Lightweight image super-resolution reconstruction system and method for underground mobile equipment

Abstract

The invention discloses a lightweight image super-resolution reconstruction system and method for underground mobile equipment, and belongs to the technical field of image reconstruction. Comprising a shallow feature extraction module, a deep feature extraction module, a feature aggregation module and an image reconstruction module. The deep feature extraction module comprises a high-frequency enhanced distillation block, and the high-frequency enhanced distillation block comprises a feature refining module, a multi-scale information distillation module and an information fusion module; and the feature refining module comprises three high-frequency enhanced residual blocks which are connected in series. According to the method, an information distillation architecture is adopted, a two-way branch structure is adopted in a feature extraction trunk, channel segmentation is carried out on input features, the calculation amount is reduced, the capturing capacity of a network on detail information is improved by utilizing global feature extraction and high-frequency enhancement branches, and deep information is efficiently extracted; and adopting a multi-scale information distillation method to perform multi-scale high-frequency information distillation on the features after feature extraction trunk refinement, and fusing the distilled multi-scale high-frequency information by using a mixed feature enhancement block.

Description

Technical Field

[0001] The present invention belongs to the technical field of image reconstruction, and in particular relates to a lightweight image super-resolution reconstruction system and method for underground mobile equipment. Background Art

[0002] At present, underground mobile devices are widely used in complex environments. For example, mining vehicles are usually equipped with cameras to monitor the surrounding environment and avoid collisions; some modern drilling rigs are equipped with image acquisition systems that can monitor the drilling process in real time and analyze the rock structure; remote-controlled detection robots are equipped with high-resolution cameras and sensors to obtain environmental images and data for underground detection, inspection and safety monitoring. Due to the complex and harsh underground environment, severe lack of light, and limited reliance on lighting systems, the image brightness is uneven and the clarity is low. Dust and moisture introduce noise, which further affects the image quality. Therefore, there are still many difficulties in improving the image quality obtained by the equipment. At this time, image super-resolution reconstruction technology (SR) has become a better solution and has attracted more and more attention. SR is an image processing technology that aims to improve the quality of low-resolution images through algorithms to make them present higher-resolution visual effects. At present, there are many image super-resolution reconstruction algorithms based on deep learning. For example, the latest research uses conditional GAN ​​(cGAN) to generate high-resolution images and improve image details and realism through adversarial training. However, GAN models usually require a lot of computing resources and are difficult to implement real-time processing on mobile devices. Models such as SRCNN, VDSR, and ESPCN can restore image details to a certain extent by increasing network depth and optimizing convolutional layer design. However, their complexity is still high, which limits their application in resource-constrained underground environments. In order to meet the needs of mobile devices, researchers have begun to explore lightweight network architectures such as MobileNet and ShuffleNet. These models improve real-time performance by reducing the number of parameters and computational complexity, but their performance is limited and they cannot adapt to the changing underground environment.

[0003] Although similar technologies have made certain progress in image super-resolution reconstruction, they still face problems such as high computational complexity and poor adaptability in the application scenarios of underground mobile devices, and more efficient and adaptable technical solutions need to be developed. First, in the task of super-resolution reconstruction, high-frequency information is particularly critical for the reconstruction of image details. However, the detailed features in the underground environment are often weakened due to factors such as low illumination and noise, resulting in unsatisfactory results in the model when extracting high-frequency information and insufficient detail restoration of the reconstructed image. When used in the underground environment, the existing technology often requires a deeper and more complex network structure to compensate for the lack of detailed information, which significantly increases the computational overhead and makes it difficult to meet the real-time requirements of the underground environment. Secondly, there is a wealth of information of different scales in the underground image, and the detection of small devices and tiny targets requires the support of information of different scales. Most of the existing super-resolution models use fixed-scale feature extraction methods, lack an effective fusion mechanism for multi-scale features, and cannot flexibly cope with the detailed information of varying scales in the underground environment. This results in the model often being unable to take into account both the overall structure and local details when processing the same image. In addition, the model has high computational complexity and is difficult to be lightweight. Downhole equipment has very strict requirements on the computational complexity and storage space of the model. However, existing super-resolution models are usually deep neural networks with high computational complexity, high resource consumption, and high requirements on hardware performance. This limits the application of these models on mobile downhole equipment, especially in scenarios with high real-time processing requirements, and cannot guarantee fast response and real-time monitoring effects.

[0004] In summary, the existing algorithms have the following shortcomings:

[0005] 1. Most existing algorithms use deep and complex network structures to make up for the lack of detailed information, which requires a lot of computational overhead and lacks effective methods for extracting high-frequency information;

[0006] 2. Most existing algorithms use fixed-scale feature extraction methods, lack an effective fusion mechanism for multi-scale features, and cannot flexibly respond to detailed information with varying scales in the underground environment.

[0007] 3. The existing model has high computational complexity and a large number of parameters, making it difficult to lightweight and unable to meet real-time requirements.

[0008] Therefore, how to solve the problem of detailed information with variable scales in the underground environment and realize effective high-frequency information extraction. Summary of the invention

[0009] The object of the present invention is to provide a lightweight image super-resolution reconstruction system and method for underground mobile equipment to solve the problems raised in the above-mentioned background technology.

[0010] The object of the present invention is achieved as follows: a lightweight image super-resolution reconstruction system for underground mobile equipment, characterized in that: the reconstruction system includes a shallow feature extraction module, a deep feature extraction module, a feature aggregation module and an image reconstruction module;

[0011] The deep feature extraction module includes a high-frequency enhancement distillation block, which includes a feature refinement module, a multi-scale information distillation module and an information fusion module;

[0012] The feature refinement module includes three high-frequency enhancement residual blocks connected in series, which are used to extract and refine detail information layer by layer;

[0013] The multi-scale information distillation module includes four branches, including a first branch, a second branch, a third branch and a fourth branch, and each branch extracts high-frequency information through multi-scale sampling;

[0014] The information fusion module uses a hybrid feature enhancement block to perform information fusion.

[0015] Preferably, the high-frequency enhancement residual block includes global feature extraction, an upper high-frequency enhancement branch and a lower high-frequency enhancement branch, and the upper high-frequency enhancement branch includes a 3×3 convolution kernel, a 7×7 depth-separable convolution, a Sigmoid and a GELU activation function;

[0016] The lower high-frequency enhancement branch includes a maximum pooling layer, a 1×1 convolution kernel, and a GELU activation function. The maximum pooling layer extracts high-frequency information from the input features and enhances the high-frequency features through the 1×1 convolution kernel and the GELU activation function.

[0017] The outputs of the upper high-frequency enhancement branch and the lower high-frequency enhancement branch are connected through Concat and sent to a 1×1 convolution kernel to fuse the information, and finally a residual connection is introduced to fuse the input information.

[0018] Preferably, the four branches respectively use a 1×1 convolution kernel, the first branch inputs the original scale information, the second branch, the third branch and the fourth branch all subtract from the original input by downsampling and upsampling at different multiples to obtain multi-scale high-frequency information.

[0019] Preferably, the hybrid feature enhancement block HFEB includes Concat, C shuffle channels and 3×3 convolution kernel blocks. After distillation of four branches in the multi-scale information distillation module, it is connected through Concat features and then shuffled through C shuffle channels to enhance information exchange between different channels, and then a 3×3 convolution kernel is used to further extract deep features.

[0020] A lightweight image super-resolution reconstruction method for underground mobile equipment is characterized by:

[0021] Step S1: obtaining an original image of the underground mobile device, and using the original image to obtain a low-resolution image;

[0022] Step S2: inputting the input low-resolution image into the reconstruction system;

[0023] Step S3: extract shallow features using a shallow feature extraction module;

[0024] Step S4: extract deep features using high-frequency enhancement distillation blocks;

[0025] Step S5: performing feature aggregation using a feature aggregation module;

[0026] Step S6: Reconstructing the image using a sub-pixel volume method;

[0027] Step S7: The reconstruction system outputs a super-resolution image.

[0028] Preferably, in step S3, shallow feature extraction is performed using a shallow feature extraction module, specifically:

[0029] The feature extraction module uses a 3×3 convolution to extract shallow features from the input image. The process is expressed as:

[0030] F 0 =h(I LR );

[0031] Among them, h is the shallow feature extraction function, F 0 is the extracted shallow features.

[0032] Preferably, in step S4, the high-frequency enhanced distillation block is used to extract deep features, specifically:

[0033] Step S4-1: shallow features F extracted by shallow feature extraction module 0 The input is sent to multiple recursively stacked high-frequency enhancement distillation blocks to gradually refine and extract deep features. The process is expressed as:

[0034] F k =H k (F k-1 ),k=1,...,m;

[0035] Among them, H k is the kth HFEDB feature extraction function; F k is the output feature of the kth HFEDB; F k-1 is the output feature of the k-1th HFEDB and the input feature of the kth HFEDB; when k=1, F 0 is the extracted shallow features;

[0036] Step S4-2: Input the original scale information through the first branch, use 1×1 convolution to halve the number of channels of the input feature, and use it as the feature after distillation of the first branch information;

[0037] Step S4-3: through three series-connected high-frequency enhancement residual blocks HFERB, in each HFERB, the input features are respectively extracted and refined layer by layer through the upper high-frequency enhancement branch and the lower high-frequency enhancement branch;

[0038] Step S4-4: The information enhanced by the three high-frequency enhancement residual blocks is input into the second, third, and fourth branches respectively. Each branch is subtracted from the original input by different multiples of downsampling and upsampling to obtain multi-scale high-frequency information; then each branch uses 1×1 convolution to halve the number of channels of the input feature as the features after distillation of the second, third, and fourth information;

[0039] Step S4-5: The features after distillation of the four-way information are fused through the hybrid feature enhancement block HFEB. Let the input be F k-1 , the process is expressed as:

[0040] F Hi =H HFERB (F k-1 ),i=1,2,3;

[0041]

[0042] F k =H HFEB (F d );

[0043] Among them, H HFERB is the HFERB feature refinement function; F Hi For each HFERB output; F d is the feature after distillation of four-way information; C 1 It is a 1×1 convolution; It is a three-way downsampling operation, downsampling by 2 times, 4 times, and 8 times respectively; It is a three-way upsampling operation, upsampling by 2 times, 4 times, and 8 times respectively; H HFEB is the information fusion function.

[0044] Preferably, in step S5, feature aggregation is performed using a feature aggregation module, specifically:

[0045] The intermediate features output by the high-frequency enhancement distillation block are first aggregated by a 1×1 convolutional layer, then smoothed by a 3×3 convolutional layer, and finally added to the shallow features extracted in the first part. The process is expressed as:

[0046] F a =F0 +H a (Concat(F out1 ,...,F outm ));

[0047] Among them, H a represents the feature aggregation function, F a is the aggregated feature, F out1 ,...,F outm It represents the intermediate features output from the 1st HFEDB to the mth HFEDB, and Concat represents the feature connection operation.

[0048] Preferably, in step S6, a sub-pixel volume method is used to reconstruct the image, specifically:

[0049] Assuming the target magnification is r, first use 3×3 convolution to change the number of channels of the input feature map to r 2 , and then r for each pixel of the feature image 2 The channels are rearranged into an r×r region, corresponding to an r×r sub-block in the high-resolution image, so that the size is H×W×r 2 The feature image is rearranged into a high-resolution image of rH×rW×1, and the reconstruction process is expressed as:

[0050] I SR =R(F a );

[0051] Where R represents the reconstruction function, I SR is the output super-resolution image of the network.

[0052] Compared with the prior art, the present invention has the following improvements and advantages:

[0053] 1. Adopting the information distillation architecture, a dual-path branch structure is used in the feature extraction trunk to perform channel segmentation on the input features to reduce the amount of calculation. Then, the global feature extraction and high-frequency enhancement branches are used to enhance the network's ability to capture detailed information and efficiently extract deep information.

[0054] 2. A multi-scale information distillation method is used to perform multi-scale high-frequency information distillation on the features after feature extraction trunk refinement, and a hybrid feature enhancement block is used to fuse the distilled multi-scale high-frequency information.

[0055] 3. Construct a high-frequency enhancement distillation block. By connecting high-frequency enhancement residual blocks in series and using multi-scale high-frequency information distillation methods, the high-frequency information extraction method is optimized, and multi-scale information is efficiently extracted and integrated, thereby improving network performance while ensuring the lightweight requirements of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a structural diagram of the reconstruction system of the present invention.

[0057] Figure 2 Flow chart of the method of the present invention.

[0058] Figure 3 It is a structural diagram of the high frequency enhancement distillation module HFEDB in the present invention.

[0059] Figure 4 It is a structural diagram of the high frequency enhanced residual block HFERB in the present invention.

[0060] Figure 5 It is a structural diagram of the hybrid feature enhancement block HFEB in the present invention. DETAILED DESCRIPTION

[0061] The present invention is further summarized below with reference to the accompanying drawings.

[0062] like Figure 1 As shown, a lightweight image super-resolution reconstruction system for underground mobile equipment, the reconstruction system includes a shallow feature extraction module, a deep feature extraction module, a feature aggregation module and an image reconstruction module;

[0063] The shallow feature extraction module extracts shallow features from the input image through a 3×3 convolution. The process is expressed as:

[0064] F 0 =h(I LR );

[0065] Among them, h is the shallow feature extraction function, F 0 is the extracted shallow features.

[0066] like Figure 3 As shown, the deep feature extraction module includes a high-frequency enhancement distillation block, and the high-frequency enhancement distillation block includes a feature refinement module, a multi-scale information distillation module and an information fusion module;

[0067] The feature refinement module consists of three serially connected high-frequency enhancement residual blocks, which are used to extract and refine detail information layer by layer; Figure 4 As shown in the figure, the high-frequency enhancement residual block includes global feature extraction, an upper high-frequency enhancement branch and a lower high-frequency enhancement branch. The upper high-frequency enhancement branch includes a 3×3 convolution kernel, a 7×7 depth-separable convolution, a Sigmoid and a GELU activation function; the 3×3 convolution is used to extract local features, and the 7×7 depth-separable convolution can expand the receptive field while ensuring computational efficiency. The Sigmoid function generates weights that reflect the global importance of pixels, which are multiplied pixel by pixel with the extracted local features to enhance the features that are beneficial to image restoration and are output through the GELU activation function.

[0068] The lower high-frequency enhancement branch includes a maximum pooling layer, a 1×1 convolution kernel, and a GELU activation function. The maximum pooling layer extracts high-frequency information from the input features and enhances the high-frequency features through a 1×1 convolution kernel and a GELU activation function. The outputs of the upper high-frequency enhancement branch and the lower high-frequency enhancement branch are connected through Concat and sent to the 1×1 convolution kernel to fuse the information. Finally, a residual connection is introduced to fuse the input information.

[0069] The multi-scale information distillation module includes four branches, including the first branch, the second branch, the third branch and the fourth branch. Each branch extracts high-frequency information through multi-scale sampling; the information fusion module uses a hybrid feature enhancement block for information fusion.

[0070] The four branches use 1×1 convolution kernels respectively. The first branch inputs the original scale information, and the second, third and fourth branches subtract the original input by downsampling and upsampling at different multiples to obtain multi-scale high-frequency information.

[0071] The information fusion module uses a hybrid feature enhancement block for information fusion, such as Figure 5 As shown in the figure, the hybrid feature enhancement block HFEB includes Concat, C shuffle channels and 3×3 convolution kernel blocks. After the distillation of four branches in the multi-scale information distillation module, it is connected through the Concat feature and then shuffled through the C shuffle channel to enhance the information exchange between different channels, and then a 3×3 convolution kernel is used to further extract deep features.

[0072] like Figure 2 As shown, a lightweight image super-resolution reconstruction method for an underground mobile device comprises the following steps:

[0073] Step S1: obtaining an original image of the underground mobile device, and using the original image to obtain a low-resolution image;

[0074] Step S2: inputting the input low-resolution image into the reconstruction system;

[0075] Step S3: extract shallow features using a shallow feature extraction module;

[0076] Step S4: extract deep features using high-frequency enhancement distillation blocks;

[0077] The high-frequency enhancement distillation block is used to extract deep features, specifically:

[0078] Step S4-1: shallow features F extracted by shallow feature extraction module 0 The input is sent to multiple recursively stacked high-frequency enhancement distillation blocks to gradually refine and extract deep features. The process is expressed as:

[0079] Fk =H k (F k-1 ),k=1,...,m;

[0080] Among them, H k is the kth HFEDB feature extraction function; F k is the output feature of the kth HFEDB; F k-1 is the output feature of the k-1th HFEDB and the input feature of the kth HFEDB; when k=1, F 0 is the extracted shallow features;

[0081] Step S4-2: Input the original scale information through the first branch, use 1×1 convolution to halve the number of channels of the input feature, and use it as the feature after distillation of the first branch information;

[0082] Step S4-3: through three series-connected high-frequency enhancement residual blocks HFERB, in each HFERB, the input features are respectively extracted and refined layer by layer through the upper high-frequency enhancement branch and the lower high-frequency enhancement branch;

[0083] Step S4-4: The information enhanced by the three high-frequency enhancement residual blocks is input into the second, third, and fourth branches respectively. Each branch is subtracted from the original input by different multiples of downsampling and upsampling to obtain multi-scale high-frequency information; then each branch uses 1×1 convolution to halve the number of channels of the input feature as the features after distillation of the second, third, and fourth information;

[0084] Step S4-5: The features after distillation of the four-way information are fused through the hybrid feature enhancement block HFEB. Let the input be F k-1 , the process is expressed as:

[0085] F Hi =H HFERB (F k-1 ),i=1,2,3;

[0086]

[0087] F k =H HFEB (F d );

[0088] Among them, H HFERB is the HFERB feature refinement function; F Hi For each HFERB output; F d is the feature after distillation of four-way information; C 1 It is a 1×1 convolution; It is a three-way downsampling operation, downsampling by 2 times, 4 times, and 8 times respectively; It is a three-way upsampling operation, upsampling by 2 times, 4 times, and 8 times respectively; H HFEB is the information fusion function.

[0089] Step S5: performing feature aggregation using a feature aggregation module;

[0090] Use the feature aggregation module to perform feature aggregation, specifically:

[0091] The intermediate features output by the high-frequency enhancement distillation block are first aggregated by a 1×1 convolutional layer, then smoothed by a 3×3 convolutional layer, and finally added to the shallow features extracted in the first part. The process is expressed as:

[0092] F a =F 0 +H a (Concat(F out1 ,...,F outm ));

[0093] Among them, H a represents the feature aggregation function, F a is the aggregated feature, F out1 ,...,F outm It represents the intermediate features output from the 1st HFEDB to the mth HFEDB, and Concat represents the feature connection operation.

[0094] Step S6: Reconstructing the image using a sub-pixel volume method;

[0095] The sub-pixel volume method is used for image reconstruction, specifically:

[0096] Assuming the target magnification is r, first use 3×3 convolution to change the number of channels of the input feature map to r 2 , and then r for each pixel of the feature image 2 The channels are rearranged into an r×r region, corresponding to an r×r sub-block in the high-resolution image, so that the size is H×W×r 2 The feature image is rearranged into a high-resolution image of rH×rW×1, and the reconstruction process is expressed as:

[0097] I SR =R(F a );

[0098] Where R represents the reconstruction function, I SR is the output super-resolution image of the network.

[0099] Step S7: The reconstruction system outputs a super-resolution image.

[0100] The present invention proposes a high-frequency enhanced residual block with dual-path branches, which improves the network's ability to capture detail information. Compared with traditional deep and complex networks, this efficient design can reduce computational overhead while maintaining the integrity of detail information.

[0101] Most existing algorithms use fixed-scale feature extraction methods and lack an effective fusion mechanism for multi-scale features. This makes them inflexible when dealing with variable-scale detail information in underground environments, and affects the reconstruction effect. The present invention proposes a multi-scale sampling high-frequency information distillation method, which performs multi-scale high-frequency information distillation on the refined features and combines them with a hybrid feature enhancement block for effective fusion, thereby enhancing the model's ability to deal with variable detail information in underground environments, thereby improving the reconstruction effect.

[0102] The invention optimizes the extraction process of high-frequency information by connecting high-frequency enhancement residual blocks in series with multi-scale high-frequency information distillation methods. This design not only improves the performance of the network, but also fully considers the lightweight of the model, ensures its real-time requirements on mobile equipment underground, and meets the strict requirements of computational complexity and parameter quantity.

[0103] 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 image super-resolution reconstruction system for underground mobile equipment, characterized by: The reconstruction system includes a shallow feature extraction module, a deep feature extraction module, a feature aggregation module and an image reconstruction module; The deep feature extraction module includes a high-frequency enhancement distillation block, which includes a feature refinement module, a multi-scale information distillation module and an information fusion module; The feature refinement module includes three high-frequency enhancement residual blocks connected in series, which are used to extract and refine detail information layer by layer; The multi-scale information distillation module includes four branches, including a first branch, a second branch, a third branch and a fourth branch, and each branch extracts high-frequency information through multi-scale sampling; The information fusion module uses a hybrid feature enhancement block to perform information fusion.

2. The lightweight image super-resolution reconstruction system for underground mobile equipment according to claim 1, characterized in that: The high-frequency enhancement residual block includes global feature extraction, an upper high-frequency enhancement branch and a lower high-frequency enhancement branch, and the upper high-frequency enhancement branch includes a 3×3 convolution kernel, a 7×7 depth-separable convolution, a Sigmoid and a GELU activation function; The lower high-frequency enhancement branch includes a maximum pooling layer, a 1×1 convolution kernel, and a GELU activation function. The maximum pooling layer extracts high-frequency information from the input features and enhances the high-frequency features through the 1×1 convolution kernel and the GELU activation function. The outputs of the upper high-frequency enhancement branch and the lower high-frequency enhancement branch are connected through Concat and sent to a 1×1 convolution kernel to fuse the information, and finally a residual connection is introduced to fuse the input information.

3. The lightweight image super-resolution reconstruction system for underground mobile equipment according to claim 1, characterized in that: The four branches use 1×1 convolution kernels respectively, the first branch inputs the original scale information, the second branch, the third branch and the fourth branch are subtracted from the original input by downsampling and upsampling at different multiples to obtain multi-scale high-frequency information.

4. The lightweight image super-resolution reconstruction system for underground mobile equipment according to claim 1, characterized in that: The hybrid feature enhancement block HFEB includes Concat, C shuffle channels and 3×3 convolution kernel blocks. After the distillation of four branches in the multi-scale information distillation module, it is connected through Concat features and then shuffled through C shuffle channels to enhance the information exchange between different channels, and then a 3×3 convolution kernel is used to further extract deep features.

5. The method for generating and reconstructing a lightweight image super-resolution reconstruction system for underground mobile equipment according to any one of claims 1 to 4, characterized in that: Step S1: obtaining an original image of the underground mobile device, and obtaining a low-resolution image using the original image; Step S2: inputting the input low-resolution image into the reconstruction system; Step S3: extract shallow features using a shallow feature extraction module; Step S4: extract deep features using high-frequency enhancement distillation blocks; Step S5: performing feature aggregation using a feature aggregation module; Step S6: Reconstructing the image using a sub-pixel volume method; Step S7: The reconstruction system outputs a super-resolution image.

6. The lightweight image super-resolution reconstruction method for underground mobile equipment according to claim 5, characterized in that: In step S3, shallow feature extraction is performed using a shallow feature extraction module, specifically: The shallow feature extraction module uses a 3×3 convolution to extract shallow features from the input image. The process is expressed as: F0=h(I LR ); Among them, h is the shallow feature extraction function, and F0 is the extracted shallow feature.

7. The lightweight image super-resolution reconstruction method for underground mobile equipment according to claim 5, characterized in that: In step S4, the high-frequency enhancement distillation block is used to extract deep features, specifically: Step S4-1: The shallow feature F0 extracted by the shallow feature extraction module is input into multiple recursively stacked high-frequency enhancement distillation blocks to gradually refine and extract deep features. The process is expressed as follows: F k =H k (F k-1 ),k=1,...,m; Among them, H k is the kth HFEDB feature extraction function; F k is the output feature of the kth HFEDB; F k-1 is the output feature of the k-1th HFEDB and the input feature of the kth HFEDB; when k=1, F0 is the extracted shallow feature; Step S4-2: Input the original scale information through the first branch, use 1×1 convolution to halve the number of channels of the input feature, and use it as the feature after distillation of the first branch information; Step S4-3: through three series-connected high-frequency enhancement residual blocks HFERB, in each HFERB, the input features are respectively extracted and refined layer by layer through the upper high-frequency enhancement branch and the lower high-frequency enhancement branch; Step S4-4: The information enhanced by the three high-frequency enhancement residual blocks is input into the second, third, and fourth branches respectively. Each branch is subtracted from the original input by different multiples of downsampling and upsampling to obtain multi-scale high-frequency information; then each branch uses 1×1 convolution to halve the number of channels of the input feature as the features after distillation of the second, third, and fourth information; Step S4-5: The features after distillation of the four-way information are fused through the hybrid feature enhancement block HFEB. Let the input be F k-1 , the process is expressed as: F Hi =H HFERB (F k-1 ),i=1,2,3; F k =H HFEB (F d ); Among them, H HFERB is the HFERB feature refinement function; F Hi For each HFERB output; F d It is the feature after four-way information distillation; C1 is 1×1 convolution; It is a three-way downsampling operation, downsampling by 2 times, 4 times, and 8 times respectively; It is a three-way upsampling operation, upsampling by 2 times, 4 times, and 8 times respectively; H HFEB is the information fusion function.

8. The lightweight image super-resolution reconstruction method for underground mobile equipment according to claim 5, characterized in that: In step S5, feature aggregation is performed using a feature aggregation module, specifically: The intermediate features output by the high-frequency enhancement distillation block are first aggregated by a 1×1 convolutional layer, then smoothed by a 3×3 convolutional layer, and finally added to the shallow features extracted in the first part. The process is expressed as: F a =F0+H a (Concat(F out1 ,...,F outm )); Among them, H a represents the feature aggregation function, F a is the aggregated feature, F out1 ,...,F outm It represents the intermediate features output from the 1st HFEDB to the mth HFEDB, and Concat represents the feature connection operation.

9. The lightweight image super-resolution reconstruction method for underground mobile equipment according to claim 5, characterized in that: In step S6, the sub-pixel volume method is used to reconstruct the image, specifically: Assuming the target magnification is r, first use 3×3 convolution to change the number of channels of the input feature map to r 2 , and then r for each pixel of the feature image 2 The channels are rearranged into an r×r region, corresponding to an r×r sub-block in the high-resolution image, so that the size is H×W×r 2 The feature image is rearranged into a high-resolution image of rH×rW×1, and the reconstruction process is expressed as: I SR =R(F a ); Where R represents the reconstruction function, I SR is the output super-resolution image of the network.

Images