CN112766717B - Time dimension amplification method for urban construction land - Google Patents
Time dimension amplification method for urban construction land Download PDFInfo
- Publication number
- CN112766717B CN112766717B CN202110057306.0A CN202110057306A CN112766717B CN 112766717 B CN112766717 B CN 112766717B CN 202110057306 A CN202110057306 A CN 202110057306A CN 112766717 B CN112766717 B CN 112766717B
- Authority
- CN
- China
- Prior art keywords
- urban area
- main urban
- amplification
- image
- main
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 230000003321 amplification Effects 0.000 title claims abstract description 110
- 238000003199 nucleic acid amplification method Methods 0.000 title claims abstract description 110
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000010276 construction Methods 0.000 title claims abstract description 44
- 239000011159 matrix material Substances 0.000 claims description 78
- 238000012163 sequencing technique Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 230000001360 synchronised effect Effects 0.000 claims description 13
- 230000001174 ascending effect Effects 0.000 claims description 7
- 238000012935 Averaging Methods 0.000 claims description 2
- 230000003416 augmentation Effects 0.000 claims 2
- 238000011160 research Methods 0.000 abstract description 6
- 230000006870 function Effects 0.000 description 9
- 238000004364 calculation method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/16—Real estate
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Artificial Intelligence (AREA)
- Quality & Reliability (AREA)
- Development Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of urban construction land amplification, in particular to a time dimension amplification method for urban construction land. The invention provides a time dimension amplification method for urban construction land based on knowledge constraint rules, which can effectively solve the problem of limited data volume in the evolution process of the urban construction land and can set time section intervals according to actual research needs.
Description
Technical Field
The invention relates to the technical field of urban construction land amplification, in particular to a time dimension amplification method for urban construction land.
Background
The research aiming at the evolution process of urban construction land is an important means for urban and rural planning and research. The existing evolution research technology mainly depends on a remote sensing satellite to obtain a remote sensing image, and obtains the change information of the construction land of the related city through means such as artificial interpretation, but the method has high requirement on the quality of remote sensing data, is difficult to set time section intervals, and has limited data volume in the evolution process of the construction land of a single city.
The invention provides a time dimension amplification technology for urban construction land based on knowledge constraint rules, which can effectively solve the problem of limited data volume in the evolution process of the urban construction land and can set time section intervals according to actual research needs.
Disclosure of Invention
In order to solve the technical problem, the invention provides a time dimension amplification method for urban construction land, which comprises the following steps:
(1) setting the number of sections to be amplified and initialization parameters of each model;
(2) sequentially taking out image data of time sections of two adjacent cities to be predicted from the existing data, carrying out graying and binarization processing on the data of the two sections, and carrying out image difference on the image data of the two time sections to obtain a difference image as all variable quantities of the city construction land plots in the time span;
(3) setting a proper cluster number aiming at the difference image difference in the step (2), sequencing the clustered plots according to the area size through a clustering algorithm, defining a plurality of plots as main urban region plots according to a certain constraint rule, and defining the rest plots as non-main urban region plots;
(4) performing secondary clustering on the main urban area clusters according to the number of the time sections, wherein the number of the clusters is set as the number of the time sections, further determining a main urban area amplification module, recording coordinates of the center points of the cluster clusters, and taking the average value obtained by the coordinate values of the center points as the center point of the corresponding main urban area; amplifying the non-main urban areas by adopting two modes, wherein the first mode is completely consistent with the main urban area amplification module, namely clustering all the non-main urban areas as a whole again according to the amplification number; calculating the step required by each amplification according to the amplification number of each non-main urban area cluster, wherein in the condition, each amplification is synchronous amplification of a plurality of non-main urban area clusters;
(5) combining the main urban area amplification modules and the non-main urban area amplification modules, sequencing the data generated by each main urban area amplification module in an ascending order according to the distance from the center of each main urban area, namely, the data with the smallest distance is positioned at the forefront and the data with the largest distance is positioned at the rearmost, determining the attributes of the amplification modules of each main urban area, and simultaneously adding the non-main urban area amplification modules, wherein the two modes in the step (4) can be adopted;
(6) and (3) taking the initial image of the previous time section acquired in the step (2) as a basic image, amplifying according to the attributes of the main urban area amplification module and the non-main urban area amplification module determined in the step (5), generating and storing image data through an image generation module in each amplification, and amplifying on the basis of the previous amplification in each amplification.
As a preferred technical solution of the present invention, the step (1) specifically includes the following steps:
(1.1) opening python programming IDE, and respectively setting the number of time sections to be amplified of the urban construction land change data, the picture address of the time section to be amplified, and the area distinguishing threshold parameter of a main urban area and a non-main urban area;
(1.2) carrying out initialization assignment on the number of the time sections to be amplified, the picture addresses of the time sections to be amplified, and the area distinguishing threshold parameters of the main urban area and the non-main urban area;
as a preferable aspect of the present invention, in the step (2), the image difference specifically includes:
(2.1) reading in the picture address through a third-party module of Python according to the initialization result of the picture address variable of the time section to be amplified in the steps (1.1) and (1.2), wherein the reading-in mode is a gray scale mode, and a gray scale matrix representation form related to the picture data is obtained;
(2.2) obtaining a gray matrix representation form related to the picture data according to the step (2.1), and performing further graying and binarization processing on the original picture aiming at the condition that the gray values are not uniform in the processing process; carrying out image difference on the matrix image data of the two time sections after graying and binarization processing to obtain a binarization difference image;
as a preferred technical solution of the present invention, in the step (2.2), the specific step of obtaining the gray-scale matrix expression form related to the picture data includes:
(2.2.1) obtaining matrix image data of a previous time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2.2.2) obtaining the dimensionality of the previous time section image data through a python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.3) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.2) aiming at the corresponding position of the matrix image index obtained in the step (2.2.1);
(2.2.4) obtaining binarized image data on a previous time section of the time section matrix image data, wherein the background is 255 and the foreground land is 0;
(2.2.5) obtaining the matrix image data of the next time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2.2.6) obtaining the dimensionality of the image data at the next time through the python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.7) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.6) aiming at the corresponding position of the matrix image index obtained in the step (2.2.5);
(2.2.8) obtaining binary image data of a time section behind the time section matrix image data, wherein the background is 255 and the foreground plot is 0;
(2.2.9) calling a third party for image difference according to the binary image data obtained in the step (2.2.4) and the step (2.2.8);
(2.2.10) calling a third party to perform an image difference result according to the binarized image data obtained in the step (2.2.9), and judging whether the gray value of each pixel point is 0;
(2.2.11) aiming at the judgment result of the step (2.2.10), establishing a gray matrix index of the binary difference image for the pixel point with the gray value of 0;
(2.2.12) obtaining a gray matrix index of the binary difference image according to the judgment result of the step (2.2.10), wherein the index is in a form of binary group, the first item of the binary group is X dimension, and the second item is Y dimension;
(2.2.13) for the matrix index of step (2.2.12), get the length of the metaancestor element, go through the length of the metaancestor element, get the two-dimensional index matrix of length x 2 about the index.
As a preferred technical solution of the present invention, in the step (3), the specific step of defining the plurality of plots as main urban plots includes:
(3.1) analyzing the binary difference image obtained in the step (2) by adopting a clustering mode, firstly setting the clustering value as an odd number, and obtaining each block part of a main urban area and a non-main urban area;
(3.2) calculating the area of each clustered part and sequencing the clustered parts in a descending order;
(3.3) comparing the ratio of the first two area sizes of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), if the ratio is greater than the threshold, indicating that the first one is the main urban area, if the ratio is not greater than the threshold, continuing to compare the ratio of the second area size to the third area size of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), and repeating until the condition that the ratio is greater than the threshold is found out, and ending;
and (3.4) recording the length of the traversed index sequence before the step (3.3) is terminated as a main urban area, and taking the rest as non-main urban areas.
As a preferred technical solution of the present invention, in the step (4), the step of determining the main urban area extension module and recording the coordinates of the center point of the cluster of the number of the cross sections includes:
(4.1) traversing all the main urban areas, and traversing all the land parcels in each urban area;
(4.2) carrying out secondary clustering on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.3) calling a third-party-based library to perform secondary clustering to obtain clustering clusters with the number of the sections to be amplified;
(4.4) obtaining the coordinates of the central point of each cluster based on a third party library;
(4.5) summing the coordinates of the central points of all the clustering clusters, and then taking the average as the central coordinate of the corresponding main urban area;
(4.6) numbering each main urban area respectively;
(4.7) constructing a dictionary by taking the number of each main urban area in the step (4.6) as a keyword;
(4.8) inputting the dictionary value corresponding to the keyword of each main urban area into the center coordinate of each corresponding main urban area obtained in the step (4.5);
(4.9) selecting parameters according to a non-main urban area generation mode;
(4.10) if the first mode is selected, the mode of amplification comprises a plurality of amplification steps with reference to the main urban area extension module;
(4.11) if mode two is selected, the mode of amplification comprises multiple amplification steps.
As a preferred technical solution of the present invention, in the step (4.10), the non-main urban area expansion mode refers to the main urban area expansion module, and the specific steps include:
(4.10.1) traversing all the non-main urban areas, and traversing all the land parcels in the non-main urban areas;
(4.10.2) carrying out secondary clustering on the number of the sections needing to be amplified according to the parameter setting in the step (1);
(4.10.3) calling a third-party-based library to perform secondary clustering to obtain a cluster of the number of the sections to be amplified;
(4.10.4) obtaining coordinates of the center point of each cluster based on the third party library;
(4.10.5) summing the coordinates of the central points of all the clusters, and then taking the average as the central coordinate of the corresponding non-main urban area;
(4.10.6) numbering each non-primary metropolitan area separately;
(4.10.7) constructing a dictionary by using the number of each non-main urban area in the step (4.10.6) as a keyword;
(4.10.8) inputting the dictionary value corresponding to the keyword of each non-main urban area obtained in the step (4.10.7) into the center coordinates of each corresponding non-main urban area obtained in the step (4.10.5);
as a preferred technical solution of the present invention, in step (4.11), the specific steps of the second mode include:
(4.11.1) determining the generation mode and the average mode, and amplifying;
(4.11.2) performing variable definition on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.11.3) according to the parameter setting obtained in the step (4.11.2), carrying out variable assignment on the number of the sections to be amplified;
(4.11.4) according to the variables in the step (4.11.2) and the step (4.11.3) as the number to be amplified, preparing to obtain a non-main urban area dictionary in the step (2);
(4.11.5) according to the variable obtained in the step (4.11.4) as the number to be amplified, removing each cluster of the non-main urban area dictionary obtained in the step (2) by the number of sections to be amplified so as to obtain the step length of each amplification;
(4.11.6) in the amplification process, traversing the non-main urban area dictionary, and amplifying the image with the step length each time;
(4.11.7) determining the generation mode, randomly amplifying;
(4.11.8) performing variable definition on the number of cross sections to be amplified according to the parameter setting in the step (1);
(4.11.9) according to the parameter setting obtained in the step (4.11.8), carrying out variable assignment on the number of the sections to be amplified;
(4.11.10) according to the variable obtained in the step (4.11.9) as the number to be amplified, preparing to obtain a non-main urban area dictionary in the step (2);
(4.11.11) according to the variable obtained in the step (4.11.10) as the number to be amplified, carrying out Gaussian random generation step length generation on each cluster of the non-main urban area dictionary obtained in the step (2) according to an interval range;
(4.11.12) during the amplification process, the non-main urban area dictionary is traversed, and the step length image is amplified each time.
As a preferred technical solution of the present invention, the step (5) comprises the following steps:
(5.1) acquiring coordinates of the central points of the clustering clusters of the urban areas and the non-urban areas of the number of the time sections obtained in the step (4);
(5.2) acquiring the central coordinates of each main urban area and each non-main urban area, which are obtained by averaging the central coordinates of each cluster after each urban area is clustered in the step (4);
(5.3) calling a Python third-party library, and calculating the central coordinates of the various clustering clusters obtained in the step (5.1) according to the distance from the central coordinates of the main urban areas and the non-main urban areas obtained in the step (5.2);
(5.4) calling a Python third-party library, and sequencing the results obtained after the distance calculation from the central point coordinate of each cluster in the step (5.3) to the central point coordinate of the corresponding main urban area and non-main urban area in an ascending manner, namely, the distance is from small to large;
(5.5) obtaining the number of the clustering clusters as the traversal length according to the step (5.4);
(5.6) traversing according to the number of the clustering clusters obtained in the step (5.5) as the traversal length;
(5.7) constructing a dictionary about the central point of the cluster according to the traversal process in the step (5.6);
(5.8) on the basis of constructing a dictionary about the central point of the cluster, taking the traversal index as a key;
(5.9) on the basis of constructing the dictionary about the central point of the cluster according to the step (5.6), taking the traversal index as a key, and taking the value corresponding to the corresponding key as all coordinates under the corresponding cluster;
(5.10) constructing a list for storing the generated dictionaries;
and (5.11) in the traversal process in the step (5.7), sequentially adding the list constructed in the step (5.10) and storing the list in sequence.
As a preferable aspect of the present invention, in the step (6), the specific step of generating and storing the image data includes:
(6.1) sequentially taking the previous image data of the time sections of the two adjacent cities to be predicted from the data obtained in the step (2) as an initial image;
(6.2) traversing the number of the pictures to be amplified based on the number parameter of the pictures to be amplified in the step (2) for the initial image obtained in the step (6.1);
(6.4) in the traversing process, based on the sub-clusters of each main urban area obtained in the steps (3), (4) and (5), the step length of each non-main urban area is combined with the initial image obtained in the step (6.1) to perform traversing synchronous amplification;
(6.5) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.4);
(6.6) calling an image generation module of Python on the basis of the step (6.5), and further setting parameters for generating the image quality;
(6.7) calling an image generation module of Python on the basis of the step (6.6), and further setting parameters for generating image picture storage addresses;
and (6.8) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.6) to further generate the image.
Advantageous effects
The invention provides a time dimension amplification method for urban construction land based on knowledge constraint rules, which can effectively solve the problem of limited data volume in the evolution process of the urban construction land and can set time section intervals according to actual research needs.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a time-before cross-sectional image data of data to be amplified according to an embodiment of the present invention;
FIG. 3 is post-time cross-sectional image data of data to be amplified in accordance with an embodiment of the present invention;
FIG. 4 is a diagram illustrating the process of the present invention for the case of the urban construction site from 1990 to 2005.
Detailed Description
The disclosure may be understood more readily by reference to the following detailed description of preferred embodiments of the invention and the examples included therein. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. In case of conflict, the present specification, including definitions, will control.
The terms "comprises," "comprising," "includes," "including," "has," "having," "contains," "containing," or any other variation thereof, as used herein, are intended to cover a non-exclusive inclusion. For example, a composition, process, method, article, or apparatus that comprises a list of elements is not necessarily limited to only those elements but may include other elements not expressly listed or inherent to such composition, process, method, article, or apparatus.
Approximating language, as used herein throughout the specification and claims, is intended to modify a quantity, such that the invention is not limited to the specific quantity, but includes portions that are literally received for modification without substantial change in the basic function to which the invention is related. Accordingly, the use of "about" to modify a numerical value means that the invention is not limited to the precise value. In some instances, the approximating language may correspond to the precision of an instrument for measuring the value. In the present description and claims, range limitations may be combined and/or interchanged, including all sub-ranges contained therein if not otherwise stated.
The invention provides a time dimension amplification method for urban construction land, which comprises the following steps:
(1) setting the number of sections to be amplified and initialization parameters of each model;
(2) sequentially taking out image data of time sections of two adjacent cities to be predicted from the existing data, carrying out graying and binarization processing on the data of the two sections, and carrying out image difference on the image data of the two time sections to obtain a difference image as all variable quantities of the city construction land plots in the time span;
(3) setting a proper cluster number aiming at the difference image difference in the step (2), sequencing the clustered plots according to the area size through a clustering algorithm, defining a plurality of plots as main urban region plots according to a certain constraint rule, and defining the rest plots as non-main urban region plots;
(4) performing secondary clustering on the main urban area clusters according to the number of the time sections, wherein the number of the clusters is set as the number of the time sections, further determining a main urban area amplification module, recording coordinates of the center points of the cluster clusters, and taking the average value obtained by the coordinate values of the center points as the center point of the corresponding main urban area; amplifying the non-main urban areas by adopting two modes, wherein the first mode is completely consistent with the main urban area amplification module, namely clustering all the non-main urban areas as a whole again according to the amplification number; calculating the step required by each amplification according to the amplification number of each non-main urban area cluster, wherein in the condition, each amplification is synchronous amplification of a plurality of non-main urban area clusters;
(5) combining the main urban area amplification modules and the non-main urban area amplification modules, sequencing the data generated by each main urban area amplification module in an ascending order according to the distance from the center of each main urban area, namely, the data with the smallest distance is positioned at the forefront and the data with the largest distance is positioned at the rearmost, determining the attributes of the amplification modules of each main urban area, and simultaneously adding the non-main urban area amplification modules, wherein the two modes in the step (4) can be adopted;
(6) and (3) taking the initial image of the previous time section acquired in the step (2) as a basic image, amplifying according to the attributes of the main urban area amplification module and the non-main urban area amplification module determined in the step (5), generating and storing image data through an image generation module in each amplification, and amplifying on the basis of the previous amplification in each amplification.
In a preferred embodiment, the step (1) specifically comprises the following steps:
(1.1) opening python programming IDE, and respectively setting the number of time sections to be amplified of the urban construction land change data, the picture address of the time section to be amplified, and the area distinguishing threshold parameter of a main urban area and a non-main urban area;
and (1.2) carrying out initialization assignment on the number of the time sections to be amplified, the picture address of the time section to be amplified, and the area distinguishing threshold parameters of the main urban area and the non-main urban area.
In a preferred embodiment, in the step (2), the image difference step includes:
(2.1) reading in the picture address through a third-party module of Python according to the initialization result of the picture address variable of the time section to be amplified in the steps (1.1) and (1.2), wherein the reading-in mode is a gray scale mode, and a gray scale matrix representation form related to the picture data is obtained;
(2.2) obtaining a gray matrix representation form related to the picture data according to the step (2.1), and performing further graying and binarization processing on the original picture aiming at the condition that the gray values are not uniform in the processing process; and carrying out image difference on the matrix image data of the two time sections after the graying and binarization processing to obtain a binarization difference image.
In a preferred embodiment, in step (2.2), the specific step of obtaining the grayscale matrix representation form related to the picture data includes:
(2.2.1) obtaining matrix image data of a previous time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2.2.2) obtaining the dimensionality of the previous time section image data through a python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.3) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.2) aiming at the corresponding position of the matrix image index obtained in the step (2.2.1);
(2.2.4) obtaining binarized image data on a previous time slice with respect to the time slice matrix image data, wherein the background is 255 and the foreground (land) is 0.
And (2.2.5) obtaining the matrix image data of the next time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255.
(2.2.6) obtaining the dimensionality of the image data at the next time through the python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.7) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.6) aiming at the corresponding position of the matrix image index obtained in the step (2.2.5);
(2.2.8) obtaining binarized image data on a subsequent time slice with respect to the time slice matrix image data, wherein the background is 255 and the foreground (parcel) is 0.
(2.2.9) calling a third party for image difference according to the binary image data obtained in the step (2.2.4) and the step (2.2.8);
(2.2.10) calling a third party to perform an image difference result according to the binarized image data obtained in the step (2.2.9), and judging whether the gray value of each pixel point is 0;
(2.2.11) aiming at the judgment result of the step (2.2.10), establishing a gray matrix index of the binary difference image for the pixel point with the gray value of 0;
(2.2.12) obtaining a gray matrix index of the binary difference image according to the judgment result of the step (2.2.10), wherein the index is in a form of binary group, the first item of the binary group is X dimension, and the second item is Y dimension;
(2.2.13) for the matrix index of step (2.2.12), get the length of the metaancestor element, go through the length of the metaancestor element, get the two-dimensional index matrix of length x 2 about the index.
In a preferred embodiment, in step (3), the specific step of defining the plurality of plots as main urban plots includes:
(3.1) analyzing the binary difference image obtained in the step (2) by adopting a clustering mode, firstly setting the clustering value as an odd number, and obtaining each block part of a main urban area and a non-main urban area;
(3.2) calculating the area of each clustered part and sequencing the clustered parts in a descending order;
(3.3) comparing the ratio of the first two area sizes of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), if the ratio is greater than the threshold, indicating that the first one is the main urban area, if the ratio is not greater than the threshold, continuing to compare the ratio of the second area size to the third area size of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), and repeating until the condition that the ratio is greater than the threshold is found out, and ending;
and (3.4) recording the length of the traversed index sequence before the step (3.3) is terminated as a main urban area, and taking the rest as non-main urban areas.
In a preferred embodiment, in step (4), the step of determining the main urban area extension module, and recording the coordinates of the center point of the cluster of the number of sections includes:
(4.1) traversing all the main urban areas, and traversing all the land parcels in each urban area;
(4.2) carrying out secondary clustering on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.3) calling a third-party-based library to perform secondary clustering to obtain clustering clusters with the number of the sections to be amplified;
(4.4) obtaining the coordinates of the central point of each cluster based on a third party library;
(4.5) summing the coordinates of the central points of all the clustering clusters, and then taking the average as the central coordinate of the corresponding main urban area;
(4.6) numbering each main urban area respectively;
(4.7) constructing a dictionary by taking the number of each main urban area in the step (4.6) as a keyword;
and (4.8) inputting the dictionary value corresponding to the keyword of each main urban area into the center coordinates of each corresponding main urban area obtained in the step (4.5).
(4.9) selecting parameters according to a non-main urban area generation mode;
(4.10) if the first mode is selected, the mode of amplification comprises a plurality of amplification steps with reference to the main urban area extension module;
(4.11) if mode two is selected, the mode of amplification comprises multiple amplification steps.
As a preferred technical solution of the present invention, in the step (4.10), the non-main urban area expansion mode refers to the main urban area expansion module, and the specific steps include:
(4.10.1) traversing all the non-main urban areas, and traversing all the land parcels in the non-main urban areas;
(4.10.2) carrying out secondary clustering on the number of the sections needing to be amplified according to the parameter setting in the step (1);
(4.10.3) calling a third-party-based library to perform secondary clustering to obtain a cluster of the number of the sections to be amplified;
(4.10.4) obtaining coordinates of the center point of each cluster based on the third party library;
(4.10.5) summing the coordinates of the central points of all the clusters, and then taking the average as the central coordinate of the corresponding non-main urban area;
(4.10.6) numbering each non-primary metropolitan area separately;
(4.10.7) constructing a dictionary by using the number of each non-main urban area in the step (4.10.6) as a keyword;
(4.10.8) inputting the dictionary value corresponding to the keyword of each non-main urban area obtained in the step (4.10.7) as the center coordinate of each corresponding non-main urban area obtained in the step (4.10.5).
As a preferred technical solution of the present invention, in step (4.11), the specific steps of the second mode include:
(4.11.1) determining the generation mode and the average mode, and amplifying;
(4.11.2) performing variable definition on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.11.3) according to the parameter setting obtained in the step (4.11.2), carrying out variable assignment on the number of the sections to be amplified;
(4.11.4) preparing the non-main urban area dictionary obtained in the step (2) according to the variables in the step (4.11.2) and the step (4.11.3) as the amplification number;
(4.11.5) according to the variable obtained in the step (4.11.4) as the number to be amplified, removing each cluster of the non-main urban area dictionary obtained in the step (2) to obtain the number of amplified sections so as to obtain the step length of each amplification;
(4.11.6) during the amplification process, the non-main urban area dictionary is traversed, and the step length image is amplified each time.
(4.11.7) determining the generation mode, randomly amplifying;
(4.11.8) performing variable definition on the number of cross sections to be amplified according to the parameter setting in the step (1);
(4.11.9) according to the parameter setting obtained in the step (4.11.8), carrying out variable assignment on the number of the sections to be amplified;
(4.11.10) according to the variable obtained in the step (4.11.9) as the number to be amplified, preparing to obtain a non-main urban area dictionary in the step (2);
(4.11.11) according to the variable obtained in the step (4.11.10) as the number to be amplified, carrying out Gaussian random generation step length generation on each cluster of the non-main urban area dictionary obtained in the step (2) according to an interval range;
(4.11.12) during the amplification process, the non-main urban area dictionary is traversed, and the step length image is amplified each time.
In a preferred embodiment, the specific steps of step (5) include:
(5.1) acquiring coordinates of the central points of the clustering clusters of the urban areas and the non-urban areas of the number of the time sections obtained in the step (4);
(5.2) acquiring the central coordinates of each main urban area and each central coordinate of a non-main urban area obtained in the step (4), and clustering the central coordinates of each cluster to obtain the average central coordinates;
(5.3) calling a Python third-party library, and calculating the central coordinates of the various clustering clusters obtained in the step (5.1) according to the distance from the central coordinates of the main urban areas and the non-main urban areas obtained in the step (5.2);
(5.4) calling a Python third-party library, and sequencing the results obtained after the distance calculation from the central point coordinate of each cluster in the step (5.3) to the central point coordinate of the corresponding main urban area and non-main urban area in an ascending manner, namely, the distance is from small to large;
(5.5) obtaining the number of the clustering clusters as the traversal length according to the step (5.4);
(5.6) traversing according to the number of the clustering clusters obtained in the step (5.5) as the traversal length;
(5.7) constructing a dictionary about the central point of the cluster according to the traversal process in the step (5.6);
(5.8) on the basis of constructing a dictionary about the central point of the cluster, taking the traversal index as a key;
(5.9) on the basis of constructing the dictionary about the central point of the cluster according to the step (5.6), taking the traversal index as a key, and taking the value corresponding to the corresponding key as all coordinates under the corresponding cluster;
(5.10) constructing a list for storing the generated dictionaries;
and (5.11) in the traversal process in the step (5.7), sequentially adding the list constructed in the step (5.10) and storing the list in sequence.
In a preferred embodiment, in step (6), the specific step of generating and storing the image data includes:
(6.1) sequentially taking the previous image data of the time sections of the two adjacent cities to be predicted from the data obtained in the step (2) as an initial image;
(6.2) traversing the number of the pictures to be amplified based on the number parameter of the pictures to be amplified in the step (2) for the initial image obtained in the step (6.1);
(6.4) in the traversing process, based on the sub-clusters of each main urban area obtained in the steps (3), (4) and (5), the step length of each non-main urban area is combined with the initial image obtained in the step (6.1) to perform traversing synchronous amplification;
(6.5) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.4);
(6.6) calling an image generation module of Python on the basis of the step (6.5), and further setting parameters of the generated image, such as picture quality;
(6.7) calling an image generation module of Python on the basis of the step (6.6), and setting parameters of the generated image, such as a picture storage address;
and (6.8) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.6) to further generate the image.
The present invention will be specifically described below by way of examples. It should be noted that the following examples are only for illustrating the present invention and should not be construed as limiting the scope of the present invention, and that the insubstantial modifications and adaptations of the present invention by those skilled in the art based on the above disclosure are still within the scope of the present invention.
Examples
The embodiment takes a Xuan city as an example, and provides a technical method for time dimension amplification of urban construction land based on a domain knowledge constraint rule. The section image data of the construction land for urban construction in 1990 of the Xuan city and the section image data of the construction land for urban construction in 2005 of the Xuan city are taken as the preceding time section image data and the following time section image data of the data to be amplified, respectively. As shown in fig. 1, the method specifically comprises the following steps:
(1) setting parameters: the number of sections to be amplified and the initialization parameters of each model are set. The parameters involved are:
(1-1) commanding the calling of python programming IDE;
(1-2) the picture reading mode is a gray scale reading parameter;
(1-3) propagandizing 1990 section image data address of urban construction land in city;
(1-4) announcing 2005 urban construction land section image data address of the city;
(1-5) the number of the first clustering clusters is 7;
(1-6) the number of the second clustering clusters is 30;
(1-7) the number of image data to be amplified is 30;
(1-8) distinguishing a main urban area from a non-main urban area by a threshold parameter of 2;
(1-9) generating an image data file storage address parameter.
(2) Obtaining data of Xuan city image difference
Sequentially extracting image data of discontinuous sections in the city released in 1990 and 2005 from the existing data, respectively referring to fig. 2 and 3, carrying out gray level binary processing on the data of the two sections, and carrying out image difference on the image data of the two time sections to obtain a difference image as the total variation of a city construction land parcel in the span of 1990-2005;
(2-1) reading in the picture through a Python third-party module according to the initialization result of each parameter in the step (1), wherein the reading mode is a gray level mode, and a gray level matrix representation form of picture data of the public city construction land is obtained;
(2-2) aiming at the condition that the grey values of the picture data of the construction land of the city in Xuan City are not uniform, carrying out graying and binarization processing by programming a program; writing a program, and carrying out image difference on the matrix image data of the binary discontinuities of the city in 1990 and 2005 to obtain a binary difference image;
the concrete steps are as follows:
(2-2-1) writing a program based on reading in the matrix image data of the Xuan city in 1990 of the previous time section of each two time sections, judging whether each pixel point is 255-gray value by using a calling library function, and establishing a matrix image index with the pixel point gray value not being 255;
(2-2-2) writing a program through a python third-party library, calling a function of the program, obtaining the time section dimension of the image data of the city announced in 1990, and initializing a pure background matrix with the gray value of 255 in the same dimension according to the dimension of the image data obtained through the python third-party library;
(2-2-3) writing a program on the obtained pure background matrix, and setting a gray value to be 0 according to the corresponding position of the matrix image index obtained in the step (2-2-2);
(2-2-4) obtaining binary image data about 1990 time sections of Xuancheng city, wherein the background is 255 and the foreground plot is 0;
(2-2-5) writing a program based on the matrix image data of the Xuan city in 2005 of the next time section of each two time sections obtained by reading in, aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2-2-6) obtaining the dimensionality of the image data at the next time through a python third-party library, writing a program to define background matrix variables, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2-2-7) setting a gray value to be 0 at the corresponding position of the obtained matrix image index on the obtained pure background matrix;
(2-2-8) obtaining binary image data about 2005 time sections of the Xuancheng city, wherein the background is 255 and the foreground (plot) is 0;
(2-2-9) writing a program, calling a third party difference function for the obtained binary image data of the Xuancheng city, and carrying out image difference;
(2-2-10) writing a program, calling a third party to perform an image difference result according to the obtained binary image data of the Xuancheng city, and judging whether the gray value of each pixel point is 0;
(2-2-11) writing a program, and establishing a gray matrix index of the binary difference image for the pixel point with the gray value of 0 according to the judgment result;
(2-2-12) writing a program, defining matrix index variables, and obtaining a gray matrix index of the binary difference image according to a judgment result, wherein the index is in a binary form, a first item of the binary is an X dimension, and a second item of the binary is a Y dimension;
(2-2-13) writing a program, calling a third-party library function according to the obtained matrix index to obtain the length of the element ancestor element, and traversing the length of the element ancestor element to obtain a two-dimensional index matrix of which the length of the index is multiplied by 2.
(3) Defining a plot of a main urban area of a Xuan city and a plot of a non-main urban area;
(3-1) compiling a program, analyzing the binary difference image of the Xuan city obtained in the step (2) in a clustering mode, firstly assigning a clustering value variable to be an odd number 7, and calling a third-party clustering function to obtain each block part of a main city area and a non-main city area of the Xuan city;
(3-2) compiling a program, calling a Python native sorting function, calculating the area of each clustered plot part of the Xuan city and sorting the clustered plots in a descending order;
(3-3) writing a program, calculating the ratio of the first two area sizes of the sequencing result, comparing the ratio with a main urban area threshold value 2, if the ratio is greater than the threshold value, indicating that the first urban area is the main urban area, if the ratio is not greater than the threshold value, continuing to compare the ratio of the second area size to the third area size of the sequencing result with the obtained main urban area threshold value, and repeating the steps until a condition that the ratio is greater than the threshold value is found, and ending;
and (3-4) writing a program, defining a variable of a main urban area of the Xuan city, assigning values to the main urban area according to the step (3-3), and taking the rest as non-main urban areas.
(4) Determining a main urban area extension module of a Xuan city and acquiring the center coordinate of each main urban area cluster
(4-1) writing a program, traversing all main urban areas of the announced city, and traversing all land parcels in each urban area;
(4-2) compiling a program according to the parameter setting in the step (1), calling a third-party clustering function, and carrying out secondary clustering on the number of the sections to be amplified;
(4-3) compiling a program to obtain 30 cluster clusters;
(4-4) compiling a program, and obtaining the coordinates of the central points of all the clustering clusters in the Xuancheng city based on a third-party library calling function;
(4-5) compiling a program, summing the coordinates of the central points of all the clustering clusters, and then taking the average as the central coordinate of the corresponding main urban area;
(4-6) writing a program, and respectively defining variables and numbering for each main city area of the Xuan city;
(4-7) writing a program, using the number of each main urban area in the Xuancheng city as a keyword, defining a dictionary and assigning values;
and (4-8) writing a program, and assigning dictionary values corresponding to the keywords of each main urban area of the Xuancheng city as the obtained central coordinates of each corresponding main urban area.
(4-9) amplification module for determining non-main urban areas of Xuan City
(4-10) writing a program, performing parameter assignment according to a generation mode of the non-main urban area of the Xuan city and entering corresponding selection;
(4-11) writing a program, firstly selecting a first mode, wherein the amplification mode comprises a plurality of amplification steps;
the concrete steps are
(4-11-1) writing a program, traversing all non-main urban areas of the announced city, and traversing all land parcels in the non-main urban areas;
(4-11-2) writing a program, and performing secondary clustering on the number of the sections to be amplified according to the parameter setting in the step (1);
(4-11-3) compiling a program, calling a third-party-library-based program to perform secondary clustering, and obtaining 30 clustering clusters;
(4-11-4) writing a program, and obtaining the coordinates of the central point of each cluster based on a third party library;
(4-11-5) compiling a program, summing the central point coordinates of all the clustering clusters, and then taking the average as the central coordinate of the non-main urban area of the corresponding public city;
(4-11-6) writing a program, and numbering each non-main urban area of the Xuan city respectively;
(4-11-7) writing a program, and constructing a dictionary by taking the number of each non-main city area in the Xuan city as a keyword;
(4-11-8) writing a program, and inputting the obtained dictionary values corresponding to the keywords of each non-main urban area of the Xuan city into the obtained central coordinates of each corresponding non-main urban area;
(4-12) writing a program, selecting a second mode, wherein the amplification mode comprises a plurality of amplification steps;
the concrete steps are as follows:
(4-12-1) writing a program, and determining the program as an average mode to perform amplification;
(4-12-1-1) writing a program, and performing variable definition on the number of sections to be amplified;
(4-12-1-2) writing a program, and performing variable assignment on the number of sections to be amplified;
(4-12-1-3) writing a program, and taking the assignment variable as the number to be amplified to obtain a Xuan city non-main urban area dictionary;
(4-12-1-4) writing a program, and removing the variables of 30 to obtain the step length of each amplification after assigning the variables of each cluster of the non-main urban area dictionary of the Xuan city;
(4-12-1-5) writing a program, traversing the public city non-main urban area dictionary, and amplifying the image with the step length each time.
(5) Determining the amplification sequence of the city construction land in Xuancheng city
(5-1) writing a program, and acquiring coordinate variables of the central points of the clustering clusters of the Xuan city urban areas and the non-urban areas of the obtained 30 time sections;
(5-2) compiling a program, and obtaining the obtained central coordinate variables of each main urban area and each non-main urban area of the Xuan city (the central coordinates of each cluster after each urban area is clustered are obtained on average);
(5-3) compiling a program, calling a Python third-party library, and calculating the obtained central coordinates of various clustering clusters according to the distance between the central coordinates of various main urban areas and central coordinates of non-main urban areas of the Xuan city;
(5-4) writing a program, calling a Python third-party library, and sequencing the calculated results in an ascending manner, namely, the distance is from small to large;
(5-5) writing a program, and taking the number of the cluster clusters as the length to be traversed;
(5-6) writing a program, and traversing according to the number of the cluster clusters as the length to be traversed;
(5-7) writing a program, defining and constructing a dictionary about the central point of the cluster;
(5-8) writing a program, and taking the traversal index as a key on the basis of constructing a dictionary about the central point of the cluster;
(5-9) writing a program, taking the traversal index as a key and taking the value corresponding to the key as all coordinates under the corresponding cluster on the basis of constructing a dictionary about the central point of the cluster;
(5-10) writing a program, constructing a list and storing the generated dictionaries;
(5-11) writing programs, sequentially adding the programs into the constructed list, and storing the programs in sequence;
(6) generating and storing each time of amplification of the urban construction land in the Xuan City;
(6-1) writing a program for extracting image data of a time section of 1990 s of the Xuan City from the obtained data as an initial image;
(6-2) compiling a program, and traversing the number of the pictures to be amplified based on the number parameter 30 of the pictures to be amplified;
(6-3) compiling a program, obtaining sub-clusters of each main urban area of the Xuancheng city and the step length of each non-main urban area in the traversal process, and performing traversal synchronous amplification by combining the obtained initial image;
(6-4) writing a program, calling an image generation module of Python, and further setting key parameters of the generated image, such as picture quality and the like;
(6-5) writing a program, calling an image generation module of Python, and setting parameters of the generated image, such as a picture storage address;
(6-6) writing a program, calling an image generation module of Python, and further generating an image;
(6-7) image data on amplification was obtained and confirmed, and image 4 was a process diagram of amplification from 1990 to 2005 in city building sites in Xuanchen City.
The foregoing examples are merely illustrative and serve to explain some of the features of the method of the present invention. The appended claims are intended to claim as broad a scope as is contemplated, and the examples presented herein are merely illustrative of selected implementations in accordance with all possible combinations of examples. Accordingly, it is applicants' intention that the appended claims are not to be limited by the choice of examples illustrating features of the invention. Also, where numerical ranges are used in the claims, subranges therein are included, and variations in these ranges are also to be construed as possible being covered by the appended claims.
Claims (8)
1. A time dimension amplification method for urban construction land is characterized by comprising the following steps:
(1) setting the number of sections to be amplified and initialization parameters of each model, wherein the step (1) specifically comprises the following steps:
(1.1) opening python programming IDE, and respectively setting the number of time sections to be amplified of the urban construction land change data, the picture address of the time section to be amplified, and the area distinguishing threshold parameter of a main urban area and a non-main urban area;
(1.2) carrying out initialization assignment on the number of the time sections to be amplified, the picture addresses of the time sections to be amplified, and the area distinguishing threshold parameters of the main urban area and the non-main urban area;
(2) sequentially taking out image data of time sections of two adjacent cities to be predicted from the existing data, carrying out graying and binarization processing on the data of the two sections, and carrying out image difference on the image data of the two time sections to obtain a difference image as all variable quantities of the city construction land plots in the time span;
(3) setting a proper cluster number aiming at the difference image difference in the step (2), sequencing the clustered plots according to the area size through a clustering algorithm, defining a plurality of plots as main urban region plots according to a certain constraint rule, and defining the rest plots as non-main urban region plots;
(4) performing secondary clustering on the main urban area clusters according to the number of the time sections, wherein the number of the clusters is set as the number of the time sections, further determining a main urban area amplification module, recording coordinates of the center points of the cluster clusters, and taking the average value obtained by the coordinate values of the center points as the center point of the corresponding main urban area; amplifying the non-main urban areas by adopting two modes, wherein the first mode is completely consistent with the main urban area amplification module, namely clustering all the non-main urban areas as a whole again according to the amplification number; calculating the step required by each amplification according to the amplification number of each non-main urban area cluster, wherein in the condition, each amplification is synchronous amplification of a plurality of non-main urban area clusters;
(5) combining the main urban area amplification modules and the non-main urban area amplification modules, sequencing data generated by the main urban area amplification modules in an ascending order according to the distance from the center of each main urban area, namely, the data with the smallest distance is at the forefront and the data with the largest distance is at the rearmost, determining the attributes of the amplification modules of each main urban area, and simultaneously adding the non-main urban area amplification modules, wherein two modes in the step (4) can be adopted, and the specific step in the step (5) comprises the following steps:
(5.1) acquiring coordinates of the central points of the clustering clusters of the urban areas and the non-urban areas of the number of the time sections obtained in the step (4);
(5.2) acquiring the central coordinates of the main urban area and the non-main urban area which are obtained by averaging the central coordinates of the clusters after the clustering of the urban areas in the step (4);
(5.3) calling a Python third-party library, and calculating the central coordinates of the various clustering clusters obtained in the step (5.1) according to the distance from the central coordinates of the main urban area and the non-main urban area obtained in the step (5.2);
(5.4) calling a Python third-party library, and sequencing the results obtained after calculating the distance from the central point coordinate of each cluster in the step (5.3) to the central point coordinates of the main urban area and the non-main urban area in an ascending manner, namely, the distance is from small to large;
(5.5) obtaining the number of the clustering clusters as the traversal length according to the step (5.4);
(5.6) traversing according to the number of the clustering clusters obtained in the step (5.5) as the traversal length;
(5.7) constructing a dictionary about the central point of the cluster according to the traversal process in the step (5.6);
(5.8) on the basis of constructing a dictionary about the central point of the cluster, taking the traversal index as a key;
(5.9) on the basis of constructing the dictionary about the central point of the cluster according to the step (5.6), taking the traversal index as a key, and taking the value corresponding to the corresponding key as all coordinates under the corresponding cluster;
(5.10) constructing a list for storing the generated dictionaries;
(5.11) in the traversal process in the step (5.7), sequentially adding the list constructed in the step (5.10) and storing the list in sequence;
(6) and (3) taking the initial image of the previous time section acquired in the step (2) as a basic image, amplifying according to the attributes of the main urban area amplification module and the non-main urban area amplification module determined in the step (5), generating and storing image data through an image generation module in each amplification, and amplifying on the basis of the previous amplification in each amplification.
2. The urban construction land time dimension amplification method according to claim 1, wherein in the step (2), the image difference comprises the following specific steps:
(2.1) reading in the picture address through a third-party module of Python according to the initialization result of the picture address variable of the time section to be amplified in the steps (1.1) and (1.2), wherein the reading-in mode is a gray scale mode, and a gray scale matrix representation form related to the picture data is obtained;
(2.2) obtaining a gray matrix representation form related to the picture data according to the step (2.1), and performing further graying and binarization processing on the original picture aiming at the condition that the gray values are not uniform in the processing process; and carrying out image difference on the matrix image data of the two time sections after the graying and binarization processing to obtain a binarization difference image.
3. The method for time-dimension augmentation of urban construction land according to claim 2, wherein in step (2.2), the specific step of obtaining the grayscale matrix expression form for the picture data comprises:
(2.2.1) obtaining matrix image data of a previous time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2.2.2) obtaining the dimensionality of the previous time section image data through a python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.3) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.2) aiming at the corresponding position of the matrix image index obtained in the step (2.2.1);
(2.2.4) obtaining binarized image data on a previous time section of the time section matrix image data, wherein the background is 255 and the foreground land is 0;
(2.2.5) obtaining the matrix image data of the next time section of every two time sections based on the step (2.1), aligning each pixel point to judge whether the gray value is 255, and establishing a matrix image index with the gray value of the pixel point not being 255;
(2.2.6) obtaining the dimensionality of the image data at the next time through the python third-party library, and initializing a pure background matrix with the same dimensionality and the gray value of 255 according to the dimensionality of the image data obtained through the python third-party library;
(2.2.7) setting a gray value to be 0 on the pure background matrix obtained in the step (2.2.6) aiming at the corresponding position of the matrix image index obtained in the step (2.2.5);
(2.2.8) obtaining binary image data of a time section behind the time section matrix image data, wherein the background is 255 and the foreground plot is 0;
(2.2.9) calling a third party for image difference according to the binary image data obtained in the step (2.2.4) and the step (2.2.8);
(2.2.10) calling a third party to perform an image difference result according to the binarized image data obtained in the step (2.2.9), and judging whether the gray value of each pixel point is 0;
(2.2.11) aiming at the judgment result of the step (2.2.10), establishing a gray matrix index of the binary difference image for the pixel point with the gray value of 0;
(2.2.12) obtaining a gray matrix index of the binary difference image according to the judgment result of the step (2.2.10), wherein the index is in a form of binary group, the first item of the binary group is X dimension, and the second item is Y dimension;
(2.2.13) for the matrix index of step (2.2.12), get the length of the metaancestor element, go through the length of the metaancestor element, get the two-dimensional index matrix of length x 2 about the index.
4. The method for time dimension expansion of urban construction land according to claim 1, wherein in step (3), the specific step of defining the plurality of plots as main urban plots comprises:
(3.1) analyzing the binary difference image obtained in the step (2) by adopting a clustering mode, firstly setting the clustering value as an odd number, and obtaining each block part of a main urban area and a non-main urban area;
(3.2) calculating the area of each clustered part and sequencing the clustered parts in a descending order;
(3.3) comparing the ratio of the first two area sizes of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), if the ratio is greater than the threshold, indicating that the first one is the main urban area, if the ratio is not greater than the threshold, continuing to compare the ratio of the second area size to the third area size of the sorting result with the main urban area threshold obtained in the step (1.1) and the step (1.2), and repeating until the condition that the ratio is greater than the threshold is found out, and ending;
and (3.4) recording the length of the traversed index sequence before the step (3.3) is terminated as a main urban area, and taking the rest as non-main urban areas.
5. The urban construction land time dimension amplification method according to claim 1, wherein in step (4), the specific step of determining the main urban area extension surface module, recording the coordinates of the center point of the cluster of the number of the cross sections, comprises:
(4.1) traversing all the main urban areas, and traversing all the land parcels in each urban area;
(4.2) carrying out secondary clustering on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.3) calling a third-party-based library to perform secondary clustering to obtain clustering clusters with the number of the sections to be amplified;
(4.4) obtaining the coordinates of the central point of each cluster based on a third party library;
(4.5) summing the coordinates of the central points of all the clustering clusters, and then taking the average as the central coordinate of the corresponding main urban area;
(4.6) numbering each main urban area respectively;
(4.7) constructing a dictionary by taking the number of each main urban area in the step (4.6) as a keyword;
(4.8) inputting the dictionary value corresponding to the keyword of each urban area (main urban area) into the center coordinate of each corresponding main urban area obtained in the step (4.5);
(4.9) selecting parameters according to a non-main urban area generation mode;
(4.10) if the first mode is selected, the mode of amplification comprises a plurality of amplification steps with reference to the main urban area extension module;
(4.11) if mode two is selected, the mode of amplification comprises multiple amplification steps.
6. The method for time dimension expansion of urban construction land according to claim 5, wherein in step (4.10), the non-main urban area expansion mode refers to a main urban area expansion module, and the specific steps include:
(4.10.1) traversing all the non-main urban areas, and traversing all the land parcels in the non-main urban areas;
(4.10.2) carrying out secondary clustering on the number of the sections needing to be amplified according to the parameter setting in the step (1);
(4.10.3) calling a third-party-based library to perform secondary clustering to obtain a cluster of the number of the sections to be amplified;
(4.10.4) obtaining coordinates of the center point of each cluster based on the third party library;
(4.10.5) summing the coordinates of the central points of all the clusters, and then taking the average as the central coordinate of the corresponding non-main urban area;
(4.10.6) numbering each non-primary metropolitan area separately;
(4.10.7) constructing a dictionary by using the number of each non-main urban area in the step (4.10.6) as a keyword;
(4.10.8) inputting the dictionary value corresponding to the keyword of each non-main urban area obtained in the step (4.10.7) as the center coordinate of each corresponding non-main urban area obtained in the step (4.10.5).
7. The method for time dimension expansion of urban construction land according to claim 5, wherein in step (4.11), the specific steps of the second mode comprise:
(4.11.1) determining the generation mode and the average mode, and amplifying;
(4.11.2) performing variable definition on the number of the sections to be amplified according to the parameter setting in the step (1);
(4.11.3) according to the parameter setting obtained in the step (4.11.2), carrying out variable assignment on the number of the sections to be amplified;
(4.11.4) according to the variables in the step (4.11.2) and the step (4.11.3) as the number to be amplified, preparing to obtain a non-main urban area dictionary in the step (2);
(4.11.5) according to the variable obtained in the step (4.11.4) as the amplification number, removing each cluster of the non-main urban area dictionary obtained in the step (2) by the number of the cross sections to be amplified so as to obtain the step length of each amplification;
(4.11.6) in the amplification process, traversing the non-main urban area dictionary, and amplifying the image with the step length each time;
(4.11.7) determining the generation mode, randomly amplifying;
(4.11.8) performing variable definition on the number of cross sections to be amplified according to the parameter setting in the step (1);
(4.11.9) according to the parameter setting obtained in the step (4.11.8), carrying out variable assignment on the number of the sections to be amplified;
(4.11.10) according to the variable obtained in the step (4.11.9) as the number to be amplified, preparing to obtain a non-main urban area dictionary in the step (2);
(4.11.11) according to the variable obtained in the step (4.11.10) as the number to be amplified, carrying out Gaussian random generation step length generation on each cluster of the non-main urban area dictionary obtained in the step (2) according to an interval range;
(4.11.12) during the amplification process, the non-main urban area dictionary is traversed, and the step length image is amplified each time.
8. The method for time-dimension augmentation of urban construction land according to claim 1, wherein in the step (6), the specific step of generating and storing image data comprises:
(6.1) sequentially taking the previous image data of the time sections of the two adjacent cities to be predicted from the data obtained in the step (2) as an initial image;
(6.2) traversing the number of the pictures to be amplified based on the number parameter of the pictures to be amplified in the step (2) for the initial image obtained in the step (6.1);
(6.4) in the traversing process, based on the sub-clusters of each main urban area obtained in the steps (3), (4) and (5), the step length of each non-main urban area is combined with the initial image obtained in the step (6.1) to perform traversing synchronous amplification;
(6.5) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.4);
(6.6) calling an image generation module of Python on the basis of the step (6.5), and further setting parameters for generating the image quality;
(6.7) calling an image generation module of Python on the basis of the step (6.6), and further setting parameters for generating image picture storage addresses;
and (6.8) calling an image generation module of Python in the process of traversing synchronous amplification in the step (6.6) to further generate the image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110057306.0A CN112766717B (en) | 2021-01-15 | 2021-01-15 | Time dimension amplification method for urban construction land |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110057306.0A CN112766717B (en) | 2021-01-15 | 2021-01-15 | Time dimension amplification method for urban construction land |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112766717A CN112766717A (en) | 2021-05-07 |
| CN112766717B true CN112766717B (en) | 2022-03-08 |
Family
ID=75702028
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110057306.0A Active CN112766717B (en) | 2021-01-15 | 2021-01-15 | Time dimension amplification method for urban construction land |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112766717B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108537710A (en) * | 2018-03-26 | 2018-09-14 | 重庆交通大学 | A kind of urban growth boundary demarcation method based on Markov-FLUS models |
| EP3376160A1 (en) * | 2015-11-13 | 2018-09-19 | Obschestvo s Ogranichennoi Otvetstvennostyu "Helgi LAB" | Method and system for identifying urban objects |
| CN110135351A (en) * | 2019-05-17 | 2019-08-16 | 东南大学 | Built-up areas Boundary Recognition method and apparatus based on urban architecture spatial data |
| CN111652198A (en) * | 2019-11-04 | 2020-09-11 | 南京图申图信息科技有限公司 | Urban edge area identification method and system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150039523A1 (en) * | 2013-07-30 | 2015-02-05 | Universitat De Girona | Methods and devices for urban planning |
-
2021
- 2021-01-15 CN CN202110057306.0A patent/CN112766717B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3376160A1 (en) * | 2015-11-13 | 2018-09-19 | Obschestvo s Ogranichennoi Otvetstvennostyu "Helgi LAB" | Method and system for identifying urban objects |
| CN108537710A (en) * | 2018-03-26 | 2018-09-14 | 重庆交通大学 | A kind of urban growth boundary demarcation method based on Markov-FLUS models |
| CN110135351A (en) * | 2019-05-17 | 2019-08-16 | 东南大学 | Built-up areas Boundary Recognition method and apparatus based on urban architecture spatial data |
| CN111652198A (en) * | 2019-11-04 | 2020-09-11 | 南京图申图信息科技有限公司 | Urban edge area identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112766717A (en) | 2021-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Barber et al. | Target‐group backgrounds prove effective at correcting sampling bias in Maxent models | |
| CN110610166B (en) | Text region detection model training method and device, electronic equipment and storage medium | |
| CN106844781B (en) | Data processing method and device | |
| CN112116613B (en) | Image vectorization method and system | |
| CN111143685B (en) | Commodity recommendation method and device | |
| CN109359186B (en) | Method and device for determining address information and computer readable storage medium | |
| CN113344956A (en) | Ground feature contour extraction and classification method based on unmanned aerial vehicle aerial photography three-dimensional modeling | |
| CN114972759B (en) | Remote sensing image semantic segmentation method based on hierarchical contour cost function | |
| CN106682414A (en) | Method and device for establishing timing sequence prediction model | |
| CN115861816A (en) | Three-dimensional low vortex identification method and device, storage medium and terminal | |
| CN116596021A (en) | Model parameter optimization method and device based on improved sparrow search algorithm | |
| CN113516060B (en) | Building space fusion discrimination method and device based on multi-temporal high-resolution data | |
| CN111653268A (en) | Man-machine voice interaction system and method for shopping cabin | |
| CN112766717B (en) | Time dimension amplification method for urban construction land | |
| Rav et al. | Flood risk analysis on terrains | |
| CN113901936B (en) | Hard-pen calligraphy field character grid section image extraction method, system and equipment | |
| CN112905792B (en) | Text clustering method, device, equipment and storage medium based on non-text scene | |
| CN115424131A (en) | Remote sensing image cloud detection optimal threshold selection method based on absolute pixels, cloud detection method and system | |
| CN109740804B (en) | Water quality prediction method, terminal device and computer-readable storage medium | |
| CN113362286A (en) | Natural resource element change detection method based on deep learning | |
| CN109308565B (en) | Crowd performance grade identification method and device, storage medium and computer equipment | |
| CN114596498B (en) | Assignment method and system for geochemical sampling blind area and storage medium | |
| CN110738305A (en) | method and system for analyzing logistics waybill address | |
| CN116303376B (en) | Asset management optimization method and system based on asset big data platform | |
| CN115049899B (en) | Model training method, reference expression generation method and related equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |