An adaptive image super-resolution reconstruction method of intelligent reconnaissance equipment

Abstract

The present application relates to the technical field of computer vision, and propose a kind of self-adapting image super-resolution reconstruction method of intelligent reconnaissance equipment, comprising the following steps: low-resolution image is collected by intelligent reconnaissance equipment;The low-resolution image is input into trained degradation model to extract features, and obtain first degradation feature;The low-resolution image is carried out no-reference image quality assessment, obtain the degradation type and degradation degree of image, then it is mapped into vector, obtain second degradation feature;The first degradation feature and second degradation feature are carried out feature fusion, and obtain comprehensive degradation vector feature;The low-resolution image and the comprehensive degradation vector feature are input into the super-resolution reconstruction model based on depth separable convolution and are handled, and obtain reconstructed high-resolution image;Wherein, the super-resolution reconstruction model is according to the adaptive adjustment of network layer according to the comprehensive degradation vector feature.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and more particularly to an adaptive image super-resolution reconstruction method for intelligent reconnaissance equipment. Background Art

[0002] Intelligent reconnaissance equipment, as observation devices mounted on drones and other vehicles, can be equipped with a variety of sensors and has demonstrated its unique application value in numerous fields. Whether in military reconnaissance, disaster monitoring, environmental assessment, or urban planning, intelligent reconnaissance equipment provides crucial image and data support. The accuracy and clarity of this image data directly impacts subsequent analysis and application. However, due to various factors such as flight speed, camera shake, and atmospheric interference, images captured by intelligent reconnaissance equipment often suffer from low resolution and blurred details. Image super-resolution technology, in particular, can restore high-resolution images from low-resolution ones, thereby improving image clarity and usability. Therefore, image super-resolution technology holds significant application prospects in the field of intelligent reconnaissance equipment.

[0003] Due to the complexity of flight conditions, images acquired by intelligent reconnaissance equipment may contain multiple types of degradation, such as motion blur, noise, and illumination variations. These complex degradation conditions make it difficult for traditional super-resolution methods to effectively restore image details. Secondly, existing super-resolution methods often rely on predefined degradation models, which may not be able to adapt to the complex degradation conditions of intelligent reconnaissance equipment images. Furthermore, the application scenarios of intelligent reconnaissance equipment often require real-time processing of large amounts of image data, which places higher demands on the efficiency and computing resources of super-resolution algorithms. Therefore, how to effectively address these issues and improve the performance and efficiency of super-resolution reconstruction of intelligent reconnaissance equipment images is of great research significance and application value. Summary of the Invention

[0004] In order to overcome the defect that the above-mentioned existing super-resolution reconstruction methods are difficult to effectively restore image details, the present invention provides an adaptive image super-resolution reconstruction method for intelligent reconnaissance equipment.

[0005] In order to solve the above technical problems, the technical solutions of the present invention are as follows:

[0006] An adaptive image super-resolution reconstruction method for intelligent reconnaissance equipment comprises the following steps:

[0007] Collect low-resolution images through intelligent reconnaissance equipment;

[0008] Inputting the low-resolution image into a trained degradation model to extract features and obtain a first degradation feature;

[0009] The low-resolution image is subjected to no-reference image quality assessment to obtain the degradation type and degradation degree of the image, and then the degradation type and degradation degree are mapped into a vector to obtain a second degradation feature;

[0010] The first degradation feature and the second degradation feature are subjected to feature fusion to obtain a comprehensive degradation vector feature;

[0011] The low-resolution image and the comprehensive degradation vector feature are input into a deep separable convolution-based super-resolution reconstruction model for processing to obtain a reconstructed high-resolution image; wherein the super-resolution reconstruction model performs adaptive adjustment of the number of network layers according to the comprehensive degradation vector feature.

[0012] Further, the present application also proposes a device comprising an intelligent reconnaissance equipment, wherein a memory and a processor are deployed on the intelligent reconnaissance equipment, the memory stores computer readable instructions, and the computer readable instructions are executed by the processor to make the processor execute all or part of the steps of the adaptive image super-resolution reconstruction method proposed by the present application.

[0013] Further, the present application also proposes a storage medium storing computer readable instructions, wherein the computer readable instructions are executed by a processor to implement all or part of the steps of the adaptive image super-resolution reconstruction method proposed by the present application.

[0014] Compared with the prior art, the beneficial effects of the technical scheme of the present application are:

[0015] The present application fuses the degradation features extracted by the degradation model and the no-reference image quality assessment results to obtain a comprehensive degradation vector feature, which is further used for super-resolution reconstruction, can more comprehensively understand and compensate image degradation, improves the accuracy and depth of feature extraction, and further enhances the quality and reliability of the reconstructed image;

[0016] The super-resolution reconstruction model in the present application performs adaptive adjustment of the number of network layers according to the comprehensive degradation vector feature, that is, the network structure and parameters can be optimized in real time according to different degradation vectors to adapt to the current image degradation, improves the generalization ability of the super-resolution reconstruction model, and enables the intelligent reconnaissance equipment to stably provide high-quality image output in various real environments, such as city monitoring, border patrol, disaster rescue, etc. BRIEF DESCRIPTION OF DRAWINGS

[0017] Figure 1 The present application is an adaptive image super-resolution reconstruction method according to an embodiment of the present application.

[0018] Figure 2The figure is a flow chart of an adaptive image super-resolution reconstruction method according to an embodiment of the present invention.

[0019] Figure 3 FIG. 4 is a training flow chart according to an embodiment of the present invention. DETAILED DESCRIPTION

[0020] Exemplary embodiments will be described in detail herein, examples of which are illustrated in the accompanying drawings. In the following description, when referring to the drawings, like numbers in different figures represent like or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments are not intended to represent all possible embodiments consistent with the present invention. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the present invention, as detailed in the appended claims.

[0021] The terms used in this invention are for the purpose of describing specific embodiments only and are not intended to limit the invention. The singular forms "a," "the," and "the" used in this invention and the appended claims are also intended to include plural forms unless the context clearly indicates otherwise. It should also be understood that the term "and / or" as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0022] It should be understood that although the terms "first," "second," "third," etc. may be used in the present invention to describe various information, such information should not be limited to these terms. These terms are merely used to distinguish information of the same type from one another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the present invention. Depending on the context, the term "if" as used herein may be interpreted as "when," "when," or "in response to determining."

[0023] The present invention is described in detail below with reference to the accompanying drawings and specific embodiments.

[0024] Example 1

[0025] This embodiment proposes an adaptive image super-resolution reconstruction method for intelligent reconnaissance equipment, such as Figure 1 、 2 FIG. 1 is a flow chart of the adaptive image super-resolution reconstruction method according to the present embodiment.

[0026] The adaptive image super-resolution reconstruction method proposed in this embodiment includes the following steps:

[0027] S1. Collect low-resolution images through intelligent reconnaissance equipment;

[0028] S2. Inputting the low-resolution image into a trained degradation model to extract features and obtain a first degradation feature;

[0029] S3. Performing a non-reference image quality assessment on the low-resolution image to obtain the degradation type and degradation degree of the image, and then mapping the obtained degradation type and degradation degree into a vector to obtain a second degradation feature;

[0030] S4. Fusing the first degradation feature and the second degradation feature to obtain a comprehensive degradation vector feature;

[0031] S5. Input the low-resolution image and the comprehensive degradation vector feature into a super-resolution reconstruction model based on depthwise separable convolution for processing to obtain a reconstructed high-resolution image; wherein the super-resolution reconstruction model adaptively adjusts the number of network layers according to the comprehensive degradation vector feature.

[0032] This embodiment uses the degree of degradation of low-resolution images obtained through no-reference image quality assessment as an explicit feature, and combines it with the degradation representation learned through the degradation model as an implicit feature, which is then further used for super-resolution reconstruction. This can more comprehensively understand and compensate for image degradation, effectively improve the accuracy and depth of feature extraction, and thus enhance the quality and reliability of the reconstructed image.

[0033] The super-resolution reconstruction model in this embodiment adaptively adjusts the number of network layers based on the comprehensive degradation vector features. That is, the network structure and parameters can be optimized in real time according to different degradation vectors to adapt to the current image degradation situation. This improves the generalization capability of the super-resolution reconstruction model and enables intelligent reconnaissance equipment to stably provide high-quality image output in changing real-world environments, such as urban monitoring, border patrols, disaster relief, and other scenarios.

[0034] In an optional embodiment, the intelligent reconnaissance equipment is equipped with a visible light image sensor and an edge computing device. The visible light image sensor is used to capture low-resolution images, which are then transmitted to the edge computing device via a high-speed data transmission interface for image super-resolution reconstruction.

[0035] For example, the intelligent reconnaissance equipment is equipped with an sCMOS camera, boasting an ultra-high resolution of 3200×3200 pixels and capable of capturing images at 498 frames per second while maintaining a quantum efficiency of up to 95%. This camera's design meets stringent requirements for image detail and acquisition speed, enabling it to produce high-quality images even in low-light conditions. This makes it particularly well-suited to the high-definition imagery required by intelligent reconnaissance equipment in fast-moving, dynamic environments. Furthermore, this high-speed acquisition capability enables the camera to continuously record rapidly occurring events without motion blur or loss of critical details, ensuring the acquisition of highly detailed and sharp image data, providing ideal input material for subsequent super-resolution image reconstruction.

[0036] For example, the intelligent reconnaissance equipment is equipped with a 64GB Jetson AGX Orin Developer Kit, an edge computing device with powerful hardware performance and flexible interface design, capable of processing high-resolution image data in real time. Through this efficient image acquisition and processing process, the intelligent reconnaissance equipment can provide high-quality raw image data for image super-resolution reconstruction tasks, significantly improving the clarity and detail of the reconstructed images and meeting the real-time requirements of the intelligent reconnaissance equipment during mission execution.

[0037] In an optional embodiment, the training process of the super-resolution reconstruction model includes the following steps:

[0038] Step 1: Collect high-resolution image samples, perform random degradation operations on the high-resolution image samples to obtain low-resolution image samples, and construct HR-LR image pairs as training data;

[0039] Step 2: Input the low-resolution image samples obtained through random degradation operation into the degradation model for feature extraction to obtain implicit degradation features;

[0040] Step 3: The degradation operation record and degradation parameters of the low-resolution image sample obtained through the random degradation operation are used as explicit degradation features;

[0041] Step 4: Fusing the implicit degradation features and the explicit degradation features to obtain a comprehensive degradation vector feature, and inputting the feature and the low-resolution image sample into the super-resolution reconstruction model for training to obtain a trained super-resolution reconstruction model.

[0042] like Figure 3 The figure shows the degradation model training flow chart of this embodiment.

[0043] Among them, the explicit degradation feature model can directly learn the impact of degradation operations, while the implicit degradation feature can help the model understand the interactions and overall impact of degradation operations.

[0044] The combination of dual degradation features selected in this embodiment can enhance the adaptability of the model to unknown or complex degradation situations, improve its robustness and generalization ability in practical applications, and further enable intelligent reconnaissance equipment to more comprehensively understand and compensate for image degradation when performing super-resolution reconstruction, thereby improving the accuracy and depth of feature extraction, and thereby enhancing the quality and reliability of the reconstructed image.

[0045] Furthermore, during the testing phase, a no-reference image quality assessment is performed on low-resolution image samples used as test data. The degree of image degradation is evaluated by calculating a series of objective metrics to obtain explicit degradation information for the low-resolution images, such as blur, noise, and compression. These degradation types and degrees are then mapped into vectors as explicit degradation features. These features are then combined with implicit degradation features extracted by the degradation model to generate a comprehensive degradation vector feature, which is then input into the super-resolution reconstruction model to complete the model testing.

[0046] In this embodiment, to simulate the real-world degradation process, a series of degradation operations and their parameters are predefined to degrade high-resolution images into low-resolution images. This allows for more realistic simulation of degradation in different scenarios, making the trained model more adaptable to inputs with various degradation types.

[0047] Furthermore, in an optional embodiment, performing a random degradation operation on the high-resolution image sample in step 1 to obtain a low-resolution image sample includes the following steps:

[0048] Step 1-1: For any high-resolution image I HR , randomly select K degradation operations from the preset degradation operations, and randomly select degradation parameters from the value range of [0,1] for each degradation operation, perform the corresponding degradation operation, and obtain K degraded low-resolution image samples I LR,k , k=1,2,...,K, where K is the preset number of degradation operations;

[0049] Step 1-2: Record each low-resolution image sample I LR,k The corresponding degradation operation and its parameters are used as the explicit degradation feature Among them, O k Represents a low-resolution image sample I LR,k The selected degradation operation, Denotes the degenerate operation O k The corresponding degradation parameter.

[0050] As an example, in step 1, a series of degradation operations are predefined, such as blur, noise, blur, etc., which are represented as O1, O2, O3, ..., O M , where each degradation operation has corresponding degradation parameters P1, P2, P3, ..., P M , used to control the degree of the degradation operation, and the value range of each parameter is 0-1, and its specific value is random. The expression is as follows:

[0051]

[0052] Among them, Random(a,b) means generating a random number in the interval [a,b]. Indicates the degradation operation O k Randomly selected degradation parameters. HR Randomly select the degradation operation and its parameters to generate the corresponding low-resolution image I LR , the specific formula is:

[0053]

[0054] Among them, DegradationOperations(·) represents a series of degradation operations on the image.

[0055] In this embodiment, the degradation model predefines various possible degradation conditions, such as blur, compression, and noise. This allows for more realistic simulation and compensation of degradation effects in low-resolution images during super-resolution reconstruction, thereby improving the quality and detail of the reconstructed image. This also enhances the image processing capabilities of intelligent reconnaissance equipment in complex environments and provides more accurate visual information for subsequent image analysis and decision-making.

[0056] Furthermore, in an optional embodiment, in step 2, the low-resolution image samples obtained by the random degradation operation are input into the degradation model for feature extraction; the steps include:

[0057] Step 2-1, cropping and dividing the input low-resolution image samples;

[0058] Step 2-2: Input the image blocks into the degradation model to perform feature extraction to obtain degradation features of each image block.

[0059] Traditional super-resolution methods often rely on accurately estimating degradation models, which requires extensive prior knowledge and manual adjustments. However, in practical applications, image degradation processes can be very complex and difficult to accurately estimate. By extracting and fusing known degradation information, this embodiment allows the model to learn abstract features of the degradation process, providing a more flexible and adaptable approach to handling unknown or complex degradation scenarios.

[0060] For illustrative purposes, this embodiment assumes that the degradation type within the same image is the same, but that the degradation across different images varies. During feature extraction, low-resolution images are first segmented and then feature extraction is performed. Each input low-resolution image is divided into 196 x 196 image blocks, and feature extraction is performed on each block.

[0061] Exemplarily, the degradation model includes a ResNet50 network. Then its expression is:

[0062] F i =ResNet50(X i )

[0063] Among them, X i Represents a low-resolution image I LR The i-th image block in F i Represents the features extracted from the i-th image block.

[0064] Furthermore, in an optional embodiment, the method further comprises the following steps:

[0065] The degradation model is subjected to degradation feature representation learning by an unsupervised learning method, and different degradation representations in the feature space are distinguished by a contrastive learning method; wherein different image blocks X from the same image are i and X j As positive sample pairs, different image patches X from different images i and X k As negative sample pairs, the objective function L is constructed with the goal of maximizing the similarity of positive sample pairs and minimizing the similarity of negative sample pairs. contrastive ; Its expression is:

[0066]

[0067] Among them, F i ,F j ,F k Represents image blocks X i ,X j ,X k degradation characteristics; τ is the temperature parameter used to control the comparison between positive and negative samples; sim(·,·) is the similarity calculation function.

[0068] This embodiment assumes that the degradation types of different image blocks corresponding to the same image are the same.

[0069] This embodiment uses a contrastive learning method to distinguish different degraded representations in the feature space, with the goal of bringing different image blocks of the same image (positive sample pairs) closer together in the feature space and moving image blocks of different images (negative sample pairs) further apart in the feature space.

[0070] Specifically, for each image block X i , the corresponding degenerate expression is F i ; Take another image block X of the image j , the corresponding degenerate expression is F j ; For the image block X of another image k , the corresponding degenerate expression is Fk Then, relative to F i In terms of i and F j are positive samples for each other; relative to F i , F k is a negative sample. The goal of the above formula is to maximize the similarity of positive sample pairs while minimizing the similarity of negative sample pairs, making the feature vectors of the same image patch closer and the feature vectors of different image patches farther apart. This approach helps the model better learn the differences between features, thereby improving its ability to recognize different images and degradation types.

[0071] Furthermore, in an optional embodiment, performing no-reference image quality assessment on the low-resolution image sample in step S3 includes the following steps:

[0072] Calculate the noise level of the image sample; its expression is:

[0073]

[0074] Among them, noise_score represents the noise level score of the image, std(I LR ) represents image I LR The standard deviation, mean(I LR ) represents image I LR The average value of

[0075] Calculate the compression level of image samples; the expression is:

[0076]

[0077] Among them, compression_ratio represents the compression degree score of the image, Originalsize(I LR ) represents the size of the original image, Compressedsize(I LR ) represents the compressed image size;

[0078] Calculate the blur noise of the image sample; its expression is:

[0079]

[0080] Among them, blue_score represents the blur score of the image, gradient_magnitude(I LR ) represents the gradient size of the image, H represents the height of the image, and W represents the width of the image. The gradient size can be obtained by calculating the gradient of the low-resolution image in the horizontal and vertical directions. Its expression is:

[0081]

[0082] Among them, G x,LR and G y,LR Represent the gradient of the image in the horizontal and vertical directions, I LR,i,j Represents the pixel value of the low image at position (i, j), H and W represent the height and width of the image respectively;

[0083] The noise level score, compression level score and blur level score of the image are mapped into vectors to obtain explicit degradation vector features.

[0084] Furthermore, in an optional embodiment, the super-resolution reconstruction model in step S5 adaptively adjusts the number of network layers according to the comprehensive degradation vector feature, including the following steps:

[0085] The number of network layers L is determined to be increased or decreased according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted; its expression is:

[0086]

[0087] Among them, L0 is the initial layer number of the basic network, Denotes the degenerate operation O k The corresponding degradation parameter; f layers (·) is used to dynamically adjust the number of network layers according to the degree of different degradation types; τ1, τ2 are preset degradation thresholds; λ1, λ2 are incremental coefficients used to determine the amount of increase in the number of network layers;

[0088] The number of filters F of each layer of the basic network is determined according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted to enhance the learning ability of feature degradation features; its expression is:

[0089]

[0090] Among them, F0 is the initial number of filters in each layer of the basic network, Denotes the degenerate operation O k The corresponding degradation parameter; g filters (·) is used to dynamically adjust the number of filters according to the degree of different degradation types; λ3 and λ4 are incremental coefficients used to determine the amount of increase in the number of filters;

[0091] The number of skip connections SC in the basic network is determined according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted; its expression is:

[0092]

[0093] wherein, wherein, SCO is the initial number of skip connections of the base network, T is a preset degradation degree threshold; D full is the overall degradation degree of the image; h sc (·) for dynamically adjusting the number of skip connections according to the overall degradation degree of the image; a is the rate of controlling the growth of skip connections, used to adjust the amount of increase of skip connections. Wherein, if the degradation vector indicates that the image degradation is more serious, the information flow from the deep layer to the shallow layer can be strengthened by increasing the skip connections; for the image with mild degradation, the number of skip connections can be reduced to simplify the network structure.

[0094] The embodiment according to the uneven situation of the degradation degree, selects the piecewise function to dynamically adjust the network layer and the filter number. Specifically, by setting the degradation threshold τ1, τ2, the network will be adjusted according to the different intervals of the degradation characteristics. When less than the threshold τ1, the network does not increase the additional layer and the filter number; when in the interval [τ1, τ2], the network increases a certain number of layers and a certain number of filter numbers; and when exceeds the threshold τ2, the network will significantly increase the number of layers and significantly increase the number of filters.

[0095] Wherein, the increment of the number of layers and the number of filters in each interval can be adjusted by setting λ1, λ2, λ3, λ4 to cope with different degradation complexities, so as to enhance the adaptability and generalization ability of the network while maintaining the computing efficiency.

[0096] Further, according to the size relationship between the overall degradation degree of the image and the preset threshold, when D full >T, it indicates that the degradation of the image is relatively serious, and the information is greatly lost, and the number of skip connections needs to be increased to further recover the detail information of the image and improve the generalization ability and recovery ability of the model; otherwise, the number of skip connections is not changed, indicating that the degradation of the current image is within an acceptable range.

[0097] The embodiment dynamically adjusts the network structure according to the degradation vector, so that the model can better cope with various complex degradation situations and improve the effect and quality of the super-resolution reconstruction of the low-resolution image. This adaptive adjustment mechanism significantly improves the image processing generalization ability of the intelligent reconnaissance equipment in various complex environments, ensures the high-quality output of the super-resolution reconstruction image, and can provide clear visual effect and accurate detail information in both long-distance reconnaissance and low-light monitoring tasks.

[0098] Further, in an optional embodiment, the super-resolution reconstruction model in the S5 step includes the following steps when performing super-resolution reconstruction:

[0099] Perform a depth-separable convolution operation on the input comprehensive degradation vector feature to obtain a high-resolution feature F HR ;

[0100] For the high-resolution feature F HR Upsample to generate high-resolution images Its expression is:

[0101]

[0102] Where M′ is a set of modulation coefficients used to modulate the features of different channels; Upsample(·) represents the upsampling operation.

[0103] Optionally, a loss function is designed to measure the difference between the reconstructed image and the true high-resolution image. The specific formula is as follows:

[0104]

[0105] Where λ is the regularization term weight and Ω(P) is the regularization term of the network parameters, including the modulation coefficient M′.

[0106] During the super-resolution reconstruction process in this embodiment, the intelligent reconnaissance equipment can not only handle common image degradation types, but also adapt to unknown or multiple complex degradation scenarios. This improved generalization capability enables the intelligent reconnaissance equipment to stably provide high-quality image output in diverse real-world environments, such as urban surveillance, border patrols, and disaster relief. Furthermore, this generalization capability means that the intelligent reconnaissance equipment can quickly adapt to new degradation patterns without requiring extensive retraining data, thereby improving its practicality and responsiveness.

[0107] Example 2

[0108] This embodiment proposes a device including intelligent reconnaissance equipment, wherein a memory and a processor are deployed on the intelligent reconnaissance equipment, and the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor performs all or part of the steps of the adaptive image super-resolution reconstruction method proposed in Example 1.

[0109] It can be understood that the system of this embodiment corresponds to the method of the above-mentioned embodiment 1, and the options in the above-mentioned embodiment 1 are also applicable to this embodiment, so they will not be described again here.

[0110] Example 3

[0111] This embodiment proposes a storage medium having computer-readable instructions stored thereon, wherein the computer-readable instructions, when executed by a processor, implement all or part of the steps of the adaptive image super-resolution reconstruction method proposed in Example 1.

[0112] Exemplarily, the storage medium includes, but is not limited to, a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and other media that can store program codes.

[0113] Exemplarily, the instructions, programs, code sets or instruction sets may be implemented using conventional programming languages.

[0114] Exemplarily, the processor includes but is not limited to a smart phone, a personal computer, a server, a network device, etc., and is used to execute all or part of the steps of the adaptive image super-resolution reconstruction method described in Example 1.

[0115] The terms in the drawings are for illustrative purposes only and are not to be construed as limiting the present invention;

[0116] Obviously, the above embodiments of the present invention are merely examples for the purpose of clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Those skilled in the art will appreciate that other variations or modifications can be made based on the above description. It is not necessary and impossible to enumerate all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the claims of the present invention.

Claims

1. An adaptive image super-resolution reconstruction method for intelligent reconnaissance equipment, characterized in that: The following steps are involved: Collect low-resolution images through intelligent reconnaissance equipment; Inputting the low-resolution image into a trained degradation model to extract features and obtain a first degradation feature; Performing a no-reference image quality assessment on the low-resolution image to obtain the degradation type and degradation degree of the image, and then mapping the obtained degradation type and degradation degree into a vector to obtain a second degradation feature; Fusing the first degradation feature and the second degradation feature to obtain a comprehensive degradation vector feature; Inputting the low-resolution image and the comprehensive degradation vector feature into a super-resolution reconstruction model based on depthwise separable convolution for processing to obtain a reconstructed high-resolution image; wherein the super-resolution reconstruction model adaptively adjusts the number of network layers according to the comprehensive degradation vector feature; The training process of the super-resolution reconstruction model includes the following steps: Collect high-resolution image samples, perform random degradation operations on the high-resolution image samples to obtain low-resolution image samples, and construct HR-LR image pairs as training data; The low-resolution image samples obtained through random degradation operation are input into the degradation model for feature extraction to obtain implicit degradation features; The degradation operation records and degradation parameters of the low-resolution image samples obtained by random degradation operation are used as explicit degradation features; The implicit degradation features and the explicit degradation features are fused to obtain a comprehensive degradation vector feature, which is input into the super-resolution reconstruction model together with the low-resolution image sample for training to obtain a trained super-resolution reconstruction model.

2. The adaptive image super-resolution reconstruction method according to claim 1, characterized in that: The step of performing a random degradation operation on the high-resolution image sample to obtain a low-resolution image sample comprises the following steps: For any high-resolution image I HR , randomly select K degradation operations from the preset degradation operations, and randomly select degradation parameters from the value range of [0,1] for each degradation operation, perform the corresponding degradation operation, and obtain K degraded low-resolution image samples I LR,k , k=1,2,...,K; Record each low-resolution image sample I LR,k The corresponding degradation operation and its parameters are used as the explicit degradation feature Among them, O k Represents a low-resolution image sample I LR,k The selected degradation operation, Denotes the degenerate operation O k The corresponding degradation parameter.

3. The adaptive image super-resolution reconstruction method according to claim 2, characterized in that: The step of inputting the low-resolution image samples obtained through random degradation operation into the degradation model for feature extraction comprises the following steps: Crop and block the input low-resolution image samples; The image blocks are input into the degradation model to perform feature extraction, and degradation features of each image block are obtained.

4. The adaptive image super-resolution reconstruction method according to claim 3, characterized in that: The method further comprises the following steps: The degradation model is subjected to degradation feature representation learning by an unsupervised learning method, and different degradation representations in the feature space are distinguished by a contrastive learning method; wherein different image blocks X from the same image are i and X j As positive sample pairs, different image patches X from different images i and X k As negative sample pairs, the objective function L is constructed with the goal of maximizing the similarity of positive sample pairs and minimizing the similarity of negative sample pairs. contrastive .

5. The adaptive image super-resolution reconstruction method according to claim 1, characterized in that: The step of performing no-reference image quality assessment on the low-resolution image comprises the following steps: Calculate the noise level of the image sample; its expression is: Among them, noise_score represents the noise level score of the image, std(I LR ) represents image I LR The standard deviation, mean(I LR ) represents image I LR The average value of Calculate the compression level of image samples; the expression is: Among them, compression_ratio represents the compression degree score of the image, Originalsize(I LR ) represents the size of the original image, Compressedsize(I LR ) represents the compressed image size; Calculate the blur noise of the image sample; its expression is: Among them, blue_score represents the blur score of the image, gradient_magnitude(I LR ) represents the gradient size of the image, H represents the height of the image, and W represents the width of the image; The noise level score, compression level score and blur level score of the image are mapped into vectors to obtain explicit degradation vector features.

6. The adaptive image super-resolution reconstruction method according to claim 1, characterized in that: The super-resolution reconstruction model adaptively adjusts the number of network layers according to the comprehensive degradation vector feature, comprising the following steps: The number of network layers L is determined to be increased or decreased according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted; its expression is: Among them, L0 is the initial layer number of the basic network, Denotes the degenerate operation O k The corresponding degradation parameter; f layers (·) is used to dynamically adjust the number of network layers according to the degree of different degradation types; τ1, τ2 are preset degradation thresholds; λ1, λ2 are incremental coefficients used to determine the amount of increase in the number of network layers; The number of filters F of each layer of the basic network is determined according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted; its expression is: Among them, F0 is the initial number of filters in each layer of the basic network, Denotes the degenerate operation O k The corresponding degradation parameter; g filters (·) is used to dynamically adjust the number of filters according to the degree of different degradation types; λ3 and λ4 are incremental coefficients used to determine the amount of increase in the number of filters; The number of skip connections SC in the basic network is determined according to the comprehensive degradation vector feature, and the super-resolution reconstruction model is adjusted; its expression is: Among them, SC0 is the initial jump connection number of the basic network, T is the preset degradation threshold; D full is the overall degradation degree of the image; h sc (·) is used to dynamically adjust the number of skip connections according to the overall degradation of the image; α is the rate at which the skip connections grow and is used to adjust the amount of skip connections added.

7. The adaptive image super-resolution reconstruction method according to any one of claims 1 to 6, characterized in that: When performing super-resolution reconstruction, the super-resolution reconstruction model includes the following steps: Perform a depth-separable convolution operation on the input comprehensive degradation vector feature to obtain a high-resolution feature F HR ; For the high-resolution feature F HR Upsample to generate high-resolution images Its expression is: Where M' is a set of modulation coefficients used to modulate the features of different channels; Upsample(·) represents the upsampling operation.

8. A device comprising intelligent reconnaissance equipment, characterized in that: The intelligent reconnaissance equipment is deployed with a memory and a processor, the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the processor performs all or part of the steps of the adaptive image super-resolution reconstruction method according to any one of claims 1 to 7.

9. A storage medium having computer-readable instructions stored thereon, characterized in that: When the computer-readable instructions are executed by a processor, all or part of the steps of the adaptive image super-resolution reconstruction method according to any one of claims 1 to 7 are implemented.

Images