A remote sensing image target segmentation method based on feature adaptive processing

Abstract

The present invention discloses a method for remote sensing image target segmentation based on feature adaptive processing, which relates to the field of remote sensing image processing technology. The method comprises the following steps: Step 1: Acquire remote sensing images and perform preprocessing and data enhancement to obtain a training data set; Step 2: Construct a remote sensing image segmentation network and train it using the training data set to obtain a remote sensing image segmentation model; The remote sensing image segmentation network comprises an encoder, a feature adaptive processing module, a multi-scale feature fusion module, and a decoder connected in sequence; Step 3: Acquire the remote sensing image to be segmented, input it into the remote sensing image segmentation model, and obtain a target segmentation result. By introducing the feature adaptive processing module and multi-scale feature fusion technology, the present invention can effectively improve the segmentation accuracy of targets in remote sensing images.

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 target segmentation method based on feature adaptive processing. Background Art

[0002] With the rapid development of remote sensing technology, remote sensing imagery has been widely used in a variety of fields, including military, geology, agriculture, and environmental monitoring. The core challenge of remote sensing image segmentation lies in effectively extracting and accurately segmenting targets from complex backgrounds. Traditional segmentation methods often rely on hand-crafted feature extraction algorithms. While effective in certain scenarios, these methods perform poorly in complex environments. Specifically, traditional methods often suffer from misidentification or omission when dealing with issues such as illumination variations, terrain undulations, and the similarity between target and background. With the rise of deep learning, particularly convolutional neural networks (CNNs), data-driven automatic feature learning has gradually become the mainstream approach in remote sensing image segmentation. Deep learning methods can automatically extract features from training data, overcoming the limitations of manual feature design in traditional methods. In particular, segmentation models based on network architectures such as fully convolutional neural networks (FCNs) and U-Nets have achieved remarkable progress. However, despite the excellent performance of these methods in many tasks, some difficult challenges remain in object segmentation in remote sensing images.

[0003] First, the distinction between targets and background in remote sensing images is often subtle. This is particularly true for aircraft detection and recognition. When aircraft targets share similar texture or color with background objects such as the ground or clouds, existing deep learning models are easily affected by background interference, resulting in reduced segmentation accuracy. Second, remote sensing images typically have high resolution, requiring segmentation models to possess strong multi-scale feature extraction capabilities to handle aircraft targets of varying sizes, shapes, and orientations. Various approaches have been proposed to address these issues. Some methods enhance the recognition accuracy of target regions by enhancing model context or introducing attention mechanisms. However, these methods typically focus on integrating information at a single scale and ignore the multi-scale feature representation in remote sensing images. Other methods attempt to enhance target recognizability by leveraging multi-channel or multi-view image information, but this often incurs a high computational cost. Therefore, how to efficiently fuse multi-scale features, enhance the model's focus on key regions, and reduce computational resource consumption remains an urgent challenge in remote sensing image segmentation.

[0004] To address these issues, feature adaptive processing technology has become a research hotspot in the field of remote sensing image segmentation in recent years. Feature adaptive processing methods can effectively highlight key areas and suppress irrelevant background by dynamically adjusting feature weights, thereby improving segmentation accuracy and robustness. Unlike traditional static feature extraction methods, feature adaptive processing can adaptively select appropriate features for processing based on changes in image content. This method is particularly effective when the difference between the target area and the background in the image is small. However, existing feature adaptive processing methods mostly focus on simple single-scale feature fusion. For complex remote sensing images, especially when there are large scale differences or multiple interference factors, the effectiveness of existing technologies is still limited.

[0005] Therefore, how to further improve the feature adaptive processing capability and improve the segmentation accuracy of targets in remote sensing images through adaptive fusion of multi-scale features is an urgent problem that technicians in this field need to solve. Summary of the Invention

[0006] In light of this, this paper provides a method for remote sensing image target segmentation based on feature adaptive processing. By incorporating a feature adaptive processing module and multi-scale feature fusion technology, it effectively improves the segmentation accuracy of targets in remote sensing images, especially under complex backgrounds and diverse environments. This technology enables more precise target segmentation from remote sensing images, providing powerful technical support for fields such as remote sensing monitoring and military reconnaissance.

[0007] In order to achieve the above object, the present invention adopts the following technical solutions:

[0008] A remote sensing image target segmentation method based on feature adaptive processing includes the following steps:

[0009] Step 1: Collect remote sensing images and perform preprocessing and data enhancement to obtain a training dataset;

[0010] Step 2: Construct a remote sensing image segmentation network and train it using the training data set to obtain a remote sensing image segmentation model; the remote sensing image segmentation network includes an encoder, a feature adaptive processing module, a multi-scale feature fusion module, and a decoder connected in sequence;

[0011] Step 3: Collect the remote sensing image to be segmented, input it into the remote sensing image segmentation model, and obtain the target segmentation result.

[0012] Preferably, the preprocessing in step 1 includes cropping, scaling, and annotation, and data augmentation includes rotation, inversion, and color adjustment. Cropping and scaling the image to fit the model input size; annotating the image to determine the location and shape of the ship target and generate an accurate segmentation mask to provide a learning target for the model; performing data augmentation operations such as rotation, flipping, and color adjustment to simulate various conditions that may occur in the training set and enhance the model's ability to recognize ship targets under different conditions; performing preprocessing and data augmentation before training the network can improve the model's training efficiency and generalization ability.

[0013] Preferably, the process of processing the training image by the remote sensing image segmentation network includes:

[0014] The encoder consists of multiple convolutional modules connected in sequence. Images in the training dataset are input to the convolutional modules, and each convolutional module extracts a high-dimensional feature map of a certain scale.

[0015] The feature adaptive processing module performs pooling, fusion, and multi-head attention mechanism enhancement operations on the high-dimensional feature map to obtain an adaptive feature map;

[0016] The multi-scale feature fusion module extracts features and adaptively fuses the adaptive feature map to obtain a fused feature map;

[0017] The decoder performs weighted fusion, convolution adjustment and upsampling on the fused feature map in sequence to obtain the target segmentation result.

[0018] The technical effect of the above technical solution is that the high-dimensional feature maps of multiple scales output by the encoder represent semantic information at different levels, including edges, regional context and global structure; the feature adaptive processing module can enhance the semantic information of the features; the multi-scale feature fusion module further improves the feature representation capability and helps the network capture important areas and detail information; the decoder generates high-quality segmentation result images.

[0019] Preferably, the network weights are updated using a backpropagation algorithm and gradient descent to minimize the loss function. Early stopping is used to determine the optimal number of training rounds. Training is stopped when the optimal number of training rounds is reached, and a remote sensing image segmentation model is obtained. The remote sensing image segmentation model is fine-tuned to optimize model hyperparameters, including learning rate and batch size. By updating the network weights and minimizing the loss function, the segmentation accuracy of the model is improved, and model performance is further enhanced through fine-tuning of the model.

[0020] Preferably, during the training process, the model needs to be verified regularly, and the validation set is used to evaluate the model performance to prevent overfitting. After obtaining the remote sensing image segmentation model, the test set is used to perform a final evaluation of the model to verify the generalization ability of the model on unseen data, and necessary adjustments are made based on the test results.

[0021] Preferably, the process of preprocessing and data enhancement of the remote sensing image in step 1 includes:

[0022] Step 11: Annotate the remote sensing images and perform normalization on the annotated remote sensing images, normalizing the pixels to [0, 1] to eliminate the brightness and contrast differences between different images;

[0023] Step 12: Crop the normalized remote sensing image according to the preset target size (H, W) to adapt to the input requirements of the model, using random cropping or center cropping methods, expressed as:

[0024]

[0025] in, Represents a remote sensing image after normalization; Represents the cropped image; Crop represents the cropping operation;

[0026] Step 13: Randomly rotate or flip horizontally or vertically the cropped image to obtain the transformed image, which is expressed as:

[0027]

[0028] Among them, θ represents the rotation angle, θ∈[-θ max ,θ max ];θ max Indicates the preset maximum rotation angle; Rotate indicates the rotation transformation operation; Flip indicates the flip transformation operation; axis indicates the flip axis direction; Represents the transformed image;

[0029] Step 14: Perform color adjustment on the transformed image; perform random perturbations on brightness, contrast, and saturation to obtain the adjusted image

[0030] Step 15: Generate segmentation labels ψ based on the annotation information of the remote sensing image, and adjust the image Paired with the segmentation label ψ to form a training dataset

[0031] Preferably, the encoder includes three groups of convolution modules, each of which includes a convolution layer, an activation function layer, and a pooling layer connected in sequence. Each convolution module processes the image as follows:

[0032] X i =MaxPool(ReLU(Conv(X i-1 ))) fori=1,2,3

[0033] Among them, X i-1 represents the image input to the convolution module, X i Represents the feature map output by the convolution module; i represents the i-th convolution module, and the first convolution module inputs the adjusted image in the training dataset Conv represents the convolution operation; ReLU represents the activation function; MaxPool represents the maximum pooling operation; the first convolution module outputs a high-dimensional feature map Xx with a size of Contains underlying edge and texture information; the second convolution module outputs a high-dimensional feature map X2 with a size of Contains higher-level regional context information; the third convolution module outputs a high-dimensional feature map X3 with a size of Contains global structure and complex pattern information.

[0034] Preferably, the feature adaptive processing module includes a first average pooling layer, a second average pooling layer, an initial fusion layer, a multi-head attention layer, a first 1×1 convolution layer, an activation function layer, a second 1×1 convolution layer and an attention fusion layer. The specific processing process is:

[0035] Step 211: The high-dimensional feature map X1 is passed through the first average pooling layer to obtain a pooled feature map X′1, and the high-dimensional feature map X2 is passed through the second average pooling layer to obtain a pooled feature map X′2;

[0036] Step 212: The pooled feature map X′1, the pooled feature map X′2 and the high-dimensional feature map X3 are concatenated or weighted fused in the initial fusion layer to obtain the initial fusion feature map X fusion ;

[0037] Step 213: Initial fusion feature X fusion In the multi-head attention layer and mapped to multiple subspaces, multiple detection heads are used for parallel calculation to obtain multiple attention maps, and all attention maps are combined with the initial fusion feature X fusion Multiply to obtain the attention weighted feature map X attn ;

[0038] Step 214: The attention-weighted feature map is convolved in the first 1×1 convolutional layer to obtain a compressed feature map.

[0039] Step 215: The compressed feature map is activated in the activation function layer to obtain an activated feature map;

[0040] Step 216: The activated feature map is convolved in the second 1×1 convolutional layer to obtain a weight map W;

[0041] Step 217: The attention fusion layer adds the attention weighted feature map X attn Multiply it with the weight map W to obtain the adaptive feature map Xenhanced .

[0042] Preferably, the multi-scale feature fusion module includes an upper branch, a middle branch, and a lower branch; the upper branch includes a third 1×1 convolution layer and a third average pooling layer connected in sequence; the middle branch includes a fourth 1×1 convolution layer, an activation function layer, a fourth average pooling layer, a scale fusion layer, and a scale splicing layer connected in sequence; the lower branch includes a fifth average pooling layer, a branch splicing layer, a fifth 1×1 convolution layer, and a sixth 1×1 convolution layer; the processing process of the multi-scale feature fusion module is:

[0043] Step 221: Adaptive feature map X enhanced After the convolution operation of the third 1×1 convolutional layer, the average pooling operation is performed in the third average pooling layer to obtain the global feature x α , expressed as:

[0044] x α =AvgPool(1×1Conv(X enhanced ))

[0045] Among them, AvgPool represents average pooling; 1×1Conv represents 1*1 convolution operation;

[0046] Adaptive feature map X enhanced After the convolution operation of the fourth 1×1 convolutional layer, the weight map A is obtained by sequentially passing the activation operation of the activation function layer and the average pooling operation of the fourth average pooling layer. β , expressed as:

[0047] A β =AvgPool(ReLU(1×1Conv(X enhanced )))

[0048] Among them, RELU means applying the RELU activation function;

[0049] Adaptive feature map X enhanced After the average pooling operation of the fifth average pooling layer, the feature map is obtained Feature Map and adaptive feature map X enhanced The branch splicing layer is added to obtain the splicing feature map, and the enhanced feature map is sequentially subjected to the convolution operation of the fifth 1×1 convolution layer and the sixth 1×1 convolution layer to obtain the enhanced feature map x γ , expressed as:

[0050]

[0051] Step 222: Enhance feature map x γ Input to the scale fusion layer and weight map A βMultiply to obtain the enhanced weighted feature map x β , expressed as:

[0052] x β =A β ·x γ ;

[0053] Step 223: Enhance the weighted feature map x β and the global feature map x α Input to the scale splicing layer for addition to obtain the fusion feature map X″ enhanced .

[0054] Preferably, the decoder includes a convolution layer, an upsampling layer and an activation function layer connected in sequence; the fusion feature map X″ enhanced The target segmentation result is obtained by sequentially performing the convolution operation of the convolution layer, the bilinear interpolation upsampling operation of the upsampling layer, and the activation operation of the activation function layer; the convolution layer adopts a 1×1 convolution layer.

[0055] Preferably, the remote sensing image segmentation network adopts a hybrid loss function L optimization model during the training process, which is expressed as:

[0056] L=εL1+δL2+μL3

[0057]

[0058] Among them, L1 represents cross entropy loss; L2 represents Dice loss; L3 represents IoU value; N represents the total number of pixels of the adjusted image in the training dataset; P i represents the predicted probability at pixel i in the target segmentation result predicted by the remote sensing image segmentation network; ψ i represents the segmentation label of pixel i in the training dataset; ε, δ, and μ are the scaling coefficients respectively.

[0059] Preferably, the remote sensing image segmentation network minimizes the hybrid loss function through back propagation and gradient descent during the training process; the back propagation algorithm calculates the gradient of the model parameters according to the hybrid loss function, and then updates the network weights through gradient descent. The network weight update expression is:

[0060]

[0061] Where η represents the learning rate; represents the gradient of the hybrid loss function with respect to the parameter θ.

[0062] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention discloses a remote sensing image target segmentation method based on feature adaptive processing. By introducing a feature adaptive processing module, it can effectively enhance the semantic information of the image and adaptively fuse multi-scale features, thereby more accurately identifying and segmenting the target. This method combines the advantages of deep learning models and improves the model's ability to recognize targets in complex backgrounds and different environmental conditions through steps such as data preprocessing and enhancement, feature adaptive processing, and multi-scale feature fusion. It is suitable for various remote sensing image processing tasks. Specifically, the present invention has the following beneficial effects:

[0063] 1) Through the feature adaptive processing module, it can adaptively fuse multi-scale features, improving the segmentation accuracy of targets in remote sensing images, especially the target recognition ability under complex backgrounds and different environmental conditions;

[0064] 2) The introduction of a multi-head attention mechanism and a weighted fusion strategy enhances the model's focus on key areas, resulting in superior performance in detail capture and segmentation accuracy. Through efficient parameter fine-tuning, the resource requirements during training and deployment are reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] 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.

[0066] Figure 1 This is a schematic diagram of the remote sensing image segmentation model processing process provided by the present invention. DETAILED DESCRIPTION

[0067] 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.

[0068] In terms of monitoring and identifying aircraft targets, aircraft targets in remote sensing images are often highly complex and diverse, and are affected by multiple factors such as weather, lighting, terrain, and the target's own appearance. Therefore, accurately segmenting aircraft targets in remote sensing images is extremely challenging. The present invention discloses a method for segmenting remote sensing image targets based on feature adaptive processing, which segments aircraft targets in remote sensing images, including the following steps:

[0069] S1: Collect remote sensing images and perform preprocessing and data enhancement to obtain training datasets;

[0070] S2: Build a remote sensing image segmentation network and train it using a training dataset to obtain a remote sensing image segmentation model; the remote sensing image segmentation network includes an encoder, a feature adaptive processing module, a multi-scale feature fusion module, and a decoder connected in sequence;

[0071] S3: Collect the remote sensing image to be segmented, input it into the remote sensing image segmentation model, and obtain the aircraft target segmentation result.

[0072] Furthermore, preprocessing in S1 includes cropping, scaling, and annotation, while data augmentation includes rotation, inversion, and color adjustment. Images are cropped and scaled to fit the model input size; images are annotated to determine the location and shape of ship targets, generating accurate segmentation masks and providing learning targets for the model. Data augmentation operations include rotation, flipping, and color adjustment to simulate various conditions that may occur in the training set, enhancing the model's ability to recognize ship targets under different conditions. Preprocessing and data augmentation before network training can improve the model's training efficiency and generalization capabilities.

[0073] Furthermore, a remote sensing image segmentation network is constructed and trained to obtain a remote sensing image segmentation model. First, the processed image in S1 is used as the input image, and high-dimensional feature maps are extracted through multiple convolution modules of the encoder. These feature maps represent semantic information at different levels, including edges, regional context, and global structure. Next, the feature adaptive processing module is used to enhance the semantic information of the features through pooling, splicing, weighted fusion, and multi-head attention mechanism, and obtain weighted feature maps. Then, the feature maps are subjected to multi-scale feature extraction and adaptive fusion through a multi-scale feature fusion module with three branches (upper branch, middle branch, and lower branch), further improving the feature representation ability and helping the network capture important areas and detailed information. Finally, the decoder performs weighted fusion, convolution adjustment, and upsampling operations to generate a high-quality segmentation result image. This process improves segmentation accuracy and the representation of image details through multi-level feature fusion and spatial restoration.

[0074] Furthermore, in the training and optimization process of the remote sensing image segmentation model, the network is trained using preprocessed and enhanced remote sensing image data, and the model weights are updated through the backpropagation algorithm and gradient descent method to minimize the loss function to improve the segmentation accuracy of the model; during the training process, the model needs to be verified regularly, and the model performance is evaluated using the validation set to prevent overfitting; the early stopping technique is used to determine the optimal training rounds; after training, the model is fine-tuned and hyperparameters such as learning rate and batch size are optimized to further improve model performance; finally, the model is finally evaluated using the test set to verify the model's generalization ability on unseen data, and necessary adjustments are made based on the test results.

[0075] The remote sensing image target segmentation method of the present invention, based on a feature adaptive processing module, significantly improves the segmentation accuracy of aircraft targets in remote sensing images by enhancing the feature representation capability of the image and multi-scale information fusion. In addition, through efficient parameter fine-tuning and the use of adapters, the resource requirements for model training and deployment are reduced. The method can be effectively deployed under limited computing resources, making it suitable for remote sensing image processing tasks in various computing environments.

[0076] In a specific embodiment, before the deep learning model is trained, the input original remote sensing image is Perform data preprocessing and enhancement operations to improve the training efficiency and generalization ability of the model; the specific process is as follows:

[0077] S1, perform image annotation, standardization and cropping; label the image content; input image Normalize the pixel values ​​to [0, 1] to eliminate the brightness and contrast differences between different images; crop the image to the target size (H, W) to adapt to the input requirements of the model, using random cropping or center cropping methods, which are recorded as:

[0078]

[0079] in, is the cropped image;

[0080] S2, diversified data enhancement; by using data enhancement methods to simulate the complex situations that may occur in the training set to enhance the robustness of the model, first use the random rotation θ∈[-θ max ,θ max ], or perform horizontal and vertical flips, defined as:

[0081]

[0082] Where θ represents the rotation angle (in degrees), θ maxIt is the maximum rotation angle set. Rotate is an operation function used to rotate the input image. Flip is an operation function used to flip the input image. Axis indicates the axis direction of the flip.

[0083] Then the image Perform color adjustment and randomly perturb the brightness, contrast, and saturation of the image to obtain the image

[0084] S3, based on the annotation information of the original remote sensing image, generates the corresponding segmentation label (mask) ψ, where the target area (aircraft) is marked as the foreground (value 1) and the rest of the area is marked as the background (value 0); the processed image Paired with the corresponding mask ψ to form a training data set

[0085] In a specific embodiment, the remote sensing image segmentation model processes the image as follows: Figure 1 As shown, specifically:

[0086] S1: processed image As the input image of the network, the input image The size is C×H×W, where C is the number of channels, H and W are the height and width of the image respectively;

[0087] The image passes through multiple convolution modules of the encoder in sequence. Each convolution module is regarded as a stage. Each convolution module consists of several convolution layers, activation functions (such as ReLU) and pooling layers (such as maximum pooling). By extracting high-dimensional features of different semantic levels layer by layer, three high-dimensional features X1, X2 and X3 are obtained, where i = 1, 2, 3. Each feature map represents semantic information at a different level:

[0088] X i =MaxPool(ReLU(Conv(X i-1 ))) fori=1,2,3

[0089] Among them, X1 represents the features after the first stage, and the size is Contains the underlying edge and texture information; X2 represents the features after the second stage, with a size of Contains higher-level regional context information; X3 represents the features after the third stage, with a size of Contains global structure and complex pattern information; these feature maps provide rich semantic information for subsequent decoding and segmentation tasks;

[0090] S2: Apply average pooling operations to feature maps X1 and X2 respectively to obtain pooled feature maps X′1 and X′2;

[0091] The pooled features X′1 and X′2 are concatenated or weighted fused with the feature map X3 to obtain the fused feature X fusion , the size of the feature map is This feature will serve as the input of the subsequent multi-head attention mechanism;

[0092] Adopting multi-head attention mechanism, integrating feature X fusion It is mapped to multiple subspaces and computed in parallel by multiple heads to capture different attention information;

[0093] By multiplying the attention map with the fusion feature, we get the feature map X weighted by the attention mechanism. attn ;

[0094] The feature map X after attention is applied through a 1×1 convolutional layer attn The number of channels is compressed or adjusted, and then nonlinear features are introduced through the activation function ReLU. Then, feature adjustment is performed through a 1×1 convolution layer to obtain the final weight map W;

[0095] The obtained weight map W is combined with the feature map X that has been weighted by the attention mechanism. attn Multiply by to obtain the enhanced adaptive feature X enhanced , whose size is Where C′ is the number of channels output by the convolutional layer; the feature map contains information after multi-head attention and adaptive weight adjustment, which can better represent the important features in the input image;

[0096] S3: Adaptive Feature X enhanced The quality of feature representation will be improved through multi-scale feature extraction and adaptive fusion through the upper, middle and lower branches, so that the network can better capture semantic information at different levels when processing image segmentation tasks, and finally obtain the enhanced feature map X″ enhanced The specific process is as follows:

[0097] S31: The upper branch first performs adaptive feature X enhanced Perform a 1×1 convolution operation to extract channel information and reduce the amount of calculation. Then, perform an average pooling operation. The purpose is to compress the spatial dimension through the pooling layer, thereby retaining the information of a larger semantic area without losing important global features. Through this process, an overall, high-level global feature x can be obtained. α , expressed as:

[0098] x α =AvgPool(1×1Conv(X enhanced)) Among them, AvgPool represents average pooling, and 1×1Conv represents a 1*1 convolutional layer; the purpose of this branch is to extract large-scale contextual information in the image through pooling, retaining global features without paying too much attention to local details;

[0099] The middle branch first performs adaptive feature X enhanced Perform 1×1 convolution, and then perform nonlinear transformation through ReLU activation function to increase the expressive power of features. Then, apply average pooling operation to further reduce the spatial resolution of feature map, thereby highlighting the significant areas or object structures in the image. Finally, the output is weight map A β , these weights will be used in the subsequent weighted fusion stage and are expressed as:

[0100] A β =AvgPool(ReLU(1×1Conv(X enhanced )))

[0101] Among them, RELU represents the application of RELU activation function; the design purpose of the middle branch is to learn the importance of different regions in the feature map and enhance or suppress the features of certain regions through the weight map, helping the network to focus more on key areas;

[0102] The lower branch first performs adaptive feature X enhanced Perform average pooling operation to obtain a lower resolution feature map This provides a basis for subsequent feature weighting, and then the pooled feature map Compared with the original adaptive feature X enhanced Add, combine low-resolution information and original features to enhance the detail information of the image, then further adjust and refine the feature map through two 1×1 convolution operations, and finally obtain the enhanced feature map x γ :

[0103]

[0104] The lower branch can improve the network's ability to capture details by combining low-resolution features with high-resolution features. This is especially important in segmentation tasks, where capturing fine boundaries and local information is crucial.

[0105] S32: Weight Graph A β And the adjusted feature map x γ Multiply to get the weighted feature map x β The key to this step is to adjust the contribution of different parts of the feature map by introducing weights, so that the network can pay more attention to important areas, which can be expressed as:

[0106] x β =Aβ ·x γ The weight map here plays a role in weighting important feature areas, enhancing the model's response to key areas and helping to improve segmentation accuracy;

[0107] S33: The feature map x of the upper branch α The weighted feature map x of the middle branch β Add together to get the final fusion feature map X″ enhanced In this way, the network combines feature information at different levels to comprehensively improve the expressive power of features, which can be expressed as:

[0108] X″ enhanced =x α +x β ;

[0109] The upper branch provides global semantic information, and the middle branch provides weighted information of important areas. The combination of the two can better describe the overall and local features of the image, thereby improving segmentation performance.

[0110] S4: Enhanced fusion feature map X″ enhanced After further processing through a 1×1 convolutional layer, the goal is to reduce the number of channels and optimize feature expression, and then upsampled through bilinear interpolation to restore the spatial resolution and make the image details clearer. Finally, the upsampled feature map passes through an activation function to obtain the final output aircraft target segmentation result P; the upsampling operation restores the spatial resolution of the image, enabling the network to generate high-quality segmentation results, while the 1×1 convolutional layer plays a role in further optimizing and integrating features.

[0111] In a specific embodiment, a loss function is used to measure the difference between the predicted result and the true label (mask ψ) during remote sensing image segmentation model training and optimization. The network output is the aircraft target segmentation result P, which represents the segmentation result image. The overall loss function is expressed as a hybrid loss function L:

[0112] L=εL1+δL2+μL3

[0113]

[0114] Among them, ε, δ, μ are scaling coefficients; L1 represents cross entropy loss, which measures the difference between the predicted probability distribution and the true distribution; L2 represents Dice loss, which is used to measure the similarity between two sets and is suitable for binary classification tasks, especially in the case of class imbalance; L3 represents IoU value, which is another common indicator for evaluating segmentation accuracy, calculating the intersection over union ratio of the predicted area and the true area; N represents the total number of pixels of the adjusted image in the training dataset; P iRepresents the predicted probability of the aircraft target segmentation result at pixel i in the remote sensing image segmentation network prediction output; ψ i represents the segmentation label of pixel i in the training dataset, ψ i is the label (0 or 1) of pixel i in the ground-truth mask.

[0115] Furthermore, during the training process, the loss function is minimized through backpropagation and gradient descent. The backpropagation algorithm calculates the gradient of the model parameters according to the loss function, and then updates the model weights through gradient descent. The weights are updated according to the following formula:

[0116]

[0117] Where η is the learning rate, It is the gradient of the loss function with respect to the parameter θ; through iterative optimization of backpropagation and gradient descent, the model continuously adjusts the parameters to reduce losses and improve performance.

[0118] After initial training, the model is typically fine-tuned. This involves adjusting hyperparameters such as the learning rate and batch size. By further training the model on both the training and validation sets, fine-tuning helps the model better adapt to new data and tasks, thereby improving segmentation accuracy. A fine-tuned model typically further improves performance and achieves better segmentation results.

[0119] 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.

[0120] 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 target segmentation method based on feature adaptive processing, characterized in that: The following steps are involved: Step 1: Collect remote sensing images and perform preprocessing and data enhancement to obtain a training dataset; Step 2: Construct a remote sensing image segmentation network and train it using the training data set to obtain a remote sensing image segmentation model; the remote sensing image segmentation network includes an encoder, a feature adaptive processing module, a multi-scale feature fusion module, and a decoder connected in sequence; Step 3: Collect the remote sensing image to be segmented, input it into the remote sensing image segmentation model, and obtain the target segmentation result; The process of remote sensing image segmentation network processing training images includes: The image in the training data set is input into the encoder for feature map extraction to obtain high-dimensional feature maps of multiple scales, including high-dimensional feature map X1, high-dimensional feature map X2, and high-dimensional feature map X3; The feature adaptive processing module performs pooling, fusion, and multi-head attention mechanism enhancement operations on the high-dimensional feature map to obtain an adaptive feature map; The multi-scale feature fusion module extracts features and adaptively fuses the adaptive feature map to obtain a fused feature map; The decoder performs weighted fusion, convolution adjustment and upsampling on the fused feature map in sequence to obtain the target segmentation result; The feature adaptive processing module includes the first average pooling layer, the second average pooling layer, the initial fusion layer, the multi-head attention layer, the first 1×1 convolution layer, the activation function layer, the second 1×1 convolution layer and the attention fusion layer. The specific processing process is as follows: Step 211: The high-dimensional feature map X1 is passed through the first average pooling layer to obtain a pooled feature map X′1, and the high-dimensional feature map X2 is passed through the second average pooling layer to obtain a pooled feature map X′2; Step 212: The pooled feature map X′1, the pooled feature map X′2 and the high-dimensional feature map X3 are concatenated or weighted fused in the initial fusion layer to obtain the initial fusion feature map X fusion ; Step 213: Initial fusion feature X fusion In the multi-head attention layer and mapped to multiple subspaces, multiple detection heads are used for parallel calculation to obtain multiple attention maps, and all attention maps are combined with the initial fusion feature X fusion Multiply to obtain the attention weighted feature map X attn ; Step 214: Attention-weighted feature map X attn Perform convolution operation in the first 1×1 convolution layer to obtain a compressed feature map; Step 215: The compressed feature map is activated in the activation function layer to obtain an activated feature map; Step 216: The activated feature map is convolved in the second 1×1 convolutional layer to obtain a weight map W; Step 217: The attention fusion layer adds the attention weighted feature map X attn Multiply it with the weight map W to obtain the adaptive feature map X enhanced .

2. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 1, characterized in that: In step 1, preprocessing includes cropping, scaling, and labeling, and data enhancement includes rotation, inversion, and color adjustment.

3. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 2, characterized in that: The process of preprocessing and data enhancement of remote sensing images in step 1 includes: Step 11: Label the remote sensing image, standardize the labeled remote sensing image, and normalize the pixels to [0,1]; Step 12: Crop the standardized remote sensing image according to the preset target size; Step 13: Randomly rotate or horizontally flip or vertically flip the cropped image to obtain the transformed image; Step 14: Perform color adjustment on the transformed image to obtain the adjusted image Step 15: Generate segmentation labels ψ based on the annotation information of the remote sensing image, and adjust the image Paired with the segmentation label ψ to form a training dataset 4. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 1, characterized in that: The process of remote sensing image segmentation network processing training images includes: The images in the training dataset are input into the encoder for feature map extraction to obtain high-dimensional feature maps of multiple scales; The feature adaptive processing module performs pooling, fusion, and multi-head attention mechanism enhancement operations on the high-dimensional feature map to obtain an adaptive feature map; The multi-scale feature fusion module extracts features and adaptively fuses the adaptive feature map to obtain a fused feature map; The decoder performs convolution adjustment and upsampling on the fused feature map in sequence to obtain the target segmentation result.

5. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 4, characterized in that: The encoder consists of three groups of convolution modules. Each convolution module consists of a convolution layer, an activation function layer, and a pooling layer connected in sequence. Each convolution module processes the image as follows: X i =MaxPool(ReLU(Conv(X i-1 ))) holes=1,2,3 Among them, X i-1 represents the image input to the convolution module, X i Represents the feature map output by the convolution module; i represents the i-th convolution module, and the first convolution module inputs the image in the training dataset; Conv represents the convolution operation; ReLU represents the activation function; MaxPool represents the maximum pooling operation; the first convolution module outputs a high-dimensional feature map X1, the second convolution module outputs a high-dimensional feature map X2, and the third convolution module outputs a high-dimensional feature map X3.

6. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 4, characterized in that: The multi-scale feature fusion module includes an upper branch, a middle branch, and a lower branch; the upper branch includes the third 1×1 convolution layer and the third average pooling layer connected in sequence; the middle branch includes the fourth 1×1 convolution layer, the activation function layer, the fourth average pooling layer, the scale fusion layer, and the scale splicing layer connected in sequence; the lower branch includes the fifth average pooling layer, the branch splicing layer, the fifth 1×1 convolution layer, and the sixth 1×1 convolution layer; the processing process of the multi-scale feature fusion module is as follows: Step 221: After the adaptive feature map undergoes the convolution operation of the third 1×1 convolution layer, the average pooling operation is performed in the third average pooling layer to obtain the global feature map x α , expressed as: x α =AvgPool(1×1Conv(X enhanced )) Among them, AvgPool represents average pooling; 1×1Conv represents 1*1 convolution operation; X enhanced Represents the adaptive feature map; After the adaptive feature map passes through the convolution operation of the fourth 1×1 convolution layer, it passes through the activation operation of the activation function layer and the average pooling operation of the fourth average pooling layer in sequence to obtain the weight map A β , expressed as: A β =AvgPool(ReLU(1×1Conv(X enhanced ))) Among them, RELU means applying the RELU activation function; The adaptive feature map is obtained after the average pooling operation of the fifth average pooling layer. Feature Map The enhanced feature map is then passed through the fifth 1×1 convolution layer and the sixth 1×1 convolution layer to obtain the enhanced feature map x. γ , expressed as: Step 222: Enhance feature map x γ Input to the scale fusion layer and weight map A β Multiply to obtain the enhanced weighted feature map x β , expressed as: x β =A β ·x γ ; Step 223: Enhance the weighted feature map x β and the global feature map x α Input to the scale splicing layer for addition to obtain the fusion feature map X″ enhanced .

7. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 4, characterized in that: The decoder consists of a convolutional layer, an upsampling layer, and an activation function layer connected in sequence; The fused feature map undergoes the convolution operation of the convolution layer, the bilinear interpolation upsampling operation of the upsampling layer, and the activation operation of the activation function layer in sequence to obtain the target segmentation result.

8. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 3, characterized in that: The remote sensing image segmentation network uses a hybrid loss function L to optimize the model during training, which is expressed as: L=εL1+δL2+μL3 Among them, L1 represents cross entropy loss; L2 represents Dice loss; L3 represents IoU value; N represents the total number of pixels of the adjusted image in the training dataset; P i represents the predicted probability at pixel i in the target segmentation result predicted by the remote sensing image segmentation network; ψ i represents the segmentation label of pixel i in the training dataset; ε, δ, and μ are the scaling coefficients respectively.

9. The method for remote sensing image target segmentation based on feature adaptive processing according to claim 8, characterized in that: During the training process, the remote sensing image segmentation network minimizes the hybrid loss function through back propagation and gradient descent. The back propagation algorithm calculates the gradient of the model parameters according to the hybrid loss function, and then updates the network weights through gradient descent.

Images