Flood area identification method and device and electronic equipment

Abstract

The invention provides a flood area identification method and device and electronic equipment, and relates to the technical field of identification, and the method comprises the steps: obtaining a post-disaster remote sensing image of a target area; acquiring post-disaster surface reflectance images of the plurality of target wavebands based on the post-disaster remote sensing image; for each pixel in the post-disaster surface reflectance image, a target index value of the pixel is determined based on the surface reflectance value of the pixel under each target wave band, and the target index is an index sensitive to flood recognition; at least one target pixel corresponding to a target index value in a preset index range in the post-disaster surface reflectance image is determined, the preset index range is determined based on the target index value of each random point, and the random points are determined points representing flood occurrence in the post-disaster surface reflectance image; and determining a flood area in the target area based on all the target pixels. According to the invention, the identification efficiency and the identification precision of the flood area are improved.

Description

Technical Field

[0001] The present invention relates to the field of identification technology, and in particular to a flood area identification method, device and electronic equipment. Background Art

[0002] Floods and waterlogging caused by heavy rains are the most important natural disasters currently facing agriculture, and are also natural disasters that may cause serious production reductions or even total production losses. Rapid and accurate disaster-affected area identification technology can provide objective data support for disaster relief guidance, insurance company claims investigation, and bank agricultural credit repayment capacity assessment. The timeliness and accuracy of disaster-affected data will affect the effectiveness of related business development, and it is necessary to have convenient, fast, and accurate technical methods to support the rapid and accurate identification of flood-affected areas.

[0003] In related technologies, a recognition model based on a deep learning algorithm is usually used to identify flooded areas.

[0004] However, in the above-mentioned related technologies, when training the recognition model, it is necessary to manually survey the sample remote sensing images to mark the flooded areas, which results in a slow marking speed, thereby reducing the recognition efficiency of the flooded areas. In addition, since the geographical scope included in the sample remote sensing images may be inconsistent with the geographical scope included in the remote sensing images taken when the flooded areas are actually identified, the recognition accuracy will be low when the flooded areas are identified through the recognition model. Summary of the invention

[0005] The present invention provides a flood area recognition method, device and electronic equipment, which are used to solve the defects of low recognition efficiency and low recognition accuracy of flood areas in the prior art, and improve the recognition efficiency and recognition accuracy of flood areas.

[0006] The present invention provides a flood area identification method, comprising: Obtain post-disaster remote sensing images of the target area; Acquire post-disaster surface reflectance images of a plurality of target bands based on the post-disaster remote sensing images; For each pixel in the post-disaster surface reflectance image, based on the surface reflectance value of the pixel in each target band, determine a target index value of the pixel, the target index being an index sensitive to flood identification; Determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image, wherein the preset index range is determined based on the target index value of each random point, and the random point is a point indicating the occurrence of a flood determined in the post-disaster surface reflectance image; Based on all the target pixels, a flooded area within the target area is determined.

[0007] According to a flood area identification method provided by the present invention, the post-disaster remote sensing image includes a surface reflectance image of the 3rd band, the 4th band and the 8th band of a first spatial resolution, and a surface reflectance image of the 11th band of a second spatial resolution, wherein the second spatial resolution is smaller than the first spatial resolution; The step of acquiring a plurality of post-disaster surface reflectance images of the target bands based on the post-disaster remote sensing images comprises: Resampling the surface reflectance image of the 11th band of the second spatial resolution to obtain the surface reflectance image of the 11th band of the first spatial resolution; The surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution and the surface reflectance image of the 11th band of the first spatial resolution are superimposed to obtain the surface reflectance images of the multiple target bands.

[0008] According to a flood area identification method provided by the present invention, the target bands include band 3, band 4, band 8 and band 11; Determining the target index value of the pixel based on the surface reflectance value of the pixel in each target band includes: Determine the ratio water index of the pixel based on the surface reflectance values ​​of the pixel in the third band, the fourth band, the eighth band and the eleventh band; Determine a difference vegetation index of the pixel based on the respective surface reflectance values ​​of the pixel in the eighth band and the fourth band; The ratio water index and the difference vegetation index are determined as the target index values.

[0009] According to a flood area identification method provided by the present invention, the ratio water index of the pixel is determined based on the surface reflectance values ​​of the pixel in the third band, the fourth band, the eighth band and the eleventh band, including: Determine the sum of the ground reflectance values ​​of the pixel in the third band and the fourth band; Determine the difference between the ground reflectance values ​​of the pixel in the 8th band and the 11th band; Determine the ratio of the sum value to the difference value as the ratio water index of the pixel; The step of determining the difference vegetation index of the pixel based on the surface reflectance values ​​of the pixel in the eighth band and the fourth band, comprises: The difference between the ground reflectance values ​​of the pixel in the 8th band and the 4th band is determined as the difference vegetation index of the pixel.

[0010] According to a flood area identification method provided by the present invention, the preset index range includes a preset ratio water index range and a preset difference vegetation index range; The step of determining at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image includes: Determine a first pixel set corresponding to the ratio water index within the preset ratio water index range in the post-disaster surface reflectance image; Determine a second pixel set corresponding to the difference vegetation index within the preset difference vegetation index range in the post-disaster surface reflectance image; The intersection of all the first pixel sets and all the second pixel sets is determined as the at least one target pixel.

[0011] According to a flood area identification method provided by the present invention, the method of determining the flood area within the target area based on all the target pixels includes: Acquire pre-disaster remote sensing images of the target area; Determine a pre-disaster surface reflectance image of a first spatial resolution based on the pre-disaster remote sensing image, and perform super-resolution reconstruction on the pre-disaster surface reflectance image of the first spatial resolution to obtain a surface reflectance image of a third spatial resolution, wherein the first spatial resolution is smaller than the third spatial resolution; Determining the cultivated land area within the target area based on the surface reflectance image of the third spatial resolution; The intersection of the area corresponding to all the target pixels and the cultivated land area is determined as the flood area.

[0012] According to a flood area identification method provided by the present invention, the step of determining at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectivity image comprises: Normalizing the target index value of each pixel to obtain the normalized target index value of each pixel; At least one target pixel corresponding to a normalized target index value within a preset index range in the post-disaster surface reflectance image is determined.

[0013] The present invention also provides a flood area identification device, comprising: An acquisition module is used to obtain post-disaster remote sensing images of the target area; The acquisition module is further used to acquire post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images; A determination module, for determining, for each pixel in the post-disaster surface reflectance image, a target index value of the pixel based on the surface reflectance value of the pixel in each target band, wherein the target index is an index sensitive to flood identification; The determination module is further used to determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectivity image, wherein the preset index range is determined based on the target index value of each random point, and the random point is a point indicating the occurrence of a flood determined in the post-disaster surface reflectivity image; The determination module is further used to determine the flooded area within the target area based on all the target pixels.

[0014] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the flood area identification methods described above is implemented.

[0015] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the method for identifying a flooded area as described above is implemented.

[0016] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the method for identifying a flood-affected area as described above is implemented.

[0017] The method, device and electronic device for identifying flooded areas provided by the present invention obtain post-disaster remote sensing images of the target area, and obtain post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images. For each pixel in the post-disaster surface reflectance image, a target index value of the pixel is determined based on the surface reflectance value of the pixel in each target band. The target index is an index sensitive to flood identification, and at least one target pixel corresponding to the target index value within a preset index range in the post-disaster surface reflectance image is determined. The preset index range is determined based on the target index value of each random point. The random point is a point determined in the post-disaster surface reflectance image that represents the occurrence of a flood, thereby determining the flooded area within the target area based on all target pixels. Since the preset index range is determined based on the target index value of the random point where the flood occurs, the screened target pixels are all pixels within the flood area, so that the area composed of all target pixels can be determined as the flood area, which overcomes the defect in the related technology that when the flood area is identified through the regional recognition model, the samples need to be marked by manual survey each time when the regional recognition model is trained, resulting in slow training speed of the regional recognition model and low efficiency of flood area identification. At the same time, it can overcome the problem of low recognition accuracy when the flood area is identified through the regional recognition model due to the possible inconsistency between the geographical scope included in the sample remote sensing image and the geographical scope included in the remote sensing image taken when the flood area is actually identified, thereby improving the accuracy of flood area identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the present invention or 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 some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A schematic flow chart of a flood area identification method provided in an embodiment of the present invention.

[0020] Figure 2 A value range distribution diagram of the ratio water index (WRI) provided in an embodiment of the present invention.

[0021] Figure 3 This is a value range distribution diagram of the difference vegetation index DVI provided in an embodiment of the present invention.

[0022] Figure 4 An overall schematic diagram of a flood area identification method provided by an embodiment of the present invention.

[0023] Figure 5A schematic diagram of the structure of a flood area identification device provided in an embodiment of the present invention.

[0024] Figure 6 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0026] At present, monitoring flooded areas through remote sensing technology is generally carried out by supervised classification, which requires collecting sample remote sensing images, investigating a part of the affected area through manual field investigation, marking the flooded areas in the sample remote sensing images, and using the machine learning algorithm classifier to classify the area as a disaster-stricken sample, or using a deep learning algorithm to train a regional recognition model. The regional recognition model can identify the area affected by the flood and the area of ​​the flooded area. However, when using the regional recognition model of supervised classification, it is necessary to manually survey the sample remote sensing images to mark the flooded areas. The sample marking speed is slow, and the geographical scope included in the sample remote sensing images may be inconsistent with the geographical scope included in the remote sensing images taken when the flooded area is actually identified, which will cause the problem of low recognition accuracy when the flooded area is identified through the regional recognition model.

[0027] Based on this, the present invention provides a flood area recognition method. After determining the post-disaster surface reflectance image, the target index sensitive to flood recognition can be determined based on the surface reflectance value of each pixel in the post-disaster surface reflectance image under each target band, and then at least one target pixel corresponding to the target index value within a preset index range can be screened out. Since the preset index range is determined based on the target index value of the random point where the flood occurs, the screened target pixels are all pixels within the flood area, so that the area composed of all target pixels can be determined as the flood area, which overcomes the defect that when the flood area is recognized by the regional recognition model, when the regional recognition model is trained, each time the sample needs to be marked by manual survey, resulting in a slow training speed of the regional recognition model, thereby resulting in a low efficiency of flood area recognition. At the same time, it can overcome the problem that the regional range included in the sample remote sensing image and the regional range included in the remote sensing image taken when the flood area is actually recognized may be inconsistent, resulting in low recognition accuracy when the flood area is recognized by the regional recognition model, thereby improving the accuracy of flood area recognition.

[0028] Combine the following Figure 1-Figure 4 The method for identifying flooded areas of the present invention is described. The execution subject of the method for identifying flooded areas can be an electronic device such as a terminal, a tablet computer, or a computer, or a flooded area identification device set in the electronic device, and the flooded area identification device can be implemented by software, hardware, or a combination of the two.

[0029] Figure 1 A schematic diagram of a flow chart of a flood area identification method provided by an embodiment of the present invention, such as Figure 1 As shown, the flood area identification method includes the following steps: Step 101: Acquire post-disaster remote sensing images of the target area.

[0030] The target area can be any area where flood disaster identification is required, and can also be called a study area.

[0031] In this step, taking XX County, XX City, XX Province as the target area for example, according to the time when the flood occurred in the target area, the remote sensing image of the target area obtained after the flood occurred is used as the post-disaster remote sensing image.

[0032] Step 102: Acquire post-disaster surface reflectance images of multiple target bands based on post-disaster remote sensing images.

[0033] In this step, after obtaining the post-disaster remote sensing images, the post-disaster remote sensing images are calibrated by radiation, atmospheric correction is performed through the atmospheric correction model (Fast Line-of-sight Atmospheric Analysis of Spectral Hypercubes, FLAASH), geometric registration and orthorectification are performed to obtain post-disaster surface reflectance images of multiple target bands. The target bands here include bands 3, 4, 8 and 11, a total of 4 bands. Among them, band 3 is the green band, band 4 is the red band, band 8 is the near infrared band, and band 11 is the short-wave infrared band.

[0034] Step 103: for each pixel in the post-disaster surface reflectance image, based on the surface reflectance value of the pixel in each target band, determine the target index value of the pixel, and the target index is an index sensitive to flood identification.

[0035] In this step, the target index includes the Water Resources Index (WRI) and / or the Difference Vegetation Index (DVI). The Water Resources Index (WRI) can significantly reflect the flood-affected areas, is sensitive to the water bodies in the flood-affected areas, and is less disturbed by weak vegetation information, while the Difference Vegetation Index (DVI) is sensitive to the vegetation information in the flood-affected areas and is less disturbed by the water bodies in the flood-affected areas. Therefore, both the Water Resources Index (WRI) and the Difference Vegetation Index (DVI) are indexes that are sensitive to flood identification. After a flood occurs, the Water Resources Index (WRI) of the disaster-affected areas will increase significantly, and the Difference Vegetation Index (DVI) will decrease significantly. These two indices are suitable for the identification of flood-affected areas.

[0036] For each pixel in the post-disaster surface reflectance image, the ratio water index WRI and / or difference vegetation index DVI of the pixel can be determined according to the surface reflectance value of the pixel in each target band. Among them, the surface reflectance value usually refers to the reflectivity of surface objects to solar radiation. It is a physical quantity used to describe the ratio of solar radiation energy reflected by the surface of an object to the incident solar radiation energy. In the field of remote sensing, surface reflectance values ​​are often used to evaluate the spectral characteristics of surface objects and are an important basis for remote sensing image interpretation and classification.

[0037] Step 104: determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image, where the preset index range is determined based on the target index value of each random point, and the random point is a point in the post-disaster surface reflectance image that represents a flood.

[0038] Specifically, after obtaining post-disaster surface reflectance images of multiple target bands, visual interpretation of sample points in the flooded area and interpretation of precision verification points are performed on the basis of the post-disaster surface reflectance images to determine multiple interpretation sample points in the flooded area, i.e., random points, wherein the interpretation sample points in the flooded area are used to assist in the screening of water index and vegetation index categories, and to determine the preset index range of the screened ratio water index WRI and / or difference vegetation index DVI. After determining multiple random points, in order to further improve the accuracy of the random points, field surveys can also be conducted.

[0039] In addition, the interpretation of accuracy verification points is mainly used for accuracy verification after the identification of flood-affected areas is completed. Verification points can be randomly arranged and interpreted within the scope of cultivated land plots in the target area, so that the recognition accuracy of the flood-affected areas can be verified through these verification points.

[0040] After determining the target index of each pixel in the post-disaster surface reflectance image, the target index values ​​of the pixels corresponding to the above random points can be screened out, so that the numerical range composed of the target index values ​​of these pixels is determined as the corresponding preset index range.

[0041] Taking the target index including the ratio water index WRI and the difference vegetation index DVI as an example, Figure 2 The value range distribution diagram of the ratio water index WRI provided in the embodiment of the present invention is as follows: Figure 2 As shown, assuming that the number of determined random points is 520, after determining the ratio water index WRI of the 520 random points, a value range frequency line graph of the ratio water index WRI of the flooded area is drawn based on the ratio water index WRI of the 520 random points. By analyzing the value range of the value range frequency line graph, the preset index range corresponding to the ratio water index WRI can be determined, such as 0.4-0.7.

[0042] Figure 3 The value range distribution diagram of the difference vegetation index DVI provided by the embodiment of the present invention is as follows: Figure 3 As shown in the figure, after determining the difference vegetation index DVI of the above 520 random points, a value range frequency line graph of the difference vegetation index DVI of the flooded area is drawn based on the difference vegetation index DVI of the 520 random points. By analyzing the value range of the value range frequency line graph, the preset index range corresponding to the difference vegetation index DVI can be determined, such as 0.086-0.6.

[0043] Since the random points are points that represent floods, the preset index range determined based on the target index values ​​of the pixels corresponding to the random points can represent the index range of the flooded area. Therefore, at least one target pixel corresponding to the target index value within the preset index range in the post-disaster surface reflectance image can be determined. It should be understood that these target pixels are all pixels within the flooded area.

[0044] Step 105: Determine the flooded area within the target area based on all target pixels.

[0045] In this step, after determining the target pixels corresponding to all target index values ​​within the preset index range in the post-disaster surface reflectance image, the area obtained by extracting these target pixels can be determined as the flood area within the target area.

[0046] The method for identifying flooded areas provided by an embodiment of the present invention obtains a post-disaster remote sensing image of a target area, and obtains post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing image. For each pixel in the post-disaster surface reflectance image, a target index value of the pixel is determined based on the surface reflectance value of the pixel in each target band. The target index is an index sensitive to flood identification, and at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image is determined. The preset index range is determined based on the target index value of each random point. The random point is a point determined in the post-disaster surface reflectance image that represents the occurrence of a flood, thereby determining the flooded area within the target area based on all target pixels. Since the preset index range is determined based on the target index value of the random point where the flood occurs, the screened target pixels are all pixels within the flood area, so that the area composed of all target pixels can be determined as the flood area, which overcomes the defect in the related technology that when the flood area is identified through the regional recognition model, the samples need to be marked by manual survey each time when the regional recognition model is trained, resulting in slow training speed of the regional recognition model and low efficiency of flood area identification. At the same time, it can overcome the problem of low recognition accuracy when the flood area is identified through the regional recognition model due to the possible inconsistency between the geographical scope included in the sample remote sensing image and the geographical scope included in the remote sensing image taken when the flood area is actually identified, thereby improving the accuracy of flood area identification.

[0047] Exemplarily, based on the above embodiment, the post-disaster remote sensing image includes the surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution, and the surface reflectance image of the 11th band of the second spatial resolution, and the second spatial resolution is smaller than the first spatial resolution. When obtaining the post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing image, it can be specifically implemented in the following ways: The surface reflectance image of the 11th band of the second spatial resolution is resampled to obtain the surface reflectance image of the 11th band of the first spatial resolution, and the surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution and the surface reflectance image of the 11th band of the first spatial resolution are superimposed to obtain surface reflectance images of multiple target bands.

[0048] Among them, the first spatial resolution is 10 meters, and the second spatial resolution is 20 meters.

[0049] Specifically, after preprocessing the post-disaster remote sensing images such as radiation calibration, atmospheric correction and orthorectification, the preprocessed remote sensing images can be obtained. The preprocessed remote sensing images include surface reflectance images of the 3rd, 4th and 8th bands with a resolution of 10 meters, and the surface reflectance image of the 11th band with a resolution of 20 meters.

[0050] The spatial resolution of the surface reflectance image of the 11th band with a resolution of 20 meters is resampled to obtain a surface reflectance image of the 11th band with a resolution of 10 meters. The surface reflectance images of the 3rd band, the 4th band and the 8th band with a resolution of 10 meters and the surface reflectance image of the 11th band with a resolution of 10 meters obtained after resampling are superimposed and combined to obtain a combined image. The combined image is cropped using the boundary of the target area to obtain a 4-band surface reflectance image of the target area, wherein the 4-band surface reflectance image can be, for example, a multispectral digital orthophoto map (DOM) with a resolution of 10 meters.

[0051] In this embodiment, the obtained surface reflectance image of the 11th band of the second spatial resolution is spatially resampled to obtain the surface reflectance image of the 11th band of the first spatial resolution, and then the surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution and the surface reflectance image of the 11th band of the first spatial resolution are superimposed to obtain surface reflectance images of multiple target bands, so as to facilitate the subsequent identification of flooded areas based on the surface reflectance images of multiple target bands.

[0052] Exemplarily, based on the above embodiment, the target bands include band 3, band 4, band 8 and band 11. When determining the target index value of the pixel based on the surface reflectance value of the pixel in each target band, the ratio water index value of the pixel can be determined based on the surface reflectance values ​​of the pixel in band 3, band 4, band 8 and band 11, and the difference vegetation index value of the pixel can be determined based on the surface reflectance values ​​of the pixel in band 8 and band 4, and then the ratio water index value and the difference vegetation index value are determined as the target index value.

[0053] At present, among the commonly used water body indices and vegetation indices, the main water body indices used for sensitivity analysis include the Normalized Difference Moisture Stress Index (NDMSI), the Normalized Ponded Water Index (NPDI), the Simple Water Index (SWI), the Water Ratio Index (WRI), the Normalized Difference Water Index (NDWI), etc.; the main vegetation indices used for sensitivity analysis include the Normalized Difference Vegetation Index (NDVI), the Ratio Vegetation Index (RVI), the Enhanced Vegetation Index (EVI), the Difference Vegetation Index (DVI), the Infrared Percentage Vegetation Index (IPVI), the Green Normalized Difference Vegetation Index (GNDVI), etc.

[0054] Combined with the interpreted surface reflectance values ​​of 520 random points representing the flooded areas in each band, it was finally determined that the ratio water index WRI and the difference vegetation index DVI were more sensitive to identifying the flooded areas. Therefore, the ratio water index WRI and the difference vegetation index DVI were used as target indices.

[0055] For each pixel in the post-disaster surface reflectance image, when determining the ratio water index (WRI) of the pixel based on the surface reflectance values ​​of the pixel in the 3rd band, the 4th band, the 8th band and the 11th band, the sum of the surface reflectance values ​​of the pixel in the 3rd band and the 4th band, and the difference between the surface reflectance values ​​of the pixel in the 8th band and the 11th band can be determined, and then the ratio of the sum and the difference can be determined as the ratio water index of the pixel.

[0056] Specifically, the water index (WRI) value of a pixel can be determined by the following formula (1): (1) in, Indicates the green band, that is, the surface reflectance value in the third band. Represents the red band, that is, the surface reflectance value in the 4th band. Indicates the surface reflectance value in the near-infrared band, that is, the 8th band. Represents the surface reflectance value in the shortwave infrared band, that is, the 11th band.

[0057] For each pixel in the post-disaster surface reflectance image, when determining the difference vegetation index of the pixel based on the surface reflectance values ​​of the pixel in the 8th band and the 4th band, the difference between the surface reflectance values ​​of the pixel in the 8th band and the 4th band can be determined as the difference vegetation index of the pixel.

[0058] Specifically, the difference vegetation index DVI value of the pixel can be determined by the following formula (2): (2) Among them, through the above method, the ratio water index WRI value and the difference vegetation index DVI value of each pixel in the post-disaster surface reflectance image can be quickly and accurately calculated.

[0059] In addition, the ratio water index value and the difference vegetation index value are determined as the target index values. Since the ratio water index is more sensitive to water bodies, and the difference vegetation index is more sensitive to vegetation, the accuracy of the identification results can be improved when the flooded areas in the target area are subsequently identified based on the ratio water index and the difference vegetation index.

[0060] Exemplarily, based on the above embodiment, the aforementioned preset index range includes a preset ratio water index range and a preset difference vegetation index range. When determining at least one target pixel corresponding to a target index value within the preset index range in the post-disaster surface reflectance image, it can be achieved in the following manner: Determine a first pixel set corresponding to a ratio water index within a preset ratio water index range in the post-disaster surface reflectance image, and determine a second pixel set corresponding to a difference vegetation index within a preset difference vegetation index range in the post-disaster surface reflectance image, and determine the intersection of all first pixel sets and all second pixel sets as at least one target pixel.

[0061] Specifically, when the current index includes the ratio water index WRI and the difference vegetation index DVI, the corresponding preset index range also includes the preset ratio water index range and the preset difference vegetation index range. For example, the preset ratio water index range can be 0.4-0.7, and the preset difference vegetation index range can be 0.086-0.6.

[0062] By traversing the ratio water index value of each pixel in the post-disaster surface reflectance image, the first pixel set corresponding to the ratio water index value within the preset ratio water index range is screened, and the difference vegetation index value of each pixel in the post-disaster surface reflectance image is traversed to screen the second pixel set corresponding to the difference vegetation index value within the preset difference vegetation index range.

[0063] In order to improve the accuracy of the target pixel finally determined, the intersection between all the first pixel sets and all the second pixel sets may be taken, and the intersection may be determined as at least one target pixel.

[0064] In this embodiment, by jointly determining the target pixel from two dimensions of the ratio water index WRI and the difference vegetation index DVI, the determined target pixel can be made more accurate.

[0065] Exemplarily, based on the above embodiment, when determining the flood area in the target area based on all target pixels, it can also be determined in the following manner: Acquire pre-disaster remote sensing images of the target area, determine pre-disaster surface reflectance images of a first spatial resolution based on the pre-disaster remote sensing images, and perform super-resolution reconstruction on the pre-disaster surface reflectance images of the first spatial resolution to obtain surface reflectance images of a third spatial resolution, where the first spatial resolution is smaller than the third spatial resolution. Based on the surface reflectance images of the third spatial resolution, after determining the cultivated land area in the target area, determine the intersection of the areas corresponding to all target pixels and the cultivated land area as the flood area.

[0066] Specifically, pre-disaster remote sensing images can be understood as remote sensing images taken before the flood occurs. Similar to post-disaster remote sensing images, pre-disaster remote sensing images can be pre-processed by radiometric calibration, atmospheric correction, orthorectification, etc. to obtain pre-processed pre-disaster remote sensing images, which include surface reflectance images of bands 3, 4, and 8 with a spatial resolution of 10 meters, and surface reflectance images of band 11 with a spatial resolution of 20 meters.

[0067] The spatial resolution of the surface reflectance image of the 11th band with a spatial resolution of 20 meters is resampled to obtain a surface reflectance image of the 11th band with a spatial resolution of 10 meters, and the surface reflectance images of the 3rd band, the 4th band and the 8th band with a spatial resolution of 10 meters and the surface reflectance image of the 11th band with a spatial resolution of 10 meters obtained after resampling are superimposed and combined to obtain a pre-disaster combined image, and the pre-disaster combined image is cropped using the boundary of the target area to obtain a pre-disaster surface reflectance image of the target area with a first spatial resolution, wherein the pre-disaster surface reflectance image of the first spatial resolution can be, for example, a multispectral digital orthophoto map (DOM) with a spatial resolution of 10 meters.

[0068] Furthermore, the image super-resolution reconstruction technology can be used to super-resolution the spatial resolution of the pre-disaster surface reflectance image of the first spatial resolution to a third spatial resolution to obtain a surface reflectance image of the third spatial resolution, wherein the third spatial resolution can be, for example, a 2-meter spatial resolution.

[0069] Since the 2-meter-resolution surface reflectance image has a high resolution and can distinguish the surface conditions more clearly, the intelligent remote sensing interpretation technology of cultivated land plots can be used to identify and detect cultivated land plots, obtain the distribution data of cultivated land plots in the target area before the disaster, and thus obtain the cultivated land area.

[0070] In practical applications, after a flood disaster occurs, it is usually necessary to count the affected area of ​​the cultivated land area. The area composed of all target pixels is the area where the flood occurred. Therefore, the area composed of the target pixels and the determined cultivated land area can be further intersected to remove the influence of other land types. After determining the intersection of the area composed of all target pixels and the cultivated land area, the cultivated land area where the flood occurred in the target area can be obtained, and the affected area can be calculated.

[0071] In this embodiment, the cultivated land area in the target area is determined based on the pre-disaster remote sensing image of the target area, and the intersection of the area corresponding to all target pixels and the cultivated land area is determined as the flood area. In this way, the cultivated land area where the flood occurs can be determined, eliminating the influence of other land types, and providing a basis for the subsequent calculation of the effective disaster-affected area.

[0072] Exemplarily, based on the above embodiments, when determining at least one target pixel corresponding to a target index value within a preset index range in a post-disaster surface reflectance image, the target index value of each pixel can be normalized to obtain the normalized target index value of each pixel, and then at least one target pixel corresponding to the normalized target index value within the preset index range in the post-disaster surface reflectance image is determined.

[0073] Specifically, taking the target index including the ratio water index WRI and the difference vegetation index DVI as an example, since the calculation methods of the ratio water index WRI and the difference vegetation index DVI are inconsistent, it is necessary to regularize the two indices separately to adjust the value range of the two indices to between 0 and 1.

[0074] For example, the target index value of each pixel can be normalized based on the following formula (3) to obtain the normalized target index value of each pixel: (3) in, represents the target index value of the pixel, Represents the normalized target index value of the pixel, It represents the minimum target index value of all pixels in the post-disaster surface reflectance image. Represents the maximum value of the target index of all pixels in the post-disaster surface reflectance image.

[0075] It should be understood that after normalizing the target index value of each pixel, the preset index range determined based on the target index value of the random point is also determined based on the normalized value. Therefore, the normalized target index values ​​of each pixel in the post-disaster surface reflectivity image can be traversed, and the pixels corresponding to the normalized target index values ​​within the preset index range can be determined as target pixels.

[0076] In this embodiment, the target index value of each pixel is normalized so that the target index value is adjusted to between 0 and 1, thereby simplifying the amount of calculation and improving the efficiency of determining the target pixel.

[0077] Figure 4 The overall schematic diagram of the flood area identification method provided by the embodiment of the present invention is as follows: Figure 4 As shown, pre-disaster remote sensing images and post-disaster remote sensing images of the target area are obtained, pre-disaster remote sensing images and post-disaster remote sensing images are pre-processed respectively, and after resampling the surface reflectance image of the 11th band with a spatial resolution of 20 meters, the surface reflectance images of the 3rd band, 4th band and 8th band with a spatial resolution of 10 meters and the resampled 11th band are superimposed and spatially cropped to obtain pre-disaster surface reflectance images of multiple target bands and post-disaster surface reflectance images of multiple target bands.

[0078] After visual interpretation of the post-disaster surface reflectance image, multiple random points representing floods and multiple verification points for accuracy verification were obtained. According to the post-disaster surface reflectance image, the ratio water index value and the difference vegetation index value of each pixel can be determined based on the surface reflectance value of each pixel in each target band, and the ratio water index value and the difference vegetation index value are normalized to obtain the normalized ratio water index value and the normalized difference vegetation index value of each pixel.

[0079] The normalized ratio water index value of the random point is determined as the preset ratio water index range, and the normalized difference vegetation index value of the random point is determined as the preset difference vegetation index range. The intersection of the first pixel set corresponding to the ratio water index value in the post-disaster surface reflectance image within the preset ratio water index range and the second pixel set corresponding to the difference vegetation index value in the post-disaster surface reflectance image within the preset difference vegetation index range is determined as the target pixel, and the disaster-stricken area composed of all the target pixels is determined.

[0080] For the pre-disaster surface reflectance image, super-resolution processing was performed on the pre-disaster surface reflectance image to obtain the pre-disaster surface reflectance image with a spatial resolution of 2 meters, and the cultivated land area in the target area was identified from the pre-disaster surface reflectance image with a spatial resolution of 2 meters, so that the intersection of the cultivated land area and the disaster-stricken area composed of all target pixels was determined as the flood area.

[0081] Furthermore, the identification accuracy of the flooded area will be verified through the determined verification points, such as verifying whether these verification points are within the determined flooded area. When the verification passes, it means that the determined flooded area is accurate. If the verification fails, the preset ratio water index range and the preset difference vegetation index range will be readjusted based on the normalized ratio water index value and the normalized difference vegetation index value of the random point to further improve the accuracy of the determination of the flooded area.

[0082] For example, based on the surface reflectance image collected in XX County, XX City, XX Province, the present invention randomly selected 175 verification points for manual visual interpretation as the true value, and established a confusion matrix with the remote sensing recognition result to evaluate the accuracy. Table 1 shows the results of visual interpretation: Table 1

[0083] Among them, TP (True Positive) is the number of samples predicted to be affected and actually are affected; TN (True Negative) is the number of samples predicted to be unaffected and actually are not affected; FP (False Positive) is the number of samples predicted to be affected but actually are not affected, i.e. false positives; FN (False Negative) is the number of samples predicted to be unaffected but actually are affected, i.e. false negatives. The indicators used for accuracy evaluation include Precision, Recall and F1. Precision can be expressed by the following formula (4), Recall can be expressed by the following formula (5), and F1 can be expressed by the following formula (6): (4) (5) (6) After calculation, the recognition accuracy of the flooded area identified by the method of the present invention is 98.02%, the recall rate is 96.12%, and the F1 value is 97.06%.

[0084] The accuracy evaluation results show that the flood area identification method of the present invention can effectively identify flood-affected areas, and can quickly and accurately identify the affected area without field survey samples. When combined with field survey samples, it can also greatly improve the recognition efficiency and ensure the recognition accuracy compared with the traditional visual interpretation method. In actual use, the method described in the present invention can be used to quickly identify flood-affected areas, provide timely data reference for disaster relief guidance, agricultural insurance rapid claims, agricultural credit repayment capacity assessment, etc. After obtaining field survey sample data, the recognition results can be further corrected to improve the accuracy of the final recognition results.

[0085] The flood area identification device provided by the present invention is described below. The flood area identification device described below and the flood area identification method described above can be referenced to each other.

[0086] Figure 5 A schematic diagram of the structure of a flood area identification device provided by an embodiment of the present invention is shown in FIG. Figure 5 As shown, the flood area identification device 500 includes an acquisition module 11 and a determination module 12, wherein: An acquisition module 11 is used to acquire post-disaster remote sensing images of the target area; The acquisition module 11 is further used to acquire post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images; A determination module 12 is used to determine, for each pixel in the post-disaster surface reflectance image, a target index value of the pixel based on the surface reflectance value of the pixel in each target band, where the target index is an index sensitive to flood identification; The determination module 12 is further used to determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectivity image, wherein the preset index range is determined based on the target index value of each random point, and the random point is a point indicating the occurrence of a flood determined in the post-disaster surface reflectivity image; The determination module 12 is further configured to determine the flooded area within the target area based on all the target pixels.

[0087] The flood area identification device provided by the present invention obtains a post-disaster remote sensing image of a target area, and obtains post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing image. For each pixel in the post-disaster surface reflectance image, based on the surface reflectance value of the pixel in each target band, a target index value of the pixel is determined, and the target index is an index sensitive to flood identification. At least one target pixel corresponding to the target index value within a preset index range in the post-disaster surface reflectance image is determined, and the preset index range is determined based on the target index value of each random point, and the random point is a point determined in the post-disaster surface reflectance image that represents the occurrence of a flood, thereby determining the flood area in the target area based on all target pixels. Since the preset index range is determined based on the target index value of the random point where the flood occurs, the screened target pixels are all pixels within the flood area, so that the area extracted based on all the target pixels can be determined as the flood area, which overcomes the problem in the related art that when the flood area is identified through the regional recognition model, the samples need to be labeled by manual survey each time when the regional recognition model is trained, resulting in slow training speed of the regional recognition model and low efficiency of flood area identification. At the same time, it can overcome the problem of low recognition accuracy when the flood area is identified through the regional recognition model due to the possible inconsistency between the geographical scope included in the sample remote sensing image and the geographical scope included in the remote sensing image taken when the flood area is actually identified, thereby improving the accuracy of flood area identification.

[0088] Based on any of the above embodiments, the post-disaster remote sensing image includes surface reflectance images of bands 3, 4 and 8 of a first spatial resolution, and a surface reflectance image of band 11 of a second spatial resolution, and the second spatial resolution is smaller than the first spatial resolution; The acquisition module 11 is specifically used for: Resampling the surface reflectance image of the 11th band of the second spatial resolution to obtain the surface reflectance image of the 11th band of the first spatial resolution; The surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution and the surface reflectance image of the 11th band of the first spatial resolution are superimposed to obtain the surface reflectance images of the multiple target bands.

[0089] Based on any of the above embodiments, the target band includes band 3, band 4, band 8 and band 11; The determining module 12 is specifically used for: Determine the ratio water index of the pixel based on the surface reflectance values ​​of the pixel in the third band, the fourth band, the eighth band and the eleventh band; Determine a difference vegetation index of the pixel based on the respective surface reflectance values ​​of the pixel in the eighth band and the fourth band; The ratio water index and the difference vegetation index are determined as the target index values.

[0090] Based on any of the above embodiments, the determining module 12 is specifically configured to: Determine the sum of the ground reflectance values ​​of the pixel in the third band and the fourth band; Determine the difference between the ground reflectance values ​​of the pixel in the 8th band and the 11th band; Determine the ratio of the sum value to the difference value as the ratio water index of the pixel; The determining module 12 is specifically used for: The difference between the ground reflectance values ​​of the pixel in the 8th band and the 4th band is determined as the difference vegetation index of the pixel.

[0091] Based on any of the above embodiments, the preset index range includes a preset ratio water index range and a preset difference vegetation index range; The determination module 12 is specifically used for: Determine a first pixel set corresponding to the ratio water index within the preset ratio water index range in the post-disaster surface reflectance image; Determine a second pixel set corresponding to the difference vegetation index within the preset difference vegetation index range in the post-disaster surface reflectance image; The intersection of all the first pixel sets and all the second pixel sets is determined as the at least one target pixel.

[0092] Based on any of the above embodiments, the determination module 12 is specifically configured to: Acquire pre-disaster remote sensing images of the target area; Determine a pre-disaster surface reflectance image of a first spatial resolution based on the pre-disaster remote sensing image, and perform super-resolution reconstruction on the pre-disaster surface reflectance image of the first spatial resolution to obtain a surface reflectance image of a third spatial resolution, wherein the first spatial resolution is smaller than the third spatial resolution; Determining the cultivated land area within the target area based on the surface reflectance image of the third spatial resolution; The intersection of the area corresponding to all the target pixels and the cultivated land area is determined as the flood area.

[0093] Based on any of the above embodiments, the determination module 12 is specifically configured to: Normalizing the target index value of each pixel to obtain the normalized target index value of each pixel; At least one target pixel corresponding to a normalized target index value within a preset index range in the post-disaster surface reflectance image is determined.

[0094] Figure 6 A schematic diagram of the physical structure of an electronic device provided by an embodiment of the present invention, such as Figure 6 As shown, the electronic device may include: a processor (processor) 610 , a communication interface (Communications Interface) 620 , a memory (memory) 630 and a communication bus 640 , wherein the processor 610 , the communication interface 620 , and the memory 630 communicate with each other through the communication bus 640 . The processor 610 can call the logic instructions in the memory 630 to execute a method for identifying a flooded area, which method includes: obtaining a post-disaster remote sensing image of the target area; obtaining a post-disaster surface reflectance image of multiple target bands based on the post-disaster remote sensing image; for each pixel in the post-disaster surface reflectance image, determining a target index value of the pixel based on the surface reflectance value of the pixel in each target band, the target index being an index sensitive to flood identification; determining at least one target pixel in the post-disaster surface reflectance image corresponding to a target index value within a preset index range, the preset index range being determined based on the target index value of each random point, the random point being a point in the post-disaster surface reflectance image that is determined to represent a flood; and determining a flooded area within the target area based on all the target pixels.

[0095] In addition, the logic instructions in the above-mentioned memory 630 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0096] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the flood area identification method provided by the above-mentioned methods, which includes: obtaining a post-disaster remote sensing image of the target area; obtaining a post-disaster surface reflectivity image of multiple target bands based on the post-disaster remote sensing image; for each pixel in the post-disaster surface reflectivity image, based on the surface reflectivity value of the pixel in each target band, determining the target index value of the pixel, the target index is an index sensitive to flood identification; determining at least one target pixel corresponding to the target index value in the post-disaster surface reflectivity image that is within a preset index range, the preset index range is determined based on the target index value of each random point, and the random point is a point in the post-disaster surface reflectivity image that is determined to represent the occurrence of a flood; based on all the target pixels, determining the flood area within the target area.

[0097] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the flood area identification method provided by the above-mentioned methods, the method comprising: obtaining a post-disaster remote sensing image of the target area; obtaining a post-disaster surface reflectivity image of multiple target bands based on the post-disaster remote sensing image; for each pixel in the post-disaster surface reflectivity image, determining a target index value of the pixel based on the surface reflectivity value of the pixel in each target band, the target index being an index sensitive to flood identification; determining at least one target pixel in the post-disaster surface reflectivity image corresponding to a target index value within a preset index range, the preset index range being determined based on the target index value of each random point, the random point being a point in the post-disaster surface reflectivity image that is determined to represent a flood; and determining a flood area within the target area based on all the target pixels.

[0098] The device embodiments described above are only illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0099] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0100] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 invention.

Claims

1. A method for identifying flooded areas, characterized in that: include: Obtain post-disaster remote sensing images of the target area; Acquire post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images; For each pixel in the post-disaster surface reflectance image, based on the surface reflectance value of the pixel in each target band, determine a target index value of the pixel, the target index being an index sensitive to flood identification; Determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image, wherein the preset index range is determined based on the target index value of each random point, and the random point is a point indicating the occurrence of a flood determined in the post-disaster surface reflectance image; Based on all the target pixels, a flooded area within the target area is determined.

2. The flood area identification method according to claim 1, characterized in that: The post-disaster remote sensing images include surface reflectance images of bands 3, 4 and 8 of a first spatial resolution, and a surface reflectance image of band 11 of a second spatial resolution, wherein the second spatial resolution is smaller than the first spatial resolution; The step of acquiring post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images includes: Resampling the surface reflectance image of the 11th band of the second spatial resolution to obtain the surface reflectance image of the 11th band of the first spatial resolution; The surface reflectance images of the 3rd band, the 4th band and the 8th band of the first spatial resolution and the surface reflectance image of the 11th band of the first spatial resolution are superimposed to obtain the surface reflectance images of the multiple target bands.

3. The flood area identification method according to claim 1, characterized in that: The target bands include band 3, band 4, band 8 and band 11; Determining the target index value of the pixel based on the surface reflectance value of the pixel in each target band includes: Determine the ratio water index of the pixel based on the surface reflectance values ​​of the pixel in the third band, the fourth band, the eighth band and the eleventh band; Determine a difference vegetation index of the pixel based on the respective surface reflectance values ​​of the pixel in the eighth band and the fourth band; The ratio water index and the difference vegetation index are determined as the target index values.

4. The flood area identification method according to claim 3, characterized in that: The determining of the ratio water index of the pixel based on the surface reflectance values ​​of the pixel in the third band, the fourth band, the eighth band and the eleventh band, comprises: Determine the sum of the ground reflectance values ​​of the pixel in the third band and the fourth band; Determine the difference between the ground reflectance values ​​of the pixel in the 8th band and the 11th band; Determine the ratio of the sum value to the difference value as the ratio water index of the pixel; The step of determining the difference vegetation index of the pixel based on the surface reflectance values ​​of the pixel in the eighth band and the fourth band, comprises: The difference between the ground reflectance values ​​of the pixel in the 8th band and the 4th band is determined as the difference vegetation index of the pixel.

5. The flood area identification method according to claim 3, characterized in that: The preset index range includes a preset ratio water index range and a preset difference vegetation index range; The step of determining at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image includes: Determine a first pixel set corresponding to the ratio water index within the preset ratio water index range in the post-disaster surface reflectance image; Determine a second pixel set corresponding to the difference vegetation index within the preset difference vegetation index range in the post-disaster surface reflectance image; The intersection of all the first pixel sets and all the second pixel sets is determined as the at least one target pixel.

6. The flood area identification method according to claim 5, characterized in that: Determining the flood area within the target area based on all the target pixels includes: Acquire pre-disaster remote sensing images of the target area; Determine a pre-disaster surface reflectance image of a first spatial resolution based on the pre-disaster remote sensing image, and perform super-resolution reconstruction on the pre-disaster surface reflectance image of the first spatial resolution to obtain a surface reflectance image of a third spatial resolution, wherein the first spatial resolution is smaller than the third spatial resolution; Determining the cultivated land area within the target area based on the surface reflectance image of the third spatial resolution; The intersection of the area corresponding to all the target pixels and the cultivated land area is determined as the flood area.

7. The flood area identification method according to any one of claims 1 to 6, characterized in that: The step of determining at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectance image includes: Normalizing the target index value of each pixel to obtain the normalized target index value of each pixel; At least one target pixel corresponding to a normalized target index value within a preset index range in the post-disaster surface reflectance image is determined.

8. A flood area identification device, characterized in that: include: An acquisition module is used to obtain post-disaster remote sensing images of the target area; The acquisition module is further used to acquire post-disaster surface reflectance images of multiple target bands based on the post-disaster remote sensing images; A determination module, for determining, for each pixel in the post-disaster surface reflectance image, a target index value of the pixel based on the surface reflectance value of the pixel in each target band, wherein the target index is an index sensitive to flood identification; The determination module is further used to determine at least one target pixel corresponding to a target index value within a preset index range in the post-disaster surface reflectivity image, wherein the preset index range is determined based on the target index value of each random point, and the random point is a point indicating the occurrence of a flood determined in the post-disaster surface reflectivity image; The determination module is further used to determine the flooded area within the target area based on all the target pixels.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the flood-hit area identification method according to any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the flood-damaged area identification method according to any one of claims 1 to 7 is implemented.

Images