Remote sensing image feature extraction model pre-training method and system based on frequency domain feature variation

Abstract

The present invention discloses a method and system for pre-training a remote sensing image feature extraction model based on frequency domain feature variation, and belongs to the technical field of remote sensing image processing. The pre-training method comprises the following steps: S1: constructing a remote sensing image feature extraction model based on frequency domain feature variation; wherein the remote sensing image feature extraction model based on frequency domain feature variation comprises a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module and a reconstruction module; the frequency domain feature variation processing module comprises a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimension reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module; S2: pre-training the remote sensing image feature extraction model based on frequency domain feature variation using remote sensing images. The present invention can more accurately capture the refined features of remote sensing images, thereby improving their performance accuracy on downstream tasks.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing image processing, and more particularly to a remote sensing image feature extraction model pre-training method and system based on frequency domain feature variation. Background Art

[0002] Remote sensing imagery holds broad application prospects in fields such as national defense and security, environmental monitoring, and urban planning. Remote sensing image interpretation has long been a research priority in the field, with object detection and instance segmentation in remote sensing images being particularly sought-after. Current mainstream remote sensing image interpretation methods primarily design and train models based on a supervised training paradigm. These models, built on convolutional neural networks, undergo feature extraction, feature fusion, and feature decomposition, and then output masks of potential target regions, along with predicted bounding boxes and type information. However, supervised model training requires extensive annotation information, including object categories, locations, and boundaries, often requiring significant human and material resources. This results in significant labor costs and hinders the scalability of these models to similar interpretation tasks. In contrast, unsupervised model pre-training methods can learn semantic relationships between image features without any annotations. In practical applications, they require only fine-tuning on downstream tasks such as object detection and instance segmentation to achieve good detection accuracy. This approach significantly reduces annotation costs, significantly improving the scalability and generalization of remote sensing image interpretation models. However, due to the characteristics of remote sensing images such as complex background and target scale transformation, conventional vision-based pre-training methods perform poorly and are often limited by the interference of remote sensing image noise, which makes it difficult for the model to effectively capture the refined features of typical remote sensing targets, and thus has poor accuracy performance in downstream tasks.

[0003] Therefore, how to provide a remote sensing image feature extraction model pre-training method and system that can more accurately capture the refined features of remote sensing images and thereby improve their performance accuracy in downstream tasks is an urgent problem that technicians in this field need to solve. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide a remote sensing image feature extraction model pre-training method and system based on frequency domain feature variation.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A remote sensing image feature extraction model pre-training method based on frequency domain feature variation includes the following steps:

[0007] S1: Constructing a remote sensing image feature extraction model based on frequency domain feature variation; wherein, the remote sensing image feature extraction model based on frequency domain feature variation includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module and a reconstruction module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimensionality reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module;

[0008] S2: Use remote sensing images to pre-train the remote sensing image feature extraction model based on frequency domain feature variation.

[0009] Preferably, S2 specifically includes:

[0010] The remote sensing image is input into the noise adding module to add Gaussian noise to obtain a noisy image.

[0011] Preferably, S2 specifically further includes:

[0012] Inputting the remote sensing image into the fast Fourier transform module to obtain a phase vector and an amplitude vector;

[0013] Inputting the amplitude vector into the convolution module and the multi-layer perceptron module in sequence to obtain a denoised amplitude vector;

[0014] The denoised amplitude vector and the phase vector are combined and input into the first inverse Fourier transform module to obtain a denoised image.

[0015] Preferably, S2 specifically further includes:

[0016] The denoised amplitude vector is added to the amplitude vector, and then combined with the phase vector and input into the first inverse Fourier transform module to obtain a denoised image.

[0017] Preferably, S2 specifically further includes:

[0018] Inputting the phase vector into the feature dimension reduction module to obtain a reduced-dimensional phase vector;

[0019] Inputting the amplitude vector into the upsampling module to obtain an upsampled amplitude vector;

[0020] The dimension-reduced phase vector and the up-sampled amplitude vector are combined and input into the second inverse Fourier transform module to obtain a loss frequency image.

[0021] Preferably, S2 specifically further includes:

[0022] Input the remote sensing image into the mask module for random masking to obtain the masked remote sensing image data MASK ;

[0023] The mask remote sensing image data MASK Modeled as a word vector F that can be input to the Transformer encoder M ; where the relative position encoding is added to the word vector F M middle;

[0024] The word vector F M Input to the Transformer encoder to obtain the feature map F trans ;

[0025] The mask remote sensing image data MASK Modeled as the feature map F trans Word vectors of the same shape

[0026] The feature map F trans and the word vector Add together to obtain the complete feature map F All ;

[0027] The complete feature map F All Input to the Transformer decoder to obtain the output sequence F out ;

[0028] The output sequence F out The data is input to the reconstruction module, and the reconstruction module reconstructs the remote sensing image according to the relative position code to obtain a remote sensing reconstructed image.

[0029] Preferably, during the pre-training process, KL divergence loss is used to perform loss calculation on the loss frequency image and the denoised image.

[0030] Preferably, during the pre-training process, the following loss function is used to calculate the loss of the denoised image, the noisy image and the remote sensing reconstructed image in pixel space:

[0031]

[0032] Among them, Loss represents the loss function; MSE represents the pixel mean square error; represents the remote sensing reconstructed image; Img_G represents the noisy image; Img_NoNoise represents the denoised image; a and b represent weight coefficients, and the optimization direction of the model is determined by adjusting the weight coefficients a and b.

[0033] A remote sensing image feature extraction model pre-training system based on frequency domain feature variation includes a frequency domain feature variation processing module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimensionality reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module;

[0034] The noise adding module is used to add Gaussian noise to the remote sensing image to obtain a noisy image;

[0035] The fast Fourier transform module is used to perform fast Fourier transform on the remote sensing image to obtain a phase vector and an amplitude vector;

[0036] The convolution module is used to perform a convolution operation on the amplitude vector;

[0037] The multi-layer perceptron module is used to optimize the amplitude vector after convolution to obtain the denoised amplitude vector;

[0038] The feature dimension reduction module is used to perform dimension reduction processing on the phase vector to obtain a reduced-dimensional phase vector;

[0039] The upsampling module is used to perform upsampling processing on the amplitude vector to obtain an upsampled amplitude vector;

[0040] The first inverse Fourier transform module is used to perform an inverse Fourier transform on the combined denoised amplitude vector and the phase vector to obtain a denoised image;

[0041] The second inverse Fourier transform module is used to perform inverse Fourier transform on the combined reduced-dimensional phase vector and the up-sampled amplitude vector to obtain a loss frequency image.

[0042] Preferably, the above system further includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module, and a reconstruction module;

[0043] The mask module is used to randomly mask the remote sensing image to obtain the mask remote sensing image data MASK ;

[0044] The Transformer encoder is used to transform the word vector F M Encode and obtain the feature map F trans ; Among them, the word vector F that can be input to the Transformer encoder M Based on the mask remote sensing image data MASK Modeling is obtained, and the relative position encoding is added to the word vector F M middle;

[0045] The Transformer decoder is used to complete the feature map F All Decode and obtain the output sequence F out ; Wherein, the mask remote sensing image data MASK Modeled as the feature map F trans Word vectors of the same shape Then, the feature map F trans Add together to obtain the complete feature map F All ;

[0046] The reconstruction module is used to reconstruct the output sequence F according to the relative position code out Perform remote sensing image reconstruction to obtain a remote sensing reconstructed image.

[0047] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a method and system for pre-training a remote sensing image feature extraction model based on frequency domain feature variation, which can achieve the following beneficial technical effects:

[0048] 1) The present invention can more accurately capture the refined features of remote sensing images, thereby improving their performance accuracy in downstream tasks.

[0049] 2) The remote sensing image feature extraction model pre-training method based on frequency domain feature variation proposed in this invention can effectively improve the quality of remote sensing image feature maps during the feature extraction process, help the model fully explore the different characteristics of typical remote sensing targets in different frequency domain feature expressions during the pre-training stage, and then obtain higher quality pre-training weights, which has better performance in downstream tasks.

[0050] 3) The remote sensing image feature extraction network pre-training model based on frequency domain feature variation proposed in the present invention establishes the connection between noise-added / denoised / lost frequency images in multiple dimensions during the frequency domain feature processing according to the differential properties of feature maps in frequency domain feature representation, guiding the model to learn the differentiated feature information of remote sensing targets, thereby better capturing the contextual feature information about potential target areas, and helping the model to understand the image content more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0052] Figure 1 A schematic diagram of the structure of a remote sensing image feature extraction model based on frequency domain feature variation provided by the present invention;

[0053] Figure 2 The present invention provides a flowchart of a remote sensing image feature extraction model pre-training method based on frequency domain feature variation. DETAILED DESCRIPTION

[0054] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0055] like Figure 2 As shown, the embodiment of the present invention discloses a remote sensing image feature extraction model pre-training method based on frequency domain feature variation, comprising the following steps:

[0056] S1: Constructing a remote sensing image feature extraction model based on frequency domain feature variation; wherein, the remote sensing image feature extraction model based on frequency domain feature variation includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module and a reconstruction module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimensionality reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module;

[0057] S2: Use remote sensing images to pre-train the remote sensing image feature extraction model based on frequency domain feature variation.

[0058] Furthermore, S2 specifically includes:

[0059] The remote sensing image is input into the noise adding module to add Gaussian noise to obtain a noisy image.

[0060] The process can be formally expressed as:

[0061] Img_G=GaussianNoise(Img);

[0062] Where Img∈R H×W×C Represents the input remote sensing image, C represents the channel information, H*W represents the shape of the remote sensing image; GaussianNoise represents the Gaussian noise operation; Img_G represents the noisy image, and its shape is consistent with Img.

[0063] Furthermore, S2 specifically includes:

[0064] Inputting the remote sensing image into the fast Fourier transform module to obtain a phase vector and an amplitude vector;

[0065] The process can be formally expressed as:

[0066] P,A=FFT(Img);

[0067] Among them, FFT represents the fast Fourier transform module; P and A represent the phase vector and amplitude vector obtained by the fast Fourier transform module respectively.

[0068] Inputting the amplitude vector into the convolution module and the multi-layer perceptron module in sequence to obtain a denoised amplitude vector;

[0069] Specifically: The amplitude vector A is extracted through the convolution module to obtain multiple feature maps F A =[F1,F2,…,F i ,…,F n ], Among them H i ×W i Represents the feature map F i Dimensions, C i Represents the feature map F i The number of channels, i represents the convolution extraction after i layers.

[0070] The multilayer perceptron module is the core operator of the frequency domain feature variation processing module. Its calculation process can be formally expressed as follows:

[0071] F i-mlp =MLP(F i );

[0072] Among them, MLP represents the multi-layer perceptron module, which is composed of C i input neurons, C i *10 hidden layer neurons and 3 output neurons, which transport information interactively by assigning dynamic weights to each channel to capture high-value channel information during the learning process; F i-mlp is the feature map output after the multi-layer perceptron module, that is, the optimized amplitude vector, which is the denoised amplitude vector; F i-mlp Has the same shape as the amplitude vector A.

[0073] The denoised amplitude vector and the phase vector are combined and input into the first inverse Fourier transform module to obtain a denoised image.

[0074] The process can be formally expressed as:

[0075] Img_NoNoise=iFFT(P,Fi-mlp );

[0076] Among them, iFFT represents the first inverse Fourier transform module; Img_NoNoise represents the denoised image, whose shape is consistent with the input remote sensing image Img.

[0077] Furthermore, S2 specifically includes:

[0078] The denoised amplitude vector is added to the amplitude vector, and then combined with the phase vector and input into the first inverse Fourier transform module to obtain a denoised image.

[0079] Furthermore, S2 specifically includes:

[0080] Inputting the phase vector into the feature dimension reduction module to obtain a reduced-dimensional phase vector;

[0081] Inputting the amplitude vector into the upsampling module to obtain an upsampled amplitude vector;

[0082] It can be understood that in order to help the model pay more attention to low-frequency feature information during pre-training, the phase vector and amplitude vector are processed using the feature dimensionality reduction module and the upsampling module to reduce their resolution. This process can be formally expressed as:

[0083] P_l=FDR(P);

[0084] A_l=Upsample(A);

[0085] Among them, Upsample represents the upsampling module, which is used to standardize the shape of the feature map for subsequent calculations; FDR represents the feature dimensionality reduction module, which is used to map the high-dimensional channel features of the feature map to a lower dimension to standardize the dimensional shape of the feature map and facilitate subsequent calculations; P_l represents the dimensionality reduction phase vector; A_l represents the upsampled amplitude vector;

[0086] After upsampling and feature dimensionality reduction, the amplitude vector A and phase vector P, containing frequency domain feature information of different dimensions, are processed into lower-resolution shapes. The purpose of using different feature dimension processing methods here is to maximize the preservation of the difference information contained in the different feature maps without losing it due to operator characteristics.

[0087] The dimension-reduced phase vector and the up-sampled amplitude vector are combined and input into the second inverse Fourier transform module to obtain a loss frequency image.

[0088] The process can be formally expressed as:

[0089] Img_low=iFFT(P_1,A_1);

[0090] Wherein, iFFT represents the second inverse Fourier transform module; Img_low represents the loss frequency image.

[0091] Furthermore, S2 specifically includes:

[0092] Input the remote sensing image into the mask module for random masking to obtain the masked remote sensing image data MASK ;

[0093] Specifically: the remote sensing image is loaded and enhanced through the data loader and then input into the mask module. The calculation process of the data loader is expressed as:

[0094] data=f dataloder (img);

[0095] Where Img∈R H×W×C represents the input remote sensing image, C represents the channel information, and H*W represents the shape of the remote sensing image; f dataloder Represents the data loader function, which is used to load data and data enhancement; data represents the remote sensing image input to the mask module;

[0096] The mask remote sensing image data MASK Modeled as a word vector F that can be input to the Transformer encoder M ; where the relative position encoding is added to the word vector F M middle;

[0097] Specifically: word vector F M =[F1,F2,…,F i ,…,F n ], Among them C i Indicates channel information, N i is the i-th word vector with a shape of 1*1.

[0098] Relative position encoding is used to determine the relative position of each word vector to facilitate subsequent remote sensing image reconstruction.

[0099] The word vector F M Input to the Transformer encoder to obtain the feature map F trans ;

[0100] It can be understood that the Transformer encoder uses a self-attention mechanism to calculate the word vector to capture the contextual feature relationship of the potential target area. The calculation process can be formally expressed as:

[0101] F trans =Transformerencoder (F M );

[0102] Among them, F trans Represents the feature map obtained by the Transformer encoder, Transformer encoder Represents the Transformer encoder, and its calculation process can be expressed as:

[0103]

[0104] Among them, Q represents the query matrix, K represents the key value, and V represents the value matrix. The three are composed of the input word vector F M Obtained through linear mapping.

[0105] The mask remote sensing image data MASK Modeled as the feature map F trans Word vectors of the same shape

[0106] The feature map F trans and the word vector Add together to obtain the complete feature map F All ;

[0107] The calculation process can be formally expressed as:

[0108] The complete feature map F All Input to the Transformer decoder to obtain the output sequence F out ;

[0109] The output sequence F out The data is input to the reconstruction module, and the reconstruction module reconstructs the remote sensing image according to the relative position code to obtain a remote sensing reconstructed image.

[0110] The calculation process can be formally expressed as:

[0111] F out =Transformer decoder (F All );

[0112] Among them, Transformer decoder Denotes the Transformer decoder, which maps the input to the word vector probability of a given output through the self-attention mechanism to obtain a prediction of the content of each sequence. out is the output sequence obtained after the Transformer decoder, which will be reconstructed into the remote sensing image imgs according to the relative position encoding Re .

[0113] Furthermore, during the pre-training process, KL divergence loss is used to perform loss calculation on the loss frequency image and the denoised image.

[0114] It can be understood that in order to promote the effective expression of the target features of the remote sensing image in the frequency domain dimension of the difference, the KL divergence loss is used to calculate the loss of the lost frequency image and the denoised image. The calculation process can be formally expressed as:

[0115] loss1=KLloss(Img_low,Img_NoNoise);

[0116] KLloss stands for KL divergence loss, a quantitative metric that estimates the difference between two probability distributions. By reducing loss1 during self-supervised training, the model can be effectively guided to perceive the difference between the loss frequency image and the denoised image, leading to a more effective understanding of remote sensing image content.

[0117] Furthermore, during the pre-training process, the following loss function is used to calculate the loss of the denoised image, the noisy image, and the remote sensing reconstructed image in the pixel space:

[0118]

[0119] Among them, Loss represents the loss function; MSE represents the pixel mean square error; represents the remote sensing reconstructed image; Img_G represents the noisy image; Img_NoNoise represents the denoised image; a and b represent weight coefficients, and the optimization direction of the model is determined by adjusting the weight coefficients a and b.

[0120] It can be understood that the pre-trained remote sensing image feature extraction model based on frequency domain feature variation is used as a feature extraction network to be fine-tuned on the remote sensing image target detection task and instance segmentation task to adapt to downstream tasks.

[0121] The model training for remote sensing image target detection and instance segmentation tasks is performed using focal loss (FocalLoss), rotated box intersection-over-union loss (RotatedIoULoss) and cross-entropy loss (CrossEntropyLoss), which can be formally expressed as:

[0122]

[0123] Among them, y represents the target true value label, Represents the model prediction result. Loss obj and Loss insThe total loss used in training for the object detection and instance segmentation tasks, respectively, is represented by FocalLoss; RotatedIoULoss represents the rotated box intersection-over-union loss; and CrossEntropyLoss represents the cross-entropy loss. Once the network is trained until the total loss no longer decreases, the network training reaches stability and the training process is complete. The trained remote sensing image object detection model and remote sensing image instance segmentation model based on frequency domain feature variation are obtained.

[0124] Furthermore, the trained target detection model and instance segmentation model are used to test the remote sensing image to be tested, which can be formally expressed as:

[0125]

[0126]

[0127] Among them, od-Detector represents the trained remote sensing image feature extraction model based on frequency domain feature variation as the target detection model of the feature extraction network, ins-Detector represents the trained remote sensing image feature extraction model based on frequency domain feature variation as the instance segmentation model of the feature extraction network, and x Test and They represent the remote sensing images to be tested and their corresponding prediction results respectively.

[0128] like Figure 1 As shown, an embodiment of the present invention further provides a remote sensing image feature extraction model pre-training system based on frequency domain feature variation, including a frequency domain feature variation processing module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimensionality reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module;

[0129] The noise adding module is used to add Gaussian noise to the remote sensing image to obtain a noisy image;

[0130] The fast Fourier transform module is used to perform fast Fourier transform on the remote sensing image to obtain a phase vector and an amplitude vector;

[0131] The convolution module is used to perform a convolution operation on the amplitude vector;

[0132] The multi-layer perceptron module is used to optimize the amplitude vector after convolution to obtain the denoised amplitude vector;

[0133] The feature dimension reduction module is used to perform dimension reduction processing on the phase vector to obtain a reduced-dimensional phase vector;

[0134] The upsampling module is used to perform upsampling processing on the amplitude vector to obtain an upsampled amplitude vector;

[0135] The first inverse Fourier transform module is used to perform an inverse Fourier transform on the combined denoised amplitude vector and the phase vector to obtain a denoised image;

[0136] The second inverse Fourier transform module is used to perform inverse Fourier transform on the combined reduced-dimensional phase vector and the up-sampled amplitude vector to obtain a loss frequency image.

[0137] Furthermore, the above system also includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module and a reconstruction module;

[0138] The mask module is used to randomly mask the remote sensing image to obtain the mask remote sensing image data MASK ;

[0139] The Transformer encoder is used to transform the word vector F M Encode and obtain the feature map F trans ; Among them, the word vector F that can be input to the Transformer encoder M Based on the mask remote sensing image data MASK Modeling is obtained, and the relative position encoding is added to the word vector F M middle;

[0140] The Transformer decoder is used to complete the feature map F All Decode and obtain the output sequence F out ; Wherein, the mask remote sensing image data MASK Modeled as the feature map F trans Word vectors of the same shape Then, the feature map F trans Add together to obtain the complete feature map F All ;

[0141] The reconstruction module is used to reconstruct the output sequence F according to the relative position code out Perform remote sensing image reconstruction to obtain a remote sensing reconstructed image.

[0142] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0143] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A remote sensing image feature extraction model pre-training method based on frequency domain feature variation, characterized in that: The following steps are involved: S1: construct a remote sensing image feature extraction model based on frequency domain feature variation; wherein the remote sensing image feature extraction model based on frequency domain feature variation includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module and a reconstruction module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimension reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module; S2: Pre-training the remote sensing image feature extraction model based on frequency domain feature variation using remote sensing images; S2 specifically includes: Inputting the remote sensing image into the noise adding module to add Gaussian noise to obtain a noisy image; Inputting the remote sensing image into the fast Fourier transform module to obtain a phase vector and an amplitude vector; Inputting the amplitude vector into the convolution module and the multi-layer perceptron module in sequence to obtain a denoised amplitude vector; Combining the denoised amplitude vector and the phase vector and inputting the combined vectors into the first inverse Fourier transform module to obtain a denoised image; After adding the denoised amplitude vector to the amplitude vector, the denoised amplitude vector is combined with the phase vector and input into the first inverse Fourier transform module to obtain a denoised image; Inputting the phase vector into the feature dimension reduction module to obtain a dimension-reduced phase vector; Inputting the amplitude vector into the up-sampling module to obtain an up-sampled amplitude vector; The dimension-reduced phase vector and the up-sampled amplitude vector are combined and input into the second inverse Fourier transform module to obtain a loss frequency image.

2. The remote sensing image feature extraction model pre-training method based on frequency domain feature variation according to claim 1 is characterized in that: S2 specifically includes: The remote sensing image is input into the mask module for random masking to obtain the masked remote sensing image data MASK ; The mask remote sensing image data MASK Modeled as a word vector F that can be input to the Transformer encoder M ; where the relative position encoding is added to the word vector F M middle; The word vector F M Input to the Transformer encoder to obtain the feature map F trans ; The mask remote sensing image data MASK Modeled as the feature map F trans Word vectors F of the same shape dataMASK ; The feature map F trans and the word vector F dataMASK Add together to get the complete feature map F All ; The complete feature map F All Input to the Transformer decoder to obtain the output sequence F out ; The output sequence F out The data is input to the reconstruction module, and the reconstruction module reconstructs the remote sensing image according to the relative position code to obtain the remote sensing reconstructed image.

3. The remote sensing image feature extraction model pre-training method based on frequency domain feature variation according to claim 2 is characterized in that: During the pre-training process, the KL divergence loss is used to calculate the loss of the loss frequency image and the denoised image.

4. The remote sensing image feature extraction model pre-training method based on frequency domain feature variation according to claim 2 is characterized in that: During the pre-training process, the following loss function is used to calculate the loss of the denoised image, the noisy image and the remote sensing reconstructed image in the pixel space: Among them, Loss represents the loss function; MSE represents the pixel mean square error; represents the remote sensing reconstructed image; Img_G represents the noisy image; Img_NoNoise represents the denoised image; a and b represent weight coefficients, and the optimization direction of the model is determined by adjusting the weight coefficients a and b.

5. A remote sensing image feature extraction model pre-training system based on frequency domain feature variation, characterized in that: It includes a frequency domain feature variation processing module; the frequency domain feature variation processing module includes a noise addition module, a fast Fourier transform module, a convolution module, a multi-layer perceptron module, a feature dimension reduction module, an upsampling module, a first inverse Fourier transform module and a second inverse Fourier transform module; The noise adding module is used to add Gaussian noise to the remote sensing image to obtain a noisy image; The fast Fourier transform module is used to perform fast Fourier transform on the remote sensing image to obtain a phase vector and an amplitude vector; The convolution module is used to perform a convolution operation on the amplitude vector; The multi-layer perceptron module is used to optimize the amplitude vector after convolution to obtain the denoised amplitude vector; The feature dimension reduction module is used to perform dimension reduction processing on the phase vector to obtain a dimension-reduced phase vector; The up-sampling module is used to perform up-sampling processing on the amplitude vector to obtain an up-sampled amplitude vector; The first inverse Fourier transform module is used to perform inverse Fourier transform on the combined denoised amplitude vector and the phase vector to obtain a denoised image; The second inverse Fourier transform module is used to perform an inverse Fourier transform on the combined reduced-dimensional phase vector and the up-sampled amplitude vector to obtain a loss frequency image.

6. The remote sensing image feature extraction model pre-training system based on frequency domain feature variation according to claim 5, characterized in that: It also includes a mask module, a Transformer encoder, a Transformer decoder, a frequency domain feature variation processing module, and a reconstruction module; The mask module is used to randomly mask the remote sensing image to obtain the mask remote sensing image data MASK ; The Transformer encoder is used to transform the word vector F M Encode and obtain the feature map F trans ; Wherein, the word vector F that can be input to the Transformer encoder M Based on the mask remote sensing image data MASK Modeling is obtained, and the relative position encoding is added to the word vector F M middle; The Transformer decoder is used to complete the feature map F All Decode and obtain the output sequence F out ; Wherein, the mask remote sensing image data MASK Modeled as the feature map F trans Word vectors of the same shape Then, with the feature map F trans Add together to obtain the complete feature map F All ; The reconstruction module is used to reconstruct the output sequence F according to the relative position code out Perform remote sensing image reconstruction to obtain a remote sensing reconstructed image.

Images