Line discharge intensity detection method, device, equipment, medium and program product

Abstract

The invention relates to a line discharge intensity detection method and device, computer equipment, a computer readable storage medium and a computer program product. The method is applied to a lightweight holder, and comprises the following steps: if a line component target exists in a current scene, obtaining an initial ultraviolet image and an initial visible light image; if the initial visible light image meets the reference image requirement, determining the position of a line component target, and obtaining a registered ultraviolet image according to the initial visible light image and the distance between the visible light camera and the line component target; determining a first visible light filtering image corresponding to the initial visible light image, and obtaining a first ultraviolet conversion image based on the registered ultraviolet image so as to determine a corresponding first ultraviolet filtering image; and fusing the first visible light filtering image and the first ultraviolet filtering image to obtain a first detection image, and if a discharge defect is identified based on the actual discharge intensity of the line component target after a discharge phenomenon is determined according to the first detection image, sending out alarm prompt information, so that the detection efficiency is improved.

Description

Technical Field

[0001] The present application relates to the field of discharge detection technology, and in particular to a method, device, computer equipment, computer-readable storage medium and computer program product for detecting line discharge intensity. Background Art

[0002] With the development of detection technology, people have paid attention to the fact that under the influence of long-term electric fields, mechanical stress and environmental factors, insulation aging, deterioration, breakage, cracking and loosening may occur in transmission lines. At the same time, improper handling of any link in the design, manufacturing, installation, operation and maintenance may cause defects, leading to local electric field concentration and possible corona discharge.

[0003] In the related art, patrol personnel are usually required to patrol the power transmission lines to detect whether there is a discharge phenomenon in the power transmission lines. However, it is difficult to perform efficient discharge detection on the power transmission lines by manual patrol, that is, there is a problem of low efficiency in line discharge intensity detection. Summary of the invention

[0004] Based on this, it is necessary to provide a line discharge intensity detection method, device, computer equipment, computer readable storage medium and computer program product that can improve the efficiency of line discharge intensity detection in response to the above technical problems.

[0005] In a first aspect, the present application provides a line discharge intensity detection method, which is applied to a lightweight gimbal, comprising:

[0006] In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are acquired, wherein the initial ultraviolet image is acquired by an ultraviolet camera photographing the target transmission line at a matching first pitch angle, and the initial visible light image is acquired by a visible light camera photographing the target transmission line at a matching second pitch angle;

[0007] When it is verified that the initial visible light image meets the reference image requirement, performing target detection on the initial visible light image to determine the line component target and the position of the line component target;

[0008] Taking the initial visible light image as a reference image, and based on the distance between the visible light camera and the line component target, registering the initial ultraviolet image to obtain a registered ultraviolet image;

[0009] Based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering processing, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering processing;

[0010] Based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in a line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters;

[0011] Determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0012] When it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

[0013] In a second aspect, the present application also provides a line discharge intensity detection device, comprising:

[0014] An image acquisition module, for acquiring an initial ultraviolet image and an initial visible light image when a line component target is detected in the current scene, wherein the initial ultraviolet image is obtained by photographing the target transmission line with an ultraviolet camera at a matching first pitch angle, and the initial visible light image is obtained by photographing the target transmission line with a visible light camera at a matching second pitch angle;

[0015] A target detection module, configured to perform target detection on the initial visible light image to determine the line component target and the position of the line component target when it is verified that the initial visible light image meets the reference image requirement;

[0016] An image registration module, configured to register the initial ultraviolet image based on the distance between the visible light camera and the circuit component target, using the initial visible light image as a reference image, to obtain a registered ultraviolet image;

[0017] An image filtering module, configured to obtain a first visible light filtered image by performing visible light filtering processing based on the initial visible light image, and to perform format conversion on the registered ultraviolet image according to a preset format to obtain a first ultraviolet converted image, and to obtain a first ultraviolet filtered image by performing ultraviolet filtering processing based on the first ultraviolet converted image;

[0018] a distance determination module, configured to obtain a first detection image through image fusion processing based on the first visible light filter image and the first ultraviolet filter image, and determine the distance between the ultraviolet camera and the line component target based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters, when it is determined that the line component target has a discharge phenomenon based on the first detection image;

[0019] an intensity determination module, for determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0020] The information issuing module is used to issue an alarm prompt information corresponding to the discharge defect when a discharge defect is detected in the line component target according to the actual discharge intensity.

[0021] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0022] In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are acquired, wherein the initial ultraviolet image is acquired by an ultraviolet camera photographing the target transmission line at a matching first pitch angle, and the initial visible light image is acquired by a visible light camera photographing the target transmission line at a matching second pitch angle;

[0023] When it is verified that the initial visible light image meets the reference image requirement, performing target detection on the initial visible light image to determine the line component target and the position of the line component target;

[0024] Taking the initial visible light image as a reference image, and based on the distance between the visible light camera and the line component target, registering the initial ultraviolet image to obtain a registered ultraviolet image;

[0025] Based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering processing, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering processing;

[0026] Based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in a line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters;

[0027] Determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0028] When it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

[0029] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0030] In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are acquired, wherein the initial ultraviolet image is acquired by an ultraviolet camera photographing the target transmission line at a matching first pitch angle, and the initial visible light image is acquired by a visible light camera photographing the target transmission line at a matching second pitch angle;

[0031] When it is verified that the initial visible light image meets the reference image requirement, performing target detection on the initial visible light image to determine the line component target and the position of the line component target;

[0032] Taking the initial visible light image as a reference image, and based on the distance between the visible light camera and the line component target, registering the initial ultraviolet image to obtain a registered ultraviolet image;

[0033] Based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering processing, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering processing;

[0034] Based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in a line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters;

[0035] Determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0036] When it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

[0037] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0038] In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are acquired, wherein the initial ultraviolet image is acquired by an ultraviolet camera photographing the target transmission line at a matching first pitch angle, and the initial visible light image is acquired by a visible light camera photographing the target transmission line at a matching second pitch angle;

[0039] When it is verified that the initial visible light image meets the reference image requirement, performing target detection on the initial visible light image to determine the line component target and the position of the line component target;

[0040] Taking the initial visible light image as a reference image, and based on the distance between the visible light camera and the line component target, registering the initial ultraviolet image to obtain a registered ultraviolet image;

[0041] Based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering processing, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering processing;

[0042] Based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in a line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters;

[0043] Determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0044] When it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

[0045] The above-mentioned line discharge intensity detection method, device, computer equipment, computer-readable storage medium and computer program product are applied to a lightweight pan / tilt. When a line component target is detected in the current scene, the detection is confirmed to be turned on, and the pitch angles of the ultraviolet camera and the visible light camera are pre-checked to obtain the first pitch angle and the second pitch angle that match each other, which can ensure that the target transmission line is accurately photographed, thereby obtaining the initial ultraviolet image and the initial visible light image. When the initial visible light image is verified to meet the reference image requirements, that is, the initial visible light image with richer information is pre-checked and can be used as a registration reference, and the initial visible light image is subjected to target detection to accurately detect the line component target and the position of the line component target. Taking the initial visible light image as the reference image, the initial ultraviolet image is registered based on the distance between the visible light camera and the line component target to obtain a registered ultraviolet image; based on the initial visible light image, a first visible light filtered image is obtained through visible light filtering, and the registered ultraviolet image is converted into a first ultraviolet conversion image according to a preset format, and based on the first ultraviolet conversion image, a first ultraviolet filtered image is obtained through ultraviolet filtering; based on the first visible light filtered image and the first ultraviolet filtered image, a first detection image is obtained through image fusion processing. In the case that the line component target is determined to have a discharge phenomenon based on the first detection image, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filtered image, the line component target preset actual size, and the preset ranging parameters of the lightweight pan-tilt head. Based on the first ultraviolet filtered image, ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target, the actual discharge intensity on the line component target can be accurately identified. Based on this, it is possible to more accurately verify whether there is a discharge defect, thereby improving the accuracy of discharge detection. When a discharge defect is detected in the line component target according to the actual discharge intensity, an alarm prompt message corresponding to the discharge defect is automatically issued, thereby enabling timely early warning. Under the premise of ensuring the accuracy of line discharge intensity detection, automated processing and automated alarms are used throughout the process, eliminating the need for manual inspections by inspection personnel, thereby improving the efficiency of line discharge intensity detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0047] Figure 1 is an application environment diagram of a line discharge intensity detection method in an embodiment;

[0048] Figure 2 is a partial schematic diagram of a drone in one embodiment;

[0049] Figure 3 is a schematic diagram of a housing of a control unit in one embodiment;

[0050] Figure 4 A schematic diagram of a turbo blower cooling fan arrangement in one embodiment;

[0051] Figure 5 1 is a flow chart of a method for detecting line discharge intensity in one embodiment;

[0052] Figure 6 is a structural block diagram of a line discharge intensity detection device in one embodiment;

[0053] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0055] The line discharge intensity detection method provided in the embodiment of the present application can be applied to Figure 1 In the application environment shown in the figure, Figure 1 It shows that the drone 102 communicates with the lightweight gimbal 104 through the network. For example, new equipment is deployed on the drone, and the new equipment includes a collection device and a lightweight gimbal 104. Among them, the collection equipment includes but is not limited to ultraviolet cameras, visible light cameras, and rangefinders. For example, the collection equipment can also be deployed directly on the gimbal. Among them, the lightweight gimbal 104 and the micro-discharge detection sensor are integrated, and the total weight of the gimbal and the micro-discharge detection sensor is less than 200g. The micro-discharge detection sensor includes an ultraviolet sensor and a visible light camera. For example, the gimbal can be a dual-light layout of an ultraviolet camera and a visible light camera. The gimbal is located on the top of the drone, has pitch adjustment and anti-shake functions, includes an end-side intelligent processing unit, that is, a local end-side AI (Artificial Intelligence) computing power and architecture, and has intelligent recognition functions such as insulators and wire clamps.

[0056] like Figure 2, which is a partial schematic diagram of a drone in one embodiment. Figure 2 The figure shows the local structure of the drone, on which a lightweight gimbal is deployed, and on which a servo unit, an ultraviolet camera, and a lens of a visible light camera (such as a wide-angle visible light camera) are deployed. For example, the lens of the visible light camera can ensure that the ultraviolet detection spot is superimposed and displayed on the visible light screen in real time.

[0057] Among them, a card slot and a heat dissipation unit are embedded in the housing of the control unit in the gimbal. The ultraviolet camera and the visible light camera are set on the drone body through the steering unit; the rangefinder is set on the drone body, and the rangefinder is used to measure the distance between the visible light camera and the target power transmission line, and also to measure the distance between the ultraviolet camera and the target power transmission line. Exemplarily, the rangefinder can be a laser rangefinder. Exemplarily, the material of the drone body and the steering unit is aluminum alloy.

[0058] like Figure 3 The figure is a schematic diagram of the housing of a control unit in one embodiment. A heat dissipation unit can be set on the housing, and a heat sink is embedded in the housing surface of the control unit. The heat sink is passive heat dissipation. The heat sink is toothed, which can increase the contact area between the external air and the heat sink, thereby effectively increasing the heat dissipation area and enhancing the heat dissipation effect. A turbo blower heat dissipation fan is embedded in the heat sink to actively dissipate heat, such as Figure 4 Shown is a schematic diagram of the turbo blower cooling fan setting in one embodiment. The heat dissipation unit includes a heat sink and a turbo blower cooling fan. It should be noted that the turbo blower cooling fan has the characteristics of low power consumption and large air volume. It can quickly blow away the heat on the heat sink, reduce the temperature of the heat sink, thereby reducing the temperature of the heat-generating components and achieving a good heat dissipation effect. The specific setting process of the turbo blower cooling fan: embed it into the heat sink, with the air suction side facing upward, and the air outlet aligned with the tooth-like protrusions on the heat sink. This setting design can increase the intake air volume, while allowing the cooling wind to take away more heat.

[0059] For example, the lightweight gimbal 104 can also be wirelessly connected to the drone body, and the drone body can also be directly wirelessly connected to the control unit in the gimbal, which is used to control the drone body to fly along the target power transmission line. For example, the control unit is wirelessly connected to the drone body, the steering unit, the ultraviolet camera, the visible light camera and the rangefinder respectively; the control unit is used to control the drone body to fly along the power transmission line, control the steering unit to adjust the posture of the ultraviolet camera and the visible light camera, and control the ultraviolet camera and the visible light camera to synchronously collect the initial ultraviolet light image and the initial visible light image of the target power transmission line.

[0060] In other embodiments, the newly added equipment deployed on the drone also includes a positioning unit, which is used to obtain the location information of the drone body; the location information includes the longitude, latitude and altitude of the drone body. Exemplarily, the positioning unit can also be wirelessly connected to the control unit. The positioning unit sends the location information to the control unit. Exemplarily, the control unit can determine the exact discharge position of the target transmission line where the discharge phenomenon exists based on the longitude, latitude, altitude and distance of the drone body, which facilitates the staff to carry out the next step of work and improves the detection efficiency and positioning efficiency.

[0061] The control unit in the above-mentioned gimbal can be an intelligent handheld terminal, a microprocessor or an edge computing unit. The edge computing unit can be an AI (Artificial Intelligence) unit. The AI ​​unit consists of a carrier board, a core board and a shell. The core board consists of basic components such as memory, MCU (Microcontroller Unit), flash (a non-volatile memory), power interface, and network port. The shell of the AI ​​unit can be made of aluminum alloy or magnesium-aluminum alloy, with an average wall thickness of 1.2 mm, which is easy to carry. An opening is provided on the surface of the shell to facilitate the transmission of data from the input and output ends of the carrier board and the core board. For example, there is a heat sink above the AI ​​unit, and thermal grease is applied to both the AI ​​unit and the heat sink, which can increase the thermal contact surface and enhance the thermal efficiency.

[0062] The servo unit mentioned above includes a servo and a metal shell. The servo is built into the metal shell to hide the interface wiring, making the structure compact and both beautiful and safe. The servo unit is connected to the control unit through a U-shaped structure. The U-shaped structure is used to fix the camera and maintain stability. The UV camera interface inside the control unit is connected to the UV camera through an extremely fine coaxial cable passing through the servo arm. This allows the wiring to be hidden in the servo arm, making the overall structure more compact, with no exposed wiring on the outside, and reducing wind resistance.

[0063] In some embodiments, when the lightweight gimbal 104 detects the presence of a line component target in the current scene, it obtains an initial ultraviolet image and an initial visible light image, wherein the initial ultraviolet image is obtained by photographing the target transmission line with a matching first pitch angle by the ultraviolet camera, and the initial visible light image is obtained by photographing the target transmission line with a matching second pitch angle by the visible light camera; when the lightweight gimbal 104 verifies that the initial visible light image meets the reference image requirements, it performs target detection on the initial visible light image to determine the positions of the line component target and the line component target; using the initial visible light image as the reference image, based on the distance between the visible light camera and the line component target, it aligns the initial ultraviolet image to obtain an aligned ultraviolet image; based on the initial visible light image, the lightweight gimbal 104 obtains a first visible light filtered image through visible light filtering processing, The registered ultraviolet image is converted in a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained through ultraviolet filtering processing; based on the first visible light filtered image and the first ultraviolet filtered image, a first detection image is obtained through image fusion processing, and when it is determined based on the first detection image that a discharge phenomenon exists in the line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filtered image, the preset actual size of the line component target, and the preset ranging parameters of the lightweight pan-tilt head; the actual discharge intensity on the line component target is determined based on the first ultraviolet filtered image, the ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target; when a discharge defect is found in the line component target based on the actual discharge intensity, an alarm prompt information corresponding to the discharge defect is issued.

[0064] The lightweight pan / tilt 104 may be a terminal, which may be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and the like.

[0065] In an exemplary embodiment, Figure 5 As shown, a line discharge intensity detection method is provided, and the method is applied to Figure 1 The lightweight pan / tilt head 104 in the embodiment is used as an example to illustrate the method, which includes the following steps S502 to S514. Among them:

[0066] Step S502, when it is detected that there is a line component target in the current scene, an initial ultraviolet image and an initial visible light image are obtained, the initial ultraviolet image is obtained by shooting the target transmission line with an ultraviolet camera at a matching first pitch angle, and the initial visible light image is obtained by shooting the target transmission line with a visible light camera at a matching second pitch angle.

[0067] The target transmission line is the transmission line to be detected, and the line component target can be understood as the line component on the target transmission line that is detected as a target. For example, the line component target can be a hardware, an insulator, and the like.

[0068] Exemplarily, when the detection cycle is reached, the current scene where the drone is located is preliminarily photographed by a visible light camera to obtain a scene image. The scene image is identified by the gimbal to obtain an identification result. If the identification result indicates that there is a line component target in the current scene, the lightweight gimbal generates an acquisition request for line discharge intensity detection, and sends it to the ultraviolet camera and the visible light camera on the drone respectively, to instruct the ultraviolet camera to adjust its posture so that the ultraviolet camera is at a first pitch angle, and to instruct the visible light camera to adjust its posture so that the visible light camera is at a second pitch angle, and to instruct the ultraviolet camera at the first pitch angle and the visible light camera at the second pitch angle to simultaneously capture images of the target transmission line to obtain an initial ultraviolet image and an initial visible light image. The lightweight gimbal receives the initial ultraviolet image captured by the ultraviolet camera and the initial visible light image captured by the visible light camera. The shooting direction of the ultraviolet camera is the same as that of the visible light camera, and they are collected synchronously.

[0069] Exemplarily, when the detection cycle is reached, the current scene where the drone is located is preliminarily photographed by a visible light camera to obtain a scene image. The scene image is recognized by a target detection unit in a lightweight gimbal to obtain a recognition result. If the recognition result indicates that there is a line component target on the target transmission line in the current scene, the pitch angle adjustment unit of the lightweight gimbal determines a first pitch angle that matches the target transmission line and the ultraviolet camera, and determines a second pitch angle that matches the target transmission line and the visible light camera. According to the first pitch angle and the second pitch angle, a collection request for line discharge intensity detection is generated to instruct the ultraviolet camera to adjust its posture so that the ultraviolet camera is at the first pitch angle, and to instruct the visible light camera to adjust its posture so that the visible light camera is at the second pitch angle, and to instruct the ultraviolet camera at the first pitch angle and the visible light camera at the second pitch angle to simultaneously collect images of the target transmission line to obtain an initial ultraviolet image and an initial visible light image.

[0070] Step S504: When it is verified that the initial visible light image meets the reference image requirement, target detection is performed on the initial visible light image to determine the line component target and the position of the line component target.

[0071] Among them, the benchmark image can be understood as a reference standard when performing image registration on the image to be registered. The benchmark image requirement can be that the image quality of the image reaches the image quality of the benchmark image. For example, the higher the resolution of the image, the higher the probability that the image meets the benchmark image requirement.

[0072] Optionally, the lightweight gimbal determines the resolution of the initial visible light image, and determines whether the initial visible light image meets the reference image requirement based on the resolution.

[0073] Exemplarily, the control unit in the lightweight gimbal scores the image quality of the initial visible light image according to the resolution to obtain a corresponding image quality score. If the image quality score is greater than or equal to a preset quality score threshold, it is determined that the initial visible light image meets the benchmark image requirements.

[0074] For example, the control unit of the lightweight gimbal obtains an image quality assessment model based on a neural network, inputs the resolution of the initial visible light image into the image quality assessment model, and obtains an image quality score.

[0075] It should be noted that in the discharge detection scenario, the initial ultraviolet image is grayscale and the initial visible light image is color. Generally, the initial visible light image may obtain more details of the target transmission line. Since the initial ultraviolet image has a stronger ability to capture discharge features, the baseline image requirement is used to pre-verify whether the initial visible light image has more details. If so, the initial ultraviolet image is aligned based on the initial visible light image with more details to ensure that the discharge features in the aligned ultraviolet image are obvious and have more detail information, so that discharge detection can be performed more accurately.

[0076] Object detection is used to identify target objects and locations from images.

[0077] Exemplarily, when the lightweight gimbal verifies that the initial visible light image meets the reference image requirements, it calls the target detection model or target detection algorithm to perform image detection on the initial visible light image, and determines the line component target and the position of the line component target in the initial visible light image. Further, the size of the line component target is determined.

[0078] Exemplarily, the target detection model can be constructed based on a neural network, and the target detection algorithm can be a YOLO (You Only Look Once, a detection algorithm) series algorithm, or a PKAMNet (a small target detection algorithm) algorithm, etc., without specific limitation.

[0079] Step S506 , using the initial visible light image as a reference image, and based on the distance between the visible light camera and the circuit component target, registering the initial ultraviolet image to obtain a registered ultraviolet image.

[0080] In some embodiments, the method also includes: determining the resolution of the initial ultraviolet image and the resolution of the initial visible light image; when the resolution of the initial ultraviolet image is less than or equal to the resolution of the initial visible light image, determining that the initial visible light image meets the baseline image requirements; when the resolution of the initial ultraviolet image is greater than the resolution of the initial visible light image, determining that the initial visible light image does not meet the baseline image requirements.

[0081] Exemplarily, when the resolution of the initial ultraviolet image and the resolution of the initial visible light image are both greater than or equal to a resolution threshold, the control unit of the lightweight gimbal compares the resolution of the initial ultraviolet image and the resolution of the initial visible light image, and determines that the initial visible light image meets the benchmark image requirement when the resolution of the initial ultraviolet image is less than or equal to the resolution of the initial visible light image; and determines that the initial visible light image does not meet the benchmark image requirement when the resolution of the initial ultraviolet image is greater than the resolution of the initial visible light image.

[0082] Exemplarily, when the resolution of the initial ultraviolet image is greater than or equal to the resolution threshold, and the resolution of the initial visible light image is less than the resolution threshold, it is determined that the initial visible light image does not meet the reference image requirement.

[0083] Exemplarily, when the resolution of the initial ultraviolet image is less than the resolution threshold and the resolution of the initial visible light image is greater than or equal to the resolution threshold, it is determined that the initial visible light image meets the reference image requirement.

[0084] In this embodiment, by judging whether the resolution of the initial visible light image is higher than the resolution of the initial ultraviolet image, if it is higher, it means that the details of the initial visible light image are higher than the details of the initial ultraviolet image, and the initial visible light image with more details is selected as the reference. If it is lower, it means that the details of the initial visible light image are lower than the details of the initial ultraviolet image, and the initial ultraviolet image is selected as the reference. In this way, the accuracy and effectiveness of the discharge detection are ensured.

[0085] Optionally, the initial visible light image is used as the reference image, and based on the position of the visible light camera and the position of the line component target, the distance between the visible light camera and the line component target is determined. Based on the distance, the initial visible light image is registered through corresponding registration processing to obtain a registered ultraviolet image.

[0086] Optionally, when the control unit of the lightweight gimbal verifies that the initial visible light image meets the requirements of the reference image, it uses the initial visible light image as the reference image, calls the first affine transformation matrix registration table, and registers the initial ultraviolet image based on the distance between the visible light camera and the line component target and the distance between the visible light camera and the ultraviolet camera to obtain a registered ultraviolet image.

[0087] Exemplarily, the step of determining the first affine transformation matrix registration table includes: obtaining a first image of the calibration plate taken by a visible light camera at each fixed distance, and a second image of the calibration plate taken by an ultraviolet camera at each fixed distance, and preprocessing the first image and the second image, the preprocessing operations sequentially including using a Wiener filtering algorithm to remove multiplicative noise and salt and pepper noise in the first image and the second image, using a median filtering algorithm to filter out Gaussian noise in the first image and the second image, and using a He algorithm (a defogging algorithm) to defog the first image and the second image to obtain the first image and the second image after defogging. A contour detection algorithm and a circle center detection algorithm are applied to calculate the coordinates of each pixel in the first image and the second image after dehazing. Then, based on the coordinates of each pixel in the first image after dehazing, the coordinates of each pixel in the first image after dehazing are calculated, and the calculated first image after dehazing is used as the first registered image. A random sampling consensus algorithm is applied to calculate the optimal affine transformation matrix with the first image as the reference image based on the first registered image, and a first affine transformation matrix registration table is constructed based on each distance and the corresponding optimal affine transformation matrix.

[0088] Step S508, based on the initial visible light image, a first visible light filtered image is obtained by visible light filtering, and the format of the registered ultraviolet image is converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by ultraviolet filtering.

[0089] The visible light filtering process may be at least one of least squares filtering and bilateral filtering. The preset format may be a YUV (Y represents brightness, that is, grayscale value; U and V represent chrominance) format. The ultraviolet filtering process may be least squares filtering.

[0090] Optionally, the control unit of the lightweight gimbal performs at least one of least square filtering and bilateral filtering on the initial visible light image to obtain a first visible light filtered image. The registered ultraviolet image is converted into a first ultraviolet conversion image in YUV format, and the first ultraviolet conversion image is subjected to least square filtering to obtain a first ultraviolet filtered image.

[0091] Exemplarily, the control unit of the lightweight gimbal performs least square filtering on the initial visible light image to obtain a first visible light filtered image. Alternatively, the lightweight gimbal performs bilateral filtering on the initial visible light image to obtain a first visible light filtered image. Alternatively, the lightweight gimbal performs least square filtering on the initial visible light image to obtain a first filtered sub-image, and performs bilateral filtering on the first filtered sub-image to obtain a second filtered sub-image. The first filtered sub-image and the second filtered sub-image are fused to obtain the first visible light filtered image.

[0092] In some embodiments, based on the initial visible light image, a first visible light filtered image is obtained through visible light filtering processing, including: performing least squares filtering processing on the initial visible light image to obtain a first filtered sub-image; performing bilateral filtering processing on the first filtered sub-image to obtain a second filtered sub-image, and the first filtered sub-image and the second filtered sub-image have the same image size; performing mean calculation on the pixel values ​​at the same pixel position in the first filtered sub-image and the second filtered sub-image to obtain the mean corresponding to each pixel position; and generating the first visible light filtered image based on the mean corresponding to each pixel position.

[0093] Exemplarily, after determining the first filter sub-image and the second filter sub-image, the control unit of the lightweight gimbal obtains, for each pixel position, a first pixel value of the pixel position from the first filter sub-image, obtains a second pixel value of the pixel position from the second filter sub-image, and averages the first pixel value and the second pixel value to obtain the average at the pixel position. A first visible light filter image is generated based on the average values ​​at each pixel.

[0094] In this embodiment, after two filterings, the corresponding first filtered sub-image and second filtered sub-image are obtained respectively, and more accurate pixel values ​​can be obtained by mean calculation to generate a more effective first visible light filtered image to ensure the effectiveness of subsequent discharge detection.

[0095] In some embodiments, based on the first ultraviolet conversion image, a first ultraviolet filtered image is obtained through ultraviolet filtering processing, including: performing channel separation on the first ultraviolet conversion image to obtain a channel ultraviolet image belonging to the target channel; performing least squares filtering on the channel ultraviolet image to obtain the first ultraviolet filtered image.

[0096] Exemplarily, the first ultraviolet conversion image is channel-separated to obtain a channel ultraviolet image of the Y channel, a channel ultraviolet image of the U channel, and a channel ultraviolet image of the V channel. A target channel is selected from the Y channel, the U channel, and the V channel, and the channel ultraviolet image of the target channel is subjected to least squares filtering to obtain a first ultraviolet filtered image.

[0097] Exemplarily, the information present in the channel ultraviolet image of the Y channel is more relevant to discharge detection, and thus the Y channel can be used as the target channel.

[0098] Exemplarily, when the channel ultraviolet image of the target channel is subjected to least squares filtering, a base sub-image and an ultraviolet filter sub-image are obtained, wherein the base sub-image can be regarded as a base sub-image.

[0099] In this embodiment, after converting the registered ultraviolet image into a first ultraviolet converted image in a preset format, ultraviolet filtering processing adapted to the ultraviolet image is performed to obtain a first ultraviolet filtered image that is more suitable for discharge detection, thereby ensuring the effectiveness of subsequent discharge detection.

[0100] Step S510, based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in the line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the preset actual size of the line component target, and the preset ranging parameters of the lightweight gimbal.

[0101] Exemplarily, a preset first image fusion mode and a preset second image fusion mode are obtained, wherein the first image fusion mode is a fusion mode based on the space domain or the frequency domain, and the second image fusion mode is a fusion mode based on the discharge area.

[0102] The control unit of the lightweight pan / tilt head selects a target fusion mode from the first image fusion mode and the second image fusion mode, and performs image fusion according to the target fusion mode based on the first visible light filter image and the first ultraviolet filter image to obtain a first detection image. According to the first detection image, a discharge detection is performed on the line component target to determine whether there is a discharge phenomenon in the line component target, and if so, the actual discharge intensity on the line component target is further determined.

[0103] Specifically, when it is determined based on the first detection image that a discharge phenomenon exists in the line component target, the preset actual size of the detected line component target and the preset ranging parameters of the lightweight pan-tilt are obtained. Thus, according to the line component target size in the first visible light filtered image, the preset actual size of the line component target, and the preset ranging parameters of the lightweight pan-tilt, the distance between the lens of the visible light camera and the line component target, and the distance between the lens of the ultraviolet camera and the line component target are determined.

[0104] Therefore, the actual discharge intensity is subsequently determined based on the determined distance between the lens of the ultraviolet camera and the circuit component target.

[0105] The following introduces the process of image fusion using the first image fusion method. In some embodiments, the first ultraviolet filtered image includes a base sub-image and an ultraviolet filtered sub-image. Based on the first visible light filtered image and the first ultraviolet filtered image, an image fusion process is performed to obtain a first detection image, including: based on the first visible light filtered image and the ultraviolet filtered sub-image, an intermediate fused image is obtained through domain fusion processing, and the domain fusion process includes one of time domain fusion and frequency domain fusion; the base sub-image and the intermediate fused image are superimposed to obtain the first detection image.

[0106] Among them, the domain fusion processing can be spatial domain fusion or frequency domain fusion. Among them, spatial domain fusion includes alpha fusion (a fusion method based on transparency), pyramid fusion, image Poisson fusion, IHS (Intensity, Hue, Saturation) fusion and PCA (Principal Component Analysis) fusion. Frequency domain fusion methods include DCT (Discrete Cosine Transform) fusion and wavelet fusion.

[0107] Exemplarily, after the intermediate fusion image is obtained, the pixel values ​​at the same pixel position in the base sub-image and the intermediate fusion image are superimposed to obtain the sum value corresponding to each pixel position. Based on each sum value, a superimposed image is generated, and the superimposed image is converted into RGB format to obtain the first detection image.

[0108] In this embodiment, the first visible light filter image and the first ultraviolet filter image are effectively fused by domain fusion, thereby ensuring the effectiveness of subsequent line discharge intensity detection.

[0109] The following introduces the process of image fusion using the second image fusion method. In some embodiments, the first ultraviolet filtered image includes a base sub-image and an ultraviolet filtered sub-image. Based on the first visible light filtered image and the first ultraviolet filtered image, a first detection image is obtained through image fusion processing, including: performing format conversion on the first visible light filtered image according to a preset format to obtain a first visible light converted image; performing region identification on the discharge region in the ultraviolet filtered sub-image to obtain a discharge region image; performing channel separation on the first visible light converted image to obtain a channel visible light image belonging to the target channel; and fusing the channel visible light image, the discharge region image and the base sub-image to obtain the first detection image.

[0110] Exemplarily, the first visible light filter image is converted into an image in YUV format to obtain a first visible light conversion image. The discharge area in the ultraviolet filter sub-image is identified to obtain a discharge area image. The first visible light conversion image is channel-separated to obtain a channel visible light image of the Y channel, a channel visible light image of the U channel, and a channel visible light image of the Y channel. The Y channel is used as the target channel, and the channel visible light image of the Y channel is fused with the discharge area image to obtain an intermediate fused registration image, and the intermediate fused registration image and the base sub-image are superimposed to obtain a first detection image.

[0111] Exemplarily, a base wavelet is selected to perform single-scale wavelet transform on the discharge area image and the channel visible light image of the Y channel, respectively obtaining a transformed discharge area image and a transformed channel visible light image, and frequency classification of the two transformed images is performed for weighted averaging to obtain a fused transformed registered image; an inverse wavelet transform is performed on the fused transformed registered image to obtain a fused registered Y channel area, and the fused registered Y channel area is used to replace the discharge area corresponding to the channel visible light image of the Y channel to obtain an intermediate fused registered image.

[0112] Exemplarily, a discharge area recognition model based on a neural network is obtained, and the ultraviolet filter sub-image is input into the discharge area recognition model to obtain a discharge area image.

[0113] Exemplarily, the maximum inter-class variance method is applied to determine the pixel threshold between the discharge area and the background area in the ultraviolet filter sub-image. For each pixel position in the ultraviolet filter sub-image, the pixel value at the pixel position is compared with the pixel threshold to determine a comparison result, which indicates whether the pixel position is the position of the discharge area. According to the comparison results of each pixel position, the discharge area image in the ultraviolet filter sub-image is obtained.

[0114] Exemplarily, after the intermediate fused registration image and the base sub-image are superimposed to obtain a corresponding superimposed image, the superimposed image is converted into an image in RGB format to obtain a first detection image.

[0115] In this embodiment, the discharge area in the ultraviolet filter sub-image is effectively identified through a fusion method based on the discharge area, so that after the fusion is completed, the detail information of the discharge area in the first detection image is more prominent, ensuring the accuracy of subsequent discharge detection.

[0116] Step S512, determining the actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target.

[0117] Exemplarily, the actual discharge intensity on the line component target is determined based on the number of ultraviolet photons within the line component target range contained in the first ultraviolet filtered image, the magnification, ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target.

[0118] Step S514: when it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

[0119] Exemplarily, when the PTZ determines that the actual discharge intensity is greater than the threshold intensity corresponding to the discharge defect, it determines that a discharge defect occurs in the target power transmission circuit, and determines a matching alarm level based on the type of the discharge defect, and sends an alarm prompt message corresponding to the alarm level.

[0120] In the above-mentioned line discharge intensity detection method, a lightweight pan / tilt is applied. When a line component target is detected in the current scene, the detection is confirmed to be turned on, and the pitch angles of the ultraviolet camera and the visible light camera are pre-checked to obtain the first pitch angle and the second pitch angle that match each other, which can ensure that the target transmission line is accurately photographed, thereby obtaining the initial ultraviolet image and the initial visible light image. When the initial visible light image is verified to meet the requirements of the reference image, that is, the initial visible light image with richer information is pre-checked and can be used as a registration reference, and the initial visible light image is subjected to target detection to accurately detect the line component target and the position of the line component target. Taking the initial visible light image as the reference image, the initial ultraviolet image is registered based on the distance between the visible light camera and the line component target to obtain a registered ultraviolet image; based on the initial visible light image, a first visible light filtered image is obtained through visible light filtering, and the registered ultraviolet image is converted into a first ultraviolet conversion image according to a preset format, and based on the first ultraviolet conversion image, a first ultraviolet filtered image is obtained through ultraviolet filtering; based on the first visible light filtered image and the first ultraviolet filtered image, a first detection image is obtained through image fusion processing. In the case that the line component target is determined to have a discharge phenomenon based on the first detection image, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filtered image, the line component target preset actual size, and the preset ranging parameters of the lightweight pan-tilt head. Based on the first ultraviolet filtered image, ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target, the actual discharge intensity on the line component target can be accurately identified. Based on this, it is possible to more accurately verify whether there is a discharge defect, thereby improving the accuracy of discharge detection. When a discharge defect is detected in the line component target according to the actual discharge intensity, an alarm prompt message corresponding to the discharge defect is automatically issued, thereby enabling timely early warning. Under the premise of ensuring the accuracy of line discharge intensity detection, automated processing and automated alarms are used throughout the process, eliminating the need for manual inspections by inspection personnel, thereby improving the efficiency of line discharge intensity detection.

[0121] In some embodiments, the method also includes: when it is verified that the initial visible light image does not meet the requirements of the reference image, using the initial ultraviolet image as the reference image, and based on the distance between the ultraviolet camera and the line component target, aligning the initial visible light image to obtain a registered visible light image; based on the registered visible light image, performing visible light filtering processing to obtain a second visible light filtered image, performing format conversion on the initial ultraviolet image according to a preset format to obtain a second ultraviolet converted image, and based on the second ultraviolet converted image, performing ultraviolet filtering processing to obtain a second ultraviolet filtered image; based on the second visible light filtered image and the second ultraviolet filtered image, performing image fusion processing to obtain a second detection image, and determining whether there is a discharge phenomenon in the line component target based on the second detection image.

[0122] Exemplarily, the initial ultraviolet image is used as the reference image, the second affine transformation matrix registration table is called, and the initial visible light image is registered based on the distance between the ultraviolet camera and the line component target and the distance between the ultraviolet camera and the visible light camera to obtain the registered visible light image.

[0123] Exemplarily, the registered visible light image is least square filtered to obtain a third filtered sub-image; the third filtered sub-image is bilaterally filtered to obtain a fourth filtered sub-image, and the third filtered sub-image and the fourth filtered sub-image have the same image size; the pixel values ​​at the same pixel position in the third filtered sub-image and the fourth filtered sub-image are mean calculated to obtain the mean corresponding to each pixel position; based on the mean corresponding to each pixel position, a second visible light filtered image is generated.

[0124] Exemplarily, the second ultraviolet conversion image is subjected to channel separation to obtain a channel initial ultraviolet image belonging to the target channel; and the channel initial ultraviolet image is subjected to least squares filtering to obtain a second ultraviolet filtered image.

[0125] Exemplarily, the second UV-converted image includes other base sub-images and other UV-filtered sub-images.

[0126] Exemplarily, the process of image fusion using domain fusion is as follows: based on the second visible light filtered image and other ultraviolet filtered sub-images, other intermediate fused images are obtained through domain fusion processing, and the domain fusion processing includes one of time domain fusion and frequency domain fusion; other base sub-images and other intermediate fused images are superimposed to obtain a second detection image.

[0127] Exemplarily, the process of image fusion using the discharge area-based fusion method is as follows:

[0128] According to a preset format, the second visible light filter image is format converted to obtain a second visible light conversion image; the discharge area in other ultraviolet filter sub-images is region identified to obtain other discharge area images; the second visible light conversion image is channel separated to obtain a channel visible light conversion image belonging to the target channel; the channel visible light conversion image, other discharge area images and other substrate sub-images are fused to obtain a second detection image.

[0129] For example, the target channel may be a Y channel and the preset format may be a YUV image.

[0130] Exemplarily, the process of fusing the channel visible light conversion image, other discharge area images and other substrate sub-images to obtain the second detection image is similar to the method of fusing the channel visible light image, the discharge area image and the substrate sub-image to obtain the first detection image as mentioned above, and reference may be made to the above text.

[0131] In this embodiment, when it is determined that the initial visible light image does not meet the reference image requirements, the initial ultraviolet image contains more information and discharge details, so the initial ultraviolet image is used as a reference for registration, thereby performing image fusion, which can ensure the accuracy of image fusion.

[0132] In a specific embodiment, the line discharge intensity detection method is applied to a lightweight gimbal, and the specific implementation process is as follows: the ultraviolet camera and the visible light camera on the drone simultaneously shoot the target transmission line, and obtain the initial ultraviolet image captured by the ultraviolet camera and the initial visible light image captured by the visible light camera. The ultraviolet camera and the visible light camera on the drone send the initial ultraviolet image and the initial visible light image to the lightweight gimbal respectively. The following process is performed by the lightweight gimbal:

[0133] In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are obtained, wherein the initial ultraviolet image is obtained by photographing the target transmission line with an ultraviolet camera at a matching first pitch angle, and the initial visible light image is obtained by photographing the target transmission line with a visible light camera at a matching second pitch angle. The resolution of the initial ultraviolet image and the resolution of the initial visible light image are determined; if the resolution of the initial ultraviolet image is less than or equal to the resolution of the initial visible light image, it is determined that the initial visible light image meets the reference image requirements; if the resolution of the initial ultraviolet image is greater than the resolution of the initial visible light image, it is determined that the initial visible light image does not meet the reference image requirements.

[0134] When it is verified that the initial visible light image meets the requirements of the reference image, the initial visible light image is used as the reference image, and the initial ultraviolet image is registered based on the distance between the visible light camera and the line component target to obtain the registered ultraviolet image. The initial visible light image is least square filtered to obtain a first filtered sub-image; the first filtered sub-image is bilaterally filtered to obtain a second filtered sub-image, and the image sizes of the first filtered sub-image and the second filtered sub-image are the same; the pixel values ​​at the same pixel position in the first filtered sub-image and the second filtered sub-image are averaged to obtain the mean corresponding to each pixel position; based on the mean corresponding to each pixel position, the first visible light filtered image is generated. The first ultraviolet conversion image is channel separated to obtain a channel ultraviolet image belonging to the target channel; the channel ultraviolet image is least square filtered to obtain a first ultraviolet filtered image. The first ultraviolet filtered image includes a base sub-image and an ultraviolet filtered sub-image.

[0135] Subsequently, based on the first visible light filter image and the ultraviolet filter sub-image, an intermediate fused image is obtained through domain fusion processing, and the domain fusion processing includes one of time domain fusion and frequency domain fusion; the base sub-image and the intermediate fused image are superimposed to obtain a first detection image.

[0136] Alternatively, the first visible light filter image is format converted according to a preset format to obtain a first visible light conversion image; the discharge area in the ultraviolet filter sub-image is region identified to obtain a discharge area image; the first visible light conversion image is channel separated to obtain a channel visible light image belonging to the target channel; the channel visible light image, the discharge area image and the substrate sub-image are fused to obtain a first detection image.

[0137] When it is verified that the initial visible light image meets the requirements of the reference image, target detection is performed on the initial visible light image to determine the position of the line component target and the line component target; the initial visible light image is used as the reference image, and based on the distance between the visible light camera and the line component target, the initial ultraviolet image is registered to obtain a registered ultraviolet image; based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering; based on the first visible light filtering The image and the first ultraviolet filtered image are processed by image fusion to obtain a first detection image. When it is determined that the line component target has a discharge phenomenon based on the first detection image, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filtered image, the preset actual size of the line component target, and the preset ranging parameters of the lightweight pan / tilt. The actual discharge intensity on the line component target is determined based on the first ultraviolet filtered image, the ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target. When it is verified that the line component target has a discharge defect based on the actual discharge intensity, an alarm prompt information corresponding to the discharge defect is issued.

[0138] When it is verified that the initial visible light image does not meet the requirements of the reference image, the initial ultraviolet image is used as the reference image, and the initial visible light image is registered based on the distance between the ultraviolet camera and the target transmission line to obtain the registered visible light image. The registered visible light image is subjected to least squares filtering to obtain a third filtered sub-image; the third filtered sub-image is subjected to bilateral filtering to obtain a fourth filtered sub-image, and the image sizes of the third filtered sub-image and the fourth filtered sub-image are the same; the pixel values ​​at the same pixel position in the third filtered sub-image and the fourth filtered sub-image are averaged to obtain the mean corresponding to each pixel position; based on the mean corresponding to each pixel position, a second visible light filtered image is generated. The second ultraviolet converted image is channel separated to obtain the channel initial ultraviolet image belonging to the target channel; the channel initial ultraviolet image is subjected to least squares filtering to obtain the second ultraviolet filtered image.

[0139] Next, the process of image fusion using domain fusion is as follows: based on the second visible light filtered image and other ultraviolet filtered sub-images, other intermediate fused images are obtained through domain fusion processing, and the domain fusion processing includes one of time domain fusion and frequency domain fusion; other base sub-images and other intermediate fused images are superimposed to obtain a second detection image.

[0140] Alternatively, the second visible light filter image is format converted according to a preset format to obtain a second visible light conversion image; the discharge area in other ultraviolet filter sub-images is region identified to obtain other discharge area images; the second visible light conversion image is channel separated to obtain a channel visible light conversion image belonging to the target channel; the channel visible light conversion image, other discharge area images and other substrate sub-images are fused to obtain a second detection image. Based on the second detection image, it is determined whether there is a discharge phenomenon in the line component target. If so, it is further determined whether a discharge defect occurs based on the actual discharge intensity of the line component target. If so, a corresponding alarm prompt information is issued.

[0141] In this embodiment, a lightweight pan / tilt is used. When a line component target is detected in the current scene, the detection is confirmed to be turned on, and the pitch angles of the ultraviolet camera and the visible light camera are pre-checked to obtain the first pitch angle and the second pitch angle that match each other, so as to ensure that the target power transmission line is accurately photographed, thereby obtaining the initial ultraviolet image and the initial visible light image. When the initial visible light image is verified to meet the requirements of the reference image, that is, the initial visible light image with richer information is pre-checked and can be used as a registration reference, and the initial visible light image is subjected to target detection to accurately detect the line component target and the position of the line component target. Taking the initial visible light image as the reference image, the initial ultraviolet image is registered based on the distance between the visible light camera and the line component target to obtain a registered ultraviolet image; based on the initial visible light image, a first visible light filtered image is obtained through visible light filtering, and the registered ultraviolet image is converted into a first ultraviolet conversion image according to a preset format, and based on the first ultraviolet conversion image, a first ultraviolet filtered image is obtained through ultraviolet filtering; based on the first visible light filtered image and the first ultraviolet filtered image, a first detection image is obtained through image fusion processing. In the case that the line component target is determined to have a discharge phenomenon based on the first detection image, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filtered image, the line component target preset actual size, and the preset ranging parameters of the lightweight pan-tilt head. Based on the first ultraviolet filtered image, ultraviolet camera parameters, and the distance between the ultraviolet camera and the line component target, the actual discharge intensity on the line component target can be accurately identified. Based on this, it is possible to more accurately verify whether there is a discharge defect, thereby improving the accuracy of discharge detection. When a discharge defect is detected in the line component target according to the actual discharge intensity, an alarm prompt message corresponding to the discharge defect is automatically issued, thereby enabling timely early warning. Under the premise of ensuring the accuracy of line discharge intensity detection, automated processing and automated alarms are performed throughout the process, and there is no need for patrol personnel to conduct manual inspections, thereby improving the efficiency of line discharge intensity detection. It should be understood that although the various steps in the flowcharts involved in the various embodiments described above are displayed in sequence as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the steps or stages in other steps.

[0142] Based on the same inventive concept, the embodiment of the present application also provides a line discharge intensity detection device for implementing the line discharge intensity detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more line discharge intensity detection device embodiments provided below can refer to the limitations of the line discharge intensity detection method above, and will not be repeated here.

[0143] In an exemplary embodiment, Figure 6 As shown, a line discharge intensity detection device 600 is provided, comprising: an image acquisition module 602, a target detection module 604, an image registration module 606, an image filtering module 608, a distance determination module 610, an intensity determination module 612 and an information sending module 614, wherein:

[0144] An image acquisition module 602 is used to acquire an initial ultraviolet image and an initial visible light image when a line component target is detected in the current scene, wherein the initial ultraviolet image is obtained by photographing the target transmission line with an ultraviolet camera at a matching first pitch angle, and the initial visible light image is obtained by photographing the target transmission line with a visible light camera at a matching second pitch angle;

[0145] The target detection module 604 is used to perform target detection on the initial visible light image to determine the line component target and the position of the line component target when the initial visible light image is verified to meet the reference image requirement;

[0146] An image registration module 606 is used to register the initial ultraviolet image based on the distance between the visible light camera and the line component target using the initial visible light image as a reference image to obtain a registered ultraviolet image;

[0147] The image filtering module 608 is used to obtain a first visible light filtered image by performing visible light filtering processing based on the initial visible light image, and to convert the format of the registered ultraviolet image into a preset format to obtain a first ultraviolet converted image, and to obtain a first ultraviolet filtered image by performing ultraviolet filtering processing based on the first ultraviolet converted image;

[0148] The distance determination module 610 is used to obtain a first detection image through image fusion processing based on the first visible light filter image and the first ultraviolet filter image, and determine the distance between the ultraviolet camera and the line component target based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan-tilt preset ranging parameters when it is determined that the line component target has a discharge phenomenon based on the first detection image;

[0149] An intensity determination module 612, for determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target;

[0150] The information issuing module 614 is used to issue an alarm prompt information corresponding to the discharge defect when a discharge defect is detected in a line component target according to the actual discharge intensity.

[0151] In some embodiments, the device also includes a requirement determination module, which is used to determine the resolution of the initial ultraviolet image and the resolution of the initial visible light image; when the resolution of the initial ultraviolet image is less than or equal to the resolution of the initial visible light image, it is determined that the initial visible light image meets the baseline image requirement; when the resolution of the initial ultraviolet image is greater than the resolution of the initial visible light image, it is determined that the initial visible light image does not meet the baseline image requirement.

[0152] In some embodiments, the image filtering module 608 is used to perform least squares filtering on the initial visible light image to obtain a first filtered sub-image; perform bilateral filtering on the first filtered sub-image to obtain a second filtered sub-image, and the image sizes of the first filtered sub-image and the second filtered sub-image are the same; perform mean calculation on the pixel values ​​at the same pixel position in the first filtered sub-image and the second filtered sub-image to obtain the mean corresponding to each pixel position; generate a first visible light filtered image based on the mean corresponding to each pixel position; the image filtering module 608 is used to perform channel separation on the first ultraviolet conversion image to obtain a channel ultraviolet image belonging to the target channel; perform least squares filtering on the channel ultraviolet image to obtain a first ultraviolet filtered image.

[0153] In some embodiments, the first ultraviolet filtered image includes a base sub-image and an ultraviolet filtered sub-image, and the intensity determination module 612 is used to obtain an intermediate fused image through domain fusion processing based on the first visible light filtered image and the ultraviolet filtered sub-image, and the domain fusion processing includes one of time domain fusion and frequency domain fusion; superimpose the base sub-image and the intermediate fused image to obtain a first detection image.

[0154] In some embodiments, the first ultraviolet filtered image includes a base sub-image and an ultraviolet filtered sub-image, and the intensity determination module 612 is used to convert the format of the first visible light filtered image according to a preset format to obtain a first visible light converted image; perform region identification on the discharge region in the ultraviolet filtered sub-image to obtain a discharge region image; perform channel separation on the first visible light converted image to obtain a channel visible light image belonging to the target channel; and fuse the channel visible light image, the discharge region image and the base sub-image to obtain a first detection image.

[0155] In some embodiments, the image registration module 606 is also used to, when it is verified that the initial visible light image does not meet the requirements of the reference image, use the initial ultraviolet image as the reference image, and based on the distance between the ultraviolet camera and the line component target, register the initial visible light image to obtain a registered visible light image; the image filtering module 608 is also used to obtain a second visible light filtered image through visible light filtering based on the registered visible light image, convert the format of the initial ultraviolet image according to a preset format to obtain a second ultraviolet converted image, and based on the second ultraviolet converted image, obtain a second ultraviolet filtered image through ultraviolet filtering; the intensity determination module 612 is also used to obtain a second detection image through image fusion based on the second visible light filtered image and the second ultraviolet filtered image, and determine whether there is a discharge phenomenon in the line component target according to the second detection image.

[0156] Each module in the above-mentioned line discharge intensity detection device can be implemented in whole or in part by software, hardware or a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the corresponding operations of each module.

[0157] In an exemplary embodiment, a computer device is provided. The computer device is the aforementioned lightweight pan-tilt head. The lightweight pan-tilt head may also be a terminal. The internal structure diagram thereof may be as shown in FIG. Figure 7 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a line discharge intensity detection method is implemented.

[0158] Those skilled in the art will understand that Figure 7 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0159] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0160] 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 steps in the above-mentioned method embodiments are implemented.

[0161] In one embodiment, a computer program product is provided, including a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0162] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0163] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. 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). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0164] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0165] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting line discharge intensity, characterized in that: Applied to a lightweight gimbal, the method comprises: In the case where a line component target is detected in the current scene, an initial ultraviolet image and an initial visible light image are acquired, wherein the initial ultraviolet image is acquired by an ultraviolet camera photographing the target transmission line at a matching first pitch angle, and the initial visible light image is acquired by a visible light camera photographing the target transmission line at a matching second pitch angle; When it is verified that the initial visible light image meets the reference image requirement, performing target detection on the initial visible light image to determine the line component target and the position of the line component target; Taking the initial visible light image as a reference image, and based on the distance between the visible light camera and the line component target, registering the initial ultraviolet image to obtain a registered ultraviolet image; Based on the initial visible light image, a first visible light filtered image is obtained by performing visible light filtering processing, and the registered ultraviolet image is format-converted according to a preset format to obtain a first ultraviolet converted image, and based on the first ultraviolet converted image, a first ultraviolet filtered image is obtained by performing ultraviolet filtering processing; Based on the first visible light filter image and the first ultraviolet filter image, a first detection image is obtained through image fusion processing. When it is determined based on the first detection image that a discharge phenomenon exists in a line component target, the distance between the ultraviolet camera and the line component target is determined based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters; Determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target; When it is verified according to the actual discharge intensity that a discharge defect occurs in the line component target, an alarm prompt information corresponding to the discharge defect is issued.

2. The method according to claim 1, characterized in that: The method further comprises: Determining a resolution of the initial ultraviolet image and a resolution of the initial visible light image; In a case where the resolution of the initial ultraviolet image is less than or equal to the resolution of the initial visible light image, determining that the initial visible light image meets the reference image requirement; When the resolution of the initial ultraviolet image is greater than the resolution of the initial visible light image, it is determined that the initial visible light image does not meet the reference image requirement.

3. The method according to claim 1, characterized in that: The step of obtaining a first visible light filtered image by performing visible light filtering based on the initial visible light image comprises: Performing least squares filtering on the initial visible light image to obtain a first filtered sub-image; Performing bilateral filtering on the first filtered sub-image to obtain a second filtered sub-image, wherein the first filtered sub-image and the second filtered sub-image have the same image size; Calculating the mean of pixel values ​​at the same pixel position in the first filtered sub-image and the second filtered sub-image to obtain the mean corresponding to each pixel position; Generate a first visible light filtered image based on the mean value corresponding to each pixel position; The method of obtaining a first ultraviolet filtered image by ultraviolet filtering based on the first ultraviolet converted image comprises: Performing channel separation on the first ultraviolet conversion image to obtain a channel ultraviolet image belonging to a target channel; The channel ultraviolet image is subjected to least squares filtering to obtain a first ultraviolet filtered image.

4. The method according to claim 1, characterized in that: The first ultraviolet filter image includes a base sub-image and an ultraviolet filter sub-image, and the first detection image is obtained by image fusion processing based on the first visible light filter image and the first ultraviolet filter image, including: Based on the first visible light filtered image and the ultraviolet filtered sub-image, an intermediate fused image is obtained by performing domain fusion processing, wherein the domain fusion processing includes one of time domain fusion and frequency domain fusion; The base sub-image and the intermediate fused image are superimposed to obtain a first detection image.

5. The method according to claim 1, characterized in that The first ultraviolet filter image includes a base sub-image and an ultraviolet filter sub-image, and the first detection image is obtained by image fusion processing based on the first visible light filter image and the first ultraviolet filter image, including: Performing format conversion on the first visible light filtered image according to a preset format to obtain a first visible light converted image; Performing region recognition on the discharge region in the ultraviolet filter sub-image to obtain a discharge region image; Performing channel separation on the first visible light converted image to obtain a channel visible light image belonging to a target channel; The channel visible light image, the discharge area image and the substrate sub-image are fused to obtain a first detection image.

6. The method according to claim 1, characterized in that The method further comprises: When it is verified that the initial visible light image does not meet the reference image requirement, the initial ultraviolet image is used as the reference image, and based on the distance between the ultraviolet camera and the circuit component target, the initial visible light image is registered to obtain a registered visible light image; Based on the registered visible light image, a second visible light filtered image is obtained by performing visible light filtering, the initial ultraviolet image is format-converted according to a preset format to obtain a second ultraviolet converted image, and based on the second ultraviolet converted image, a second ultraviolet filtered image is obtained by performing ultraviolet filtering; Based on the second visible light filter image and the second ultraviolet filter image, a second detection image is obtained through image fusion processing, and according to the second detection image, it is determined whether there is a discharge phenomenon in the line component target.

7. A line discharge intensity detection device, characterized in that: The device comprises: An image acquisition module, for acquiring an initial ultraviolet image and an initial visible light image when a line component target is detected in the current scene, wherein the initial ultraviolet image is obtained by photographing the target transmission line with an ultraviolet camera at a matching first pitch angle, and the initial visible light image is obtained by photographing the target transmission line with a visible light camera at a matching second pitch angle; A target detection module, configured to perform target detection on the initial visible light image to determine the line component target and the position of the line component target when it is verified that the initial visible light image meets the reference image requirement; An image registration module, configured to register the initial ultraviolet image based on the distance between the visible light camera and the circuit component target, using the initial visible light image as a reference image, to obtain a registered ultraviolet image; An image filtering module, configured to obtain a first visible light filtered image by performing visible light filtering processing based on the initial visible light image, and to perform format conversion on the registered ultraviolet image according to a preset format to obtain a first ultraviolet converted image, and to obtain a first ultraviolet filtered image by performing ultraviolet filtering processing based on the first ultraviolet converted image; a distance determination module, configured to obtain a first detection image through image fusion processing based on the first visible light filter image and the first ultraviolet filter image, and determine the distance between the ultraviolet camera and the line component target based on the line component target size in the first visible light filter image, the line component target preset actual size, and the lightweight pan / tilt preset ranging parameters, when it is determined that the line component target has a discharge phenomenon based on the first detection image; an intensity determination module, for determining an actual discharge intensity on the line component target based on the first ultraviolet filtered image, ultraviolet camera parameters, and a distance between the ultraviolet camera and the line component target; The information issuing module is used to issue an alarm prompt information corresponding to the discharge defect when a discharge defect is detected in the line component target according to the actual discharge intensity.

8. 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 6 are implemented.

9. 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 6 are implemented.

10. A computer program product, comprising a computer program, 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 6 are implemented.

Images