Light-weight mine image super-resolution reconstruction system and method based on depth feature calibration

Abstract

The invention belongs to the technical field of image resolution reconstruction, and discloses a lightweight mine image super-resolution reconstruction system and method based on depth feature calibration, the system comprises a shallow feature extraction layer, a deep feature extraction layer and a reconstruction module layer, and the reconstruction method comprises the following steps: extracting shallow features through the shallow feature extraction layer; the method comprises the following steps: firstly, superficial layer features are extracted, the superficial layer features are input into a plurality of stacked residual attention feature modules for deep feature extraction, firstly, the deep features are aggregated and then fused with the superficial layer features in the step 1, and the overlapped image is input into a reconstruction module layer for image reconstruction, so that a super-resolution image can be obtained. According to the method, a more accurate result is obtained in image reconstruction, and a better reconstruction effect is achieved for a mine image with a complex structure.

Description

Technical Field

[0001] The invention belongs to the technical field of image resolution and reconstruction, and in particular relates to a lightweight mine image super-resolution reconstruction system and method based on depth feature calibration. Background Art

[0002] Image super-resolution technology plays an important role in medical imaging, smart mining, computational photography and other fields. It aims to upgrade low-resolution images to high resolution to enhance the clarity and details of the image. The main super-resolution reconstruction methods currently include interpolation, reconstruction and learning.

[0003] Interpolation methods generally use bicubic interpolation and interpolation methods based on geometric features. Although the calculation is simple and fast, the generated images are obviously insufficient in details and authenticity, and are prone to artifacts such as image oscillation and edge blur. Reconstruction methods such as maximum a posteriori estimation and iterative backprojection use the prior knowledge and statistical characteristics of the image to try to infer the possible form of the high-resolution image from the low-resolution image. However, the reconstruction method has high computational complexity and is sensitive to the magnification factor. Different magnifications may require re-adjustment of model parameters, which brings certain limitations in practical applications. With the gradual maturity of machine learning technology, learning methods have begun to emerge in the field of image super-resolution. The neighborhood embedding method maps low-resolution image blocks to neighborhoods in the high-resolution image space and reconstructs high-resolution image blocks using the similarity between sample pairs. This method can capture the local features of the image to a certain extent, but has limited processing capabilities for complex scenes and large-scale images. The sparse representation method is based on the sparsity assumption of the image under a specific dictionary. It achieves high-resolution image reconstruction by learning the sparse representation coefficients of low-resolution and high-resolution image pairs. It shows certain advantages in processing image textures and details, but also faces problems of computational efficiency and model adaptability.

[0004] Chinese patent application ZL CN2023111940240 discloses a lightweight image super-resolution reconstruction system and method for edge mobile devices, in which the model can better utilize multi-scale information and improve the perception of details and overall structure, but does not continue to pay attention to more detailed information such as the edges and textures of the original low-resolution image, and there is neglect or loss of high-frequency information.

[0005] Chinese patent application ZL CN2023110111616 discloses a super-resolution reconstruction method for mine images based on residual mixed attention. The proposed multi-scale residual dense mixed attention super-resolution network pursues the improvement of indicators, but still has problems such as not paying attention to whether the reconstructed image is consistent with human perception, whether it is close to the true image, and the insufficient accuracy of the reconstructed image. At the same time, the network model in this patent application directly stacks the number of network modules, which improves the performance of the network while causing huge computational overhead, and is not suitable for application in mobile terminals or edge computing devices in mine environments.

[0006] In summary, the current super-resolution network often focuses on image reconstruction performance and ignores its application in mobile terminals in real life. In particular, mine video surveillance plays an important role in safety monitoring and alarm, but due to the unique environment and equipment limitations of mines, the mine pictures taken have more or less quality and visual problems. At this time, it is of great significance to reconstruct mine images through image super-resolution technology and then restore them to clear high-quality images. The computational cost of the super-resolution model is closely related to the number and structure of modules. As the network depth increases, the network does not make full use of the information of all convolutional layers and feature information of different granularities, resulting in insufficient richness of the reconstructed image; at the same time, the lightweight often lacks the guidance of global information, which makes the reconstructed image have a gap with the real image, which does not conform to the subjective perception of human vision. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a lightweight mine image super-resolution reconstruction system and method based on deep feature calibration, designs a deep feature calibration block and a deep feature calibration attention, and on this basis, further constructs a lightweight mine image super-resolution reconstruction system based on deep feature calibration. The system has a better reconstruction effect for mine images with complex structures.

[0008] In order to achieve the above object, the present invention is achieved through the following technical solutions:

[0009] The present invention is a lightweight mine image super-resolution reconstruction system based on deep feature calibration, the lightweight mine image super-resolution reconstruction system comprises a shallow feature extraction layer, a deep feature extraction layer and a reconstruction module layer, wherein:

[0010] The shallow feature extraction layer is a convolution layer with a kernel size of 3×3, which performs shallow feature extraction on the input image, and the output of the shallow feature extraction layer serves as the input of the deep feature extraction layer;

[0011] The deep feature extraction layer is composed of a plurality of residual attention feature modules (FARG), wherein the residual attention feature module (FARG) includes a deep feature calibration attention module (HFFCA) and a deep feature calibration module, wherein the deep feature calibration module includes a high frequency feature refinement module (HFFOB), a high frequency feature non-redundant module (HFNRB), and a multi-scale feature enhancement module (MSFEB);

[0012] The reconstruction module layer includes a sub-pixel convolution layer and a convolution layer with a kernel size of 3×3, and the sub-pixel convolution layer includes a convolution layer with a kernel size of 3×3.

[0013] The present invention provides a lightweight mine image super-resolution reconstruction method based on deep feature calibration, and the reconstruction method specifically comprises the following steps:

[0014] Step 1: extract shallow features from the input image through the shallow feature extraction layer to obtain extracted shallow features;

[0015] Step 2: Input the shallow features extracted in step 1 into multiple stacked residual attention feature modules (FARG) for deep feature extraction;

[0016] Step 3: Aggregate the output of each residual attention feature module (FARG) in step 2 and fuse it with the shallow features extracted in step 1;

[0017] Step 4: Input the features fused in step 3 into the image reconstruction module layer for image reconstruction, and output the reconstructed super-resolution image.

[0018] A further improvement of the present invention is that in step 1, shallow feature extraction is performed on the input image through the shallow feature extraction layer, and the expression is: F0 = Conv3 (I LR );

[0019] Among them, I LR is the input image; F0 is the extracted shallow feature; Conv3(·) is the convolution operation with a kernel size of 3×3.

[0020] A further improvement of the present invention is that in step 2, the extracted shallow features are input into multiple stacked residual attention feature modules (FARG) for deep feature extraction, which specifically includes the following steps:

[0021] Step 2.1, input the extracted shallow features into multiple cascaded deep feature calibration modules to fully extract high-frequency information that is conducive to image texture detail recovery, such as texture details, edge features, etc., while ensuring the non-redundancy of high-frequency information;

[0022] Step 2.2, the output of each deep feature calibration module is input into the deep feature calibration attention module (HFFCA) along the transmission path of the residual attention feature module to calibrate and select high-frequency information that is critical for image texture detail recovery;

[0023] Step 2.3, fuse the output of each deep feature calibration module and the output of the deep feature calibration attention module (HFFCA), and then pass it through channel contrast attention (CCA) to capture image features of different channel dimensions and obtain richer feature information, where the fusion is divided into feature aggregation path and attention aggregation path.

[0024] A further improvement of the present invention is that in step 2.1, the deep feature calibration module extracts high-frequency information that is beneficial to image texture detail recovery through a high-frequency feature refinement module (HFFOB), a high-frequency feature non-redundant module (HFNRB) and a multi-scale feature enhancement module (MSFEB), while ensuring the non-redundancy of the high-frequency information, specifically comprising the following steps:

[0025] Step 2.1.1, the high-frequency feature refinement module (HFFOB) uses upsampling and downsampling methods of different multiples, standard convolution and depth-separable convolution to extract high-frequency information, expressed as:

[0026] Y1=H LFEB (H Sampling (X1))

[0027] Y2=SConv(Gelu(DeConv(X1)))

[0028]

[0029] Among them, H Sampling (·) is the function after double, quadruple, and octave up- and down-sampling fusion, H LFEB (·) is the function of LFEB, DeConv(·) is a 2×2 deconvolution operation, SConv(·) is a strided convolution with a step size of 2, σ is the Sigmoid function, It is expressed as element-by-element multiplication, where Y is the output of the high-frequency feature refinement module HFFOB, and Y1 and Y2 are temporary tensors in the neural network;

[0030] Step 2.1.2, the high-frequency feature non-redundant module (HFNRB) uses maximum pooling, standard convolution, and depth-separable convolution to reduce repeated high-frequency information in feature propagation to ensure the non-redundancy of high-frequency information, which is expressed as:

[0031] Z1=H LEFB (X2′)

[0032] Z2=Gelu(Conv1(H Max (X″2)))

[0033] Z=Conv1(Cat(Z1+Z2))+X2

[0034] Among them, H Max (·) is the maximum pooling function, Z is the output of the high-frequency feature non-redundant module HNFRB, and Z1 and Z2 are temporary tensors in the neural network;

[0035] Step 2.1.3, the multi-scale feature enhancement module (MSFEB) guides and learns the global information of the features aggregated by the high-frequency feature refinement module (HFFOB) and the high-frequency feature non-redundant module (HFNRB) to obtain the comprehensive and rich output features of the multi-scale feature enhancement module (MSFEB), which is expressed as:

[0036] M1=Conv1(H CS (Cat(Y,Z)))

[0037]

[0038] M=DW 3×3 (Conv1(M2))+Gelu(DW 3×3 (Conv1(M2)))+X2

[0039] Among them, H CS (·) is the channel shuffle operation, DW m×n (·) is a depthwise separable convolution with kernel size m×n, M is the output of the multi-scale feature enhancement module (MSFEB), and M1 and M2 are temporary tensors in the neural network.

[0040] A further improvement of the present invention is that the step 2.2 specifically includes the following steps:

[0041] Step 2.2.1, take the output of the deep feature calibration module as the input feature, perform a 1×1 convolution operation on the input feature, and then perform a channel segmentation operation to divide the input feature into two parts;

[0042] Step 2.2.2: Use the parallel branches of maximum pooling and average pooling to input the features of step 2.2.1 into the maximum pooling branch and the average pooling branch respectively, which effectively highlights the information area and helps the model learn the main features of the image.

[0043] Step 2.2.3, multiply the output of the two parts after branching with the corresponding input through a convolution layer with a kernel size of 1×1 and a Sigmoid activation function to perform feature high-frequency calibration;

[0044] Step 2.2.4: The outputs of the two parts after branching are fused together through a convolutional layer with a kernel size of 1×1 and Concat splicing to form the output of the attention feature.

[0045] A further improvement of the present invention is that: in step 2.3, the output of each deep feature calibration module and the output of the deep feature calibration attention module (HFFCA) are fused, specifically: in the feature aggregation path, in order to effectively utilize the feature information, the feature output of each deep feature calibration module (HFFCB) is sent to the end of RAFG, and feature aggregation is performed. In the attention aggregation path, the attention output of each deep feature calibration module is directly sent to the deep feature calibration attention module to calibrate and select high-frequency information that is more critical to the image texture details, and then transmitted to the end of RAFG for aggregation. Finally, the channel contrast attention CCA is used to adjust the feature aggregation path and the feature information after the fusion of the attention aggregation path, so that it focuses on the key and important channel content, and then added to the initial input.

[0046] A further improvement of the present invention is that: the step 3 aggregates the output of each residual attention feature module and merges it with the shallow feature; it is expressed as:

[0047]

[0048] Among them, F FC n ,F AC n represents the feature output and attention output of the nth residual attention feature module, Concat(·) represents the cascade in the channel dimension; Conv1(·) is a 1×1 convolution, F ff Represents the output after feature fusion.

[0049] A further improvement of the present invention is that: in step 4, the fused features are input to the image reconstruction module layer for image reconstruction, and the reconstructed super-resolution image I is output. SR , expressed as:

[0050] I SR =Conv3(H PixelShuffle (F ff +F0))

[0051] Among them, H PixelShuffle (·) is the sub-pixel convolution layer, I SR is the reconstructed super-resolution image.

[0052] The beneficial effects of the present invention are:

[0053] The present invention designs a deep feature calibration block, which fully extracts high-frequency information that is beneficial to the recovery of image texture details through high-frequency feature refinement blocks and high-frequency feature non-redundant blocks, while ensuring the non-redundancy of high-frequency information; in addition, through a multi-scale feature enhancement module, the receptive field range is further expanded, and global information is captured, thereby improving the accuracy and visual quality of image reconstruction.

[0054] The present invention proposes deep feature calibration attention, which accurately calibrates and selects high-frequency information that is crucial for image texture detail recovery through high-frequency feature calibration attention, thereby obtaining more accurate results in image reconstruction.

[0055] Based on the deep feature calibration block and the deep feature calibration attention, the present invention further constructs a lightweight mine image super-resolution reconstruction system based on deep feature calibration, which has a better reconstruction effect for mine images with complex structures. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a structural framework diagram of the lightweight mine image super-resolution reconstruction system of the present invention.

[0057] Figure 2 It is a structural diagram of the depth feature calibration module of the present invention.

[0058] Figure 3 It is a visual comparison diagram of the reconstructed image of the method of the present invention and the four-fold reconstruction result of the low-resolution image on the mine image. DETAILED DESCRIPTION

[0059] The following will disclose the embodiments of the present invention with drawings. For the purpose of clear description, many practical details will be described together in the following description. However, it should be understood that these practical details should not be used to limit the present invention. That is to say, in some embodiments of the present invention, these practical details are not necessary.

[0060] like Figure 1As shown, the present invention is a lightweight mine image super-resolution reconstruction system based on deep feature calibration, characterized in that: the lightweight mine image super-resolution reconstruction system includes a shallow feature extraction layer, a deep feature extraction layer and a reconstruction module layer, wherein: the shallow feature extraction layer is a convolution layer with a kernel size of 3×3, and performs shallow feature extraction on the input image, and the output of the shallow feature extraction layer is used as the input of the deep feature extraction layer; the deep feature extraction layer is composed of multiple residual attention feature modules (FARG), and the residual attention feature module (FARG) includes a deep feature calibration attention module (HFFCA) and a deep feature calibration module, and the deep feature calibration module includes a high-frequency feature refinement module (HFFOB), a high-frequency feature non-redundant module (HFNRB), and a multi-scale feature enhancement module (MSFEB); the reconstruction module layer includes a sub-pixel convolution layer and a convolution layer with a kernel size of 3×3, and the sub-pixel convolution layer includes a convolution layer with a kernel size of 3×3.

[0061] When used, the low-resolution image is input into the shallow feature extraction module. LR After a 3×3 convolution, shallow features are extracted to obtain shallow features F0; shallow features F0 are processed by multiple residual attention feature modules to obtain deep features F n ; Deep feature F n After adding it to the shallow feature F0, it passes through the sub-pixel convolution layer and the 3×3 convolution to obtain the reconstructed super-resolution image I SR .

[0062] Based on the reconstruction system, the present invention also proposes a lightweight mine image super-resolution reconstruction method based on deep feature calibration, and the reconstruction method specifically includes the following steps:

[0063] Step 1: Perform shallow feature extraction on the input image through the shallow feature extraction layer to obtain the extracted shallow features, which are expressed as:

[0064] F0=Conv3(I LR );

[0065] Among them, I LR is the input image; F0 is the extracted shallow feature; Conv3(·) is the convolution operation with a kernel size of 3×3.

[0066] Step 2: Input the shallow features extracted in step 1 into multiple stacked residual attention feature modules (FARG) for deep feature extraction. The specific steps include:

[0067] Step 2.1: Input the extracted shallow features into multiple cascaded deep feature calibration modules to fully extract high-frequency information that is conducive to the restoration of image texture details, such as texture details, edge features, etc., while ensuring the non-redundancy of high-frequency information. The specific steps include the following:

[0068] Step 2.1.1, the high-frequency feature refinement module (HFFOB) uses upsampling and downsampling methods of different multiples, standard convolution and depth-separable convolution to extract high-frequency information, expressed as:

[0069] Y1=H LFEB (H Sampling (X1))

[0070] Y2=SConv(Gelu(DeConv(X1)))

[0071]

[0072] Among them, H Sampling (·) is the function after double, quadruple, and octave up- and down-sampling fusion, H LFEB (·) is the function of LFEB, DeConv(·) is a 2×2 deconvolution operation, SConv(·) is a strided convolution with a step size of 2, σ is the Sigmoid function, It is represented as element-by-element multiplication, where Y is the output of HFFOB, and Y1 and Y2 are temporary tensors in the neural network;

[0073] Step 2.1.2, the high-frequency feature non-redundant module (HFNRB) uses maximum pooling, standard convolution, and depth-separable convolution to reduce repeated high-frequency information in feature propagation to ensure the non-redundancy of high-frequency information, which is expressed as:

[0074] Z1=H LEFB (X′2)

[0075] Z2=Gelu(Conv1(H Max (X″2)))

[0076] Z=Conv1(Cat(Z1+Z2))+X2

[0077] Among them, H Max (·) is the maximum pooling function, Z is the output of HNFRB, Z1 and Z2 are temporary tensors in the neural network;

[0078] Step 2.1.3, the multi-scale feature enhancement module (MSFEB) guides and learns the global information of the features aggregated by the high-frequency feature refinement module (HFFOB) and the high-frequency feature non-redundant module (HFNRB) to obtain the comprehensive and rich output features of the multi-scale feature enhancement module (MSFEB), which is expressed as:

[0079] M1=Conv1(H CS (Cat(Y,Z)))

[0080]

[0081] M=DW 3×3 (Conv1(M2))+Gelu(DW 3×3 (Conv1(M2)))+X2

[0082] Among them, H CS (·) is the channel shuffle operation, DW m×n (·) is a depthwise separable convolution with kernel size m×n, M is the output of the multi-scale feature enhancement module (MSFEB), and M1 and M2 are temporary tensors in the neural network.

[0083] Step 2.2: Input the output of each deep feature calibration module into the deep feature calibration attention module (HFFCA) along the transmission path of the residual attention feature module to calibrate and select high-frequency information that is critical to image texture detail recovery. Specifically, the following steps are included:

[0084] Step 2.2.1, take the output of the deep feature calibration module as the input feature, perform a 1×1 convolution operation on the input feature, and then perform a channel segmentation operation to divide the input feature into two parts;

[0085] Step 2.2.2: Use the parallel branches of maximum pooling and average pooling to input the features of step 2.2.1 into the maximum pooling branch and the average pooling branch respectively, which effectively highlights the information area and helps the model learn the main features of the image.

[0086] Step 2.2.3, multiply the output of the two parts after branching with the corresponding input through a convolution layer with a kernel size of 1×1 and a Sigmoid activation function to perform feature high-frequency calibration;

[0087] Step 2.2.4: The outputs of the two parts after branching are fused together through a convolutional layer with a kernel size of 1×1 and Concat splicing to form the output of the attention feature.

[0088] Step 2.3, the output of each deep feature calibration module is fused with the output of the deep feature calibration attention module (HFFCA), and then it is passed through the channel contrast attention (CCA) to capture the image features of different channel dimensions and obtain richer feature information, wherein the fusion is divided into a feature aggregation path and an attention aggregation path, and the output of each deep feature calibration module is fused with the output of the deep feature calibration attention module (HFFCA), specifically: in the feature aggregation path, in order to effectively utilize the feature information, the feature output of each deep feature calibration module (HFFCB) is sent to the end of RAFG, and feature aggregation is performed, in the attention aggregation path, the attention output of each deep feature calibration module is directly sent to the deep feature calibration attention module to calibrate and select the high-frequency information that is more critical to the image texture details, and then transmitted to the end of RAFG for aggregation, finally, the channel contrast attention CCA is used to adjust the feature information after the fusion of the feature aggregation path and the attention aggregation path, so that it focuses on the key and important channel content, and then added to the initial input.

[0089] Step 3: Aggregate the output of each residual attention feature module (FARG) in step 2 and fuse it with the shallow features extracted in step 1, expressed as:

[0090]

[0091] Among them, F FC n ,F AC n represents the feature output and attention output of the nth residual attention feature module, Concat(·) represents the cascade in the channel dimension; Conv1(·) is a 1×1 convolution, F ff Represents the output after feature fusion.

[0092] Step 4: Input the features fused in step 3 into the image reconstruction module layer for image reconstruction, and output the reconstructed super-resolution image I SR , expressed as:

[0093] I SR =Conv3(H PixelShuffle (F ff +F0))

[0094] Among them, H PixelShuffle (·) is the sub-pixel convolution layer, I SR is the reconstructed super-resolution image.

[0095] In order to evaluate the feasibility and effectiveness of the method of the present invention, this embodiment is experimentally verified, and the specific contents are as follows:

[0096] like Figure 3 As shown, in order to further verify the superiority of the super-resolution image reconstruction method proposed in the present invention, a 4-fold image reconstruction experiment was conducted on a mine image dataset with complex textures, and the images reconstructed using the present method were compared with the results of low-resolution images. It can be clearly seen from these image results that compared with low-resolution images, the method proposed in the present invention can reconstruct images more realistically, and the images reconstructed by the method proposed in the present invention are basically consistent with the original images. This shows that the method proposed in the present invention has obvious superiority in image super-resolution reconstruction.

[0097] The above description is only an embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent substitution, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of the claims of the present invention.

Claims

1. A lightweight mine image super-resolution reconstruction system based on deep feature calibration, characterized by: The lightweight mine image super-resolution reconstruction system comprises a shallow feature extraction layer, a deep feature extraction layer and a reconstruction module layer, wherein: The shallow feature extraction layer is a convolution layer with a kernel size of 3×3, which performs shallow feature extraction on the input image, and the output of the shallow feature extraction layer serves as the input of the deep feature extraction layer; The deep feature extraction layer is composed of a plurality of residual attention feature modules (FARG), wherein the residual attention feature module (FARG) includes a deep feature calibration attention module (HFFCA) and a deep feature calibration module (HFFCB), and the deep feature calibration module includes a high-frequency feature refinement module (HFFOB), a high-frequency feature non-redundant module (HFNRB), and a multi-scale feature enhancement module (MSFEB); The reconstruction module layer includes a sub-pixel convolution layer and a convolution layer with a kernel size of 3×3, and the sub-pixel convolution layer includes a convolution layer with a kernel size of 3×3.

2. A lightweight mine image super-resolution reconstruction method based on deep feature calibration, characterized by: The lightweight mine image super-resolution reconstruction method implements the reconstruction system of claim 1, and the reconstruction method specifically comprises the following steps: Step 1: extract shallow features from the input image through the shallow feature extraction layer to obtain extracted shallow features; Step 2: Input the shallow features extracted in step 1 into multiple stacked residual attention feature modules (FARG) for deep feature extraction; Step 3: Aggregate the output of each residual attention feature module (FARG) in step 2 and fuse it with the shallow features extracted in step 1; Step 4: Input the features fused in step 3 into the image reconstruction module layer for image reconstruction, and output the reconstructed super-resolution image.

3. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 2 is characterized in that: In step 1, shallow feature extraction is performed on the input image through the shallow feature extraction layer, and the expression is: F0=Conv3(I LR ); Among them, I LR is the input image; F0 is the extracted shallow feature; Conv3(·) is the convolution operation with a kernel size of 3×3.

4. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 2 is characterized in that: In step 2, the extracted shallow features are input into multiple stacked residual attention feature modules (FARG) for deep feature extraction, which specifically includes the following steps: Step 2.1, input the extracted shallow features into multiple cascaded deep feature calibration modules to extract high-frequency information that is conducive to restoring image texture details while ensuring the non-redundancy of high-frequency information; Step 2.2: Input the output of each deep feature calibration module into the deep feature calibration attention module (HFFCA) along the transmission path of the residual attention feature module to calibrate and select high-frequency information; Step 2.3, fuse the output of each deep feature calibration module and the output of the deep feature calibration attention module (HFFCA), and then pass it through channel contrast attention (CCA) to capture image features of different channel dimensions and obtain feature information, wherein the fusion is divided into a feature aggregation path and an attention aggregation path.

5. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 4 is characterized in that: In step 2.1, the deep feature calibration module extracts high-frequency information that is beneficial to image texture detail recovery through a high-frequency feature refinement module (HFFOB), a high-frequency feature non-redundant module (HFNRB) and a multi-scale feature enhancement module (MSFEB), while ensuring the non-redundancy of the high-frequency information, specifically comprising the following steps: Step 2.1.1, the high-frequency feature refinement module (HFFOB) uses upsampling and downsampling methods of different multiples, standard convolution and depth-separable convolution to extract high-frequency information, expressed as: Y1=H LFEB (H Sampling (X1)) Y2=SConv(Gelu(DeConv(X1))) Among them, H Sampling (·) is the function after double, quadruple, and octave up- and down-sampling fusion, H LFEB (·) is the function of LFEB, DeConv(·) is a 2×2 deconvolution operation, SConv(·) is a strided convolution with a step size of 2, σ is the Sigmoid function, It is represented as element-by-element multiplication, where Y is the output of HFFOB, and Y1 and Y2 are temporary tensors in the neural network; Step 2.1.2, the high-frequency feature non-redundant module (HFNRB) uses maximum pooling, standard convolution, and depth-separable convolution to reduce repeated high-frequency information in feature propagation to ensure the non-redundancy of high-frequency information, which is expressed as: Z1=H LEFB (X2′) Z2=Gelu(Conv1(H Max (X2″))) Z=Conv1(Cat(Z1+Z2))+X2 Among them, H Max (·) is the maximum pooling function, Z is the output of HNFRB, Z1 and Z2 are temporary tensors in the neural network; Step 2.1.3, the multi-scale feature enhancement module (MSFEB) guides and learns the global information of the features aggregated by the high-frequency feature refinement module (HFFOB) and the high-frequency feature non-redundant module (HFNRB) to obtain the output features of the multi-scale feature enhancement module (MSFEB), which is expressed as: M1=Conv1(H CS (Cat(Y,Z))) <h2 style=";text-align:left;direction:ltr">M=DW<h2 style=";text-align:left;direction:ltr"> 3×3 <h2 style=";text-align:left;direction:ltr"> (Conv1(M2))+Gelu(DW<h2 style=";text-align:left;direction:ltr"> 3×3 <h2 style=";text-align:left;direction:ltr"> (Conv1(M2))+X2 Among them, H CS (·) is the channel shuffle operation, DW m×n (·) is a depthwise separable convolution with kernel size m×n, M is the output of the multi-scale feature enhancement module (MSFEB), and M1 and M2 are temporary tensors in the neural network.

6. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 4 is characterized in that: The step 2.2 specifically includes the following steps: Step 2.2.1, take the output of the deep feature calibration module as the input feature, perform a 1×1 convolution operation on the input feature, and then perform a channel segmentation operation to divide the input feature into two parts; Step 2.2.2: Use the parallel branches of maximum pooling and average pooling to input the features of step 2.2.1 into the maximum pooling branch and the average pooling branch respectively, which effectively highlights the information area and helps the model learn the main features of the image. Step 2.2.3, multiply the output of the two parts after branching with the corresponding input through a convolution layer with a kernel size of 1×1 and a Sigmoid activation function to perform feature high-frequency calibration; Step 2.2.4: The outputs of the two parts after branching are fused together through a convolutional layer with a kernel size of 1×1 and Concat splicing to form the output of the attention feature.

7. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 4 is characterized in that: In step 2.3, the output of each deep feature calibration module and the output of the deep feature calibration attention module (HFFCA) are fused. Specifically, in the feature aggregation path, the feature output of each deep feature calibration module (HFFCB) is sent to the end of RAFG, and feature aggregation is performed. In the attention aggregation path, the attention output of each deep feature calibration module is directly sent to the deep feature calibration attention module to calibrate and select high-frequency information, and then transmitted to the end of RAFG for aggregation. Finally, the channel contrast attention CCA is used to adjust the feature information after the fusion of the feature aggregation path and the attention aggregation path, so that it focuses on the key and important channel content, and then added to the initial input.

8. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 2 is characterized in that: The step 3 aggregates the output of each residual attention feature module and merges it with the shallow features; it is expressed as: Among them, F FC n ,F AC n represents the feature output and attention output of the nth residual attention feature module, Concat(·) represents the cascade in the channel dimension; Conv1(·) is a 1×1 convolution, F ff Represents the output after feature fusion.

9. The lightweight mine image super-resolution reconstruction method based on deep feature calibration according to claim 2 is characterized in that: The step 4 inputs the fused features into the image reconstruction module layer for image reconstruction, and outputs the reconstructed super-resolution image I SR , expressed as: I SR =Conv3(H PixelShuffle (F ff +F0)) Among them, H PixelShuffle (·) is the sub-pixel convolution layer, I SR is the reconstructed super-resolution image.

Images