Multi-source Data Processing Method and System Applied to Territorial Spatial Planning

Abstract

The present invention relates to the technical field of image processing, and specifically relates to a multi-source data processing method and system applied to territorial spatial planning. For any scale, according to the morphological differences of the corresponding connected regions of remote sensing images between different times in each same area, the stable change regions are screened out; the morphological feature vectors of the corresponding connected regions of each stable change region at different times are used to form the row vectors of the morphological change feature matrix; the augmented prediction matrix of the morphological change feature matrix is obtained, and according to the position distribution of the pixel points in the corresponding connected regions of the stable change regions at different times and the change stability corresponding in the augmented prediction matrix, the remote sensing attention degree of each stable change region is obtained; furthermore, the final fusion voting value of each stable change region at each scale is obtained; data fusion is performed on the remote sensing images. By obtaining the accurate final fusion voting value of the remote sensing images at each scale, the present invention improves the effect of remote sensing data fusion.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and particularly to a multi-source data processing method and system applied to territorial spatial planning. Background Art

[0002] In territorial spatial planning, multi-source data processing technology is to better integrate, analyze and apply data from different sources, so as to provide a scientific basis for planning decisions. Specifically, multi-source refers to remote sensing data from different sensor platforms and different types of sensors. Different sensors can provide data with different field of view ranges, spatial resolutions, temporal resolutions and observation angles. Since the data obtained by different sensors in the same area may be redundant or contradictory, through data fusion, the advantages of different sensors can be fully utilized to eliminate these inconsistencies, obtain more accurate and reliable information, and at the same time try to retain and enhance important key information such as space, spectrum, time, geometry, etc., to ensure that the final data has good performance in many aspects.

[0003] For multi-source remote sensing data, synthesis is required to accurately analyze the overall characteristics of the region. In the prior art, mean coverage can be used to perform data fusion on multi-source remote sensing data; however, since remote sensing images present different characteristics at different scales over the time dimension, ignoring the multi-scale characteristics of the time dimension will result in direct mean fusion being unable to comprehensively capture these changes, and the effect of remote sensing image data fusion is poor. Summary of the Invention

[0004] In order to solve the technical problem that the effect of remote sensing image data fusion is poor due to ignoring the multi-scale characteristics of the time dimension, the purpose of the present invention is to provide a multi-source data processing method and system applied to territorial spatial planning, and the specific technical solutions adopted are as follows:

[0005] The present invention proposes a multi-source data processing method applied to territorial spatial planning, and the method includes:

[0006] Obtain remote sensing images of different preset scales at each moment in the area to be fused during territorial spatial planning;

[0007] Obtain multiple connected components of each remote sensing image according to the gray distribution of pixel points in the remote sensing image; for any scale, obtain the change effect of the connected components corresponding to each region according to the morphological differences of the connected components corresponding to the same region in the remote sensing images between different moments; screen out the changed regions according to the change effects of the connected components corresponding to all regions; obtain the change stability of the connected components corresponding to each changed region according to the morphological differences of the connected components corresponding to each changed region between adjacent moments; screen out the stably changed regions according to the change stabilities of the connected components corresponding to all changed regions;

[0008] Taking the morphological features of the connected regions corresponding to each change-stable region at different times as the row vectors of the morphological change feature matrix; obtaining the augmented prediction matrix of the morphological change feature matrix, and obtaining the remote sensing attention degree of each change-stable region according to the position distribution of the pixel points in the connected regions corresponding to the change-stable regions at different times and the change stability corresponding in the augmented prediction matrix.

[0009] According to the morphological features of the connected regions corresponding to each change-stable region at different times at each scale and the remote sensing attention degree, obtaining the final fusion voting value of each change-stable region at each scale; based on the final fusion voting values of each change-stable region at different scales, performing data fusion on the remote sensing images during the territorial spatial planning.

[0010] Further, the method for obtaining the change effect includes:

[0011] Obtaining the number of pixel points in each connected region as the morphological feature.

[0012] For any scale, obtaining the morphological feature differences of the connected regions corresponding to the same region in the remote sensing images between different adjacent times, accumulating all the morphological feature differences between adjacent times, and normalizing them as the change effect of the connected regions corresponding to each region.

[0013] Further, the method for obtaining the change region includes:

[0014] If the change effect of the connected region corresponding to the region is included in the preset change range, the corresponding region is used as the change region.

[0015] Further, the method for obtaining the change stability includes:

[0016] Obtaining the morphological feature difference between the connected regions corresponding to each change region at each moment and the previous adjacent moment as the change difference of the corresponding change region at each moment.

[0017] Obtaining the difference of the change differences corresponding to the change region between adjacent times and performing a negative correlation mapping as the difference similarity between adjacent times.

[0018] Calculating the mean value of the difference similarities between all adjacent times of each change region as the change stability of the connected region corresponding to each change region.

[0019] Further, the method for obtaining the change-stable region includes:

[0020] If the change stability of the connected region corresponding to the change region is included in the preset stable range, the corresponding change region is used as the change-stable region.

[0021] Further, the method for obtaining the remote sensing attention degree includes:

[0022] For each stable change region, obtain the different pixel points within the corresponding connected domain between each moment and the previous adjacent moment. Connect each different pixel point to the center of the connected domain at the corresponding moment by a straight line, and obtain the angle between the straight line and the horizontal direction as the change angle of each different pixel point at the corresponding moment.

[0023] Obtain the average value of the change angles of all different pixel points at the corresponding moment as the local moment change angle; obtain the average value of the moment change angles at all moments as the overall moment change angle; obtain the difference between the local moment change angle and the overall moment change angle at each moment as the change angle difference.

[0024] According to the change angle difference of each stable change region and the change stability in the augmented prediction matrix, obtain the remote sensing attention degree of each stable change region. The change angle difference is negatively correlated with the remote sensing attention degree, and the change stability is positively correlated with the remote sensing attention degree.

[0025] Further, the method for obtaining the final fusion voting value includes:

[0026] Obtain the average value of the morphological feature of the corresponding connected domain at all moments of each stable change region at each scale as the local morphological feature of the corresponding connected domain of each stable change region at each scale.

[0027] Fuse the local morphological feature and the remote sensing attention degree of each stable change region at each scale, and perform normalization mapping as the final fusion voting value of each stable change region at each scale.

[0028] Further, the method for obtaining the augmented prediction matrix includes:

[0029] Use the ARIMA prediction algorithm to predict each row vector of the morphological change feature matrix, obtain the predicted value of each row vector, and form the row vector of the augmented prediction matrix with the elements of the predicted value and the corresponding row vector of the morphological change matrix.

[0030] Further, the method for obtaining the connected domain includes:

[0031] Use CANNY edge detection to obtain the edge detection grayscale image of each remote sensing image; use the connected domain detection algorithm to obtain multiple connected domains of the edge detection grayscale image.

[0032] The present invention also provides a multi-source data processing system applied to territorial spatial planning, including a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the steps of any one of the multi-source data processing methods applied to territorial spatial planning are implemented.

[0033] The present invention has the following beneficial effects:

[0034] The present invention takes into account that different types of ground objects and regions are distributed in remote sensing images, and obtains multiple connected components of each remote sensing image according to the gray-scale distribution of pixel points in the remote sensing image; for any scale, according to the morphological differences of the connected components corresponding to the same region in the remote sensing images at different times, the stable change regions are screened out, and those regions with stable changes and clear trends are screened out; the morphological characteristics of the connected components corresponding to each stable change region at different times are used to form the row vectors of the morphological change feature matrix; the augmented prediction matrix of the morphological change feature matrix is obtained to enhance the prediction ability and stability of the feature matrix, which helps to more accurately describe the laws and trends of ground object changes. According to the position distribution of pixel points in the connected components corresponding to the stable change regions at different times and the change stability corresponding to the augmented prediction matrix, the remote sensing attention degree of each stable change region is obtained, which reflects the importance and attention degree of different stable change regions in remote sensing data analysis, and provides a weight basis for subsequent fusion voting and data fusion; considering the time change characteristics of different scales, according to the morphological characteristics of the connected components corresponding to each stable change region at different times and scales, and the remote sensing attention degree, the final fusion voting value of each stable change region is obtained; data fusion is performed on the remote sensing images. By fusing data from different sources and scales, the deficiencies of a single data source can be made up, and the accuracy and efficiency of information extraction can be improved. The present invention improves the effect of remote sensing data fusion by obtaining accurate final fusion voting values for remote sensing images at each scale. Description of the Drawings

[0035] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0036] Figure 1 It is a flowchart of a multi-source data processing method applied to territorial spatial planning provided by an embodiment of the present invention;

[0037] Figure 2 It is a flowchart of a method for obtaining change stability provided by an embodiment of the present invention;

[0038] Figure 3 It is a flowchart of a method for obtaining remote sensing attention degree provided by an embodiment of the present invention. Detailed Embodiments

[0039] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following specifically describes, with reference to the accompanying drawings and preferred embodiments, a multi-source data processing method and system applied to territorial spatial planning, including its specific implementation manner, structure, features, and effects, as follows. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments may be combined in any suitable form.

[0040] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which the present invention belongs.

[0041] The following specifically describes, with reference to the accompanying drawings, the specific solution of a multi-source data processing method and system applied to territorial spatial planning provided by the present invention.

[0042] Please refer to Figure 1 , which shows the flowchart of a multi-source data processing method applied to territorial spatial planning provided by an embodiment of the present invention. The specific method includes:

[0043] Step S1: Obtain remote sensing images of different scales at each moment in the area to be fused during territorial spatial planning.

[0044] In an embodiment of the present invention, remote sensing technology can be applied to multiple fields such as territorial spatial planning, construction land monitoring, land geological survey, environmental protection, and earthquake disasters to timely discover key information such as changes in surface cover types, trends of urban expansion, and the affected areas after disasters. Since multi-source remote sensing data have their own characteristics and advantages, in order to highlight the key feature areas of images at different scales and improve the accuracy and reliability of remote sensing information, data fusion of multi-source remote sensing data is required. First, it is necessary to analyze at a fixed collection location to obtain remote sensing images of different scales at each moment in the area to be fused.

[0045] It should be noted that in an embodiment of the present invention, the time interval is one week, and the scales are resolutions and field of view ranges of different sizes, which are increased in an arithmetic progression until the maximum resolution and field of view range are reached, and the remote sensing images of different field of view ranges at different resolutions are analyzed; among them, the value increased each time is 1 / 10 of the maximum resolution or field of view range; in an embodiment of the present invention, the size of the time interval and scale can be specifically set according to specific circumstances, and will not be limited and elaborated here.

[0046] Step S2: Obtain multiple connected components of each remote sensing image according to the gray-scale distribution of pixel points in the remote sensing image; for any scale, obtain the change effect of the connected components corresponding to each same area in the remote sensing images between different times according to the morphological differences of the connected components; screen out the changed areas according to the change effects of the connected components corresponding to all areas; obtain the change stability of the connected components corresponding to each changed area according to the morphological differences of the connected components corresponding to each changed area between adjacent times; screen out the stable changed areas according to the change stabilities of the connected components corresponding to all changed areas.

[0047] Since remote sensing images usually contain complex surface information, such as buildings, roads, vegetation, water bodies, etc., and pixel points with different gray-scale characteristics are presented in the images. Therefore, obtaining multiple connected components of each remote sensing image according to the gray-scale distribution of pixel points in the remote sensing image can reduce the interference of noise on the analysis, which helps to perform separate processing and analysis on each area subsequently, thereby improving the accuracy and pertinence of the processing.

[0048] Preferably, in an embodiment of the present invention, the method for obtaining connected components includes:

[0049] Use the CANNY edge detection algorithm to obtain the edge detection gray-scale image of each remote sensing image; use the connected component detection algorithm to obtain multiple connected components of the edge detection gray-scale image.

[0050] It should be noted that the specific CANNY edge detection algorithm and connected component detection algorithm are well-known technical means to those skilled in the art and will not be elaborated here.

[0051] Since the vegetation area may be affected by factors such as seasonal withering or fire, and when karst collapse occurs in the geology, the objects in the corresponding area will also change. At different times, the objects in the corresponding area of the image may expand or contract, resulting in the area of the corresponding connected component may increase or decrease, and the morphological characteristics of the connected component change, and the change effect of the corresponding connected component is relatively large. Therefore, for any scale, obtain the change effect of the connected component corresponding to each same serial number according to the morphological differences of the connected components between different times.

[0052] Preferably, in an embodiment of the present invention, the method for obtaining the change effect includes:

[0053] Obtain the number of pixel points in each connected component as the morphological feature;

[0054] For any scale, obtain the morphological feature differences of the connected components corresponding to each same area in the remote sensing images between different adjacent times, accumulate all the morphological feature differences between adjacent times, and perform normalization, which is used as the change effect of the connected component corresponding to each area.

[0055] In an embodiment of the present invention, for any scale, the formula for the variation effect is expressed as:

[0056] ;

[0057] Wherein, represents the variation effect of the connected domain corresponding to the th region; represents the morphological feature of the connected domain corresponding to the th region of the remote sensing image at the th moment; represents the morphological feature of the connected domain corresponding to the th region of the remote sensing image at the th moment; represents the number of all moments; represents taking the absolute value; represents the normalization function.

[0058] In the formula for the variation effect, represents calculating the difference in the morphological features of the connected domains corresponding to the same regions of the remote sensing image at different moments. The greater the difference in morphological features, the greater the difference in the number of pixel points within the connected domain, and the greater the variation in the remote sensing information within the connected domain, and the more attention needs to be paid.

[0059] The variation effect can reflect which regions of the image have changed significantly at different times. By screening out the regions with significant changes, the dynamic changes in the corresponding scene of the image can be understood in real time; therefore, according to the variation effects of the connected domains corresponding to all regions, the regions with changes are screened out.

[0060] Preferably, in an embodiment of the present invention, the method for obtaining the variable connected domain includes:

[0061] If the variation effect of the connected domain corresponding to the region is included within a preset variation range, the corresponding region is used as the variable region.

[0062] It should be noted that, in an embodiment of the present invention, the preset variation range is 0.8 - 1. In other embodiments of the present invention, the size of the preset variation range can be specifically set according to specific situations, and no limitation and elaboration are made here.

[0063] The continuous change of the morphological features of the connected domain at different moments reflects the stability and trend of the change in the corresponding region. The more consistent the trend of the differential change, the relatively stable the change in the changed region, and the more conducive to subsequent analysis; according to the morphological differences of the connected domains corresponding to each variable region between adjacent moments, the variation stability of the connected domain corresponding to each variable region is obtained.

[0064] Preferably, in an embodiment of the present invention, the method for obtaining the variation stability includes referring toFigure 2 , which shows a flowchart of a method for obtaining variable stability, including:

[0065] Step S201: Obtain the morphological feature difference of the corresponding connected domain between each variable region at each moment and the previous adjacent moment, as the variability of the corresponding variable region at each moment.

[0066] In an embodiment of the present invention, the formula for variability is expressed as:

[0067] ;

[0068] Wherein, represents the variability of the th moment corresponding to the th variable region; represents the morphological feature of the connected domain corresponding to the th variable region in the remote sensing image at the th moment; represents the morphological feature of the connected domain corresponding to the th variable region in the remote sensing image at the th moment; represents taking the absolute value.

[0069] In the formula for variability, represents the morphological feature difference of the connected domain corresponding to the th moment and the th moment in the remote sensing image of the th variable region. The greater the difference, the greater the variability.

[0070] Step S202: Obtain the difference of the corresponding variability between each variable region at adjacent moments, and perform a negative correlation mapping, as the difference similarity between adjacent moments.

[0071] The corresponding variability between each variable region at adjacent moments reflects the dynamic change of the corresponding region in time. Calculating the difference of the variability can quantify the consistency of the regional dynamic change. The greater the difference, the smaller the change consistency. Therefore, a negative correlation mapping is performed on the difference of the variability. The greater the difference, the smaller the difference similarity.

[0072] Step S203: Calculate the mean value of the difference similarity between each variable region at all adjacent moments, as the variable stability of the corresponding connected domain of each variable region.

[0073] Quantify the overall distribution of the difference similarity between each variable region at all adjacent moments by taking the mean value to obtain variable stability. The smaller the difference similarity, the greater the variable stability.

[0074] In an embodiment of the present invention, the acquisition formula for the variation stability is expressed as:

[0075] ;

[0076] wherein, represents the variation stability of the connected domain corresponding to the th variation region; represents the variation difference of the th moment corresponding to the th variation region; represents the variation difference of the th moment corresponding to the th variation region; represents the exponential function with the natural constant as the base; represents the number of all moments.

[0077] In the formula for the variation stability, represents performing a negative correlation mapping on through the exponential function with the natural constant as the base, that is, the difference similarity. represents the difference between the variation differences of the th moment and the th moment corresponding to the th variation region. The greater the difference, the greater the difference in the variation differences and the smaller the difference similarity; represents calculating the mean value of the difference similarities between all adjacent moments of each variation region, that is, the variation stability. The smaller the mean value of the difference similarities, the smaller the difference similarity, the greater the difference in the variation differences, the more inconsistent the variation situation, and the smaller the variation stability.

[0078] It should be noted that in an embodiment of the present invention, is used to perform a negative correlation mapping on to form a negative correlation relationship where the smaller the difference, the more consistent the variation situation, and the greater the variation stability. In other embodiments of the present invention, the reciprocal of can be taken to achieve the negative correlation relationship. Among them, if the reciprocal is used to achieve the negative correlation, a manually set parameter such as 0.01 needs to be added to the denominator to avoid the denominator being 0 and the formula being meaningless. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0079] In remote sensing images, there are often a large number of variation regions, but not all regions have the same stability. By screening the variation stable regions, those regions with frequent changes, instability, or high noise can be removed, thereby reducing the redundancy and complexity of the data and helping to obtain useful information more quickly. According to the variation stability of the connected domains corresponding to all variation regions, the variation stable regions are screened out.

[0080] Preferably, in an embodiment of the present invention, the method for obtaining the variable stable connected region includes:

[0081] If the change stability of the connected region corresponding to the variable region is included in the preset stable range, the corresponding variable region is used as the variable stable region.

[0082] It should be noted that, in an embodiment of the present invention, the size of the preset stable range is 0.9 - 1. In other embodiments of the present invention, the size of the preset stable range can be specifically set according to specific circumstances, and no limitation and elaboration will be made here.

[0083] Step S3: Use the morphological feature of the connected region corresponding to each variable stable region at different times to form the row vector of the morphological change feature matrix; obtain the augmented prediction matrix of the morphological change feature matrix, and obtain the remote sensing attention degree of each variable stable region according to the position distribution of the pixel points in the connected region corresponding to the variable stable region at different times and the change stability of the connected region in the augmented prediction matrix.

[0084] The morphological change feature matrix quantifies the morphological features of each variable stable region at different times, making the morphological changes concrete and visual, which helps to more intuitively understand the changes of the region. Use the morphological feature of the connected region corresponding to each variable stable region at different times to form the row vector of the morphological change feature matrix. It should be noted that each element in the row vector is the number of pixel points in the connected region corresponding to each variable stable region at each moment.

[0085] In order to more accurately analyze the changes at different times, obtain the augmented prediction matrix of the morphological change feature matrix, and more comprehensively understand the future change trend of the region.

[0086] Preferably, in an embodiment of the present invention, the method for obtaining the augmented prediction matrix includes:

[0087] Use the ARIMA prediction algorithm to predict each row vector of the morphological change feature matrix, obtain the predicted value of each row vector, and form the row vector of the augmented prediction matrix with the predicted value and the elements of the corresponding row vector of the morphological change matrix.

[0088] It should be noted that the specific ARIMA prediction algorithm is a technical means well-known to those skilled in the art, and no elaboration will be made here.

[0089] The positional distribution of pixel points can reflect the complexity and dynamics of the internal structure of the region. By comparing the positional distributions at different times, it is possible to identify which regions remain stable over time and which regions have undergone significant changes, which helps to understand which regions need to be concerned. The augmented prediction matrix can evaluate future change trends. The greater the corresponding change stability, the greater the remote sensing attention. Combining the two for comprehensive analysis can more accurately evaluate the remote sensing attention of each change-stable region. According to the positional distribution of pixel points in the corresponding connected domain of the change-stable region at different times and the change stability in the augmented prediction matrix, the remote sensing attention of each change-stable region is obtained.

[0090] Preferably, in an embodiment of the present invention, for the method of obtaining remote sensing attention, please refer to Figure 3 , which shows a flowchart of a method for obtaining remote sensing attention, including:

[0091] Step S301: For each change-stable region, obtain the differential pixel points within the corresponding connected domain between each moment and the previous adjacent moment. Connect each differential pixel point to the center of the connected domain at the corresponding moment with a straight line, and obtain the angle between the straight line and the horizontal direction as the change angle of each differential pixel point at the corresponding moment.

[0092] Differential pixel points represent the pixel points where the connected domain has changed between adjacent moments, reflecting the dynamic changes within the region. By calculating the angle between the straight line connecting the differential pixel point and the center of the connected domain and the horizontal direction, the change direction of each differential pixel point can be quantified, which helps to understand the trend of change.

[0093] It should be noted that the center of the connected domain refers to the centroid of the connected domain, that is, the average position of all pixel points within the connected domain.

[0094] Step S302: Obtain the average value of the change angles of all differential pixel points at the corresponding moment as the local moment change angle; obtain the average value of the moment change angles at all moments as the overall moment change angle; obtain the difference between the local moment change angle and the overall moment change angle at each moment as the change angle difference.

[0095] By calculating the average value of the change angles of all differential pixel points, it is possible to reflect the direction and trend of changes within the connected domain at the corresponding moment, as well as the overall direction and trend of changes in the connected domain at all moments, for a global description. By comparing the difference between the local change angle and the overall change angle at each moment, the degree of difference between the changes within each moment and the overall changes can be quantified, reflecting the direction inconsistency between the changes within each moment and the overall changes, and reflecting the complexity or uncertainty of the changes.

[0096] Step S303: Obtain the remote sensing attention degree of each change stable area according to the change angle difference of each change stable area and the change stability corresponding to the augmented prediction matrix. The change angle difference is negatively correlated with the remote sensing attention degree, and the change stability is positively correlated with the remote sensing attention degree.

[0097] It should be noted that in an embodiment of the present invention, the method for obtaining the change stability corresponding to each change stable area in the augmented prediction matrix is the same as the change stability of the connected domain corresponding to each change area. By obtaining the difference between adjacent elements in the row vector of the augmented prediction matrix corresponding to each change stable area, the change stability corresponding to each change stable area in the augmented prediction matrix is obtained.

[0098] Among them, the positive correlation relationship means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. That is, the greater the change stability, the more similar the change difference between adjacent moments, and the more features need to be fused and retained, and the greater the remote sensing attention degree; the negative correlation relationship means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. That is, the greater the change angle, the more uncertain factors there are, which affect the fusion efficiency, and the smaller the remote sensing attention degree.

[0099] In an embodiment of the present invention, for any change stable area, the formula for the remote sensing attention degree is expressed as:

[0100] ;

[0101] Among them, represents the remote sensing attention degree of the th change stable area; represents the change stability corresponding to the th change stable area in the augmented prediction matrix; represents the average change angle of all difference pixel points at the th moment, that is, the local moment change angle at the th moment; represents the average of the moment change angles at all moments, that is, the overall moment change angle; represents the number of all moments; represents the adjustment parameter.

[0102] In the formula for the remote sensing attention degree, represents the difference between the local moment change angle and the overall moment change angle at the th moment, that is, the change angle difference. Add the adjustment parameter to the change angle difference to avoid the formula being meaningless when it is 0. The adjustment parameter can be taken as 0.01; It means that after performing negative correlation on the difference in change angles, the mean value of all negative correlation results is calculated. The larger the mean value, the smaller the difference in change angles, the more consistent the change directions, and the more fusion is required, resulting in a higher remote sensing attention level. The more inconsistent the change directions and the more random the changes, the more likely they are caused by noise, and attention should be avoided, resulting in a lower remote sensing attention level. The greater the change stability, the higher the remote sensing attention level.

[0103] Step S4: According to the morphological features of the connected regions corresponding to each change-stable region at different times under each scale, and the remote sensing attention level, obtain the final fusion voting value of each change-stable region at each scale; Based on the final fusion voting values of each change-stable region at different scales, perform data fusion on the remote sensing images during territorial spatial planning.

[0104] The morphological features at different times under each scale can reflect the overall trend of objects in the region, and more comprehensively reflect the representativeness of each change-stable region to the actual situation. The greater the overall trend, the greater the representativeness, and the greater the final fusion voting value; The remote sensing attention level usually reflects the importance and attention of the research region or specific target. The more changes in the remote sensing information within the region, the higher the remote sensing attention level. Comprehensive analysis can ensure that important and feature-significant regions are given priority consideration during the fusion process. According to the morphological features of the connected regions corresponding to each change-stable region at different times under each scale, and the remote sensing attention level, obtain the final fusion voting value of each change-stable region at each scale.

[0105] Preferably, in an embodiment of the present invention, the method for obtaining the final fusion voting value includes:

[0106] Obtain the mean value of the morphological features of the connected regions corresponding to each change-stable region at all times under each scale as the local morphological feature of the connected region corresponding to each change-stable region at each scale;

[0107] Fuse the local morphological feature of each change-stable region at each scale and the remote sensing attention level, and perform normalization mapping as the final fusion voting value of each change-stable region at each scale.

[0108] It should be noted that in some embodiments of the present invention, the overall morphological feature and the remote sensing attention level of each change-stable region can be fused by addition or multiplication methods. The specific methods are well-known technical means to those skilled in the art and will not be elaborated here.

[0109] In an embodiment of the present invention, the formula for the final fusion voting value is expressed as:

[0110] ;

[0111] Wherein, represents the The final fusion voting value of a change stability region at the th scale; Denote the remote sensing attention of the th change stability region; Denote the th change stability region at the th scale at the th moment corresponding to the morphological features of the connected component; Denote the number of all moments; Denote the normalization function.

[0112] In the formula of the final fusion voting value, Denote the calculation of the mean value of the morphological features of the connected components corresponding to all moments at each scale for each change stability region, that is, the local morphological features. The larger the local morphological features, the larger the corresponding connected component region, the greater the remote sensing attention, the more features are shown, and the larger the final fusion voting value.

[0113] It should be noted that in another embodiment of the present invention, after obtaining the final fusion voting value, data fusion can be performed on the remote sensing image. The fusion method is as follows: for each change stability region, use the final fusion voting value at each scale as the weight of the image region corresponding to the scale, calculate the product of the final fusion voting value at each scale and the remote sensing data within the image region as the weighted remote sensing data for each scale; calculate the mean value of the weighted remote sensing data at all scales as the fused remote sensing data; for other regions, use the direct mean value fusion method to obtain the fused remote sensing data; after obtaining the fused remote sensing data, further optimize the fusion result through methods such as filtering and morphological operations to remove unreasonable details, ensure the spatial continuity and consistency of the fused image, help improve the observability of the data, and more clearly understand the information performance of the remote sensing details in the region.

[0114] In summary, for any scale, the present invention screens out the change stability regions according to the morphological differences of the connected components corresponding to the remote sensing images between different moments in each same region; uses the morphological features of the connected components corresponding to each change stability region at different moments to form the row vectors of the morphological change feature matrix; obtains the augmented prediction matrix of the morphological change feature matrix, and obtains the remote sensing attention of each change stability region according to the position distribution of the pixel points in the connected components corresponding to the change stability regions at different moments and the change stability corresponding to the augmented prediction matrix; combines the morphological features of the connected components corresponding to each change stability region at different scales and different moments to obtain the final fusion voting value of each change stability region; performs data fusion on the remote sensing image. The present invention improves the effect of remote sensing data fusion by obtaining accurate final fusion voting values of remote sensing images at each scale.

[0115] The present invention also provides a multi-source data processing system applied to territorial spatial planning, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the multi-source data processing methods applied to territorial spatial planning are implemented.

[0116] It should be noted that the above-mentioned sequence of embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired result. In some embodiments, multi-task processing and parallel processing are also possible or may be advantageous.

[0117] Each embodiment in this specification is described in a progressive manner. For the same or similar parts among the embodiments, reference can be made to each other. Each embodiment focuses on the differences from other embodiments.

Claims

1. A multi-source data processing method applied to national land space planning, characterized in that: The method comprises: Obtain remote sensing images of different preset scales at each moment in the area to be integrated during national land space planning; According to the grayscale distribution of pixels in the remote sensing image, multiple connected domains of each remote sensing image are obtained; for any scale, according to the morphological differences of the connected domains corresponding to each same area of ​​the remote sensing image at different times, the change effect of the connected domain corresponding to each area is obtained; according to the change effect of the connected domains corresponding to all areas, the change area is screened out; according to the morphological differences of the connected domains corresponding to each change area between adjacent times, the change stability of the connected domain corresponding to each change area is obtained; according to the change stability of the connected domains corresponding to all change areas, the change stable area is screened out; The row vectors of the morphological change feature matrix are formed by the morphological features of the connected domain corresponding to each stable change region at different times; the augmented prediction matrix of the morphological change feature matrix is ​​obtained, and the remote sensing attention of each stable change region is obtained according to the position distribution of the pixel points in the connected domain corresponding to the stable change region at different times and the change stability corresponding to the augmented prediction matrix; According to the morphological characteristics of the connected domain corresponding to each stable region at different times at each scale, and the remote sensing attention, the final fusion voting value of each stable region at each scale is obtained; based on the final fusion voting value of each stable region at different scales, the remote sensing images used in national land space planning are fused. The method for obtaining the remote sensing attention degree includes: For each change-stable region, obtain the difference pixel points in the corresponding connected domain between each moment and the previous adjacent moment, connect each difference pixel point with the center of the connected domain at the corresponding moment with a straight line, and obtain the angle between the straight line and the horizontal direction as the change angle of each difference pixel point at the corresponding moment; Obtain the mean value of the change angles of all difference pixel points at the corresponding moment as the local moment change angle; obtain the mean value of the moment change angles at all moments as the overall moment change angle; obtain the difference between the local moment change angle and the overall moment change angle at each moment as the change angle difference; According to the change angle difference of each change stable area and the corresponding change stability in the augmented prediction matrix, the remote sensing attention of each change stable area is obtained. The change angle difference is negatively correlated with the remote sensing attention, and the change stability is positively correlated with the remote sensing attention.

2. The multi-source data processing method for national land space planning according to claim 1 is characterized in that: The method for obtaining the change effect includes: Obtain the number of pixels in each connected domain as a morphological feature; For any scale, the differences in morphological features of the connected domains corresponding to the same area of ​​the remote sensing images between different adjacent moments are obtained, and the differences in morphological features between all adjacent moments are accumulated and normalized as the change effect of the connected domain corresponding to each area.

3. The multi-source data processing method for national land space planning according to claim 1 is characterized in that: The method for obtaining the change area includes: If the change effect of the connected domain corresponding to the region is included in the preset change range, the corresponding region is used as the change region.

4. The multi-source data processing method for national land space planning according to claim 2 is characterized in that: The method for obtaining the variation stability includes: Obtain the difference in morphological characteristics of the corresponding connected domain of each changing region at each moment and the previous adjacent moment as the change difference of the corresponding changing region at each moment; Obtaining the difference of each change region corresponding to the change difference between adjacent moments, and performing negative correlation mapping as the difference similarity between adjacent moments; The mean value of the difference similarity between each changing region at all adjacent moments is calculated as the change stability of the connected domain corresponding to each changing region.

5. The multi-source data processing method for national land space planning according to claim 1 is characterized in that: The method for obtaining the change stable region comprises: If the change stability of the connected domain corresponding to the change region is included in the preset stability range, the corresponding change region is used as the change stable region.

6. The multi-source data processing method for national land space planning according to claim 2 is characterized in that: The method for obtaining the final fusion voting value includes: Obtain the mean value of the morphological features of the connected domain corresponding to each stable region at all times at each scale as the local morphological features of the connected domain corresponding to each stable region at each scale; The local morphological features and remote sensing attention of each stable region at each scale are fused and normalized and mapped as the final fused voting value of each stable region at each scale.

7. The multi-source data processing method for national land space planning according to claim 1 is characterized in that: The method for obtaining the augmented prediction matrix includes: The ARIMA prediction algorithm is used to predict each row vector of the morphological change feature matrix to obtain the predicted value of each row vector. The predicted value and the elements of the corresponding row vector of the morphological change matrix constitute the row vector of the augmented prediction matrix.

8. The multi-source data processing method for national land space planning according to claim 1 is characterized in that: The method for obtaining the connected domain includes: The CANNY edge detection is used to obtain the edge detection grayscale image of each remote sensing image; the connected domain detection algorithm is used to obtain multiple connected domains of the edge detection grayscale image.

9. A multi-source data processing system for national land space planning, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, it implements the steps of a multi-source data processing method applied to national land space planning as described in any one of claims 1 to 8.

Images