A remote sensing image defogging method

Abstract

The present invention discloses a remote sensing image defogging method, which relates to the fields of computer vision and image processing. The method employs a convolutional network comprising multi-scale and multi-dimensional modules to fit the mapping relationship between foggy images and clear images. The method comprises the following steps: S1: establishing a defogging model; S2: designing a defogging network comprising multi-scale and multi-dimensional modules, wherein each layer of the network extracts multi-scale and multi-dimensional features, which are then processed by an atmospheric scattering model unit; S3: collecting a training dataset; S4: training the defogging network comprising multi-scale and multi-dimensional modules; and S5: defogging the remote sensing image. The advantages of the present invention are that the multi-scale and multi-dimensional modules enhance the extraction of fine details, facilitate the extraction of fine details between foggy and fog-free images, and effectively remove haze. The method allows the model to adaptively prioritize global context or salient details as needed. The combination of multiple pooling methods ensures better feature fusion, improving image defogging performance.

Description

Technical Field

[0001] The present invention relates to the fields of computer vision and image processing, and in particular to a remote sensing image defogging method. Background Art

[0002] Remote sensing image dehazing, a key task in remote sensing image processing, aims to address the impact of scattering effects such as haze and smoke on image quality. In remote sensing imagery, suspended particles in the atmosphere can reduce image contrast and blur details, hindering the accurate extraction of surface information. Particularly in areas with high humidity and severe pollution, haze interference can significantly reduce the usability of remote sensing images.

[0003] Traditional remote sensing image dehazing methods are typically based on physical models, such as atmospheric scattering models, which estimate the effects of haze and restore a clear image. However, due to the complexity of atmospheric conditions and the diverse distribution of haze in different scenarios, physical model-based methods have limited effectiveness in practical applications. With the development of deep learning technology, data-driven dehazing methods have gradually become a research hotspot. By constructing large-scale remote sensing image dehazing datasets, deep learning networks can automatically learn the effects of haze on images, thereby achieving efficient dehazing in complex scenes.

[0004] Recent methods have turned to end-to-end learning frameworks, aiming to completely bypass the limitations of physical models. Examples of such methods include multi-scale convolutional neural networks (CNNs), which directly map blurry images to dehazed images. The success of these methods is largely due to their ability to automatically extract powerful discriminative features through multi-layer convolution operations. However, one of the inherent limitations of convolution is that it is a local operation. This means that while convolutional layers are excellent at capturing fine local details, they have difficulty simulating long-range dependencies and global structural information, which are often crucial for accurately restoring blurry images. For these reasons, the present invention designs a dehazing method for remote sensing images. Summary of the Invention

[0005] The purpose of the present invention is to solve the problems in the prior art and to propose a remote sensing image defogging method.

[0006] A remote sensing image defogging method uses a convolutional network with multi-scale and multi-dimensional modules to fit the mapping relationship between foggy images and clear images. It includes the following steps:

[0007] S1: Building a dehazing model

[0008] S2: Design a dehazing network with multi-scale and multi-dimensional modules. Each layer of the network extracts multi-scale and multi-dimensional features, which are then processed by the atmospheric scattering model unit.

[0009] S3: Collect training dataset;

[0010] S4: training a dehazing network with multi-scale and multi-dimensional modules;

[0011] S5: Remote sensing image dehazing.

[0012] In the above remote sensing image defogging method, in step S1, the defogging model:

[0013] r=F(h)

[0014] Here, h represents the foggy image, r represents the restored clear image, and the function F represents the mapping relationship between the foggy image and the corresponding clear image. The mapping relationship F(h) between the foggy image and the clear image is fitted through a scale-multidimensional physical convolutional network. In this structure, the overall framework of the network is based on U-Net, and each layer of upsampling or downsampling is composed of a feature extraction block. In the extraction block structure, the multi-scale block and the multi-dimensional extraction block extract multi-scale and multi-dimensional information in parallel, and then enter the atmospheric scattering model unit for effective defogging. The atmospheric scattering model is described as:

[0015] I(x)=J(x)t(x)+A[1-t(x)]

[0016] Where I(x) is the image affected by haze; J(x) is the haze-free image to be restored; t(x) is the transmittance of light through the atmospheric medium; x represents the image coordinate; A is the global atmospheric light constant.

[0017] In the above remote sensing image defogging method, the multi-scale and multi-dimensional module includes a multi-scale extraction block and a multi-dimensional extraction block, and the multi-scale extraction block includes the following steps:

[0018] S211: Apply multiple parallel dilated convolutions with different dilation rates

[0019] S212: Fusion of multi-scale features using selective kernel module;

[0020] S213: After processing the feature map, the learned features will pass through the pixel attention mechanism;

[0021] S214: Introduces a channel attention mechanism that runs in parallel and adaptively highlights fog-related features across the entire image;

[0022] S215: The features extracted by the two attention mechanisms are fused together by summing to create a feature set. In order to refine the fused features, a 3×3 convolution is finally applied.

[0023] The multidimensional extraction block includes the following steps:

[0024] S221: Applying depthwise convolution to preserve feature representation while ensuring computational efficiency;

[0025] S222: Normalization is performed to stabilize the feature distribution, thereby improving convergence during training;

[0026] S223: Use a combination of 1×1 convolution and 3×3 convolution layers to expand the number of channels and enhance the richness of feature information. The 1×1 convolution increases the depth of the feature map, while the 3×3 convolution captures local patterns.

[0027] S224: The normalized features extracted from the convolution are fused together to more fully represent the input data. After fusion, another 3×3 convolution is applied to further refine the extracted features.

[0028] S225: After fusion, another 3×3 convolution is applied to further refine the extracted features, and then the refined features are multiplied with another branch processed by the Sigmoid function, effectively rescaling the feature values ​​and enhancing the dimensional representation;

[0029] S226: Use 1×1 convolution to reduce dimensionality to compress useful information and prevent overfitting;

[0030] S227: The reduced feature map is passed to another deep convolutional layer and the residual connection is merged to retain the original feature information, producing the final output, which effectively combines the enhanced and retained features, ready for subsequent processing tasks.

[0031] In the above remote sensing image dehazing method, in step S2, for the number of blocks in each layer, the configuration of [N1, N2, N3, N4, N5] is set to [2, 2, 4, 2, 2], and the corresponding embedding channels are [24, 48, 96, 48, 24], respectively learning multiple sub-maps in the dehazing model, and the last layer of the network maps the feature map to the original image dimension.

[0032] In the above remote sensing image dehazing method, in step S3, two synthetic remote sensing haze datasets SateHaze1k and HRSD are used;

[0033] The SateHaze1k dataset includes three subsets: light fog, moderate fog, and heavy fog. Each subset contains a training set and a test set. Light fog images use haze masks from real clouds, while moderate haze samples combine the features of fog and moderate haze. Thick fog images are generated using the transmission map of dense fog.

[0034] The HRSD dataset consists of two subsets: LHID and DHID. LHID contains training images and test images generated by the atmospheric scattering model to train the network to handle different degrees of haze in remote sensing images. At the same time, DHID includes images created from multiple real haze maps to present haze more realistically. The combination of these two subsets ensures a comprehensive evaluation of dehazing methods in synthetic haze scenes and more realistic haze scenes.

[0035] In the above remote sensing image defogging method, in step S4, the learning-based defogging method uses labeled fog samples for training. The datasets used are SateHaze1k and HRSD. In this step, the network is trained with the collected foggy image samples to learn the mapping relationship between foggy images and clear images. The L1 loss function is used to facilitate defogging, where:

[0036] L1=||J-GT||1

[0037] Among them, J is the actual output result of the network, GT is the true value image, multi-angle random rotation and horizontal flipping are used to enhance the training data set, and the stochastic gradient descent method is selected to optimize the L1 loss function.

[0038] In the above remote sensing image defogging method, in step S5, the original foggy image is re-entered into the atmospheric scattering model unit at the final output of the defogging network to guide the network to restore the original image structure.

[0039] In the above remote sensing image dehazing method, in step S212, the selective kernel module adopts hybrid SK fusion, and the hybrid SK fusion introduces global maximum pooling in parallel with the global average pooling to better preserve important details such as edges and textures. In order to balance the contributions of the global average pooling and the global maximum pooling, a hybrid module with a learnable parameter m is introduced, and this parameter is converted into a weight λ using the Sigmoid function.

[0040] Compared with the existing technology, the advantages of the present invention are:

[0041] 1. The network proposed in this paper is built on the U-net architecture and has a multi-scale and multi-dimensional module composed of a multi-scale extraction block and a multi-dimensional extraction block, which can enhance the extraction of fine details, help extract fine details between foggy and fog-free images, and effectively remove haze.

[0042] 3. The present invention allows the model to adaptively prioritize global context or salient details as needed. The combination of multiple pooling methods adopted can ensure better feature fusion and improve the performance of tasks such as image dehazing by effectively capturing global and local features.

[0043] 3. The remote sensing image defogging method designed by the present invention is end-to-end. Once the network model is trained, it is only necessary to input the image to be defogged into the network. Through the forward propagation of the network, a clear image can be restored at the output end, which is easy to operate. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 This is a diagram of the steps in the remote sensing image defogging method proposed by the present invention.

[0045] Figure 2 This is a model diagram of the multi-scale and multi-dimensional module in the remote sensing image dehazing method proposed in this invention.

[0046] Figure 3 This is a model diagram of the atmospheric scattering model in the remote sensing image defogging method proposed in this invention.

[0047] Figure 4 This is a structural diagram of the selective kernel module fusion in the remote sensing image defogging method proposed in this invention.

[0048] Figure 5 This is a visual comparison diagram of two images in the Haze1k-thin dataset in the remote sensing image dehazing method proposed in this invention.

[0049] Figure 6 This is a visual comparison diagram of two images in the Haze1k-moderate dataset in the remote sensing image dehazing method proposed in this invention.

[0050] Figure 7 This is a visual comparison diagram of two images in the Haze1k-thick dataset in the remote sensing image dehazing method proposed in this invention.

[0051] Figure 8 This is a visual comparison diagram of three images in the LHID data in the remote sensing image defogging method proposed in this invention.

[0052] Figure 9 This is a visual comparison diagram of three images in the DHID data in the remote sensing image dehazing method proposed in this invention. DETAILED DESCRIPTION

[0053] Reference Figure 1-9 A remote sensing image defogging method uses a convolutional network including multi-scale and multi-dimensional modules to fit the mapping relationship between foggy images and clear images. The flowchart of the present invention is as follows Figure 1As shown, the computer configuration used is: Intel(R) Xeon(R) CPU E5-2620 v4 processor, Nvidia GeForce GTX 1080Ti graphics processor, main frequency 2.10GHz, memory 12GB, operating system Ubuntu 18.04. The defogging method is implemented based on the Pytorch framework. The present invention is a defogging method based on convolutional neural network, which specifically includes the following steps:

[0054] Step 1: Build a dehazing model

[0055] Let h represent the foggy image, r represent the restored clear image, and function F represent the mapping relationship between the foggy image and the corresponding clear image. Then the defogging problem is modeled as follows (i.e., the defogging model):

[0056] r=F(h)

[0057] According to the above formula, once the mapping relationship F is obtained, given a foggy image h, a clear image can be obtained through functional relationship mapping, thereby achieving image defogging.

[0058] The present invention uses a convolutional network with multi-scale and multi-dimensional modules to fit the mapping relationship F(h) between foggy images and clear images. In this structure, the overall framework of the network is based on U-Net, and each upsampling or downsampling layer is composed of a feature extraction block. In the extraction block structure, the multi-scale block and the multi-dimensional extraction block extract multi-scale and multi-dimensional information in parallel, and then enter the atmospheric scattering model unit for effective defogging. The atmospheric scattering model is described as:

[0059] I(x)=J(x)t(x)+A[1-t(x)]

[0060] Where I(x) is the image affected by haze; J(x) is the haze-free image to be restored; t(x) is the transmittance of light through the atmospheric medium; x represents the image coordinate; A is the global atmospheric light constant.

[0061] In order to better restore the foggy image, the original foggy image is re-entered into the atmospheric scattering model unit at the final output of the network to guide the network to restore according to the original image structure.

[0062] Step 2: Design a dehazing network with multi-scale and multi-dimensional modules

[0063] According to the defogging model established in step 1, the design is as follows Figure 2The dehazing network of the multi-scale and multi-dimensional module shown in the figure includes a multi-scale extraction block and a multi-dimensional extraction block. The multi-scale extraction block is inspired by the pixel attention (PA) and channel attention (CA) proposed in FFA-Net. Before the pixel attention block, the present invention uses dilated convolutions with dilation rates of 1, 2, 4, and 8 to extract multi-scale detail features. The multi-dimensional extraction block uses a depth-separable convolution layer to extract features with more dimensions. In addition, the present invention designs a dehazing unit (physical model) based on the atmospheric scattering model, extracts atmospheric light (A) through a fully connected layer, extracts transmittance (t) through a convolution layer, and finally obtains a restored clear image (J). This architecture helps to extract fine details between foggy and non-fog images and can effectively remove haze.

[0064] When used, the method first applies four parallel dilated convolutions with different dilation rates, which allows the extraction of features at multiple scales and effectively captures fine details and broader contextual information. In order to further enhance the feature representation, the present invention uses an optimized selective kernel module to fuse these multi-scale features, which helps to retain important information at each scale. The selective kernel module adopts hybrid SK fusion, which is an optimization based on SK fusion (SK-Fusion) and enhances image feature selection by adjusting the receptive field. In order to improve the original SK fusion, which only uses global average pooling and may miss key features, the hybrid SK fusion layer introduces global maximum pooling in parallel with global average pooling to better retain important details such as edges and textures. In order to balance the contributions of global average pooling and global maximum pooling, a hybrid module with a learnable parameter m is introduced, and this parameter is converted into a weight λ using a Sigmoid function. This weight is dynamically adjusted during training, allowing the model to adaptively prioritize global context or significant details as needed. The combination of these pooling methods ensures better feature fusion and improves the performance of tasks such as image dehazing by effectively capturing global and local features. Specifically, in the initial parameter m, when the second layer downsampling and the first layer upsampling are fused, m is set to 0.4, and when the first layer downsampling and the second layer upsampling are fused, m is set to 0.8;

[0065] The combination of the above operations ensures that both local and multi-scale contextual features of the feature map are well preserved. After processing the feature map in this manner, the learned features are then passed through a pixel-attention mechanism. This step is crucial for extracting critical scale-specific details by emphasizing the most relevant pixel-level information. The pixel-attention mechanism focuses on identifying and enhancing important regions of the image, which are crucial for tasks such as image dehazing, where local clarity is important. In addition to pixel-attention, the present invention also introduces a channel-attention mechanism that operates in parallel. While pixel-attention focuses on specific spatial regions, channel-attention focuses on global information and adaptively highlights haze-related features across the entire image. This dual attention approach—combining pixel and channel attention—ensures that the network captures both fine local details and broader scene features. The features extracted by the two attention mechanisms are then fused together through summation, creating a more comprehensive and richer feature set. To further refine the fused features, a 3×3 convolution is finally applied. This step helps smooth and refine the features, making them more suitable for downstream tasks such as image restoration or dehazing.

[0066] The present invention uses different dilation rates in dilated convolutions. Small dilated convolutions are particularly effective in recovering detailed texture information, while larger dilations provide a wider receptive field, allowing the model to capture long-range dependencies and a wider range of structural information in the image. In the multi-dimensional extraction block (MDB) architecture, the present invention first applies depthwise convolution to maintain feature representation while ensuring computational efficiency. Normalization is then performed to stabilize the feature distribution, thereby improving convergence during training. Next, the present invention utilizes a combination of 1×1 convolution and 3×3 convolution layers to expand the number of channels and enhance the richness of feature information. 1×1 convolution increases the depth of the feature map, while 3×3 convolution captures local patterns. The normalized features extracted from these convolutions are then fused together to more comprehensively represent the input data. After fusion, the present invention applies another 3×3 convolution to further refine the extracted features. The present invention then multiplies the refined features with another branch processed by a Sigmoid function, effectively rescaling the feature values ​​and enhancing the dimensional representation. Then, the present invention uses 1×1 convolution to reduce the dimension to compress useful information and prevent overfitting. Finally, the present invention passes the reduced feature map to another depth convolution (DW Conv) layer and incorporates residual connections to retain the original feature information. This produces the final output, which effectively combines the enhanced and retained features, ready for subsequent processing tasks.

[0067] The foggy image is input into the network, and the output is the corresponding clear image. The network in the present invention is an end-to-end structure, wherein each layer of the network extracts multi-scale and multi-dimensional features, and then enters the atmospheric scattering model unit for processing. In the atmospheric scattering model unit, the present invention is based on Figure 3The model diagram re-represents the clear image (J): In order to better extract the feature information of atmospheric light (A) and transmittance (t), the present invention introduces two dilated convolution blocks before extracting features. Each dilated convolution block consists of a dilated convolution layer, a batch normalization layer, and an activation function layer. The dilated convolution can avoid information loss while expanding the receptive field, especially when processing details such as image edges and textures, it can better retain these key features. In the dehazing process, it can capture contextual information in a larger range, which helps to better understand the haze distribution and global structure in the image. Considering that atmospheric light is usually assumed to be uniform, the present invention uses global average pooling to remove redundant information in the feature space. However, due to information loss, we cannot apply global average pooling to the transmittance (t) because the transmission map is non-uniform. Therefore, we choose to use a series of 3x3 convolutional layers to extract features. For the number of blocks in each layer, we set the configuration of [N1, N2, N3, N4, N5] to [2, 2, 4, 2, 2], and the corresponding embedding channels are [24, 48, 96, 48, 24]. We learn multiple sub-maps in the dehazing model separately. The last layer of the network maps the feature map to the original image dimension.

[0068] Step 3: Collect training dataset

[0069] This paper uses two synthetic remote sensing (RS) haze datasets, SateHaze1k and HRSD. SateHaze1k includes three subsets: light haze, moderate haze, and heavy haze, each containing a training set of 320 images and a test set of 45 images. Light haze images utilize haze masks from real cloud layers, while moderate haze samples combine the characteristics of fog and moderate haze. Heavy haze images are generated using a transmission map of heavy fog. The HRSD dataset is divided into two subsets: LHID and DHID. LHID contains a total of 30,517 training images and 500 test images, all of which are generated using an atmospheric scattering model. This subset simulates various haze conditions to train the network to handle different levels of haze in remote sensing imagery. On the other hand, DHID consists of a total of 14,990 images, which were created using real haze maps to more realistically present haze. Of these, 14,490 images are used for training and 500 for testing. The combination of these two subsets ensures a comprehensive evaluation of dehazing methods in both synthetic haze scenes and more realistic haze scenes.

[0070] Step 4: Train the dehazing network with multi-scale and multi-dimensional modules

[0071] Learning-based dehazing methods require labeled fog samples for training. Currently, the most commonly used datasets are SateHaze1k and HRSD.

[0072] In this step, the network is trained with the collected foggy image samples to achieve the goal of transforming foggy images into clear images.

[0073] Learning the mapping relationship between images. In the field of dehazing, studies have shown that L1 loss is more conducive to dehazing. The L1 loss function is:

[0074] L1=||J-GT||1

[0075] Where J is the actual output of the network, and GT is the true value image. The present invention uses the PyTorch framework for training on a system equipped with four NVIDIA GeForce GTX 1080Ti GPUs. In order to enhance the training data set, the present invention performs random rotations of 90, 180, and 270 degrees and horizontal flipping. The input of the network includes RGB remote sensing images cropped to a size of 256×256 pixels. The present invention uses the Adam optimizer (β1=0.9, β2=0.999) and a batch size of 4 to train each sub-dataset. The initial learning rate is set to 0.0002, and the present invention uses a cosine annealing strategy to gradually reduce it to 0. The present invention selects the stochastic gradient descent method to optimize the loss function, uses foggy images to iteratively learn the network, and updates the network parameters. When the network loss value tends to be stable, the training can be terminated. The network parameters saved at this time are the trained defogging network model.

[0076] Step 5: Remote Sensing Image Dehazing

[0077] The remote sensing image defogging method designed by the present invention is end-to-end. Once the network model is trained, the image to be defogged only needs to be input into the network, and the restored image can be obtained at the output through the forward propagation of the network.

[0078] Clear image. The present invention uses the test set in the data set to test the effect. In order to demonstrate the competitiveness of the dehazing method of the present invention, the present invention compares the network with seven advanced dehazing methods: DCP, AOD-Net, FCTF-Net, GridDehaze-Net, FFA-Net, MixDehaze-Net and OK-Net. To ensure a fair comparison, the present invention uses the official implementations of these deep learning models in the training process. These models are provided by their respective authors. For intuitive effects, please refer to the attached figure.

[0079] In the figure below, PSNR stands for Peak Signal-to-Noise Ratio, SSIM stands for Structural Similarity, Hazy Image represents a foggy image, and GT represents a true image.

[0080] Table 1 shows the results of SateHaze1k. For the compared methods, the present invention uses bold and underline to mark the best and second best methods.

[0081] Table 1

[0082]

[0083] Table 2 shows the HRSD results. For the compared methods, the present invention uses bold and underline to mark the best and second best methods;

[0084] Table 2

[0085]

[0086] It is understood from common technical knowledge that the present invention may be implemented by other embodiments that do not depart from its spirit or essential features. Therefore, the embodiments disclosed above are, in all respects, merely illustrative and not exclusive. All modifications within the scope of the present invention or equivalent to the scope of the present invention are intended to be encompassed by the present invention.

Claims

1. A remote sensing image defogging method, characterized in that: A convolutional network with multi-scale and multi-dimensional modules is used to fit the mapping relationship between foggy images and clear images, including the following steps: S1: Establish a dehazing model; S2: Design a dehazing network with multi-scale and multi-dimensional modules. Each layer of the network extracts multi-scale and multi-dimensional features, which are then processed by the atmospheric scattering model unit. S3: Collect training dataset; S4: training a dehazing network with multi-scale and multi-dimensional modules; S5: Remote sensing image dehazing; In step S2, the multi-scale and multi-dimensional module includes a multi-scale extraction block and a multi-dimensional extraction block. The multi-scale extraction block includes the following steps: S211: Apply multiple parallel dilated convolutions with different dilation rates S212: Fusion of multi-scale features using selective kernel module; S213: After processing the feature map, the learned features will pass through the pixel attention mechanism; S214: Introduces a channel attention mechanism that runs in parallel and adaptively highlights fog-related features across the entire image; S215: The features extracted by the two attention mechanisms are fused together by summing to create a feature set. In order to refine the fused features, a 3×3 convolution is finally applied. The multidimensional extraction block includes the following steps: S221: Applying depthwise convolution to preserve feature representation while ensuring computational efficiency; S222: Normalization is performed to stabilize the feature distribution, thereby improving convergence during training; S223: Use a combination of 1×1 convolution and 3×3 convolution layers to expand the number of channels and enhance the richness of feature information. 1×1 convolution increases the depth of the feature map, while 3×3 convolution captures local patterns. S224: The normalized features extracted from the convolution are fused together to more fully represent the input data. After fusion, another 3×3 convolution is applied to further refine the extracted features. S225: After fusion, another 3×3 convolution is applied to further refine the extracted features, and then the refined features are multiplied with another branch processed by the Sigmoid function, effectively rescaling the feature values ​​and enhancing the dimensional representation; S226: Use 1×1 convolution to reduce dimensionality to compress useful information and prevent overfitting; S227: The reduced feature map is passed to another deep convolutional layer and the residual connection is merged to retain the original feature information, producing the final output, which effectively combines the enhanced and retained features, ready for subsequent processing tasks.

2. The remote sensing image defogging method according to claim 1, characterized in that: In step S1, the dehazing model: Where h represents the foggy image, r represents the restored clear image, and the function F represents the mapping relationship between the foggy image and the corresponding clear image. The mapping relationship F(h) between the foggy image and the clear image is fitted through a scale-multidimensional physical convolutional network. The overall framework of the network is based on U-Net, and each layer of upsampling or downsampling has a feature extraction block. In the extraction block structure, the multi-scale block and the multi-dimensional extraction block extract multi-scale and multi-dimensional information in parallel, and then enter the atmospheric scattering model unit for effective defogging. The atmospheric scattering model is described as: Where I(x) is the image affected by haze; J(x) is the haze-free image to be restored; t(x) is the transmittance of light through the atmospheric medium; x represents the image coordinate; A is the global atmospheric light constant; 3. The remote sensing image defogging method according to claim 1, characterized in that: In step S2, for the number of blocks in each layer, the configuration of [N1, N2, N3, N4, N5] is set to [2, 2, 4, 2, 2], and the corresponding embedding channels are [24, 48, 96, 48, 24], respectively learning multiple sub-maps in the dehazing model. The last layer of the network maps the feature map to the original image dimension.

4. The remote sensing image defogging method according to claim 1, wherein: In step S3, two synthetic remote sensing haze datasets, SateHaze1k and HRSD, are used; The SateHaze1k dataset includes three subsets: light fog, moderate fog, and heavy fog. Each subset contains a training set and a test set. Light fog images use haze masks from real clouds, while moderate haze samples combine the features of fog and moderate haze. Thick fog images are generated using the transmission map of dense fog. The HRSD dataset consists of two subsets: LHID and DHID. LHID contains training images and test images generated by an atmospheric scattering model to train the network to handle different degrees of haze in remote sensing images. At the same time, DHID includes images created from multiple real haze maps to present haze more realistically. The combination of these two subsets ensures a comprehensive evaluation of dehazing methods in both synthetic haze scenes and more realistic haze scenes.

5. The remote sensing image defogging method according to claim 1, wherein: In step S4, the learning-based dehazing method uses labeled fog samples for training. The datasets used are SateHaze1k and HRSD. In this step, the network is trained with the collected foggy image samples to learn the mapping relationship between foggy images and clear images. The L1 loss function is used to facilitate dehazing, where: Among them, J is the actual output result of the network, GT is the true value image, multi-angle random rotation and horizontal flipping are used to enhance the training data set, and the stochastic gradient descent method is selected to optimize the L1 loss function.

6. The remote sensing image defogging method according to claim 1, characterized in that: In step S5, the original foggy image is re-entered into the atmospheric scattering model unit at the final output of the defogging network to guide the network to restore the original image structure.

7. The remote sensing image defogging method according to claim 1, characterized in that: In step S212, the selective kernel module adopts hybrid SK fusion, which introduces global maximum pooling in parallel with global average pooling to better preserve important details such as edges and textures. In order to balance the contributions of global average pooling and global maximum pooling, a hybrid module with a learnable parameter m is introduced. This parameter is converted into a weight λ using the Sigmoid function. The weight is dynamically adjusted during training, allowing the model to adaptively prioritize global context or salient details as needed.

Images