Natural resource illegal land monitoring method and system

Abstract

The invention discloses a natural resource illegal land monitoring method and system, and relates to the technical field of image processing. Remote sensing image information of a target land parcel is collected, a texture image of the target land parcel is obtained, a sparse degree index and a clear degree index of textures in the texture image are obtained, and a texture evaluation index of the texture image is constructed; the method comprises the following steps: acquiring remote sensing image information of a plurality of target land parcels according to a time sequence, respectively calculating texture evaluation indexes of texture graphs, acquiring a time-varying rule of the texture evaluation indexes through a time sequence model, and taking certain abnormal land detection of the target land parcels as first target detection; and acquiring a time interval between the first target detection and the second target detection, predicting a texture evaluation index of the image during the second target detection, and when the texture evaluation index in the image corresponding to the second target detection is different from a predicted value, giving an alarm prompt to related management personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for monitoring illegal use of natural resources. Background Art

[0002] Land resources are one of the important resources. In the traditional process of identifying abnormal land use, relevant managers are required to patrol the land. This method not only requires relevant managers to pay a lot of physical labor, but also has low timeliness. With the development of information transmission and image analysis technology, image information of relevant plots is gradually collected and analyzed to obtain whether the relevant plots are occupied abnormally.

[0003] In the related methods of image comparison, it is necessary to compare the difference between the currently collected image and the image in the historical storage to determine whether there is any abnormality in the currently collected image. In terms of land resource monitoring, due to the wide monitoring range and long monitoring time, a large amount of image data will be generated in the process of monitoring a certain land block. If the current image is compared one by one with the image in the historical data, firstly a large amount of storage space is required to store the historical data, and secondly a large amount of computing resources are required for image comparison, which makes it impossible to provide effective feedback on abnormal land use. Summary of the invention

[0004] The purpose of the present invention is to provide a method for monitoring illegal use of natural resources to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] Step S100: a certain plot of land under abnormal land use monitoring is taken as a target plot, remote sensing image information of the target plot is collected, and an image texture area of ​​the image information is acquired to obtain a texture image of the target plot;

[0007] Step S200: obtaining a sparseness index and a clarity index of a texture in a texture image, and constructing a texture evaluation index of the texture image;

[0008] Step S300: when there is no anomaly in the target plot, remote sensing image information of several target plots is collected in chronological order, texture evaluation indexes of texture graphics are calculated respectively, and the law of change of texture evaluation index over time is obtained through the time series model;

[0009] Step S400: Take a certain abnormal land use detection of a target plot as the first target detection, take the corresponding image in the first target detection process as the first target image, obtain the time interval between the first target detection and the second target detection, predict the texture evaluation index of the image during the second target detection, and when the texture evaluation index in the image corresponding to the second target detection is different from the predicted value, issue an alarm to the relevant management personnel.

[0010] Furthermore, step S100 includes:

[0011] Step S101: collect remote sensing image information of any target plot, convert the remote sensing image into a grayscale image, and the grayscale quantization interval is [0, G], where G represents the maximum grayscale value in the grayscale image quantization interval;

[0012] Step S102: performing grid processing on the grayscale image, dividing the grayscale image into a number of unit grayscale images of the same shape and size, obtaining the grayscale values ​​of all the unit grayscale images, and calculating the average grayscale value of all the unit grayscale images, which is recorded as Gra;

[0013] Step S103: Obtain the i-th unit grayscale image ui among all unit grayscale images, and obtain the grayscale value G corresponding to ui ui , calculate the grayscale judgment value D of ui ui , Du i =G ui +α×Gra, where α represents the proportionality coefficient, α∈(0,2);

[0014] The dark part of the image is filtered out, and the brighter part is filtered out from the image. The remaining part is the dark part of the image, which includes the boundary part of the image. The boundary part also represents the transition area information between various graphics in the image;

[0015] Step S104: When D ui ≥G, the i-th unit grayscale image is set as the selected unit image, and all the selected unit images in the grayscale image are collected to form the image set Re;

[0016] Step S105: obtaining an image set A consisting of all unit grayscale images in the grayscale image, calculating a texture image set B, B=A-Re, and collecting all unit grayscale images in the texture image set B to form a texture image TU of the grayscale image;

[0017] Screen out some areas in the image to reduce the computing resources occupied during image processing.

[0018] Furthermore, in step S200, the step of calculating the sparsity index includes:

[0019] Step S201: Calculate the ratio β of the texture image set B to the image set A, β=numB / numA, where numB represents the number of unit grayscale images in the texture image set B, and numA represents the number of unit grayscale images in the image set A;

[0020] Step S202: in the texture image set B, an image composed of continuous unit grayscale images is set as an image block, and all image blocks in the texture image set B are labeled;

[0021] Step S203: obtaining the geometric center of each image block in the texture image TU, obtaining the distance between the geometric centers of any two image blocks in the texture image TU, calculating the variance var of the distances between all geometric centers, and calculating the sparsity index K1, K1=β×var;

[0022] The variance indicates the degree of discreteness of the data. By calculating the degree of discreteness of the geometric center distance, the distribution of the image blocks in the texture image TU is obtained.

[0023] Furthermore, in step S200, the step of calculating the clarity index includes:

[0024] Step S204: Obtain the j-th image block in the texture image TU, and obtain the maximum gradient vector grd of the gray value change in the j-th image block j , calculate the maximum gradient vector grd j The modulus length m j ;

[0025] The modulus of the gradient vector represents the maximum value of the rate of change and directional derivative of the function at a certain point. The modulus of the gradient vector represents the sharpness of pixel change. However, the larger the modulus, the faster the gray value changes, and the sharper the image appears.

[0026] Step S205: In the jth image block, obtain the maximum gradient vector grd j The unit grayscale image with the largest grayscale value in the direction and the unit grayscale image with the smallest grayscale value, where the grayscale value of the unit grayscale image with the largest grayscale value is recorded as G j max , the gray value of the unit gray image with the smallest gray value is recorded as G j min ;

[0027] Step S206: Calculate the gray value variation coefficient γ j , γ j =(G j max -G j min ) / G j max, calculate the clarity index k of the jth image block j , k j =(1-γ j )×m j , the average value of the clarity indexes of all image blocks is recorded as the clarity index K2;

[0028] Under the condition of the same change rate, the change range of the gray value is further compared. When the gray value change rate is constant, the smaller the change range, the higher the sharpness of the image.

[0029] Furthermore, step S200 further includes:

[0030] Step S207: constructing a grayscale image texture evaluation index H, H=K1×ln(1+K2), where ln represents a logarithmic function;

[0031] In order to balance the values ​​of K1 and K2, K2 is compressed through a logarithmic function to make it closer to the magnitude of K1. The change of H can better take into account the changes of both K1 and K2 parameters.

[0032] Generally speaking, natural changes in land are cyclical and not drastic. Human use of land can cause more drastic changes in the land's topography. Therefore, by collecting the changes in the grayscale texture evaluation index over time and making numerical predictions and comparing them, we can determine whether there are traces of human use on the land.

[0033] Furthermore, step S400 includes:

[0034] Step S401: obtaining an abnormal land use detection plan for a target plot, and in two adjacent abnormal land use detections for the target plot, setting the former detection as the first target detection and the latter detection as the second target detection;

[0035] Step S402: The image of the target land obtained in the first target detection process is recorded as the first target image. When there is no abnormal land use in the first target image, the texture evaluation index of the first target image is obtained, which is recorded as Q 1 ;

[0036] Step S403: Obtain the time interval between the first target detection and the second target detection, and calculate the texture evaluation prediction value Q of the second target detection according to the law of the texture evaluation index changing over time. pre 2 ;

[0037] Step S404: Record the image of the target land block obtained during the second target detection process as the second target image, and obtain the texture evaluation index of the second target image, recorded as Q 2 ;

[0038] Step S405: Obtain the difference resolution coefficient r and calculate Q pre2 and Q 2 The difference ω, ω = |Q pre2 -Q 2 |, when ω>r, an alarm is issued to relevant management personnel.

[0039] In order to better implement the above method, a natural resource illegal land use monitoring system is also proposed, which includes: a texture acquisition module, a sparsity index management module, a clarity index management module, a grayscale image texture evaluation module, a timing model management module and a judgment module, wherein the texture acquisition module is used to acquire the texture image of the target plot, the sparsity index management module is used to calculate the sparsity index of the texture image, the clarity index management module is used to calculate the clarity index of the texture image, the grayscale image texture evaluation module is used to calculate the grayscale image texture evaluation index, the timing model management module is used to obtain the law of change of the texture evaluation index over time through a time series model, and the judgment module is used to compare the texture evaluation index in the image with the predicted value.

[0040] Furthermore, the texture acquisition module includes: a grayscale image acquisition unit, a grayscale value screening unit and a texture image management unit, wherein the grayscale image acquisition unit is used to obtain a grayscale image of the remote sensing image information of the target plot, the grayscale value screening unit is used to screen the unit grayscale images in the grayscale image according to the grayscale value, and the texture image management unit is used to collect the screened grayscale images to form a texture image of the grayscale image.

[0041] Furthermore, the sparsity index management module includes: an image ratio calculation unit, a geometric center management unit and a sparsity index calculation unit, wherein the image ratio calculation unit is used to calculate the ratio of the texture image to the grayscale image, the geometric center management unit is used to obtain the geometric center of the image block, and the sparsity index calculation unit is used to calculate the sparsity index.

[0042] Furthermore, the clarity index management module includes: a gradient vector acquisition unit, a grayscale value change coefficient calculation unit and a clarity index calculation unit, wherein the gradient vector acquisition unit is used to obtain the maximum gradient vector of the grayscale value change in the image block, the grayscale value change coefficient calculation unit is used to calculate the grayscale value change coefficient, and the clarity index calculation unit is used to calculate the clarity index.

[0043] Furthermore, the judgment module includes: a plan management unit, a texture evaluation index prediction unit, a texture evaluation index comparison unit and an information prompt unit, wherein the plan management unit is used to obtain a detection plan for abnormal land use, the texture evaluation index prediction unit is used to predict the value of the texture evaluation index of the second target image, the texture evaluation index comparison unit is used to compare the difference between the actual value and the predicted value of the texture evaluation index of the second target image, and the information prompt unit is used to issue an alarm to relevant management personnel when the difference meets the conditions.

[0044] Compared with the prior art, the present invention has the following beneficial effects: the present invention collects image information corresponding to the land, pre-processes the image information, and reduces the storage volume of the image per unit quantity. The texture information of the image is collected, and the texture is evaluated by the density and clarity of the texture to obtain the texture features in the image. The law of how the texture features in the image change over time is obtained, and a reference value for the next detection is generated. The above method reduces the amount of calculation for image similarity calculation in the image feature comparison process, and at the same time, the historical image features are extracted to reduce the storage space required for the historical image information. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 This is a structural schematic diagram of a natural resource illegal land use monitoring system of the present invention;

[0046] Figure 2 A flow chart of a method for monitoring illegal land use of natural resources according to the present invention; DETAILED DESCRIPTION

[0047] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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.

[0048] Example: Figure 1 and Figure 2 As shown, the present invention provides a technical solution:

[0049] Step S100: a certain plot of land under abnormal land use monitoring is taken as a target plot, remote sensing image information of the target plot is collected, and an image texture area of ​​the image information is acquired to obtain a texture image of the target plot;

[0050] In the embodiment, after collecting the remote sensing image information of the target land parcel, the remote sensing image is subjected to noise reduction processing;

[0051] For example, the noise processing of remote sensing images is divided into additive noise and multiplicative noise and processed separately;

[0052] Among them, the additive noise in the remote sensing image is processed by a mean filter, the remote sensing image is Fourier transformed, the time domain image is converted into a frequency domain image, and the frequency component where the noise is located is filtered out;

[0053] Wherein, step S100 includes:

[0054] Step S101: collect remote sensing image information of any target plot, convert the remote sensing image into a grayscale image, and the grayscale quantization interval is [0, G], where G represents the maximum grayscale value in the grayscale image quantization interval;

[0055] Usually, the interval [0, 255] is used in the grayscale value calculation process, where 0 represents black and 255 represents white;

[0056] Step S102: performing grid processing on the grayscale image, dividing the grayscale image into a number of unit grayscale images of the same shape and size, obtaining the grayscale values ​​of all the unit grayscale images, and calculating the average grayscale value of all the unit grayscale images, which is recorded as Gra;

[0057] Step S103: Obtain the i-th unit grayscale image ui among all unit grayscale images, and obtain the grayscale value G corresponding to ui ui , calculate the grayscale judgment value D of ui ui , Du i =G ui +α×Gra, where α represents the proportionality coefficient, α∈(0,2);

[0058] Step S104: When D ui ≥G, the i-th unit grayscale image is set as the selected unit image, and all the selected unit images in the grayscale image are collected to form the image set Re;

[0059] Step S105: obtain an image set A consisting of all unit grayscale images in the grayscale image, calculate a texture image set B, B=A-Re, and collect all unit grayscale images in the texture image set B to form a texture image TU of the grayscale image.

[0060] Step S200: obtaining a sparseness index and a clarity index of a texture in a texture image, and constructing a texture evaluation index of the texture image;

[0061] Wherein, step S200 includes:

[0062] Step S201: Calculate the ratio β of the texture image set B to the image set A, β=numB / numA, where numB represents the number of unit grayscale images in the texture image set B, and numA represents the number of unit grayscale images in the image set A;

[0063] Step S202: in the texture image set B, an image composed of continuous unit grayscale images is set as an image block, and all image blocks in the texture image set B are labeled;

[0064] Step S203: obtaining the geometric center of each image block in the texture image TU, obtaining the distance between the geometric centers of any two image blocks in the texture image TU, calculating the variance var of the distances between all geometric centers, and calculating the sparsity index K1, K1=β×var;

[0065] Step S204: Obtain the j-th image block in the texture image TU, and obtain the maximum gradient vector grd of the gray value change in the j-th image block j , calculate the maximum gradient vector grd j The modulus length m j ;

[0066] Step S205: In the jth image block, obtain the maximum gradient vector grd j The unit grayscale image with the largest grayscale value in the direction and the unit grayscale image with the smallest grayscale value, where the grayscale value of the unit grayscale image with the largest grayscale value is recorded as G j max , the gray value of the unit gray image with the smallest gray value is recorded as G j min ;

[0067] Step S206: Calculate the gray value variation coefficient γ j , γ j =(G j max -G j min ) / G j max , calculate the clarity index k of the jth image block j , k j =(1-γ j )×m j , the average value of the clarity indexes of all image blocks is recorded as the clarity index K2;

[0068] Step S207: constructing a grayscale image texture evaluation index H, H=K1×ln(1+K2), where ln represents a logarithmic function.

[0069] Step S300: when there is no anomaly in the target plot, remote sensing image information of several target plots is collected in chronological order, texture evaluation indexes of texture graphics are calculated respectively, and the law of change of texture evaluation index over time is obtained through the time series model;

[0070] The time series model is used to obtain the temporal variation pattern of the texture evaluation index. Commonly used time series models include the ARMA model, the ARIMA model, and the long short-term memory network (LSTM).

[0071] Step S400: taking a certain abnormal land use detection of a target plot as a first target detection, taking the corresponding value in the first target detection process as a first target image, obtaining the time interval between the first target detection and the second target detection, predicting the texture evaluation index of the image during the second target detection, and when the texture evaluation index in the image corresponding to the second target detection is different from the predicted value, giving an alarm to the relevant management personnel;

[0072] Wherein, step S400 includes:

[0073] Step S401: obtaining an abnormal land use detection plan for a target plot, and in two adjacent abnormal land use detections for the target plot, setting the former detection as the first target detection and the latter detection as the second target detection;

[0074] Step S402: The image of the target land obtained in the first target detection process is recorded as the first target image. When there is no abnormal land use in the first target image, the texture evaluation index of the first target image is obtained, which is recorded as Q 1 ;

[0075] Step S403: Obtain the time interval between the first target detection and the second target detection, and calculate the texture evaluation prediction value Q of the second target detection according to the law of the texture evaluation index changing over time. pre 2 ;

[0076] Step S404: Record the image of the target land block obtained during the second target detection process as the second target image, and obtain the texture evaluation index of the second target image, recorded as Q 2 ;

[0077] Step S405: Obtain the difference resolution coefficient r and calculate Q pre2 and Q 2 The difference ω, ω = |Q pre2 -Q 2 |, when ω>r, an alarm is given to the relevant management personnel;

[0078] R is the discrimination coefficient, which is used to indicate the threshold of obvious difference when exceeding a certain range of values. Relevant personnel can adjust the difference judgment threshold through experience. When there is no threshold setting in the system, select r = 0.1×|Q pre2 -Q 2 |.

[0079] The system includes:

[0080] Texture acquisition module, sparsity index management module, clarity index management module, grayscale image texture evaluation module, timing model management module and judgment module;

[0081] The texture acquisition module is used to acquire the texture image of the target land parcel, wherein the texture acquisition module includes: a grayscale image acquisition unit, a grayscale value screening unit and a texture image management unit, wherein the grayscale image acquisition unit is used to acquire the grayscale image of the remote sensing image information of the target land parcel, the grayscale value screening unit is used to screen the unit grayscale image in the grayscale image according to the grayscale value, and the texture image management unit is used to collect the screened grayscale images to form the texture image of the grayscale image;

[0082] The sparseness index management module is used to calculate the sparseness index of the texture image, wherein the sparseness index management module includes: an image ratio calculation unit, a geometric center management unit and a sparseness index calculation unit, wherein the image ratio calculation unit is used to calculate the ratio of the texture image to the grayscale image, the geometric center management unit is used to obtain the geometric center of the image block, and the sparseness index calculation unit is used to calculate the sparseness index;

[0083] The clarity index management module is used to calculate the clarity index of the texture image, wherein the clarity index management module includes: a gradient vector acquisition unit, a gray value change coefficient calculation unit and a clarity index calculation unit, wherein the gradient vector acquisition unit is used to obtain the maximum gradient vector of the gray value change in the image block, the gray value change coefficient calculation unit is used to calculate the gray value change coefficient, and the clarity index calculation unit is used to calculate the clarity index;

[0084] Among them, the grayscale image texture evaluation module is used to calculate the grayscale image texture evaluation index;

[0085] Among them, the time series model management module is used to obtain the law of texture evaluation index changing over time through the time series model;

[0086] Among them, the judgment module is used to compare the texture evaluation index in the image with the predicted value, wherein the judgment module includes: a plan management unit, a texture evaluation index prediction unit, a texture evaluation index comparison unit and an information prompt unit, wherein the plan management unit is used to obtain a detection plan for abnormal land use, the texture evaluation index prediction unit is used to predict the value of the texture evaluation index of the second target image, the texture evaluation index comparison unit is used to compare the difference between the actual value and the predicted value of the texture evaluation index of the second target image, and the information prompt unit is used to issue an alarm to relevant management personnel when the difference meets the conditions.

[0087] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A method for monitoring illegal use of natural resources, characterized by: Step S100: a certain plot of land under abnormal land use monitoring is taken as a target plot, remote sensing image information of the target plot is collected, and an image texture area of ​​the image information is acquired to obtain a texture image of the target plot; Step S200: obtaining a sparseness index and a clarity index of a texture in a texture image, and constructing a texture evaluation index of the texture image; Step S300: when there is no anomaly in the target plot, remote sensing image information of several target plots is collected in chronological order, texture evaluation indexes of texture graphics are calculated respectively, and the law of change of texture evaluation index over time is obtained through the time series model; Step S400: Take a certain abnormal land use detection of a target plot as the first target detection, take the corresponding image in the first target detection process as the first target image, obtain the time interval between the first target detection and the second target detection, predict the texture evaluation index of the image during the second target detection, and when the texture evaluation index in the image corresponding to the second target detection is different from the predicted value, issue an alarm to the relevant management personnel.

2. A natural resource illegal land use monitoring method according to claim 1, characterized in that: Step S100 includes: Step S101: collect remote sensing image information of any target plot, and convert the remote sensing image into a grayscale image, wherein the grayscale quantization interval is [0, G], where G represents the maximum grayscale value in the grayscale image quantization interval; Step S102: performing grid processing on the grayscale image, dividing the grayscale image into a number of unit grayscale images of the same shape and size, obtaining the grayscale values ​​of all the unit grayscale images, and calculating the average grayscale value of all the unit grayscale images, which is recorded as Gra; Step S103: Obtain the i-th unit grayscale image ui among all unit grayscale images, and obtain the grayscale value G corresponding to ui ui , calculate the grayscale judgment value D of ui ui , D ui =G ui +α×Gra, where α represents the proportionality coefficient, α∈(0,2); Step S104: When D ui ≥G, the i-th unit grayscale image is set as the selected unit image, and all the selected unit images in the grayscale image are collected to form the image set Re; Step S105: Obtain an image set A consisting of all unit grayscale images in the grayscale image, calculate a texture image set B, B=A-Re, and collect all unit grayscale images in the texture image set B to form a texture image TU of the grayscale image.

3. A natural resource illegal land use monitoring method according to claim 2, characterized in that: In step S200, the step of calculating the sparsity index includes: Step S201: Calculate the ratio β of the texture image set B to the image set A, β=numB / numA, where numB represents the number of unit grayscale images in the texture image set B, and numA represents the number of unit grayscale images in the image set A; Step S202: in the texture image set B, an image composed of continuous unit grayscale images is set as an image block, and all image blocks in the texture image set B are marked; Step S203: obtain the geometric center of each image block in the texture image TU, obtain the distance between the geometric centers of any two image blocks in the texture image TU, calculate the variance var of the distances between all geometric centers, and calculate the sparsity index K1, K1 = β×var.

4. A natural resource illegal land use monitoring method according to claim 3, characterized in that: In step S200, the step of calculating the clarity index includes: Step S204: Obtain the j-th image block in the texture image TU, and obtain the maximum gradient vector grd of the gray value change in the j-th image block j , calculate the maximum gradient vector grd j The modulus length m j ; Step S205: In the j-th image block, obtain the maximum gradient vector grd j The unit grayscale image with the largest grayscale value in the direction and the unit grayscale image with the smallest grayscale value, where the grayscale value of the unit grayscale image with the largest grayscale value is recorded as G j max , the gray value of the unit gray image with the smallest gray value is recorded as G j min ; Step S206: Calculate the gray value variation coefficient γ j , γ j =(G j max -G j min ) / G j max , calculate the clarity index k of the jth image block j , k j =(1-γ j )×m j , the average value of the clarity indexes of all image blocks is recorded as the clarity index K2.

5. A natural resource illegal land use monitoring method according to claim 1, characterized in that: In step S200, the method for constructing the texture evaluation index includes: Step S207: constructing a grayscale image texture evaluation index H, H=K1×ln(1+K2), where ln represents a logarithmic function.

6. A natural resource illegal land use monitoring method according to claim 1, characterized in that: Step S400 includes: Step S401: obtaining an abnormal land use detection plan for a target plot, and in two adjacent abnormal land use detections for the target plot, setting the former detection as the first target detection and the latter detection as the second target detection; Step S402: Recording the image of the target land block obtained in the first target detection process as the first target image. When there is no abnormal land use in the first target image, obtaining the texture evaluation index of the first target image, recorded as Q1; Step S403: Obtain the time interval between the first target detection and the second target detection, and calculate the texture evaluation prediction value Q of the second target detection according to the law of the texture evaluation index changing over time. pre 2; Step S404: Record the image of the target land block obtained in the second target detection process as the second target image, and obtain the texture evaluation index of the second target image, recorded as Q2; Step S405: Obtain the difference resolution coefficient r and calculate Q pre2 The difference between Q2 and ω, ω = |Q pre2 -Q2|, when ω>r, an alarm is issued to the relevant management personnel.

7. A natural resource illegal land use monitoring system, used to implement a natural resource illegal land use monitoring method according to any one of claims 1 to 6, characterized in that: The system includes: A texture acquisition module, a sparsity index management module, a clarity index management module, a grayscale image texture evaluation module, a timing model management module and a judgment module, wherein the texture acquisition module is used to acquire the texture image of the target plot, the sparsity index management module is used to calculate the sparsity index of the texture image, the clarity index management module is used to calculate the clarity index of the texture image, the grayscale image texture evaluation module is used to calculate the grayscale image texture evaluation index, the timing model management module is used to obtain the law of change of the texture evaluation index over time through a time series model, and the judgment module is used to compare the texture evaluation index in the image with the predicted value.

8. A natural resource illegal land use monitoring system according to claim 7, characterized in that: The texture acquisition module includes: a grayscale image acquisition unit, a grayscale value screening unit and a texture image management unit, wherein the grayscale image acquisition unit is used to obtain a grayscale image of the remote sensing image information of the target plot, the grayscale value screening unit is used to screen the unit grayscale images in the grayscale image according to the grayscale value, and the texture image management unit is used to collect the screened grayscale images to form a texture image of the grayscale image.

9. A natural resource illegal land use monitoring system according to claim 7, characterized in that: The sparsity index management module includes: an image ratio calculation unit, a geometric center management unit and a sparsity index calculation unit, wherein the image ratio calculation unit is used to calculate the ratio of the texture image to the grayscale image, the geometric center management unit is used to obtain the geometric center of the image block, and the sparsity index calculation unit is used to calculate the sparsity index; The clarity index management module includes: a gradient vector acquisition unit, a grayscale value change coefficient calculation unit and a clarity index calculation unit, wherein the gradient vector acquisition unit is used to obtain the maximum gradient vector of the grayscale value change in the image block, the grayscale value change coefficient calculation unit is used to calculate the grayscale value change coefficient, and the clarity index calculation unit is used to calculate the clarity index.

10. A natural resource illegal land use monitoring system according to claim 7, characterized in that: The judgment module includes: a plan management unit, a texture evaluation index prediction unit, a texture evaluation index comparison unit and an information prompt unit, wherein the plan management unit is used to obtain a detection plan for abnormal land use, the texture evaluation index prediction unit is used to predict the value of the texture evaluation index of the second target image, the texture evaluation index comparison unit is used to compare the difference between the actual value and the predicted value of the texture evaluation index of the second target image, and the information prompt unit is used to issue an alarm to relevant management personnel when the difference meets the conditions.

Images