High-resolution Remote Sensing Image Water Surface Ratio Analysis Method, Device, Electronic Equipment and Medium

Abstract

The present invention provides a method, device, electronic device and medium for analyzing the water surface ratio of high-resolution remote sensing images. The method for analyzing the water surface ratio of high-resolution remote sensing images includes: obtaining high-resolution remote sensing images of a target monitoring area, and performing preprocessing on the high-resolution remote sensing images to obtain reflectance data of the high-resolution remote sensing images; extracting the high-resolution remote sensing images through the reflectance data to obtain a rough water body result; extracting the target monitoring area through a data set, and determining image shadows according to the rough water body result and the extraction result; determining a fine water body result according to the rough water body result and the image shadows; and determining the image water surface ratio of the target monitoring area through the fine water body result. By fully exploiting the advantages of the UWI index and the FROM-GLC10 data, the present invention simplifies the process of distinguishing water bodies and shadow noises, ensures the integrity of water body extraction, reduces shadow confusion, greatly reduces phenomena such as missed extraction of water areas and mis-extraction of other ground objects, reduces the manual workload, improves the extraction efficiency, and ensures the accuracy of the water surface ratio result.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular, to a method, device, electronic device and medium for analyzing the water surface ratio of high-resolution remote sensing images. Background Art

[0002] The water surface ratio refers to the ratio of the water area with water function to the total area of the region. It is a control index for urban planning and water system management, and also an intuitive manifestation of the size of the water area. Whether the water surface ratio is reasonable affects the normal functioning of the urban ecological environment function and is related to the livability of the settlement environment. The water types involved in the water surface ratio mainly include natural or artificial land surface fresh water bodies such as rivers, lakes, reservoirs, wetlands, swamps, ponds, and water pits. With the rapid development of remote sensing technology, it has become possible to extract water bodies over a large area based on remote sensing images, providing a new technical means for the rapid calculation of the water surface ratio.

[0003] Currently, the methods for extracting water bodies based on remote sensing images mainly include: threshold method, water body index method, object-oriented method, deep learning model, etc. The threshold method identifies based on the low reflectivity of the water body in a single infrared band. This method is simple and convenient, but it cannot extract small water areas, and the threshold needs to be tried many times to be determined; the water body index method is based on the spectral characteristics of the water body, constructs mathematical formulas such as differences or ratios to highlight the water body information, suppresses other background ground objects, and extracts the water body by simple band operations; the object-oriented method is based on the segmentation idea, divides the image into homogeneous objects of different sizes, and distinguishes the water body by combining information such as spectrum and texture; deep learning is a relatively hot method in recent years. By building different neural network models and training samples, water body extraction is realized, but sample delineation and model construction are often time-consuming and laborious, and there are also uncertain factors in parameter adjustment. In addition, due to the shadows generated by the occlusion of buildings and mountains being close to the spectral information of the water body, when using the above methods to extract the water body, it is easy to be confused with the shadows and generate a large number of error patches. Summary of the Invention

[0004] The main purpose of the embodiments of the present invention is to propose a method, device, electronic device and medium for analyzing the water surface ratio of high-resolution remote sensing images, which simplifies the process, reduces the manual workload, improves the extraction efficiency, and ensures the accuracy of the water surface ratio result.

[0005] One aspect of the present invention provides a method for analyzing the water surface ratio of high-resolution remote sensing images, which is characterized by including:

[0006] In response to an analysis request, obtain a high-resolution remote sensing image of the target monitoring area, and perform preprocessing on the high-resolution remote sensing image to obtain the reflectivity data of the high-resolution remote sensing image, and the preprocessing corrects the high-resolution remote sensing image through preset parameters;

[0007] Extract the high - resolution remote sensing image using the reflectivity data to obtain the first water body distribution result;

[0008] Extract the target monitoring area using the data set to obtain the extraction result based on the data set standard, and determine the image shadow according to the first water body distribution result and the extraction result;

[0009] Determine the second water body distribution result according to the first water body distribution result and the image shadow;

[0010] Determine the image water surface rate of the target monitoring area through the second water body distribution result.

[0011] According to the high - resolution remote sensing image water surface rate analysis method, where performing pre - processing on the high - resolution remote sensing image to obtain the reflectivity data of the high - resolution remote sensing image includes:

[0012] Perform radiometric correction on the high - resolution remote sensing image using the calibration coefficient to generate radiance data;

[0013] Perform atmospheric correction on the radiance data to obtain the reflectivity data.

[0014] According to the high - resolution remote sensing image water surface rate analysis method, where the method further includes:

[0015] Perform orthorectification on the reflectivity data using the RPC parameters of the multispectral image and the panchromatic image and the DEM data;

[0016] Fuse the orthorectified multispectral image and the panchromatic image;

[0017] Mosaic, splice, equalize the color of the remote sensing image, and crop according to the preset partition.

[0018] According to the high - resolution remote sensing image water surface rate analysis method, where extracting the high - resolution remote sensing image using the reflectivity data to obtain the first water body distribution result includes:

[0019] Calculate the UWI urban water body index, and the UWI calculation formula is

[0020]

[0021] where G, R, and NIR are the green band, red band, and near - infrared band of the high - resolution remote sensing image respectively;

[0022] Perform binaryzation on the image of the UWI urban water body index according to the set threshold, take the values exceeding the set threshold as water bodies, and perform the first assignment process on the water body and non - water body areas to obtain the first water body distribution result, and the first assignment process includes assigning values to the water body and non - water body respectively.

[0023] According to the method for analyzing the water surface ratio of high - resolution remote sensing images, extracting the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determining the image shadow according to the first water body distribution result and the extraction result, including:

[0024] Crop the FROM - GLC10 data including the target monitoring area;

[0025] Re - classify the FROM - GLC10 data, erode the re - classification result with a 3×3 convolution kernel, and then resample the re - classification result to obtain a resampled image;

[0026] Intersect the resampled image with the first water body distribution result to generate an initial shadow, erode the initial shadow with a 3×3 convolution kernel, and eliminate small fragmented patches of the initial shadow by setting a threshold for deleting small fragmented patches to obtain the refined image shadow.

[0027] According to the method for analyzing the water surface ratio of high - resolution remote sensing images, determining the image water surface ratio of the target monitoring area through the second water body distribution result, including:

[0028] Erode the obtained first water body distribution result to remove burrs and delete small fragmented patches, then perform vectorization and overlay it with the high - resolution remote sensing image, delete and modify incorrect vectors, and supplement the missed extraction areas to obtain the second water body distribution result, which is used to represent the precise water area range;

[0029] Calculate the precise water area range and the total area of the high - resolution remote sensing image area, and determine the image water surface ratio of the target monitoring area according to the ratio of the precise water area range to the total area of the high - resolution remote sensing image area.

[0030] Another aspect of the embodiments of the present invention provides a device for analyzing the water surface ratio of high - resolution remote sensing images, including:

[0031] A pre - processing module, configured to obtain a high - resolution remote sensing image of a target monitoring area in response to an analysis request, perform pre - processing on the high - resolution remote sensing image to obtain the reflectivity data of the high - resolution remote sensing image, and the pre - processing corrects the high - resolution remote sensing image through preset parameters;

[0032] An extraction module, configured to extract the high - resolution remote sensing image through the reflectivity data to obtain a first water body distribution result;

[0033] An image shadow module, configured to extract the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determine the image shadow according to the first water body distribution result and the extraction result;

[0034] An accurate water area module for determining a second water body distribution result based on the first water body distribution result and the image shadow;

[0035] An image water surface rate module for determining the image water surface rate of the target monitoring area through the second water body distribution result.

[0036] Another aspect of the embodiments of the present invention provides an electronic device, including a processor and a memory;

[0037] The memory is used to store programs;

[0038] The processor executes the program to implement the method described above.

[0039] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method described above.

[0040] The beneficial effects of the present invention are as follows: The high-resolution remote sensing image water surface rate calculation method based on the combination of the UWI index and FROM-GLC10 data fully exploits the advantages of the UWI index and FROM-GLC10 data, simplifies the process of distinguishing water bodies and shadow noises, ensures the integrity of water body extraction while reducing shadow confusion, and significantly reduces phenomena such as missed extraction of water areas and misclassification of other ground objects. It can be applied to the engineering large-scale and rapid statistics of the water surface rate of a certain area.

[0041] The additional aspects and advantages of the present invention will be partially given in the following description, partially become obvious from the following description, or be understood through the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The above and / or additional aspects and advantages of the present invention will become obvious and easy to understand from the description of the embodiments in conjunction with the following drawings, where:

[0043] Figure 1 is a schematic flowchart of the method of the embodiments of the present invention.

[0044] Figure 2 is a detailed flowchart of the high-resolution remote sensing image water surface rate calculation method based on the combination of the UWI index and FROM-GLC10 data in the embodiments of the present invention.

[0045] Figure 3 is a schematic diagram of the rough water body result of the embodiments of the present invention.

[0046] Figure 4 It is a schematic diagram of the image shadow in the embodiment of the present invention.

[0047] Figure 5 It is a schematic diagram of the final water body distribution result in the embodiment of the present invention.

[0048] Figure 6 It is an enlarged view of the final water body distribution result in the embodiment of the present invention.

[0049] Figure 7 It is a diagram of the device for analyzing the water surface rate of the high-resolution remote sensing image in the embodiment of the present invention. Detailed implementation manners

[0050] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions from beginning to end. In the subsequent description, the suffixes such as "module", "component" or "unit" used to represent elements are only for the convenience of description of the present invention, and they have no specific meaning by themselves. Therefore, "module", "component" or "unit" can be used interchangeably. "First", "second", etc. are only used to distinguish technical features and cannot be understood as indicating or implying relative importance or implicitly indicating the quantity of the indicated technical features or implicitly indicating the sequence of the indicated technical features. In the subsequent description of the present invention, the consecutive numbering of the method steps is for the convenience of review and understanding. Combining the overall technical solution of the present invention and the logical relationship between each step, adjusting the implementation order between steps will not affect the technical effect achieved by the technical solution of the present invention. The embodiments described below with reference to the drawings are exemplary and are only used to explain the present invention and cannot be understood as a limitation of the present invention.

[0051] As Figure 1 shown, the embodiment of the present invention provides a process of a method for analyzing the water surface rate of a high-resolution remote sensing image, and this method specifically includes but is not limited to steps S100 - S500.

[0052] Step S100, in response to an analysis request, obtain a high-resolution remote sensing image of the target monitoring area, and perform preprocessing on the high-resolution remote sensing image to obtain the reflectivity data of the high-resolution remote sensing image.

[0053] Step S200, extract the high-resolution remote sensing image through the reflectivity data to obtain a first water body distribution result, where the first water body distribution result is a rough result of the water body.

[0054] Step S300, extract the target monitoring area through the data set to obtain an extraction result based on the data set standard, and determine the image shadow according to the first water body distribution result and the extraction result.

[0055] Step S400, determining a second water body distribution result according to the first water body distribution result and the image shadow.

[0056] Step S500, determining the image water surface rate of the target monitoring area through the second water body distribution result, wherein the second water body distribution result is a detailed water area range of the water body.

[0057] like Figure 2 As shown, the embodiment of the present invention provides a detailed flow chart of a method for calculating water surface rate of high-resolution remote sensing images based on the combination of UWI index and FROM-GLC10 data, which includes the following steps in sequence:

[0058] Step 1: Obtain high-resolution remote sensing images of the monitoring area and pre-process them into reflectivity data;

[0059] Step 2, extracting rough results of water bodies using the reflectivity data;

[0060] Step 3, obtain the FROM-GLC10 data of the monitoring area and combine it with the rough results of the water body to obtain the image shadow;

[0061] Step 4, subtract the image shadow from the rough result of the water body to extract the pure water body;

[0062] Step 5: Calculate the image water surface rate.

[0063] In some embodiments, step 1 specifically includes the following steps:

[0064] Step 1.1, use the calibration coefficient to perform radiation correction on the original high-resolution remote sensing image to generate radiance data;

[0065] Step 1.2, performing atmospheric correction on the radiance data to generate reflectance data;

[0066] Step 1.3, use the RPC parameters and DEM data of the multispectral image and panchromatic image to perform orthorectification to correct the projection error and geometric distortion;

[0067] Step 1.4, fuse the orthorectified multispectral image and the panchromatic image to improve the resolution and increase the spectral information;

[0068] Step 1.5: mosaic and evenly color the high-resolution remote sensing images and crop them according to administrative regions.

[0069] In some embodiments, step 2 specifically includes the following steps:

[0070] Step 2.1, calculate the UWI urban water index. The UWI calculation formula is as follows:

[0071]

[0072] Among them, G, R, and NIR respectively represent the green band, red band, and near-infrared band of high-resolution remote sensing images.

[0073] Step 2.2: Select an appropriate threshold to binarize the UWI result image. Values greater than the threshold represent water bodies and are assigned a value of 1, while values less than the threshold represent non-water parts and are assigned a value of 0, obtaining a rough water body result.

[0074] In some embodiments, step 3 specifically includes the following steps:

[0075] Step 3.1: Crop the FROM-GLC10 data containing the test area;

[0076] Step 3.2: Reclassify the above FROM-GLC10 data, assign a value of 0 to water bodies and a value of 1 to non-water areas, and select a 3*3 convolution kernel to erode the reclassification result to reduce roughness. Resample the reclassification result according to the resolution of the used high-resolution remote sensing image to ensure consistent resolution;

[0077] Step 3.3: Intersect the resampled image with the rough water body result to generate an initial shadow. Select a 3*3 convolution kernel to erode it, contract the boundary inward, remove burrs and granular noise, set a threshold for deleting small fragmented patches, and eliminate a large number of isolated small patches to obtain a fine shadow.

[0078] In some embodiments, step 5 specifically includes the following steps:

[0079] Step 5.1: Erode the water body distribution result obtained in step 4 to remove burrs and delete small fragmented patches to make the result more complete. Vectorize it and overlay it with the original image, delete and modify incorrect vectors, and supplement the missed parts to obtain an accurate water area range;

[0080] Step 5.2: Calculate the water area and the total area of the image area, and calculate the water surface rate according to the following formula:

[0081] Water surface rate = accurate water area / total area of the area * 100%.

[0082] In some embodiments, based on Figure 2 and the detailed process of the high-resolution remote sensing image water surface rate calculation method based on the combination of the UWI index and FROM-GLC10 data, the technical solution of the present invention provides the following embodiments, and its implementation process is the same as that of Embodiment 2:

[0083] Step 1. Obtain the high-resolution 6 PMS high-resolution remote sensing image of a certain city. The high-resolution remote sensing image data includes panchromatic images (resolution of 2 meters) and multispectral images (resolution of 8 meters). The phases are October 3 and November 5, 2020. The image quality is good and completely covers the city. After pre-processing steps such as radiation correction, atmospheric correction, orthorectification, image fusion, and mosaic color uniformity, the cloudy part is removed and cropped according to the land boundary vector of a certain city to obtain reflectivity data with accurate geometric positioning.

[0084] Among them, radiation correction is processed using the calibration coefficients provided by the image metadata file. The panchromatic image outputs the apparent reflectance, and the multispectral image outputs the radiance. Atmospheric correction is to select the FLAASH model to process the multispectral image, eliminate the radiation error caused by atmospheric interference, and generate reflectance data. Orthorectification is to use the RPC parameter file and DEM data that come with the image to eliminate the geometric error and obtain the correct geometric positioning. Image fusion selects the PANSHARP method to fuse the panchromatic image and the multispectral image into one image, improve the spatial resolution of the multispectral image, and retain the spectral feature information. Mosaic uniform color is to splice the two images into one and crop them according to the land boundary of a city.

[0085] Step 2, reference Figure 3 Schematic diagram of rough results of water bodies, using the reflectivity data processed in step 1 to extract rough results of water bodies.

[0086] Step 2.1, calculate the UWI urban water index. The UWI calculation formula is as follows:

[0087]

[0088] Among them, G, R, and NIR represent the green band, red band, and near-red band of the high-resolution remote sensing image, namely the 2nd, 3rd, and 4th bands of the GF6 image. The UWI urban water index is calculated for the data preprocessed in step 1 according to the above formula;

[0089] In step 2.2, -0.2 is selected as the binarization threshold to ensure full coverage of the water body range. Values ​​greater than -0.2 represent water bodies and are assigned a value of 1, while values ​​less than -0.2 represent non-water parts and are assigned a value of 0.

[0090] Step 3: Obtain FROM-GLC10 data of the monitoring area and combine it with the rough results of the water body to obtain the image shadow. Figure 4 .

[0091] Among them, the FROM-GLC10 data is the world's first global land cover product with a 10-meter resolution developed based on Sentinel-2 data in 2017. The classification system mainly includes cultivated land, forest, grassland, shrubland, wetland, water body, tundra, artificial surface, bare land, glacier and permanent snow cover, and the overall accuracy is 72.76%.

[0092] Step 3.1, according to the product naming rule of the FROM-GLC10 data, the fromglc10v01_22_112.tif dataset containing a certain city was selected, and the basic land cover data of the city in 2017 was obtained after cropping.

[0093] Step 3.2, reclassify the land cover data cropped in Step 3.1. According to the classification standard, the non-water part is assigned a value of 1, and the water body is assigned a value of 0. Then select a 3*3 convolution kernel to erode the reclassification result to reduce roughness, and resample the reclassification result to 2 meters to ensure consistency with the resolution of the GF6-PMS data used in Step 1.

[0094] Step 3.3, intersect the resampling result in Step 3.2 with the rough water body result in Step 2 to generate the initial shadow. Select a 3*3 convolution kernel to erode it, so that the boundary shrinks inward, remove burrs and granular noise, set the threshold for deleting small fragmented patches, and eliminate a large number of isolated small patches to obtain a fine shadow.

[0095] Step 4, subtract the image shadow obtained in Step 3 from the rough water body result in Step 2 to extract the pure water body.

[0096] Step 5, calculate the water surface ratio of the image. Among them,

[0097] Step 5.1, select a 3*3 convolution kernel to erode the water body distribution result obtained in Step 4 to remove burrs, and delete small fragmented patches with an area less than 100 pixels to make the result more complete. Vectorize it and overlay it with the original image, delete and modify incorrect vectors, and supplement the missed parts to obtain the accurate water area range;

[0098] Step 5.2, calculate the water area and the total area of the image area, and calculate the water surface ratio according to the following formula:

[0099] Reference Figure 5 Based on the overall water area analysis result map, after calculation, the extracted water area of a certain city is about 319.86 square kilometers, and the land area of a certain city is about 1753.99 square kilometers (sea areas are not included), so the water surface ratio of a certain city is about 18.24%, and Figure 6 is the enlarged local water area analysis result map.

[0100] Such as Figure 7As shown in the figure, an apparatus for analyzing the water surface ratio of high-resolution remote sensing images according to an embodiment of the present invention is further provided. The apparatus includes a preprocessing module 701, an extraction module 702, an image shadow module 703, an accurate water area module 704, and an image water surface ratio module 705;

[0101] Among them, the preprocessing module is configured to obtain a high-resolution remote sensing image of a target monitoring area in response to an analysis request, and perform preprocessing on the high-resolution remote sensing image to obtain the reflectance data of the high-resolution remote sensing image. The preprocessing corrects the high-resolution remote sensing image through preset parameters; the extraction module is configured to extract the high-resolution remote sensing image through the reflectance data to obtain a first water body distribution result; the image shadow module is configured to extract the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determine an image shadow according to the first water body distribution result and the extraction result; the accurate water area module is configured to determine a second water body distribution result according to the first water body distribution result and the image shadow; the image water surface ratio module is configured to determine the image water surface ratio of the target monitoring area through the second water body distribution result.

[0102] Exemplarily, under the cooperation of the preprocessing module, the extraction module, the image shadow module, the accurate water area module, and the image water surface ratio module in the apparatus, the apparatus in the embodiment can implement any one of the foregoing methods for analyzing the water surface ratio of high-resolution remote sensing images, that is, in response to an analysis request, obtain a high-resolution remote sensing image of a target monitoring area, perform preprocessing on the high-resolution remote sensing image to obtain the reflectance data of the high-resolution remote sensing image, and correct the high-resolution remote sensing image through preset parameters; extract the high-resolution remote sensing image through the reflectance data to obtain a first water body distribution result; extract the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determine an image shadow according to the first water body distribution result and the extraction result; determine a second water body distribution result according to the first water body distribution result and the image shadow; determine the image water surface ratio of the target monitoring area through the second water body distribution result. The present invention fully exploits the advantages of the UWI index and the FROM-GLC10 data, simplifies the process of distinguishing water bodies and shadow noises, ensures the integrity of water body extraction while reducing shadow confusion, and greatly reduces the phenomena of missed extraction of water areas and mis-extraction of other ground objects. It can be applied to the engineering large-area rapid statistics of the water surface ratio of a certain area.

[0103] An embodiment of the present invention further provides an electronic device, which includes a processor and a memory;

[0104] The memory stores a program;

[0105] The processor executes a program to perform the foregoing high-resolution remote sensing image water surface rate analysis method; the electronic device has the function of carrying and running the software system for high-resolution remote sensing image water surface rate analysis provided by the embodiments of the present invention. For example, a personal computer (PC), a mobile phone, a smart phone, a personal digital assistant (PDA), a wearable device, a pocket PC (PPC), a tablet computer, etc.

[0106] Embodiments of the present invention also provide a computer-readable storage medium, and the storage medium stores a program, and the program is executed by a processor to implement the high-resolution remote sensing image water surface rate analysis method as described above.

[0107] In some alternative embodiments, the functions / operations mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the functions / operations involved, two consecutive blocks shown may actually be executed substantially simultaneously or the blocks can sometimes be executed in the reverse order. In addition, the embodiments presented and described in the flowcharts of the present invention are provided by way of example for the purpose of providing a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated, in which the order of various operations is changed and the sub-operations described as part of a larger operation are executed independently.

[0108] Embodiments of the present invention also disclose a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the foregoing high-resolution remote sensing image water surface rate analysis method.

[0109] In addition, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the functions and / or features described may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for understanding the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skills of an engineer. Thus, those skilled in the art can implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0110] If the described function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0111] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a definable sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with these instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0112] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection (electronic device) having one or more wirings, a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable media can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or, if necessary, other suitable processing, and then storing it in a computer memory.

[0113] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application-specific integrated circuits having suitable combinational logic gate circuits, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0114] In the description of this specification, the description referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in a suitable manner in any one or more embodiments or examples.

[0115] Although the embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention, and the scope of the present invention is defined by the claims and their equivalents.

[0116] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without departing from the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A method for analyzing water surface ratio of high-resolution remote sensing images, characterized in that Including: In response to an analysis request, obtain a high-resolution remote sensing image of a target monitoring area, perform preprocessing on the high-resolution remote sensing image to obtain reflectance data of the high-resolution remote sensing image, and correct the high-resolution remote sensing image through preset parameters; Extract the high-resolution remote sensing image through the reflectance data to obtain a first water body distribution result; Extract the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determine an image shadow according to the first water body distribution result and the extraction result; Determine a second water body distribution result according to the first water body distribution result and the image shadow; Determine the image water surface rate of the target monitoring area through the second water body distribution result; The extracting the high-resolution remote sensing image through the reflectance data to obtain a first water body distribution result includes: Calculate the UWI urban water body index, and the UWI calculation formula is where G, R, and NIR are the green band, red band, and near-infrared band of the high-resolution remote sensing image respectively; Binarize the image of the UWI urban water body index according to a set threshold, take the part exceeding the set threshold as water, and perform a first assignment process on the water body and non-water body areas to obtain the first water body distribution result, and the first assignment process includes assigning values to the water body and non-water body separately; The extracting the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determining an image shadow according to the first water body distribution result and the extraction result includes: Crop the FROM-GLC10 data including the target monitoring area; Reclassify the FROM-GLC10 data, erode the reclassification result through a 3*3 convolution kernel, and then resample the reclassification result to obtain a resampled image; Find the intersection of the resampled image and the first water body distribution result to generate an initial shadow, erode the initial shadow through a 3*3 convolution kernel, and eliminate small fragments of the initial shadow by setting a threshold for deleting small fragments to obtain the fine image shadow.

2. The method for analyzing the water surface rate of high-resolution remote sensing images according to claim 1, wherein The performing preprocessing on the high-resolution remote sensing image to obtain the reflectance data of the high-resolution remote sensing image includes: Perform radiometric correction on the high-resolution remote sensing image through a calibration coefficient to generate radiance data; Perform atmospheric correction on the radiance data to obtain the reflectance data.

3. The method for analyzing the water surface ratio of high-resolution remote sensing images according to claim 2, characterized in that The method further includes: Perform orthorectification on the reflectance data through RPC parameters of the multispectral image and panchromatic image and DEM data; Fuse the orthorectified multispectral image and panchromatic image; Mosaic, splice, and equalize the remote sensing images, and crop them according to a preset partition.

4. The method for analyzing the water surface rate of high-resolution remote sensing images according to claim 1, characterized in that The determining the image water surface rate of the target monitoring area through the second water body distribution result includes: Erode the obtained first water body distribution result to remove burrs and delete small fragments, then perform vectorization and overlay it with the high-resolution remote sensing image, delete and modify incorrect vectors, and supplement the missed extraction areas to obtain a second water body distribution result, and the second water body distribution result is used to represent the precise water area range; Calculate the exact water area range and the total area of the high-resolution remote sensing image area, and determine the image water surface rate of the target monitoring area according to the ratio of the exact water area range to the total area of the high-resolution remote sensing image area.

5. A water surface rate analysis device for high-resolution remote sensing images, characterized in that, Including: A preprocessing module, configured to obtain a high-resolution remote sensing image of a target monitoring area in response to an analysis request, and perform preprocessing on the high-resolution remote sensing image to obtain reflectivity data of the high-resolution remote sensing image, where the preprocessing corrects the high-resolution remote sensing image through preset parameters; An extraction module, configured to extract the high-resolution remote sensing image through the reflectivity data to obtain a first water body distribution result; An image shadow module, configured to extract the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determine an image shadow according to the first water body distribution result and the extraction result; An exact water area module, configured to determine a second water body distribution result according to the first water body distribution result and the image shadow; An image water surface rate module, configured to determine the image water surface rate of the target monitoring area through the second water body distribution result; The extracting the high-resolution remote sensing image through the reflectivity data to obtain a first water body distribution result includes: Calculating the UWI urban water body index, and the UWI calculation formula is where G, R, and NIR are the green band, red band, and near-infrared band of the high-resolution remote sensing image respectively; Binarize the image of the UWI urban water body index according to a set threshold, take the part exceeding the set threshold as water, and perform a first assignment process on the water and non-water areas to obtain the first water body distribution result, where the first assignment process includes assigning values to water and non-water respectively; The extracting the target monitoring area through a data set to obtain an extraction result based on the data set standard, and determining an image shadow according to the first water body distribution result and the extraction result includes: Cropping the FROM-GLC10 data including the target monitoring area; Reclassify the FROM-GLC10 data, erode the reclassified result through a 3*3 convolution kernel, and then resample the reclassified result to obtain a resampled image; Find the intersection of the resampled image and the first water body distribution result to generate an initial shadow, erode the initial shadow through a 3*3 convolution kernel, and set a threshold for deleting small fragmented patches to eliminate the small fragmented patches of the initial shadow to obtain the fine image shadow.

6. An electronic device, characterized in that, Including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the high-resolution remote sensing image water surface rate analysis method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by a processor to implement the high-resolution remote sensing image water surface rate analysis method according to any one of claims 1-4.

Images