Flood inundation range identification method and system, electronic equipment and storage medium

Abstract

The invention provides a flood inundation range identification method and system, electronic equipment and a storage medium, and relates to the technical field of image identification. The method comprises the following steps: determining a natural water body area according to a historical SAR image and a preset threshold value; determining a suspected water body area according to the real-time SAR image and a preset threshold value; determining water surface fluctuation data according to the real-time water level data; obtaining a corrected image according to the water surface fluctuation data and the real-time SAR image; obtaining a first water body area according to the corrected image and a preset threshold value; overlapping and fusing the first water body area and the suspected water body area to obtain a water body coverage area; and removing a natural water body area on the basis of the water body coverage area to obtain a flood inundation range. The first water body area is overlapped on the basis of the suspected water body area to obtain the water body coverage area, the recognition error caused by water surface fluctuation is weakened, the water body judgment accuracy is improved, the natural water body area is removed, the flood inundation range is obtained, and therefore the flood inundation range recognition accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a flood inundation range recognition method, system, electronic device and storage medium. Background Art

[0002] Synthetic Aperture Radar (SAR) is an active microwave remote sensing technology that generates high-resolution images by emitting electromagnetic waves and receiving echo signals reflected from ground objects. Due to its unique imaging method and all-weather capabilities, SAR plays an irreplaceable role in flood monitoring, topographic mapping, and disaster response.

[0003] Synthetic aperture radar (SAR) actively transmits microwaves through its antenna and receives echo signals reflected by ground objects. Calm water surfaces produce mirror-like reflections, resulting in very low echo intensity and appearing black in SAR images. Rough surfaces or vegetation scatter more strongly, appearing bright in SAR images, allowing water bodies to be identified. However, thunderstorms are often accompanied by strong winds, disrupting the calm surface of the water, which may be misidentified as non-water bodies, reducing the accuracy of flood inundation identification. Summary of the Invention

[0004] The problem to be solved by the present invention is that the existing submerged range identification method based on synthetic aperture radar is prone to misjudgment of the water surface during thunderstorm weather with floods, resulting in reduced identification accuracy.

[0005] To solve the above problems, in a first aspect, the present invention provides a method for identifying a flood inundation range, comprising: Acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period; determining a natural water body area based on the historical SAR image and a preset threshold; Determining a suspected water body area based on the real-time SAR image and a preset threshold; determining water surface fluctuation data based on the real-time water level data; Obtaining a corrected image based on the water surface fluctuation data and the real-time SAR image; Obtaining a first water body region according to the corrected image and a preset threshold; Superimposing and fusing the first water body area and the suspected water body area to obtain a water body coverage area; The natural water area is eliminated based on the water body coverage area to obtain the flood inundation range.

[0006] Optionally, the water surface fluctuation data includes a mean value of water level fluctuation; Determining water surface fluctuation data according to the real-time water level data includes: Based on the acquisition time point of the real-time SAR image, intercepting the real-time water level data of a preset time length; Based on the intercepted real-time water level data, multiple water level peak-valley differences are obtained, and the mean water level fluctuation is determined.

[0007] Optionally, obtaining a corrected image based on the water surface fluctuation data and the real-time SAR image includes: Comparing the sizes of the natural water body area and the suspected water body area to determine the undetermined water body area; Expand the scope of the water body to be determined in the real-time SAR image, determine the area to be processed, and obtain the image to be processed; A corrected image is obtained according to the water surface fluctuation data and the image to be processed.

[0008] Optionally, obtaining a corrected image according to the water surface fluctuation data and the image to be processed includes: Determine the fluctuation increment based on the mean value of water level fluctuation and the unit water level fluctuation value; Based on the image to be processed, the backscatter intensity in the area to be processed is subtracted from the fluctuation increment to obtain a corrected image.

[0009] Optionally, determining the fluctuation increment according to the water level fluctuation mean and the unit water level fluctuation value includes: Obtaining a backscattering intensity corresponding to the unit water level fluctuation value according to the unit water level fluctuation value, the radar incident angle, the radar wavelength, the wave number, and the dielectric constant of the natural water body; Determining a fluctuation multiple based on the water level fluctuation mean and the unit water level fluctuation value; Determining the backscattering intensity corresponding to the mean water level fluctuation value according to the fluctuation multiple and the backscattering intensity corresponding to the unit water level fluctuation value; The fluctuation increment is determined based on the backscattering intensity corresponding to the mean water level fluctuation and the standard backscattering intensity.

[0010] Optionally, the backscattering intensity corresponding to the unit water level fluctuation value is: , , , in, Indicates the backscattering intensity corresponding to the unit water level fluctuation value; represents the water surface roughness spectrum; R represents the reflection coefficient; represents the dielectric constant of natural water; θ represents the radar incident angle; represents the wave number; h represents the unit water level fluctuation value; λ represents the radar wavelength.

[0011] Optionally, the fluctuation increment is: , in, represents the fluctuation increment, represents the mean value of water level fluctuation, Indicates the standard backscatter intensity.

[0012] In a second aspect, the present invention further provides a flood inundation range identification system, comprising: A data acquisition module is used to acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period; A historical image recognition module, configured to determine a natural water body area based on the historical SAR image and a preset threshold; A real-time image recognition module is used to determine a suspected water body area based on the real-time SAR image and a preset threshold; A water level fluctuation analysis module, configured to determine water surface fluctuation data based on the real-time water level data; An image correction module, configured to obtain a corrected image based on the water surface fluctuation data and the real-time SAR image; A modified image recognition module, configured to obtain a first water body area based on the modified image and a preset threshold; A region fusion module, configured to superimpose and fuse the first water body region and the suspected water body region to obtain a water body coverage region; The flood range identification module is used to eliminate the natural water body area based on the water body coverage area to obtain the flood inundation range.

[0013] In a third aspect, the present invention provides an electronic device comprising a memory and a processor; The memory is used to store computer programs; The processor is configured to implement the flood inundation range identification method as described in the first aspect when executing the computer program.

[0014] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the flood inundation range identification method as described in the first aspect is implemented.

[0015] The present invention provides a flood inundation range identification method, system, electronic device, and storage medium. Compared with the existing technology, it has the following advantages: The natural water area can be accurately determined using historical SAR images obtained during calm weather and a preset threshold. In the event of a flood, the suspected water area can be first determined using real-time SAR images and a preset threshold. Water level sensors set up around the natural water area collect real-time water level data, thereby obtaining water level fluctuation data. The real-time SAR image is then corrected using the water surface fluctuation data to obtain a corrected image. Water body identification is then performed again based on the corrected image and a preset threshold to obtain a first water area. This first water area is then superimposed on the suspected water area to obtain a water coverage area. This reduces the impact of possible overcorrection, weakens the recognition error caused by water surface fluctuations, and improves the accuracy of water body identification. The natural water area is then eliminated, and the remaining area is the flood inundation range, thereby improving the accuracy of flood inundation range identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] 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 only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0017] Figure 1 A schematic flow chart of a flood inundation range identification method provided by an embodiment of the present invention; Figure 2 A schematic structural diagram of a flood inundation range identification system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] To make the objectives, technical solutions, and advantages of the embodiments of this application more clear, the technical solutions in the embodiments of this application are clearly and completely described. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0019] Synthetic aperture radar (SAR) is an active microwave remote sensing technology that generates high-resolution images by emitting electromagnetic waves and receiving echo signals reflected from ground objects. Specifically, SAR actively transmits microwaves through a radar antenna and then receives echo signals reflected from ground objects. Different objects reflect microwaves differently, and the echo signals from these objects can be used to identify different objects at different locations on the ground. For example, a mirror-like reflection from a calm surface will produce a very low echo intensity (appearing black in the image), while a rough surface or vegetation will scatter strongly and produce a very strong echo intensity (appearing bright in the image).

[0020] In order to better understand the above technical solution, the above technical solution will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0021] like Figure 1 As shown, the embodiment of the present application provides a method for identifying a flood inundation range, including: S1: Acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period.

[0022] S2: Determine a natural water area based on the historical SAR image and a preset threshold.

[0023] S3: Determine a suspected water body area based on the real-time SAR image and a preset threshold.

[0024] S4: Determine water surface fluctuation data based on the real-time water level data.

[0025] S5: Obtain a corrected image based on the water surface fluctuation data and the real-time SAR image.

[0026] S6: Obtain a first water body area according to the corrected image and a preset threshold.

[0027] S7: Overlay and merge the first water body area and the suspected water body area to obtain a water body coverage area.

[0028] S8: Eliminate the natural water area based on the water body coverage area to obtain the flood inundation range.

[0029] In this embodiment, natural water bodies (such as rivers, lakes, or streams) can be accurately identified using historical SAR images acquired during calm weather and a preset threshold. The natural water body areas identified in this case are those before a flood. During a flood, suspected water bodies can be identified using real-time SAR images and a preset threshold. However, due to strong winds, the water surface fluctuates, increasing surface roughness and altering reflections, potentially misidentifying them as non-water bodies. Consequently, the identified water areas may be less accurate. By setting up water level sensors around natural water areas, real-time water level data can be collected to obtain water level fluctuation data (such as peaks, troughs, or peak-to-trough differences, etc.). The water surface fluctuation data is used to correct the real-time SAR image to obtain a corrected image. At this time, the backscattering intensity of the corrected image is corrected, and water body identification is performed again based on the corrected image and the preset threshold to obtain the first water body area. The first water body area is superimposed on the suspected water body area to obtain the water body coverage area, reducing the impact of possible over-correction, weakening the recognition error caused by water surface fluctuations, and improving the accuracy of water body judgment. The natural water body area is then eliminated, and the remaining area is the flood inundation range, thereby improving the accuracy of flood inundation range identification.

[0030] Each step is described in detail below.

[0031] S1: Acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period.

[0032] Specifically, water level sensors are arranged around natural water bodies, for example, on the edge of a river bank, and water level sensors are arranged at a certain height vertically on the river bank, so that the water level sensors have a larger monitoring range and can monitor water level data from the river bank ground to a specified distance above the ground. The specified distance can be 0.5m or 1m, etc.

[0033] S2: Determine a natural water area based on the historical SAR image and a preset threshold.

[0034] S3: Determine a suspected water body area based on the real-time SAR image and a preset threshold.

[0035] Specifically, receiving echo signals reflected from ground objects can generate high-resolution images. Different objects or surfaces of varying roughness have different backscatter intensities for microwaves. Using the backscatter intensity and a preset threshold, a threshold segmentation method is used to distinguish between water and non-water bodies. For example, if the preset threshold is set to -20dB, areas with backscatter intensities greater than -20dB are considered non-water, while areas with backscatter intensities less than or equal to -20dB are considered water. This method can be used to distinguish natural water areas in historical SAR images from suspected water areas in real-time SAR images.

[0036] S4: Determine water surface fluctuation data based on the real-time water level data. The water surface fluctuation data includes a water level peak mean value and a water level trough mean value.

[0037] S41: Based on the acquisition time point of the real-time SAR image, real-time water level data of a preset time length is intercepted.

[0038] Specifically, in a short period of time, the water surface fluctuations vary little. To accurately obtain the water level fluctuations at the time of acquiring real-time SAR images, a time window starting at that moment can be captured. The data within this time window is most similar to the water surface fluctuations corresponding to the time of acquiring the real-time SAR images. The captured real-time water level data is used to analyze the water level fluctuations at the current moment. This can reduce the volume of analysis data and improve the accuracy of the analysis results. The water level sensor can monitor a water level data at every moment. By statistically analyzing this water level data on the time axis in chronological order, the continuous fluctuation of the water surface level can be obtained, forming a water level fluctuation curve. Multiple water level peak values ​​and multiple water level trough values ​​can be picked up from this curve.

[0039] S42: Based on the intercepted real-time water level data, a plurality of water level peak-valley differences are obtained, and a mean value of the water level fluctuation is determined.

[0040] Specifically, using a set of adjacent peak values ​​and trough values, a water level peak-to-valley difference can be obtained. Through multiple sets of peak-to-valley values, multiple water level peak-to-valley differences can be obtained. Then, the average value is taken to obtain the mean of the water level peak-to-valley difference, which is the mean of the water level fluctuation. This value is the water surface fluctuation caused by strong wind blowing the water surface or the flow of the water surface. The mean of the water level fluctuation indicates the degree of water surface fluctuation.

[0041] S5: Obtain a corrected image based on the water surface fluctuation data and the real-time SAR image.

[0042] S51: Compare the sizes of the natural water body area and the suspected water body area to determine the pending water body area.

[0043] S52: Expand the range of the water body to be determined in the real-time SAR image, determine the area to be processed, and obtain the image to be processed.

[0044] Specifically, due to the influence of strong winds, the suspected water area identified by real-time SAR images may be smaller than the natural water area. At this time, the water surface may fluctuate strongly, causing the entire water surface to present continuous and high-density fluctuations, making it difficult to identify the water body well. At this time, the natural water area can be used as the pending water area; and when the suspected water area is larger than or equal to the natural water area, the suspected water area can be directly used as the pending water area. Then, based on the pending water area, the area is expanded equidistantly around the pending water area according to a preset expansion distance; or the maximum width of the pending water area is calculated, and based on the pending water area, the area is expanded equidistantly around the pending water area by half the maximum width. In this way, the area to be processed is circled in the real-time SAR image to obtain the image to be processed. In the subsequent correction process, only the area to be processed needs to be corrected, which reduces the amount of data processing and improves the processing speed.

[0045] S53: Obtaining a corrected image according to the water surface fluctuation data and the image to be processed.

[0046] S531: Determine the fluctuation increment corresponding to the mean water level fluctuation value based on the mean water level fluctuation value and the unit water level fluctuation value. The steps for determining the fluctuation increment are as follows.

[0047] The backscattering intensity corresponding to the unit water level fluctuation value is obtained according to the unit water level fluctuation value, the radar incident angle, the radar wavelength, the wave number and the dielectric constant of the natural water body.

[0048] Specifically, the increase in backscatter intensity when the water surface fluctuates is the result of the combined effects of the surface roughness spectrum and the reflectivity. The roughness spectrum affects the light scattering path and angle by altering the microscopic and macroscopic structure of the water surface. The reflectivity determines the proportion of light energy that participates in scattering and the degree to which reflected light interferes with scattered light.

[0049] The backscattering intensity corresponding to the unit water level fluctuation value is: , , , in, Indicates the backscattering intensity corresponding to the unit water level fluctuation value; represents the water surface roughness spectrum; R represents the reflection coefficient; represents the dielectric constant of natural water; θ represents the radar incident angle; represents the wave number; h represents the unit water level fluctuation value; λ represents the radar wavelength.

[0050] The fluctuation multiple is determined according to the water level fluctuation mean and the unit water level fluctuation value.

[0051] The backscattering intensity corresponding to the mean value of the water level fluctuation is determined according to the fluctuation multiple and the backscattering intensity corresponding to the unit water level fluctuation value.

[0052] Specifically, as the water level fluctuation value increases, the backscattering intensity also increases accordingly, and the water level fluctuation value and the backscattering intensity corresponding to the unit water level fluctuation value increase approximately in proportion. Therefore, after calculating the backscattering intensity corresponding to the unit water level fluctuation value, the ratio between the mean water level fluctuation value and the unit water level fluctuation value can be calculated to obtain the fluctuation multiple, and then the fluctuation multiple can be multiplied by the backscattering intensity corresponding to the unit water level fluctuation value to obtain the backscattering intensity corresponding to the mean water level fluctuation value.

[0053] The fluctuation increment is determined based on the backscatter intensity corresponding to the mean water level fluctuation and the standard backscatter intensity. The fluctuation increment is obtained by subtracting the standard backscatter intensity from the backscatter intensity corresponding to the mean water level fluctuation.

[0054] The fluctuation increment is: , in, represents the fluctuation increment, represents the mean value of water level fluctuation, Indicates the standard backscatter intensity.

[0055] For example, when the water surface is calm, h = 0, only specular reflection, standard backscattering intensity ≈-25 dB. Assuming radar parameters: C band (λ=5.6cm), VV polarization, incident angle θ=30°, surface medium: fresh water (dielectric constant =80, Fresnel reflection coefficient R≈0.95), then ≈112rad / m, when the unit water level fluctuation value h=1cm, , ≈-16.8dB. If the mean water level fluctuation is also 1cm, the fluctuation increment is -16.8-(-25)=8.2dB. If the mean water level fluctuation is 1.5cm, the fluctuation increment is -16.8×1.5-(-25)=-0.2dB.

[0056] S532: Based on the image to be processed, subtract the fluctuation increment from the backscattering intensity in the area to be processed to obtain a corrected image.

[0057] Specifically, the backscattering intensity corresponding to the to-be-processed area in the to-be-processed image is subtracted from the fluctuation increment to obtain a corrected backscattering intensity, thereby forming a corrected image. In the corrected image, the area of ​​the dark area is increased.

[0058] S6: Obtain a first water body area according to the corrected image and a preset threshold.

[0059] Specifically, a first water body region is obtained based on the backscatter intensity in the corrected image and a preset threshold, wherein a region with a backscatter intensity less than or equal to the preset threshold is determined to be a water body and constitutes the first water body region.

[0060] S7: Overlay and merge the first water body area and the suspected water body area to obtain a water body coverage area.

[0061] Specifically, when the first water body area and the suspected water body area are superimposed, it is equivalent to first finding the union of the two areas. When there is a highlight area (i.e., an area with backscatter intensity greater than a preset threshold) inside the two water body areas, the area of ​​the highlight area is calculated. If the area of ​​the highlight area is smaller than the preset area, it means that the area may be an unidentified water body or a non-water body area surrounded by a water body area. The highlight area can be directly used as the water body coverage area. When the area of ​​the highlight area is greater than or equal to the preset area, it means that the area is a larger non-water body area surrounded by a water body area. The boundary of the highlight area is separately marked as the non-water body area. When part of the boundary of the two water body areas is discontinuous, if the length of the discontinuous position is less than the preset length, the discontinuous position is directly connected. When the length of the discontinuous position is greater than or equal to the preset length, the discontinuous state is maintained, and the edge burrs of the water body coverage area are smoothed. The obtained water body coverage area takes into account both the suspected water body area and the first water body area. On the one hand, it can ensure that the identified water body coverage area is diffused based on the natural water body area, avoiding the problem that the identified water body coverage area deviates from the natural water body area, causing obvious errors in the identification results. On the other hand, the first water body area identified after correction may be over-corrected, resulting in the loss of part of the water body, but the lost part may be the area included in the natural water body area. After the two are superimposed, the error caused by over-correction can be reduced and the accuracy of the identification results can be improved.

[0062] S8: Eliminate the natural water area based on the water body coverage area to obtain the flood inundation range.

[0063] Specifically, in order to better show the scope of flood inundation, the natural water area can be excluded from the water coverage area. The excess part is the flood inundation range caused by the overflow of natural water bodies due to precipitation. This can better present the direction and distribution of the flood inundation range, so as to facilitate the formulation of reasonable rescue measures.

[0064] like Figure 2 As shown, an embodiment of the present application provides a flood inundation range identification system, comprising: The data acquisition module 100 is used to acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period; A historical image recognition module 200 is used to determine a natural water body area based on the historical SAR image and a preset threshold; A real-time image recognition module 300 is used to determine a suspected water body area based on the real-time SAR image and a preset threshold; A water level fluctuation analysis module 400 is used to determine water surface fluctuation data based on the real-time water level data; An image correction module 500 is configured to obtain a corrected image based on the water surface fluctuation data and the real-time SAR image; A modified image recognition module 600 is configured to obtain a first water body region based on the modified image and a preset threshold; A region fusion module 700 is configured to superimpose and fuse the first water body region and the suspected water body region to obtain a water body coverage region; The flood range identification module 800 is used to eliminate the natural water body area based on the water body coverage area to obtain the flood inundation range.

[0065] In this embodiment, the beneficial effects of the flood inundation range identification system are similar to the beneficial effects of the above-mentioned flood inundation range identification method, and are not described in detail here.

[0066] An electronic device provided in an embodiment of the present application includes a memory and a processor; the memory is used to store a computer program; and the processor is used to implement the flood inundation range identification method described above when executing the computer program.

[0067] An embodiment of the present application provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the flood inundation range identification method described above is implemented.

[0068] In this embodiment, the beneficial effects of the electronic device and the computer-readable storage medium are similar to the beneficial effects of the above-mentioned flood inundation range identification method, and are not described in detail here.

[0069] An electronic device that can serve as a server or client of the present application will now be described, which is an example of a hardware device that can be applied to various aspects of the present application. Electronic devices are intended to represent various forms of digital electronic computer devices, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. Electronic devices can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described and / or required herein.

[0070] Electronic devices include a computing unit that can perform various appropriate actions and processes based on computer programs stored in read-only memory (ROM) or loaded from a storage unit into random access memory (RAM). RAM can also store various programs and data required for device operation. The computing unit, ROM, and RAM are connected to each other via a bus. An input / output (I / O) interface is also connected to the bus.

[0071] Those skilled in the art will appreciate that all or part of the processes in the above-described method embodiments can be implemented by instructing the relevant hardware through a computer program. The program can be stored in a computer-readable storage medium, and when executed, the program can include the processes in the above-described method embodiments. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM). In this application, the units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network elements. Some or all of these units can be selected based on actual needs to achieve the objectives of the embodiments of this application. Furthermore, the functional units in each embodiment of this application can be integrated into a single processing unit, each unit can exist physically separately, or two or more units can be integrated into a single unit. These integrated units can be implemented in either hardware or software functional units.

[0072] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device 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 device. 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 device comprising the element.

[0073] The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A flood inundation range identification method, characterized in that: include: Acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period; determining a natural water body area based on the historical SAR image and a preset threshold; Determining a suspected water body area based on the real-time SAR image and a preset threshold; determining water surface fluctuation data based on the real-time water level data; Obtaining a corrected image based on the water surface fluctuation data and the real-time SAR image; Obtaining a first water body region according to the corrected image and a preset threshold; Superimposing and fusing the first water body area and the suspected water body area to obtain a water body coverage area; The natural water area is eliminated based on the water body coverage area to obtain the flood inundation range.

2. The flood inundation range identification method according to claim 1, characterized in that: The water surface fluctuation data includes the mean value of water level fluctuation; Determining water surface fluctuation data according to the real-time water level data includes: Based on the acquisition time point of the real-time SAR image, intercepting the real-time water level data of a preset time length; Based on the intercepted real-time water level data, multiple water level peak-valley differences are obtained, and the mean water level fluctuation is determined.

3. The flood inundation range identification method according to claim 2, characterized in that: The step of obtaining a corrected image based on the water surface fluctuation data and the real-time SAR image comprises: Comparing the sizes of the natural water body area and the suspected water body area to determine the undetermined water body area; Expand the scope of the water body to be determined in the real-time SAR image, determine the area to be processed, and obtain the image to be processed; A corrected image is obtained according to the water surface fluctuation data and the image to be processed.

4. The flood inundation range identification method according to claim 3, characterized in that: The step of obtaining a corrected image based on the water surface fluctuation data and the image to be processed comprises: Determine the fluctuation increment based on the mean value of water level fluctuation and the unit water level fluctuation value; Based on the image to be processed, the backscatter intensity in the area to be processed is subtracted from the fluctuation increment to obtain a corrected image.

5. The flood inundation range identification method according to claim 4, characterized in that: Determining the fluctuation increment according to the water level fluctuation mean and the unit water level fluctuation value includes: Obtaining a backscattering intensity corresponding to the unit water level fluctuation value according to the unit water level fluctuation value, the radar incident angle, the radar wavelength, the wave number, and the dielectric constant of the natural water body; Determining a fluctuation multiple based on the water level fluctuation mean and the unit water level fluctuation value; Determining the backscattering intensity corresponding to the mean water level fluctuation value according to the fluctuation multiple and the backscattering intensity corresponding to the unit water level fluctuation value; The fluctuation increment is determined based on the backscattering intensity corresponding to the mean water level fluctuation and the standard backscattering intensity.

6. The flood inundation range identification method according to claim 5, characterized in that: The backscattering intensity corresponding to the unit water level fluctuation value is: ， ， ， in, Indicates the backscattering intensity corresponding to the unit water level fluctuation value; represents the water surface roughness spectrum; R represents the reflection coefficient; represents the dielectric constant of natural water; θ represents the radar incident angle; represents the wave number; h represents the unit water level fluctuation value; λ represents the radar wavelength.

7. The flood inundation range identification method according to claim 5, characterized in that: The fluctuation increment is: ， in, represents the fluctuation increment, represents the mean value of water level fluctuation, and h represents the unit water level fluctuation value; Indicates the backscattering intensity corresponding to the unit water level fluctuation value; Indicates the standard backscatter intensity.

8. A flood inundation range identification system, characterized in that: include: A data acquisition module is used to acquire historical SAR images, real-time SAR images during flooding, and real-time water level data collected by a water level sensor, wherein the historical SAR images are SAR images acquired during a calm period; A historical image recognition module, configured to determine a natural water body area based on the historical SAR image and a preset threshold; A real-time image recognition module is used to determine a suspected water body area based on the real-time SAR image and a preset threshold; A water level fluctuation analysis module, configured to determine water surface fluctuation data based on the real-time water level data; An image correction module, configured to obtain a corrected image based on the water surface fluctuation data and the real-time SAR image; A modified image recognition module, configured to obtain a first water body area based on the modified image and a preset threshold; A region fusion module, configured to superimpose and fuse the first water body region and the suspected water body region to obtain a water body coverage region; The flood range identification module is used to eliminate the natural water body area based on the water body coverage area to obtain the flood inundation range.

9. An electronic device, characterized in that: including memory and processor; The memory is used to store computer programs; The processor is configured to implement the flood inundation range identification method according to any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that The storage medium stores a computer program, and when the computer program is executed by the processor, the flood inundation range identification method according to any one of claims 1 to 7 is implemented.

Images