire points from the background by detecting edge information in the image. Edge detection algorithms such as Canny and Sobel can be used; region-based segmentation divides the image into regions with similar features, and wildfire points are separated by regional connectivity and similarity. Region-based growth algorithms or watershed algorithms can be used. The preprocessed image data will be used as input for the Canberra distance learning algorithm model.

[0050] 102. Input the image data into a pre-trained Canberra distance learning model to perform wildfire point location processing, and obtain a wildfire point location result of the transmission line, wherein the wildfire point location result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points;

[0051] It should be noted that the Canberra distance learning model is used to calculate the relationship between wildfire data features and wildfire points. The preprocessed image data will be used as the input of the Canberra distance learning algorithm model to locate wildfire points. It can be understood that the Canberra distance learning model is pre-trained. A large number of historical transmission line images with different wildfire points are collected in advance as training data sets and test data sets to train the model, so that the model can learn the characteristics of wildfire points in advance.

[0052] The Canberra learning algorithm model is the main component of the wildfire location method. It is used to locate and identify wildfires on power transmission lines. The Canberra machine learning algorithm is very sensitive to value changes between 0 and 1. The Canberra distance numerator measures the difference between two objects, and the denominator normalizes the difference. In image retrieval and medical image recognition, the Canberra distance is less affected by abnormal data and shows better performance.

[0053] Among them, the collection of training data sets and test data sets can be achieved through the data collection module, in which the data collection module is responsible for obtaining image data from the transmission line. Data collection can be performed using drones, surveillance cameras or other image acquisition devices. This module requires steps such as determining the acquisition equipment, planning the acquisition route, setting the acquisition parameters and performing data acquisition. Collecting data includes determining the acquisition equipment, planning the acquisition route, determining the acquisition time, setting the acquisition parameters, performing data acquisition, collecting and annotating data, and data backup and sorting steps. Through the above data collection steps, the image data of the transmission lines at different wildfire points are obtained, providing sufficient training and test data for the wildfire point positioning method based on the multi-machine learning fusion method, thereby improving the accuracy and reliability of positioning.

[0054] The data collection process can be as follows: First, select the appropriate data collection equipment according to the actual situation. Data collection can be performed using drones, surveillance cameras, or other image acquisition equipment. Ensure that the equipment has sufficient resolution and shooting capabilities to capture the details and wildfire points on the transmission line. Before collection, it is necessary to plan the collection route to ensure that the transmission line area that needs to be monitored is covered. Considering that wildfire points may occur at different locations on the transmission line, the collection route should include different areas and angles. Then set appropriate collection parameters according to the functions of the equipment, including image resolution, exposure time, frame rate, etc. Ensure that the image has sufficient clarity and details for subsequent wildfire point location and identification. Use the equipment to collect data on the planned collection route. Shoot according to the set parameters and time to ensure that each area is fully covered. During the collection process, pay attention to maintaining the stability of the equipment and the consistency of the shooting angle to avoid blurring or distortion of the image. During the data collection process, annotation work can be performed at the same time. For each collected image, the location and bounding box of the wildfire point are annotated for training and evaluating the learning network model. After completing the data collection, the collected image data will be backed up, sorted and classified. It can be organized by date, region or other relevant information for subsequent training and testing.

[0055] Then, the collected images are processed using methods such as denoising, enhancement and segmentation. In the process of data preprocessing, appropriate methods can be selected according to the specific situation, or multiple methods can be combined for processing. The goal of preprocessing is to improve image quality, highlight the characteristics of wildfire points, and provide more accurate input data for subsequent wildfire point positioning tasks. Finally, according to task requirements and data characteristics, the Canberra distance learning algorithm model is trained. The training of the machine learning algorithm model includes parameter initialization, difference calculation, difference standardization, training network, iterative training, model evaluation, and model storage and deployment.

[0056] In a feasible implementation, the inputting of the image data into a pre-trained Canberra distance learning model for wildfire location processing to obtain a wildfire location result of the transmission line includes the following steps A01, A02, A03 and A04:

[0057] A01. Extract feature vectors from the image data to obtain vectors to be located of the image data;

[0058] A02. Determine a target Canberra distance between the vector to be located and a model vector pre-learned by the Canberra distance learning model based on a preset Canberra distance algorithm, wherein the vector to be located is used to reflect the image features of the image data, the model vector is used to reflect the image features of the image data where a wildfire point exists, and the Canberra distance is used to indicate the degree of difference between the vector to be located and the model vector;

[0059] In one possible implementation, the Canberra distance algorithm includes the following mathematical expression:

[0060]

[0061] Wherein, p and q are the vector to be located and the model vector respectively, both of which are n-dimensional vectors, k is the kth component of the vector to be located and the model vector, and d is the target Canberra distance.

[0062] A03. If the target Canberra distance is less than or equal to a preset threshold, determining that the wildfire point positioning result of the transmission line is that a wildfire point exists;

[0063] A04. If the target Canberra distance is greater than a preset threshold, it is determined that the wildfire point positioning result of the transmission line is that there is no wildfire point.

[0064] Among them, the Canberra distance value range is from 0 to 1. When the difference between the vector to be located and the model vector is large, the Canberra distance is 1; when the difference between the vector to be located and the model vector is small, the Canberra distance is 0. At this time, the positioning point (i.e., label) corresponding to the model vector is the wildfire point, and the preset threshold can be a value close to 0. By training the learning algorithm model, the relationship between the learning data vector and the wildfire point is saved in the database, and then the Canberra distance is calculated by comparing with the database information to find the wildfire point, and a model suitable for the positioning of wildfire points on transmission lines is trained.

[0065] Exemplarily, the Canberra distance learning algorithm model training and positioning process may include the following steps:

[0066] S1, create vector labels to mark the location and bounding box of the wildfire point;

[0067] S2, feature vector normalization processing;

[0068] S3, training the wildfire location corresponding to the feature vector data, and saving the trained model as a file for subsequent use and deployment;

[0069] S4. Use the model to locate actual power transmission line wildfires and predict and locate new images.

[0070] S5. Use the Canberra distance learning algorithm to measure the difference between the sample and the model, where the numerator of the Canberra distance algorithm measures the difference and the denominator normalizes the difference value. When the model with the smallest difference from the sample is detected, information such as the wildfire point can be determined.

[0071] 103. When the wildfire point positioning result reflects that a wildfire point exists in the current environment of the power transmission line, a wildfire prompt is output, and the wildfire prompt includes at least the geographical location information of the wildfire point and the fire condition information of the wildfire point.

[0072] It is understandable that the trained machine learning model is imported, and the image data of the power transmission line to be located is obtained in the monitoring system, including the image data of different parts of the transmission line and different time points, and then the extracted features (such as feature vectors) are input into the trained model for prediction, and the data features are passed as input to the model to obtain the output results. The model output is post-processed by threshold determination, edge detection or other algorithms to obtain the final location of the wildfire point. The wildfire prompt can be the coordinates, bounding box or other forms of location information of the wildfire point, which is used for further monitoring and processing of the wildfire point, and an alarm is issued to notify relevant personnel or institutions so that timely action can be taken. Furthermore, if there is a wildfire, a prompt is output, otherwise if there is no wildfire, it can return to step 101 to continue monitoring the situation of the transmission line and locate the wildfire point in time.

[0073] By using machine learning methods, it is possible to accurately locate wildfire points in power transmission line images. Compared with traditional rule-based or feature extraction methods, machine learning algorithms can learn the relationship between image features and wildfire points, improving the accuracy and reliability of positioning. The present invention automates the processing and analysis of power transmission line images without human intervention. The system can automatically identify and locate wildfire points, reducing human resource consumption. A large amount of power transmission line image data can be obtained, and the location of wildfire points can be accurately marked. These data can be used for subsequent data analysis, decision support, and prediction model training to help optimize wildfire monitoring and emergency management strategies.

[0074] The present invention provides a method for locating a wildfire point of a power transmission line, the method comprising: acquiring image data of the power transmission line, the image data being used to reflect the current environment of the power transmission line; inputting the image data into a pre-trained Canberra distance learning model for wildfire point positioning processing, obtaining a wildfire point positioning result of the power transmission line, the wildfire point positioning result being used to reflect whether there is a wildfire point in the current environment of the power transmission line, the Canberra distance learning model being trained based on historical image data of several power transmission lines with wildfire points; when the wildfire point positioning result reflects that there is a wildfire point in the current environment of the power transmission line, a wildfire prompt is output, and the wildfire prompt at least includes geographical location information of the wildfire point and fire information of the wildfire point. The image is classified and located by collecting the image of the power transmission line and integrating the Canberra distance learning model (hereinafter referred to as the Canberra model) to improve the detection efficiency and accuracy of the wildfire point, thereby outputting a wildfire prompt. The present invention can quickly respond to wildfire events, improve emergency response efficiency, and reduce the damage of wildfires to power transmission lines. It can be widely used in the field of safety monitoring and maintenance of power transmission lines.

[0075] See also Figure 2 , Figure 2 FIG. 1 is a structural block diagram of a device for locating a mountain fire point on a power transmission line according to an embodiment of the present invention. Figure 2 The device shown comprises:

[0076] Data acquisition module 201: used to obtain image data of the power transmission line, wherein the image data is used to reflect the current environment of the power transmission line;

[0077] Positioning module 202: used for inputting the image data into a pre-trained Canberra distance learning model to perform wildfire point positioning processing, and obtaining a wildfire point positioning result of the transmission line, wherein the wildfire point positioning result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points;

[0078] Prompt module 203: for outputting a wildfire prompt when the wildfire point positioning result reflects that a wildfire point exists in the current environment of the power transmission line, wherein the wildfire prompt at least includes the geographical location information of the wildfire point and the fire condition information of the wildfire point.

[0079] It should be noted that Figure 2 The functions of each module in the device are Figure 1 The contents of each step in the method shown are similar. To avoid repetition, they are not described here. For details, please refer to Figure 1 The contents of each step in the method shown.

[0080] The present invention provides a device for locating a wildfire point of a power transmission line, the device comprising: a data acquisition module: used for acquiring image data of the power transmission line, the image data being used for reflecting the current environment of the power transmission line; a positioning module: used for inputting the image data into a pre-trained Canberra distance learning model for wildfire point positioning processing, and obtaining a wildfire point positioning result of the power transmission line, the wildfire point positioning result being used for reflecting whether there is a wildfire point in the current environment of the power transmission line, the Canberra distance learning model being obtained by training based on historical image data of several power transmission lines with wildfire points; a prompting module: used for outputting a wildfire prompt when the wildfire point positioning result reflects that there is a wildfire point in the current environment of the power transmission line, the wildfire prompt at least including the geographical location information of the wildfire point and the fire information of the wildfire point. The image is classified and located by collecting the image of the power transmission line and integrating the Canberra distance learning model (hereinafter referred to as the Canberra model) to improve the detection efficiency and accuracy of the wildfire point, thereby outputting a wildfire prompt. The present invention can quickly respond to wildfire events, improve the efficiency of emergency response, and reduce the damage of wildfires to power transmission lines. It can be widely used in the field of safety monitoring and maintenance of power transmission lines.

[0081] Figure 3 FIG. 1 shows an internal structure diagram of a computer device in an embodiment. The computer device may be a terminal or a server. Figure 3 As shown, the computer device includes a processor, a memory and a network interface connected via a system bus. The memory includes a non-volatile storage medium and an internal memory. The non-volatile storage medium of the computer device stores an operating system and may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. The internal memory may also store a computer program. When the computer program is executed by the processor, the processor can implement the above method. Those skilled in the art can understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0082] In one embodiment, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor performs the following steps: Figure 1 The steps of the method are shown.

[0083] In one embodiment, a computer-readable storage medium is provided, which stores a computer program. When the computer program is executed by a processor, the processor performs the following steps: Figure 1 The steps of the method are shown.

[0084] Those skilled 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 program can be stored in a non-volatile computer-readable storage medium. When the 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 non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0085] The technical features of the above embodiments may be combined arbitrarily. 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.

[0086] 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 present application. 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 present application shall be subject to the attached claims.

Claims

1. A method for locating a wildfire point on a power transmission line, characterized in that: The method comprises: Acquiring image data of the power transmission line, wherein the image data is used to reflect the current environment of the power transmission line; The image data is input into a pre-trained Canberra distance learning model to perform wildfire point location processing, and a wildfire point location result of the transmission line is obtained, wherein the wildfire point location result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points; When the wildfire point positioning result reflects that a wildfire point exists in the current environment of the power transmission line, a wildfire prompt is output, and the wildfire prompt includes at least the geographical location information of the wildfire point and the fire condition information of the wildfire point.

2. The method according to claim 1, characterized in that: The step of inputting the image data into a pre-trained Canberra distance learning model to perform wildfire point location processing to obtain a wildfire point location result of the power transmission line includes: Extracting feature vectors from the image data to obtain vectors to be located of the image data; Determine a target Canberra distance between the vector to be located and a model vector pre-learned by the Canberra distance learning model based on a preset Canberra distance algorithm, wherein the vector to be located is used to reflect the image features of the image data, the model vector is used to reflect the image features of the image data where a wildfire point exists, and the Canberra distance is used to indicate the degree of difference between the vector to be located and the model vector; If the target Canberra distance is less than or equal to a preset threshold, determining that the wildfire point positioning result of the transmission line is that a wildfire point exists; If the target Canberra distance is greater than a preset threshold, it is determined that the wildfire point positioning result of the transmission line is that there is no wildfire point.

3. The method according to claim 1 or 2, characterized in that: The Canberra distance algorithm includes the following mathematical expression: Wherein, p and q are the vector to be located and the model vector respectively, both of which are n-dimensional vectors, k is the kth component of the vector to be located and the model vector, and d is the target Canberra distance.

4. The method according to claim 1, characterized in that: The step of inputting the image data into a pre-trained Canberra distance learning model to perform wildfire point location processing to obtain a wildfire point location result of the transmission line further includes: The image data is preprocessed to obtain preprocessed image data.

5. The method according to claim 4, characterized in that: The preprocessing of the image data to obtain preprocessed image data includes: The image data is denoised using a preset denoising algorithm to obtain denoised image data, wherein the denoising algorithm includes at least one of median filtering, Gaussian filtering and bilateral filtering, and the preprocessed image data includes the denoised image data.

6. The method according to claim 5, characterized in that: The preprocessing of the image data to obtain preprocessed image data further includes: The denoised image data is subjected to image enhancement processing using a preset image enhancement algorithm to obtain enhanced image data, wherein the image enhancement algorithm includes at least one of histogram equalization, adaptive histogram equalization and contrast enhancement, and the preprocessed image data includes the enhanced image data.

7. The method according to claim 6, characterized in that: The preprocessing of the image data to obtain preprocessed image data further includes: The enhanced image data is subjected to image segmentation processing using a preset image segmentation algorithm to obtain segmented image data, wherein the image segmentation algorithm includes at least one of threshold segmentation, edge segmentation, and region segmentation, and the preprocessed image data includes the segmented image data.

8. A device for locating mountain fire points on a power transmission line, characterized in that: The device comprises: Data acquisition module: used to obtain image data of the power transmission line, wherein the image data is used to reflect the current environment of the power transmission line; Positioning module: used to input the image data into a pre-trained Canberra distance learning model to perform wildfire point positioning processing, and obtain a wildfire point positioning result of the transmission line, wherein the wildfire point positioning result is used to reflect whether there is a wildfire point in the current environment of the transmission line, and the Canberra distance learning model is trained based on historical image data of several transmission lines with wildfire points; Prompt module: used for outputting a wildfire prompt when the wildfire point positioning result reflects that there is a wildfire point in the current environment of the transmission line. The wildfire prompt at least includes the geographical location information of the wildfire point and the fire information of the wildfire point.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

10. A computer device comprising a memory and a processor, characterized in that: The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 7.

Images