Power transmission line mountain fire ranging method and device, computer equipment and storage medium

Abstract

The application relates to a power transmission line mountain fire distance measuring method and device, computer equipment and a storage medium; wherein the distance measuring method comprises the following steps: acquiring a flame image of a mountain fire collected by an image collection device arranged on a power transmission line, and obtaining light source characteristics of the mountain fire according to the flame image; in the case that the light source characteristics do not satisfy preset conditions, acquiring a unit feature vector of the mountain fire in the flame image, unit feature vectors of each sample point and position information of each sample point; obtaining corresponding sample points according to the unit feature vectors of the sample points and the unit feature vector of the mountain fire; obtaining a first position of the mountain fire relative to the image collection device according to the position information of the corresponding sample points; and processing a world coordinate of the image collection device and the first position to obtain a distance between the mountain fire and the power transmission line. The method can detect the distance between the mountain fire and the power transmission line by only using the image collection device, has low cost, and the detection of the distance is not affected by the position change of the image collection device on the power transmission line, and has high accuracy.

Description

Technical Field

[0001] The present application relates to the field of power safety technology, and in particular to a method, device, computer equipment and storage medium for measuring distance between transmission line wildfires. Background Art

[0002] With the development of power technology, transmission lines are becoming increasingly complex. Wildfires in forested areas during hot and dry seasons can produce high-temperature gases and smoke that can easily cause phase-to-phase or ground-to-ground electric field distortion in nearby transmission lines, leading to power outages or tripping. This can seriously endanger the safe and stable operation of transmission lines and cause significant losses to the power system. Therefore, it is necessary to monitor the environment surrounding transmission lines to provide effective early warning of wildfires and take measures to prevent their spread.

[0003] Currently, there are two main methods for measuring the distance to wildfires around transmission lines. One involves using drones equipped with visible light or infrared cameras for inspections, followed by manual or computer-generated image or video recognition to determine wildfire hazard levels. The other involves installing visible light or infrared camera monitoring devices on transmission towers. This technology captures real-time images of the environment around the transmission lines around the clock, and uses ranging technology to determine the wildfire hazard level. However, drone inspections lack 24 / 7 real-time monitoring, making it difficult to provide timely and effective early warning of wildfires. The distance between tower-mounted cameras and the conductors leads to significant errors in fire location. Summary of the Invention

[0004] Based on this, it is necessary to provide a transmission line wildfire ranging method, device, computer equipment and storage medium that can timely and accurately measure the distance between the wildfire and the transmission line to address the above technical problems.

[0005] A method for measuring distance of wildfires on power transmission lines, comprising the steps of:

[0006] Obtaining a flame image of a wildfire captured by an image acquisition device, and obtaining light source characteristics of the wildfire based on the flame image; wherein the image acquisition device is located on a power transmission line;

[0007] When the light source characteristic does not satisfy the preset condition, obtaining a unit feature vector of the wildfire in the flame image;

[0008] Obtain the unit eigenvector of each sample point and the position information of each sample point;

[0009] According to the unit eigenvector of the sample point and the unit eigenvector of the wildfire, the corresponding sample point is obtained;

[0010] Obtaining a first position of the wildfire relative to the image acquisition device based on position information of the corresponding sample points;

[0011] The world coordinates of the image acquisition device are obtained, and the world coordinates and the first position are processed to obtain the distance between the wildfire and the transmission line.

[0012] In one embodiment, the step of obtaining corresponding sample points according to the unit eigenvector of the sample points and the unit eigenvector of the wildfire includes:

[0013] Calculate the Euclidean distance between the unit eigenvector of the sample point and the unit eigenvector of the wildfire;

[0014] The sample point with the smallest Euclidean distance is determined as the corresponding sample point.

[0015] In one embodiment, the light source characteristics include flicker frequency and brightness; when the light source characteristics do not meet preset conditions, the step of obtaining a unit feature vector of the wildfire in the flame image includes:

[0016] When the flickering frequency exceeds a preset value and the brightness exceeds a preset brightness, a unit feature vector of the wildfire in the flame image is obtained.

[0017] In one embodiment, the image acquisition device includes a first image acquisition device, a second image acquisition device, and a third image acquisition device; the step of obtaining a unit feature vector of a wildfire in a flame image includes:

[0018] Extracting a first eigenvector of a wildfire from a flame image captured by a first image capture device;

[0019] extracting a second eigenvector of the wildfire from the flame image captured by the second image capture device;

[0020] A third eigenvector of the wildfire is extracted from the flame image captured by the third image capture device.

[0021] The first eigenvector, the second eigenvector, and the third eigenvector are processed to obtain the unit eigenvector of the wildfire.

[0022] In one embodiment, the step of obtaining the unit feature vector of each sample point includes:

[0023] Select each sample point;

[0024] Acquire a sample point image of each sample point acquired by an image acquisition device, and extract a feature vector of the sample point in the sample point image;

[0025] The eigenvectors of the sample points are processed to obtain the unit eigenvector of each sample point.

[0026] In one embodiment, the step of obtaining a first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample points includes:

[0027] The triangulation positioning algorithm is used to process the position information of the corresponding sample points to obtain the first position.

[0028] In one embodiment, the step of processing the world coordinates and the first position to obtain the distance between the wildfire and the power line includes:

[0029] Get the camera coordinates of the image acquisition device;

[0030] Processing the world coordinates and camera coordinates of the image acquisition device to obtain the transformation matrix of the camera coordinate system and the world coordinate system; the transformation matrix includes the rotation matrix and the translation matrix;

[0031] Process the rotation matrix, translation matrix and first position to get the world coordinates of the wildfire;

[0032] Get the world coordinates of the transmission line;

[0033] Process the world coordinates of the power line and the world coordinates of the wildfire to obtain the distance between the wildfire and the power line.

[0034] In one embodiment, the step of obtaining the world coordinates of the image acquisition device includes:

[0035] The RTK module is used to locate the world coordinates of the image acquisition device.

[0036] A computer device includes a memory and a processor, wherein the memory stores a computer program and the processor implements the steps of the above method when executing the computer program.

[0037] A computer-readable storage medium stores a computer program, which implements the steps of the above method when executed by a processor.

[0038] The above-mentioned method for measuring distance from wildfires on power transmission lines obtains a flame image of a wildfire captured by an image acquisition device installed on the power transmission line, and obtains the light source characteristics of the wildfire based on the flame image; if the light source characteristics do not meet preset conditions, obtains the unit feature vector of the wildfire in the flame image; obtains the unit feature vector of each sample point and the position information of each sample point; obtains the corresponding sample point based on the unit feature vector of the sample point and the unit feature vector of the wildfire; obtains the first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample point; obtains the world coordinates of the image acquisition device, and processes the world coordinates and the first position to obtain the distance between the wildfire and the power transmission line. This method achieves the ability to detect the distance between the wildfire and the power transmission line using only the image acquisition device, is low-cost, and the distance detection is not affected by changes in the position of the image acquisition device on the power transmission line, resulting in high accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the conventional technology, the following briefly introduces the drawings required for use in the embodiments or the conventional technology descriptions. 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.

[0040] Figure 1 1 is a flow chart of a method for measuring distance from a wildfire on a transmission line in one embodiment;

[0041] Figure 2 A schematic diagram of the position of an image acquisition device in one embodiment;

[0042] Figure 3 FIG1 is a flow chart of steps for obtaining corresponding sample points according to the unit characteristic vector of the sample points and the unit characteristic vector of the wildfire in one embodiment;

[0043] Figure 4 A flowchart illustrating steps for obtaining a unit feature vector of a wildfire in a flame image in one embodiment;

[0044] Figure 5 Schematic diagram of a flow chart of the steps of obtaining the unit feature vector of each sample point in one embodiment;

[0045] Figure 6 FIG. 1 is a flow chart illustrating steps for processing world coordinates and a first position to obtain the distance between a wildfire and a power line in one embodiment. DETAILED DESCRIPTION

[0046] To facilitate understanding of the present application, the present application will be described more fully below with reference to the accompanying drawings. The accompanying drawings provide embodiments of the present application. However, the present application may be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided to make the disclosure of the present application more thorough and comprehensive.

[0047] 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 pertains. The terms used herein in the specification of this application are for the purpose of describing specific embodiments only and are not intended to limit this application.

[0048] With the development of my country's power industry and the implementation of the West-to-East Power Transmission Strategy, the safe operation of transmission lines is a crucial component in ensuring grid stability. However, in recent years, due to volatile climates and human factors, wildfires have frequently broken out in forested areas during hot and dry seasons. The resulting high-temperature gases and smoke can easily distort the electric field between phases or to the ground on nearby transmission lines, causing power outages and other accidents. This seriously compromises the safe and stable operation of transmission lines and causes significant losses to the power system. Therefore, it is necessary to monitor the environment surrounding transmission lines to provide effective early warning of wildfires and take measures to prevent their spread.

[0049] In view of this, the present invention proposes a method for measuring distance of wildfires on transmission lines, which can effectively solve the above problems.

[0050] In one embodiment, Figure 1 As shown, a method for measuring distance from a wildfire on a transmission line is provided, comprising the steps of:

[0051] S110, acquiring a flame image of a wildfire captured by an image acquisition device, and obtaining light source characteristics of the wildfire based on the flame image; wherein the image acquisition device is located on a power transmission line;

[0052] Specifically, if Figure 2 As shown, the image acquisition device 10 is a device with image acquisition capabilities, including a camera, camcorder, camera, and scanner. It is installed on a power transmission line and can capture real-time images of the environment surrounding the power transmission line around the clock. This image acquisition device enables real-time monitoring of wildfires and, when a wildfire occurs, accurately and promptly determines the distance from the power transmission line. Flame images can be acquired using any method known in the art. Optionally, the image acquisition device 10 can be assigned a fixed IP address, and computer software can access image data from the image acquisition device 10 via this IP address and a designated data communication port.

[0053] It should be noted that the light source characteristics are characteristic factors of flames that are different from the external environment, including color, brightness, flicker frequency, and temperature. After obtaining the flame image, the image can be processed using any method in this field to obtain the light source characteristics of the wildfire. Optionally, the light source characteristics in the flame image can be extracted by feature extraction. Feature extraction is to extract useful data or information from the image to obtain a "non-image" representation or description of the image, such as numerical values, vectors, and symbols, and the extracted "non-image" representation or description is the feature. With the "non-image" representation or description features, the BP neural network can be trained to intelligently identify the light source characteristics in the flame image.

[0054] S120, when the light source characteristic does not satisfy the preset condition, obtaining a unit feature vector of the wildfire in the flame image;

[0055] Specifically, light source characteristics include color, brightness, and flicker frequency. Preset conditions are thresholds for flame light source characteristics. Optionally, the RGB color thresholds are 255, 255, and 0; the brightness threshold is 2 candela; and the flicker frequency threshold is 1 Hz. By setting preset conditions for wildfire light sources, the severity of wildfires can be distinguished, and distance measurement is performed only when the severity exceeds the preset level.

[0056] Specifically, the steps for obtaining the unit feature vector of a wildfire in a flame image are:

[0057] Any method in the art can be used to extract the feature vector of a wildfire in a flame image at a certain moment; when there are multiple image acquisition devices, the unit feature vector is calculated based on the following formula:

[0058]

[0059] Among them, Δλ1, λ2, λ3, and λ4 are the feature vectors of wildfire in the flame images collected by four different image acquisition devices, and L is the unit feature vector of wildfire.

[0060] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0061] S130, obtaining the unit feature vector of each sample point and the position information of each sample point;

[0062] Specifically, the sample points are points where light source characteristics of flames of different degrees are simulated. At each sample point, an adjustable custom light source is placed to simulate light source characteristics of flames of different degrees. Optionally, the light source characteristics include flicker frequency and brightness.

[0063] The location information of each sample point refers to its coordinates relative to the image acquisition device. Specifically, before the image acquisition device is fully operational, sample points are evenly selected around the power transmission line sensor, and their location information is recorded. To ensure accurate simulation of the wildfire location, n sample points are evenly selected on the ground within 200 meters of the power transmission line, and their location information is recorded.

[0064] Optionally, the unit eigenvector of each sample point is obtained based on the following formula:

[0065]

[0066] Among them, K j represents the unit eigenvector of the flame simulated at the jth sample point, where j = 1, 2, ..., n; Δλ 1j ,Δλ 2j ,Δλ 3jare the feature vectors of the flame simulated at the jth sample point captured by the three image acquisition devices.

[0067] S140, obtaining corresponding sample points based on the unit eigenvector of the sample point and the unit eigenvector of the wildfire;

[0068] Specifically, on the one hand, the Euclidean distance between the unit eigenvector of the wildfire and the unit eigenvector of the flame simulated at each sample point can be calculated, and the point with the smallest Euclidean distance can be determined as the corresponding sample point. Specifically, the unit eigenvector L of the wildfire and the unit eigenvector K of the flame simulated at the jth sample point can be calculated based on the following formula: j The Euclidean distance d between j :

[0069]

[0070] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0071] On the other hand, the unit feature vector of the wildfire can be imported into the convolutional neural network for training, and then the unit feature vector of the simulated flame at each sample point can be input into the trained neural network model for recognition, and the sample point with a true recognition result can be determined as the corresponding sample point.

[0072] S150, obtaining a first position of the wildfire relative to the image acquisition device based on position information of the corresponding sample point;

[0073] Specifically, the position information of the corresponding sample points refers to the position coordinates of the corresponding sample points relative to the image acquisition device. On the one hand, the position coordinates of the corresponding sample points relative to the image acquisition device can be directly determined as the first position of the wildfire relative to the image acquisition device; on the other hand, three corresponding sample points can be selected, M A (x A ,y A ,z A ), M B (x B ,y B ,z B ) and M C (x C ,y C ,z C ), using the triangulation algorithm, the first position (x, y, z) of the wildfire relative to the image acquisition device is obtained based on the following formula:

[0074]

[0075]

[0076]

[0077] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0078] S160 , obtaining the world coordinates of the image acquisition device, and processing the world coordinates and the first position to obtain the distance between the wildfire and the transmission line.

[0079] Specifically, the world coordinates of the image acquisition device can be obtained using any method known in the art. For example, the world coordinates of the image acquisition device can be located using a Beidou module, an RTK module, or a combination of the two. The first position of the wildfire refers to the position of the wildfire relative to the image acquisition device.

[0080] Specifically, when the world coordinates of the image acquisition device are known, an arbitrary mathematical formula is used to convert the position coordinates of the wildfire relative to the image acquisition device into the world coordinates of the wildfire; an arbitrary mathematical formula is used, and optionally, a distance calculation formula is used to process the world coordinates of the wildfire and the world coordinates of the power transmission line to obtain the distance between the wildfire and the power transmission line.

[0081] The above-mentioned method for measuring distance from wildfires on power transmission lines obtains a flame image of a wildfire captured by an image acquisition device installed on the power transmission line, and obtains the light source characteristics of the wildfire based on the flame image; if the light source characteristics do not meet preset conditions, obtains the unit feature vector of the wildfire in the flame image; obtains the unit feature vector of each sample point and the position information of each sample point; obtains the corresponding sample point based on the unit feature vector of the sample point and the unit feature vector of the wildfire; obtains the first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample point; obtains the world coordinates of the image acquisition device, and processes the world coordinates and the first position to obtain the distance between the wildfire and the power transmission line. This method achieves the ability to detect the distance between the wildfire and the power transmission line using only the image acquisition device, is low-cost, and the distance detection is not affected by changes in the position of the image acquisition device on the power transmission line, resulting in high accuracy.

[0082] In one embodiment, Figure 3 As shown, the steps of obtaining the corresponding sample points according to the unit eigenvector of the sample points and the unit eigenvector of the wildfire include:

[0083] S170, calculating the Euclidean distance between the unit eigenvector of the sample point and the unit eigenvector of the wildfire;

[0084] Specifically, Euclidean distance is used to characterize the similarity between vectors. In machine learning, vectors are usually used to represent each sample, and calculating the similarity of vectors can measure the difference between sample vectors. Specifically, the unit feature vector L of the wildfire and the unit feature vector K of the simulated flame at the jth sample point can be calculated based on the following formula: j The Euclidean distance d between j :

[0085]

[0086] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0087] S180: Determine the sample point with the smallest Euclidean distance as the corresponding sample point.

[0088] Specifically, the similarity of vectors is calculated using Euclidean distance, with smaller Euclidean distances indicating greater similarity. The sample point with the smallest Euclidean distance is selected as the corresponding sample point, accurately simulating the location of wildfires in real-world environments.

[0089] It is important to note that due to the different environments around transmission lines, the weights of each sample point can be set based on the density of combustibles. For example, sample points in areas with high combustible density can have large weights, while sample points in areas with low combustible density can have small weights.

[0090] In one embodiment, the light source characteristics include flicker frequency and brightness; when the light source characteristics do not meet preset conditions, the step of obtaining a unit feature vector of a wildfire in a flame image includes:

[0091] When the flickering frequency exceeds a preset value and the brightness exceeds a preset brightness, a unit feature vector of the wildfire in the flame image is obtained.

[0092] Specifically, the preset conditions are thresholds of flame light source characteristics. Optionally, the RGB color threshold is 255, 255, 0; the brightness threshold is 2 candela; and the flicker frequency threshold is 1 Hz.

[0093] Specifically, any method in the art can be used to extract the feature vector of a wildfire in a flame image at a certain moment; when there are multiple image acquisition devices, the unit feature vector is calculated based on the following formula:

[0094]

[0095] Among them, Δλ1, Δλ2, Δλ3, and Δλ4 are the feature vectors of wildfire in flame images captured by four different image acquisition devices, and L is the unit feature vector of wildfire.

[0096] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0097] In one embodiment, Figure 4 As shown, the image acquisition device includes a first image acquisition device, a second image acquisition device, and a third image acquisition device; the step of obtaining a unit feature vector of a wildfire in a flame image includes:

[0098] S200, extracting a first feature vector of a wildfire from a flame image captured by a first image capture device;

[0099] S210, extracting a second feature vector of the wildfire from the flame image captured by the second image capture device;

[0100] S220 , extracting a third eigenvector of the wildfire from the flame image captured by the third image capture device.

[0101] S230 , processing the first eigenvector, the second eigenvector, and the third eigenvector to obtain a unit eigenvector of the wildfire.

[0102] Specifically, any method known in the art can be used to extract the first, second, and third eigenvectors of a wildfire from a flame image, such as Fourier transform, windowed Fourier transform, wavelet transform, least squares method, and boundary direction histogram method. When there are three image acquisition devices, the unit eigenvector can be calculated based on the following formula:

[0103]

[0104] Among them, Δλ1, Δλ2, and Δλ3 are the feature vectors of wildfire in flame images captured by three different image acquisition devices, and L is the unit feature vector of wildfire.

[0105] In one embodiment, Figure 5 As shown in FIG, the steps of obtaining the unit eigenvector of each sample point include:

[0106] S240, selecting each sample point;

[0107] Specifically, before the image acquisition equipment was officially put into operation, sample points were evenly selected around the power transmission line sensor and their location information was recorded. To ensure a more accurate simulation of the wildfire location, n sample points were evenly selected on the ground within 200 meters of the power transmission line.

[0108] S250, acquiring a sample point image of each sample point acquired by an image acquisition device, and extracting a feature vector of the sample point in the sample point image;

[0109] Specifically, an adjustable custom light source is placed at each sample point to simulate light source characteristics of different flames. Optionally, the light source characteristics include flicker frequency and brightness. Specifically, any method in the art can be used to extract the feature vector of the sample point.

[0110] S260, processing the eigenvectors of the sample points to obtain the unit eigenvector of each sample point.

[0111] Specifically, the eigenvectors of the sample points can be processed based on the following formula to obtain the unit eigenvector of each sample point:

[0112]

[0113] Among them, K j represents the unit eigenvector of the flame simulated at the jth sample point, where j = 1, 2, ..., n; Δλ 1j ,Δλ 2j ,Δλ 3j are the feature vectors of the flame simulated at the jth sample point captured by the three image acquisition devices.

[0114] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0115] In one embodiment, the step of obtaining a first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample points includes:

[0116] The triangulation positioning algorithm is used to process the position information of the corresponding sample points to obtain the first position.

[0117] Specifically, three corresponding sample points M are selected A (x A ,y A ,z A ), M B (x B ,y B ,z B ) and M C (x C ,y C ,z C ), using the triangulation algorithm, the first position (x, y, z) of the wildfire relative to the image acquisition device is obtained based on the following formula:

[0118]

[0119]

[0120]

[0121] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0122] In one embodiment, Figure 6 As shown, the steps of processing the world coordinates and the first position to obtain the distance between the wildfire and the transmission line include:

[0123] S280, obtaining the camera coordinates of the image acquisition device;

[0124] Specifically, any method in the art can be used to obtain the camera coordinates of the image acquisition device; camera coordinates refer to coordinates in the camera coordinate system. The camera coordinate system is a coordinate system closely related to the observer. In the camera coordinate system, the camera is at the origin, the x-axis points to the right, the z-axis points forward (toward the screen or the direction of the camera), and the y-axis points upward (not above the world but above the camera itself). Establishing a camera coordinate system is a commonly used method in the monitoring field. Here, the camera coordinate system is a coordinate system established with the image acquisition device as the origin.

[0125] S290, processing the world coordinates and camera coordinates of the image acquisition device to obtain a transformation matrix between the camera coordinate system and the world coordinate system; the transformation matrix includes a rotation matrix and a translation matrix;

[0126] Specifically, since the image acquisition device is installed on the transmission line, the vibration and sag changes of the transmission line cause the position of the image acquisition device to change, so it is necessary to establish a world coordinate system to calculate the distance from the wildfire to the transmission line.

[0127] Specifically, given the world coordinates (x w ,y w ,z w ) and camera coordinates (x c ,y c ,z c ), the rotation matrix R and translation matrix T are obtained based on the following formula:

[0128]

[0129] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0130] S300, processing the rotation matrix, the translation matrix and the first position to obtain the world coordinates of the wildfire;

[0131] Specifically, when the rotation matrix R and the translation matrix T are known, and the first position (x, y, z) of the wildfire relative to the image acquisition device is obtained, the world coordinates (x 1w ,y1w ,z 1w ):

[0132]

[0133] It should be noted that not only the above formula but also variations of the above formula should be included in the protection scope of this application.

[0134] S310, obtaining the world coordinates of the transmission line;

[0135] S320 , processing the world coordinates of the transmission line and the world coordinates of the wildfire to obtain the distance between the wildfire and the transmission line.

[0136] Specifically, any method in the art can be used to obtain the world coordinates of the transmission line; the world coordinates of the wildfire and the world coordinates of the transmission line are calculated using a distance formula to obtain the distance between the wildfire and the transmission line.

[0137] In one embodiment, the step of obtaining the world coordinates of the image acquisition device includes:

[0138] The RTK module is used to locate the world coordinates of the image acquisition device.

[0139] Specifically, the RTK module is a module that includes RTK technology and NRTK technology.

[0140] It should be understood that although Figures 1-5 The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. In addition, Figures 1-5 At least part of the steps may include multiple steps or multiple stages. These steps or stages are not necessarily performed at the same time, but can be performed at different times. The order of execution of these steps or stages is not necessarily one by one, but can be performed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0141] In one embodiment, a wildfire ranging device is provided, comprising:

[0142] An image acquisition module, configured to acquire a flame image of a wildfire captured by an image acquisition device, and to obtain light source characteristics of the wildfire based on the flame image; wherein the image acquisition device is located on the power transmission line;

[0143] A unit feature vector extraction module for wildfires, used to obtain the unit feature vector of wildfires in flame images when the light source characteristics do not meet the preset conditions;

[0144] The sample point information acquisition module is used to obtain the unit feature vector of each sample point and the position information of each sample point;

[0145] A corresponding sample point acquisition module is used to obtain corresponding sample points according to the unit characteristic vector of the sample point and the unit characteristic vector of the wildfire;

[0146] A first position determination module is configured to obtain a first position of the wildfire relative to the image acquisition device based on position information of corresponding sample points;

[0147] The distance calculation module is used to obtain the world coordinates of the image acquisition device and process the world coordinates and the first position to obtain the distance between the wildfire and the transmission line.

[0148] In one embodiment, the corresponding sample point acquisition module includes:

[0149] The Euclidean distance calculation module is used to calculate the Euclidean distance between the unit eigenvector of the sample point and the unit eigenvector of the wildfire;

[0150] The corresponding sample point determination module is used to determine the sample point with the smallest Euclidean distance as the corresponding sample point.

[0151] In one embodiment, the light source characteristics include flicker frequency and brightness; the wildfire unit feature vector extraction module includes:

[0152] The light source characteristic judgment module is used to obtain the unit feature vector of the wildfire in the flame image when the flicker frequency exceeds a preset value and the brightness exceeds a preset brightness.

[0153] In one embodiment, the image acquisition device includes a first image acquisition device, a second image acquisition device, and a third image acquisition device; and the wildfire unit feature vector extraction module includes:

[0154] a first feature vector extraction module for a wildfire, configured to extract a first feature vector of a wildfire from a flame image captured by a first image capture device;

[0155] A second eigenvector of the wildfire, used to extract the second eigenvector of the wildfire in the flame image captured by the second image capture device;

[0156] The third eigenvector of the wildfire is used to extract the third eigenvector of the wildfire from the flame image captured by the third image capture device.

[0157] The wildfire eigenvector processing module is used to process the first eigenvector, the second eigenvector and the third eigenvector to obtain the unit eigenvector of the wildfire.

[0158] In one embodiment, the sample point information acquisition module includes:

[0159] Sample point selection module, used to select each sample point;

[0160] A sample point feature vector extraction module is used to obtain a sample point image of each sample point acquired by an image acquisition device and extract a feature vector of the sample point in the sample point image;

[0161] The feature vector processing module of the sample points is used to process the feature vectors of the sample points to obtain the unit feature vectors of each sample point.

[0162] In one embodiment, the first location determination module includes:

[0163] The triangulation positioning algorithm module is used to process the position information of the corresponding sample points using a triangulation positioning algorithm to obtain a first position.

[0164] In one embodiment, the distance calculation module includes:

[0165] A camera coordinate acquisition module is used to obtain the camera coordinates of the image acquisition device;

[0166] A matrix calculation module is used to process the world coordinates and camera coordinates of the image acquisition device to obtain the transformation matrix of the camera coordinate system and the world coordinate system; the transformation matrix includes a rotation matrix and a translation matrix;

[0167] The world coordinate calculation module of the wildfire is used to process the rotation matrix, translation matrix and the first position to obtain the world coordinates of the wildfire;

[0168] A transmission line world coordinate acquisition module, used to obtain the world coordinates of the transmission line;

[0169] The coordinate distance calculation module is used to process the world coordinates of the transmission line and the world coordinates of the wildfire to obtain the distance between the wildfire and the transmission line.

[0170] In one embodiment, the distance calculation module further includes:

[0171] The positioning module is used to locate the world coordinates of the image acquisition device using the RTK module.

[0172] For the specific limitations of the wildfire ranging device, please refer to the limitations of the transmission line wildfire ranging method above, which will not be repeated here. The various modules in the above-mentioned wildfire ranging device can be implemented in whole or in part by 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.

[0173] In one embodiment, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the following steps when executing the computer program:

[0174] obtaining a flame image of a wildfire collected by an image collection device, and obtaining a light source characteristic of the wildfire according to the flame image; wherein the image collection device is arranged on a power transmission line;

[0175] in a case where the light source characteristic does not satisfy a preset condition, obtaining a unit feature vector of the wildfire in the flame image;

[0176] obtaining the unit feature vector of each sample point and position information of each sample point;

[0177] obtaining a corresponding sample point according to the unit feature vector of the sample point and the unit feature vector of the wildfire;

[0178] obtaining a first position of the wildfire relative to the image collection device according to the position information of the corresponding sample point;

[0179] obtaining a world coordinate of the image collection device, and processing the world coordinate and the first position to obtain a distance between the wildfire and the power transmission line.

[0180] In one embodiment, the processor further implements the following steps when executing the computer program:

[0181] calculating an Euclidean distance between the unit feature vector of the sample point and the unit feature vector of the wildfire;

[0182] determining the sample point with the minimum Euclidean distance as the corresponding sample point.

[0183] In one embodiment, the processor further implements the following steps when executing the computer program:

[0184] in a case where the flicker frequency exceeds a preset value and the brightness exceeds a preset brightness, obtaining the unit feature vector of the wildfire in the flame image.

[0185] In one embodiment, the image collection device comprises a first image collection device, a second image collection device and a third image collection device; and the processor further implements the following steps when executing the computer program:

[0186] extracting a first feature vector of the wildfire in the flame image collected by the first image collection device;

[0187] extracting a second feature vector of the wildfire in the flame image collected by the second image collection device;

[0188] extracting a third feature vector of the wildfire in the flame image collected by the third image collection device.

[0189] The first eigenvector, the second eigenvector, and the third eigenvector are processed to obtain the unit eigenvector of the wildfire.

[0190] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0191] Select each sample point;

[0192] Acquire a sample point image of each sample point acquired by an image acquisition device, and extract a feature vector of the sample point in the sample point image;

[0193] The eigenvectors of the sample points are processed to obtain the unit eigenvector of each sample point.

[0194] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0195] The triangulation positioning algorithm is used to process the position information of the corresponding sample points to obtain the first position.

[0196] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0197] Get the camera coordinates of the image acquisition device;

[0198] Processing the world coordinates and camera coordinates of the image acquisition device to obtain the transformation matrix of the camera coordinate system and the world coordinate system; the transformation matrix includes the rotation matrix and the translation matrix;

[0199] Process the rotation matrix, translation matrix and first position to get the world coordinates of the wildfire;

[0200] Get the world coordinates of the transmission line;

[0201] Process the world coordinates of the power line and the world coordinates of the wildfire to obtain the distance between the wildfire and the power line.

[0202] In one embodiment, when the processor executes the computer program, the processor further implements the following steps:

[0203] The RTK module is used to locate the world coordinates of the image acquisition device.

[0204] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0205] Obtaining a flame image of a wildfire captured by an image acquisition device, and obtaining light source characteristics of the wildfire based on the flame image; wherein the image acquisition device is located on a power transmission line;

[0206] When the light source characteristic does not satisfy the preset condition, obtaining a unit feature vector of the wildfire in the flame image;

[0207] Obtain the unit eigenvector of each sample point and the position information of each sample point;

[0208] According to the unit eigenvector of the sample point and the unit eigenvector of the wildfire, the corresponding sample point is obtained;

[0209] Obtaining a first position of the wildfire relative to the image acquisition device based on position information of the corresponding sample points;

[0210] The world coordinates of the image acquisition device are obtained, and the world coordinates and the first position are processed to obtain the distance between the wildfire and the transmission line.

[0211] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0212] Calculate the Euclidean distance between the unit eigenvector of the sample point and the unit eigenvector of the wildfire;

[0213] The sample point with the smallest Euclidean distance is determined as the corresponding sample point.

[0214] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0215] When the flickering frequency exceeds a preset value and the brightness exceeds a preset brightness, a unit feature vector of the wildfire in the flame image is obtained.

[0216] In one embodiment, the image acquisition device includes a first image acquisition device, a second image acquisition device, and a third image acquisition device; when the computer program is executed by a processor, the computer program further implements the following steps:

[0217] Extracting a first eigenvector of a wildfire from a flame image captured by a first image capture device;

[0218] extracting a second eigenvector of the wildfire from the flame image captured by the second image capture device;

[0219] A third eigenvector of the wildfire is extracted from the flame image captured by the third image capture device.

[0220] The first eigenvector, the second eigenvector, and the third eigenvector are processed to obtain the unit eigenvector of the wildfire.

[0221] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0222] Select each sample point;

[0223] Acquire a sample point image of each sample point acquired by an image acquisition device, and extract a feature vector of the sample point in the sample point image;

[0224] The eigenvectors of the sample points are processed to obtain the unit eigenvector of each sample point.

[0225] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0226] The triangulation positioning algorithm is used to process the position information of the corresponding sample points to obtain the first position.

[0227] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0228] Get the camera coordinates of the image acquisition device;

[0229] Processing the world coordinates and camera coordinates of the image acquisition device to obtain the transformation matrix of the camera coordinate system and the world coordinate system; the transformation matrix includes the rotation matrix and the translation matrix;

[0230] Process the rotation matrix, translation matrix and first position to get the world coordinates of the wildfire;

[0231] Get the world coordinates of the transmission line;

[0232] Process the world coordinates of the power line and the world coordinates of the wildfire to obtain the distance between the wildfire and the power line.

[0233] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented:

[0234] The RTK module is used to locate the world coordinates of the image acquisition device.

[0235] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiment methods can be implemented 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 may include at least one of non-volatile and volatile memory. Non-volatile memory may include read-only memory (ROM), magnetic tape, floppy disk, flash memory or optical memory, etc. Volatile memory may 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).

[0236] Throughout this specification, references to terms such as "some embodiments," "other embodiments," and "desired embodiments" indicate that a particular feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. Although these terms are used interchangeably throughout this specification, they do not necessarily refer to the same embodiment or example.

[0237] The technical features of the above embodiments can 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.

[0238] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for measuring distance from wildfires on power transmission lines, characterized in that: Including steps: Obtaining a flame image of a wildfire captured by an image acquisition device, and obtaining light source characteristics of the wildfire based on the flame image; wherein the image acquisition device is located on a power transmission line; the image acquisition device includes a first image acquisition device, a second image acquisition device, and a third image acquisition device; When the light source characteristics do not meet the preset conditions, obtaining a unit feature vector of the wildfire in the flame image; the light source characteristics include flicker frequency and brightness; Obtaining the unit feature vector of each sample point and the position information of each sample point; Obtaining corresponding sample points according to the unit eigenvector of the sample point and the unit eigenvector of the wildfire; Obtaining a first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample points; Obtaining the world coordinates of the image acquisition device, and processing the world coordinates and the first position to obtain the distance between the wildfire and the transmission line; The step of obtaining the unit feature vector of the wildfire in the flame image when the light source characteristic does not satisfy the preset condition includes: When the flickering frequency exceeds a preset value and the brightness exceeds a preset brightness, obtaining a unit feature vector of the wildfire in the flame image; The step of obtaining the unit feature vector of the wildfire in the flame image includes: extracting a first feature vector of a wildfire from the flame image captured by the first image capture device; extracting a second eigenvector of the wildfire from the flame image captured by the second image capture device; extracting a third eigenvector of the wildfire from the flame image captured by the third image capture device; Processing the first eigenvector, the second eigenvector, and the third eigenvector to obtain a unit eigenvector of the wildfire; The step of obtaining a first position of the wildfire relative to the image acquisition device based on the position information of the corresponding sample points includes: Processing the position information of the corresponding sample points using a triangulation positioning algorithm to obtain the first position; The step of obtaining the world coordinates of the image acquisition device includes: The RTK module is used to locate the world coordinates of the image acquisition device.

2. The method for measuring distance of a wildfire on a power transmission line according to claim 1, characterized in that: The step of obtaining corresponding sample points according to the unit eigenvector of the sample points and the unit eigenvector of the wildfire includes: Calculating the Euclidean distance between the unit eigenvector of the sample point and the unit eigenvector of the wildfire; The sample point with the smallest Euclidean distance is determined as the corresponding sample point.

3. The method for measuring distance of wildfires on power transmission lines according to claim 1, characterized in that: The step of obtaining the unit feature vector of each sample point includes: Select each sample point; Acquire a sample point image of each of the sample points acquired by the image acquisition device, and extract a feature vector of the sample point in the sample point image; The eigenvectors of the sample points are processed to obtain a unit eigenvector of each of the sample points.

4. The method for measuring distance of a wildfire on a transmission line according to claim 1, wherein: The step of processing the world coordinates and the first position to obtain the distance between the wildfire and the transmission line includes: Obtaining the camera coordinates of the image acquisition device; Processing the world coordinates of the image acquisition device and the camera coordinates to obtain a transformation matrix between the camera coordinate system and the world coordinate system; the transformation matrix includes a rotation matrix and a translation matrix; Processing the rotation matrix, the translation matrix, and the first position to obtain the world coordinates of the wildfire; Obtaining the world coordinates of the transmission line; The world coordinates of the transmission line and the world coordinates of the wildfire are processed to obtain a distance between the wildfire and the transmission line.

5. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 4 are implemented.

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

Images