A dynamic identification method and system based on ecological restoration of abandoned mines

Abstract

The present invention discloses a dynamic identification method and system based on abandoned mine ecological restoration. Through the proposed dynamic identification method of mine ecological restoration, the RGB value C in any pixel area in the remote sensing image is used to identify the abandoned mine ecological restoration. ij As the independent variable, the reference value of the influencing factor in the remote sensing image acquisition process is used as the dependent variable to build a regression model and calculate the RGB value C of the pixel area in the remote sensing image. mn , thereby obtaining the correction coefficient ζ, correcting each pixel area in the remote sensing image to be identified, extracting the normalized vegetation index NDVI of the corrected remote sensing image, and thus completing the dynamic identification of the ecological restoration of abandoned mines. This can reduce the impact of the deviation between the obtained vegetation area image and the actual vegetation area due to interference factors such as the external environment and temperature, improve the accuracy of the dynamic identification of the ecological restoration of abandoned mines, and thus improve the accuracy of the assessment of the degree of ecological restoration.

Description

Technical Field

[0001] The present invention relates to the technical field of mine ecological restoration effect evaluation, and in particular to a dynamic identification method and system based on abandoned mine ecological restoration. Background Art

[0002] Mine ecological restoration refers to restoring ecosystems damaged by mining to a state close to their pre-mining natural state, reconstructing them to a state suitable for human use, or restoring them to another state that is harmonious with the surrounding environment. Mine ecological restoration primarily involves four components: topographic remodeling, soil reconstruction, vegetation restoration, and landscape reconstruction. Mine ecological restoration is a dynamic process, and its effectiveness will change over time.

[0003] At present, in the dynamic identification process of ecological restoration, remote sensing images of the mining area are obtained and analyzed, and the coverage ratio of the vegetation area to the mining area in the image is calculated to evaluate the degree of ecological restoration. When acquiring remote sensing images, due to various interference factors such as the external environment and temperature, there will be a deviation between the obtained vegetation area image and the actual vegetation area, which affects the assessment of the degree of ecological restoration and cannot accurately realize the dynamic identification of abandoned mine ecological restoration. To this end, we propose a dynamic identification method and system based on abandoned mine ecological restoration. Summary of the Invention

[0004] The main purpose of the present invention is to provide a dynamic identification method and system based on ecological restoration of abandoned mines, which can effectively solve the problems in the background technology.

[0005] To achieve the above object, the technical solution adopted by the present invention is:

[0006] A dynamic identification method based on abandoned mine ecological restoration includes the following steps:

[0007] Step 1: Collect multiple sets of remote sensing images of the mine area to be evaluated, and obtain the RGB value C of any pixel area in each remote sensing image. ij , where i is the number of the remote sensing image, and j is the number of the pixel area in the i-th remote sensing image;

[0008] Step 2: determining the influencing factors in the process of acquiring the remote sensing image, and collecting reference values ​​of the influencing factors in the process of acquiring the remote sensing image;

[0009] Step 3: Take the RGB value C in any pixel area of ​​the remote sensing image ij As the dependent variable, a regression model is constructed with the reference values ​​of the influencing factors in the remote sensing image acquisition process as independent variables. The expression of the regression model is: ; Among them, X1 is the reference value of the first influencing factor, X k is the reference value of the kth influencing factor;

[0010] Step 4: Determine the remote sensing image to be identified, select n pixel areas in the remote sensing image, and obtain the RGB values ​​C of the n pixel areas in the remote sensing image to be identified. n , and calculate the RGB value C of n pixel areas in the remote sensing image according to the regression model mn , where m=1,2,...,i; n=1,2,...,j;

[0011] Step 5: The RGB measurement value C of the nth pixel area in the remote sensing image to be identified is n and the calculated value C mn The mean of the ratios is used as the correction coefficient ρ to calculate the correction coefficient value, wherein the calculation formula of the correction coefficient is: ; Step six, according to the correction coefficient obtained in step five, correct each pixel area in the remote sensing image to be identified, obtain the corrected remote sensing image, and extract the normalized vegetation index NDVI of the corrected remote sensing image, thereby completing the dynamic identification of the ecological restoration of abandoned mines.

[0012] Furthermore, the method for obtaining the pixel area in step 1 is:

[0013] Determine the boundary contours of remote sensing images and adjust multiple sets of remote sensing images of the mining area to be evaluated to a uniform size;

[0014] Place the remote sensing image in the same quadrant of the plane coordinate system and divide the entire remote sensing image into grids with a step size of ε;

[0015] The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis, and the remote sensing image area covered by the grid is the pixel area with the corresponding number.

[0016] Furthermore, the influencing factors in the remote sensing image acquisition process in step 2 are determined according to the remote sensing image acquisition method. Common remote sensing image acquisition methods include acquisition through remote sensing satellites, remote sensing acquisition through aircraft, and remote sensing acquisition through drones.

[0017] Furthermore, in step three, the number of independent variables of the regression model is equal to the number of influencing factors in the remote sensing image acquisition process.

[0018] Furthermore, the value of the step length ε is inversely proportional to the resolution of the remote sensing image and is determined by an empirical formula, wherein the calculation formula of the step length ε is: ; Wherein, λ is a constant coefficient, and the value range of λ is (0,0.5]; p is the resolution value of the remote sensing image; Es is the scale value of the remote sensing image placed in the plane coordinate system.

[0019] A dynamic identification system based on abandoned mine ecological restoration, including:

[0020] An image acquisition module is used to collect remote sensing images of the mine area to be evaluated and obtain the RGB value of any pixel area in the remote sensing image;

[0021] The data acquisition module is used to obtain reference values ​​of various factors affecting the accuracy of remote sensing image acquisition during the remote sensing image acquisition process of the mining area to be evaluated;

[0022] The data processing module is used to construct a regression model, obtain a model relationship between the reference value of each influencing factor of the remote sensing image and the RGB value in the pixel area, and obtain the RGB value of the pixel area in the remote sensing image according to the model relationship;

[0023] a data analysis module, the data analysis module being communicatively connected to the image acquisition module and the data processing module, and configured to receive the calculation results of the RGB values ​​within any pixel region in the remote sensing image and the RGB values ​​of the pixel region in the remote sensing image calculated by the regression model, and calculate the correction coefficient of the remote sensing image to be identified based on the obtained RGB values;

[0024] An image correction module is used to correct each pixel area in the remote sensing image to be identified and obtain a corrected remote sensing image;

[0025] The image extraction module is used to extract the normalized vegetation index NDVI from the corrected remote sensing image, thereby dynamically identifying the ecological restoration of abandoned mines.

[0026] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor.

[0027] Furthermore, the operating steps of the system are as follows:

[0028] Step 1) collect remote sensing images of the mine area to be evaluated through the image acquisition module, determine the boundary contours of the remote sensing images, adjust multiple groups of remote sensing images of the mine area to be evaluated to a uniform size, place the remote sensing images in the same quadrant of the plane coordinate system, and divide the entire remote sensing image into grids with a step size of ε. The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis respectively. The remote sensing image area covered by the grid is the pixel area with the corresponding number, and the RGB value of any pixel area in the remote sensing image is obtained;

[0029] Step 2) Determine the remote sensing image acquisition method, analyze the influencing factors in the remote sensing image acquisition process, and obtain reference values ​​of various influencing factors affecting the remote sensing image acquisition accuracy during the remote sensing image acquisition process of the mining area to be evaluated through the data acquisition module;

[0030] Step 3) constructing a regression model through the data processing module to obtain the model relationship between the reference value of each influencing factor of the remote sensing image and the RGB value in the pixel area, and obtaining the RGB value of the pixel area in the remote sensing image according to the model relationship;

[0031] Step 4), receiving the calculation results of the RGB values ​​in any pixel area in the remote sensing image and the RGB values ​​of the pixel area in the remote sensing image calculated by the regression model through the data analysis module, and calculating the correction coefficient of the remote sensing image to be identified based on the obtained RGB values;

[0032] Step 5) Correct each pixel area in the remote sensing image to be identified through the image correction module. The specific steps are as follows:

[0033] The image acquisition module obtains the RGB value of any pixel area in the remote sensing image to be identified;

[0034] The product of the RGB value in any pixel area of ​​the remote sensing image to be identified and the correction coefficient is used as the new RGB value, and each pixel area is refilled to obtain the corrected remote sensing image;

[0035] Step 6) The normalized vegetation index NDVI of the corrected remote sensing image is extracted through the image extraction module, thereby dynamically identifying the ecological restoration of abandoned mines.

[0036] Compared with the prior art, the present invention has the following beneficial effects:

[0037] (1) The technical solution of the present invention proposes a dynamic identification method for mine ecological restoration, which collects multiple sets of remote sensing images of the mine area to be evaluated, obtains the RGB value of any pixel area in each remote sensing image, determines the influencing factors in the process of obtaining the remote sensing image, collects the reference value of the influencing factors in the process of obtaining the remote sensing image, and uses the RGB value C in any pixel area in the remote sensing image to identify the dynamic identification method for mine ecological restoration. ij As the independent variable, the reference value of the influencing factor in the remote sensing image acquisition process is used as the dependent variable to build a regression model, and the RGB value C of the n pixel area in the remote sensing image is calculated according to the regression model. mn , the RGB measurement value C of the nth pixel area in the remote sensing image to be identified n and the calculated value C mnThe mean of the ratios is used as the correction coefficient ζ to correct each pixel area in the remote sensing image to be identified, obtain the corrected remote sensing image, and extract the normalized vegetation index NDVI of the corrected remote sensing image, thereby completing the dynamic identification of the ecological restoration of abandoned mines. This can reduce the impact of the deviation between the acquired vegetation area image and the actual vegetation area due to various interference factors such as the external environment and temperature, improve the accuracy of the dynamic identification of the ecological restoration of abandoned mines, and thus improve the accuracy of the assessment of the degree of ecological restoration. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 This is an overall flow chart of a dynamic identification method based on abandoned mine ecological restoration of the present invention;

[0039] Figure 2 This is a structural diagram of a dynamic identification system based on abandoned mine ecological restoration according to the present invention;

[0040] Figure 3 Schematic diagram of the distribution of pixel areas of the present invention.

[0041] In the figure: 1, pixel region numbered 1; 2, pixel region numbered 2; 3, pixel region numbered 3; 4, pixel region numbered 4; 5, pixel region numbered 5; 6, pixel region numbered 6;

[0042] A. Boundary contour of remote sensing image;

[0043] The direction of the arrows represents the numbering direction of the pixel area. DETAILED DESCRIPTION

[0044] The present invention will be further described below in conjunction with specific embodiments. The accompanying drawings are for illustrative purposes only and represent only schematic diagrams rather than actual drawings. They should not be understood as limiting the present invention. In order to better illustrate the specific embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of the actual product. Example 1

[0045] The technical solution of the present invention is described by taking remote sensing satellites acquiring remote sensing images as an example:

[0046] like Figure 1 As shown, the dynamic identification method for mine ecological restoration proposed by the technical solution of the present invention includes the following steps:

[0047] Step 1) Collect multiple sets of remote sensing images of the mine area to be evaluated through remote sensing satellites, and obtain the RGB value C of any pixel area in each remote sensing image. ij , where the pixel area taken from each remote sensing image is the same area;

[0048] The method for obtaining the pixel area is:

[0049] Determine the boundary contours of remote sensing images and adjust multiple sets of remote sensing images of the mining area to be evaluated to a uniform size;

[0050] like Figure 3 As shown, the remote sensing image is placed in the same quadrant of the plane coordinate system, and the entire remote sensing image is divided into grids with a step size of ε;

[0051] The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis respectively. The remote sensing image area covered by the grid is the pixel area with the corresponding number.

[0052] Step 2), determining the influencing factors in the process of remote sensing image acquisition and collecting reference values ​​of the influencing factors in the process of remote sensing image acquisition;

[0053] In this embodiment, remote sensing images are acquired using remote sensing satellites, and factors affecting remote sensing satellite images include sensor resolution, noise level, atmospheric aerosol concentration, cloud cover, satellite altitude, etc. Data such as sensor resolution, noise level, atmospheric aerosol concentration, cloud cover, and satellite altitude during the acquisition of remote sensing images are obtained as reference values ​​for the influencing factors.

[0054] Step 3: Take the RGB value C of any pixel area in the remote sensing image ij As the dependent variable, the reference value of the influencing factors in the remote sensing image acquisition process is used as the independent variable to build a regression model. The expression of the regression model is: ; Among them, X1-X5 are sensor resolution, noise value, atmospheric aerosol concentration, cloud cover, and satellite altitude value respectively;

[0055] The RGB value C in any pixel area of ​​the collected remote sensing image ij The reference values ​​of the influencing factors in the process of remote sensing image acquisition were input into SPSS software to obtain the expression of the regression model;

[0056] Step 4: If you want to evaluate the ecological restoration status of mines within a certain period of time, select the satellite remote sensing image collected during the corresponding period as the remote sensing image to be identified, and arbitrarily select n pixel areas in the remote sensing image to obtain the RGB values ​​C of the n pixel areas in the remote sensing image to be identified. n , and calculate the RGB value C of n pixel areas in the remote sensing image according to the regression model mn , where m=1,2,...,i; n=1,2,...,j;

[0057] Step 5: The RGB measurement value C of the nth pixel area in the remote sensing image to be identified n and the calculated value Cmn The mean of the ratios is used as the correction coefficient ρ to calculate the correction coefficient value, wherein the calculation formula of the correction coefficient is: ; Step six, according to the correction coefficient obtained in step five, correct each pixel area in the remote sensing image to be identified, obtain the corrected remote sensing image, and extract the normalized vegetation index NDVI of the corrected remote sensing image, thereby completing the dynamic identification of the ecological restoration of abandoned mines.

[0058] The specific implementation steps of the dynamic identification method for mine ecological restoration proposed in the technical solution of the present invention are as follows:

[0059] Step 1) collect remote sensing images of the mine area to be evaluated through the image acquisition module, determine the boundary contours of the remote sensing images, adjust multiple sets of remote sensing images of the mine area to be evaluated to a uniform size, place the remote sensing images in the same quadrant of the plane coordinate system, and divide the entire remote sensing image into grids with a step size of ε. The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis respectively. The remote sensing image area covered by the grid is the pixel area with the corresponding number, and the RGB value of any pixel area in the remote sensing image is obtained;

[0060] Step 2) Determine the remote sensing image acquisition method, analyze the influencing factors in the remote sensing image acquisition process, and obtain reference values ​​of various influencing factors affecting the remote sensing image acquisition accuracy during the remote sensing image acquisition process of the mining area to be evaluated through the data acquisition module;

[0061] Step 3) constructing a regression model through the data processing module to obtain the model relationship between the reference value of each influencing factor of the remote sensing image and the RGB value in the pixel area, and obtaining the RGB value of the pixel area in the remote sensing image according to the model relationship;

[0062] Step 4), receiving the calculation results of the RGB values ​​in any pixel area in the remote sensing image and the RGB values ​​of the pixel area in the remote sensing image calculated by the regression model through the data analysis module, and calculating the correction coefficient of the remote sensing image to be identified based on the obtained RGB values;

[0063] Step 5) Correct each pixel area in the remote sensing image to be identified through the image correction module. The specific steps are as follows:

[0064] The image acquisition module obtains the RGB value of any pixel area in the remote sensing image to be identified;

[0065] The product of the RGB value in any pixel area of ​​the remote sensing image to be identified and the correction coefficient is used as the new RGB value, and each pixel area is refilled to obtain the corrected remote sensing image;

[0066] Step 6) The normalized vegetation index NDVI of the corrected remote sensing image is extracted through the image extraction module, thereby dynamically identifying the ecological restoration of abandoned mines. Example 2

[0067] The technical solution of the present invention is explained by taking the acquisition of remote sensing images by an unmanned aerial vehicle platform as an example:

[0068] like Figure 1 As shown, the dynamic identification method for mine ecological restoration proposed by the technical solution of the present invention includes the following steps:

[0069] Step 1) Use a drone equipped with a remote sensing sensor to collect multiple sets of remote sensing images of the mine area to be evaluated, and obtain the RGB value C of any pixel area in each remote sensing image. ij , where the pixel area taken from each remote sensing image is the same area;

[0070] The method for obtaining the pixel area is:

[0071] Determine the boundary contours of remote sensing images and adjust multiple sets of remote sensing images of the mining area to be evaluated to a uniform size;

[0072] like Figure 3 As shown, the remote sensing image is placed in the same quadrant of the plane coordinate system, and the entire remote sensing image is divided into grids with a step size of ε;

[0073] The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis respectively. The remote sensing image area covered by the grid is the pixel area with the corresponding number.

[0074] Step 2), determining the influencing factors in the process of remote sensing image acquisition and collecting reference values ​​of the influencing factors in the process of remote sensing image acquisition;

[0075] In this embodiment, since remote sensing images are acquired by using a drone equipped with a remote sensing sensor, factors affecting the drone remote sensing images include the layout of image control points, wind speed, haze index, pixels, exposure time, overlap rate, flight altitude, etc., data such as the number of image control points, wind speed value, haze index value, pixel value, exposure time value, overlap rate, and flight altitude value of the remote sensing satellite during the process of acquiring remote sensing images are obtained as reference values ​​of the influencing factors.

[0076] Step 3: Take the RGB value C of any pixel area in the remote sensing image ij As the dependent variable, the reference value of the influencing factors in the remote sensing image acquisition process is used as the independent variable to build a regression model. The expression of the regression model is: ; Among them, X1-X5 are the number of image control points, wind speed value, haze index value, pixel value, exposure time value, overlap rate, and flight altitude value respectively;

[0077] The RGB value C in any pixel area of ​​the collected remote sensing image ij The reference values ​​of the influencing factors in the process of remote sensing image acquisition were input into SPSS software to obtain the expression of the regression model;

[0078] Step 4: If you want to evaluate the ecological restoration status of mines within a certain period of time, select the satellite remote sensing image collected during the corresponding period as the remote sensing image to be identified, and arbitrarily select n pixel areas in the remote sensing image to obtain the RGB values ​​C of the n pixel areas in the remote sensing image to be identified. n , and calculate the RGB value C of n pixel areas in the remote sensing image according to the regression model mn , where m=1,2,...,i; n=1,2,...,j;

[0079] Step 5: The RGB measurement value C of the nth pixel area in the remote sensing image to be identified n and the calculated value C mn The mean of the ratios is used as the correction coefficient ρ to calculate the correction coefficient value, wherein the calculation formula of the correction coefficient is: ; Step six, according to the correction coefficient obtained in step five, correct each pixel area in the remote sensing image to be identified, obtain the corrected remote sensing image, and extract the normalized vegetation index NDVI of the corrected remote sensing image, thereby completing the dynamic identification of the ecological restoration of abandoned mines.

[0080] The specific implementation steps of the dynamic identification method for mine ecological restoration proposed in the technical solution of the present invention are as follows:

[0081] Step 1) collect remote sensing images of the mine area to be evaluated through the image acquisition module, determine the boundary contours of the remote sensing images, adjust multiple sets of remote sensing images of the mine area to be evaluated to a uniform size, place the remote sensing images in the same quadrant of the plane coordinate system, and divide the entire remote sensing image into grids with a step size of ε. The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis respectively. The remote sensing image area covered by the grid is the pixel area with the corresponding number, and the RGB value of any pixel area in the remote sensing image is obtained;

[0082] Step 2) Determine the remote sensing image acquisition method, analyze the influencing factors in the remote sensing image acquisition process, and obtain reference values ​​of various influencing factors affecting the remote sensing image acquisition accuracy during the remote sensing image acquisition process of the mining area to be evaluated through the data acquisition module;

[0083] Step 3) constructing a regression model through the data processing module to obtain the model relationship between the reference value of each influencing factor of the remote sensing image and the RGB value in the pixel area, and obtaining the RGB value of the pixel area in the remote sensing image according to the model relationship;

[0084] Step 4), receiving the calculation results of the RGB values ​​in any pixel area in the remote sensing image and the RGB values ​​of the pixel area in the remote sensing image calculated by the regression model through the data analysis module, and calculating the correction coefficient of the remote sensing image to be identified based on the obtained RGB values;

[0085] Step 5) Correct each pixel area in the remote sensing image to be identified through the image correction module. The specific steps are as follows:

[0086] The image acquisition module obtains the RGB value of any pixel area in the remote sensing image to be identified;

[0087] The product of the RGB value in any pixel area of ​​the remote sensing image to be identified and the correction coefficient is used as the new RGB value, and each pixel area is refilled to obtain the corrected remote sensing image;

[0088] Step 6) The normalized vegetation index NDVI of the corrected remote sensing image is extracted through the image extraction module, thereby dynamically identifying the ecological restoration of abandoned mines.

[0089] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A dynamic identification method based on ecological restoration of abandoned mines, characterized by: The following steps are involved: Step 1: Collect multiple sets of remote sensing images of the mine area to be evaluated and obtain the RGB value of any pixel area in each remote sensing image. , where i is the number of the remote sensing image, and j is the number of the pixel area in the i-th remote sensing image; Step 2: determining the influencing factors in the process of acquiring the remote sensing image, and collecting reference values ​​of the influencing factors in the process of acquiring the remote sensing image; Step 3: Take the RGB value of any pixel area in the remote sensing image As the dependent variable, a regression model is constructed with the reference values ​​of the influencing factors in the remote sensing image acquisition process as independent variables. The expression of the regression model is: ; Among them, X1 is the reference value of the first influencing factor, X k is the reference value of the kth influencing factor; Step 4: Determine the remote sensing image to be identified, select n pixel areas in the remote sensing image, and obtain the RGB values ​​C of the n pixel areas in the remote sensing image to be identified. n , and calculate the RGB value C of n pixel areas in the remote sensing image according to the regression model mn , where m=1,2,...,i; n=1,2,...,j; Step 5: The RGB measurement value C of the nth pixel area in the remote sensing image to be identified is n and the calculated value C mn The mean of the ratios is used as the correction coefficient ρ to calculate the correction coefficient value, wherein the calculation formula of the correction coefficient is: ; Step six, based on the correction coefficient obtained in step five, correct each pixel area in the remote sensing image to be identified, obtain the corrected remote sensing image, and extract the normalized vegetation index NDVI of the corrected remote sensing image, thereby completing the dynamic identification of the ecological restoration of the abandoned mine.

2. A dynamic identification method based on abandoned mine ecological restoration according to claim 1, characterized in that: The method for obtaining the pixel area in step 1 is: Determine the boundary contours of remote sensing images and adjust multiple sets of remote sensing images of the mining area to be evaluated to a uniform size; Place the remote sensing image in the same quadrant of the plane coordinate system and divide the entire remote sensing image into grids with a step size of ε; The grids are numbered in sequence along the positive direction of the X axis and the positive direction of the Y axis, and the remote sensing image area covered by the grid is the pixel area with the corresponding number.

3. The dynamic identification method based on abandoned mine ecological restoration according to claim 1 is characterized by: The influencing factors in the remote sensing image acquisition process in step 2 are determined according to the remote sensing image acquisition method.

4. The dynamic identification method based on abandoned mine ecological restoration according to claim 1 is characterized by: In step three, the number of independent variables in the regression model is equal to the number of influencing factors in the remote sensing image acquisition process.

5. The dynamic identification method based on abandoned mine ecological restoration according to claim 2 is characterized by: The value of the step length ε is inversely proportional to the resolution of the remote sensing image and is determined by an empirical formula, wherein the calculation formula of the step length ε is: ; Wherein, λ is a constant coefficient, and the value range of λ is (0,0.5]; p is the resolution value of the remote sensing image; Es is the scale value of the remote sensing image placed in the plane coordinate system.

6. A dynamic identification system based on abandoned mine ecological restoration, the system being used to implement the dynamic identification method based on abandoned mine ecological restoration according to any one of claims 1 to 5, characterized in that: include: An image acquisition module is used to collect remote sensing images of the mine area to be evaluated and obtain the RGB value of any pixel area in the remote sensing image; The data acquisition module is used to obtain reference values ​​of various factors affecting the accuracy of remote sensing image acquisition during the remote sensing image acquisition process of the mining area to be evaluated; The data processing module is used to construct a regression model, obtain a model relationship between the reference value of each influencing factor of the remote sensing image and the RGB value in the pixel area, and obtain the RGB value of the pixel area in the remote sensing image according to the model relationship; a data analysis module, the data analysis module being communicatively connected to the image acquisition module and the data processing module, and configured to receive the calculation results of the RGB values ​​within any pixel region in the remote sensing image and the RGB values ​​of the pixel region in the remote sensing image calculated by the regression model, and calculate the correction coefficient of the remote sensing image to be identified based on the obtained RGB values; An image correction module is used to correct each pixel area in the remote sensing image to be identified and obtain a corrected remote sensing image; The image extraction module is used to extract the normalized vegetation index NDVI from the corrected remote sensing image, thereby dynamically identifying the ecological restoration of abandoned mines.

7. 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, it can implement a dynamic identification method based on ecological restoration of abandoned mines according to any one of claims 1 to 5.

Images