Surface water body intelligent identification sample library construction method based on remote sensing image

Abstract

The invention provides a surface water body intelligent identification sample library construction method based on a remote sensing image. The method comprises the following steps: acquiring land utilization data and a satellite remote sensing image; extracting surface water body polygons and corresponding water body center points from the land utilization data, wherein each water body center point represents one water body; drawing quadrat areas with different sizes according to the distribution of the central points of the water body; selecting a water body in the quadrat area as a sample; generating a picture of each sample by using the satellite remote sensing image; performing sample classification according to the remote sensing image classification features and the polygon shape classification features; and establishing an information table of all samples. According to the surface water body intelligent identification sample library construction method based on the remote sensing image, intelligent identification of the surface water body is achieved on the basis of public global highest-resolution land utilization data and online high-resolution remote sensing data in combination with surface water body distribution characteristics.

Description

Technical Field

[0001] The present invention relates to the technical field of remote sensing target recognition, and in particular to a method for constructing a surface water body intelligent recognition sample library based on remote sensing images. Background Art

[0002] In recent years, with the advancement of Earth observation technology, remote sensing image data has grown exponentially, placing higher demands on fast and accurate interpretation methods and techniques. The contradiction between the massive accumulation of raw image data and the insufficient extraction of usable information has become increasingly prominent. A massive and diverse remote sensing image sample library is the foundation for achieving high-precision intelligent interpretation of large-scale, massive remote sensing imagery. Currently, remote sensing interpretation sample data is constructed for different interpretation tasks, primarily including scene classification samples, ground object detection samples, ground feature classification samples, and change detection samples. In recent years, the application of deep learning technology to tasks such as scene understanding, ground object detection, and land cover classification has driven rapid development in the acquisition, annotation, and application of remote sensing classification sample data. By training deep learning networks with large amounts of sample data, the efficiency of remote sensing image feature extraction has been significantly improved. However, overall, the practical application and commercialization of intelligent remote sensing interpretation systems have not yet reached the level of common image interpretation methods such as facial and fingerprint recognition.

[0003] Surface water bodies, as a typical land feature, are influenced by factors such as scale, topography, rainfall, and economic development level. This results in heterogeneity in remote sensing imagery characteristics for similar water bodies across different regions. This leads to high annotation costs, inconsistent classification systems, and a small number of existing samples, making it difficult to accurately identify and classify massive amounts of water bodies in large-scale imagery.

[0004] Patent application number CN 119723332 A discloses a method, device, system, and storage medium for extracting surface water from remote sensing images. The method comprises the following steps: Step S1: Acquire a remote sensing surface water dataset; Step S2: Construct a remote sensing surface water extraction network (RSWE-Net) based on the remote sensing surface water dataset; Step S3: Partition the remote sensing surface water dataset to obtain a training set and a test set; Step S4: Train the remote sensing surface water extraction network (RSWE-Net) based on the training set; and Step S5: Input the test set into the trained RSWE-Net to extract surface water from the remote sensing image. However, this method only extracts water from the remote sensing image and cannot classify the surface water.

[0005] Patent application number CN 118736438 A discloses a method for extracting surface water bodies based on satellite hyperspectral remote sensing data. The method includes the following main steps: Step 1: Preprocessing multiple acquired satellite hyperspectral remote sensing data; Step 2: Selecting characteristic pixels of different ground objects in the image and constructing spectral characteristic curves of the ground objects; Step 3: Analyzing the spectral characteristic curves of different ground objects, constructing a new water extraction model, and processing the image using the new model; Step 4: Constructing an algorithm to separate water bodies from other ground objects in the processed image. The disadvantage of this method is that it can extract water bodies from hyperspectral remote sensing data and distinguish them from other ground object types, but it cannot determine the specific type of water body. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention proposes a method for constructing a sample library for intelligent surface water body identification based on remote sensing images. Based on the publicly available global highest-resolution land use data and online high-resolution remote sensing data, combined with the distribution characteristics of surface water bodies, the method realizes intelligent identification of surface water bodies.

[0007] The purpose of the present invention is to provide a method for constructing a sample library for intelligent surface water body identification based on remote sensing images, which includes obtaining land use data and satellite remote sensing images, and further includes the following steps: Step 1: Extracting surface water polygons and corresponding water body center points from the land use data, where each water body center point represents a water body; Step 2: drawing sample areas of different sizes according to the distribution of the center points of the water body; Step 3: Select the water body within the sample area as the sample; Step 4: Generate a picture of each sample using the satellite remote sensing image; Step 5: Classify samples based on remote sensing image classification features and polygon shape classification features; Step 6: Create an information table for all samples.

[0008] Preferably, step 1 includes extracting a raster with water body attributes from 10m resolution land use raster data, converting the obtained water body raster into a vector polygon using ArcGIS software, and saving it as a polygon file in shp format; using the FeatureToPoint tool to extract the coordinates of the center point of each polygon, and saving the point file in shp format to represent the geographical location of the corresponding water body polygon.

[0009] In any of the above schemes, preferably, step 2 includes setting the sample center points at intervals of 5° longitude × 5° latitude, and searching for the center points of water bodies around each sample center point from near to far, and taking the longitude and latitude distance when the number of water bodies reaches 100 as the sample area radius. If the sample area radius is 5 (in degrees), and the number of water bodies is less than 100, 5 is used as the sample area radius. The formula is:

[0010]

[0011] in, R i For the sample area i The radius, n is the number of water bodies within the quadrat area when the radius is 5, l 100 For the sample area i The distance from the center of the sample plot to the water body point farthest from the center of the sample plot among the 100 water bodies closest to the center of the sample plot.

[0012] In any of the above schemes, it is preferred that the distance from the water body to the center point of the sample plot is calculated as follows:

[0013]

[0014] in, l i,j For water bodies j To the sample area i The distance from the center point, x i and y i are the latitude and longitude coordinates of the center point of the sample plot, x j and y j are the latitude and longitude coordinates of the center point of the water body respectively.

[0015] In any of the above solutions, preferably, step 2 further includes drawing a buffer zone of each sample area with the center point of each sample area as the center and the radius of the sample area as the distance to obtain the circular sample area of ​​all the sample areas.

[0016] In any of the above schemes, preferably, step 3 includes using the circular sample area and water body center point layer to perform the Identity tool in ArcGIS software, extracting the sample number into the water body center point layer, and using the join and Calculate Field tools to associate the sample number with the water body polygon layer. The water body polygon that obtains the sample number is the selected water body sample.

[0017] In any of the above solutions, preferably, step 4 includes the following sub-steps: Step 41: Load the sample point layer into ArcGIS software, load ESRI's publicly available online high-definition imagery World Imagery as the background, and set the water sample polygon to be hollow, displaying only the boundary. Step 42: Write a batch processing program and use ArcGIS software to generate a png format image for each water sample.

[0018] In any of the above solutions, preferably, the generating method includes the following sub-steps: Step 421: Obtain each water body polygon object; Step 422: Obtain the outer bounding box of the water body polygon; Step 423: Enlarge the outer frame of the water body polygon; Step 424: assigning the coordinates of the enlarged water body polygon outer frame to the map; Step 425: Set the image export path; Step 426: Execute the image export command.

[0019] In any of the above solutions, preferably, the types of sample classification include: reservoirs, ponds, rivers, lakes, artificial ponds, natural ponds, ditches and temporary water bodies.

[0020] In any of the above schemes, the classification characteristics of remote sensing images of various samples are preferably 1) Reservoir: There are obvious water-blocking facilities on one side of the water body and obvious features of blocking the river; 2) Pond dam: It has obvious features of blocking the river but the dam body is not obvious and is generally small in area; 3) River: A section of a river that is clearly visible on the remote sensing image; 4) Lakes: There are no artificial facilities around the sample, and the shoreline is naturally formed; 5) Artificial ponds: The sample week is an artificial water retaining facility; 6) Natural pond: an independent water body surrounded by artificial structures and with an irregular sample perimeter; 7) Ditches: Artificial ditches can be seen on both sides of the water body. 8) Temporary water bodies: river beaches and low-lying areas except for stagnant water.

[0021] In any of the above solutions, it is preferred that the polygonal shape classification features of each type of sample are 1) Reservoir: The sample shape is generally an asymmetric polygon; 2) Pond dam: similar in shape to a reservoir, but with a small area; 3) River: The sample shape is mainly slender; 4) Lakes: mainly circular or oval, with smooth boundaries, located at the lowest point of the terrain; 5) Artificial ponds: square, rectangular, circular or oval, with smooth edges; 6) Natural ponds: rough boundaries and irregular shapes; 7) Ditch: The pattern is long and straight, with uniform width; 8) Temporary water bodies: irregular in shape.

[0022] In any of the above solutions, preferably, step 6 includes standardizing the sample results to form a water body classification remote sensing sample library.

[0023] In any of the above solutions, preferably, step 6 includes the following sub-steps: Step 61: Based on the classification results, a sample information table is created, including the sample number, sample type, center point longitude, center point latitude, and water body area; Step 62: Store the samples in folders according to their types and number them in sequence. Reservoirs, dams, rivers, lakes, artificial ponds, natural ponds, ditches, and temporary water bodies are numbered a, b, c, d, e, f, g, and h respectively, and then numbered in sequence according to 6-digit numbers.

[0024] The present invention proposes a method for constructing a sample library for intelligent surface water identification based on remote sensing images. Based on global public high-resolution land use data and online high-resolution remote sensing data, combined with the distribution characteristics of surface water bodies, a sample library for intelligent surface water identification is constructed, which can provide samples for training intelligent models for refined surface water classification. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 The flowchart is a preferred embodiment of the method for constructing a surface water body intelligent identification sample library based on remote sensing images according to the present invention.

[0026] Figure 2 This is a schematic diagram of an embodiment of a sample point image of a method for constructing a sample library for intelligent surface water body identification based on remote sensing images according to the present invention.

[0027] Figure 3 A schematic diagram of a reservoir according to a preferred embodiment of the method for constructing a sample library for intelligent surface water body identification based on remote sensing images of the present invention.

[0028] Figure 4 A schematic diagram of a pond or dam according to a preferred embodiment of the method for constructing a sample library for intelligent surface water body identification based on remote sensing images according to the present invention.

[0029] Figure 5 A schematic diagram of a river according to a preferred embodiment of the method for constructing a sample library for intelligent identification of surface water bodies based on remote sensing images of the present invention.

[0030] Figure 6 A schematic diagram of a lake according to a preferred embodiment of the method for constructing a sample library for intelligent identification of surface water bodies based on remote sensing images of the present invention.

[0031] Figure 7 Schematic diagram of an artificial pond according to a preferred embodiment of the method for constructing a sample library for intelligent identification of surface water bodies based on remote sensing images of the present invention.

[0032] Figure 8 A schematic diagram of a natural pond according to a preferred embodiment of the method for constructing a sample library for intelligent identification of surface water bodies based on remote sensing images of the present invention.

[0033] Figure 9 A schematic diagram of a ditch according to a preferred embodiment of the method for constructing a sample library for intelligent identification of surface water bodies based on remote sensing images of the present invention.

[0034] Figure 10 This is a temporary water body schematic diagram according to a preferred embodiment of the method for constructing a surface water body intelligent identification sample library based on remote sensing images of the present invention. DETAILED DESCRIPTION

[0035] The present invention will be further described below with reference to the accompanying drawings and specific embodiments.

[0036] Example 1 like Figure 1 As shown, a method for constructing a sample library for intelligent surface water body identification based on remote sensing images is to execute step 1000 to obtain land use data and satellite remote sensing images.

[0037] Execute step 1100 to extract surface water body polygons and corresponding water body center points from the land use data, where each water body center point represents a water body. Extract rasters with water body attributes from the 10m resolution land use raster data, convert the obtained water body rasters into vector polygons using ArcGIS software, and save them as polygon files in shp format. Use the FeatureToPoint tool to extract the coordinates of each polygon center point, and save them as a point file in shp format to represent the geographic location of the corresponding water body polygon.

[0038] Execute step 1200 to draw sample areas of different sizes based on the distribution of the water body center points. Set the sample center points at intervals of 5° longitude × 5° latitude, and search for water body center points around each sample center point from near to far. The longitude and latitude distance when the number of water bodies reaches 100 is used as the sample area radius. If the sample area radius is 5 (in degrees) and the number of water bodies is less than 100, 5 is used as the sample area radius. The formula is:

[0039]

[0040] in, R i For the sample area i The radius, n is the number of water bodies within the quadrat area when the radius is 5, l 100 For the sample area i The distance from the center of the sample plot to the water body point farthest from the center of the sample plot among the 100 water bodies closest to the center of the sample plot.

[0041] The calculation formula for the distance from the water body to the center point of the sample plot is:

[0042]

[0043] in, l i,j For water bodies j To the sample area i The distance from the center point, x i and y i are the latitude and longitude coordinates of the center point of the sample plot, x j and y j are the latitude and longitude coordinates of the center point of the water body respectively.

[0044] The buffer zone of each sample area is drawn with the center point of each sample area as the center and the radius of the sample area as the distance to obtain the circular sample area of ​​all sample areas.

[0045] Execute step 1300, select the water body in the sample area as the sample, use the circular sample area and water body center point layer to perform the Identity tool in ArcGIS software, extract the sample number to the water body center point layer, use the join and Calculate Field tools to associate the sample number with the water body polygon layer, and the water body polygon with the sample number is the selected water body sample.

[0046] Executing step 1400 to generate a picture of each sample using the satellite remote sensing image includes the following sub-steps: Execute step 1410 to load the sample point layer into ArcGIS software, load ESRI's publicly available online high-definition imagery World Imagery as a background, and set the water body sample polygon to be hollow, displaying only the boundary. Execute step 1420 to write a batch processing program and use ArcGIS software to generate a PNG format image for each water body sample.

[0047] The generation method includes the following sub-steps: Execute step 1421 to obtain each water body polygon object; Execute step 1422 to obtain the polygonal outer bounding box of the water body; Execute step 1423 to enlarge the outer bounding box of the water body polygon; Execute step 1424 to assign the coordinates of the enlarged water body polygon outer frame to the map; Execute step 1425 to set the image export path; Execute step 1426 to execute the image export command.

[0048] Execute step 1500 to classify samples according to remote sensing image classification features and polygon shape classification features. The sample classification types include: reservoirs, ponds, rivers, lakes, artificial ponds, natural ponds, ditches and temporary water bodies.

[0049] The classification features of remote sensing images of various samples are 1) Reservoir: There are obvious water-blocking facilities on one side of the water body and obvious features of blocking the river; 2) Pond dam: It has obvious features of blocking the river but the dam body is not obvious and is generally small in area; 3) River: A section of a river that is clearly visible on the remote sensing image; 4) Lakes: There are no artificial facilities around the sample, and the shoreline is naturally formed; 5) Artificial ponds: The sample week is an artificial water retaining facility; 6) Natural pond: an independent water body surrounded by artificial structures and with an irregular sample perimeter; 7) Ditches: Artificial ditches can be seen on both sides of the water body. 8) Temporary water bodies: river beaches and low-lying areas except for stagnant water.

[0050] The polygonal shape classification features of various samples are 1) Reservoir: The sample shape is generally an asymmetric polygon; 2) Pond dam: similar in shape to a reservoir, but with a small area; 3) River: The sample shape is mainly slender; 4) Lakes: mainly circular or oval, with smooth boundaries, located at the lowest point of the terrain; 5) Artificial ponds: square, rectangular, circular or oval, with smooth edges; 6) Natural ponds: rough boundaries and irregular shapes; 7) Ditch: The pattern is long and straight, with uniform width; 8) Temporary water bodies: irregular in shape.

[0051] Execute step 1600 to create an information table of all samples, including the following sub-steps: Execute step 1610 to create a sample information table based on the classification results, including the sample number, sample type, center point longitude, center point latitude, and water area; Execute step 1620 to store the samples in folders according to type and number them in sequence. Reservoirs, dams, rivers, lakes, artificial ponds, natural ponds, ditches, and temporary water bodies are numbered a, b, c, d, e, f, g, and h respectively, and then numbered in sequence according to 6-digit numbers.

[0052] Example 2 This paper proposes a method to construct a sample library based on high-resolution land use data and remote sensing image data. The process is as follows: The first step is to obtain surface water polygons and their corresponding center points, with each center point representing a water body. Specifically, extract water body rasters from the 10m resolution land use raster data. Use ArcGIS to convert the resulting water body rasters into vector polygons and save them as polygon files in .shp format. Use the FeatureToPoint tool to extract the coordinates of each polygon center point and save them as point files in .shp format, which are used to represent the geographic location of the corresponding water body polygon.

[0053] In the second step, sample plots of different sizes are drawn globally based on the distribution of water body center points. Taking into account the differences in topography, rainfall, water resource utilization methods, etc. in different regions of the world, the characteristics of similar water bodies in images are inconsistent. Therefore, sample plots of different scales are used in different regions based on the sparse distribution of samples. The specific approach is: Set the sample center points at intervals of 5° (longitude) × 5° (latitude), and search for the water body center points around each sample center point from near to far, and use the longitude and latitude distance when the number of water bodies reaches 100 as the sample area radius. If the sample area radius is 5 (in degrees), and the number of water bodies is less than 100, 5 is used as the sample area radius. The formula is as follows:

[0054]

[0055] Where, R i Indicates the sample area i The radius, n Indicates the number of water bodies within the quadrat area when the radius is 5, l 100 Indicates the area away from the sample plot i The distance from the center of the sample plot to the water body point farthest from the center of the sample plot among the 100 water bodies closest to the center of the sample plot.

[0056] The distance from the water body to the center point of the sample plot is calculated as follows:

[0057]

[0058] Where, l i,j Indicates water body j To the sample area i The distance from the center point, x i 、 y i Represent the latitude and longitude coordinates of the center point of the sample, x j 、 y j They represent the latitude and longitude coordinates of the center point of the water body respectively.

[0059] The buffer zone of each quadrat was drawn with the center point of each quadrat as the center and the radius of the quadrat as the distance to obtain the circular area of ​​all quadrat.

[0060] Step 3: Determine the sample points. Use the circular sample area drawn in the previous step and the water body center point layer obtained in the first step to perform the Identity tool in ArcGIS software. Extract the sample number to the water body center point layer. Then use the Join and Calculate Field tools to associate the sample number with the water body polygon layer. The water body polygon with the sample number is the selected water body sample.

[0061] Step 4: Extract the remote sensing image of each sample. The specific steps are: load the sample point layer into ArcGIS software, load ESRI's publicly available online high-definition image World Imagery as the background, set the water sample polygon to be hollow, and only display the boundary. Write a batch program and use ArcGIS software to generate a PNG format image for each water sample. The generation method is: first obtain the outer rectangular frame of the sample polygon and enlarge the rectangular frame by 1.5 times. This ensures that the sample polygon and surrounding images can be clearly displayed in the image, which facilitates the next classification and labeling step.

[0062] The core code for image export is as follows: Get each water body polygon object: Set pF = pFClass.GetFeature(i); Get the outer bounding box of the water body polygon: Set pEnvelope = pF.Shape.Envelope; Enlarge the outer frame of the water polygon: pEnvelope.Expand 1.5, 1.5, True; Assign the coordinates of the enlarged water polygon outer frame to the map: pPixelBoundsEnv.PutCoordsexportRECT.Left, exportRECT.Top, exportRECT.Right, exportRECT.bottom; pExport.PixelBounds = pPixelBoundsEnv; Set the image export path: pExport.ExportFileName = "D:\pic1\" + picName + ".png"; Execute the image export command: pActiveView.Output hDC, 100, exportRECT, Nothing,Nothing.

[0063] Step 5: Classify samples. According to the classification of water bodies by peers, they are generally divided into rivers, lakes, reservoirs, ponds, ditches, glaciers, etc. However, based on the characteristics of remote sensing images, it is difficult to clearly distinguish them. For example, my country defines a reservoir as "a water surface enclosed by the shoreline of a reservoir with a total designed storage capacity of ≥100,000 cubic meters formed by artificial interception." However, the storage capacity cannot be distinguished in remote sensing images. Therefore, this application combines the remote sensing image characteristics of water bodies and the polygonal characteristics of water bodies to reclassify water bodies. The samples are divided into 8 categories: reservoirs, ponds, rivers, lakes, artificial ponds, natural ponds, ditches, and temporary water bodies, and the image classification characteristics and shape characteristics of each type of sample are redefined. Table 1 shows the definition of each type of sample and the characteristics of the image sample. During the classification process, a small number of unclear and poor quality samples obscured by clouds and fog are eliminated.

[0064] Table 1 Sample definition and classification characteristics

[0065]

[0066] Step 6: Standardize the sample results to create a water body classification remote sensing sample library. Based on the classification results, create a sample information table, including sample number, sample type, center point longitude, center point latitude, and water body area. Samples are stored in folders according to type and numbered sequentially. Reservoirs, dams, rivers, lakes, artificial ponds, natural ponds, ditches, and temporary water bodies are numbered a, b, c, d, e, f, g, and h, respectively. Then, they are numbered sequentially using six-digit numbers. For example, the first reservoir sample is numbered a000001.

[0067] Example 3 (1) Extract the center points of water bodies from the global 2023 10-meter resolution land use data.

[0068] (2) Based on the distribution of water body center points, draw sample area ranges of different radii.

[0069] (3) Select the water bodies within each sample area as sampling points.

[0070] (4) If Figure 2 As shown, load the sample point layer into ArcGIS, use ESRI's publicly available online high-definition imagery, World Imagery, as the background, and set the water sample polygons to be hollow, displaying only the boundaries. Write a batch processing program to generate a PNG image for each water sample using ArcGIS.

[0071] (5) Examples of pictures of different types of samples obtained by classification, such as Figure 3 The picture example shown is a reservoir, e.g. Figure 4 The picture shown is an example of a pond dam, e.g. Figure 5 The picture example shown is a river, e.g. Figure 6 The picture example shown is a lake, e.g. Figure 7 The picture shown is an example of an artificial pond, e.g. Figure 8 The picture examples shown are natural ponds, e.g. Figure 9 The picture example shown is a ditch, e.g. Figure 10 The picture examples shown are temporary bodies of water.

[0072] In order to better understand the present invention, the above is described in detail in conjunction with the specific embodiments of the present invention, but it is not intended to limit the present invention. Any simple modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention. Each embodiment in this specification focuses on the differences from other embodiments, and the same or similar parts between the various embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

Claims

1. A method for constructing a surface water body intelligent identification sample library based on remote sensing images, comprising obtaining land use data and satellite remote sensing images, characterized in that: The following steps are also included: Step 1: Extracting surface water polygons and corresponding water body center points from the land use data, where each water body center point represents a water body; Step 2: Draw sample areas of different sizes according to the distribution of the water body center points, including setting the sample center points at intervals of 5° longitude × 5° latitude, and searching for the water body center points around each sample center point from near to far, and use the longitude and latitude distance when the number of water bodies reaches 100 as the sample area radius. If the sample area radius is 5 (in degrees) and the number of water bodies is less than 100, then 5 is used as the sample area radius. The formula is ， in, R i For the sample area i The radius, n is the number of water bodies within the quadrat area when the radius is 5, l 100 For the sample area i The distance from the center of the sample plot to the water body point farthest from the center of the sample plot among the 100 water bodies closest to the center of the sample plot; The calculation formula for the distance from the water body to the center point of the sample plot is: ， in, l i,j For water bodies j To the sample area i The distance from the center point, x i and y i are the latitude and longitude coordinates of the center point of the sample plot, x j and y j are the latitude and longitude coordinates of the center point of the water body respectively; Step 3: Select the water body within the sample area as the sample; Step 4: Generate a picture of each sample using the satellite remote sensing image; Step 5: Classify samples based on remote sensing image classification features and polygon shape classification features; Step 6: Create an information table for all samples.

2. The method for constructing a sample library for intelligent surface water body identification based on remote sensing images according to claim 1, characterized in that: The step 1 includes extracting a grid with water attributes from 10m resolution land use grid data, converting the obtained water grid into a vector polygon using ArcGIS software, and saving it as a polygon file in shp format; using the FeatureToPoint tool to extract the coordinates of the center point of each polygon, and saving it as a point file in shp format to represent the geographical location of the corresponding water polygon.

3. The method for constructing a surface water body intelligent identification sample library based on remote sensing images according to claim 2, characterized in that: The step 2 further includes drawing a buffer zone of each sample area with the center point of each sample area as the center and the radius of the sample area as the distance to obtain the circular sample area of ​​all the sample areas.

4. The method for constructing a surface water body intelligent identification sample library based on remote sensing images according to claim 3, characterized in that: Step 3 includes using the circular sample area and water body center point layer to perform the Identity tool in ArcGIS software, extracting the sample number into the water body center point layer, and using the join and Calculate Field tools to associate the sample number with the water body polygon layer. The water body polygon that obtains the sample number is the selected water body sample.

5. The method for constructing a sample library for intelligent surface water identification based on remote sensing images according to claim 4, characterized in that: The step 4 includes the following sub-steps: Step 41: Load the sample point layer into ArcGIS software, load ESRI's publicly available online high-definition imagery World Imagery as the background, and set the water sample polygon to be hollow, displaying only the boundary. Step 42: Write a batch processing program and use ArcGIS software to generate a png format image for each water sample.

6. The method for constructing a surface water body intelligent identification sample library based on remote sensing images according to claim 5, characterized in that: The generation method includes the following sub-steps: Step 421: Obtain each water body polygon object; Step 422: Obtain the outer bounding box of the water body polygon; Step 423: Enlarge the outer frame of the water body polygon; Step 424: assigning the coordinates of the enlarged water body polygon outer frame to the map; Step 425: Set the image export path; Step 426: Execute the image export command.

7. The method for constructing a sample library for intelligent surface water identification based on remote sensing images according to claim 6, characterized in that: The types of sample classification include: reservoirs, ponds, rivers, lakes, artificial ponds, natural ponds, ditches and temporary water bodies.

8. The method for constructing a sample library for intelligent surface water identification based on remote sensing images according to claim 7, characterized in that: The step 6 includes standardizing the sample results to form a water body classification remote sensing sample library.

9. The method for constructing a sample library for intelligent surface water identification based on remote sensing images according to claim 8, characterized in that: The step 6 includes the following sub-steps: Step 61: Based on the classification results, a sample information table is created, including the sample number, sample type, center point longitude, center point latitude, and water body area; Step 62: Store the samples in folders according to their types and number them in sequence. Reservoirs, dams, rivers, lakes, artificial ponds, natural ponds, ditches, and temporary water bodies are numbered a, b, c, d, e, f, g, and h respectively, and then numbered in sequence according to 6-digit numbers.

Images