A Crop Status Evaluation System and Method Based on Satellite Remote Sensing Images

Abstract

The present invention discloses a crop status evaluation system and method based on satellite remote sensing images, belonging to the field of agricultural engineering, including a processing module, a storage module, a satellite remote sensing image acquisition module, a crop variety and spectral feature parameter acquisition module, a planting area acquisition and characteristic color marking module, a true edge point extraction module, a planting area calculation module, and a planting area distribution evaluation module for providing data transmission and executing programs for each module. By obtaining or processing the planting areas of typical crops in satellite remote sensing images, the planting area and distribution evaluation indexes of crops are obtained, solving the problems that the traditional methods for obtaining crop planting areas and areas and the evaluation process are time-consuming and laborious, and the results may deviate greatly from the actual situation, making the acquisition of crop planting areas and status standardized and facilitating rapid programming processing of typical crops by scientific research personnel. Moreover, the obtained results are repeatable and verifiable.

Description

Technical Field

[0001] The present invention relates to the technical field of agricultural engineering, and particularly relates to a crop status evaluation system and method based on satellite remote sensing images. Background Technique

[0002] In agricultural engineering, the planting status of crops is an important aspect for evaluating the agricultural development of a region. Generally speaking, the evaluation of crop planting status includes the types, areas, and distribution of typical crops planted locally. For a certain region, the types of crops are relatively fixed, and the types of typical crops planted, especially those of the leading agricultural industries, will not change significantly. However, the areas and distribution of crops may fluctuate greatly in different years. Quickly obtaining the planting areas and distribution of typical crops can provide a basis for local agricultural departments in aspects such as guiding crop planting, promoting the process of agricultural modernization, estimating yields, formulating agricultural policies, building water conservancy, and allocating agricultural machinery.

[0003] The traditional planting areas and distribution of crops are mainly obtained through on-site surveys by investigators, statistical classification, or estimation based on the breeding conditions of major crops. This method requires a large amount of manpower, material resources, and is slow in progress. The results obtained may have a large deviation from the actual situation. In addition, there is no unified evaluation standard for the planting distribution status of crops, and traditional evaluation indicators are diverse, and the planting area distribution status cannot be visually displayed macroscopically. Summary of the Invention

[0004] The purpose of the present invention is to solve the defects existing in the prior art, and to propose a crop status evaluation system and method based on satellite remote sensing images.

[0005] In order to achieve the above purpose, the present invention adopts the following technical solutions:

[0006] A crop status evaluation system based on satellite remote sensing images includes a processing module, a storage module, a satellite remote sensing image acquisition module, a crop type and spectral feature parameter acquisition module, a planting area acquisition and feature color marking module, a true edge point extraction module, a planting area calculation module, and a planting area distribution evaluation module for providing data transmission and executing programs for each module.

[0007] Further, the processing module is used to execute the programs of each module and provide information processing for each module, and the storage module is used to store the information transmitted by each module and store the execution programs of each module;

[0008] The satellite remote sensing image acquisition module is used to acquire recent satellite remote sensing images, determine the boundaries of the area to be evaluated, and record the area within the boundaries as the evaluation area;

[0009] The crop type and spectral feature parameter acquisition module is used to select typical crop types and give the spectral feature parameters of the corresponding remote sensing images of the selected crops in the current season.

[0010] Furthermore, the planting area acquisition and characteristic color marking module is used to acquire the planting areas of typical crops and mark the corresponding planting areas with characteristic colors;

[0011] The true edge point extraction module is used to traverse all the edge points of the crop planting area, judge whether the edge point is a true edge point or a false edge point, eliminate the false edge points, and form a new set of true edge points;

[0012] The planting area calculation module is used to obtain the estimated planting area of each crop by the method of scanning the pixel points of the planting area line by line;

[0013] The planting area distribution evaluation module is used to evaluate the distribution index of the planting areas of typical planted crops according to the set of true edge points and the estimated area values of each typical crop, and obtain the evaluation indexes of the planting area distribution of each crop.

[0014] Another object of the present invention is: a method for evaluating the status of crops based on satellite remote sensing images. Therefore, on the basis of the above technical solutions, the present invention also proposes the following technical solutions:

[0015] A method for evaluating the status of crops based on satellite remote sensing images includes the following steps:

[0016] Step S1: Obtain recent satellite remote sensing images and determine the evaluation area;

[0017] Step S2: Select typical crop types and obtain spectral feature parameters;

[0018] Step S3: Obtain the planting areas of typical crops and mark them with characteristic colors;

[0019] Step S4: Traverse the edge points of the planting area to obtain a set of true edge points;

[0020] Step S5: Scan the remote sensing image of the planting area line by line to obtain the estimated planting area;

[0021] Step S6: Evaluate the distribution of the planting areas of typical planted crops according to the set of true edge points and the estimated area values, and obtain evaluation indexes.

[0022] Furthermore, it includes the following steps:

[0023] Step S10: Obtain the satellite remote sensing image when the local area has clear weather recently, record the actual distance \(l\) corresponding to a single pixel of this image, determine the boundary of the area to be evaluated, mark the area within the boundary as the evaluation area, and set the image of the area outside the boundary to an invalid value;

[0024] Step S20: According to the basic situation of local crop planting types, select typical crop types. Denote the number of selected typical crop types as \(N\), and give the spectral characteristic parameters of the corresponding remote sensing images of the selected crops in the current season;

[0025] Step S30: In the evaluation area, based on the types of selected crops and their spectral characteristic parameters of remote sensing images, obtain the planting areas of the corresponding crops, mark the corresponding planting areas with characteristic colors, and denote the area marked with the characteristic color of the \(i\)-th typical crop as \(T_i\);

[0026] Step S40: According to the first method, for all the edge point sets \(Q_i\) of the characteristic color areas of the \(i\)-th typical crop, traverse all the edge points of the planting area of this crop, and according to the second method, judge whether this edge point is a true edge point or a false edge point, eliminate the false edge points, and form a set \(U_i\) with the true edge points;

[0027] Step S50: According to the area \(T_i\) marked with the characteristic color of the \(i\)-th typical crop, use the third method to calculate the area estimated value \(W_i\) of the planting area of this crop; traverse the number \(N\) of typical crop types, and successively obtain the area estimated values of the planting areas of each crop;

[0028] Step S60: According to the true edge point sets \(U_i\) and area estimated values \(W_i\) of each typical crop, use the fourth method to evaluate the distribution index of the planting areas of typical planted crops; traverse the number \(N\) of typical crop types, and successively obtain the evaluation indexes of the distribution of the planting areas of each crop.

[0029] Furthermore, the steps of the second method used in step S40 are as follows:

[0030] Step S41: Take the edge point set \(Q_i\) of the \(i\)-th typical crop, obtain the RGB values of its surrounding 8 pixels. If the RGB values of at least 6 edge points are consistent with the characteristic color, then it is a false edge point, otherwise it is a true edge point;

[0031] Step S42: Traverse all the edge points of the edge point set \(Q_i\), eliminate the false edge points, and obtain the set \(U_i\) of true edge points.

[0032] Furthermore, the steps of the third method used in step S50 are as follows:

[0033] Step S51: Scan the evaluation area of the remote sensing image row by row, and count the number of pixel points with the i-th typical crop characteristic color during each row scan. After all scans are completed, obtain the cumulative sum si of the number of pixel points with the characteristic color.

[0034] Step S52: Obtain the estimated area value of the i-th typical crop through the following formula

[0035] W i = s i * l 2

[0036] where l is the actual distance corresponding to a single pixel of this remote sensing image.

[0037] Furthermore, the steps for the fourth method described in step S60 are as follows:

[0038] Step S61: Calculate the reference radius ri of the planting area distribution of the i-th typical crop according to the following formula:

[0039]

[0040] Step S62: Calculate the maximum distance d between every two pixel points in the set Ui of true edge points of the i-th typical crop max ;

[0041] Step S63: Calculate the evaluation index of the planting area distribution situation of the i-th typical crop according to the following formula:

[0042]

[0043] Furthermore, the calculation formula for the maximum distance described in step S62 is:

[0044] k ∈ U i , j ∈ U i , and k ≠ j}

[0045] where (x k , y k ) and (x j , y j ) are the horizontal and vertical coordinate values of the k-th and j-th pixel points, and max represents taking the maximum value of all values.

[0046] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0047] By obtaining or processing the planting area of typical crops in satellite remote sensing images, the planting area and distribution evaluation index of crops are obtained, solving the problems that the traditional method of obtaining the planting area and region of crops and the evaluation process are time-consuming and laborious, and the results may deviate greatly from the actual situation.

[0048] By clarifying the processing flow and standardizing the processing method, the acquisition of crop planting area and status is made standardized and normalized, which is conducive to rapid programming processing of typical crops by researchers, and the obtained results are repeatable and verifiable. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the present invention, and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention, and do not constitute a limitation to the present invention.

[0050] Figure 1 It is a schematic flow chart of a crop status evaluation system based on satellite remote sensing images proposed by the present invention;

[0051] Figure 2 It is a step flow chart of a crop status evaluation method based on satellite remote sensing images proposed by the present invention;

[0052] Figure 3 It is a schematic diagram of the steps of obtaining an evaluation area and selecting crops in a crop status evaluation method based on satellite remote sensing images proposed by the present invention;

[0053] Figure 4 It is a schematic diagram of the steps of obtaining a crop planting area and marginalizing it in a crop status evaluation method based on satellite remote sensing images proposed by the present invention;

[0054] Figure 5 It is a schematic diagram of performing area labeling in a crop status evaluation method based on satellite remote sensing images proposed by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0055] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments.

[0056] According to a specific embodiment of the present invention, a crop status evaluation system based on satellite remote sensing images is provided.

[0057] Refer to Figure 1 , a crop status evaluation system based on satellite remote sensing images includes a processing module, a storage module, a satellite remote sensing image acquisition module, a crop type and spectral feature parameter acquisition module, a planting area acquisition and feature color marking module, a true edge point extraction module, a planting area area calculation module, and a planting area distribution evaluation module for providing data transmission and executing programs for each module.

[0058] The processing module is used to execute the programs of each module and provide information processing for each module, and the storage module is used to store the information transmitted by each module and store the execution programs of each module;

[0059] The satellite remote sensing image acquisition module is used to acquire recent satellite remote sensing images, determine the boundary of the area to be evaluated, and record the area within the boundary as the evaluation area;

[0060] The crop type and spectral feature parameter acquisition module is used to select typical crop types and give the spectral feature parameters of the corresponding remote sensing images of the selected crops in the current season;

[0061] The planting area acquisition and characteristic color marking module is used to acquire the planting areas of typical crops and mark the corresponding planting areas with characteristic colors;

[0062] The true edge point extraction module is used to traverse all edge points of the crop planting area, judge whether the edge point is a true edge point or a false edge point, eliminate the false edge points, and form a new set of true edge points;

[0063] The planting area calculation module is used to obtain the estimated value of the planting area of each crop by the method of scanning line by line to obtain the number of pixel points in the planting area;

[0064] The planting area distribution evaluation module is used to evaluate the index of the planting area distribution of typical planted crops according to the set of true edge points and the estimated area value of each typical crop, and obtain the evaluation index of the planting area distribution of each crop.

[0065] In this embodiment, the processing module uses any one of an I7 processor or an Alibaba Cloud server. Among them, any processor with equivalent performance or function can also be used for information processing in connection, and the storage module uses any storage device that matches the processing module.

[0066] According to an embodiment of the present invention, a method for evaluating the state of crops based on satellite remote sensing images is also provided.

[0067] Embodiment 1

[0068] Refer to Figure 2 , a method for evaluating the state of crops based on satellite remote sensing images, including the following steps:

[0069] Step S1: Acquire recent satellite remote sensing images and determine the evaluation area;

[0070] Step S2: Select typical crop types and obtain spectral feature parameters;

[0071] Step S3: Acquire the planting areas of typical crops and mark them with characteristic colors;

[0072] Step S4: Traverse the edge points of the planting area to obtain a set of true edge points;

[0073] Step S5: Scan the telemetry image of the planting area row by row to obtain an estimated value of the planting area;

[0074] Step S6: Evaluate the distribution of the planting areas of typical planted crops based on the set of true edge points and the area estimate value to obtain evaluation indicators.

[0075] Example Two

[0076] Refer to Figures 3 - 5 , on the basis of Example One, a method for evaluating the status of crops based on satellite remote sensing images includes the following steps:

[0077] Step S10, obtain a satellite remote sensing image when the local area has clear weather recently, record the actual distance l corresponding to a single pixel of this image, determine the boundary of the area to be evaluated, mark the area within the boundary as the evaluation area, and set the area image outside the boundary to an invalid value;

[0078] Step S20, according to the basic situation of the local crop planting types, select typical crop types, record the number of selected typical crop types as N, and give the spectral characteristic parameters of the corresponding remote sensing images of the selected crops in the current season;

[0079] Step S30, in the evaluation area, obtain the planting areas of the corresponding crops based on the types of the selected crops and their spectral characteristic parameters of the remote sensing images, mark the corresponding planting areas with characteristic colors, and mark the area with the characteristic color of the i-th typical crop as Ti;

[0080] Step S40, according to the first method, obtain all the edge point sets Qi of the characteristic color area of the i-th typical crop, traverse all the edge points of the planting area of this crop, and judge whether this edge point is a true edge point or a false edge point according to the second method, eliminate the false edge points, and form a set Ui of the true edge points;

[0081] Specifically, the first method is the Prewitt difference method or the sobel difference method.

[0082] More specifically, the steps of the second method are as follows:

[0083] Step S41, take the edge point set Qi of the i-th typical crop, obtain the RGB values of its surrounding 8 pixels. If the RGB values of at least 6 edge points are the same as the characteristic color, then it is a false edge point, otherwise it is a true edge point;

[0084] Step S42: Traverse all the edge points in the edge point set Qi, eliminate the pseudo-edge points, and obtain the set Ui of true edge points.

[0085] Step S50: According to the area Ti marked with the characteristic color of the i-th typical crop, use the third method to calculate the estimated area value Wi of the planting area of this crop; traverse the number N of typical crop types, and sequentially obtain the estimated planting area values of each crop.

[0086] Specifically, the steps of the third method are as follows:

[0087] Step S51: Scan the remote sensing image evaluation area row by row, count the number of pixel points with the color of the characteristic color of the i-th typical crop during each row scan. After all scans are completed, obtain the cumulative sum si of the number of pixel points with the characteristic color.

[0088] Step S52: Obtain the estimated area value of the i-th typical crop through the following formula

[0089] W i =s i *l 2

[0090] where l is the actual distance corresponding to a single pixel of this remote sensing image.

[0091] Step S60: According to the set Ui of true edge points and the estimated area value Wi of each typical crop, use the fourth method to evaluate the index of the distribution of the planting areas of typical planted crops; traverse the number N of typical crop types, and sequentially obtain the evaluation indexes of the distribution of the planting areas of each crop.

[0092] Specifically, the steps of the fourth method are as follows:

[0093] Step S61: Calculate the reference radius ri of the distribution of the planting area of the i-th typical crop according to the following formula:

[0094]

[0095] Step S62: Calculate the maximum distance d between every two pixel points in the set Ui of true edge points of the i-th typical crop max ;

[0096] Step S63: Calculate the evaluation index of the distribution of the planting area of the i-th typical crop according to the following formula:

[0097]

[0098] The minimum value of this index is 1. The closer the value is to 1, the more concentrated the distribution of the planting area of this crop is, which is conducive to large-scale centralized operations and centralized management; the larger the value, the more dispersed the distribution is, which is not conducive to centralized management.

[0099] More specifically, the calculation formula for the maximum distance is:

[0100] k ∈ U i , j ∈ U i , and k ≠ j}

[0101] where, (x k , y k ) and (x j , y j ) are the horizontal and vertical coordinate values of the k-th and j-th pixel points, and max represents taking the maximum value of all values.

[0102] Embodiment III

[0103] Based on Embodiment II, it includes steps S10 - S60:

[0104] Step S101, obtain a satellite remote sensing image when the local area has clear weather recently. Through the telemetry data acquisition method, obtain that the actual distance l corresponding to a single pixel of this image is 5 km, and record the scale of the remote sensing image as 5 km / pixel; determine the boundary of the area to be evaluated, record the area within the boundary as the evaluation area, and set the image of the area outside the boundary to an invalid value. The evaluation area can be a certain city or a certain region.

[0105] Step S201, according to the basic situation of the local crop planting types, select typical crop types as soybeans and corn, record the number of selected typical crop types as 2, and give the spectral characteristic parameters of soybeans and corn in the remote sensing image. Common spectral characteristic parameters include red edge (RE), blue edge (BE), yellow edge (YE), leaf area index (LAI), normalized difference vegetation index (NDVI), maximum value of the first-stage number of the red edge (DRE), leaf water content index (WI), leaf chlorophyll index (LCI), etc.

[0106] Step S301, in the evaluation area, based on the selected crop types and their spectral characteristic parameters of the remote sensing image, obtain the planting areas of the corresponding crops, and mark the corresponding planting areas with characteristic colors. Record the area marked with the characteristic color of soybeans as T1, and the area marked with the characteristic color of corn as T2;

[0107] Step S401: Obtain all the edge point sets Q1 and Q2 of the characteristic color regions of soybeans and corn according to the first method. Traverse all the edge points of the two, and judge whether the edge point is a true edge point or a false edge point according to the second method. Eliminate the false edge points, and form sets U1 and U2 with the true edge points. The specific description is as follows:

[0108] The first method can be the Prewitt difference method or the sobel difference method, or it can be processed separately by PS;

[0109] It should be noted that taking the Prewitt difference method as an example, this difference method performs gray difference on the eight pixel points near the central pixel point to judge whether it is an edge point, which is expressed by the formula:

[0110]

[0111] If then (x, y) is an edge point; where F is a preset threshold, and f(x, y) is the gray value at the coordinate (x, y), represents the gradient value. See Figure 2-4 for the schematic diagram of the edge point;

[0112] Furthermore, the steps of the second method are as follows:

[0113] Take a certain pixel point in sets Q1 and Q2, calculate the RGB values of its surrounding 8 pixels. If the RGB values of at least 6 edge points are consistent with the characteristic color of soybeans / corn, then it is a pseudo-edge point, otherwise it is a true edge point;

[0114] Traverse all the edge points in the edge point sets Q1 and Q2, eliminate the pseudo-edge points, and obtain the sets U1 and U2 of true edge points;

[0115] According to the coloring regions T1 and T2 of soybeans and corn, use the third method to calculate the area estimation values W1 and W2 of the crop planting area;

[0116] Specifically, the steps of the third method are as follows:

[0117] Scan the remote sensing image evaluation area row by row, count the number of pixel points with the characteristic color of soybeans during each row scan. After all scans are completed, obtain the cumulative sum s1 = 228 of the number of pixel points with the characteristic color. Then scan the remote sensing image evaluation area row by row again, count the number of pixel points with the characteristic color of corn during each row scan. After all scans are completed, obtain the cumulative sum s2 = 190 of the number of pixel points with the characteristic color;

[0118] Obtain the area estimation values W1 and W2 of soybeans and corn through the following formula

[0119] W1 = s i *l 2= 228 * 5 2 = 5700 km 2

[0120] W2 = s i * l 2 = 190 * 5 2 = 4750 km 2

[0121] Among them, l is the actual distance corresponding to a single pixel of the remote sensing image, which is 5 km here;

[0122] Step S601: According to the true edge point sets U1 and U2 of soybeans and corn and the area estimation values W1 and W2, use the fourth method to evaluate the distribution of their planting areas;

[0123] Specifically, the steps of the fourth method are as follows:

[0124] Calculate the reference radii r1 and r2 of the planting area distributions of soybeans and corn according to the following formula:

[0125]

[0126]

[0127] Calculate the maximum distance d between every two pixel points of the true edge point sets U1 and U2 of soybeans and corn respectively max ;

[0128] The formula for calculating the maximum distance is:

[0129] k ∈ U i ,j ∈ U i ,and k ≠ j}

[0130] Among them, (x k ,y k ) and (x j ,y j ) are the horizontal and vertical coordinate values of the kth and jth pixel points, and max represents taking the maximum value of all values;

[0131] According to the calculation, the maximum distance of the true edge point pixels of soybeans is 85, and the maximum distance of the true edge point pixels of corn is 39;

[0132] Calculate the evaluation index of the planting area distribution of soybeans and corn according to the following formula:

[0133]

[0134]

[0135] Among them, the minimum value of this index is 1. The closer the value is to 1, the more concentrated the distribution of the planting area of this crop is, which is conducive to large-scale centralized operations and convenient for centralized management; the larger the value is, the more dispersed the distribution is, which is not conducive to centralized management.

[0136] In this embodiment, the above formulas are all calculated by removing the dimension and taking their numerical values. The formulas are obtained by collecting a large amount of data for software simulation to get a formula that is closest to the actual situation. The preset parameters and preset thresholds in the formulas are set by those skilled in the art according to the actual situation or obtained by simulating a large amount of data.

[0137] The above is only a preferred specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto.

Claims

1. A crop status evaluation system based on satellite remote sensing images, characterized in that It includes a processing module for providing data transmission and program execution for each module, a storage module, a satellite remote sensing image acquisition module, a crop variety and spectral feature parameter acquisition module, a planting area acquisition and characteristic color marking module, a true edge point extraction module, a planting area calculation module, and a planting area distribution evaluation module; The processing module is used to execute the programs of each module and provide information processing for each module, and the storage module is used to store the information transmitted by each module and store the execution programs of each module; The satellite remote sensing image acquisition module is used to acquire recent satellite remote sensing images, determine the boundary of the area to be evaluated, and record the area within the boundary as the evaluation area; The crop variety and spectral feature parameter acquisition module is used to select typical crop varieties and give the spectral feature parameters of the corresponding remote sensing images of the selected crops in the current season; The planting area acquisition and characteristic color marking module is used to acquire the planting areas of typical crops and mark the corresponding planting areas with characteristic colors; The true edge point extraction module is used to traverse all edge points of the crop planting area, judge whether the edge point is a true edge point or a false edge point, eliminate the false edge points, and form a new set of true edge points; Among them, the process of judging whether the edge point is a true edge point or a false edge point, eliminating the false edge points, and forming a new set of true edge points is as follows: Take the edge point set Qi of the i-th typical crop, obtain the RGB values of its surrounding 8 pixels. If the RGB values of at least 6 edge points are consistent with the characteristic color, then it is a pseudo-edge point, otherwise it is a true edge point; Traverse all edge points of the edge point set Qi, eliminate the pseudo-edge points, and obtain the set Ui of true edge points; The planting area calculation module is used to obtain the estimated planting area of each crop by the method of scanning row by row to obtain the number of pixel points in the planting area; Among them, the specific process of obtaining the estimated planting area of each crop by scanning row by row to obtain the number of pixel points in the planting area is as follows: Scan the evaluation area of the remote sensing image row by row, count the number of pixel points with the color of the characteristic color of the i-th typical crop during each row scan. After all scans are completed, obtain the cumulative sum si of the number of pixel points with the characteristic color; Obtain the estimated area value of the i-th typical crop through the following formula: ， Among them, is the actual distance corresponding to a single pixel of the remote sensing image; The planting area distribution evaluation module is used to evaluate the planting area distribution index of typical planted crops according to the set of true edge points and the estimated area value of each typical crop, and obtain the evaluation index of the planting area distribution of each crop.

2. A method for evaluating the status of crops based on satellite remote sensing images, which is used for the system for evaluating the status of crops based on satellite remote sensing images described in claim 1, and is characterized in that: This method for evaluating the state of crops based on satellite remote sensing images includes the following steps: Step S10, obtain a satellite remote sensing image when the local area has clear weather recently, record the actual distance corresponding to a single pixel of the image, determine the boundary of the area to be evaluated, mark the area within the boundary as the evaluation area, and set the image of the area outside the boundary to an invalid value; l , determine the boundary of the area to be evaluated, mark the area within the boundary as the evaluation area, and set the image of the area outside the boundary to an invalid value; Step S20, according to the basic situation of local crop planting varieties, select typical crop varieties, record the number of selected typical crop varieties as N, and give the spectral feature parameters of the corresponding remote sensing images of the selected crops in the current season; Step S30, in the evaluation area, based on the varieties of selected crops and their spectral feature parameters of remote sensing images, obtain the planting areas of the corresponding crops, mark the corresponding planting areas with characteristic colors, and record the area marked with the characteristic color of the i-th typical crop as Ti; Step S40: According to the first method, obtain all the edge point sets Qi of the characteristic color regions of the i-th typical crop, traverse all the edge points in the crop planting region, judge whether the edge point is a true edge point or a false edge point according to the second method, eliminate the false edge points, and form a set Ui with the true edge points. Step S50: According to the region Ti marked with the characteristic color of the i-th typical crop, use the third method to calculate the area estimation value Wi of the crop planting region; traverse the number N of typical crop types, and successively obtain the area estimation values of each crop. Step S60: According to the true edge point sets Ui and area estimation values Wi of each typical crop, use the fourth method to evaluate the index of the distribution of the planting regions of the typical planted crops; traverse the number N of typical crop types, and successively obtain the evaluation indexes of the distribution of the planting regions of each crop.

3. The method for evaluating the state of crops based on satellite remote sensing images according to claim 2, characterized in that, Specifically, in step S10, through the way of obtaining remote sensing data, the actual distance l corresponding to a single pixel of this image is obtained as 5 km, and the ratio of the remote sensing image is recorded as 5 km / pixel; determine the boundary of the area to be evaluated, record the area within the boundary as the evaluation area, set the image of the area outside the boundary to an invalid value, and the evaluation area is a certain city or a certain region. Specifically, in step S20, the number of selected typical crop types is recorded as 2, and the spectral characteristic parameters of soybeans and corn in the remote sensing image are given. The spectral characteristic parameters include red edge (RE), blue edge (BE), yellow edge (YE), leaf area index of vegetation (LAI), normalized difference vegetation index (NDVI), maximum value of the first-stage number of the red edge (DRE), leaf water content index (WI), and leaf chlorophyll index (LCI). Specifically, in step S30, mark the characteristic color for the corresponding planting region, record the region marked with the characteristic color of soybeans as T1, and the region marked with the characteristic color of corn as T2. Specifically, in step S40, according to the first method, obtain all the edge point sets Q1 and Q2 of the characteristic color regions of soybeans and corn, traverse all their edge points, judge whether the edge point is a true edge point or a false edge point according to the second method, eliminate the false edge points, and form sets U1 and U2 with the true edge points.

4. The method for evaluating the state of crops based on satellite remote sensing images according to claim 3, wherein The steps for the fourth method described in step S60 are as follows: Step S61, calculate the reference radius of the planting area distribution of the i-th typical crop according to the following formula :[[]]END]] ； Step S62, calculate the maximum distance between every two pixel points in the true edge point set Ui of the i-th typical crop ; Step S63: Calculate the evaluation index of the distribution of the planting region of the i-th typical crop according to the following formula: 。 5. The method for evaluating the state of crops based on satellite remote sensing images according to claim 4, wherein, The formula for the maximum distance described in step S62 is: ， Among them, ( , ) and ( , ) are the horizontal and vertical coordinate values of the k-th and j-th pixel points, and max represents taking the maximum value of all values.

Images