Power transmission line inspection image super-resolution reconstruction method and system

Abstract

The invention discloses a power transmission line inspection image super-resolution reconstruction method and system, and the method comprises the steps: obtaining at least one power transmission line inspection image, and carrying out the Sharla fuzzy processing of the power transmission line inspection image, and obtaining at least one target inspection image; constructing a super-resolution reconstruction network based on convolution shape convolution, and inputting the target inspection image as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model; and inputting the obtained real-time power transmission line inspection image into the target super-resolution reconstruction model, and outputting the target super-resolution reconstruction model to obtain a reconstructed image. According to the method, a low-quality and fuzzy image can be improved into a high-resolution image, so that the definition of image details is enhanced, and a target detection technology can identify and analyze the discharge and heating state of the insulator more accurately.

Description

Technical Field

[0001] The present invention belongs to the technical field of image processing, and in particular relates to a method and system for super-resolution reconstruction of transmission line inspection images. Background Art

[0002] Insulators are an indispensable and important component in the power system, mainly used to support and isolate high-voltage wires to prevent current leakage through the air or other media, thereby ensuring the stability and safety of power transmission. With the continuous growth of power demand and the increasing complexity of power systems, higher requirements are placed on the maintenance and detection of insulators.

[0003] Traditional insulator inspection methods mainly include manual inspection and regular maintenance. Manual inspection relies on experienced technicians to inspect by naked eye and hand tools. This method is not only inefficient, but also easily affected by human factors, making it difficult to detect potential faults in time. Although regular maintenance can prevent faults to a certain extent, it often has a large lag due to the lack of real-time performance and cannot meet the high standards of modern power systems.

[0004] With the rapid development of computer vision and deep learning technologies, image-based target detection technology has gradually become a new trend in insulator detection. Target detection technology can automatically identify and locate insulators in images, and monitor their discharge and heating status in real time through ultraviolet imagers, greatly improving the accuracy and efficiency of detection. Especially in the daily inspection of transmission lines, target detection technology can quickly detect defects in insulators, such as cracks, breakage, pollution, etc., and take timely measures to avoid power outages and safety accidents caused by insulator failures.

[0005] However, despite the great potential of target detection technology in insulator detection, it still faces some challenges. For example, the complex environment of the transmission line, the low pixel image produced by the drone during the shooting process, or the unclear quality of the external light image during the shooting process, all these factors increase the accuracy of detection. The scale of the target in the image varies greatly, and the existing detection algorithm is unstable when dealing with multi-scale targets. Summary of the invention

[0006] The present invention provides a transmission line inspection image super-resolution reconstruction method and system, which are used to solve the technical problem that the scale of the target in the image varies greatly and the performance of the existing detection algorithm is unstable when processing multi-scale targets.

[0007] In a first aspect, the present invention provides a method for super-resolution reconstruction of a transmission line inspection image, comprising: Acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; A super-resolution reconstruction network is constructed based on convolutional shape convolution, and the target inspection image is input as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The acquired real-time transmission line inspection image is input into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0008] In a second aspect, the present invention provides a transmission line inspection image super-resolution reconstruction system, comprising: An acquisition module is configured to acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; The training module is configured to construct a super-resolution reconstruction network based on convolutional shape convolution, and input the target inspection image as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The output module is configured to input the acquired real-time transmission line inspection image into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0009] According to a third aspect, an electronic device is provided, comprising: at least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can perform the steps of the method for super-resolution reconstruction of transmission line inspection images according to any embodiment of the present invention.

[0010] In a fourth aspect, the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the steps of the method for super-resolution reconstruction of transmission line inspection images of any embodiment of the present invention.

[0011] The transmission line inspection image super-resolution reconstruction method and system of the present application have the following beneficial effects: 1. The multi-scale feature coordination mechanism is adopted. By setting up three different scale Bconv modules of 9x9, 5x5 and 3x3 in parallel, the coordinated capture of local details, regional features and global context information of the image is achieved. This feature extraction method effectively solves the problem of detail loss in complex texture restoration caused by traditional single-scale convolution. The HDSA module is used to adaptively assign weights to multi-scale features, and the feature space alignment and semantic association are achieved through the deformable attention mechanism. Compared with conventional channel splicing or weighted fusion, the feature fusion effect is improved under low-quality input. Through the residual learning of cascade processing and reconstruction modules, the noise amplification effect is suppressed while maintaining high-frequency details, and the PSNR indicator is greatly improved compared with the traditional residual network. 2. The SRBConv loss function uses multi-scale Gaussian blur contrast terms to forcibly retain high-frequency details at different scales, while using the channel variance maximization mechanism to enhance feature diversity; the dynamic weight parameters achieve an adaptive balance between detail preservation and feature optimization, ultimately maintaining the efficiency and robustness of model training while improving the quality of image restoration; 3. Through four-way feature decoupling, the traditional square convolution kernel is decomposed into branch convolutions in four orthogonal directions: horizontal (left / right) and vertical (up / down), forming a convoluted receptive field. This design can achieve the equivalent perception range of 9x9 convolution while maintaining the computational efficiency of 3x3 convolution. Through direction-sensitive feature extraction, each branch uses narrow convolution kernels (kx1 and 1xk) to specifically capture edge and texture features in specific directions. Compared with standard convolution, the error rate in directional texture reconstruction tasks is reduced. Through four-branch channel splitting, while ensuring feature diversity, the number of parameters is controlled to 1 / 3 of the standard convolution, achieving a balance between computational efficiency and feature expression capabilities. 4. The spatial adaptability of convolutional convolution is combined with the global relationship modeling of self-attention. Through the dynamically generated offset, the attention calculation can be focused on the semantically related deformation area, which improves the reasoning speed in image restoration tasks compared to the traditional Transformer. The convolutional convolution path retains local geometric details, the self-attention path establishes long-range dependencies, and the dual-path features are complementary enhanced through the gating mechanism. Through the temperature scaling coefficient k and the learned offset amplitude control, the network can automatically adjust the degree of deformation according to the complexity of the input features, while maintaining stability. Improve the modeling ability of complex deformations; the zero initialization of the residual projection layer ensures that the initial stage of the network is equivalent to the identity mapping, and cooperates with the batch normalization layer to improve the convergence speed of the deep network and effectively alleviate the gradient disappearance problem. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0013] Figure 1 A flowchart of a method for super-resolution reconstruction of a power transmission line inspection image provided by one embodiment of the present invention; Figure 2 A block diagram of a transmission line inspection image super-resolution reconstruction process according to a specific embodiment of the present invention; Figure 3 A flowchart of the internal processing of the HDSA module provided by one embodiment of the present invention; Figure 4 A structural block diagram of a transmission line inspection image super-resolution reconstruction system provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] See also Figure 1 , which shows a flow chart of a method for super-resolution reconstruction of a power transmission line inspection image of the present application.

[0016] like Figure 1 As shown, the transmission line inspection image super-resolution reconstruction method specifically includes the following steps: Step S101, acquiring at least one power transmission line inspection image, and performing Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image.

[0017] In this step, edge detection is performed on a transmission line inspection image, and convolution is performed on the transmission line inspection image through a Gaussian blur kernel to obtain a fuzzy transmission line inspection image, wherein the expression for convolution of the transmission line inspection image through the Gaussian blur kernel is: , , In the formula, is the midpoint of the fuzzy transmission line inspection image The pixel value at is the midpoint of the transmission line inspection image The pixel value at is the Gaussian kernel, is the convolution operation, is the standard deviation of the Gaussian kernel, which controls the degree of blur; The transmission line inspection image and the fuzzy transmission line inspection image are fused to obtain a target inspection image, which is expressed as: , , In the formula, The midpoint of the target inspection image The pixel value at is the edge strength of each pixel in the image, obtained by the Sobel operator, is the weight factor, is the maximum edge intensity value in the fuzzy transmission line inspection image.

[0018] Step S102, constructing a super-resolution reconstruction network based on convolutional shape convolution, and inputting the target inspection image as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model.

[0019] In this step, the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of different sizes of Bconv (convolutional large-scale convolution) branches in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerically stable term.

[0020] It should be noted that the target super-resolution reconstruction model includes: Input layer: The input is a low-resolution feature map of (1x128x128).

[0021] The parallel convolutional convolution layer connected to the input layer includes a first convolutional convolution layer with a convolution kernel of 9x9, a second convolutional convolution layer with a convolution kernel of 5x5, and a third convolutional convolution layer with a convolution kernel of 3x3. It is used to input the low-resolution input image into three convolutional convolution layers of 9x9, 5x5, and 3x3 in parallel to extract image information in different areas.

[0022] HDSA modules connected with parallel convolutional convolutional layers; and The reconstruction layer connected to the HDSA module is used to input the output of the fusion layer into the reconstruction layer. Through two convolutions with a kernel of 3, the number of channels of the image is reduced from 64 to 1 to keep consistent with the size of the original input image.

[0023] Step S103, inputting the acquired real-time transmission line inspection image into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0024] In this step, see Figure 2 , the real-time power transmission line inspection image is respectively input into the first convolutional convolution layer with a convolution kernel of 9x9, the second convolutional convolution layer with a convolution kernel of 5x5, and the third convolutional convolution layer with a convolution kernel of 3x3, and the corresponding outputs are the first convolution result, the second convolution result, and the third convolution result; the first convolution result, the second convolution result, and the third convolution result are spliced ​​to obtain the first output image; the first output image is input into the HDSA (High-Dimensional Self-Attention, high-dimensional self-attention module) module, and the first feature map is deeply fused according to the HDSA module to obtain the second output image; the second output image is sequentially subjected to the convolutional convolution with a kernel size of 5 and the convolutional convolution with a kernel size of 3 to obtain the third output image; the third output image and the real-time power transmission line inspection image are input into the reconstruction layer, and the high-level features in the third output image are mapped to the real-time power transmission line inspection image according to the reconstruction layer, and finally the reconstructed image is obtained.

[0025] Specifically, the detailed expansion of the convolution operation: , In the formula, is the left convolution kernel, is the right-direction convolution kernel, is the upward convolution kernel, is the convolution kernel in the downward direction, is the residual projection kernel, It is a channel splicing operation; The outputs of all convolutional layers are concatenated and the expression is: , In the formula, is the first feature map, This is the feature map obtained by the first convolutional layer with a convolution kernel of 9x9. This is the feature map obtained by the first convolutional layer with a convolution kernel of 5x5. It is the feature map obtained by the first convolutional layer with a convolution kernel of 3x3; The specific operation method is: , In the formula, It is the feature map after concatenating three-way convolution operations.

[0026] For further information, see Figure 3 , the HDSA module performs deep attention feature fusion on the first feature map to obtain a second output image including: Perform feature projection on the first feature map, and the expression is:

[0027] In the formula, is the query vector, is the key vector, is a value vector, is the weight matrix of the query vector, is the weight matrix of the key vector, is the weight matrix of the value vector, is the first feature map; The query projection formula is: , The key projection formula is: , The value projection formula is: , The query vector and key vector The spatial dimension of is flattened, and the expression is: , , , , In the formula, , represents the spatial position after flattening, is the total number of spatial points in the feature map, is the flattened query matrix, is the number of output batches, for The number of channels, , are the length and width of the output position, respectively. is the flattened bond matrix, for The number of channels, is the feature map batch; Calculate the attention weights of the flattened query matrix and the flattened key matrix respectively to get the attention matrix, which is expressed as: , In the formula, is the attention matrix, is the normalized attention weight, is the transpose of the flattened bond matrix; Perform deformable convolution calculations based on the value vector, including: right Keep the original dimension for deformable convolution, the expression is: , In the formula, It is the feature map after deformable convolution processing; The offset is generated by: , In the formula, is the result of generating the first offset, is the first offset convolution kernel; , In the formula, is the result of the second offset. is the second offset convolution kernel, is the convolution operation; , In the formula, is the deformation offset; The coordinate calculation formula for deformable convolution is: , In the formula, is the convolution kernel position, For the Location The offset of the direction, For the Location The offset of the direction, is the weight of the deformable convolution kernel, is the feature map after the input feature map is projected, For a full slice operation, take all elements of this dimension. is the step length, All are relative offsets within the nucleus; The attention matrix performs weighted fusion on the output of the deformable convolution to obtain a second output image, wherein the expression of the second output image is: , In the formula, is the second output image, is the activation function, For batch normalization, is the projected convolution kernel, is the convolution operation, is the attention-weighted feature, is the original input, which does not refer to the initial input image of the entire network, but the initial feature map input into the HDSA module by the previous module. x is added to the output of the fused feature through the residual connection, ensuring that the model can retain the original input information in the deep part of the network, thereby optimizing the feature fusion process and increasing the stability during training and the integrity of information transmission.

[0028] It should be noted that the second output image is sequentially subjected to a convolutional convolution with a kernel size of 5 and a convolutional convolution with a kernel size of 3 to obtain a third output image including: The second output image is input into the convolution with a kernel size of 5, and the first result is output, which is expressed as: , In the formula, is a convolutional convolution with a kernel size of 5, is the second output image, For batch normalization, is the activation function, For channel splicing operations, is the left vertical convolution feature, is the right vertical convolution feature, is the upward horizontal convolution feature, It is the downward horizontal convolution feature; Among them, the expression of the left vertical convolution feature is: , In the formula, After the left convolution operation, the position in the output feature map is The corresponding value, is the number of output batches, is the number of output channels, , are the length and width of the output position, respectively. is the vertical displacement within the nucleus, is the left convolution, is the number of input channels, Indicates that the second output image is Sampling is carried out at Represents the position offset of the convolution kernel in the vertical direction (i.e., height direction), which is the displacement of the convolution kernel when it slides along the vertical axis of the image. It represents the sliding step size of the convolution kernel at this position. Indicates the position of the convolution kernel in the horizontal direction. Since the width of the convolution kernel is fixed to 1 in the horizontal direction (that is, the convolution kernel does not expand in the horizontal direction), there is no lateral offset and it only slides in the vertical direction.

[0029] The expression of the right vertical convolution feature is: , In the formula, To perform horizontal flip of the convolution kernel for left-to-left convolution; The expression of the upward vertical convolution feature is: , In the formula, After the upward convolution operation, the position in the output feature map is The corresponding value, is the intranuclear horizontal shift, Indicates that the second output image is Sampling is carried out at Represents the horizontal position offset of the convolution kernel (i.e., width direction), which is the displacement of the convolution kernel when it slides along the vertical axis of the image. It represents the sliding step of the convolution kernel at this position. It represents the position of the convolution kernel in the vertical direction. Since the height of the convolution kernel is fixed to 1 in the vertical direction (that is, the convolution kernel does not expand in the vertical direction), there is no longitudinal offset and it only slides in the horizontal direction.

[0030] The expression of the downward vertical convolution feature is: , In the formula, To perform horizontal flipping of the convolution kernel for upward convolution; The first result is input into a first adaptive convolution module, and the second result is output. , , In the formula, is the second calculation result, is the first adaptive convolution module, is the residual weight coefficient, is the convolution operation, is the weighted input; The second result is input into the convolutional convolution with a kernel size of 3, and the third result is output. The third result is input into the second adaptive convolution module, and the third output image is output. The expression is: , In the formula, is the third output image, is the second adaptive convolution module, is a convolution with a kernel size of 3.

[0031] The expression for reconstructing the image is: , , , , , , In the formula, To reconstruct the image, Reconstructing the image. For real-time transmission line inspection images, is the tanh output, the output range is [-1, 1], is the hyperbolic tangent function, is the feature map of the final output convolution, is the output feature after being processed by the LeakyReLU activation function, is a 3x3 convolution kernel with no bias. is the second bias term, is the result feature of batch normalization. is the slope of the negative semi-axis, is a learnable scaling parameter, is the mean along the channel dimension, is a learnable offset parameter, To prevent division by zero for small constants, is the variance along the channel dimension, is the dimensionality reduction convolution operation, is the convolution kernel parameter, is the output feature of the dimensionality reduction convolution, is the first bias term, is the third output image.

[0032] Traditional super-resolution reconstruction networks can achieve good reconstruction effects on single blurred images, but since most of the objects they are aimed at are restoration of old images or single images generated by low-resolution visible light devices, they do not take into account the reliability of actual applications in which the shooting equipment may be blurred due to insufficient light or due to limited resource deployment on drones, making these models difficult to promote in actual applications in the power field. Therefore, the method of this application uses a new convolutional convolution layer, which uses padding in four different directions (horizontal and vertical) to capture texture information in more directions of the insulator, and can upgrade low-quality, blurred images to high-resolution images, thereby enhancing the clarity of image details, so that target detection technology can more accurately identify and analyze the discharge and heating state of the insulator.

[0033] See also Figure 4, which shows a structural block diagram of a transmission line inspection image super-resolution reconstruction system of the present application.

[0034] like Figure 4 As shown, the transmission line inspection image super-resolution reconstruction system 200 includes an acquisition module 210 , a training module 220 and an output module 230 .

[0035] The acquisition module 210 is configured to acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; The training module 220 is configured to construct a super-resolution reconstruction network based on convolutional shape convolution, and input the target inspection image as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The output module 230 is configured to input the acquired real-time transmission line inspection image into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0036] It should be understood that Figure 4 Modules and references documented in Figure 1 Therefore, the operations and features described above for the method and the corresponding technical effects are also applicable to Figure 4 The modules in it will not be described in detail here.

[0037] In some other embodiments, the embodiments of the present invention further provide a computer-readable storage medium having a computer program stored thereon, wherein when the program instructions are executed by a processor, the processor executes the transmission line inspection image super-resolution reconstruction method in any of the above method embodiments; As an implementation mode, the computer-readable storage medium of the present invention stores computer-executable instructions, and the computer-executable instructions are configured as follows: Acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; A super-resolution reconstruction network is constructed based on convolutional shape convolution, and the target inspection image is input as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The acquired real-time transmission line inspection image is input into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0038] The computer-readable storage medium may include a program storage area and a data storage area, wherein the program storage area may store an operating system and an application required by at least one function; the data storage area may store data created according to the use of the transmission line inspection image super-resolution reconstruction system, etc. In addition, the computer-readable storage medium may include a high-speed random access memory, and may also include a memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the computer-readable storage medium may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the transmission line inspection image super-resolution reconstruction system via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0039] Figure 5 is a schematic diagram of the structure of an electronic device provided by an embodiment of the present invention, such as Figure 5 As shown, the device includes: a processor 310 and a memory 320. The electronic device may also include: an input device 330 and an output device 340. The processor 310, the memory 320, the input device 330 and the output device 340 may be connected via a bus or other means. Figure 5 In the example, the connection through the bus is taken as an example. The memory 320 is the above-mentioned computer-readable storage medium. The processor 310 executes various functional applications and data processing of the server by running the non-volatile software programs, instructions and modules stored in the memory 320, that is, the transmission line inspection image super-resolution reconstruction method of the above-mentioned method embodiment is realized. The input device 330 can receive input digital or character information, and generate key signal input related to user settings and function control of the transmission line inspection image super-resolution reconstruction system. The output device 340 may include a display device such as a display screen.

[0040] The electronic device can execute the method provided by the embodiment of the present invention, and has the functional modules and beneficial effects corresponding to the execution method. For technical details not described in detail in this embodiment, please refer to the method provided by the embodiment of the present invention.

[0041] As an implementation mode, the electronic device is applied to a transmission line inspection image super-resolution reconstruction system, and is used for a client, and includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can: Acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; A super-resolution reconstruction network is constructed based on convolutional shape convolution, and the target inspection image is input as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: , In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The acquired real-time transmission line inspection image is input into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

[0042] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for super-resolution reconstruction of transmission line inspection images, characterized in that: include: Acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; A super-resolution reconstruction network is constructed based on convolutional shape convolution, and the target inspection image is input as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: ， In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The acquired real-time transmission line inspection image is input into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

2. A method for super-resolution reconstruction of power transmission line inspection images according to claim 1, characterized in that: The acquiring at least one power transmission line inspection image and performing Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image comprises: Perform edge detection on a transmission line inspection image, and convolve the transmission line inspection image with a Gaussian blur kernel to obtain a fuzzy transmission line inspection image. The expression for convolving the transmission line inspection image with a Gaussian blur kernel is: ， ， In the formula, is the midpoint of the fuzzy transmission line inspection image The pixel value at is the midpoint of the transmission line inspection image The pixel value at is the Gaussian kernel, is the convolution operation, is the standard deviation of the Gaussian kernel, which controls the degree of blur; The transmission line inspection image and the fuzzy transmission line inspection image are fused to obtain a target inspection image, which is expressed as: ， ， In the formula, The midpoint of the target inspection image The pixel value at is the edge strength of each pixel in the image, is the weight factor, is the maximum edge intensity value in the fuzzy transmission line inspection image.

3. The method for super-resolution reconstruction of power transmission line inspection images according to claim 1, characterized in that: The target super-resolution reconstruction model includes: Input layer; A parallel convolutional convolutional layer connected to the input layer, wherein the parallel convolutional convolutional layer includes a first convolutional convolutional layer with a convolution kernel of 9x9, a second convolutional convolutional layer with a convolution kernel of 5x5, and a third convolutional convolutional layer with a convolution kernel of 3x3; an HDSA module connected to the parallel convolutional convolutional layer; and The reconstruction layer connected with the HDSA module.

4. A method for super-resolution reconstruction of power transmission line inspection images according to claim 3, characterized in that: The step of inputting the acquired real-time transmission line inspection image into the target super-resolution reconstruction model, wherein the target super-resolution reconstruction model outputs a reconstructed image, comprises: The real-time transmission line inspection image is respectively input into a first convolutional convolutional layer with a convolution kernel of 9x9, a second convolutional convolutional layer with a convolution kernel of 5x5, and a third convolutional convolutional layer with a convolution kernel of 3x3, and the first convolution result, the second convolution result, and the third convolution result are obtained as the corresponding outputs; splicing the first convolution result, the second convolution result and the third convolution result to obtain a first output image; Inputting the first output image into the HDSA module, and performing deep attention feature fusion on the first feature map according to the HDSA module to obtain a second output image; Subjecting the second output image to a convolutional convolution with a kernel size of 5 and a convolutional convolution with a kernel size of 3 in sequence to obtain a third output image; The third output image and the real-time power transmission line inspection image are input into a reconstruction layer, and high-level features in the third output image are mapped into the real-time power transmission line inspection image according to the reconstruction layer, so as to finally obtain a reconstructed image.

5. A method for super-resolution reconstruction of power transmission line inspection images according to claim 4, characterized in that: The performing deep attention feature fusion on the first feature map according to the HDSA module to obtain a second output image comprises: Perform feature projection on the first feature map, and the expression is: ， In the formula, is the query vector, is the key vector, is a value vector, is the weight matrix of the query vector, is the weight matrix of the key vector, is the weight matrix of the value vector, is the first feature map; The query vector and key vector The spatial dimension of is flattened, and the expression is: ， ， ， ， In the formula, , represents the spatial position after flattening, is the total number of spatial points in the feature map, is the flattened query matrix, is the number of output batches, for The number of channels, , are the length and width of the output position, respectively. is the flattened bond matrix, for The number of channels, is the feature map batch; Calculate the attention weights of the flattened query matrix and the flattened key matrix respectively to get the attention matrix, which is expressed as: ， In the formula, is the attention matrix, is the normalized attention weight, is the transpose of the flattened bond matrix; A deformable convolution calculation is performed according to the value vector, and the output of the deformable convolution is weightedly fused according to the attention matrix to obtain a second output image, wherein the expression of the second output image is: ， In the formula, is the second output image, is the activation function, For batch normalization, is the projected convolution kernel, is the convolution operation, is the attention-weighted feature, is the original input.

6. A method for super-resolution reconstruction of power transmission line inspection images according to claim 4, characterized in that: The step of sequentially subjecting the second output image to a convolutional convolution with a kernel size of 5 and a convolutional convolution with a kernel size of 3 to obtain a third output image comprises: The second output image is input into the convolution with a kernel size of 5, and the first result is output, which is expressed as: ， In the formula, is a convolutional convolution with a kernel size of 5, is the second output image, For batch normalization, is the activation function, For channel splicing operations, is the left vertical convolution feature, is the right vertical convolution feature, is the upward horizontal convolution feature, It is the downward horizontal convolution feature; Among them, the expression of the left vertical convolution feature is: ， In the formula, After the left convolution operation, the position in the output feature map is The corresponding value, is the number of output batches, is the number of output channels, , are the length and width of the output position, respectively. is the vertical displacement within the nucleus, is the left convolution, is the number of input channels, Indicates that the second output image is Sampling is carried out at The expression of the right vertical convolution feature is: ， In the formula, To perform horizontal flip of the convolution kernel for left-to-left convolution; The expression of the upward vertical convolution feature is: ， In the formula, After the upward convolution operation, the position in the output feature map is The corresponding value, is the intranuclear horizontal shift, Indicates that the second output image is Sampling is carried out at The expression of the downward vertical convolution feature is: ， In the formula, To perform horizontal flipping of the convolution kernel for upward convolution; The first result is input into a first adaptive convolution module, and the second result is output. ， ， In the formula, is the second calculation result, is the first adaptive convolution module, is the residual weight coefficient, is the convolution operation, is the weighted input; The second result is input into the convolutional convolution with a kernel size of 3, and the third result is output. The third result is input into the second adaptive convolution module, and the third output image is output. The expression is: ， In the formula, is the third output image, is the second adaptive convolution module, is a convolution with a kernel size of 3.

7. A method for super-resolution reconstruction of power transmission line inspection images according to claim 4, characterized in that: The expression of the reconstructed image is: ， ， ， ， ， ， In the formula, To reconstruct the image, Reconstructing the image. For real-time transmission line inspection images, is the tanh output, the output range is [-1, 1], is the hyperbolic tangent function, is the feature map of the final output convolution, is the output feature after being processed by the LeakyReLU activation function, is a 3x3 convolution kernel with no bias. is the second bias term, is the result feature of batch normalization. is the slope of the negative semi-axis, is a learnable scaling parameter, is the mean along the channel dimension, is a learnable offset parameter, To prevent division by zero for small constants, is the variance along the channel dimension, is the dimensionality reduction convolution operation, is the convolution kernel parameter, is the output feature of the dimensionality reduction convolution, is the first bias term, is the third output image.

8. A transmission line inspection image super-resolution reconstruction system, characterized in that: include: An acquisition module is configured to acquire at least one power transmission line inspection image, and perform Sahara blur processing on the power transmission line inspection image to obtain at least one target inspection image; The training module is configured to construct a super-resolution reconstruction network based on convolutional shape convolution, and input the target inspection image as a training set into the super-resolution reconstruction network for training to obtain a target super-resolution reconstruction model, wherein the loss function of the target super-resolution reconstruction model is expressed as: ， In the formula, is the loss function of the target super-resolution reconstruction model, is the multi-scale deformation feature alignment loss weight value, are the features of BConv branches of different sizes in the HDSA module, The standard deviation is The Gaussian convolution kernel, is the L2 norm, For scale, is the multi-level attention consistent loss weight value, is the expected value, For the The attention weight of each channel, is a logarithmic function, Represents the feature map In the Variance calculation on channels, is a numerical stability term; The output module is configured to input the acquired real-time transmission line inspection image into the target super-resolution reconstruction model, and the target super-resolution reconstruction model outputs a reconstructed image.

9. An electronic device, characterized in that: include: At least one processor, and a memory communicatively connected to the at least one processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the method described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images