Power transmission line insulator defect identification method and system based on unmanned aerial vehicle inspection
By constructing a dynamic mapping relationship and an adaptive filtering mechanism, the impact of lighting and various meteorological interferences on insulator inspection was resolved, achieving high-quality image reconstruction and defect identification, and improving inspection accuracy and efficiency.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-12-26
- Publication Date
- 2026-04-07
Smart Images
Figure CN121811283A_ABST
Abstract
Description
Technical Field
[0001] This invention belongs to the field of UAV and machine vision technology, specifically relating to a method and system for identifying defects in power transmission line insulators based on UAV inspection. Background Technology
[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.
[0003] Insulator inspections of high-voltage transmission lines can be completed using drones equipped with both infrared and conventional cameras. The infrared camera acquires thermal imaging data of the insulators to detect any temperature anomalies, while the conventional camera acquires visible light images to clearly show the insulators' physical condition (such as cracks, dirt, and damage). However, in actual inspection tasks, the following key challenges are typically encountered: (1) Temperature anomalies caused by sunlight: Direct sunlight causes uneven temperature distribution on the surface of insulators, with the temperature in the directly exposed areas being significantly higher than that in the shaded areas, seriously affecting the temperature accuracy of infrared images. The geometry and installation position of insulators cause dynamic changes in the angle and intensity of sunlight, forming a complex spatial temperature gradient. This spatial temperature gradient makes it difficult for infrared images to distinguish between real temperature anomalies (such as overheating caused by internal faults in insulators) and surface temperature fluctuations caused by sunlight. Under strong sunlight, the temperature detection accuracy of traditional infrared inspection methods is significantly reduced, leading to a sharp decline in the detection rate of insulator faults, which seriously threatens the safe operation of the power grid. Especially during the midday hours in summer, the surface temperature difference of insulators is significant, causing a large number of misjudgments and missed detections, further exacerbating the risks to power grid operation.
[0004] (2) Severe weather interference: Images often face complex environments such as strong light, strong winds, rain, and fog, leading to complex degradation such as fogging and overexposure. In strong light, overexposure causes loss of detail; in rain and fog, image contrast decreases and becomes blurry, affecting the detection of anomalies. Under rain and fog conditions, the processing effect of traditional image enhancement methods is significantly reduced, resulting in a substantial decrease in the recognition rate of surface defects on insulators. The complex superposition of meteorological conditions makes it impossible for a single degradation model to cope effectively, leading to low inspection efficiency and increased workload for manual re-inspection.
[0005] (3) Traditional image processing methods (such as frequency domain filtering and histogram equalization) rely on manually designed features and cannot adapt to changing environments; existing methods mostly focus on a single degradation type and lack the ability to jointly model and decouple composite degradation; under the superposition of multiple meteorological conditions, traditional methods often fail and cannot meet the dual requirements of accuracy and real-time performance for high-voltage insulator inspection.
[0006] Therefore, there is an urgent need for an image enhancement method for UAV inspections that can integrate multiple interference sensing and deep learning technologies, possess dynamic structural adaptability, and support high-quality image reconstruction, in order to efficiently identify defects in transmission line insulators. Summary of the Invention
[0007] To address the aforementioned issues, this invention proposes a method and system for identifying insulator defects in transmission lines based on unmanned aerial vehicle (UAV) inspection. It employs a self-attention-based adaptive filtering mechanism to construct a dynamic mapping relationship between meteorological conditions and image degradation. This solves the problem of temperature anomalies caused by illumination and the impact of severe weather conditions on insulator image inspection during high-voltage transmission line insulator inspections. It achieves joint decoupling and image reconstruction of various meteorological interferences, significantly improving the accuracy and efficiency of insulator defect identification and inspection.
[0008] According to some embodiments, the first aspect of the present invention provides a method for identifying defects in transmission line insulators based on unmanned aerial vehicle (UAV) inspection, employing the following technical solution: A method for identifying defects in transmission line insulators based on unmanned aerial vehicle (UAV) inspection includes: Real-time images and temperatures of insulators on power transmission lines to be identified were obtained using drones. Based on the real-time temperature of the transmission line insulator and the multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information, the predicted temperature of the transmission line insulator is calculated. The predicted temperature and the real-time temperature of the insulator are corrected to obtain the corrected predicted temperature result. Adaptive filtering is used to enhance the acquired real-time images of transmission line insulators, resulting in enhanced images of transmission line insulators. Based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, defects in transmission line insulators are identified, and defect identification of transmission line insulators based on UAV inspection is completed.
[0009] As a further technical limitation, the solar radiation intensity is considered in the process of calculating the predicted temperature of transmission line insulators. Absorption rate of insulator surface material Calculate each pixel Temperature rise caused by solar radiation ,Right now ;in, Thermal conductivity, calibrated based on the insulator structure and material properties; based on the temperature rise caused by solar radiation. and real-time temperature Calculate the predicted temperature at each pixel location. ,Right now ;Calculate the temperature deviation between the calculated surface temperature and the predicted temperature ,Right now ;in This refers to the surface temperature of the insulator.
[0010] Furthermore, based on the obtained temperature deviation, attention weights are calculated using an activation function. ,Right now ;in, and All are learnable parameters. The sigmoid activation function is used; the obtained attention weights are applied to the feature map of the infrared image (from the feature extraction layer of the convolutional neural network) to obtain the weighted feature map. ,Right now ;in Indicates the feature channel index; the obtained weighted feature map and neural network layer are used to predict the actual temperature of transmission line insulators. ,Right now MLP stands for Multilayer Perceptron.
[0011] Furthermore, the predicted temperature correction result for ;in, This represents the meteorological attenuation factor, i.e. ; The value represents a percentage of relative humidity. Rainfall intensity, Fog concentration, These represent the coefficients used to balance the effects of different meteorological conditions.
[0012] As a further technical limitation, the image enhancement of the acquired real-time images of transmission line insulators using adaptive filtering includes at least the construction of a degradation model, generation of a filter kernel, and optimization of image enhancement.
[0013] As a further technical limitation, after acquiring a real-time image of the transmission line insulator to be identified, the acquired real-time image is preprocessed to obtain a preprocessed image of the transmission line insulator; the preprocessing includes at least image size unification and image normalization processing.
[0014] According to some embodiments, the second aspect of the present invention provides a transmission line insulator defect identification system based on UAV inspection, which adopts the following technical solution: A defect identification system for power transmission line insulators based on drone inspection includes: The acquisition module is configured to acquire real-time images and real-time temperatures of the insulators of the transmission line to be identified based on the UAV. The prediction module is configured to calculate the predicted temperature of the transmission line insulator based on the real-time temperature of the acquired transmission line insulator and a multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information. The correction module is configured to correct the obtained predicted temperature and the acquired real-time temperature of the insulator to obtain the predicted temperature correction result. An enhancement module is configured to perform image enhancement on the acquired real-time image of the transmission line insulator using adaptive filtering to obtain an enhanced image of the transmission line insulator. The identification module is configured to identify defects in transmission line insulators based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, thus completing the identification of transmission line insulator defects based on UAV inspection.
[0015] According to some embodiments, a third aspect of the present invention provides a computer-readable storage medium, employing the following technical solution: A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the method for identifying defects in transmission line insulators based on UAV inspection as described in the first aspect of the present invention.
[0016] According to some embodiments, the fourth aspect of the present invention provides an electronic device, which adopts the following technical solution: An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the method for identifying defects in transmission line insulators based on UAV inspection as described in the first aspect of the present invention.
[0017] According to some embodiments, the fifth aspect of the present invention provides a computer program product, which adopts the following technical solution: A computer program product includes software code, wherein the program in the software code performs the steps of the method for identifying defects in transmission line insulators based on UAV inspection as described in the first aspect of the present invention.
[0018] Compared with the prior art, the beneficial effects of the present invention are as follows: This invention constructs a multimodal interference sensing and temperature prediction mechanism to effectively correct the uneven temperature distribution on the surface of insulators caused by illumination, accurately distinguish between real temperature anomalies and external illumination interference, thereby significantly improving the accuracy and reliability of infrared temperature detection and enhancing the ability to identify potential faults in insulators.
[0019] This invention establishes a joint degradation model for various meteorological conditions such as rain, fog, and strong light, and designs a meteorological impact adversarial modeling framework. This framework can adaptively suppress the degradation effect of combined meteorological conditions on image quality, significantly improve image clarity and detail retention, improve the quality of inspection images under severe weather conditions, and effectively suppress combined meteorological interference.
[0020] This invention introduces a self-attention-based adaptive filtering mechanism to dynamically establish a mapping relationship between meteorological conditions and image degradation, thereby achieving joint decoupling of multiple interference factors and high-quality image reconstruction. This effectively improves the identification rate of surface defects in insulators and reduces the reliance on manual re-inspection. Attached Figure Description
[0021] The accompanying drawings, which form part of this embodiment, are used to provide a further understanding of this embodiment. The illustrative embodiments and their descriptions are used to explain this embodiment and do not constitute an improper limitation of this embodiment.
[0022] Figure 1 This is a flowchart of the method for identifying defects in transmission line insulators based on UAV inspection in Embodiment 1 of the present invention; Figure 2 This is an architecture diagram of the method for identifying defects in transmission line insulators based on UAV inspection in Embodiment 1 of the present invention; Figure 3 This is a diagram of the temperature prediction architecture in Embodiment 1 of the present invention; Figure 4 This is an architecture diagram of image enhancement in Embodiment 1 of the present invention; Figure 5 This is a structural block diagram of the power transmission line insulator defect identification system based on UAV inspection in Embodiment 2 of the present invention. Detailed Implementation
[0023] The present invention will be further described below with reference to the accompanying drawings and embodiments.
[0024] It should be noted that the following detailed descriptions are exemplary and intended to provide further illustration of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.
[0025] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.
[0026] In this invention, terms such as "upper," "lower," "left," "right," "front," "back," "vertical," "horizontal," "side," and "bottom" indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used only to facilitate the description of the structural relationships of the various components or elements of this invention and do not specifically refer to any component or element in this invention. They should not be construed as limiting the invention.
[0027] In this invention, terms such as "fixed connection," "connected," and "linked" should be interpreted broadly, indicating a fixed connection, an integral connection, or a detachable connection; a direct connection or an indirect connection through an intermediate medium. Those skilled in the art can determine the specific meaning of these terms in this invention based on the specific circumstances, and they should not be construed as limitations on the invention.
[0028] Where there is no conflict, the embodiments and features in the embodiments of the present invention can be combined with each other.
[0029] Example 1 Embodiment 1 of this invention introduces a method for identifying defects in power transmission line insulators based on unmanned aerial vehicle (UAV) inspection.
[0030] like Figure 1 The method for identifying defects in transmission line insulators based on UAV inspection, as shown, includes: Real-time images and temperatures of insulators on power transmission lines to be identified were obtained using drones. Based on the real-time temperature of the transmission line insulator and the multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information, the predicted temperature of the transmission line insulator is calculated. The predicted temperature and the real-time temperature of the insulator are corrected to obtain the corrected predicted temperature result. Adaptive filtering is used to enhance the acquired real-time images of transmission line insulators, resulting in enhanced images of transmission line insulators. Based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, defects in transmission line insulators are identified, and defect identification of transmission line insulators based on UAV inspection is completed.
[0031] To address the issues of abnormal temperatures caused by sunlight and interference from severe weather conditions during the inspection of insulators on high-voltage transmission lines, this embodiment employs the following method: Figure 2The method for real-time image enhancement of UAVs based on dynamic interference perception and adaptive filtering, as shown, specifically involves constructing a dynamic interference perception and temperature prediction mechanism to correct uneven surface temperature distribution caused by illumination in real time, accurately distinguishing between real temperature anomalies and illumination interference, and improving the reliability of infrared temperature detection; designing a meteorological impact adversarial modeling framework to establish a joint degradation model for meteorological conditions such as rain, fog, and strong light, achieving adaptive suppression and image quality restoration against complex meteorological interference; and employing a self-attention-based adaptive filtering mechanism to establish a dynamic mapping relationship between meteorological conditions and image degradation, achieving joint decoupling of multiple meteorological interferences and high-quality image reconstruction, significantly improving the accuracy of insulator defect identification and inspection efficiency.
[0032] As one or more implementation methods, this embodiment addresses the common problems of light interference and weather degradation in the inspection of insulators of high-voltage transmission lines. It employs a drone inspection system integrating multimodal sensing and adaptive filtering, equipped with a dual-light imaging system and multiple environmental sensors to achieve simultaneous acquisition of multi-source information. Specifically, the drone inspection system used in this embodiment acquires temperature distribution images of the insulators using an infrared thermal imager. At the same time, high-resolution color images were acquired using a visible light camera. To capture the radiation characteristics and apparent information of the target respectively; integrate a meteorological sensing unit to obtain the ambient temperature in real time. relative humidity Rainfall intensity and fog concentration Key meteorological parameters, such as those mentioned above, provide data support for subsequent interference modeling and compensation. In the data preprocessing stage, this embodiment performs size unification and normalization processing on the visible light images, namely... ; ;in, and For preset input size, and These are the mean and standard deviation of the image dataset, respectively, used to improve the convergence and generalization ability of the model training.
[0033] To overcome the interference of light on infrared thermometry, such as Figure 3 As shown, this embodiment constructs a multimodal temperature prediction mechanism that integrates visible light and infrared information; firstly, a normalized illumination intensity map is extracted from the red channel of the visible light image, i.e. This map is used to quantify the spatial distribution of light intensity received in different regions. It is combined with solar radiation intensity. (Obtained from an airborne total radiation meter) and the absorptivity of the insulator surface material Calculate the temperature rise caused by solar radiation. : ; in, .
[0034] Based on the ambient temperature and the aforementioned temperature rise, the expected temperature at each pixel location is deduced. : ; Calculate temperature deviation : ; By comparing infrared measured temperatures Compared with the expected temperature, this embodiment calculates the temperature deviation. and utilize learnable parameters , And the Sigmoid activation function generates attention weights : ; in, and These are learnable parameters.
[0035] Weighting of infrared image feature maps: ; Predicted actual temperature: ; This weighting adaptively applies weights to deep features in the infrared image, enhancing the response to real anomaly regions. Finally, the corrected actual temperature map is predicted using a multilayer perceptron (MLP) structure. To mitigate the impact of meteorological conditions on temperature detection, this embodiment introduces a meteorological attenuation factor. : ; This factor comprehensively reflects the attenuation effect of humidity, rainfall, and fog on infrared radiation, and is used to recalibrate the predicted temperature. .
[0036] This embodiment fully considers meteorological impact mitigation modeling and adaptive filtering, jointly modeling image degradation caused by combined meteorological conditions such as rain, fog, and strong light, and achieving high-quality image restoration through adaptive filtering; for example... Figure 4 As shown, the image enhancement process in this embodiment is divided into three sub-stages: degradation model construction, filter kernel generation, and image enhancement optimization.
[0037] This embodiment uses raw visible light images acquired by a drone, denoted as... (That is, the degraded image actually observed). For ease of subsequent processing, it is considered as an image of the real scene. The result after meteorological interference: ; in, This represents a composite meteorological degradation operator. To decouple the effects of different meteorological factors, this embodiment constructs separate degradation models for rain / fog and strong light.
[0038] In rainy or foggy weather, image degradation follows an atmospheric scattering model: ; in, An ideal scene image without degradation (the target to be restored); Transmittance reflects the degree of attenuation of light along its propagation path; Atmospheric scattering coefficient; The scene depth is inferred from the observed images by the pre-trained depth estimation network DepthNet; The atmospheric light intensity is usually taken as the average pixel value of the brightest area in the image, or estimated through the dark channel prior.
[0039] For ease of filter design, the rain / fog degradation residual is defined as: ; This residual is used to guide the design of the rain and fog filter core.
[0040] Under strong light conditions (such as direct midday sunlight), local areas of the image lose detail due to overexposure. This embodiment models strong light degradation as a nonlinear illumination attenuation process: ; ; in, This is a normalized light intensity map; This is the strong light attenuation coefficient, reflecting the intensity of overexposure.
[0041] therefore, In fact, it refers to the degradation form under the action of strong light masks, the core of which is to generate a spatially varying attenuation factor. In actual implementation, it is not explicitly calculated. Instead of outputting the image, its degradation mechanism is embedded in the filter kernel design.
[0042] To simultaneously suppress interference from rain, fog, and strong light, this embodiment designs two types of dedicated filter cores and dynamically merges them according to the current meteorological conditions.
[0043] (1) Rain and fog filtering kernel
[0044] ; This embodiment constructs a learnable rain and fog filter kernel. Its goal is to approximately achieve the aforementioned inverse transformation. Specifically, Generate in the following way: ; in, Indicates Fourier transform, To prevent small constants from being divided by zero.
[0045] (2) High-intensity light filtering core
[0046] ; However, since information in the overexposed areas is lost, direct division would amplify the noise. Therefore, this embodiment constructs a detail-enhancing filter kernel. Its design principle is to be suitable for low-light areas. Small, keep the original image; in the highlighted areas Larger areas enhance local contrast and suppress overexposure. Specifically, this is achieved as follows: That is, first calculate the theoretical compensation factor. Then, Gaussian smoothing is used to obtain a spatially smooth filter kernel to avoid introducing high-frequency noise.
[0047] Based on current meteorological attenuation factors Dynamically adjust the weights of the two types of filter kernels: ; when Heavy rain and fog. Rain and fog cores dominate; when Small (strong sunlight on a sunny day) The strong light nucleus is dominant.
[0048] The final adaptive filter kernel is: ; Image enhancement is achieved by solving the following optimization problem: ; in, This is the total variation regularization term, used to preserve margins.
[0049] Regularization coefficient It adapts and adjusts itself according to weather conditions; the heavier the rain and fog, the better. The smaller the size, the more smooth the surface; on sunny days... Larger size, emphasizing the preservation of details.
[0050] Enhanced image Correction results with predicted temperature Input is fed into the insulator defect detection network, i.e. ; in, For defect detection results, This is the trained defect detection neural network. It outputs the insulator defect detection results (including defect location and type) and the temperature anomaly detection results.
[0051] The output is based on the data obtained during the process operation. The output results include at least the corrected temperature data, the enhanced image, and the insulator defect detection results.
[0052] The output corrected temperature data can provide an accurate temperature distribution map of the insulator surface. The system eliminates the effects of light interference through a multimodal interference sensing and temperature prediction mechanism; the temperature data includes temperature values for each region of the insulator, which is used to accurately identify temperature anomalies.
[0053] The output enhanced image provides a high-quality visible light image. It effectively suppresses meteorological interference such as rain, fog, and strong light; it contains clear visual information on defects such as cracks, dirt, and damage on the surface of insulators; it provides a high-quality image basis for manual re-inspection, greatly reducing the workload of manual re-inspection.
[0054] The obtained insulator defect detection results can be obtained by using enhanced images. and corrected temperature data The system outputs results through a defect detection network; the results are used to identify defect types (cracks, dirt, damage, etc.), location coordinates, and confidence levels; and a structured report is generated, including a defect location map, a temperature distribution map, and a defect type analysis.
[0055] This embodiment constructs a multimodal interference sensing and temperature prediction mechanism to effectively correct the uneven temperature distribution on the insulator surface caused by illumination, accurately distinguish between real temperature anomalies and external illumination interference, thereby significantly improving the accuracy and reliability of infrared temperature detection and enhancing the ability to identify potential faults in insulators.
[0056] This embodiment establishes a joint degradation model for various meteorological conditions such as rain, fog, and strong light, and designs a meteorological impact adversarial modeling framework, which can adaptively suppress the degradation effect of complex meteorological conditions on image quality, significantly improve image clarity and detail retention, improve the quality of inspection images under severe weather conditions, and effectively suppress complex meteorological interference.
[0057] This embodiment introduces a self-attention-based adaptive filtering mechanism to dynamically establish a mapping relationship between meteorological conditions and image degradation, thereby achieving joint decoupling of multiple interference factors and high-quality image reconstruction. This effectively improves the identification rate of surface defects on insulators and reduces the reliance on manual re-inspection.
[0058] Example 2 Embodiment 2 of the present invention introduces a defect identification system for power transmission line insulators based on UAV inspection.
[0059] like Figure 5 The system shown is a transmission line insulator defect identification system based on UAV inspection, comprising: The acquisition module is configured to acquire real-time images and real-time temperatures of the insulators of the transmission line to be identified based on the UAV. The prediction module is configured to calculate the predicted temperature of the transmission line insulator based on the real-time temperature of the acquired transmission line insulator and a multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information. The correction module is configured to correct the obtained predicted temperature and the acquired real-time temperature of the insulator to obtain the predicted temperature correction result. An enhancement module is configured to perform image enhancement on the acquired real-time image of the transmission line insulator using adaptive filtering to obtain an enhanced image of the transmission line insulator. The identification module is configured to identify defects in transmission line insulators based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, thus completing the identification of transmission line insulator defects based on UAV inspection.
[0060] The detailed steps are the same as those of the method for identifying defects in transmission line insulators based on UAV inspection provided in Example 1, and will not be repeated here.
[0061] Example 3 Embodiment 3 of the present invention provides a computer-readable storage medium.
[0062] A computer-readable storage medium having a program stored thereon, which, when executed by a processor, implements the steps in the method for identifying defects in transmission line insulators based on UAV inspection as described in Embodiment 1 of the present invention.
[0063] The detailed steps are the same as those of the method for identifying defects in transmission line insulators based on UAV inspection provided in Example 1, and will not be repeated here.
[0064] Example 4 Embodiment 4 of the present invention provides an electronic device.
[0065] An electronic device includes a memory, a processor, and a program stored in the memory and running on the processor. When the processor executes the program, it implements the steps in the method for identifying defects in transmission line insulators based on UAV inspection as described in Embodiment 1 of the present invention.
[0066] The detailed steps are the same as those of the method for identifying defects in transmission line insulators based on UAV inspection provided in Example 1, and will not be repeated here.
[0067] Example 5 Embodiment 5 of the present invention provides a computer program product.
[0068] A computer program product includes software code, wherein the program in the software code performs the steps of the method for identifying defects in transmission line insulators based on UAV inspection as described in Embodiment 1 of the present invention.
[0069] The detailed steps are the same as those of the method for identifying defects in transmission line insulators based on UAV inspection provided in Example 1, and will not be repeated here.
[0070] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code. The solutions in the embodiments of the present invention can be implemented using various computer languages, such as the object-oriented programming language Java and the interpreted scripting language JavaScript.
[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0072] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.
[0073] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0074] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.
[0075] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.
[0076] The above description is merely a preferred embodiment of this practice and is not intended to limit the scope of this practice. Various modifications and variations can be made to this practice by those skilled in the art. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of this practice should be included within the protection scope of this practice.
Claims
1. A method for identifying defects in transmission line insulators based on unmanned aerial vehicle (UAV) inspection, characterized in that, include: Real-time images and temperatures of insulators on power transmission lines to be identified were obtained using drones. Based on the real-time temperature of the transmission line insulator and the multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information, the predicted temperature of the transmission line insulator is calculated. The predicted temperature and the real-time temperature of the insulator are corrected to obtain the corrected predicted temperature result. Adaptive filtering is used to enhance the acquired real-time images of transmission line insulators, resulting in enhanced images of transmission line insulators. Based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, defects in transmission line insulators are identified, and defect identification of transmission line insulators based on UAV inspection is completed.
2. The method for identifying defects in transmission line insulators based on UAV inspection as described in claim 1, characterized in that, In calculating the predicted temperature of transmission line insulators, solar radiation intensity is taken into account. Absorption rate of insulator surface material Calculate each pixel Temperature rise caused by solar radiation ,Right now ;in, Thermal conductivity, calibrated based on the insulator structure and material properties; based on the temperature rise caused by solar radiation. and real-time temperature Calculate the predicted temperature at each pixel location. ,Right now ;Calculate the temperature deviation between the calculated surface temperature and the predicted temperature ,Right now ;in This refers to the surface temperature of the insulator.
3. The method for identifying defects in transmission line insulators based on UAV inspection as described in claim 2, characterized in that, Based on the obtained temperature deviation, attention weights are calculated using an activation function. ,Right now ;in, and All are learnable parameters. The sigmoid activation function is used; the obtained attention weights are applied to the feature map of the infrared image (from the feature extraction layer of the convolutional neural network) to obtain the weighted feature map. ,Right now ;in Indicates the feature channel index; the obtained weighted feature map and neural network layer are used to predict the actual temperature of transmission line insulators. ,Right now MLP stands for Multilayer Perceptron.
4. The method for identifying defects in transmission line insulators based on UAV inspection as described in claim 3, characterized in that, The predicted temperature correction result for ;in, This represents the meteorological attenuation factor, i.e. ; This represents a percentage of relative humidity. Rainfall intensity, Fog concentration, These represent the coefficients used to balance the effects of different meteorological conditions.
5. The method for identifying defects in transmission line insulators based on UAV inspection as described in claim 1, characterized in that, Image enhancement of the acquired real-time images of transmission line insulators using adaptive filtering includes at least the construction of a degradation model, generation of filter kernels, and optimization of image enhancement.
6. The method for identifying defects in transmission line insulators based on UAV inspection as described in claim 1, characterized in that, After acquiring a real-time image of the insulator of the transmission line to be identified, the acquired real-time image is preprocessed to obtain a preprocessed image of the transmission line insulator; the preprocessing includes at least image size unification and image normalization.
7. A defect identification system for transmission line insulators based on unmanned aerial vehicle (UAV) inspection, characterized in that, include: The acquisition module is configured to acquire real-time images and real-time temperatures of the insulators of the transmission line to be identified based on the UAV. The prediction module is configured to calculate the predicted temperature of the transmission line insulator based on the real-time temperature of the insulator and a multi-modal temperature prediction mechanism based on the fusion of visible light and infrared information. The correction module is configured to correct the obtained predicted temperature and the acquired real-time temperature of the insulator to obtain the predicted temperature correction result. An enhancement module is configured to perform image enhancement on the acquired real-time image of the transmission line insulator using adaptive filtering to obtain an enhanced image of the transmission line insulator. The identification module is configured to identify defects in transmission line insulators based on the obtained predicted temperature correction results and enhanced images of transmission line insulators, thus completing the identification of transmission line insulator defects based on UAV inspection.
8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps of the method for identifying defects in transmission line insulators based on UAV inspection as described in any one of claims 1-6.
9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the program, it implements the steps of the method for identifying defects in transmission line insulators based on unmanned aerial vehicle (UAV) inspection as described in any one of claims 1-6.
10. A computer program product, comprising software code, characterized in that, The program in the software code executes the steps of the method for identifying defects in transmission line insulators based on UAV inspection as described in any one of claims 1-6.