Power transmission line detection method based on unmanned aerial vehicle

By obtaining weather information and adjusting the drone inspection mode and route, and identifying transmission lines with semantic segmentation model, the problem of poor drone detection results in special weather is solved, and efficient detection of transmission lines is achieved.

CN118968349APending Publication Date: 2024-11-15GUANGDONG POWER GRID CO LTD +1
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410963780.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-18
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

In special weather, it is difficult for existing drone automatic flight systems to effectively detect the power transmission line breakage, resulting in poor detection results, which may lead to lag in maintenance.

Method used

By obtaining the weather information of the area where the transmission line belongs, the target patrol mode and route of the drone are determined, and the image denoising parameters are adjusted according to the brightness value and amplitude value, the target transmission line information is identified using a pre-trained semantic segmentation model to generate Warning information.

Benefits of technology

In extreme environments, it can effectively detect breakage of transmission lines, which improves the accuracy and timeliness of detection and solves the problem of detection lag.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118968349A_ABST
    Figure CN118968349A_ABST
Patent Text Reader

Abstract

The invention discloses a power transmission line detection method based on an unmanned aerial vehicle, and the method comprises the steps: obtaining the weather information of an area where a power transmission line belongs under the condition of detecting that the power transmission line is broken; determining a target inspection route of the unmanned aerial vehicle under the condition that the target inspection mode of the unmanned aerial vehicle is determined to be a preset inspection mode based on the weather information; in the process of routing inspection of the unmanned aerial vehicle based on the target routing inspection route, according to the brightness value and the rotation amplitude value acquired by the unmanned aerial vehicle at each moment, determining a denoising parameter of the to-be-processed image acquired by the unmanned aerial vehicle at the corresponding moment; determining target power transmission line information based on a disturbance parameter and an illumination parameter in the de-noising parameters; and when the target power transmission line information satisfies a preset condition, generating early warning information based on the to-be-processed image and / or the target image. According to the technical scheme provided by the embodiment of the invention, the detection accuracy and efficiency of the power transmission line in special weather are realized.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of data processing technology, and in particular to a transmission line detection method based on an unmanned aerial vehicle. Background Art

[0002] Usually, drones are equipped with an automatic flight system. This automatic flight system supports the drone to realize functions such as autonomous inspection, automatic return, automatic energy replenishment, intelligent data collection and analysis, etc. Furthermore, the automatic flight system reduces the difficulty of user operation and the risk caused by mistakes, so drones can be used in the power inspection process.

[0003] Usually, in special weather conditions, such as typhoons and severe convective weather, power transmission lines are easily scratched by broken branches, causing the power transmission lines to break. When a power transmission line breaks, electrical information is usually used to determine the approximate break location, and then a drone is dispatched to the break location to determine the accident site, so that technicians can determine the maintenance strategy based on the accident site information.

[0004] However, the automatic flight system of drones is mostly configured based on parameters of non-special weather conditions. Therefore, when drones are used to inspect power lines in special weather conditions, the inspection effect is poor. Summary of the invention

[0005] The present invention provides a power transmission line detection method based on a drone, so as to realize the detection of the power transmission line under special weather conditions, thereby facilitating the effect of users.

[0006] In a first aspect, an embodiment of the present invention provides a transmission line detection method based on a drone, the method comprising:

[0007] When a transmission line is detected to be broken, obtaining weather information of the area to which the transmission line belongs;

[0008] When it is determined that the target inspection mode of the drone is a preset inspection mode based on the weather information, determining a target inspection route of the drone;

[0009] In the process of the drone inspecting the target inspection route, according to the brightness value and the rotation amplitude value collected by the drone at each moment, the denoising parameters of the image to be processed collected by the drone at the corresponding moment are determined; wherein the denoising parameters are determined based on the illumination parameters corresponding to the brightness value and the disturbance parameters corresponding to the rotation amplitude value;

[0010] Based on the disturbance parameter in the denoising parameter and the illumination parameter, determining a target image corresponding to the image to be processed, and based on a pre-trained semantic segmentation model, determining target power transmission line information in the target image;

[0011] When the target power transmission line information meets a preset condition, early warning information is generated based on the image to be processed and / or the target image.

[0012] In a second aspect, an embodiment of the present invention further provides a transmission line detection method and device based on a drone, the device comprising:

[0013] A weather information acquisition module, used to acquire weather information of the area to which the transmission line belongs when a transmission line is detected to be broken;

[0014] An inspection route determination module is used to determine a target inspection route of the drone when it is determined that the target inspection mode of the drone is a preset inspection mode based on the weather information;

[0015] A parameter determination module, used to determine the denoising parameters of the to-be-processed image collected by the drone at the corresponding moment in the process of the drone inspecting the target inspection route based on the brightness value and the rotation amplitude value collected by the drone at each moment; wherein the denoising parameters are determined based on the illumination parameters corresponding to the brightness value and the disturbance parameters corresponding to the rotation amplitude value;

[0016] A power transmission line information determination module, used to determine a target image corresponding to the image to be processed based on the disturbance parameter in the denoising parameter and the illumination parameter, and determine target power transmission line information in the target image based on a pre-trained semantic segmentation model;

[0017] The warning information generating module is used to generate warning information based on the image to be processed and / or the target image when the target transmission line information meets a preset condition.

[0018] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0019] one or more processors;

[0020] a storage device for storing one or more programs,

[0021] When the one or more programs are executed by the one or more processors, the one or more processors implement the UAV-based power transmission line detection method as described in any one of the embodiments of the present invention.

[0022] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute a UAV-based power transmission line detection method as described in any one of the embodiments of the present invention.

[0023] The technical solution provided by the embodiment of the present invention can obtain weather information of the area to which the transmission line belongs when a transmission line is detected to be broken. By analyzing and processing the weather information, when it is determined that the target inspection mode of the drone is the preset inspection mode, the target inspection route of the drone can be determined. The drone is controlled to inspect along the target inspection route based on the target inspection mode. During the inspection process, the denoising parameters for processing the image to be processed collected at the current moment can be determined according to the brightness value and the amplitude value collected by the drone, and the target image can be obtained after the image to be processed is processed according to the denoising parameters. Next, after analyzing and processing the target image through the semantic segmentation model, the pixel points corresponding to the transmission line can be determined, that is, the target transmission line information is obtained. If the target transmission line information meets the preset conditions, early warning information can be generated based on the image to be processed and / or the target image, and the early warning information can be fed back to the target platform, so that the user corresponding to the target platform can confirm the specific break position and the environmental information of the broken transmission line, so as to achieve the effect of detecting the transmission line in an extreme environment, and solve the problem that the transmission line cannot be effectively detected in an extreme environment in the prior art, resulting in the hysteresis of the transmission line detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required to describe the embodiments. Obviously, the drawings introduced are only drawings of a part of the embodiments to be described in the present invention, rather than all the drawings. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0025] Figure 1 A schematic diagram of a power transmission line detection method based on a drone provided in an embodiment of the present invention;

[0026] Figure 2 A schematic diagram of a power transmission line detection method based on a drone provided in an embodiment of the present invention;

[0027] Figure 3 A schematic diagram of a power transmission line detection method based on a drone provided in an embodiment of the present invention;

[0028] Figure 4 A schematic diagram of a power transmission line detection method based on a drone provided in an embodiment of the present invention;

[0029] Figure 5 A schematic diagram of the structure of a transmission line detection device based on a drone provided in an embodiment of the present invention;

[0030] Figure 6 The present invention is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0032] Figure 1 A flow chart of a UAV-based power transmission line detection method provided in an embodiment of the present invention is provided. This embodiment is applicable to situations where power transmission lines are detected under special weather conditions. The method can be performed by a UAV-based power transmission line detection device, which can be implemented in the form of software and / or hardware. The hardware can be an electronic device, and the electronic device includes a mobile terminal or a PC.

[0033] like Figure 1 The method of this embodiment includes:

[0034] S110. When a break in a power transmission line is detected, obtain weather information of an area to which the power transmission line belongs.

[0035] Among them, each transmission line in the power system can be detected in real time or periodically based on the Geographic Information System (GIS) to determine whether the transmission line is broken. For example, the electrical quantity of each transmission line can be collected, and the electrical quantity includes parameters such as current, voltage, impedance, etc. The above electrical quantities are analyzed and processed based on any existing detection algorithm to determine whether the transmission line is broken and the location information of the break.

[0036] When it is determined based on the detection results that a transmission line is broken, the broken transmission line can be inspected using a drone to obtain on-site information corresponding to the location of the broken transmission line, and then a maintenance strategy for the transmission line can be determined.

[0037] Usually, the automatic flight system in the drone is configured with parameters based on non-special weather. For special weather, when the automatic flight system is used to handle it, there is a problem of poor processing effect. Therefore, the weather information of the area where the transmission line is broken can be obtained first, so that the automatic flight system configured in the drone can use a strategy that is compatible with the weather information for data processing.

[0038] Optionally, the weather information includes at least one of temperature, humidity, light intensity, rainfall, snowfall and wind speed.

[0039] It can be understood that the electrical quantity of each transmission line can be collected based on the GIS system, and the electrical quantity can be analyzed and processed to determine whether each transmission line is broken and the location of the break. When a transmission line is detected to be broken, at least one of the information such as temperature, humidity, light intensity, rainfall, snowfall and wind speed of the area where the transmission line is broken is obtained to determine the inspection mode of the drone based on the weather information.

[0040] In this embodiment, when a transmission line is detected to be broken, weather information of the area to which the transmission line belongs is obtained, including: for each transmission line, the electrical quantity of the transmission line is obtained; if the electrical quantity does not meet the preset power consumption conditions, it is determined that the transmission line is broken; and the weather information of the area to which the transmission line belongs is retrieved.

[0041] The preset power conditions include the amount of electricity corresponding to each transmission line when it is working properly. When the collected amount of electricity of the transmission line does not meet the amount of electricity required for the normal operation of the transmission line, it can be determined that the transmission line is broken. In this case, the broken position of the broken line can be preliminarily determined, and the weather information of the area to which the broken position belongs can be retrieved.

[0042] It should be noted that the processing method for each transmission line is the same, and one of the transmission lines is taken as an example for explanation.

[0043] S120: When the target inspection mode of the drone is determined to be a preset inspection mode based on weather information, determine a target inspection route of the drone.

[0044] The preset inspection mode may be a pre-set extreme inspection mode adapted to special weather. That is, the weather information may be analyzed and processed to determine the target inspection mode of the drone. The target inspection mode includes a normal inspection mode adapted to non-special weather or an extreme inspection mode adapted to special weather. The target inspection route is the route along which the drone inspects the broken transmission line.

[0045] Specifically, after obtaining the weather information, the weather information can be analyzed and processed to determine the target inspection mode corresponding to the drone. When the target inspection mode is a preset inspection mode, the final target inspection route of the drone can be generated according to the location information of the broken power transmission line.

[0046] In this embodiment, the method of generating the target inspection route corresponding to the drone can be: determining the inspection area with the location information of the transmission line as the center and a preset length as the query radius; determining the target inspection route based on the coordinate information of at least one transmission tower in the inspection area.

[0047] The location information of the transmission line mainly refers to the broken position of the transmission line. A circular range is generated with the broken position as the center and the specified value as the radius. The specified value is determined based on the detection algorithm, which mainly refers to the algorithm for determining the broken position of the transmission line based on electrical quantities.

[0048] It can be understood that: the preset length corresponds to a specified value, and the specified value is determined based on the detection algorithm. The inspection area is a circular area determined based on the break position as the center and the preset length as the radius. The inspection area may include multiple transmission towers, and the flight route of the drone can be determined based on the coordinate information of each transmission tower. Optionally, after obtaining the coordinates of each transmission tower in the inspection area, the coordinates can be connected in sequence to form the flight route of the drone, that is, the target inspection route. After determining the target inspection route, a drone in an idle state can be searched, and the target inspection route can be sent to the drone so that the drone can perform inspections based on the target inspection route.

[0049] S130. During the inspection process of the drone based on the target inspection route, according to the brightness value and the rotation amplitude value collected by the drone at each moment, determine the denoising parameters of the to-be-processed image collected by the drone at the corresponding moment.

[0050] Among them, the drone is equipped with a brightness sensor and an IMU. During the flight of the drone, the brightness value can be collected based on the brightness sensor and the rotation amplitude value corresponding to the current moment can be obtained based on the IMU. The denoising parameters can include disturbance parameters and brightness parameters. Based on the denoising parameters, the image to be processed collected by the drone can be analyzed and processed to improve the clarity of the target image, and then determine the environmental information corresponding to the broken transmission line.

[0051] Specifically, during the inspection process of the UAV based on the target inspection route, the brightness value and the amplitude value collected at each moment can be analyzed and processed to obtain the denoising parameters corresponding to the UAV at the corresponding collection moment.

[0052] It should be noted that the processing method for the brightness value and the amplitude value collected at each moment is the same, and the data processing corresponding to one moment is taken as an example for explanation.

[0053] S140, determining a target image corresponding to the image to be processed based on the disturbance parameters and the illumination parameters in the denoising parameters, and determining target power transmission line information in the target image based on a pre-trained semantic segmentation model.

[0054] The target image is an image obtained after the image to be processed is processed based on the denoising parameters. The semantic segmentation model is a model obtained by pre-training and used to identify the power transmission line in the target image. The target power transmission line information may include the position coordinates of the power transmission line, which mainly refers to the pixel coordinates.

[0055] Specifically, the image to be processed can be further analyzed and processed based on the disturbance parameters and the illumination parameters, and a target image adapted to the image to be processed can be obtained. The target image is input into a pre-trained semantic segmentation model. The semantic segmentation model can identify the power transmission line in the target image and output the pixel coordinates of the power transmission line. The pixel coordinates of the power transmission line can be used as the target power transmission line information.

[0056] S150. When the target power transmission line information meets a preset condition, generate warning information based on the image to be processed and / or the target image.

[0057] It can be understood that: the target transmission line information can be analyzed and processed. If the analysis result meets the preset conditions, it is confirmed that there is a transmission line break here, the surrounding environmental information can be obtained, and early warning information can be generated.

[0058] Optionally, when the target transmission line information meets preset conditions, warning information is generated based on the image to be processed and / or the target image, including: determining the minimum circumscribed rectangle including the new transmission line based on the target transmission line information; when the length and width of the minimum circumscribed rectangle meet preset conditions, determining that there is a line break in the transmission line, and obtaining the break information of the transmission line; generating warning information based on the break information, the image to be processed and / or the target image.

[0059] It can be understood that: according to the pixel coordinates in the target transmission line information, the minimum bounding rectangle including the transmission line can be determined. When the length and width of the minimum bounding rectangle meet the preset conditions, it is determined that the transmission line is broken. At this time, the environment to which the broken transmission line belongs, the image to be processed or the target image can be obtained to generate the final warning information.

[0060] Exemplarily, the target image is input into a pre-trained semantic segmentation model for semantic segmentation operation, the semantics of the pixel points are divided into transmission lines and non-transmission lines, and the pixel points of the transmission lines that belong to the same connected area and whose area of ​​the connected area is greater than a threshold are screened out from the pixel points of all transmission lines, and finally the transmission lines are characterized.

[0061] In order to quickly detect whether the transmission line is broken, the natural drooping characteristics of the line after breaking can be used to add a positive minimum circumscribed rectangle to the transmission line. The so-called positive means that the width and height of the minimum circumscribed rectangle are parallel to the X and Y axes. When the minimum circumscribed rectangle is obtained, the following formula is used to determine whether the transmission line is broken:

[0062]

[0063] Wherein, w is the width of the minimum bounding rectangle, h is the height of the minimum bounding rectangle, a and b are adjustment coefficients, and Th is the threshold.

[0064] When it is detected that the above conditions are met, it means that the power transmission line is broken, and if the above conditions are not met, it means that the power transmission line is not broken. In other words, the judgment condition corresponding to the above formula is a preset condition.

[0065] After determining that the above conditions are met, an early warning message can be generated. In order to enable the target personnel to quickly determine the maintenance plan, the final early warning message can be generated based on the fracture location, the environmental information of the fracture location, the image to be processed collected by the drone, and / or the target image obtained after processing the image to be processed. It should also be noted that when the target personnel confirms that the power transmission line here has a fault, they can manually take over the drone and control the drone to survey the nearby environment in more detail in order to formulate a detailed maintenance plan.

[0066] The technical solution provided by the embodiment of the present invention can obtain weather information of the area to which the transmission line belongs when a transmission line is detected to be broken. By analyzing and processing the weather information, when it is determined that the target inspection mode of the drone is the preset inspection mode, the target inspection route of the drone can be determined. The drone is controlled to inspect along the target inspection route based on the target inspection mode. During the inspection process, the denoising parameters for processing the image to be processed collected at the current moment can be determined according to the brightness value and the amplitude value collected by the drone, and the target image can be obtained after the image to be processed is processed according to the denoising parameters. Next, after analyzing and processing the target image through the semantic segmentation model, the pixel points corresponding to the transmission line can be determined, that is, the target transmission line information is obtained. If the target transmission line information meets the preset conditions, early warning information can be generated based on the image to be processed and / or the target image, and the early warning information can be fed back to the target platform, so that the user corresponding to the target platform can confirm the specific break position and the environmental information of the broken transmission line, so as to achieve the effect of detecting the transmission line in an extreme environment, and solve the problem that the transmission line cannot be effectively detected in an extreme environment in the prior art, resulting in the hysteresis of the transmission line detection.

[0067] Figure 2 A flow chart of a UAV-based power transmission line detection method provided in an embodiment of the present invention. Based on the aforementioned embodiment, the target inspection mode of the UAV determined based on weather information can be further refined. The specific implementation method can refer to the detailed description of the present technical solution, wherein the technical terms that are the same as or corresponding to the above-mentioned embodiments are not repeated in this embodiment.

[0068] like Figure 2 As shown, the method includes:

[0069] S210: Determine a target darkness value at the current moment according to rainfall information in a first sliding window associated with the current moment and a darkness determination function.

[0070] It should be noted that weather information can be obtained in real time, periodically, or when a broken power line is detected. Regardless of the timing of obtaining weather information, the obtained weather information must be processed only when a broken power line is detected.

[0071] Among them, the moment when the broken line is determined can be used as the current moment, and subsequently, each weather acquisition moment can be used as the current moment. The first sliding window can be understood as a pre-set window range for storing rainfall information corresponding to multiple historical moments before the current moment. The number of multiple historical moments can be set according to actual needs, that is, the number of rainfall stored in the first sliding window is set according to actual needs. The rainfall information can be obtained based on weather information, and the darkness determination function is a pre-set function for determining the darkness value at the current moment. The multiple rainfall information in the first sliding window can be substituted into the darkness determination function to obtain the target darkness value corresponding to the current moment.

[0072] It should be noted that when drones are inspecting, they pay more attention to the lighting environment and flight environment, while weather information generally does not directly provide lighting information. Considering that there is a positive correlation between rainfall and lighting information, the rainfall in weather information can be used to evaluate the lighting environment. Furthermore, in order to cooperate with drone inspections, darkness, which is opposite to brightness, can be used as an indicator of lighting information.

[0073] Optionally, the darkness determination function may be:

[0074]

[0075] Among them, Darkness is the target darkness value corresponding to the current moment, the first sliding window includes the rainfall corresponding to multiple historical moments before the current moment, and multiple historical moments and the current moment are continuous, H1 is the maximum value of the rainfall information in the first sliding window, H2 is the average value of the rainfall information in the first sliding window, a and b are pre-set weight parameters, a>b, a+b=1, c>2, which are constants and play a role of regulation, d is a constant, which represents the average darkness when there are no clouds in the sky.

[0076] In this embodiment, the thickness of the cloud layer in the sky is measured from the moment of rain (maximum rainfall), which determines the darkness, and is adjusted based on the average rainfall value, which can improve the accuracy of determining the target darkness value.

[0077] It can be understood that: the rainfall information in the first sliding window can be substituted into the above-mentioned darkness determination function, and the target darkness value corresponding to the current moment can be calculated.

[0078] It should also be noted that since clouds cannot be stacked all the time, they will form rain after reaching a certain level. Therefore, as the amount of rainfall increases, the darkness value will increase sharply until it becomes flat. This relationship fluctuates greatly and is not easy to fit using polynomials or other methods. That is, polynomial fitting will cause overfitting problems. Therefore, the above-mentioned darkness determination function can be used to determine the target darkness value.

[0079] S220. Determine a wind speed prediction sequence corresponding to the current moment according to the wind speed value in the second sliding window associated with the current moment and a wind speed prediction model, so as to determine a target wind speed value at the current moment based on the wind speed prediction sequence.

[0080] Among them, the window sizes of the first sliding window and the second sliding window are the same, and the historical moments stored are also the same. The difference is that the numerical values ​​corresponding to each historical moment represent different dimensions. The numerical values ​​in the first sliding window represent the rainfall information, and the numerical values ​​in the second sliding window represent the wind speed value in the weather information. The wind speed value in the weather information mainly refers to the wind speed at 10 meters above the ground. This height is not the flight altitude of the drone. At the same time, the wind speed values ​​at different altitudes at the same location have a certain nonlinear hierarchical relationship. Therefore, it is necessary to use the wind speed in the weather information to determine the target wind speed value corresponding to the drone's flight altitude.

[0081] Among them, the hierarchical relationship of wind speed is closely related to the environment (valleys, peaks), so the hierarchical relationship of wind speed can be modeled for the local environment. Modeling can use a sequence prediction model based on deep learning (such as an LSTM model) or a sequence reconstruction model (such as U-Net). The sample is the wind speed 10 meters above the ground, the label is the wind speed value at the flight altitude of the drone, and the loss function is the MAE function. After the model is trained, a sliding second sliding window can be added to the wind speed in the weather information, and the wind speed values ​​in the second sliding window can be combined into a sequence A. After inputting sequence A into the trained wind speed prediction model, a sequence B composed of wind speeds at the flight altitude of the local drone is output. After processing the mean of the predicted wind speed values ​​in sequence B, the target wind speed value corresponding to the flight altitude of the drone is obtained.

[0082] S230: Determine a target inspection mode of the UAV based on the target darkness value and the target wind speed value.

[0083] After determining the target darkness value and target wind speed value corresponding to the broken position of the transmission line based on the above method, the target darkness value and target wind speed value can be further processed again to obtain the target inspection mode of the drone.

[0084] In this embodiment, based on the target darkness value and the target wind speed value, determining the target inspection mode of the drone includes: determining the light level corresponding to the target darkness value based on a light piecewise function, and determining the flight level corresponding to the target wind speed value based on a wind speed piecewise function; when the sum of the light level and the flight level exceeds a preset level value, determining that the target inspection mode is an extreme inspection mode.

[0085] It can be understood that a piecewise function corresponding to the darkness value can be pre-established, and the piecewise function is a piecewise function of illumination. At the same time, a piecewise function corresponding to the target wind speed value can be established to determine the flight grade.

[0086] Specifically, the illumination segmentation function can be used to divide the darkness into five illumination levels, and the illumination level corresponding to the target darkness value can be determined. At the same time, the wind speed segmentation function can be used to divide the wind speed value into five wind speed levels, and the flight level corresponding to the target wind speed value can be determined. After determining the illumination level and the flight level, the levels can be summed to obtain the target level corresponding to the drone. When the target level exceeds the preset level value, the target inspection mode is determined to be the extreme inspection mode corresponding to the preset inspection mode. Otherwise, the target inspection mode is the ordinary inspection mode corresponding to non-special weather.

[0087] The technical solution provided in the embodiment of the present invention can analyze and process the weather information after obtaining the weather information to determine the target inspection mode of the drone. When the target inspection mode is the preset inspection mode, the technical solution provided in this embodiment can be used to process the collected data to achieve the effect of line inspection in special weather conditions.

[0088] Figure 3 A flow chart of a UAV-based power transmission line detection method provided in an embodiment of the present invention. Based on the aforementioned embodiment, the denoising parameters corresponding to the UAV can be determined during the UAV inspection based on the target inspection route. The method for determining the denoising parameters can be referred to the detailed description of this embodiment, wherein the technical terms that are the same as or corresponding to the above-mentioned embodiments are not repeated in this embodiment.

[0089] like Figure 3 As shown, the method includes:

[0090] S310: Determine the illumination parameter in the denoising parameter according to the brightness value collected by the drone at the current moment, at least one historical brightness value in the brightness sliding window, and the target darkness value.

[0091] It should be noted that the drone is equipped with a brightness sensor, an IMU and a camera. In the extreme inspection mode, the drone can call the brightness sensor to collect the brightness value of the surrounding environment in real time, call the IMU to collect its own rotation amplitude on the XYZ axis (obtained by integrating the acceleration over time), and call the camera to collect image data of the transmission line. The above collected data can be uploaded to the GIS system. The GIS system can analyze and process the above data to determine the denoising parameters.

[0092] Among them, the brightness value corresponding to the current moment can be collected based on the brightness sensor deployed on the drone. The brightness sliding window includes historical brightness values corresponding to multiple historical moments. The darkness value corresponding to the current moment is the target darkness value. The illumination parameter in the denoising parameter mainly refers to the illumination value.

[0093] It can be understood that since the drone may pass by buildings, and the lights of the buildings may affect the values collected by the brightness sensor. Further, in extreme weather, the brightness sensor may be contaminated with dust, rain, etc., and at this time, the collected brightness values have the problem of low confidence. To solve this problem, a highly confident illumination parameter can be fused from the target darkness value and multiple historical brightness values in the brightness sliding window.

[0094] Exemplarily, the following target formula is used to process multiple historical brightness values in the brightness sliding window and the target darkness value.

[0095]

[0096] Among them, Brightness is the illumination parameter, L i is the i-th historical brightness value in the brightness window, w i is the weight of the i-th brightness in the brightness window, and this weight value decays with time, that is, the closer the collection time is to the current moment, the higher the weight value of the historical brightness value, and vice versa, the farther the collection time is from the current moment, the lower the weight value of the historical brightness value. W1 is the first weight coefficient corresponding to the target darkness value, W2 is the second weight coefficient corresponding to the historical brightness value, W1 + W2 = 1, W1 < W2. Since the update frequency of Darkness is low and the detection frequency of the drone's brightness is high, the illumination parameter is mainly based on the brightness value detected by the drone.

[0097] Based on the above method, the illumination parameter in the denoising parameter can be determined.

[0098] S320. Determine the perturbation parameter in the denoising parameter according to the rotation amplitude value collected by the drone at the current moment, at least one historical rotation amplitude value in the rotation amplitude sliding window, and the target wind speed value.

[0099] It should be noted that in addition to its own jitter, the drone will also have a certain drift due to strong winds in special weather. The jitter change caused by the drift is difficult to be reflected in the rotation amplitude collected by the IMU. Therefore, the rotation amplitude can be further processed to obtain the perturbation parameter in the denoising parameter.

[0100] Among them, the rotation amplitude value can be the value collected by the IMU. The rotation amplitude sliding window includes the historical rotation amplitude values collected at multiple historical moments before the current moment. The target wind speed value is the value corresponding to the flight altitude of the UAV processed above. The disturbance parameter is the parameter caused by the UAV jitter.

[0101] Specifically, based on the rotation amplitude value collected by the UAV at the current moment, the historical rotation amplitude value corresponding to at least one historical moment in the rotation amplitude sliding window, and the target wind speed value, the winding parameter in the denoising parameter can be determined.

[0102] Optionally, determining the disturbance parameter in the denoising parameter according to the rotation amplitude value collected by the UAV at the current moment, at least one historical rotation amplitude value in the rotation amplitude sliding window, and the target wind speed value includes: determining a first value according to the target wind speed value and a first weight; determining a second value according to at least one historical rotation amplitude value in the rotation amplitude sliding window and a corresponding second weight; determining the disturbance parameter according to the second value and the corresponding weight value, and the first value.

[0103] Exemplarily, determining a disturbance parameter with a higher confidence level can be:

[0104]

[0105] Among them, Shake is the jitter parameter, i = 1, 2, 3 represents the XYZ axes, H i is the i-th rotation amplitude in the rotation amplitude sliding window, w i is the weight of the i-th rotation amplitude, and this weight is an empirical value. W1 and W2 are weights, W1 + W2 = 1, W1 < W2. Since the update frequency of Wind is relatively low and the detection frequency of the UAV rotation amplitude is relatively high, the jitter value is mainly based on the rotation amplitude detected by the UAV.

[0106] It can be understood that: after substituting the data obtained above into the above formula, the disturbance parameter corresponding to the current moment can be obtained.

[0107] The technical solution provided by the embodiment of the present invention can obtain weather information of the area to which the transmission line belongs when a transmission line is detected to be broken. By analyzing and processing the weather information, when it is determined that the target inspection mode of the drone is the preset inspection mode, the target inspection route of the drone can be determined. The drone is controlled to inspect along the target inspection route based on the target inspection mode. During the inspection process, the denoising parameters for processing the image to be processed collected at the current moment can be determined according to the brightness value and the amplitude value collected by the drone, and the target image can be obtained after the image to be processed is processed according to the denoising parameters. Next, after analyzing and processing the target image through the semantic segmentation model, the pixel points corresponding to the transmission line can be determined, that is, the target transmission line information is obtained. If the target transmission line information meets the preset conditions, early warning information can be generated based on the image to be processed and / or the target image, and the early warning information can be fed back to the target platform, so that the user corresponding to the target platform can confirm the specific break position and the environmental information of the broken transmission line, so as to achieve the effect of detecting the transmission line in an extreme environment, and solve the problem that the transmission line cannot be effectively detected in an extreme environment in the prior art, resulting in the hysteresis of the transmission line detection.

[0108] Figure 4 A UAV-based power transmission line detection method provided in an embodiment of the present invention can, on the basis of the aforementioned embodiment, determine the target image corresponding to the collected image to be processed according to the disturbance parameters and illumination parameters in the denoising parameters. The specific method can refer to the detailed description of this embodiment, wherein the technical terms that are the same or corresponding to the above-mentioned embodiment are not repeated in this embodiment.

[0109] like Figure 4 As shown, the method includes:

[0110] S410: When a transmission line break is detected, obtain weather information of the area to which the transmission line belongs.

[0111] S420: When the target inspection mode of the drone is determined to be a preset inspection mode based on weather information, determine the target inspection route of the drone.

[0112] S430. During the inspection process of the drone based on the target inspection route, according to the brightness value and the rotation amplitude value collected by the drone at each moment, determine the denoising parameters of the image to be processed collected by the drone at the corresponding moment.

[0113] S440: Substitute the disturbance parameter and the illumination parameter into the intensity function to determine the target intensity coefficient.

[0114] The intensity function is a pre-set function used to determine the intensity coefficient.

[0115] Exemplarily, the intensity function may be:

[0116]

[0117] Among them, Intensity is the target intensity coefficient, α, β, γ, δ and ε are fitted preset coefficients that play a regulatory role, Brightness is the lighting parameter corresponding to the current moment, and Shake is the disturbance parameter corresponding to the current moment.

[0118] After obtaining the illumination parameters and disturbance parameters corresponding to the current moment, they can be substituted into the above intensity function to obtain the target intensity coefficient corresponding to the current moment.

[0119] S450, mapping the target intensity coefficient to the denoising algorithm to obtain the target adjustment coefficient.

[0120] The denoising algorithm may be any existing algorithm capable of denoising, and optionally, the denoising algorithm is 2DNR. After determining a specific denoising algorithm, the target intensity coefficient may be mapped to a parameter of the denoising algorithm, and the denoising algorithm may be used to denoise the image to be processed collected by the drone.

[0121] Exemplarily, if the denoising algorithm is 2DNR, then the target intensity coefficient may be proportionally mapped into the window of 2DNR to obtain the target adjustment coefficient.

[0122] S460, binarizing the image to be processed after denoising according to the target adjustment coefficient to obtain the image to be used, and performing an opening operation on the image to be used to obtain the target image.

[0123] Among them, the image collected by the drone at the current moment is used as the image to be processed.

[0124] Specifically: the OTSU algorithm is used to perform binarization processing on the image to be processed after the denoising process, so as to obtain an image to be used in which the pixel value of the background pixel point is 0 (black) and the pixel value of the foreground pixel point is 255 (white).

[0125] It should be noted that since the image to be processed is collected by the drone at high altitude, the distant scenery will appear darker, and the nearby scenery (transmission lines) will be close to its own color, making it easier and more accurate to separate the foreground and background information.

[0126] The target image is the image obtained after final processing.

[0127] In this embodiment, an opening operation is performed on the image to be used to obtain a target image, including: first corroding and then dilating the image to be used to obtain the image to be used; and obtaining the target image by weighted processing of pixels in the image to be used and the image to be processed.

[0128] It can be understood as: opening the binary image to be used, that is, first corroding, then dilating, and then eliminating small objects, separating objects at thin places and smoothing the boundaries of larger objects, so as to obtain the image to be used. The image to be processed collected at the current moment and the image to be used by the opening operation are weightedly superimposed by pixels to obtain the target image.

[0129] It should be noted that the weighted weights of the pixels in the image to be processed are higher than the weighted weights of the pixels in the image to be applied, so as to achieve a target image in which the foreground content and the background content are distinguished.

[0130] The technical solution provided by the embodiment of the present invention can obtain weather information of the area to which the transmission line belongs when a transmission line is detected to be broken. By analyzing and processing the weather information, when it is determined that the target inspection mode of the drone is the preset inspection mode, the target inspection route of the drone can be determined. The drone is controlled to inspect along the target inspection route based on the target inspection mode. During the inspection process, the denoising parameters for processing the image to be processed collected at the current moment can be determined according to the brightness value and the amplitude value collected by the drone, and the target image can be obtained after the image to be processed is processed according to the denoising parameters. Next, after analyzing and processing the target image through the semantic segmentation model, the pixel points corresponding to the transmission line can be determined, that is, the target transmission line information is obtained. If the target transmission line information meets the preset conditions, early warning information can be generated based on the image to be processed and / or the target image, and the early warning information can be fed back to the target platform, so that the user corresponding to the target platform can confirm the specific break position and the environmental information of the broken transmission line, so as to achieve the effect of detecting the transmission line in an extreme environment, and solve the problem that the transmission line cannot be effectively detected in an extreme environment in the prior art, resulting in the hysteresis of the transmission line detection.

[0131] Figure 5 A schematic diagram of the structure of a power transmission circuit detection device based on a drone provided in an embodiment of the present invention, the device includes: a weather information acquisition module 510, an inspection route determination module 520, a parameter determination module 530, a power transmission line information determination module 540 and a warning information generation module 550.

[0132] Among them, the weather information acquisition module 510 is used to obtain the weather information of the area to which the transmission line belongs when a transmission line is detected to be broken; the inspection route determination module 520 is used to determine the target inspection route of the drone when the target inspection mode of the drone is determined to be a preset inspection mode based on the weather information; the parameter determination module 530 is used to determine the denoising parameters of the image to be processed collected by the drone at the corresponding moment according to the brightness value and the amplitude value collected by the drone at each moment during the inspection of the drone based on the target inspection route; wherein the denoising parameters are determined based on the illumination parameters corresponding to the brightness value and the disturbance parameters corresponding to the amplitude value; the transmission line information determination module 540 is used to determine the target image corresponding to the image to be processed based on the disturbance parameters and illumination parameters in the denoising parameters, and determine the target transmission line information in the target image based on the pre-trained semantic segmentation model; the warning information generation module 550 is used to generate warning information based on the image to be processed and / or the target image when the target transmission line information meets the preset conditions.

[0133] Based on the above technical solution, the weather information acquisition module includes:

[0134] The electrical quantity acquisition unit is used to obtain the electrical quantity of each transmission line; the judgment unit is used to determine whether the transmission line is broken if the electrical quantity does not meet the preset power consumption conditions; the data retrieval unit is used to retrieve weather information of the area to which the transmission line belongs.

[0135] Based on the above technical solutions, the inspection route determination module includes:

[0136] A darkness value determination unit is used to determine a target darkness value at a current moment according to rainfall information in a first sliding window associated with the current moment and a darkness determination function; wherein the first sliding window includes rainfall information corresponding to at least one moment before the current moment; a wind speed value determination unit is used to determine a wind speed prediction sequence corresponding to the current moment according to a wind speed value in a second sliding window associated with the current moment and a wind speed prediction model, so as to determine the target wind speed value at the current moment based on the wind speed prediction sequence; wherein the wind speed prediction sequence includes multiple predicted wind speeds, and the predicted wind speed is associated with the flight altitude of the UAV; an inspection route determination unit is used to generate a target inspection route for the UAV based on the location information of the power transmission line when the target inspection mode of the UAV is determined to be a preset inspection mode based on the target darkness value and the target wind speed value; wherein the preset inspection mode includes an extreme inspection mode adapted to special weather.

[0137] On the basis of the above technical solution, the inspection mode determination unit includes: a level determination subunit, used to determine the light level corresponding to the target darkness value based on the light segmentation function, and to determine the flight level corresponding to the target wind speed value based on the wind speed segmentation function; an inspection mode determination subunit, used to determine that the target inspection mode is an extreme inspection mode when the sum of the light level and the flight level exceeds a preset level value.

[0138] Based on the above technical solution, the denoising parameter determination module includes:

[0139] The illumination parameter determination unit is used to determine the illumination parameters in the denoising parameters according to the brightness value collected by the drone at the current moment, at least one historical brightness value in the brightness sliding window, and the target darkness value; the disturbance parameter determination unit is used to determine the disturbance parameters in the denoising parameters according to the rotation amplitude value collected by the drone at the current moment, at least one historical rotation amplitude value in the rotation amplitude sliding window, and the target wind speed value.

[0140] On the basis of the above technical solutions, the disturbance parameter determination unit includes:

[0141] The first value determination subunit is used to determine the first value based on the target wind speed value and the first weight; the second value determination subunit is used to determine the second value based on at least one historical amplitude value in the amplitude sliding window and the corresponding second weight; the disturbance parameter determination subunit is used to determine the disturbance parameter based on the second value and the corresponding weight value, as well as the first value.

[0142] On the basis of the above technical solutions, the target image determination module includes:

[0143] The intensity coefficient determination unit is used to substitute the disturbance parameter and the illumination parameter into the intensity function to determine the target intensity coefficient; the adjustment coefficient determination unit is used to map the target intensity coefficient to the denoising algorithm to obtain the target adjustment coefficient; the image to be used determination unit is used to binarize the image to be processed after denoising according to the target adjustment coefficient to obtain the image to be used; the target image determination unit is used to perform an opening operation on the image to be used to obtain the target image.

[0144] On the basis of the above technical solutions, the target image determination unit is further used to: first corrode and then dilate the image to be used to obtain the image to be applied; and obtain the target image by weighted processing of the pixels in the image to be applied and the image to be processed.

[0145] On the basis of the above-mentioned technical solutions, the warning information generation module is also used to determine the minimum circumscribed rectangle including the new transmission line according to the target transmission line information; when the height and width of the minimum circumscribed rectangle meet the preset conditions, it is determined that there is a line break in the transmission line and the break information of the transmission line is obtained; and the warning information is generated based on the break information, the image to be processed and / or the target image.

[0146] The technical solution provided by the embodiment of the present invention can obtain weather information of the area to which the transmission line belongs when a transmission line is detected to be broken. By analyzing and processing the weather information, when it is determined that the target inspection mode of the drone is the preset inspection mode, the target inspection route of the drone can be determined. The drone is controlled to inspect along the target inspection route based on the target inspection mode. During the inspection process, the denoising parameters for processing the image to be processed collected at the current moment can be determined according to the brightness value and the amplitude value collected by the drone, and the target image can be obtained after the image to be processed is processed according to the denoising parameters. Next, after analyzing and processing the target image through the semantic segmentation model, the pixel points corresponding to the transmission line can be determined, that is, the target transmission line information is obtained. If the target transmission line information meets the preset conditions, early warning information can be generated based on the image to be processed and / or the target image, and the early warning information can be fed back to the target platform, so that the user corresponding to the target platform can confirm the specific break position and the environmental information of the broken transmission line, so as to achieve the effect of detecting the transmission line in an extreme environment, and solve the problem that the transmission line cannot be effectively detected in an extreme environment in the prior art, resulting in the hysteresis of the transmission line detection.

[0147] The UAV-based power transmission line detection device provided in the embodiment of the present invention can execute the UAV-based power transmission line detection method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0148] It is worth noting that the various units and modules included in the above system are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0149] Figure 6 A schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Figure 6 A block diagram of an exemplary apparatus 60 suitable for use in implementing exemplary embodiments of the present invention is shown. Figure 6 The device 60 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0150] like Figure 6As shown, the device 60 is in the form of a general-purpose computing device. The components of the device 60 may include, but are not limited to: one or more processors or processing units 601, a system memory 602, and a bus 603 connecting different system components (including the system memory 602 and the processing unit 601).

[0151] Bus 603 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus structures. For example, these architectures include but are not limited to Industry Standard Architecture (ISA) bus, Micro Channel Architecture (MAC) bus, Enhanced ISA bus, Video Electronics Standards Association (VESA) local bus and Peripheral Component Interconnect (PCI) bus.

[0152] Device 60 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by device 60, including volatile and non-volatile media, removable and non-removable media.

[0153] System memory 602 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 604 and / or cache memory 605. Device 60 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 606 may be used to read and write non-removable, non-volatile magnetic media ( Figure 6 not shown, usually called a "hard drive"). Although Figure 6 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 603 via one or more data medium interfaces. Memory 602 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of various embodiments of the present invention.

[0154] A program / utility 608 having a set (at least one) of program modules 607 may be stored, for example, in the memory 602, such program modules 607 including but not limited to an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. The program modules 607 generally perform the functions and / or methods of the embodiments described herein.

[0155] The device 60 may also communicate with one or more external devices 609 (e.g., keyboards, pointing devices, displays 610, etc.), may communicate with one or more devices that enable a user to interact with the device 60, and / or may communicate with any device that enables the device 60 to communicate with one or more other computing devices (e.g., a network card, a modem, etc.). Such communication may be performed via an input / output (I / O) interface 611. Furthermore, the device 60 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 612. As shown, the network adapter 612 communicates with the other modules of the device 60 via the bus 603. It should be understood that although Figure 6 Not shown, other hardware and / or software modules may be used in conjunction with device 60, including but not limited to microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0156] The processing unit 601 executes various functional applications and data processing by running the programs stored in the system memory 602, such as implementing the UAV-based power transmission line detection method provided in the embodiment of the present invention.

[0157] An embodiment of the present invention also provides a storage medium containing computer executable instructions, which are used to execute a UAV-based power transmission line detection method when executed by a computer processor.

[0158] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0159] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0160] Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0161] Computer program code for performing the operation of embodiments of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" or similar programming languages. The program code may be executed entirely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0162] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A transmission line detection method based on drone, characterized in that: include: When a transmission line is detected to be broken, obtaining weather information of the area to which the transmission line belongs; When it is determined that the target inspection mode of the drone is a preset inspection mode based on the weather information, determining a target inspection route of the drone; In the process of the drone inspecting the target inspection route, according to the brightness value and the rotation amplitude value collected by the drone at each moment, the denoising parameters of the image to be processed collected by the drone at the corresponding moment are determined; wherein the denoising parameters are determined based on the illumination parameters corresponding to the brightness value and the disturbance parameters corresponding to the rotation amplitude value; Based on the disturbance parameter in the denoising parameter and the illumination parameter, determining a target image corresponding to the image to be processed, and based on a pre-trained semantic segmentation model, determining target power transmission line information in the target image; When the target power transmission line information meets a preset condition, early warning information is generated based on the image to be processed and / or the target image.

2. The method according to claim 1, characterized in that: When a transmission line is detected to be broken, obtaining weather information of an area to which the transmission line belongs includes: For each transmission line, obtaining the electrical quantity of the transmission line; If the electrical quantity does not meet the preset power consumption condition, it is determined that the power transmission line is broken; Retrieve weather information for the area to which the transmission line belongs.

3. The method according to claim 1, characterized in that The step of determining a target inspection route of the drone when the target inspection mode of the drone is determined to be a preset inspection mode based on the weather information includes: Determine the target darkness value at the current moment according to the rainfall information in the first sliding window associated with the current moment and the darkness determination function; wherein the first sliding window includes the rainfall information corresponding to at least one moment before the current moment; According to the wind speed value in the second sliding window associated with the current moment and the wind speed prediction model, determine the wind speed prediction sequence corresponding to the current moment, so as to determine the target wind speed value at the current moment based on the wind speed prediction sequence; wherein the wind speed prediction sequence includes a plurality of predicted wind speeds, and the predicted wind speeds are associated with the flight altitude of the UAV; When it is determined that the target inspection mode of the drone is a preset inspection mode based on the target darkness value and the target wind speed value, a target inspection route of the drone is generated based on the location information of the power transmission line; Among them, the preset inspection mode is an extreme inspection mode adapted to special weather.

4. The method according to claim 3, characterized in that The step of determining the target inspection mode of the drone as a preset inspection mode based on the target darkness value and the target wind speed value includes: Determining the illumination level corresponding to the target darkness value based on an illumination piecewise function, and determining the flight level corresponding to the target wind speed value based on a wind speed piecewise function; When the sum of the illumination level and the flight level exceeds a preset level value, the target inspection mode is determined to be an extreme inspection mode.

5. The method according to claim 3, characterized in that: The generating a target inspection route of the drone based on the location information of the power transmission line includes: Taking the location information of the transmission line as the center and a preset length as the query radius, determining the inspection area; The target inspection route is determined based on the coordinate information of at least one transmission tower in the inspection area.

6. The method according to claim 1, characterized in that Determining the denoising parameters of the image to be processed collected by the drone at the corresponding moment according to the brightness value and the amplitude value collected by the drone at each moment includes: Determine the illumination parameter in the denoising parameter according to the brightness value collected by the drone at the current moment, at least one historical brightness value in the brightness sliding window, and the target darkness value; The disturbance parameter in the denoising parameter is determined according to the rotation amplitude value collected by the UAV at the current moment, at least one historical rotation amplitude value in the rotation amplitude sliding window, and the target wind speed value.

7. The method according to claim 6, characterized in that The determining of the disturbance parameter in the denoising parameter according to the rotation amplitude value collected by the drone at the current moment, at least one historical rotation amplitude value in the rotation amplitude sliding window, and the target wind speed value comprises: Determining a first value according to the target wind speed value and a first weight; Determine a second value according to at least one historical amplitude rotation value in the amplitude rotation sliding window and a corresponding second weight; The disturbance parameter is determined according to the second value and the corresponding weight value, and the first value.

8. The method according to claim 1, characterized in that The step of determining a target image corresponding to the image to be processed based on the disturbance parameter in the denoising parameter and the illumination parameter comprises: Substituting the disturbance parameter and the illumination parameter into an intensity function to determine a target intensity coefficient; Mapping the target intensity coefficient into a denoising algorithm to obtain a target adjustment coefficient; Binarizing the image to be processed after denoising according to the target adjustment coefficient to obtain an image to be used; An opening operation is performed on the image to be used to obtain the target image.

9. The method according to claim 8, characterized in that The step of performing an opening operation on the image to be used to obtain the target image includes: The image to be used is first corroded and then expanded to obtain an image to be applied; The target image is obtained by weighted processing of the pixel points in the image to be applied and the image to be processed.

10. The method according to claim 1, characterized in that When the target power transmission line information meets a preset condition, generating warning information based on the image to be processed and / or the target image includes: Determining a minimum circumscribed rectangle including the new transmission line according to the target transmission line information; When the height and width of the minimum circumscribed rectangle meet preset conditions, determining that there is a line break in the transmission line, and obtaining the break information of the transmission line; The warning information is generated based on the fracture information, the image to be processed and / or the target image.

Citation Information

Cited By

  • Electric power inspection early warning prompting method and system based on edge calculation, and storage medium

    CN121353959A