A SAR image self-adaptive registration method based on GLU-Net-Evaluate

Abstract

The present application relates to the field of image processing, especially to a SAR image adaptive registration method based on GLU-Net-Evaluate; technical problem: when the SAR image is registered, the mature visible light image registration model is applied to the SAR image registration, due to the large difference between the characteristics and distribution of the visible light image and the SAR image, the effect is often poor, and due to the serious data scarcity problem of SAR image registration, not only the training and verification of the algorithm are affected, but also the overfitting and poor generalization performance problems may be caused; technical scheme: a SAR image adaptive registration method based on GLU-Net-Evaluate, comprising generating the final predicted optical flow field by using the optical flow estimation network, so as to complete the image registration; the present application trains the GLU-Net network by setting the transfer learning technology, then trains on the scarce SAR data, and adds the evaluation network, uses the evaluation network to guide the training on the SAR, can overcome the limitation of the existing method, and improve the performance of the SAR image registration.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a SAR image adaptive registration method based on GLU-Net-Evaluate. Background Art

[0002] Traditional SAR image registration research can be divided into two major categories of methods: feature matching-based and region-based methods; the core idea of ​​the region-based method is to define a similarity measurement criterion, use the intensity information of the image to calculate the similarity between the current window and the template at each position in the image to be registered, and estimate the geometric transformation model by optimizing the similarity between the reference image and the image to be registered; these methods usually perform image registration in a specific transform domain (such as Fourier domain, wavelet domain, etc.); for example, frequency domain matching uses Fourier transform to convert the image to the frequency domain and then perform registration; while wavelet transform uses wavelet transform to extract multi-scale features of the image for registration; commonly used similarity measurement criteria include mutual information, cross-accumulated residual entropy, normalized mutual information, etc.; however, region-based SAR image registration methods perform poorly in processing geometric differences and radiation differences in SAR images, have high computational complexity, and usually require a long computing time, which limits their widespread application; in contrast, deep learning-based registration methods have obvious development prospects; these methods take advantage of deep learning and can learn from large-scale samples through large-scale sample learning. SAR images can be registered with the help of deep learning, which can extract richer deep semantic information from SAR images. Compared with traditional methods, SAR registration methods based on deep learning can capture more complex image features and establish more refined image space mapping relationships. Through the feature representation of deep learning, registration methods can mine more abstract and discriminative features from SAR images, making the common features between SAR images more prominent and achieving more accurate image matching. This method based on deep learning not only performs well in cases with limited samples or complex scenes, but also can show excellent performance in large-scale data and diverse scenes. Therefore, deep learning methods have broad application potential, especially for specific application scenarios, rather than a general solution. When registering SAR images, the mature visible light image registration model is applied to SAR image registration. Due to the large differences in characteristics and distribution between visible light images and SAR images, the effect is often poor. In addition, due to the serious problem of data scarcity in SAR image registration, it not only has a negative impact on the training and verification of the algorithm, but may also lead to overfitting and poor generalization performance. Summary of the Invention

[0003] In order to overcome the problem that when registering SAR images, the mature visible light image registration model is applied to SAR image registration, but the effect is often poor due to the large differences in characteristics and distribution between visible light images and SAR images. In addition, due to the serious data scarcity problem in SAR image registration, it not only affects the training and verification of the algorithm, but also may lead to overfitting and poor generalization performance.

[0004] The technical solution of the present invention is: a SAR image adaptive registration method based on GLU-Net-Evaluate, comprising the following steps:

[0005] S11: performing data preprocessing on the input SAR image data to convert different SAR image data into standardized image data;

[0006] S12: Extract features from the preprocessed image data using a feature network;

[0007] S13: performing feature matching on the SAR image data after feature extraction, and finding the same feature points or feature areas in multiple SAR image data;

[0008] S14: Generate the final predicted optical flow field using the optical flow estimation network, and complete image registration using the predicted optical flow field;

[0009] When using the optical flow estimation network to generate the final predicted optical flow field and using the predicted optical flow field to complete image registration, the following steps are included:

[0010] S31: First, a feature extractor is used to extract features from the input target image It and the source image Is at different resolutions, wherein the different resolutions include L1, L2, L3 and L4, and the resolution levels of L1, L2, L3 and L4 increase in sequence;

[0011] S32: Then at resolution L1, the network calculates the global correlation between the source feature FL1 and the target feature FL1, and uses normalization and ReLU activation functions to process the obtained global correlation to strengthen the certain matches and reduce the weights of uncertain matches;

[0012] S33: Global correlation is mapped to decoder M top Converted into a two-dimensional dense correspondence map m1, which is then converted into a displacement field w1(x)=m1(x)-x, where x is the pixel coordinate of the image, to obtain a rough optical flow from the source image to the target image;

[0013] S34: The calculated local correlation module is used to further refine the optical flow on different resolution layers L2, L3 and L4 in turn. At the same time, the optical flow decoder uses the local correlation and the optical flow sampled from the previous layer to calculate the residual optical flow. The residual optical flow is then added to the optical flow of the previous layer to obtain the complete optical flow of the current layer.

[0014] When the optical flow estimation network is used to generate the final predicted optical flow field and the predicted optical flow field is used to complete image registration, the evaluation network is used to update and optimize the parameters of the optical flow estimation network. The evaluation network uses LSTM to generate a scene for evaluation and inputs it into the loss calculation function to guide the overall parameter update by integrating historical information. The workflow of the evaluation network is as follows:

[0015] S41: receiving optical flow estimation data of the image as network input;

[0016] S42: Network input data is processed through fully connected layers, batch normalization layers, and residual connections to achieve feature extraction and enhancement;

[0017] S43: The extracted features are regularized by the Dropout layer to obtain a preliminary evaluation field;

[0018] S44: LSTM layer processes the preliminary evaluation field;

[0019] S45: The LSTM output passes through two fully connected layers to generate the evaluation field.

[0020] Preferably, the GLU-Net network is used to obtain the predicted optical flow field between the two images, and the image to be registered is generated based on this predicted optical flow field to complete the image registration task; this process includes data preprocessing, feature extraction, feature matching, optical flow estimation and calculation of the optical flow loss function.

[0021] Preferably, the key advantage of introducing the evaluation field is that it can accelerate the convergence speed of the model during training, especially in the case of data scarcity. By introducing the evaluation field, the model can learn and adapt to the changing data distribution more quickly, thereby improving the training efficiency and registration performance of the model.

[0022] Preferably, the LSTM model designed in this algorithm has an important function. It can continuously capture and update the evaluation field features of each pair of images in the historical iteration to help output the evaluation field of the pair of images at the current moment; in the order of training iterations, each pair of images sequentially passes its historical evaluation field to the LSTM model to integrate information from each historical moment; this helps to increase the information provided by each pair of images in the current training round, thereby filling the gap in information shortage when data is scarce; in this way, the LSTM model outputs the evaluation field of the current training round, effectively guiding the optical flow estimation network to better complete the SAR image registration task.

[0023] Preferably, when data preprocessing is performed on the input SAR image data to convert different SAR image data into standardized image data, the input image includes an active image Is and a target image It.

[0024] Preferably, when performing data preprocessing on the input SAR image data to convert different SAR image data into standardized image data, the following steps are included:

[0025] S21: First, adjust the source image Is and the target image It to appropriate resolutions; wherein the formula for adjusting the resolution is:

[0026] Is'=adjusted resolution (Is), It'=adjusted resolution (It),

[0027] Where Is' is the source image after adjusting the resolution, It' is the target image after adjusting the resolution;

[0028] S22: performing normalization processing on the source image Is' and the target image It' after adjusting the resolution; wherein the principle formula of the normalization processing is:

[0029] Is”=standardization (Is'), It”=standardization (It');

[0030] Wherein, Is” is the source image after the resolution is adjusted and normalized, and It” is the target image after the resolution is adjusted and normalized.

[0031] Preferably, when using a feature network to extract features from preprocessed image data, the feature network used is a VGG network; wherein the VGG network uses a 3×3 convolution kernel and increases the network depth to extract the source image and target image after adjusting the resolution and standardization.

[0032] Preferably, the VGG network uses the VGG-16 model to extract features from the preprocessed image data; wherein the form of the VGG network is:

[0033] Conv3×3→ReLU→MaxPool2×2;

[0034] Among them, → indicates that these layers are connected sequentially, Conv is the convolution layer, ReLU is the activation function, and MaxPool is the maximum pooling layer.

[0035] Preferably, the structure of the VGG network is: Input (preprocessed image) → (Conv3×3→ReLU)×2→MaxPool→(Conv3×3→ReLU)×2→MaxPool→......→FC→Output (feature output); the VGG network effectively captures the multi-scale information of the image through multi-layer convolution and pooling; these features are crucial for the image registration task because they provide sufficient information to find the correspondence between different images; the purpose of the feature extraction layer is to capture local and global information in the image, which is crucial for subsequent image registration tasks; after feature extraction, a high-dimensional feature space that can describe the image content and structure is obtained, which greatly improves the model's ability to perform accurate registration in complex scenes.

[0036] Preferably, when feature matching is performed on the SAR image data after feature extraction, when the same feature points or feature regions are found in multiple SAR image data, feature matching is performed using a global-local feature matching method.

[0037] Preferably, when performing feature matching, global feature matching is mainly responsible for overall large-scale motion, while local feature matching is responsible for subtle local motion. The entire GLU-Net feature M matching is a process based on a collaborative mechanism, which means that global and local feature matching are performed simultaneously so that more comprehensive matching information can be obtained at different scales and fields of view.

[0038] Preferably, when performing feature matching, a special correlation layer Correlation is used to perform feature matching, and the correlation layer Correlation is used to calculate the correlation between different features; wherein, the correlation layer Correlation calculates the inner product of the feature of one image and the feature of another image, and generates a correlation graph, thereby achieving feature matching.

[0039] Preferably, the correlation layer Correlation uses the rectangular image patch image1patch of the source image to perform a convolution operation on the target image image2patch when calculating the correlation between different features.

[0040] Preferably, the specific calculation process of Correlation is based on the convolution operation in CNN, but the convolution operation in CNN is deformed. Compared with the use of a specific convolution kernel for convolution in CNN, the rectangular image block patch (image1patch) of the first image is used to perform a convolution operation on the pacth (image2patch) of another image, so the operation does not contain training parameters; for the rectangular image block (patch) of image1 (width w, height h, number of channels c) with x1 as the center and extending up and down by a length k (the length and width of the rectangular block is 2k+1), a correlation calculation between it and the rectangular image block (patch) in image2 (w, h, c) with x2 as the center and extending up and down by a length k can be expressed as:

[0041] c(x1,x2)=∑ 0∈[-k,k]×[-k,k] (f1(x1+o),f2(x2+o));

[0042] In detail, the point x1 in image1(w,h,c) means that a pixel point centered on x1 is selected from the first image image1, and the "rectangular image patch with a length of k above and below" here means that instead of considering the entire image, a small area around the point x1 is considered. This area is a square patch with a side length of 2k+1; this size is based on "k", which is a parameter that defines the radius of the patch; therefore, if k is 1, then the patch size will be 3x3; a correlation between it and the rectangular image patch with a length of k above and below the center of x2 in image2(w,h,c) means that, The corresponding patch centered at x2 is selected in the second image image2; what needs to be calculated is the correlation between the patch centered at x1 in image1 and the patch centered at x2 in image2; this calculation will compare the two patches and produce a numerical value indicating the similarity or degree of match between them; this correlation is calculated by comparing the patch in image1 with all possible patches in image2; in order to find the best matching area, in the optical flow prediction, this best matching area will tell us where x1 has moved to in image2, so that the movement of the pixel point x1 between two consecutive frames, that is, the optical flow, can be calculated.

[0043] Beneficial effects of the present invention:

[0044] 1、Present to the prior art in the SAR image registration, the mature visible light image registration model is applied to SAR image registration, due to the difference between the characteristics and distribution of visible light image and SAR image is larger, often the effect is poor, and due to the SAR image registration aspect data scarcity problem is more serious, therefore not only the training and verification of algorithm have influence, and may lead to over fitting and generalization performance problem; The SAR image registration method trains the GLU-Net network by setting the transfer learning technology, then trains on the scarce SAR data, and adds the evaluation network, guides its training on SAR using the evaluation network, can the limitation of existing method, improve the performance of SAR image registration;

[0045] 2、The key advantage of introducing the evaluation field is that it can accelerate the convergence speed of the model in the training process, especially in the face of data scarcity, through the introduction of the evaluation field, the model can learn and adapt to the changing data distribution faster, thereby improving the training efficiency and registration performance of the model;

[0046] 3、The designed LSTM model in the algorithm has important functions, which can continuously capture and update the evaluation field features of each pair of image historical iterations to help the evaluation field output of the pair of images at the current time; In the order of training iterations, each pair of images passes its historical evaluation field to the LSTM model to integrate the information of each historical time; This helps to increase the information provided by each pair of images in the current training round, thereby filling the defect of insufficient information in the case of data scarcity; In this way, the LSTM model outputs the evaluation field of the current training round, effectively guiding the optical flow estimation network to better complete the SAR image registration task. BRIEF DESCRIPTION OF DRAWINGS

[0047] Figure 1 The flowchart of the SAR image adaptive registration method based on GLU-Net-Evaluate of the application is shown;

[0048] Figure 2 The specific flowchart of the SAR image adaptive registration method based on GLU-Net-Evaluate of the application is shown;

[0049] Figure 3 The model diagram of the evaluation network in the SAR image adaptive registration method based on GLU-Net-Evaluate of the application is shown;

[0050] Figure 4 The workflow diagram of the evaluation network in the SAR image adaptive registration method based on GLU-Net-Evaluate of the application is shown. DETAILED DESCRIPTION

[0051] The present invention will be further described below with reference to the accompanying drawings and examples.

[0052] See also Figure 1-2 The present invention provides an embodiment: a SAR image adaptive registration method based on GLU-Net-Evaluate, including the following steps:

[0053] S11: performing data preprocessing on the input SAR image data to convert different SAR image data into standardized image data;

[0054] S12: Extract features from the preprocessed image data using a feature network;

[0055] S13: performing feature matching on the SAR image data after feature extraction, and finding the same feature points or feature areas in multiple SAR image data;

[0056] S14: Use the optical flow estimation network to generate the final predicted optical flow field, and use the predicted optical flow field to complete image registration.

[0057] Preferably, the GLU-Net network is used to obtain the predicted optical flow field between the two images, and the image to be registered is generated based on this predicted optical flow field to complete the image registration task; this process includes data preprocessing, feature extraction, feature matching, optical flow estimation and calculation of the optical flow loss function.

[0058] Preferably, when data preprocessing is performed on the input SAR image data to convert different SAR image data into standardized image data, the input image includes an active image Is and a target image It.

[0059] Preferably, when performing data preprocessing on the input SAR image data to convert different SAR image data into standardized image data, the following steps are included:

[0060] S21: First, adjust the source image Is and the target image It to appropriate resolutions; wherein the formula for adjusting the resolution is:

[0061] Is'=adjusted resolution (Is), It'=adjusted resolution (It),

[0062] Where Is' is the source image after adjusting the resolution, It' is the target image after adjusting the resolution;

[0063] S22: performing normalization processing on the source image Is' and the target image It' after adjusting the resolution; wherein the principle formula of the normalization processing is:

[0064] Is”=Standardization (Is'), It”=Standardization (It');

[0065] Wherein, Is” is the source image after the resolution is adjusted and normalized, and It” is the target image after the resolution is adjusted and normalized.

[0066] Preferably, when using a feature network to extract features from preprocessed image data, the feature network used is a VGG network; wherein the VGG network uses a 3×3 convolution kernel and increases the network depth to extract the source image and target image after adjusting the resolution and standardization.

[0067] Preferably, the VGG network uses the VGG-16 model to extract features from the preprocessed image data; wherein the form of the VGG network is:

[0068] Conv3×3→ReLU→MaxPool2×2;

[0069] Among them, → indicates that these layers are connected sequentially, Conv is the convolution layer, ReLU is the activation function, and MaxPool is the maximum pooling layer.

[0070] Preferably, the structure of the VGG network is: Input (preprocessed image) → (Conv3×3→ReLU)×2→MaxPool→(Conv3×3→ReLU)×2→MaxPool→......→FC→Output (feature output); the VGG network effectively captures the multi-scale information of the image through multi-layer convolution and pooling; these features are crucial for the image registration task because they provide sufficient information to find the correspondence between different images; the purpose of the feature extraction layer is to capture local and global information in the image, which is crucial for subsequent image registration tasks; after feature extraction, a high-dimensional feature space that can describe the image content and structure is obtained, which greatly improves the model's ability to perform accurate registration in complex scenes.

[0071] Preferably, when feature matching is performed on the SAR image data after feature extraction, when the same feature points or feature regions are found in multiple SAR image data, feature matching is performed using a global-local feature matching method.

[0072] Preferably, when performing feature matching, global feature matching is mainly responsible for overall large-scale motion, while local feature matching is responsible for subtle local motion. The entire GLU-Net feature M matching is a process based on a collaborative mechanism, which means that global and local feature matching are performed simultaneously so that more comprehensive matching information can be obtained at different scales and fields of view.

[0073] Preferably, when performing feature matching, a special correlation layer Correlation is used to perform feature matching, and the correlation layer Correlation is used to calculate the correlation between different features; wherein, the correlation layer Correlation calculates the inner product of the feature of one image and the feature of another image, and generates a correlation graph, thereby achieving feature matching.

[0074] Preferably, the correlation layer Correlation uses the rectangular image patch image1patch of the source image to perform a convolution operation on the target image image2patch when calculating the correlation between different features.

[0075] Preferably, the specific calculation process of Correlation is based on the convolution operation in CNN, but the convolution operation in CNN is deformed. Compared with the use of a specific convolution kernel for convolution in CNN, the rectangular image block patch (image1patch) of the first image is used to perform a convolution operation on the pacth (image2patch) of another image, so the operation does not contain training parameters; for the rectangular image block (patch) of image1 (width w, height h, number of channels c) with x1 as the center and extending up and down by a length k (the length and width of the rectangular block is 2k+1), a correlation calculation between it and the rectangular image block (patch) in image2 (w, h, c) with x2 as the center and extending up and down by a length k can be expressed as:

[0076] c(x1,x2)=∑ o∈[-k,k]×[-k,k] (f1(x1+o),f2(x2+o));

[0077] In detail, the point x1 in image1(w,h,c) means that a pixel point centered on x1 is selected from the first image image1, and the "rectangular image patch with a length of k above and below" here means that instead of considering the entire image, a small area around the point x1 is considered. This area is a square patch with a side length of 2k+1; this size is based on "k", which is a parameter that defines the radius of the patch; therefore, if k is 1, then the patch size will be 3x3; a correlation between it and the rectangular image patch with a length of k above and below the center of x2 in image2(w,h,c) means that, The corresponding patch centered at x2 is selected in the second image image2; what needs to be calculated is the correlation between the patch centered at x1 in image1 and the patch centered at x2 in image2; this calculation will compare the two patches and produce a numerical value indicating the similarity or degree of match between them; this correlation is calculated by comparing the patch in image1 with all possible patches in image2; in order to find the best matching area, in the optical flow prediction, this best matching area will tell us where x1 has moved to in image2, so that the movement of the pixel point x1 between two consecutive frames, that is, the optical flow, can be calculated.

[0078] See also Figure 3-4 In this embodiment, when the optical flow estimation network is used to generate the final predicted optical flow field and the predicted optical flow field is used to complete the image registration, the following steps are included:

[0079] S31: First, a feature extractor is used to extract features from the input target image It and the source image Is at different resolutions, wherein the different resolutions include L1, L2, L3 and L4, and the resolution levels of L1, L2, L3 and L4 increase in sequence;

[0080] S32: Then at resolution L1, the network calculates the global correlation between the source feature FL1 and the target feature FL1, and uses normalization and ReLU activation functions to process the obtained global correlation to strengthen the certain matches and reduce the weights of uncertain matches;

[0081] S33: Global correlation is mapped to decoder M top Converted into a two-dimensional dense correspondence map m1, which is then converted into a displacement field w1(x)=m1(x)-x, where x is the pixel coordinate of the image, to obtain a rough optical flow from the source image to the target image;

[0082] S34: The calculated local correlation module is used to further refine the optical flow on different resolution layers L2, L3 and L4 in turn. At the same time, the optical flow decoder uses the local correlation and the optical flow sampled from the previous layer to calculate the residual optical flow, and then the residual optical flow is added to the optical flow of the previous layer to obtain the complete optical flow of the current layer.

[0083] Preferably, when the optical flow estimation network is used to generate the final predicted optical flow field and the predicted optical flow field is used to complete image registration, the evaluation network is used to update and optimize the parameters of the optical flow estimation network. The evaluation network uses LSTM to generate a scene for evaluation and inputs it into the loss calculation function to guide the overall parameter update by integrating historical information. The workflow of the evaluation network is as follows:

[0084] S41: receiving optical flow estimation data of the image as network input;

[0085] S42: Network input data is processed through fully connected layers, batch normalization layers, and residual connections to achieve feature extraction and enhancement;

[0086] S43: The extracted features are regularized by the Dropout layer to obtain a preliminary evaluation field;

[0087] S44: LSTM layer processes the preliminary evaluation field;

[0088] S45: The LSTM output passes through two fully connected layers to generate the evaluation field.

[0089] Preferably, the key advantage of introducing the evaluation field is that it can accelerate the convergence speed of the model during training, especially in the case of data scarcity. By introducing the evaluation field, the model can learn and adapt to the changing data distribution more quickly, thereby improving the training efficiency and registration performance of the model.

[0090] Preferably, the LSTM model designed in this algorithm has an important function. It can continuously capture and update the evaluation field features of each pair of images in the historical iteration to help output the evaluation field of the pair of images at the current moment; in the order of training iterations, each pair of images sequentially passes its historical evaluation field to the LSTM model to integrate information from each historical moment; this helps to increase the information provided by each pair of images in the current training round, thereby filling the gap in information shortage when data is scarce; in this way, the LSTM model outputs the evaluation field of the current training round, effectively guiding the optical flow estimation network to better complete the SAR image registration task.

[0091] The embodiments of the present invention are described in detail above with reference to the accompanying drawings. However, the present invention is not limited to the above embodiments. Various changes can be made within the scope of knowledge of those skilled in the art without departing from the spirit of the present invention.

Claims

1. A SAR image adaptive registration method based on GLU-Net-Evaluate; characterized by: The following steps are included: S11: performing data preprocessing on the input SAR image data to convert different SAR image data into standardized image data; S12: Extract features from the preprocessed image data using a feature network; S13: performing feature matching on the SAR image data after feature extraction, and finding the same feature points or feature areas in multiple SAR image data; S14: Generate the final predicted optical flow field using the optical flow estimation network, and complete image registration using the predicted optical flow field; When using the optical flow estimation network to generate the final predicted optical flow field and using the predicted optical flow field to complete image registration, the following steps are included: S31: First, a feature extractor is used to extract features from the input target image It and the source image Is at different resolutions, wherein the different resolutions include L1, L2, L3 and L4, and the resolution levels of L1, L2, L3 and L4 increase in sequence; S32: Then at resolution L1, the network calculates the global correlation between the source feature FL1 and the target feature FL1, and uses normalization and ReLU activation functions to process the obtained global correlation to strengthen the certain matches and reduce the weights of uncertain matches; S33: Global correlation is mapped to decoder M top Converted into a two-dimensional dense correspondence map m1, which is then converted into a displacement field w1(x)=m1(x)-x, where x is the pixel coordinate of the image, to obtain a rough optical flow from the source image to the target image; S34: The calculated local correlation module is used to further refine the optical flow on different resolution layers L2, L3 and L4 in turn. At the same time, the optical flow decoder uses the local correlation and the optical flow sampled from the previous layer to calculate the residual optical flow. The residual optical flow is then added to the optical flow of the previous layer to obtain the complete optical flow of the current layer. When the optical flow estimation network is used to generate the final predicted optical flow field and the predicted optical flow field is used to complete image registration, the evaluation network is used to update and optimize the parameters of the optical flow estimation network. The evaluation network uses LSTM to generate a scene for evaluation and inputs it into the loss calculation function to guide the overall parameter update by integrating historical information. The workflow of the evaluation network is as follows: S41: receiving optical flow estimation data of the image as network input; S42: Network input data is processed through fully connected layers, batch normalization layers, and residual connections to achieve feature extraction and enhancement; S43: The extracted features are regularized by the Dropout layer to obtain a preliminary evaluation field; S44: LSTM layer processes the preliminary evaluation field; S45: The LSTM output passes through two fully connected layers to generate the evaluation field.

2. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 1, characterized in that: When data preprocessing is performed on input SAR image data to convert different SAR image data into standardized image data, the input image includes an active image Is and a target image It.

3. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 2, characterized in that: When preprocessing the input SAR image data to convert different SAR image data into standardized image data, the following steps are included: S21: First, adjust the source image Is and the target image It to appropriate resolutions; wherein the formula for adjusting the resolution is: Is'=adjusted resolution (Is), It'=adjusted resolution (It), Where Is' is the source image after adjusting the resolution, It' is the target image after adjusting the resolution; S22: performing normalization processing on the source image Is' and the target image It' after adjusting the resolution; wherein the principle formula of the normalization processing is: Is”=standardization (Is'), It”=standardization (It'); Wherein, Is” is the source image after the resolution is adjusted and normalized, and It” is the target image after the resolution is adjusted and normalized.

4. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 3, characterized in that: When using a feature network to extract features from preprocessed image data, the feature network used is a VGG network; wherein, the VGG network uses a 3×3 convolution kernel and increases the network depth to extract the source image and target image after adjusting the resolution and standardization.

5. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 4, characterized in that: The VGG network uses the VGG-16 model to extract features from the preprocessed image data; the form of the VGG network is: Conv3×3→ReLU→MaxPool2×2; Among them, → indicates that these layers are connected sequentially, Conv is the convolution layer, ReLU is the activation function, and MaxPool is the maximum pooling layer.

6. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 5, characterized in that: When feature matching is performed on the SAR image data after feature extraction, when the same feature points or feature areas are found in multiple SAR image data, feature matching is performed using a global-local feature matching method.

7. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 6, characterized in that: When performing feature matching, a special correlation layer is used to perform feature matching. The correlation layer is used to calculate the correlation between different features. The correlation layer calculates the inner product of the features of one image and the features of another image and generates a correlation graph to achieve feature matching.

8. The SAR image adaptive registration method based on GLU-Net-Evaluate according to claim 7, characterized in that: The correlation layer uses the rectangular image patch image1patch of the source image to perform a convolution operation on the target image image2patch when calculating the correlation between different features.

Images