CN109492796A - A kind of Urban Spatial Morphology automatic Mesh Partition Method and system - Google Patents
A kind of Urban Spatial Morphology automatic Mesh Partition Method and system Download PDFInfo
- Publication number
- CN109492796A CN109492796A CN201811188233.3A CN201811188233A CN109492796A CN 109492796 A CN109492796 A CN 109492796A CN 201811188233 A CN201811188233 A CN 201811188233A CN 109492796 A CN109492796 A CN 109492796A
- Authority
- CN
- China
- Prior art keywords
- urban spatial
- spatial morphology
- space
- building
- cluster
- 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.)
- Pending
Links
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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Abstract
The invention discloses a kind of Urban Spatial Morphology automatic Mesh Partition Method and system, method includes: the Urban Spatial Morphology basic data obtained in given range, obtains multiple space cells；It for each space cell, is calculated automatically according to multiple Urban Spatial Morphology indexs of setting, generates Urban Spatial Morphology feature summary sheet；Matrix corresponding to Urban Spatial Morphology feature summary sheet is clustered using Unsupervised clustering algorithm, in cluster process, different clustering parameters is set and carries out repeatedly cluster operation, and is scored each cluster result, determines best cluster result；According to best cluster result, the result of Urban Spatial Morphology auto-partition is obtained；And further can correlation between analysis indexes, obtain crucial effect index.The present invention can feature that is objective and comprehensively knowing Urban Spatial Morphology clearly, and then formed auto-partition result and crucial effect index, avoid the subjective judgement being easy to appear in conventional method or investigate dimension it is single the problems such as.
Description
Technical field
The invention belongs to urban planning field, be related to a kind of Urban Spatial Morphology partition method and system, in particular to one
Kind carries out the side of Urban Spatial Morphology auto-partition by extracting the morphological feature of itself various dimensions of city Spatial three-dimensional dispersion
Method and system.
Background technique
Urban Spatial Morphology is the core research object of Urban Planning Subject.In rapid urbanization course, city is constantly
" opening up outside " and " growing tall ", Urban Spatial Morphology also becomes even more complex.It is different from political divisions, resource partitioning, ecological grades point
Area etc., Urban Spatial Morphology subregion are the architectural entity progress block divisions for city three-dimensional material space.City space shape
State subregion is the important link for parsing Urban Spatial Morphology, is capable of discrimination Urban Spatial Morphology by Urban Spatial Morphology subregion
Inherent mechanism, and then seek the structural rule of city space.
The determination of Urban Spatial Morphology subregion common at present is referred to by the single dimensions form such as plot ratio, density, height
Mark carries out subregion by the way of the interval threshold of setting target to portray.Such as the dimension based on maximum building height
Urban Spatial Morphology is divided into lower zone, multilayer area, small high-rise area, high rise zone, Super High area, the dimension based on site coverage by degree
Urban Spatial Morphology is divided into low density area, middle density region, high density area etc..Such subregion, which exists, cannot be considered in terms of to city
The three-dimensional globality of spatial shape, index section, which determine, is related to that human brain judgement, arbitrariness is also big for technical result, working efficiency is low
Problem.
Summary of the invention
Goal of the invention: it is an object of that present invention to provide a kind of Urban Spatial Morphology automatic Mesh Partition Method and systems, can be certainly
It is dynamic to generate Urban Spatial Morphology division result, and crucial effect index is further obtained, to avoid cannot be considered in terms of in traditional operation
It is determined to the three-dimensional globality of Urban Spatial Morphology, index section and is related to that human brain judgement, arbitrariness is also big for technical result, working efficiency
Low problem.
Technical solution: to achieve the above object, a kind of Urban Spatial Morphology automatic Mesh Partition Method of the present invention, including
Following steps:
(1) the Urban Spatial Morphology basic data in given range is obtained, is wrapped in the Urban Spatial Morphology basic data
Multiple space cells are included or can extract, the profile of the space cell is the polygon space of closure, and inside includes at least
One building, the profile of the building are the polygon space of closure, and the building has the number of plies and/or height is believed
Breath；
(2) it is directed to each space cell, is calculated automatically according to multiple Urban Spatial Morphology indexs of setting, it is empty to generate city
Between morphological feature summary sheet；Wherein Urban Spatial Morphology index includes land area, site coverage, plot ratio, maximum basal surface
At least two in product, maximum building height, maximum construction area, average building height and degree straggly；
(3) matrix corresponding to Urban Spatial Morphology feature summary sheet is clustered using Unsupervised clustering algorithm, is gathered
In class process, different clustering parameters is set and carries out repeatedly cluster operation, and uses the Cluster Assessment based on data unique characteristics
Index scores to each cluster result, so that it is determined that best cluster result；
(4) according to best cluster result, each space cell and its corresponding cluster number are obtained, as city space shape
The result of state auto-partition.
In preferred embodiments, the method also includes: in Urban Spatial Morphology feature summary sheet data progress
Correlation analysis exports the crucial effect index of Urban Spatial Morphology auto-partition.
In preferred embodiments, the space cell is to divide the vector space to be formed according to block, land used or property right
Unit.In preferred embodiments, the land area of the space cell is empty by the polygon constituted to closure multi-section-line
Between geometry calculate obtain；The site coverage is the sum of floor space of owned building in space cell and space cell land used
The ratio of area；The plot ratio be the owned building in space cell floor space and building number of plies product summation with
The ratio of space cell land area；The maximum area of base is the maximum of the floor space of the owned building in space cell
Value；The maximum building height is the maximum value of the height of the owned building in space cell；It is described maximum construction area be
The floor space of owned building in space cell and the maximum value of building number of plies product；The average building height is space
The average value of the height of owned building in unit；The degree straggly is the side of the height of the owned building in space cell
Difference；The floor space of the building is calculated by the polygon space geometry constituted to closure multi-section-line and is obtained.
In preferred embodiments, the multiple Urban Spatial Morphology index is close for the land area of space cell, building
Degree, plot ratio, maximum area of base, maximum building height, maximum construction area, average building height and degree straggly.
In a particular embodiment, the Unsupervised clustering algorithm is K-means clustering algorithm based on central point, is based on
One in the hierarchical clustering algorithm of Connected degree, the DBSCAN clustering algorithm based on density and the GMM-EM clustering algorithm based on distribution
Kind is a variety of；The Cluster Assessment index is one in Dunn index, Davies-Bouldin index and Silhouette coefficient
Kind.
In preferred embodiments, use the K-means clustering algorithm based on mahalanobis distance to city in the step (3)
Matrix corresponding to spatial shape feature summary sheet is clustered, and in cluster process, different clusters numbers is arranged and carries out repeatedly
Operation is clustered, and is scored using Silhouette coefficient with the best cluster result of determination；Wherein Silhouette coefficient calculating side
Method are as follows:
Indicate data point i to the average value of like numbers strong point distance, b (i) expression any point i in data set, a (i)
For data point i to the minimum value in other Various types of data point distance averages, s (i) indicates the Silhouette coefficient of data point i；
The Silhouette coefficient of all data points is averaged be exactly cluster result overall Silhouette coefficient.
In preferred embodiments, the step that crucial effect index determines includes: to Urban Spatial Morphology feature summary sheet
In data carry out correlation operation, obtain correlation matrix figure；Compare the sum of every absolute value maximum in correlation matrix figure
Index, as the crucial effect index in Urban Spatial Morphology.
In preferred embodiments, in the step (4) after obtaining each space cell and its corresponding cluster number,
The filling that a kind of color is carried out to the space cell of same class cluster number, by the result of Urban Spatial Morphology subregion with color lump
Plane geometry image show.
A kind of Urban Spatial Morphology auto-partition system of the present invention, comprising:
Space cell obtains module, and for obtaining the Urban Spatial Morphology basic data in given range, the city is empty
Between include in morphological basis data or multiple space cells can be extracted, the profile of the space cell is the polygon of closure
Space, inside include at least one building, and the profile of the building is the polygon space of closure, and the building has
The number of plies and/or elevation information；
Spatial shape index computing module, for being directed to each space cell, according to multiple Urban Spatial Morphologies of setting
Index calculates automatically, generates Urban Spatial Morphology feature summary sheet；Wherein Urban Spatial Morphology index includes land area, building
In density, plot ratio, maximum area of base, maximum building height, maximum construction area, average building height and degree straggly
At least two；
Cluster Assessment module, for calculating matrix corresponding to Urban Spatial Morphology feature summary sheet using Unsupervised clustering
Method is clustered, and in cluster process, different clustering parameters is arranged and carries out repeatedly cluster operation, and using special based on data itself
The Cluster Assessment index of sign scores to each cluster result, so that it is determined that best cluster result；
And as a result output module, for obtaining each space cell and its corresponding cluster according to best cluster result
Number, the result as Urban Spatial Morphology auto-partition；Or the crucial effect of output Urban Spatial Morphology auto-partition refers to
Target exports the crucial effect index of Urban Spatial Morphology subregion simultaneously；The crucial effect index passes through to Urban Spatial Morphology
Data in feature summary sheet carry out correlation analysis and obtain.
A kind of Urban Spatial Morphology auto-partition system of the present invention includes at least a computer equipment, described
Computer equipment include memory, processor and storage on a memory and the computer program that can run on a processor, institute
It states when computer program is loaded on processor and realizes the Urban Spatial Morphology automatic Mesh Partition Method.
The utility model has the advantages that a kind of Urban Spatial Morphology automatic Mesh Partition Method proposed by the present invention and system, by city space shape
State is three-dimensional whole as one, comprehensively considers various dimensions morphological feature, using computerized algorithm, is included in multiple Urban Spatial Morphologies
Feature carries out cluster operation, can be realized utmostly approach to " entirety " of spatial shape rather than estimating for " side "；For
The output of division result is also based on the data unique characteristics parameter such as Silhouette coefficient, and result is converged on to cluster knot automatically
Fruit is distributed optimal state, and human brain judgement is avoided to lead to the randomness of technical result.And further to Urban Spatial Morphology point
Crucial effect index is determined in area, the space shape for the control that is conducive to concentrate on crucial points in the planning and designing in research range
State index feature, and then the Urban Spatial Morphology characteristic of the research range is held on the whole.The invention avoids traditional operations
In cannot be considered in terms of Urban Spatial Morphology three-dimensional globality, for crucial effect index judgement lack scientific basis, index
Section, which determines, is related to human brain judgement, the problem that arbitrariness is also big for technical result, working efficiency is low.For being capable of discrimination city space shape
The inherent mechanism of state, and then the structural rule of city space is sought, provide reliable cognitive science foundation.
Detailed description of the invention
Fig. 1 is the method flow diagram of the embodiment of the present invention.
Fig. 2 carries out K- for matrix corresponding to the Dengfeng Urban Spatial Morphology feature summary sheet in the embodiment of the present invention
The result schematic diagram of means clustering algorithm, wherein (a) k=2, (b) k=4, (c) k=6, (d) k=10.
Fig. 3 is the result figure to be scored using Silhouette coefficient cluster result in the embodiment of the present invention.
Fig. 4 is the method flow diagram of another embodiment of the present invention.
Fig. 5 is the correlation matrix figure that Pearson Correlation Matrix operation is used in the embodiment of the present invention.
Specific embodiment
The technical scheme of the present invention will be explained in further detail with reference to the accompanying drawings and examples.
As shown in Figure 1, the embodiment of the invention discloses a kind of Urban Spatial Morphology automatic Mesh Partition Methods, it mainly include following
Step:
S1: the Urban Spatial Morphology basic data in given range is obtained, is obtained from basic data as partitioning algorithm
Several space cells of foundation.
In this step, the basic data of Urban Spatial Morphology can be obtained by government department or other data provision platforms
Library includes several space cells according to block, land used or property right in basic database；Geographic information processing can also be passed through
Software to map or image data are handled, and voluntarily process acquisition in conjunction with City Building basic data.Space cell is logical
Often it is block (geometry that urban road encloses), may be land used (according to " Classification of Urban Land and planning construction are used
Ground standard " to block further division) or property right (spatial dimension formed based on land ownership), profile be closed it is more
The polygon space that section line is constituted, data format can be dwg format or shp format etc..Generally there is building inside space cell
Object, contour of building are also the polygon space for being closed multi-section-line and constituting, and data format is also possible to dwg format or shp format,
The label of each building inside space cell has information (such as 1,2,3 ...) and/or elevation information.In no height
In the case where information, elevation information (number of plies information * 3m) can also be extrapolated by the number of plies.
S2: calculating for each space cell according to multiple Urban Spatial Morphology indexs of setting automatically, and it is empty to generate city
Between morphological feature summary sheet.
In this step, the useful ground area of Urban Spatial Morphology index, site coverage, plot ratio, maximum area of base, maximum
The index of the representation spaces unit self-characteristics such as building height, maximum construction area, average building height and degree straggly.Pass through
The geometric area that space cell profile can be obtained is calculated the polygon space geometry that closure multi-section-line is constituted, space cell
Land area can be indicated with the geometric area of its profile；Equally, the polygon space geometry by being constituted to closure multi-section-line
Calculate the geometric area that can also obtain contour of building, the floor space as each building in space cell.
Site coverage is the ratio of the sum of floor space of owned building in space cell with space cell land area；
Plot ratio is the floor space of the owned building in space cell and the summation of building number of plies product and space cell ground
Long-pending ratio；Maximum area of base is the maximum value of the floor space of the owned building in space cell；Maximum building height is
The maximum value of the height of owned building in space cell；Maximum construction area is the bottom of the owned building in space cell
The maximum value of area and building number of plies product；Average building height is being averaged for the height of the owned building in space cell
Value；Degree straggly is the variance of the height of the owned building in space cell.
Two kinds in the These parameters spatial shape feature summary sheets for calculating each space cell are generally at least selected, in reality
Combination can be voluntarily selected in operating process by user or provides the indicator combination of default, such as: site coverage, plot ratio group
It closes, Synthetic Measurement is carried out to the intensity scope in the form of city space；Maximum building height, average building height, degree straggly
Combination carries out Synthetic Measurement to the height scope in Urban Spatial Morphology；Maximum area of base, is most built in large scale maximum building height
Areal array is built, Synthetic Measurement is carried out to the significant scope of building in Urban Spatial Morphology；Whole indicator combinations, with maximum journey
Spend the global concept scope of this object of " approaching " Urban Spatial Morphology.It should be noted that Urban Spatial Morphology is one multiple
Miscellaneous and comprehensive concept or object, the index of each dimension, which can be seen as defining from a side, describes this object；
With increasing for index, the label for describing this object of Urban Spatial Morphology is also more, the dimension for being defined and describing to it
Also increase therewith；Land area that the embodiment of the present invention is enumerated, site coverage, plot ratio, maximum area of base, maximum building are high
Degree, maximum construction area, average building height, degree straggly for the Urban Spatial Morphology of one space cell of description it is the most universal and
Common index；But the present invention is not limited to These parameters, however not excluded that there is a possibility that other index, such as institute through the invention
The mutual operation enumerated between index can infinitely define new index.
S3: matrix corresponding to Urban Spatial Morphology feature summary sheet is clustered, and is joined by the way that different clusters is arranged
Number carries out repeatedly cluster operation, selects best cluster result using the Cluster Assessment index based on data unique characteristics.
In this step, common Unsupervised clustering algorithm can be used and carry out cluster operation, such as based on the K-means of central point
Cluster, the hierarchical clustering based on Connected degree, the DBSCAN cluster based on density, the GMM-EM cluster based on distribution.Cluster process
In, for successively specifying and being polymerized to different clusters numbers (such as 2,3,4 ... 30) based on central point and based on the clustering algorithm of distribution
Obtain multiple cluster results；For the clustering algorithm based on Connected degree, tree obtained will be clustered, it is downward from root node
Successively traversal, each layer correspond to a cluster result；For density-based algorithms, it is sequentially increased radius of neighbourhood acquisition
Multiple cluster results.For using multiple cluster results of any acquisition of above method, using based on data unique characteristics
Cluster Assessment index, such as: Dunn index, Davies-Bouldin index and Silhouette coefficient (silhouette coefficient) are to poly-
Class result scores, and selects best cluster result according to scoring.
S4: according to best cluster result, each space cell and its corresponding cluster number are obtained, as city space shape
The result of state auto-partition.Division result can export or with the displaying of corresponding Urban Spatial Morphology sectional image.
Using the Urban Spatial Morphology automatic Mesh Partition Method of the embodiment of the present invention, city sky can be known clearly with rationality and comprehensively
Between form feature, and then formed auto-partition as a result, avoiding the subjective judgement or investigation being easy to appear in conventional method
The problems such as dimension is single, to more fully understand and organizing the complication system of Urban Spatial Morphology to provide the foundation of science.
Technical solution of the present invention will be described in detail by taking the division of Dengfeng City's Urban Spatial Morphology as an example below.Tool
The Urban Spatial Morphology automatic Mesh Partition Method of body specifically includes that
(1) using the Urban Spatial Morphology of Dengfeng as research object, its Urban Spatial Morphology basic data is obtained.This example is to it
Urban Spatial Morphology raster image carries out vector quantization and arranges and space cell division；It specifically includes:
(1.1) it is inserted into Urban Spatial Morphology raster image corresponding in research range in CAD software, and is adjusted to real
Border size；
(1.2) contour line for sketching the contours of all blocks in Urban Spatial Morphology forms the space cell of vector quantization；
(1.3) contour line for drawing all buildings inside each block, is labeled in this for the number of plies number that every building is built and builds
Build the inside of contour line.
(2) space cell of division is numbered, and carries out multiple Urban Spatial Morphologies for each space cell
Index calculates, and generates Urban Spatial Morphology feature summary sheet；It specifically includes:
(2.1) 1,2 is numbered to the space cell being made of block ..., n forms 7 indexs to each space cell
Calculating, corresponding code is respectively YDMJ, JZMD, RJL, ZDJZGD, ZDJZMJ, PJJZGD, CLD；
1 Urban Spatial Morphology index of table
(2.2) summarize the calculated result of YDMJ, JZMD, RJL, ZDJZGD, ZDJZMJ, PJJZGD, CLD, it is empty to generate city
Between morphological feature summary sheet, be considered as the matrix of a n*7.
(3) matrix corresponding to the Urban Spatial Morphology feature summary sheet of Dengfeng is subjected to the K-means based on mahalanobis distance
Clustering algorithm in cluster process, sets gradually k=2, and 3 ..., 30, as shown in Fig. 2, wherein k=2 is only enumerated in figure, 4,6,10
Corresponding result；It for each k value, is scored using Silhouette coefficient cluster result, score highest k
Value, then be optimal k value, corresponding to cluster result be best cluster result, as shown in figure 3, display as k=4, be best
Cluster result.
For any data point i in data set, a (i) is enabled to indicate average value of the data point i to like numbers strong point distance, b
(i) indicate data point i to the minimum value in other Various types of data point distance averages.S (i) indicates data point i's
Silhouette coefficient, Silhouette coefficient can be defined as:
Note: for the cluster of s (i)=1, it is scored at 0.This constraint is added to prevent cluster quantity from dramatically increasing.For one
A data set, its Silhouette coefficient are the average value of all data point Silhouette coefficients.Generic data skip distance
Remoter with a distance from close and different classes of data, score is higher.For s (i) close to 1, it would be desirable to a (i) < <b (i).Due to s
It (i) is to measure i and its own cluster measurement that have much degree different, therefore lesser value means that it is matching well.
In addition, big b (i) means that i cluster adjacent thereto matches very much.Therefore, the s (i) close to 1 means that data are suitably gathered
Class.If s (i) passes through identical logic close to negative value, it is seen that, can more if it is gathered in its adjacent cluster
Properly.S (i) means that the data are located on the boundary of two natural clusters close to zero.
(4) each space cell and its number export of corresponding cluster are obtained by city space according to best cluster result
The result of form auto-partition.It specifically includes:
(4.1) each space cell and its number export of corresponding cluster are obtained by city sky according to best cluster result
Between form auto-partition result；
(4.2) filling that a kind of color is carried out to the space cell of same class cluster number, by Urban Spatial Morphology subregion
Result be restored to spatial image, i.e., division result is shown with the plane geometry image of color lump.
As shown in figure 4, a kind of Urban Spatial Morphology automatic Mesh Partition Method disclosed in another embodiment of the present invention, with aforementioned reality
It applies example to compare, may further comprise:
S5: the correlation in analysis institute's given range between Urban Spatial Morphology index, output Urban Spatial Morphology are automatic
The crucial effect index of subregion.It specifically includes:
(5.1) Pearson Correlation Matrix fortune is carried out to the data in Urban Spatial Morphology feature summary sheet
It calculates, generates correlation matrix figure, such as Fig. 5；
(5.2) compare the maximum index of the sum of every absolute value in correlation matrix figure, be in the present embodiment ZDJZGD,
As the crucial effect index in the Urban Spatial Morphology of Dengfeng.
Correlation operation method employed in this step further includes in addition to Pearson Correlation Matrix
Spearman's rank correlation、Kendall rank correlation、Goodman and Kruskal'
Srank correlation, Somers'D analysis etc..
A kind of Urban Spatial Morphology auto-partition system disclosed in another embodiment of the present invention, comprising: space cell obtains
Module includes or energy for obtaining the Urban Spatial Morphology basic data in given range, in Urban Spatial Morphology basic data
Multiple space cells are enough extracted, the profile of space cell is the polygon space of closure, and inside includes at least one building,
The profile of building is the polygon space of closure, and building has the number of plies and/or elevation information；Spatial shape index calculates mould
Block calculates automatically according to multiple Urban Spatial Morphology indexs of setting for being directed to each space cell, generates city space shape
State feature summary sheet；Wherein Urban Spatial Morphology index includes land area, site coverage, plot ratio, maximum area of base, most
At least two in big building height, maximum construction area, average building height and degree straggly；Cluster module is used for city
Matrix corresponding to city's spatial shape feature summary sheet is clustered using Unsupervised clustering algorithm, and in cluster process, setting is not
Same clustering parameter carries out repeatedly cluster operation, and using the Cluster Assessment index based on data unique characteristics to each cluster result
It scores, so that it is determined that best cluster result；And as a result output module, for obtaining each according to best cluster result
Space cell and its corresponding cluster number, the result as Urban Spatial Morphology auto-partition.Further, which also wraps
Spatial shape crucial effect index generation module is included, for the correlation between Urban Spatial Morphology index in range of analyzing and researching
Property, obtain the crucial effect index of Urban Spatial Morphology subregion.As a result output module output Urban Spatial Morphology auto-partition
As a result the crucial effect index of Urban Spatial Morphology subregion is exported while.The system embodiment belongs to above method embodiment
Identical inventive concept, specific implementation details can refer to above method embodiment, and details are not described herein again.
Based on identical inventive concept, the embodiment of the invention also discloses a kind of Urban Spatial Morphology auto-partition system,
The system includes at least a computer equipment, which includes memory, processor and store on a memory simultaneously
The computer program that can be run on a processor, the computer program realize above-mentioned city space shape when being loaded on processor
State automatic Mesh Partition Method.The unspecified part of the embodiment of the present invention is the prior art.
Claims (10)
1. a kind of Urban Spatial Morphology automatic Mesh Partition Method, which comprises the steps of:
(1) obtain the Urban Spatial Morphology basic data in given range, include in the Urban Spatial Morphology basic data or
Multiple space cells can be extracted, the profile of the space cell is the polygon space of closure, and inside includes at least one
Building, the profile of the building are the polygon space of closure, and the building has the number of plies and/or elevation information；
(2) it is directed to each space cell, is calculated automatically according to multiple Urban Spatial Morphology indexs of setting, city space shape is generated
State feature summary sheet；Wherein Urban Spatial Morphology index includes land area, site coverage, plot ratio, maximum area of base, most
At least two in big building height, maximum construction area, average building height and degree straggly；
(3) matrix corresponding to Urban Spatial Morphology feature summary sheet is clustered using Unsupervised clustering algorithm, was clustered
Cheng Zhong is arranged different clustering parameters and carries out repeatedly cluster operation, and uses the Cluster Assessment index based on data unique characteristics
It scores each cluster result, so that it is determined that best cluster result；
(4) according to best cluster result, each space cell and its corresponding cluster number are obtained, certainly as Urban Spatial Morphology
The result of dynamic subregion.
2. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that the method is also wrapped
It includes: correlation analysis is carried out to the data in Urban Spatial Morphology feature summary sheet, output Urban Spatial Morphology auto-partition
Crucial effect index.
3. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that the space cell
It is that the vector space unit to be formed is divided according to block, land used or property right.
4. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that the space cell
Land area be by closure multi-section-line constitute polygon space geometry calculate obtain；The site coverage is space list
The ratio of the sum of floor space of owned building in member and space cell land area；The plot ratio is in space cell
The ratio of the floor space of owned building and the summation of building number of plies product and space cell land area；The maximum substrate
Area is the maximum value of the floor space of the owned building in space cell；The maximum building height is the institute in space cell
There is the maximum value of the height of building；The maximum construction area is the floor space and building of the owned building in space cell
The maximum value of nitride layer number product；The average building height is the average value of the height of the owned building in space cell；Institute
State the variance that degree straggly is the height of the owned building in space cell；The floor space of the building passes through to closure multistage
The polygon space geometry that line is constituted, which calculates, to be obtained.
5. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that described unsupervised poly-
Class algorithm is the K-means clustering algorithm based on central point, the hierarchical clustering algorithm based on Connected degree, the DBSCAN based on density
One of clustering algorithm and GMM-EM clustering algorithm based on distribution are a variety of；The Cluster Assessment index be Dunn index,
One of Davies-Bouldin index and Silhouette coefficient.
6. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that the step (3)
It is middle that matrix corresponding to Urban Spatial Morphology feature summary sheet is gathered using the K-means clustering algorithm based on mahalanobis distance
Class in cluster process, is arranged different clusters numbers and carries out repeatedly cluster operation, and scored using Silhouette coefficient with true
Fixed best cluster result；Wherein Silhouette coefficient calculation method are as follows:
Indicate data point i to the average value of like numbers strong point distance, b (i) expression data any point i in data set, a (i)
For point i to the minimum value in other Various types of data point distance averages, s (i) indicates data point i's
Silhouette coefficient；The Silhouette coefficient of all data points is averaged be exactly cluster result totality
Silhouette coefficient.
7. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 2, which is characterized in that crucial effect index
Determining step includes:
Correlation operation is carried out to the data in Urban Spatial Morphology feature summary sheet, obtains correlation matrix figure；
Compare the maximum index of the sum of every absolute value in correlation matrix figure, refers to as the crucial effect in Urban Spatial Morphology
Mark.
8. a kind of Urban Spatial Morphology automatic Mesh Partition Method according to claim 1, which is characterized in that the step (4)
In obtain each space cell and its corresponding cluster number after, to same class cluster number space cell carry out a kind of face
The filling of color shows the result of Urban Spatial Morphology subregion with the plane geometry image of color lump.
9. a kind of Urban Spatial Morphology auto-partition system characterized by comprising
Space cell obtains module, for obtaining the Urban Spatial Morphology basic data in given range, the city space shape
Include in state basic data or multiple space cells can be extracted, the profile of the space cell is that the polygon of closure is empty
Between, inside includes at least one building, and the profile of the building is the polygon space of closure, and the building has layer
Several and/or elevation information；
Spatial shape index computing module, for being directed to each space cell, according to multiple Urban Spatial Morphology indexs of setting
It is automatic to calculate, generate Urban Spatial Morphology feature summary sheet；Wherein Urban Spatial Morphology index include land area, building it is close
In degree, plot ratio, maximum area of base, maximum building height, maximum construction area, average building height and degree straggly extremely
It is two kinds few；
Cluster Assessment module, for by matrix corresponding to Urban Spatial Morphology feature summary sheet using Unsupervised clustering algorithm into
Row clusters, and in cluster process, different clustering parameters is arranged and carries out repeatedly cluster operation, and using based on data unique characteristics
Cluster Assessment index scores to each cluster result, so that it is determined that best cluster result；
And as a result output module, for obtaining each space cell and its corresponding cluster volume according to best cluster result
Number, the result as Urban Spatial Morphology auto-partition；Or the crucial effect index of output Urban Spatial Morphology auto-partition
While export Urban Spatial Morphology subregion crucial effect index；The crucial effect index passes through to Urban Spatial Morphology spy
Data in sign summary sheet carry out correlation analysis and obtain.
10. a kind of Urban Spatial Morphology auto-partition system, includes at least a computer equipment, the computer equipment includes
Memory, processor and storage are on a memory and the computer program that can run on a processor, which is characterized in that the meter
Calculation machine program realizes Urban Spatial Morphology auto-partition side according to claim 1-8 when being loaded on processor
Method.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811188233.3A CN109492796A (en) | 2018-10-12 | 2018-10-12 | A kind of Urban Spatial Morphology automatic Mesh Partition Method and system |
| PCT/CN2018/116290 WO2020073430A1 (en) | 2018-10-12 | 2018-11-20 | Method and system for automatically partitioning urban spatial morphology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811188233.3A CN109492796A (en) | 2018-10-12 | 2018-10-12 | A kind of Urban Spatial Morphology automatic Mesh Partition Method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109492796A true CN109492796A (en) | 2019-03-19 |
Family
ID=65689449
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811188233.3A Pending CN109492796A (en) | 2018-10-12 | 2018-10-12 | A kind of Urban Spatial Morphology automatic Mesh Partition Method and system |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN109492796A (en) |
| WO (1) | WO2020073430A1 (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977600A (en) * | 2019-04-10 | 2019-07-05 | 中国科学院城市环境研究所 | A kind of standardized urban spatial shape compactedness Measurement Method and system |
| CN110135043A (en) * | 2019-05-08 | 2019-08-16 | 南京大学 | A kind of city street exterior feature spatial shape classification method and system |
| CN111311748A (en) * | 2020-02-19 | 2020-06-19 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN112184174A (en) * | 2020-10-12 | 2021-01-05 | 中国科学院计算技术研究所厦门数据智能研究院 | Method for automatically generating construction scheme of shelter type building |
| CN113393129A (en) * | 2021-06-17 | 2021-09-14 | 中国测绘科学研究院 | Massive building multi-scale block combination method considering road network association constraint |
| CN115049028A (en) * | 2022-08-17 | 2022-09-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN117408829A (en) * | 2023-10-27 | 2024-01-16 | 东北农业大学 | Method for automatically inducing and diagnosing barrier factors in farmland protection partition and characteristics |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130011069A1 (en) * | 2010-01-29 | 2013-01-10 | The Hong Kong University Of Science And Technology | Architectural pattern detection and modeling in images |
| CN103325010A (en) * | 2013-06-04 | 2013-09-25 | 东南大学 | Overall city height control partition method based on comprehensive divisor evaluation |
| CN104077448A (en) * | 2014-07-01 | 2014-10-01 | 东南大学 | Urban employment space analysis method based on employment network perspective |
| CN106529560A (en) * | 2015-12-09 | 2017-03-22 | 中国科学院城市环境研究所 | Method of identifying urban function area integrated with population density and landscape structure |
| CN108345688A (en) * | 2018-03-09 | 2018-07-31 | 东南大学 | A kind of digitlization translation of urban design and application process |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104679951B (en) * | 2015-02-11 | 2018-08-21 | 唐子来 | A kind of Urban Streets function zoning method of multifactor space clustering |
| CN107679229B (en) * | 2017-10-20 | 2021-06-01 | 东南大学 | Comprehensive acquisition and analysis method for high-precision spatial big data of urban three-dimensional building |
| CN107909111B (en) * | 2017-11-24 | 2020-06-26 | 中国地质大学（武汉） | Multi-level graph clustering partitioning method for residential area polygons |
| CN108416392A (en) * | 2018-03-16 | 2018-08-17 | 电子科技大学成都研究院 | Building clustering method based on SOM neural networks |
-
2018
- 2018-10-12 CN CN201811188233.3A patent/CN109492796A/en active Pending
- 2018-11-20 WO PCT/CN2018/116290 patent/WO2020073430A1/en active Application Filing
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130011069A1 (en) * | 2010-01-29 | 2013-01-10 | The Hong Kong University Of Science And Technology | Architectural pattern detection and modeling in images |
| CN103325010A (en) * | 2013-06-04 | 2013-09-25 | 东南大学 | Overall city height control partition method based on comprehensive divisor evaluation |
| CN104077448A (en) * | 2014-07-01 | 2014-10-01 | 东南大学 | Urban employment space analysis method based on employment network perspective |
| CN106529560A (en) * | 2015-12-09 | 2017-03-22 | 中国科学院城市环境研究所 | Method of identifying urban function area integrated with population density and landscape structure |
| CN108345688A (en) * | 2018-03-09 | 2018-07-31 | 东南大学 | A kind of digitlization translation of urban design and application process |
Non-Patent Citations (1)
| Title |
|---|
| 陈东梅: "《1960年代广州城市立体形态特征研究》", 《广州广播电视大学学报》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109977600A (en) * | 2019-04-10 | 2019-07-05 | 中国科学院城市环境研究所 | A kind of standardized urban spatial shape compactedness Measurement Method and system |
| CN109977600B (en) * | 2019-04-10 | 2022-06-14 | 中国科学院城市环境研究所 | Standardized urban three-dimensional space form compactness measuring method and system |
| CN110135043A (en) * | 2019-05-08 | 2019-08-16 | 南京大学 | A kind of city street exterior feature spatial shape classification method and system |
| CN110135043B (en) * | 2019-05-08 | 2023-04-18 | 南京大学 | City street contour space form classification method and system |
| CN111311748A (en) * | 2020-02-19 | 2020-06-19 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN111311748B (en) * | 2020-02-19 | 2023-06-30 | 广东小天才科技有限公司 | Indoor stereogram construction method and device, terminal equipment and storage medium |
| CN112184174A (en) * | 2020-10-12 | 2021-01-05 | 中国科学院计算技术研究所厦门数据智能研究院 | Method for automatically generating construction scheme of shelter type building |
| CN112184174B (en) * | 2020-10-12 | 2022-05-27 | 中国科学院计算技术研究所厦门数据智能研究院 | Method for automatically generating construction scheme of shelter type building |
| CN113393129A (en) * | 2021-06-17 | 2021-09-14 | 中国测绘科学研究院 | Massive building multi-scale block combination method considering road network association constraint |
| CN115049028A (en) * | 2022-08-17 | 2022-09-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN115049028B (en) * | 2022-08-17 | 2022-12-13 | 中建五局第三建设有限公司 | Construction area partitioning method, system, terminal and medium based on unsupervised learning |
| CN117408829A (en) * | 2023-10-27 | 2024-01-16 | 东北农业大学 | Method for automatically inducing and diagnosing barrier factors in farmland protection partition and characteristics |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2020073430A1 (en) | 2020-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109492796A (en) | A kind of Urban Spatial Morphology automatic Mesh Partition Method and system | |
| CN101763644B (en) | Pulmonary nodule three-dimensional segmentation and feature extraction method and system thereof | |
| CN106779087A (en) | A kind of general-purpose machinery learning data analysis platform | |
| CN106537422A (en) | Systems and methods for capture of relationships within information | |
| CN104239299B (en) | Three-dimensional model retrieval method and apparatus | |
| CN105005789B (en) | A kind of remote sensing images terrain classification method of view-based access control model vocabulary | |
| CN109902736A (en) | A kind of Lung neoplasm image classification method indicated based on autocoder construction feature | |
| CN107679368A (en) | PET/CT high dimensional feature level systems of selection based on genetic algorithm and varied precision rough set | |
| CN104966106B (en) | A kind of biological age substep Forecasting Methodology based on support vector machines | |
| CN108540988A (en) | A kind of scene partitioning method and device | |
| CN111626321B (en) | Image data clustering method and device | |
| CN111524140B (en) | Medical image semantic segmentation method based on CNN and random forest method | |
| CN110349159A (en) | 3D shape dividing method and system based on the distribution of weight energy self-adaptation | |
| CN115713605A (en) | Commercial building group automatic modeling method based on image learning | |
| CN110348478B (en) | Method for extracting trees in outdoor point cloud scene based on shape classification and combination | |
| Dong et al. | New quantitative approach for the morphological similarity analysis of urban fabrics based on a convolutional autoencoder | |
| CN102349075A (en) | System for analyzing expression profile and program thereof | |
| CN113989291A (en) | Building roof plane segmentation method based on PointNet and RANSAC algorithm | |
| CN117408167A (en) | Debris flow disaster vulnerability prediction method based on deep neural network | |
| CN106815320B (en) | Investigation big data visual modeling method and system based on expanded three-dimensional histogram | |
| CN101241520A (en) | Model state creation method based on characteristic suppression in finite element modeling | |
| CN105243474A (en) | Spatio-temporal information based tailing pond safety risk evaluation method | |
| CN110264010B (en) | Novel rural power saturation load prediction method | |
| CN106980878A (en) | The determination method and device of three-dimensional model geometric style | |
| CN115273645B (en) | Map making method for automatically clustering indoor surface elements |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190319 |