Power transmission and transformation line remote sensing image enhancement system based on digital twinning

Abstract

The invention belongs to the technical field of image processing, and provides a digital twinning-based remote sensing image enhancement system for a power transmission and transformation line, and the system comprises a remote sensing image collection module which is used for collecting and obtaining an original remote sensing image of the power transmission and transformation line; the digital twinborn model construction module is used for constructing a virtual digital twinborn model of the power transmission and transformation line according to the original remote sensing image on the basis of a digital twinborn technology; and the image enhancement processing module is used for performing enhancement processing on the original remote sensing image based on the virtual digital twinborn model, and performing verification and optimization to obtain an enhanced remote sensing image. According to the method, the original remote sensing image of the power transmission and transformation line is enhanced by using the digital twin technology, so that the image processing effect and the image quality of the remote sensing image can be improved, and a basis is provided for efficient utilization of the remote sensing image.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a remote sensing image enhancement system for transmission and transformation lines based on digital twin. Background Art

[0002] The transmission and transformation project has many points, wide areas and long lines. The terrain at the construction site is intricate. The main processes of the project include house demolition, tree felling, road construction, land leveling, foundation pit excavation, material transportation, foundation pouring, tower erection, conductor and ground wire laying, and trial operation and other processes. Due to the long spatial distance and large time span of the project construction, there are many points of surface disturbance, many environmental protection and water conservation problems are prone to occur, and the social attention is high.

[0003] Traditional environmental protection supervision work is manual methods such as inspections and field surveys, which are difficult to conduct full-line environmental and water conservation monitoring in a timely manner. With the development of high-resolution remote sensing technology in recent years, it has made it possible to conduct high-frequency, fast, and high-efficiency full-line environmental and water conservation monitoring of the power grid, laying a strong foundation data support for the development of environmental and water conservation target intelligent recognition technology.

[0004] In the process of processing remote sensing images, there are problems such as relatively single processing technology, low processing efficiency, large processing difficulty for some remote sensing images, and poor processing effect, resulting in low utilization rate of remote sensing images.

[0005] Therefore, it is necessary to provide a remote sensing image enhancement system for transmission and transformation lines based on digital twin. Summary of the Invention

[0006] The present invention provides a remote sensing image enhancement system for transmission and transformation lines based on digital twin. By using digital twin technology to perform enhancement processing operations on the original remote sensing images of transmission and transformation lines, the image processing effect and image quality of remote sensing images can be improved, providing a basis for the efficient utilization of remote sensing images.

[0007] The present invention provides a remote sensing image enhancement system for transmission and transformation lines based on digital twin, including:

[0008] A remote sensing image acquisition module, configured to acquire the original remote sensing images of transmission and transformation lines;

[0009] A digital twin model construction module, configured to construct a virtual digital twin model of transmission and transformation lines based on digital twin technology according to the original remote sensing images;

[0010] An image enhancement processing module, configured to perform enhancement processing on the original remote sensing images based on the virtual digital twin model, and perform verification and optimization to obtain enhanced remote sensing images.

[0011] Further, acquiring the original remote sensing images of transmission and transformation lines includes:

[0012] Configure an image acquisition device for accessing high-resolution satellites and set the working parameters of the image acquisition device;

[0013] Based on the working parameters, use the image acquisition device to receive and collect the original remote sensing images of the power transmission and transformation lines through high-resolution satellites.

[0014] Furthermore, the original remote sensing images include the project images of the power transmission and transformation lines and the along-line environmental images; the project images include, but are not limited to, the images of the specific line trajectories, deployment scales, and construction site locations of the projects; the along-line environmental images include, but are not limited to, the images of buildings, vegetation coverage, and road terrain.

[0015] Furthermore, the digital twin model construction module includes an image processing unit and a model construction unit;

[0016] The image processing unit is used to perform gray-scale preprocessing on the original remote sensing images and extract image features to obtain the target image features for constructing the model;

[0017] The model construction unit is used to construct a digital twin model based on the target image features, relying on the Unity3D platform, based on the set model algorithms, model structures, and model parameters.

[0018] Furthermore, the image enhancement processing module includes a processing unit and a verification and optimization unit;

[0019] The processing unit is used to perform enhancement processing on the original remote sensing images based on the digital twin model using virtual reality technology to obtain enhanced remote sensing images;

[0020] The verification and optimization unit is used to perform simulation analysis on the process of image enhancement processing to verify and optimize the image enhancement effect.

[0021] Furthermore, performing enhancement processing on the original remote sensing images based on the digital twin model using virtual reality technology to obtain enhanced remote sensing images includes:

[0022] Based on the digital twin model, perform three-dimensional image feature extraction on the original remote sensing images through a three-dimensional convolutional neural network algorithm to obtain three-dimensional image feature data;

[0023] According to the three-dimensional image feature data, perform three-dimensional modeling using virtual reality technology to obtain a three-dimensional auxiliary model;

[0024] Based on the three-dimensional auxiliary model, perform enhancement processing on the original remote sensing images using GAN image enhancement technology to obtain enhanced remote sensing images.

[0025] Furthermore, performing simulation analysis on the process of image enhancement processing to verify and optimize the image enhancement effect includes:

[0026] Construct a standard image database that meets the image enhancement standard; several standard images are stored in the standard image database;

[0027] Use the set simulation model to perform simulation analysis on the process of enhancing the original remote sensing image, and obtain the simulation analysis result and the simulated enhanced image;

[0028] Perform a comparative analysis of the resolution between the simulated enhanced image and the standard image, and verify the simulated enhanced image according to the comparative analysis result; if the resolution comparison value is less than the set resolution comparison threshold, confirm the verification result of the simulated enhanced image; if the resolution comparison value is greater than the set resolution comparison threshold, further optimize the resolution of the original remote sensing image corresponding to the simulated enhanced image.

[0029] Furthermore, further optimize the resolution of the original remote sensing image corresponding to the simulated enhanced image, including:

[0030] Obtain the original remote sensing image, cluster the distribution of pixel points of the original remote sensing image, and obtain several clustering regions;

[0031] For the clustering regions with the number of pixel points greater than the set quantity value threshold, adopt the method of pixel interpolation to enhance the resolution of the original remote sensing image and obtain the first enhanced remote sensing image;

[0032] For the clustering regions with the number of pixel points less than the set quantity value threshold, based on the neural network prediction model, predict the missing pixel points to obtain the prediction result, and perform the operations of averaging, eliminating or supplementing the missing pixel points according to the prediction result to obtain the second enhanced remote sensing image;

[0033] Combine the pixel density and local texture complexity of the clustering regions, set and dynamically adjust the weights of pixel interpolation and the weights of neural network prediction, and optimize and enhance the first enhanced remote sensing image and the second enhanced remote sensing image according to the comprehensive weights composed of the weights of pixel interpolation and the weights of neural network prediction to obtain the enhanced first enhanced remote sensing image and the second enhanced remote sensing image; the calculation formula of the comprehensive weight is:

[0034]

[0035] W i represents the comprehensive weight, α represents the adjustment factor, N i is the number of pixels in the i-th clustering region; N t represents the total number of pixels, C i is the texture complexity of the i-th clustering region, which is the local window gray variance; C max is the maximum texture complexity value; when W iWhen it is greater than the set weight threshold, interpolation pixel points are preferentially used for enhancement to optimize and enhance the first enhanced remote sensing image; when W i is less than or equal to the set weight threshold, neural network prediction is used to supplement pixels to optimize and enhance the second enhanced remote sensing image;

[0036] The first enhanced remote sensing image and the second enhanced remote sensing image after enhancement are summarized to obtain the original remote sensing image with further optimized resolution.

[0037] Furthermore, it also includes managing and updating the standard image database, specifically including:

[0038] Based on the cloud platform, the standard image database is set as a cloud database;

[0039] Based on the management program in the cloud platform, the standard image database is managed;

[0040] Using geographic information system big data, the first update data is periodically retrieved;

[0041] The image data obtained by the camera shooting operation carried by the unmanned aerial vehicle is used as the second update data;

[0042] Based on the operation records at the construction site of the transmission and transformation line, the ground close-range image data is obtained as the third update data;

[0043] The first update data, the second update data, and the third update data are used as the update data of the standard image database to update the standard image database.

[0044] Furthermore, it also includes a result output and verification module for verifying the enhanced remote sensing image in actual applications, specifically including:

[0045] Verify the texture features of the enhanced remote sensing image, specifically: use the set extraction template to extract the texture features of the enhanced remote sensing image and obtain the texture feature description information; based on the comparison and analysis of the texture feature description information with the data in the set texture description information database, obtain the comparison result, and according to the comparison result, obtain the first verification result;

[0046] Identify the specific targets of the enhanced remote sensing image, specifically: use the target recognition model to perform target recognition on the enhanced remote sensing image to obtain the target recognition result; based on the accuracy of the target recognition result, obtain the second verification result;

[0047] According to the first verification result and the second verification result, obtain the verification result of the enhanced remote sensing image.

[0048] Compared with the prior art, the present invention has the following advantages and beneficial effects: It can achieve efficient and accurate enhancement processing of remote sensing images of power transmission and transformation lines. First, through the remote sensing image acquisition module, high-quality and high-resolution original remote sensing images can be obtained, providing a reliable data basis for subsequent processing. The digital twin model construction module uses advanced digital twin technology to construct a virtual digital twin model highly consistent with the actual situation, providing strong support for image enhancement processing. The image enhancement processing module effectively improves the clarity and detail expressiveness of the images. The function of managing and updating the standard image database can dynamically update and optimize the standard image database according to the actual situation and requirements, thereby improving the adaptability and practicability of the system. The result output and verification module can perform texture feature verification and target recognition verification on the enhanced remote sensing images, further ensuring the quality and reliability of the images.

[0049] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures specifically pointed out in the written specification and the drawings.

[0050] The technical solution of the present invention will be further described in detail below through the drawings and embodiments. Description of the Drawings

[0051] The drawings are used to provide a further understanding of the present invention and constitute a part of the specification. They are used together with the embodiments of the present invention to explain the present invention and do not constitute a limitation to the present invention. In the drawings:

[0052] Figure 1 is a schematic structural diagram of a remote sensing image enhancement system for power transmission and transformation lines based on digital twins;

[0053] Figure 2 is a schematic structural diagram of the digital twin model construction module;

[0054] Figure 3 is a schematic structural diagram of the image enhancement processing module. Detailed Embodiments

[0055] The following describes the preferred embodiments of the present invention with reference to the drawings. It should be understood that the preferred embodiments described herein are only for explaining and illustrating the present invention and are not used to limit the present invention.

[0056] The present invention provides a remote sensing image enhancement system for power transmission and transformation lines based on digital twins, as Figure 1 shown, including:

[0057] A remote sensing image acquisition module for acquiring the original remote sensing images of power transmission and transformation lines;

[0058] A digital twin model construction module, which is used to construct a virtual digital twin model of the power transmission and transformation line based on digital twin technology according to the original remote sensing image;

[0059] An image enhancement processing module, which is used to perform enhancement processing on the original remote sensing image based on the virtual digital twin model, and perform verification and optimization to obtain an enhanced remote sensing image.

[0060] The working principle of the above technical solution is as follows: In order to implement a remote sensing image enhancement system for power transmission and transformation lines based on digital twins, first, the remote sensing image acquisition module uses high-precision remote sensing equipment, such as high-definition cameras carried by satellites or drones, to photograph the power transmission and transformation lines to obtain the original remote sensing images. These images contain detailed information about the power transmission and transformation lines and their surrounding environment, but may have poor image quality due to factors such as weather and lighting, making it difficult to directly use them for analysis and judgment; then, the digital twin model construction module uses digital twin technology to construct a virtual digital twin model of the power transmission and transformation line based on these original remote sensing images. This model not only contains the physical structure information of the power transmission and transformation line, but also can simulate its operating state and changes in the surrounding environment, providing a basis for subsequent image enhancement processing; then, the image enhancement processing module performs enhancement processing on the original remote sensing image based on this virtual digital twin model. By comparing the differences between the virtual model and the actual image, the module can identify problems such as blurring and noise in the image and use advanced image processing algorithms for correction and optimization. After processing, the remote sensing image not only has improved clarity, but also can better reflect the actual situation of the power transmission and transformation line; finally, the enhanced remote sensing image will also be verified and optimized to ensure the quality and accuracy of the image. This step usually includes manual inspection of the image, comparison with on-site survey data, etc., to ensure that the final enhanced remote sensing image can meet the requirements of actual applications.

[0061] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, the quality and usability of the remote sensing image of the power transmission and transformation line can be significantly improved; by introducing digital twin technology, the system can construct a virtual model highly consistent with the actual situation, providing an accurate basis for image enhancement. At the same time, the application of advanced image processing algorithms effectively solves problems such as blurring and noise in the image, improving the clarity and accuracy of the image; in addition, by verifying and optimizing the enhanced remote sensing image, the quality and accuracy of the image are further ensured, enabling it to better serve the monitoring, maintenance, and management of power transmission and transformation lines; this not only improves work efficiency, but also reduces the cost and risk of manual inspection, which is of great significance for improving the safety and stability of the power system.

[0062] In one embodiment, acquiring the original remote sensing images of the power transmission and transformation line includes:

[0063] Configuring an image acquisition device for accessing high-resolution satellites and setting the working parameters of the image acquisition device;

[0064] Based on the working parameters, using the image acquisition device to receive and acquire the original remote sensing images of the power transmission and transformation line through high-resolution satellites.

[0065] The working principle of the above technical solution is as follows: By configuring the image acquisition device and setting its working parameters, such as satellite orbit, acquisition time, resolution, etc., it can ensure that the acquired original remote sensing images have the required quality and accuracy; Subsequently, the image acquisition device uses the observation ability of high-resolution satellites to receive and acquire the original remote sensing images of the power transmission and transformation line. These original image data contain detailed information about the power transmission and transformation line and its surrounding environment, providing a basis for subsequent image enhancement processing.

[0066] The beneficial effect of the above technical solution is: By adopting the solution provided in this embodiment, through the use of an image acquisition device accessing high-resolution satellites, it is possible to ensure the acquisition of accurate original remote sensing images of the power transmission and transformation line.

[0067] In one embodiment, the original remote sensing images include the project images of the power transmission and transformation line and the images of the surrounding environment along the line; The project images include, but are not limited to, the images of the specific line trajectory, deployment scale, and construction site location of the project; The images of the surrounding environment along the line include, but are not limited to, the images of buildings, vegetation coverage, and road terrain.

[0068] The working principle of the above technical solution is as follows: The original remote sensing images, as the basic data for constructing the digital twin model, their comprehensiveness is crucial for subsequent digital twin modeling and image enhancement processing; The project images detail the actual layout of the power transmission and transformation line, including the line trajectory, deployment scale, and the specific location of the construction site. These information are crucial for understanding the physical characteristics and spatial distribution of the power transmission and transformation line, while the images of the surrounding environment along the line capture the key environmental factors around the line, such as the distribution of buildings, vegetation coverage, and the characteristics of road terrain. These environmental information help analyze the possible natural and human factors affecting the line operation.

[0069] The beneficial effect of the above technical solution is: By adopting the solution provided in this embodiment, through the definition of the original remote sensing images, it provides a target for the acquisition of images.

[0070] In one embodiment, as Figure 2 shown, the digital twin model construction module includes an image processing unit and a model construction unit;

[0071] An image processing unit for performing grayscale preprocessing on the original remote sensing image and extracting image features to obtain target image features for constructing a model;

[0072] A model construction unit for constructing a digital twin model based on the target image features, relying on the Unity3D platform, and based on the set model algorithm, model structure, and model parameters.

[0073] The working principle of the above technical solution is as follows: The image processing unit first performs grayscale processing on the collected original remote sensing image. This step helps to reduce the interference of color information in the image and highlight the structural and textural features of the image. Subsequently, the image processing unit uses an advanced image feature extraction algorithm to accurately identify and extract the key image features related to the power transmission and transformation line. These features constitute the basic data for constructing the digital twin model. The model construction unit then takes over these target image features and relies on the powerful Unity3D platform, which is known for its high flexibility and powerful 3D rendering capabilities. The model construction unit gradually constructs a digital twin model that is highly consistent with the real power transmission and transformation line according to the preset model algorithm, fine model structure, and optimized model parameters. In this process, the selection of the algorithm, the setting of the structure, and the adjustment of the parameters have all been repeatedly verified and optimized to ensure that the finally constructed digital twin model can not only truly reflect the actual situation of the power transmission and transformation line but also meet the requirements of subsequent image enhancement and analysis.

[0074] The beneficial effect of the above technical solution is: By adopting the solution provided in this embodiment, through grayscale preprocessing of the original remote sensing image and constructing a digital twin model, it provides a basis for subsequent enhancement processing of the original remote sensing image.

[0075] In one embodiment, as Figure 3 shown, the image enhancement processing module includes a processing unit and a verification and optimization unit;

[0076] A processing unit for using virtual reality technology to perform enhancement processing on the original remote sensing image based on the digital twin model to obtain an enhanced remote sensing image;

[0077] In the process of enhancing the original remote sensing image, since the original remote sensing image often contains various noises that affect the image quality, the present invention measures the noise intensity by calculating the noise standard deviation of the local area of the image. For each pixel point, a window of size n×n (such as n = 3) is set with it as the center, and the standard deviation of the pixel values within the window is calculated:

[0078]

[0079] K local represents the noise standard deviation, x ijrepresents the pixel value at the \(i\)-th row and \(j\)-th column within the representative window, reflecting the pixel information at each specific position within the window, \(x\) average represents the average value of the pixels within the window, representing the average level of the pixel values within the window; \(n\) represents the number of windows; \(n\) 2 represents the set window size centered on the current pixel point;

[0080] According to the calculated noise standard deviation, adaptively adjust the parameters of the Gaussian filter; when the noise standard deviation is large, increase the standard deviation of the Gaussian filter to enhance the noise suppression effect; when the noise standard deviation is small, decrease the standard deviation of the Gaussian filter to avoid over-smoothing the image details; among them, the response formula of the Gaussian filter is:

[0081]

[0082] In the above formula, \(G(x,y)\) represents the weight matrix, \((x,y)\) represents the position coordinates of the Gaussian filter on the image plane, used to determine the effect of the filter on pixels at different positions in the image; \(\sigma\) represents the standard deviation of the Gaussian filter, which determines the smoothing degree and filtering effect of the Gaussian filter; the larger the value of \(\sigma\), the flatter the curve of the Gaussian function, the wider the range of action of the filter, the stronger the smoothing effect on the image, and more neighboring pixels will participate in the filtering calculation; the smaller the value of \(\sigma\), the steeper the curve, the more concentrated the range of action of the filter near the central pixel, the relatively weaker the smoothing effect on the image, and it can better retain the details of the image; the response formula of the Gaussian filter is used to generate the weight matrix \(G(x,y)\), and this matrix determines the weight of each pixel during the filtering process. When filtering the remote sensing image, the weight matrix of the filter is weighted and summed with the pixel values within the window to obtain the filtered pixel value. For pixels closer to the central pixel, their \((x\) 2 +y 2 ) value is smaller, the corresponding weight matrix \(G(x,y)\) is larger, and the contribution to the filtering result is also larger; while pixels farther from the central pixel have smaller weights and relatively less influence on the filtering result;

[0083] The verification and optimization unit is used to perform simulation analysis on the process of image enhancement processing to verify and optimize the image enhancement effect.

[0084] The working principle of the above technical solution is as follows: The image enhancement processing module of the present invention first receives the original remote sensing image data, which usually comes from images obtained by means such as UAV aerial photography and satellite remote sensing. After the processing unit starts working, using virtual reality technology and combining with the already constructed digital twin model, it conducts a detailed analysis and enhancement processing on the received original remote sensing image; in this process, not only the basic attributes such as the overall brightness and contrast of the image are considered, but also the noise problem in the image is particularly concerned; by calculating the noise standard deviation of the local area of the image, the intensity and distribution of the noise in the image can be accurately identified. Subsequently, according to the size of the noise standard deviation, the parameters of the Gaussian filter are adaptively adjusted to ensure that while effectively suppressing the noise, as much detail information in the image as possible is retained. This adaptive adjustment mechanism enables the system to provide the best enhancement effect when facing different types of remote sensing images; after the preliminary processing by the processing unit, the enhanced remote sensing image is generated and transmitted to the verification and optimization unit. At this stage, the system uses simulation analysis technology to deeply verify and optimize the process of image enhancement processing; by comparing the image quality before and after processing, the system can accurately evaluate the effect of image enhancement processing and fine-tune the processing parameters according to the evaluation results to ensure that the finally output enhanced remote sensing image reaches the best quality level.

[0085] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, through enhancing the original remote sensing image and conducting verification and optimization, the effect of enhancing the original remote sensing image can be improved; calculating the standard deviation of the pixel values within the calculation window and adaptively adjusting the parameters of the Gaussian filter according to the calculated noise standard deviation can achieve the smoothing processing of the image, while suppressing the noise, as much edge and detail information in the image as possible is retained. When processing the remote sensing image of the power transmission and transformation line, by adjusting the σ value, the filtering effect can be flexibly controlled according to the noise conditions and image detail requirements of different regions, achieving a better image enhancement purpose.

[0086] In one embodiment, using virtual reality technology and based on the digital twin model, enhancing the original remote sensing image to obtain an enhanced remote sensing image includes:

[0087] Based on the digital twin model, through a three-dimensional convolutional neural network algorithm, extracting three-dimensional image feature data from the original remote sensing image;

[0088] According to the three-dimensional image feature data, using virtual reality technology to conduct three-dimensional modeling to obtain a three-dimensional auxiliary model;

[0089] Based on the three-dimensional auxiliary model, using GAN image enhancement technology to enhance the original remote sensing image to obtain an enhanced remote sensing image.

[0090] The working principle of the above technical solution is as follows: To more effectively implement the enhancement processing of the original remote sensing image, the present invention first utilizes the high-fidelity of the digital twin model to map the original remote sensing image into the digital twin space. Through the three-dimensional convolutional neural network algorithm, the three-dimensional feature information in the image is deeply mined. These feature data contain important information such as the spatial structure and texture details of the image, providing a solid foundation for subsequent enhancement processing. Then, according to the extracted three-dimensional image feature data and combined with virtual reality technology, a three-dimensional auxiliary model corresponding to the original remote sensing image is constructed. This model not only has a high degree of realism but also can intuitively display key information such as the terrain and landforms and the route directions in the image, providing a more intuitive and convenient observation means for technicians. Finally, based on the constructed three-dimensional auxiliary model, the GAN (Generative Adversarial Network) image enhancement technology is used to further enhance the original remote sensing image. Through the adversarial training of the generator and the discriminator, the GAN technology can continuously optimize the quality of the generated image to make it clearer and more delicate. In this process, the three-dimensional auxiliary model provides rich prior knowledge for the GAN technology to guide it to perform image enhancement more accurately, and finally obtain a high-quality enhanced remote sensing image.

[0091] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, through the digital twin model and based on the three-dimensional auxiliary model, the original remote sensing image is enhanced, and a high-quality enhanced remote sensing image can be obtained.

[0092] In one embodiment, a simulation analysis is performed on the process of image enhancement processing to verify and optimize the image enhancement effect, including:

[0093] Construct a standard image database that meets the image enhancement standard; several standard images are stored in the standard image database;

[0094] Using the set simulation model, a simulation analysis is performed on the process of enhancing the original remote sensing image to obtain the simulation analysis result and the simulated enhanced image;

[0095] A resolution comparison analysis is performed between the simulated enhanced image and the standard image. According to the comparison analysis result, the simulated enhanced image is verified. If the resolution comparison value is less than the set resolution comparison threshold, the verification result of the simulated enhanced image is confirmed. If the resolution comparison value is greater than the set resolution comparison threshold, the resolution of the original remote sensing image corresponding to the simulated enhanced image is further optimized.

[0096] The working principle of the above technical solution is as follows: In order to simulate and analyze the process of image enhancement processing, verify and optimize the image enhancement effect, the present invention first constructs a standard image database, which contains a large number of high-quality standard images that have been professionally calibrated. These images serve as the reference benchmarks for the image enhancement effect, ensuring the objectivity and accuracy of the evaluation. Using an advanced simulation model, the system can simulate the entire process of enhancing the original remote sensing image, thereby generating a simulated enhanced image. This step not only helps to understand the actual effect of the enhancement process but also provides data support for subsequent optimization. Next, a detailed comparative analysis of the resolution between the simulated enhanced image and the standard image is carried out. This comparative analysis process is based on a high-precision image processing algorithm, which can accurately calculate the difference in resolution between the simulated enhanced image and the standard image. Through a set resolution comparison threshold, the system can automatically determine whether the simulated enhanced image meets the preset quality standard. If the resolution comparison value of the simulated enhanced image is less than the set resolution comparison threshold, it is considered that its quality meets the standard, and the system will confirm the verification result of the simulated enhanced image and use it as a candidate for subsequent processing or application. On the contrary, if the resolution comparison value is greater than the set resolution comparison threshold, the system will automatically trigger a further optimization process for the resolution of the original remote sensing image in order to obtain a higher-quality enhanced image.

[0097] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, through simulating and analyzing the process of image enhancement processing, verifying and optimizing the image enhancement effect, the quality of image enhancement can be guaranteed.

[0098] In one embodiment, further optimizing the resolution of the original remote sensing image corresponding to the simulated enhanced image includes:

[0099] Obtain the original remote sensing image, cluster the distribution of pixel points of the original remote sensing image to obtain several clustering regions;

[0100] For the clustering regions with the number of pixel points greater than the set quantity value threshold, adopt the method of pixel interpolation to enhance the resolution of the original remote sensing image and obtain the first enhanced remote sensing image;

[0101] For the clustering regions with the number of pixel points less than the set quantity value threshold, based on the neural network prediction model, predict the missing pixel points to obtain a prediction result, and according to the prediction result, perform operations such as averaging, eliminating, or supplementing the missing pixel points to obtain the second enhanced remote sensing image;

[0102] Combining the pixel density of the clustering region and the local texture complexity, set and dynamically adjust the weights of pixel point interpolation and the weights of neural network prediction. According to the comprehensive weights composed of the weights of pixel point interpolation and the weights of neural network prediction, optimize and enhance the first enhanced remote sensing image and the second enhanced remote sensing image to obtain the enhanced first enhanced remote sensing image and the second enhanced remote sensing image; the calculation formula of the comprehensive weight is:

[0103]

[0104] W i represents the comprehensive weight, α represents the adjustment factor, N i is the number of pixels in the i-th clustering region; N t represents the total number of pixels, C i is the texture complexity of the i-th clustering region, which is the local window gray variance; C max is the maximum texture complexity value; when W i is greater than the set weight threshold, preferentially use interpolated pixel points for enhancement to optimize and enhance the first enhanced remote sensing image; when W i is less than or equal to the set weight threshold, use neural network prediction to supplement pixels to optimize and enhance the second enhanced remote sensing image;

[0105] Summarize the enhanced first enhanced remote sensing image and the second enhanced remote sensing image to obtain the original remote sensing image with further optimized resolution.

[0106] The working principle of the above technical solution is as follows: Traditional resolution enhancement methods usually use a fixed threshold to divide the interpolation and prediction regions. However, there are significant differences in pixel density and texture complexity in different regions of actual images. For example, the conductor region (high density, low complexity) of the power transmission and transformation line and the surrounding vegetation (low density, high complexity) require different enhancement strategies. In order to further optimize the resolution of the original remote sensing image corresponding to the simulated enhanced image, the present invention first obtains the original remote sensing image, clusters the distribution of pixel points in the original remote sensing image to obtain several clustering regions; divides the image into multiple regions through a clustering algorithm (such as K-means), counts the number of pixels in each region, and the density weight reflects the sampling sufficiency of the region. High-density regions (such as conductors) are suitable for interpolation enhancement because they have sufficient original information; then, for the clustering regions with the number of pixel points greater than the set numerical threshold, the method of interpolating pixel points is adopted to enhance the resolution of the original remote sensing image and obtain the first enhanced remote sensing image; then, for the clustering regions with the number of pixel points less than the set numerical threshold, based on the neural network prediction model, the missing pixel points are predicted. High-complexity regions (such as vegetation) need to rely on neural network prediction to supplement detailed information to obtain the prediction result. According to the prediction result, operations such as averaging, removing, or supplementing the missing pixel points are performed to obtain the second enhanced remote sensing image; combining the pixel density and local texture complexity of the clustering regions, the weights of pixel point interpolation and neural network prediction are set and dynamically adjusted. According to the comprehensive weight composed of the weights of pixel point interpolation and neural network prediction, the first enhanced remote sensing image and the second enhanced remote sensing image are optimized and enhanced to obtain the enhanced first enhanced remote sensing image and the second enhanced remote sensing image; the calculation formula of the comprehensive weight is:

[0107]

[0108] W i represents the comprehensive weight, α represents the adjustment factor, and N i is the number of pixels in the i-th clustering region; N t represents the total number of pixels, and C i is the texture complexity of the i-th clustering region, which is the local window gray variance; C max is the maximum texture complexity value; when W i is greater than the set weight threshold, interpolation pixel point enhancement is preferred to optimize and enhance the first enhanced remote sensing image; when W i is less than or equal to the set weight threshold, neural network prediction is used to supplement pixels to optimize and enhance the second enhanced remote sensing image to give priority to ensuring the accuracy of high-density regions; according to actual requirements (such as the requirement for conductor clarity), the weight threshold can be set to 0.5. When W iWhen it is greater than 0.5, bicubic interpolation is used to enhance the resolution; otherwise, a convolutional neural network is used to predict the missing pixels.

[0109] Finally, the first enhanced remote sensing image and the second enhanced remote sensing image are aggregated to obtain the original remote sensing image with further optimized resolution.

[0110] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment, the resolution of the original remote sensing image corresponding to the simulated enhanced image is further optimized, which can avoid the blurring problem caused by interpolation in the low-density area. In the high-complexity area, details are supplemented by the neural network, which can improve the recognition accuracy of targets such as tower bases and vegetation boundaries, and further ensure the effect of image enhancement.

[0111] In one embodiment, it further includes managing and updating the standard image database, specifically including:

[0112] Based on the cloud platform, the standard image database is set as a cloud database;

[0113] Based on the management program in the cloud platform, the standard image database is managed;

[0114] Using geographic information system big data, the first update data is periodically retrieved;

[0115] Using the image data obtained by the camera carried by the drone for shooting operations as the second update data;

[0116] Based on the operation records at the construction site of the power transmission and transformation line, the ground close-range image data is obtained as the third update data;

[0117] The first update data, the second update data, and the third update data are used as the update data of the standard image database to update the standard image database.

[0118] The working principle of the above technical solution is as follows: In order to realize the efficient utilization of the standard image database, the present invention further includes managing and updating the standard image database. First, based on the cloud platform, the standard image database is set as a cloud database; then, based on the management program in the cloud platform, the standard image database is managed; finally, using geographic information system big data, the first update data is periodically retrieved; using the image data obtained by the camera carried by the drone for shooting operations as the second update data; based on the operation records at the construction site of the power transmission and transformation line, the ground close-range image data is obtained as the third update data; finally, the first update data, the second update data, and the third update data are used as the update data of the standard image database to update the standard image database.

[0119] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment and managing and updating the standard image database, efficient management of the standard image database can be achieved.

[0120] In one embodiment, it further includes a result output and verification module, which is used to verify the enhanced remote sensing image in actual applications. Specifically, it includes:

[0121] Verify the texture features of the enhanced remote sensing image. Specifically: Use the set extraction template to extract the texture features of the enhanced remote sensing image and obtain texture feature description information; Based on the comparison and analysis of the texture feature description information with the data in the set texture description information database, obtain a comparison result, and based on the comparison result, obtain the first verification result;

[0122] Identify the specific targets of the enhanced remote sensing image. Specifically: Use the target recognition model to perform target recognition on the enhanced remote sensing image and obtain the target recognition result; Based on the accuracy of the target recognition result, obtain the second verification result;

[0123] Obtain the verification result of the enhanced remote sensing image according to the first verification result and the second verification result.

[0124] The working principle of the above technical solution is as follows: In order to better verify the application of the enhanced remote sensing image, the present invention further includes a result output and verification module, which is used to verify the enhanced remote sensing image in actual applications. First, verify the texture features of the enhanced remote sensing image. Specifically: Use the set extraction template to extract the texture features of the enhanced remote sensing image and obtain texture feature description information; Based on the comparison and analysis of the texture feature description information with the data in the set texture description information database, obtain a comparison result, and based on the comparison result, obtain the first verification result; Then, identify the specific targets of the enhanced remote sensing image. Specifically: Use the target recognition model to perform target recognition on the enhanced remote sensing image and obtain the target recognition result; Based on the accuracy of the target recognition result, obtain the second verification result; Finally, obtain the verification result of the enhanced remote sensing image according to the first verification result and the second verification result.

[0125] The beneficial effects of the above technical solution are as follows: By adopting the solution provided in this embodiment and verifying the application of the enhanced remote sensing image, a basis for the efficient utilization of the enhanced remote sensing image is provided.

[0126] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalent technologies, the present invention also intends to include these changes and modifications.

Claims

1. A remote sensing image enhancement system for power transmission and transformation lines based on digital twin, characterized in that, Including: A remote sensing image acquisition module, which is used to acquire the original remote sensing images of the power transmission and transformation lines; A digital twin model construction module, which is used to construct a virtual digital twin model of the power transmission and transformation lines based on the digital twin technology according to the original remote sensing images; An image enhancement processing module, which is used to perform enhancement processing on the original remote sensing images based on the virtual digital twin model, and perform verification and optimization to obtain enhanced remote sensing images.

2. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 1, characterized in that, Acquiring the original remote sensing images of the power transmission and transformation lines includes: Configuring an image acquisition device for accessing high-resolution satellites and setting the working parameters of the image acquisition device; Based on the working parameters, using the image acquisition device to receive and acquire the original remote sensing images of the power transmission and transformation lines through high-resolution satellites.

3. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 2, characterized in that, The original remote sensing images include the project images of the power transmission and transformation lines and the images of the surrounding environment along the lines; the project images include, but are not limited to, the images of the specific line trajectories, deployment scales, and construction site locations of the projects; the images of the surrounding environment along the lines include, but are not limited to, the images of buildings, vegetation coverage, and road terrain.

4. A remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 1, characterized in that, The digital twin model construction module includes an image processing unit and a model construction unit; The image processing unit is used to perform grayscale preprocessing on the original remote sensing images and extract image features to obtain target image features for constructing the model; The model construction unit is used to construct a digital twin model based on the target image features, relying on the Unity3D platform, based on the set model algorithms, model structures, and model parameters.

5. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 1, wherein, The image enhancement processing module includes a processing unit and a verification and optimization unit; The processing unit is used to perform enhancement processing on the original remote sensing images based on the digital twin model using virtual reality technology to obtain enhanced remote sensing images; The verification and optimization unit is used to perform simulation analysis on the process of image enhancement processing to verify and optimize the image enhancement effect.

6. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 5, wherein, Using virtual reality technology to perform enhancement processing on the original remote sensing images based on the digital twin model to obtain enhanced remote sensing images includes: Based on the digital twin model, using a three-dimensional convolutional neural network algorithm to extract three-dimensional image features from the original remote sensing images to obtain three-dimensional image feature data; According to the three-dimensional image feature data, using virtual reality technology to perform three-dimensional modeling to obtain a three-dimensional auxiliary model; Based on the three-dimensional auxiliary model, using the GAN image enhancement technology to perform enhancement processing on the original remote sensing images to obtain enhanced remote sensing images.

7. A remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 5, characterized in that, Performing simulation analysis on the process of image enhancement processing to verify and optimize the image enhancement effect includes: Constructing a standard image database that meets the image enhancement standards; several standard images are stored in the standard image database; Using the set simulation model to perform simulation analysis on the process of performing enhancement processing on the original remote sensing images to obtain simulation analysis results and simulation enhanced images; Performing a comparative analysis of the resolutions of the simulation enhanced images and the standard images, and verifying the simulation enhanced images according to the comparative analysis results; if the resolution comparison value is less than the set resolution comparison threshold, the verification result of the simulation enhanced images is confirmed; if the resolution comparison value is greater than the set resolution comparison threshold, the resolution of the original remote sensing images corresponding to the simulation enhanced images is further optimized.

8. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 7, characterized in that, Further optimize the resolution of the original remote sensing image corresponding to the simulation-enhanced image, including: Obtain the original remote sensing image, cluster the distribution of pixel points of the original remote sensing image, and obtain several clustering regions; For the clustering regions with the number of pixel points greater than the set numerical threshold, adopt the method of interpolating pixel points to enhance the resolution of the original remote sensing image and obtain the first enhanced remote sensing image; For the clustering regions with the number of pixel points less than the set numerical threshold, based on the neural network prediction model, predict the missing pixel points to obtain a prediction result, and perform operations such as averaging, eliminating, or supplementing the missing pixel points according to the prediction result to obtain the second enhanced remote sensing image; Combine the pixel density of the clustering region and the local texture complexity, set and dynamically adjust the weights of pixel point interpolation and the weights of neural network prediction. According to the comprehensive weights composed of the weights of pixel point interpolation and the weights of neural network prediction, optimize and enhance the first enhanced remote sensing image and the second enhanced remote sensing image to obtain the enhanced first enhanced remote sensing image and the second enhanced remote sensing image; The calculation formula for the comprehensive weight is: W i represents the comprehensive weight, α represents the adjustment factor, and N i is the number of pixels in the i-th clustering region; N t represents the total number of pixels, and C i is the texture complexity of the i-th clustering region, which is the local window gray variance; C max is the maximum texture complexity value; when W i is greater than the set weight threshold, interpolation pixel points are preferentially used for enhancement, and the first enhanced remote sensing image is optimized and enhanced; when W i is less than or equal to the set weight threshold, neural network prediction is used to supplement pixels, and the second enhanced remote sensing image is optimized and enhanced; Summarize the enhanced first enhanced remote sensing image and the second enhanced remote sensing image to obtain the original remote sensing image with further optimized resolution.

9. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 7, characterized in that, It also includes managing and updating the standard image database, specifically including: Based on the cloud platform, set the standard image database as a cloud database; Manage the standard image database based on the management program in the cloud platform; Use big data of geographic information systems to periodically retrieve and obtain the first update data; Use the image data obtained by the camera carried by the unmanned aerial vehicle for shooting operations as the second update data; Based on the operation records at the construction site of the power transmission and transformation line, obtain the ground close-range image data as the third update data; Use the first update data, the second update data, and the third update data as the update data of the standard image database to update the standard image database.

10. The remote sensing image enhancement system for power transmission and transformation lines based on digital twin according to claim 1, wherein, It also includes a result output and verification module for verifying the enhanced remote sensing image in actual applications, specifically including: Verify the texture features of the enhanced remote sensing image, specifically: use the set extraction template to extract the texture features of the enhanced remote sensing image and obtain the texture feature description information; based on the comparison and analysis of the texture feature description information and the data in the set texture description information database, obtain the comparison result, and obtain the first verification result according to the comparison result; Identify the specific targets of the enhanced remote sensing image, specifically: use the target recognition model to perform target recognition on the enhanced remote sensing image to obtain the target recognition result; obtain the second verification result based on the accuracy of the target recognition result; Obtain the verification result of the enhanced remote sensing image according to the first verification result and the second verification result.

Images