A method for extracting urban impervious surfaces from high-resolution remote sensing images

Abstract

The present invention discloses a method for extracting urban impervious surfaces from high-resolution remote sensing images, and relates to the technical field of remote sensing extraction of impervious surfaces. The method comprises: acquiring high-spatial-resolution remote sensing data of the area to be analyzed; creating a sample data set based on the characteristics of the impervious surfaces; improving the quality of the imbalanced sample data distribution in the sample data set to obtain a high-quality sample data set, which is divided into a training set and a test set; constructing a feature-fused deep convolutional neural network semantic segmentation model; inputting the training set into the semantic segmentation model for model training to obtain a trained semantic segmentation model; inputting the test set into the trained semantic segmentation model for object classification to generate a classification result of urban objects with dense regional semantics; and employing a shadow area impervious surface extraction scheme using a multi-scale segmentation and knowledge hierarchical model, and finally integrating the impervious surface extraction results of the non-shadow area and the shadow area to obtain the urban impervious surface distribution. The present invention can improve the accuracy of impervious surface extraction.

Description

Technical Field

[0001] The invention relates to the technical field of remote sensing extraction of impervious surfaces, and in particular to a method for extracting urban impervious surfaces from high-resolution remote sensing images. Background Art

[0002] The continuous pace of urbanization has led to a rapid expansion of impervious surfaces. Impervious surfaces refer to natural or artificial surfaces that prevent surface water from penetrating into the soil. Examples include waterproof roofs, urban roads, squares, and parking lots. Impervious surfaces absorb heat quickly and have low specific heat capacity, making them a high-heat storage mass in cities. This increases urban surface temperatures and creates the urban heat island effect. The expansion of urban impervious surfaces prevents surface water from infiltrating, leading to increased runoff, exacerbating urban flooding caused by rainstorms and causing ecological and environmental problems such as water pollution. Therefore, impervious surface information not only reflects changes in land use and land cover caused by urbanization but also has a profound impact on the urban ecological environment. Impervious surfaces are a key indicator for evaluating the quality of urban ecological environments. Timely, accurate, and automated extraction of high-precision impervious surface information is crucial for monitoring urbanization, planning sponge cities, and promoting ecological development, as well as achieving sustainable development in urban and rural areas.

[0003] Traditional methods for acquiring impervious surface data rely primarily on manual ground surveys and mapping, but this method is costly and slow to update. With the rapid development of satellite Earth observation technology, remote sensing data, with its advantages of low cost, high efficiency, timely delivery, wide coverage, and repeatability, has become widely used in research related to impervious surface extraction. Current methods for extracting impervious surfaces based on different remote sensing data include spectral hybrid decomposition methods based on optical and radar remote sensing data, regression models, decision tree models, spectral index methods, and classification.

[0004] Therefore, it is an urgent problem for those skilled in the art to propose a method for extracting urban impervious surfaces from high-resolution remote sensing images to solve the difficulties existing in the existing technology. Summary of the Invention

[0005] In view of this, the present invention provides a method for extracting urban impervious surfaces from high-resolution remote sensing images, which can improve the extraction accuracy of impervious surface types and spatial distribution.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] A method for extracting urban impervious surfaces from high-resolution remote sensing images, comprising:

[0008] S1. Obtain high spatial resolution remote sensing data, high precision DSM data and open source POI geospatial data of the area to be analyzed;

[0009] S2. Create a sample dataset based on the characteristics of urban impervious surfaces;

[0010] S3. Use data augmentation and mixed sampling techniques to improve the distribution quality of unbalanced sample data in the sample dataset, obtain a high-quality sample dataset, and divide the high-quality sample dataset into a training set and a test set;

[0011] S4. Construct a deep convolutional neural network semantic segmentation model with feature fusion;

[0012] S5. Inputting the training set into the feature-fused deep convolutional neural network semantic segmentation model for model training to obtain a trained feature-fused deep convolutional neural network semantic segmentation model;

[0013] S6. Input the test set into the trained feature-fused deep convolutional neural network semantic segmentation model to perform object classification and generate the urban object classification results with regional dense semantics;

[0014] S7. Use a multi-scale segmentation and knowledge hierarchical model to extract impervious surfaces in shadow areas, and integrate the impervious surface extraction results of non-shadow areas and shadow areas to obtain the final urban impervious surface distribution.

[0015] In the above method, optionally, the high spatial resolution remote sensing data of the area to be analyzed in S1 include: high spatial resolution optical satellite Gaofen-2 remote sensing data of the area to be analyzed, high-precision DSM data generated by stereo image pairs of the Ziyuan-3 satellite of the area to be analyzed, and open source POI geospatial data of the area to be analyzed crawled based on an open interface.

[0016] In the above method, optionally, the sample data set in S2 includes: remote sensing data, spectral index data, and labeled data;

[0017] Each sample data is in the form of: image-annotation-spectral index data;

[0018] The preparation of sample datasets includes: data preprocessing, sample annotation and spectral index extraction;

[0019] Sample labeling: By directly labeling the original pixels with categories and vectorizing them, urban features are classified into categories including bare land, grass, water bodies, trees, roads, buildings, squares, and shadows. Roads, buildings, and squares are all impervious surface extraction results in non-shadow areas.

[0020] Spectral index extraction The spectral indexes of impervious surfaces include: NDWI index and NDVI index;

[0021] The NDVI index is calculated using the near-infrared band and red band in the acquired high-spatial-resolution remote sensing data image, and the NDWI index is calculated using the near-infrared band and green band.

[0022] In the above method, optional data enhancement in S3 includes: translation, rotation, mirroring, scaling, color space switching and adding interference;

[0023] Hybrid sampling: Combining random undersampling and random oversampling, it enhances the distribution of balanced data for the minority class, reduces the classifier's bias towards the majority class, and obtains a high-quality sample data set.

[0024] In the above method, optionally, in S4, a feature-fused deep convolutional neural network semantic segmentation model is constructed based on the ResNet50 residual network and the VGG-16 convolutional neural network. The feature-fused deep convolutional neural network semantic segmentation model includes: an encoding module, a decoding module, and a Softmax layer;

[0025] The encoding module adopts a dual-channel structure. The first channel uses the ResNet50 residual network as the backbone network, combined with void convolution to extract features and obtain RGB image features. The second channel is a branch network that inputs NDVI and NDWI data. The five convolutional layers of the VGG-16 convolutional neural network are used as the backbone. After four times of 2x sampling, the final 16x downsampled feature output is generated to obtain spectral index features. The stacking and gluing fusion method of multiple input vectors on the specified axis is used to explicitly establish the correlation between the RGB image features and the spectral index features NDVI and NDWI multi-feature maps.

[0026] The decoding module adopts a multi-step decoder. In the decoding stage, the input of each layer includes the output of the previous deconvolution layer, as well as the convolution output of the corresponding layer in the encoding stage, gradually restoring the feature map to the original resolution. The global-local Transformer block is introduced. The Transformer block consists of an efficient global-local attention mechanism, a multi-layer perceptron, two batch normalization operations, and two sum operations.

[0027] The above method is optional, and the specific content of S5 is: using the training set data, iteratively training the constructed feature-fused deep convolutional neural network semantic segmentation model, updating the full convolutional network parameters in the feature-fused deep convolutional neural network semantic segmentation model, and completing the model training.

[0028] In the above method, optionally, in S7, shadow-based segmentation recognition objects are obtained through multi-scale segmentation;

[0029] The vegetation, bare soil, water bodies and impervious surfaces in the shadow area are reclassified to assist in distinguishing the impervious surfaces under tree canopy cover. The impervious surface extraction results of the non-shadow area and the shadow area are integrated to obtain the final urban impervious surface distribution.

[0030] Through the above technical solutions, it can be seen that compared with the existing technology, the present invention provides a method for extracting urban impervious surfaces from high-resolution remote sensing images, which has the following beneficial effects: 1) The present invention uses a deep learning method with multi-feature fusion to extract impervious surface information, which can obtain optimal model parameters, reduce the dependence on prior knowledge and human intervention, and obtain higher impervious surface extraction accuracy; 2) A pixel-level spatial scale urban land feature classification model is constructed, which can realize large-scale and refined impervious surface extraction and improve the accuracy of the model in extracting impervious surfaces; 3) Shadows are extracted as a separate category, and secondary classification is performed based on the classified shadow results, while spectral index is used to extract the impervious surface information. The input of numerical data includes vegetation index and water body index, which are input into the convolutional neural network classification model to help distinguish water bodies, vegetation and shadow categories; 4) The classification accuracy of ground objects and non-ground objects is improved, and the shape of buildings can be more accurately portrayed, which is conducive to solving the problem of distinguishing between the same object with different spectra / different objects with the same spectrum and impervious buildings and trees in shadow areas in high-resolution images; 5) Optimize the extraction of roads and extract road information under tree canopy cover, merge the building categories and road / square categories obtained after hierarchical classification into the final impervious surface information, and obtain more accurate impervious surface coverage extraction by combining multi-source and multi-modal data fusion with deep learning methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] 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.

[0032] Figure 1 A flowchart of a method for extracting urban impervious surfaces from high-resolution remote sensing images provided by the present invention;

[0033] Figure 2 This is a diagram showing the module composition of the feature-fused deep convolutional neural network semantic segmentation model provided by the present invention;

[0034] Figure 3 This is a structural diagram of the deep convolutional neural network semantic segmentation model with feature fusion provided by the present invention. DETAILED DESCRIPTION

[0035] 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.

[0036] In this application, relational terms such as first and second are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. The terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or apparatus comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article or apparatus comprising the element.

[0037] Reference Figure 1 As shown, the present invention discloses a method for extracting urban impervious surfaces from high-resolution remote sensing images, comprising:

[0038] S1. Obtain high spatial resolution remote sensing data, high precision DSM data and open source POI geospatial data of the area to be analyzed;

[0039] S2. Create a sample dataset based on the characteristics of urban impervious surfaces;

[0040] S3. Use data augmentation and mixed sampling techniques to improve the distribution quality of unbalanced sample data in the sample dataset, obtain a high-quality sample dataset, and divide the high-quality sample dataset into a training set and a test set;

[0041] S4. Construct a deep convolutional neural network semantic segmentation model with feature fusion;

[0042] S5. Inputting the training set into the feature-fused deep convolutional neural network semantic segmentation model for model training to obtain a trained feature-fused deep convolutional neural network semantic segmentation model;

[0043] S6. Input the test set into the trained feature-fused deep convolutional neural network semantic segmentation model to perform object classification and generate the urban object classification results with regional dense semantics;

[0044] S7. Use a multi-scale segmentation and knowledge hierarchical model to extract impervious surfaces in shadow areas, and integrate the impervious surface extraction results of non-shadow areas and shadow areas to obtain the final urban impervious surface distribution.

[0045] Furthermore, the high spatial resolution remote sensing data of the area to be analyzed in S1 include: high spatial resolution optical satellite Gaofen-2 remote sensing data of the area to be analyzed, high-precision DSM data generated by the stereo image pair of the Ziyuan-3 satellite in the area to be analyzed, and open source POI geospatial data of the area to be analyzed crawled based on an open interface.

[0046] Furthermore, S2 creates a sample database based on the characteristics of urban impervious surfaces, adding rich samples of multi-band and multi-object types, thus providing sample dataset support for multi-feature fusion high-resolution remote sensing image object classification;

[0047] The sample dataset includes: remote sensing data, spectral index data and annotation data;

[0048] Each sample data is in the form of "image-annotation-spectral index data", that is, for each original image, its corresponding annotation data and spectral index data can be obtained;

[0049] The preparation of sample data sets includes: data preprocessing, sample annotation and spectral index extraction;

[0050] Sample labeling: By directly labeling the original pixels with categories and vectorization, urban features are classified into categories including bare land, grassland, water bodies, trees, roads, buildings, squares, and shadows. Roads, buildings, and squares are all impervious surface extraction results in non-shadow areas. Category labeling is performed directly on the original pixels, including multiple labeling forms such as polyline, rectangle, straight line, ellipse, circle, arbitrary rectangle (three-point method), parallelogram, and arbitrary polygon.

[0051] Spectral index extraction selects impervious surface spectral indicators including NDWI and NDVI, which can further improve the classification accuracy of water, trees, and shadows. They serve as input factors of the feature fusion network and correspond one-to-one with the original image and the annotated data.

[0052] The NDVI index is calculated using the near-infrared band and red band in the acquired high-spatial-resolution remote sensing data image, and the NDWI index is calculated using the near-infrared band and green band.

[0053] Furthermore, data augmentation in S3 includes: translation, rotation, mirroring, scaling, color space switching and adding interference to generate new samples through data augmentation technology;

[0054] Hybrid sampling improves the imbalanced distribution of sample sets from both global and local perspectives. It also combines remote sensing images with other different spectral indices, and adds other multi-source data that is beneficial for extracting minority classes such as water bodies and roads. This can help distinguish minority classes from other land feature types in complex areas.

[0055] Hybrid sampling combines random undersampling and random oversampling to balance the distribution of training data by enhancing minority classes such as permeable surfaces, and attempts to reduce the classifier's bias towards majority classes such as grassland and bare land. Ultimately, a sufficiently high-quality training sample set is obtained, which helps to effectively use samples in the training phase, so that the trained deep learning model can also achieve better classification performance.

[0056] Furthermore, in S4, based on the ResNet50 residual network and the VGG-16 convolutional neural network, combined with the Transformer module for extracting global information and the encoding-decoding structure, the multi-scale features of the full convolutional network and contextual information are effectively combined to enhance the feature extraction of ground objects in remote sensing images and construct a feature-fused deep convolutional neural network semantic segmentation model.

[0057] Reference Figure 2 As shown in Figure 1, the feature fusion deep convolutional neural network semantic segmentation model includes: encoding module, decoding module, and Softmax layer;

[0058] The network model consists of two parallel networks, and through the feature fusion module, the entire network can learn branch fusion features. This parallel structure simultaneously processes RGB image data and impervious surface-specific spectral index data (NDVI data and NDWI data). Through the network structure, it can extract impervious surface categories and other ground object categories with regional dense semantics. It can not only identify different ground object targets, but also restore clearer ground object boundaries, significantly improving the recognition accuracy of impervious surface categories, forming a complete end-to-end high-resolution remote sensing image classification model.

[0059] Further, refer to Figure 3As shown, the encoding module adopts a dual-channel structure. The first channel uses the ResNet50 residual network as the skeleton network, combined with the void convolution to extract features and obtain RGB image features. The ResNet50 residual network consists of a convolution layer and four blocks. Each block has several bottleneck units. Inside the bottleneck unit, there is a shortcut connection between the input and output. ResNet solves the gradient disappearance problem by connecting the bypass information and using the bottleneck block, and obtains higher accuracy and a smaller model under deep networks. The standard ResNet50 is a 32-fold downsampling structure. The present invention changes the convolution step size of the first bottleneck block 3*3 in block3 to 1. At the same time, in order to maintain the receptive field of the remaining convolution kernels in block3, the standard convolution is replaced by a void convolution with a void rate of 2 to obtain the original The image is downsampled 16 times. To better capture global information, the last feature map of the module uses global average pooling plus 1*1 convolution to change the number of channels. This method can provide richer global information than maximum pooling. The second channel is a branch network that inputs NDVI data and NDWI data. The five convolutional layers of the VGG-16 convolutional neural network are used as the backbone. After four times of 2-fold sampling, a 16-fold downsampled feature output is finally generated to obtain the spectral index feature. The stacking and gluing fusion method of multiple input vectors on the specified axis is used to explicitly establish the correlation between the RGB image features and the spectral index features NDVI and NDWI multi-feature maps. This method not only enhances the model's ability to recognize impervious surface features, but also avoids the introduction of redundant features and noisy images.

[0060] The decoding module uses a multi-step decoder. In the decoding stage, the input of each layer includes the output of the previous deconvolution layer and the convolution output of the corresponding encoding stage, gradually restoring the feature map to the original resolution. The global-local Transformer block is introduced. The Transformer block consists of an efficient global-local attention mechanism, a multi-layer perceptron, two batch normalization operations, and two sum operations.

[0061] The global-local attention mechanism combines the global attention branch and the convolutional local branch to capture global and local context information. In the global branch, a window-based multi-head self-attention and cross-window context interaction module are introduced to capture the global context with low complexity. In the local branch, a convolutional layer is applied to extract the local context.

[0062] The calculation formula of multi-head self-attention is:

[0063] MultiHead(Q,K,V)=Concat(head1,...,head h )W O

[0064]

[0065] Among them, Q represents the query vector (Query), K represents the key vector (Key), and V represents the value vector (Value); head i (i=1, 2, ..., h, where h is the number of heads) represents the attention result calculated by the i-th “head”; W O Represents a learnable weight matrix that linearly transforms the concatenated results of multiple "heads" and maps them to the appropriate output space dimension; represents the weight matrix corresponding to the query vector for the i-th “head”, represents the weight matrix corresponding to the key vector of the i-th "head", represents the weight matrix corresponding to the value vector of the i-th "head", represents the linear transformation matrix from the model hidden dimension to the key vector dimension, represents the linear transformation matrix from the model hidden dimension to the value vector dimension, Represents the linear transformation matrix from the dimension after multi-head attention splicing to the hidden dimension of the model. The attention function calculated by each head is usually the scaled dot product attention. The matrix Q, K, V can be defined as follows: the i-th row is the vector q i 、k i and v i Matrix, linear transformation of vector:

[0066]

[0067] in, represents the dot product of each query vector in Q and each key vector in K; d k represents the dimension of the key vector K, which is used to scale the attention score; Represents the value vector (Value) matrix, which is obtained by linear transformation of the input sequence

[0068] The weighted sum operation (WS) can selectively weight the two features to learn more effective fusion features based on their contribution to segmentation accuracy. The batch normalization layer of the Transformer block makes the features extracted by the network more stable. Suppose the input of a batch is x = x 1，…，m , where m is the batch size and the algorithm training parameters are γ and β,

[0069] Calculate the average value of the batch data as:

[0070]

[0071] The variance is:

[0072]

[0073] The normalization method is expressed as:

[0074]

[0075] Where ε is a small positive number (usually 10 -8 The purpose is to prevent the variance A division by zero error occurs when the number is very small;

[0076] The output of the algorithm is:

[0077]

[0078] Among them, γ is used to scale the normalized data, and β is used to translate the normalized data. By adjusting γ and β, the model can learn the most appropriate data distribution; BN γ,β represents a batch normalization operation with learnable parameters γ and β, which are used to adjust the data distribution and optimize model training.

[0079] Finally, classification is performed through the Softmax layer, and the final feature map is converted into a category probability distribution, so that the network can output the probability that each pixel belongs to each category, providing accurate classification results for the extraction of impervious surfaces and surrounding land features.

[0080] Furthermore, the specific content of S5 is: using the training set data, iteratively training the constructed feature fusion deep convolutional neural network semantic segmentation model, updating the full convolutional network parameters in the feature fusion deep convolutional neural network semantic segmentation model, and completing the model training;

[0081] Furthermore, in S7, the shadow area segmentation is first obtained through multi-resolution segmentation to identify the object, and the selection of scale parameters, determination of thresholds, and rule-based hierarchical knowledge strategies are formulated;

[0082] Due to the limitations of optical remote sensing sensors, multi-source heterogeneous data such as DSM and POI are used as supplementary data sources for decision-level fusion. For example, impervious surfaces in large geographic spaces have low proportions and high clustering characteristics. Through a graphics-based target domain reduction method, thresholds for multiple features in multi-source heterogeneous data are established based on a knowledge base. As shown in Table 1, the prior knowledge of the knowledge base is constructed from candidate samples provided by the impervious surface extraction results of the fully convolutional network. Vegetation (including grass and trees), bare soil, water bodies, and impervious surfaces in shadow areas are reclassified, while assisting in distinguishing impervious surfaces under tree canopy cover. Finally, the impervious surface extraction results of non-shadow areas and shadow areas are integrated to obtain the final urban impervious surface distribution.

[0083] Table 1. Knowledge base of impervious surface identification model

[0084]

[0085]

[0086] Each embodiment in this specification is described in a progressive manner. The same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system or system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment. The system embodiment described above is only exemplary, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment. A person of ordinary skill in the art can understand and implement it without making any creative efforts.

[0087] 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 method for extracting urban impervious surfaces from high-resolution remote sensing images, characterized in that: include: S1. Obtain high spatial resolution remote sensing data, high precision DSM data and open source POI geospatial data of the area to be analyzed; S2. Create a sample dataset based on the characteristics of urban impervious surfaces; S3. Use data augmentation and mixed sampling techniques to improve the distribution quality of unbalanced sample data in the sample dataset, obtain a high-quality sample dataset, and divide the high-quality sample dataset into a training set and a test set; S4. Construct a deep convolutional neural network semantic segmentation model with feature fusion; In S4, based on the ResNet50 residual network and the VGG-16 convolutional neural network, a feature-fused deep convolutional neural network semantic segmentation model is constructed. The feature-fused deep convolutional neural network semantic segmentation model includes: an encoding module, a decoding module, and a Softmax layer; The encoding module adopts a dual-channel structure. The first channel uses the ResNet50 residual network as the backbone network, combined with void convolution to extract features and obtain RGB image features. The second channel is a branch network that inputs NDVI and NDWI data. The five convolutional layers of the VGG-16 convolutional neural network are used as the backbone. After four times of 2x sampling, the final 16x downsampled feature output is generated to obtain spectral index features. The stacking and gluing fusion method of multiple input vectors on the specified axis is used to explicitly establish the correlation between the RGB image features and the spectral index features NDVI and NDWI multi-feature maps. The decoding module uses a multi-step decoder. In the decoding stage, the input of each layer includes the output of the previous deconvolution layer and the convolution output of the corresponding encoding stage, gradually restoring the feature map to the original resolution. The global-local Transformer block is introduced. The Transformer block consists of an efficient global-local attention mechanism, a multi-layer perceptron, two batch normalization operations, and two sum operations. S5. Inputting the training set into the feature-fused deep convolutional neural network semantic segmentation model for model training to obtain a trained feature-fused deep convolutional neural network semantic segmentation model; S6. Input the test set into the trained feature-fused deep convolutional neural network semantic segmentation model to perform object classification and generate the urban object classification results with regional dense semantics; S7. Use a multi-scale segmentation and knowledge hierarchical model to extract impervious surfaces in shadow areas, and integrate the impervious surface extraction results of non-shadow areas and shadow areas to obtain the final urban impervious surface distribution.

2. The method for extracting urban impervious surfaces from high-resolution remote sensing images according to claim 1, characterized in that: The high spatial resolution remote sensing data of the area to be analyzed in S1 include: high spatial resolution optical satellite Gaofen-2 remote sensing data of the area to be analyzed, high-precision DSM data generated by the stereo image pairs of the Ziyuan-3 satellite in the area to be analyzed, and open source POI geospatial data of the area to be analyzed crawled based on open interfaces.

3. The method for extracting urban impervious surfaces from high-resolution remote sensing images according to claim 1, characterized in that: The sample data set in S2 includes: remote sensing data, spectral index data and annotation data; Each sample data is in the form of: image-annotation-spectral index data; The preparation of sample datasets includes: data preprocessing, sample annotation and spectral index extraction; Sample labeling: By directly labeling the original pixels with categories and vectorizing them, urban features are classified into categories including bare land, grass, water bodies, trees, roads, buildings, squares, and shadows. Roads, buildings, and squares are all impervious surface extraction results in non-shadow areas. Spectral index extraction The spectral indexes of impervious surfaces include: NDWI index and NDVI index; The NDVI index is calculated using the near-infrared band and red band in the acquired high-spatial-resolution remote sensing data image, and the NDWI index is calculated using the near-infrared band and green band.

4. The method for extracting urban impervious surfaces from high-resolution remote sensing images according to claim 1, characterized in that: Data enhancement in S3 includes: translation, rotation, mirroring, scaling, color space switching, and adding interference; Hybrid sampling: Combining random undersampling and random oversampling, it enhances the distribution of balanced data for the minority class, reduces the classifier's bias towards the majority class, and obtains a high-quality sample data set.

5. The method for extracting urban impervious surfaces from high-resolution remote sensing images according to claim 1, characterized in that: The specific content of S5 is: using the training set data, iteratively training the constructed feature-fused deep convolutional neural network semantic segmentation model, updating the full convolutional network parameters in the feature-fused deep convolutional neural network semantic segmentation model, and completing model training.

6. The method for extracting urban impervious surfaces from high-resolution remote sensing images according to claim 1, characterized in that: In S7, shadow-based segmentation is obtained through multi-scale segmentation to identify objects; The vegetation, bare soil, water bodies and impervious surfaces in the shadow area are reclassified to assist in distinguishing the impervious surfaces under tree canopy cover. The impervious surface extraction results of the non-shadow area and the shadow area are integrated to obtain the final urban impervious surface distribution.

Images