Flood disaster range extraction method

Abstract

The invention discloses a method for extracting a flood disaster range, and relates to the technical field of flood monitoring. The method comprises the following steps: obtaining a remote sensing image of an agricultural flood disaster range through remote sensing monitoring technology, marking an identifiable area, obtaining a grayscale-gradient co-occurrence matrix of the identifiable area and a background area of ​​the flood disaster range, calculating grayscale values ​​between adjacent pixel points in the identifiable area, analyzing grayscale value ratios between adjacent pixel points at different positions, determining an abnormal area in the image, extracting an image texture uniform deviation value, a cloud index floating degree value, and a real-time rainfall density index from image information for the abnormal area, constructing a data testing model, and determining the flood disaster range according to the model testing result. This method not only makes the monitoring and identification of the flood disaster more automated, and helps to improve efficiency, but also, when the flood disaster range is determined, emergency response and preparation can be initiated more quickly, which helps to minimize the impact of the disaster.

Description

Technical Field

[0001] The invention relates to the technical field of flood monitoring, and in particular to a method for extracting a flood disaster range. Background Art

[0002] Flood disaster refers to the phenomenon of widespread inundation caused by the rapid increase of surface water due to rainfall, snowmelt, typhoons, rainstorms, etc., and the inability to quickly remove water from low-lying areas. Flood disasters may have serious impacts on humans, animals, plants and infrastructure, and are a common and dangerous natural disaster. The method of extracting the scope of flood disasters usually involves remote sensing technology. Satellite remote sensing images, especially high-resolution satellite images, can be used to capture the impact range of flood events at different times. Different bands of remote sensing images, such as visible light, infrared and microwave, are used to detect and extract water body information. Change detection technology is used to compare remote sensing images at different time points to find out the area where the water body expands. However, for areas with frequent rainfall, weather conditions may cause cloud occlusion in satellite images. Cloud occlusion may hinder the timely monitoring of the scope of flood disasters, and may also cover up the real situation in the disaster area, thereby affecting the accurate extraction of the flood scope, making it impossible to accurately obtain flood disaster information through remote sensing technology. Summary of the invention

[0003] The purpose of the present invention is to provide a method for extracting the scope of flood disasters to solve the shortcomings of the background technology.

[0004] In order to achieve the above object, the present invention provides the following technical solution: a method for extracting the scope of flood disaster, comprising the following steps:

[0005] S1: Obtain a remote sensing image of the scope of agricultural flood disasters through remote sensing monitoring technology, perform grayscale processing on the image, and mark the identifiable area, where the identifiable area is the flood disaster scope area;

[0006] S2: Obtain the grayscale-gradient co-occurrence matrix of the identifiable area and the background area of ​​the flood disaster range, calculate the grayscale values ​​between adjacent pixels in the identifiable area, analyze the grayscale value ratios between adjacent pixels at different positions, and determine the abnormal area in the image;

[0007] S3: For abnormal areas, extract the image texture uniform deviation value, cloud index floating degree value and real-time rainfall density index in the image information, build a data testing model, and determine the scope of flood disasters based on the model testing results.

[0008] In a preferred embodiment, in S2, the gray value ratio between adjacent pixels at different positions is analyzed to determine the abnormal area in the image, including:

[0009] The number of pixels in the identifiable area of ​​the grayscale image is marked as N, the number of pixels whose real-time grayscale values ​​between adjacent pixels at the same position in the identifiable area are greater than the standard grayscale value is obtained and marked as n, and the probability of the number of pixels whose real-time grayscale values ​​between adjacent pixels at different positions in the identifiable area are greater than the standard grayscale value is calculated by 2n / N.

[0010] In a preferred embodiment, the quantity probability is compared with the standard probability threshold. If the quantity probability is greater than the standard probability threshold, the identifiable area is an abnormal area; if the abnormal probability is less than or equal to the standard probability threshold, the identifiable area is a normal area.

[0011] In a preferred embodiment, the logic for obtaining the uniform deviation value is as follows:

[0012] The grayscale image of the flood disaster area is divided into multiple different small blocks, and the pixels in each small block constitute a local area. For each small block, the mean x and standard deviation u of the texture feature are calculated. For all small blocks, the number s of all small blocks in the grayscale image is obtained, and the uniform deviation value is calculated. The calculation expression is: In the formula, mc k is the average deviation value.

[0013] In a preferred embodiment, the logic for obtaining the cloud index floating degree value is as follows:

[0014] Obtain the remote sensing data obtained through remote sensing monitoring technology feedback, obtain the light reflectance sf, cloud height dr, cloud shielding degree gt in the remote sensing data, and obtain the set expected light reflectance, cloud height, and cloud shielding degree, calculate the light reflectance difference sd, cloud height difference dq, cloud shielding degree difference gh, calculate the cloud index floating degree value, and the calculation expression is: Where, dk y It is the floating value of cloud index.

[0015] In a preferred embodiment, the logic for obtaining the rainfall density index is as follows:

[0016] Get the number of rainfalls that occurred in the m time period and calculate the rainfall frequency rg k , and the rainfall in the time period m, calculate the rainfall intensity mh k , calculate the rainfall density index, the calculation expression is: In the formula, nk t is the rainfall density index, jt s is the rainfall distribution area, and k is any time point in the time period m.

[0017] In a preferred embodiment, a data testing model is constructed, and the scope of the flood disaster is determined according to the model testing results;

[0018] The uniform deviation value, cloud index floating degree value and rainfall density index are input into the pre-built data test model for comprehensive calculation to calculate the risk coefficient of flood disaster range in the abnormal area. The calculation expression is: In the formula, qt y is the risk factor, mc k is the average deviation value, dk y is the floating value of cloud index, nk t is the rainfall density index, a1, a2, a3 are the proportional coefficients of uniform deviation value, cloud index floating degree value and rainfall density index, and a2>a3>a1>0.

[0019] In a preferred embodiment, the risk coefficient of the flood disaster range in the abnormal area is compared with the risk threshold. If the risk coefficient is greater than or equal to the risk threshold, a warning signal is issued; if the risk coefficient is less than the risk threshold, no warning signal is issued.

[0020] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0021] 1. The present invention obtains remote sensing images of agricultural flood disaster areas through remote sensing monitoring technology, marks identifiable areas, obtains the grayscale-gradient co-occurrence matrix of the identifiable area and the background area of ​​the flood disaster area, calculates the grayscale value between adjacent pixels in the identifiable area, analyzes the grayscale value ratio between adjacent pixels at different positions, and determines the abnormal area in the image. It can not only accurately identify and mark potential flood disaster areas in the image, but also help to provide timely monitoring and evaluation of farmland and agricultural resources.

[0022] 2. The present invention extracts the image texture uniform deviation value, the cloud index floating degree value and the real-time rainfall density index in the image information of the abnormal area, constructs a data testing model, and determines the scope of the flood disaster according to the model test results. This not only makes the monitoring and identification of flood disasters more automated and helps to improve efficiency, but also, when the scope of the flood disaster is determined, emergency response and preparation can be initiated more quickly, which helps to minimize the impact of the disaster. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0024] Figure 1 The figure is a flow chart of the method of the present invention. DETAILED DESCRIPTION

[0025] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments 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] For examples, see Figure 1 As shown, the method for extracting the flood disaster range described in this embodiment includes the following steps:

[0027] S1: Obtain a remote sensing image of the scope of agricultural flood disasters through remote sensing monitoring technology, perform grayscale processing on the image, and mark the identifiable area, where the identifiable area is the flood disaster scope area;

[0028] S2: Obtain the grayscale-gradient co-occurrence matrix of the identifiable area and the background area of ​​the flood disaster range, calculate the grayscale values ​​between adjacent pixels in the identifiable area, analyze the grayscale value ratios between adjacent pixels at different positions, and determine the abnormal area in the image;

[0029] S3: For abnormal areas, extract the image texture uniform deviation value, cloud index floating degree value and real-time rainfall density index in the image information, build a data testing model, and determine the scope of flood disasters based on the model testing results.

[0030] Among them, in S1, remote sensing monitoring technology is used to obtain remote sensing images of agricultural flood disaster ranges, which are grayed and processed for identification, and identifiable areas are marked. The identifiable areas are flood disaster range areas, mainly including:

[0031] Remote sensing image acquisition: Obtain high-resolution remote sensing images, such as satellite images or aerial images. Make sure the images cover the farmland area to be monitored.

[0032] Image preprocessing: Preprocessing of remote sensing images, including atmospheric correction, geometric correction and image enhancement, etc. It can improve the quality and usability of images.

[0033] Grayscale processing: Grayscale converts color images into black and white images, removes color information and retains only grayscale information, which helps to simplify the image processing process.

[0034] For an RGB image, the RGB value of each pixel can be converted to a grayscale value using the following formula: Gray = 0.3*R + 0.59*G + 0.11*B.

[0035] For other color spaces (such as HSV, Lab, etc.), grayscale processing can also be performed according to their brightness.

[0036] Smoothing: Smoothing operation helps to enhance the noise and details in the image. Commonly used smoothing filters include mean-assisted and Gaussian-assisted.

[0037] Mean Assist: An instruction that replaces the value of each pixel with the surrounding pixels.

[0038] Gaussian Tip: Use a Gaussian kernel to soften the image, retaining more image details while removing noise.

[0039] Threshold segmentation: Convert the grayscale image to a binary image and separate the water body from the non-water area. Use an appropriate threshold selection method, such as global threshold or adaptive threshold.

[0040] Morphological Processing: Perform morphological processing such as dilation and erosion on binary images to remove noise, connect water areas, and fill small depressions.

[0041] Flood area identification: Image segmentation techniques, such as region growing and connected region analysis, are used to identify flood areas in processed images.

[0042] Mark identifiable areas: Mark the flooded areas on the original remote sensing image, using borders or color markings.

[0043] Verification and precision assessment: Use field survey data or other reliable ground observation data to verify the identification results and assess their precision and accuracy.

[0044] Visualization and Reporting: Visualize identification results and generate reports for deeper analysis or use in emergency response.

[0045] It should be noted that the specific methods and parameter selection in the above steps may need to be adjusted according to the characteristics of the actual data and the application scenario. When processing large-scale remote sensing image data, deep learning methods such as convolutional neural networks (CNNs) can also be considered to improve recognition accuracy.

[0046] In S2, the grayscale-gradient co-occurrence matrix of the identifiable area and the background area of ​​the flood disaster range is obtained, and the grayscale values ​​between adjacent pixels in the identifiable area are calculated, specifically:

[0047] Acquire pre-processed Sentinel-2 remote sensing images to ensure coverage of all monitored flood-affected areas.

[0048] Define the region of interest (ROI) where the area and flood hazard background area can be identified.

[0049] GLCM is calculated using grayscale images. GLCM represents the spatial distribution relationship of pixels of different grayscale levels in an image. Common statistical features include the angle of the co-occurrence matrix (0 degrees, 45 degrees, 90 degrees, 135 degrees), contrast between grayscale levels, energy, entropy, etc.

[0050] Using the statistical features in GLCM, the grayscale value information between adjacent pixels in the identifiable area is calculated. This can include calculating texture features such as contrast, energy, etc.

[0051] The statistical characteristics of the calculated grayscale-gradient co-occurrence matrix can be visualized or used for further image analysis, texture feature extraction, etc.

[0052] Verify that the features extracted by GLCM are related to the actual flood situation. Comparison can be made through field surveys, other remote sensing data or known flood maps.

[0053] It should be noted that GLCM is a gray level co-occurrence matrix, which is mainly used to describe the texture features of images. In flood monitoring, these features can be used to find image texture information related to flood disasters. The selection of appropriate gray level co-occurrence matrix parameters and features, as well as the appropriate image segmentation method, may need to be adjusted according to specific scenarios and needs.

[0054] Analyze the gray value ratio between adjacent pixels at different positions to determine the abnormal area in the image, mainly including:

[0055] The number of pixels in the identifiable area of ​​the grayscale image is marked as N, the number of pixels whose real-time grayscale values ​​between adjacent pixels at the same position in the identifiable area are greater than the standard grayscale value is obtained and marked as n, the probability of the number of pixels whose real-time grayscale values ​​between adjacent pixels at different positions in the identifiable area are greater than the standard grayscale value is calculated by 2n / N, and the number probability is compared with the standard probability threshold. If the number probability is greater than the standard probability threshold, it means that the identifiable area may be an abnormal area; if the abnormal probability is less than or equal to the standard probability threshold, it means that the identifiable area may be a normal area.

[0056] In S3, for abnormal areas, the image texture uniform deviation value, cloud index floating degree value and real-time rainfall density index in the image information are extracted to build a data test model, and the scope of flood disaster is determined according to the model test results;

[0057] In image processing and computer vision, image texture uniformity deviation usually refers to a measure of the uniformity or consistency of texture in an image.

[0058] The uniform deviation value is an indicator used to represent the uniformity of image texture, which is usually calculated by statistical analysis of local textures in the image;

[0059] The logic of obtaining the uniform deviation value is as follows: divide the grayscale image into small blocks or windows, and the pixels in each small block constitute a local area. In each small block, select a texture feature to describe the texture of the area, which can be a statistical feature of the gray-level co-occurrence matrix (GLCM), such as energy or correlation, or other texture features, such as gradient, variance, etc. For each small block, calculate the mean x and standard deviation u of the selected texture feature. For all small blocks, obtain the number s of all small blocks in the grayscale image, and calculate the uniform deviation value. The calculation expression is: In the formula, mc k is the average deviation value;

[0060] The larger the uniform deviation value, the more uneven or inconsistent the local texture in the image. When evaluating abnormal areas in an image, an increase in the uniform deviation value may have the following main effects:

[0061] Abnormal region detection: Large uniform deviation values ​​may reflect that the texture of some areas in the image is very different, which may contain disasters or abnormal conditions. In image processing, texture inhomogeneity is often associated with abnormal areas in the image (such as disasters, pollution, destruction, etc.).

[0062] Distinguishing between disaster and normal areas: Abnormal areas are often quite different from the surrounding environment, and this difference can be characterized by the uniform deviation value. A larger uniform deviation value can help distinguish disaster areas from normal areas, because the texture of disaster areas is usually affected and appears uneven.

[0063] Indicators of texture changes: The increase in the uniform deviation value can be regarded as an indicator of texture changes in the image. In disaster monitoring, some abnormal conditions may cause drastic changes in the surface texture, which can be quantified by the uniform deviation value.

[0064] Improve the sensitivity of anomaly detection: By taking uniform deviation values ​​into account, the sensitivity of the anomaly detection algorithm to texture inhomogeneities in the image can be increased. This can be particularly useful for finding small-scale anomaly regions or local anomalies.

[0065] It should be noted that the uniform deviation value, as a feature, usually needs to be combined with other image features and contextual information for comprehensive analysis. In disaster monitoring, using multiple features to evaluate the properties of abnormal areas, such as color, texture, shape, etc., can improve the accurate identification of disasters. In addition, for different types of disasters, it may be necessary to adjust and optimize the calculation method and threshold of the uniform deviation value.

[0066] The cloud index fluctuation value is a metric used to describe the extent or density of clouds in imagery or satellite data. The cloud index can be based on a variety of factors, including reflectivity in optical remote sensing data, cloud height, cloud obscuration, etc. The cloud index fluctuation value may refer to the degree of cloud change or fluctuation.

[0067] The logic for obtaining the floating degree value of the cloud index is as follows: obtain the remote sensing data obtained through remote sensing monitoring technology monitoring feedback, obtain the light reflectivity sf, cloud height dr, and cloud shielding degree gt in the remote sensing data, obtain the set expected light reflectivity, cloud height, and cloud shielding degree, calculate the light reflectivity difference sd, cloud height difference dq, and cloud shielding degree difference gh, calculate the floating degree value of the cloud index, and the calculation expression is: Where, dk y is the floating value of cloud index;

[0068] The larger the floating value of the cloud index, the more likely it is to have the following main effects on the assessment of whether the abnormal area in the image is a disaster area:

[0069] Remote sensing image clarity: An increase in the floating value of the cloud index may indicate that the distribution and occlusion of clouds in the image are greater. This will cause the clarity of the remote sensing image to decrease, making the visibility of abnormal areas less.

[0070] Abnormal area detection challenges: In the case of large cloud cover, the detection of abnormal areas becomes more difficult. Large cloud cover may obscure the true situation of the surface, affecting the performance of the disaster area. Abnormal areas may be confused or obscured, increasing the difficulty of detecting and analyzing disaster areas.

[0071] Difficulty in identifying disaster areas: The presence of clouds may cause false reflections or shadows in the image, which makes it more difficult to identify disaster areas. Disaster areas may be misclassified as cloud shadows or other noise.

[0072] Shortened monitoring time window: An increase in the floating value of the cloud index may indicate that the dynamic changes of the cloud are more obvious, resulting in the information in the image being limited by the time window. When monitoring disaster areas, a shorter time window may be needed to capture abnormal conditions to reduce the impact of clouds.

[0073] Reduced data availability: The presence of clouds may cause a portion of satellite or aerial imagery to be distorted or unavailable, reducing the effective data available for assessing the disaster area. This may limit the full assessment of the anomaly area.

[0074] The real-time rainfall density index refers to the rainfall intensity in a short period of time in the monitoring area, describing the distribution of rainfall in the geographical area, including the spatial distribution and changes of rainfall;

[0075] The logic for obtaining the rainfall density index is: obtain the number of rainfalls that occur within a time period of m and calculate the rainfall frequency rg k , and the rainfall in the time period m, calculate the rainfall intensity mh k Satellite remote sensing can provide rainfall information on a large area of ​​the surface. Through satellite observation, rainfall distribution maps of large areas can be obtained, and rainfall distribution areas can be obtained based on rainfall distribution maps. s , calculate the rainfall density index, the calculation expression is: In the formula, nk t is the rainfall density index, k is any time point in the time period m;

[0076] The higher the rainfall density index, the more important it is to assess whether the abnormal area in the image is a disaster area. The following are some possible effects:

[0077] Disaster risk assessment: An increase in the rainfall density index may indicate that the intensity or frequency of rainfall in the current area is high. Heavy rain or continuous rainfall events may lead to natural disasters such as floods and mudslides, so a higher rainfall density index may increase the risk of disasters.

[0078] Flooding: High rainfall density is usually associated with increased flood risk. In flood events, the intensity and frequency of rainfall are important factors in determining flood severity. Assessing rainfall density helps understand the potential spatial distribution and variation of floods, thereby better predicting and responding to flood disasters.

[0079] Landslide risk: High rainfall intensity may lead to an increased risk of landslides. Landslides often occur after heavy rainfall, as heavy rain can saturate the soil, increasing the likelihood of landslides. An increase in the Rainfall Intensity Index may indicate a potential risk of landslides.

[0080] Disaster emergency response: High rainfall density may require enhanced emergency response to disasters. In the case of high rainfall density, emergency management departments may need to take more urgent measures to mitigate potential disaster impacts, including evacuation, alarm, resource dispatch, etc.

[0081] Impact on image quality: Heavy rainfall may cause cloud cover, reduced visibility, etc., which may affect the quality of remote sensing images. When evaluating abnormal areas in images, if the rainfall density is high, it may be necessary to consider the impact of weather conditions on remote sensing data and adopt corresponding processing methods or multi-source data fusion.

[0082] In general, the larger the rainfall density index, the higher the disaster risk faced by the region, which may require more attention and effective monitoring, early warning, and prevention measures. When assessing whether an abnormal area in an image is a disaster area, information on rainfall density helps to fully understand the potential impact of a disaster.

[0083] The uniform deviation value, cloud index floating degree value and rainfall density index are input into the pre-built data test model for comprehensive calculation to calculate the risk coefficient of flood disaster range in the abnormal area. The calculation expression is: In the formula, qt y is the risk factor, mc k is the average deviation value, dk y is the floating value of cloud index, nk t is the rainfall density index, a1, a2, a3 are the proportional coefficients of uniform deviation value, cloud index floating degree value, and rainfall density index, and a2>a3>a1>0;

[0084] The risk coefficient of the flood disaster range in the abnormal area is compared with the risk threshold. If the risk coefficient is greater than or equal to the risk threshold, a warning signal is issued. After receiving the warning signal, the staff should promptly determine the scope of the flood disaster and respond to the emergency quickly and orderly to protect people’s lives and property safety to the greatest extent; if the risk coefficient is less than the risk threshold, no warning signal is issued.

[0085] In this embodiment, remote sensing monitoring technology is used to obtain remote sensing images of agricultural flood disaster ranges, which are grayed and processed for identification, and identifiable areas are marked. The identifiable areas are flood disaster range areas, and the grayscale-gradient co-occurrence matrix of the identifiable areas and the background areas of the flood disaster range is obtained. The grayscale values ​​between adjacent pixels in the identifiable areas are calculated, and the grayscale value ratios between adjacent pixels at different positions are analyzed to determine the abnormal areas in the image. For the abnormal areas, the image texture uniform deviation value, the cloud index floating degree value, and the real-time rainfall density index in the image information are extracted, and a data test model is constructed to determine the flood disaster range according to the model test results. The monitoring and identification of flood disasters can be more automated, which helps to improve efficiency, especially in the monitoring and analysis of large areas. At the same time, when the flood disaster range is determined, emergency response and preparation can be initiated more quickly, including evacuation, rescue, resource scheduling and other measures, which helps to minimize the impact of the disaster.

[0086] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0087] It should be understood that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. A and B can be singular or plural. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship, but it may also indicate an "and / or" relationship. Please refer to the context for specific understanding.

[0088] In this application, "at least one" means one or more, and "more than one" means two or more. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b, or c can be represented by: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0089] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0090] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0091] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0092] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0093] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0094] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0095] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several 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 methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROM), random access memories (RAM), magnetic disks or optical disks.

[0096] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A method for extracting the scope of flood disaster, characterized by: The following steps are involved: S1: Obtain a remote sensing image of the scope of agricultural flood disasters through remote sensing monitoring technology, perform grayscale processing on the image, and mark the identifiable area, where the identifiable area is the flood disaster scope area; S2: Obtain the grayscale-gradient co-occurrence matrix of the identifiable area and the background area of ​​the flood disaster range, calculate the grayscale value between adjacent pixels in the identifiable area, analyze the grayscale value ratio between adjacent pixels at different positions, and determine the abnormal area in the image; Step S2 specifically includes: marking the number of pixels in the identifiable area in the grayscale image as N, obtaining the number of pixels whose real-time grayscale values ​​between adjacent pixels at the same position in the identifiable area are greater than the standard grayscale value, marking it as n, and calculating the probability of the number of pixels whose real-time grayscale values ​​between adjacent pixels at different positions in the identifiable area are greater than the standard grayscale value by 2n / N; Compare the quantity probability with the standard probability threshold. If the quantity probability is greater than the standard probability threshold, the identifiable area is an abnormal area; if the abnormal probability is less than or equal to the standard probability threshold, the identifiable area is a normal area. S3: For abnormal areas, extract the image texture uniform deviation value, cloud index floating degree value and real-time rainfall density index in the image information, build a data testing model, and determine the scope of flood disasters based on the model test results; The logic for obtaining the average deviation value is as follows: The grayscale image of the flood disaster area is divided into multiple different small blocks, and the pixels in each small block constitute a local area. For each small block, the mean x and standard deviation u of the texture feature are calculated. For all small blocks, the number s of all small blocks in the grayscale image is obtained, and the uniform deviation value is calculated. The calculation expression is: In the formula, mc k is the average deviation value; The logic for obtaining the floating value of the cloud index is as follows: Obtain the remote sensing data obtained through remote sensing monitoring technology feedback, obtain the light reflectance sf, cloud height dr, cloud shielding degree gt in the remote sensing data, and obtain the set expected light reflectance, cloud height, and cloud shielding degree, calculate the light reflectance difference sd, cloud height difference dq, cloud shielding degree difference gh, calculate the cloud index floating degree value, and the calculation expression is: Where, dk y is the floating value of cloud index; The logic for obtaining the rainfall density index is as follows: Get the number of rainfalls that occurred in the m time period and calculate the rainfall frequency rg k , and the rainfall in the time period m, calculate the rainfall intensity mh k , calculate the rainfall density index, the calculation expression is: In the formula, nk t is the rainfall density index, jt s is the rainfall distribution area, k is any time point in the time period m; Constructing a data test model, and determining the scope of flood disasters according to the model test results, further includes: inputting the uniform deviation value, the cloud index floating degree value, and the rainfall density index into the pre-constructed data test model for comprehensive calculation, and calculating the risk coefficient of the flood disaster scope in the abnormal area, and the calculation expression is: In the formula, qt y is the risk factor, mc k is the average deviation value, dk y is the floating value of cloud index, nk t is the rainfall density index, a1, a2, a3 are the proportional coefficients of uniform deviation value, cloud index floating degree value, and rainfall density index, and a2>a3>a1>0; The risk coefficient of the flood disaster range in the abnormal area is compared with the risk threshold. If the risk coefficient is greater than or equal to the risk threshold, a warning signal is issued; if the risk coefficient is less than the risk threshold, no warning signal is issued.

Images