CN112115844B - Urban population data analysis method based on multi-source remote sensing image and road network data - Google Patents
Urban population data analysis method based on multi-source remote sensing image and road network data Download PDFInfo
- Publication number
- CN112115844B CN112115844B CN202010968786.1A CN202010968786A CN112115844B CN 112115844 B CN112115844 B CN 112115844B CN 202010968786 A CN202010968786 A CN 202010968786A CN 112115844 B CN112115844 B CN 112115844B
- Authority
- CN
- China
- Prior art keywords
- data
- road network
- population
- urban
- network data
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 238000007405 data analysis Methods 0.000 title claims abstract description 30
- 238000012937 correction Methods 0.000 claims abstract description 10
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 239000011159 matrix material Substances 0.000 claims description 22
- 230000015654 memory Effects 0.000 claims description 12
- 230000006870 function Effects 0.000 claims description 11
- 230000005855 radiation Effects 0.000 claims description 8
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000000513 principal component analysis Methods 0.000 claims description 5
- 238000004422 calculation algorithm Methods 0.000 claims description 4
- 238000011430 maximum method Methods 0.000 claims description 4
- 230000001131 transforming effect Effects 0.000 claims description 4
- 238000009499 grossing Methods 0.000 claims description 2
- 238000005070 sampling Methods 0.000 claims description 2
- 230000002194 synthesizing effect Effects 0.000 claims description 2
- 238000007619 statistical method Methods 0.000 claims 1
- 238000007726 management method Methods 0.000 abstract description 6
- 238000013468 resource allocation Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005192 partition Methods 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000012732 spatial analysis Methods 0.000 description 3
- 238000012952 Resampling Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 235000011470 Adenanthera pavonina Nutrition 0.000 description 1
- 241000428378 Lopa Species 0.000 description 1
- 206010035664 Pneumonia Diseases 0.000 description 1
- 239000000443 aerosol Substances 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 239000008264 cloud Substances 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000000875 corresponding effect Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010355 oscillation Effects 0.000 description 1
- 238000013439 planning Methods 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- 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
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/182—Network patterns, e.g. roads or rivers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
- G06V20/53—Recognition of crowd images, e.g. recognition of crowd congestion
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Multimedia (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Development Economics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of population data analysis, in particular to an urban population data analysis method based on multi-source remote sensing images and road network data, which comprises the steps of obtaining urban night light data, vegetation data and road network data and carrying out data preprocessing; generating a first human residential area index image according to the urban night light data and the vegetation data; generating a road network density graph according to the road network data; and correcting the first human residential area index image through the road network density graph to generate a second human residential area index, wherein the second human residential area index is used for statistically analyzing the population data. Because the high resolution of the city night lamp tube data and the correction of the road network density graph generated by the road network data provide more details and more obvious spatial heterogeneity aiming at population data analysis, the population data is analyzed according to the second human residential area index, the accuracy and the precision of population data analysis are improved, and the method has great reference significance for city management and city resource allocation.
Description
Technical Field
The invention relates to the technical field of population data analysis, in particular to an urban population data analysis method based on multi-source remote sensing images and road network data.
Background
Population data not only reflects the basic data of the social and economic conditions of a country or a region, but also is one of the most important basic data in social and geographic research, and the analysis of the population data is not only widely applied to social resource allocation, environmental protection, city planning and the like, but also has great reference significance for city management and city resource allocation.
The existing population data are generally collected step by taking administrative district blooms as units, typical population statistical data are obtained step by step through modes such as general survey, sampling statistics and the like, the updating period is long, the space-time resolution ratio is low, multi-source data fusion and sum spatial analysis are not facilitated, and the application of the population statistical data in the multidisciplinary field is limited.
The spatial analysis of population data can not only solve the problems in the prior art, but also realize the coupling of population and other socioeconomic data, resource data and environmental data, and has important significance for improving the comprehensive management capacity of population, resources and environment, and although the Chinese patent application (with the publication number of CN 109978249A) discloses a population data spatialization method, system and medium based on partition modeling, a research area can be partitioned and a population data spatialization model of each partition is constructed based on partition modeling, the problem of low accuracy and precision of population data still exists in the process of population data spatialization analysis.
Disclosure of Invention
In order to overcome the defect of low accuracy in the population data spatial analysis process in the prior art, the urban population data analysis method based on the multi-source remote sensing image and the road network data provided by the invention has the advantages that the spatial pattern of urban population distribution is refined, and the accuracy of population data analysis is improved.
The invention provides a city population data analysis method based on multi-source remote sensing images and road network data, which comprises the following steps:
s100: obtaining urban night light data, vegetation data and road network data and carrying out data preprocessing;
s200: generating a first human residential area index image according to the urban night light data and the vegetation data;
s300: generating a road network density graph according to the road network data;
s400: and correcting the first human residential area index image through the road network density graph to generate a second human residential area index, wherein the second human residential area index is used for statistically analyzing population data.
Further, the data preprocessing comprises projecting the urban night light data and the vegetation data to a horizontal axis mercator system, and resampling the urban night light data and the vegetation data by using a bilinear difference algorithm to unify spatial resolution;
by usingPerforming radiation correction on the urban night light data, converting a digital value of the urban night light data into a radiation brightness value, and calculating a first human residential area index;
and classifying the road network data and extracting road network central lines in the road network data.
Further, the urban night light data is obtained through the Lopa A first remote sensing data, and the vegetation data is obtained through the aerospace bureau data information service center; and acquiring the road network data through an open source map.
Further, utilizeGenerating a first human residential area index image by using the urban night light data and the vegetation data,
wherein EVI max Synthesizing by a maximum method; LJ nor Is the radiance value, LJ, of the urban night light data max Is the maximum value of radiance, LJ, of the urban night light data min And the minimum value of the radiance of the urban night light data is obtained.
Further, generating a road network density map according to the road network data comprises the following steps:
s301: selecting a bandwidth and performing kernel density estimation on the road network data to generate a kernel density graph of the road network data;
s302: determining the weight of the road network data through principal component analysis;
s303: the kernel density map overlays the weights to generate a road network density map.
Further, the kernel density estimation is performed by estimating the density of a point or a line shape by means of a mobile unit; selecting a bandwidth for determining the kernel density estimate based on the road network data and population data, the bandwidth ranging from 2000-4000 meters; by using
And performing kernel density estimation on each road network data to generate a kernel density map.
Further, determining the weight of the road network data through principal component analysis comprises the following steps:
s304: establishing an initial matrix;
s305: transforming the initial matrix to obtain a normalized matrix;
s306: calculating m values and m principal component components through the standardized matrix to obtain a decision matrix;
s307: and determining a weight model according to the decision matrix and constructing a comprehensive evaluation function so as to obtain the weight of each road network data.
Further, by Correcting the road network density map for the first human residence index image to generate a second human residence index.
The invention further provides a computer readable storage medium, which stores computer instructions, and when executed by a processor, the computer implements a city population data analysis method based on multi-source remote sensing images and road network data as described in any one of the above.
The invention also provides an electronic device, which comprises at least one processor and a memory which is in communication connection with the processor, wherein the memory stores instructions which can be executed by the at least one processor, and the instructions are executed by the at least one processor, so that the processor executes the urban population data analysis method based on the multi-source remote sensing image and the road network data.
Compared with the prior art, the urban population data analysis method based on the multi-source remote sensing image and the road network data, provided by the invention, has the advantages that more details and more obvious spatial heterogeneity are provided for population data analysis due to the high resolution of the urban night lamp data and the correction of the road network density map generated by the road network data, the population data are analyzed according to the second human residence index, the human activities in the dense urban road network region can be clearly highlighted, the accuracy and precision of population data analysis are improved, and the method has great reference significance for urban management and urban resource allocation.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can obtain other drawings based on the drawings without inventive labor.
FIG. 1 is a flow chart of demographic data analysis provided by the present invention;
FIG. 2 is a schematic diagram of city night lamp data provided by the present invention;
FIG. 3 is a schematic diagram of road network data provided by the present invention;
FIG. 4 is a flow chart of generating a road network density map according to the present invention;
FIG. 5 is a line graph of bandwidth in a kernel density estimate provided by the present invention;
FIG. 6 is a generated road network density map provided by the present invention;
FIG. 7 is a scatter plot of urban night light data and population data provided by the present invention;
FIG. 8 is a graph of a linear relationship of first human residence index to demographic data;
FIG. 9 is a graph of regression analysis of average road network density and average population density;
FIG. 10 is a graph of a second human residence index plotted against population data;
FIG. 11 is a population data density graph provided by the present invention;
fig. 12 is a schematic diagram of an architecture of an electronic device according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
In the description of the present invention, it should be noted that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", etc., indicate orientations or positional relationships based on those shown in the drawings, and are only for convenience of description and simplicity of description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention. Furthermore, the terms "first" and "second" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
As shown in fig. 1, the method for analyzing urban population data based on multi-source remote sensing images and road network data provided by the invention comprises the following steps: s100: obtaining urban night light data, vegetation data and road network data and carrying out data preprocessing; s200: generating a first human residential area index image according to the urban night light data and the vegetation data; s300: generating a road network density graph according to the road network data; s400: and correcting the first human residential area index image through the road network density graph to generate a second human residential area index, wherein the second human residential area index is used for statistically analyzing population data.
In specific implementation, as shown in fig. 1 to 11, in the analysis of urban population data in this embodiment, by taking shenzhen city as an example, by acquiring urban night light data, vegetation data and road network data and performing data preprocessing, generating a first human living quarter index image according to the urban night light data and the vegetation data, and generating a road network density map according to the road network data; and correcting the first human residential area index image through the road network density map to generate a second human residential area index, wherein the second human residential area index is used for statistically analyzing population data, and the spatial pattern of urban population distribution is refined, so that the population data analysis is more accurate and precise.
With the popularization of high-resolution remote sensing data, a spatialization method based on pixel features becomes an important means for population spatialization, and modeling auxiliary data is gradually developed into building information and social media data from land utilization data. In a common remote sensing image, night lamplight data can detect light with different intensities sharply, and the intensity and the width of human mouth space distribution can be rapidly and comprehensively expressed by fewer data sources;
with the rapid development of the remote sensing technology, the first professional noctilucent remote sensing satellite Lopa A designed by Wuhan university successfully transmits and returns images in 2018 and 6 months, and compared with the data of a visible light infrared imaging radiometer (NPP-VIIRS for short), the data of the first professional noctilucent remote sensing satellite Lopa A is remarkably improved in spatial resolution and quantitative level, so that a more perfect data source is provided for small-scale population distribution simulation.
As shown in fig. 2, in this embodiment, the urban night light data is obtained through the first ia Lopa remote sensing data, which not only improves the accuracy of urban population data analysis and population data density map generation, but also better reveals the detailed characteristics of urban population distribution; specifically, urban night light data are obtained from Hubei data and a high-resolution earth observation system website of an application center, the resolution is 130m, and the width is 250km.
Vegetation data (EVI for short) is obtained from the data information service center of the American national aerospace agency, the spatial resolution of the vegetation data is 250m, the time resolution is 16 days, and the obtained vegetation data is subjected to solar radiation correction, atmospheric correction, aerosol, water, cloud and the like, so that the influence of the reflectivity of the atmosphere and soil is reduced to the maximum extent, and preferably, 23 images of the vegetation data are obtained in the embodiment.
As shown in fig. 3, road network data is obtained from open source maps (OSM for short) according to the classification and interpretation of road classes in wikipedia.
The data preprocessing comprises the steps of preprocessing the urban night light data, the vegetation data and the road network data respectively, specifically, projecting the urban night light data and the vegetation data to a universal transverse axis mercator (UTM) system, and then resampling the urban night light data and the vegetation data by using a bilinear interpolation algorithm to unify the spatial resolution to be 100m; and registering the image of the urban night light data with the high-precision Google Map image, and then carrying out radiation correction.
In particular, utilizePerforming radiation correction on the urban night light data to convert a digital value into a radiation brightness value and calculate a first human residential area index; wherein L is the radiance value in W/(m) 2 Sr · μm), DN is the digital value of the pixel;
in order to eliminate the influence of cloud, processing the images of the vegetation data by utilizing a maximum algorithm to generate a synthesized vegetation data image;
the preprocessing of the road network data comprises classifying the road network data and extracting road network center lines in the road network data, wherein in the embodiment, the road network data comprises expressway data, road main road data, road secondary main road data, road branch road data, traffic track data and auxiliary road data, wherein the traffic track data comprises railway data and subway data, and the auxiliary road data comprises bicycle road data, pedestrian road data, residential street data and the like; since many roads are bidirectional roads and subsequent road network length calculation needs to be repeated, which affects the accuracy of the result, the center line of the two-line element in the road network is extracted by using the ArcGIS software in the embodiment.
In the prior art, the study on urban road network density only considers urban traffic results, and does not consider the relationship between urban traffic results and population, but in cities, communication and transportation between materials and residents depend on roads, the higher the road network density is, the better the road communication is, the greater the inhabitant attraction is, meanwhile, the more residents live in, the more the road traffic is suitable for the residents to go out, and the road network density is further improved, so that in consideration of the close relationship between the urban road network density and the population, the road network data is divided into the above six types and is respectively processed.
Secondly, utilizeGenerating a first human residential area index image by using urban night light data and the vegetation data, wherein EVI max In order to synthesize a plurality of vegetation data by the maximum method, in this embodiment, 23 images of vegetation data are synthesized by the maximum method, EVI max =MAX(EVI 1 ,EVI 2 ,…, EVI 23 );LJ nor Is the normalized radiance value of the urban night light data,LJ max is the maximum value of radiance, LJ, of the urban night light data min And the minimum value of the radiance of the urban night light data is obtained.
Then, a road network density map is generated according to each road network data, specifically, as shown in fig. 4 and fig. 5, the kernel density estimation estimates the density of points or lines by means of a mobile unit (equivalent to a window), in the kernel density estimation, the determination or selection of bandwidth has a great influence on the calculation result, and as the bandwidth increases, the change of the point density in space is smoother, but the density result is masked; as the bandwidth decreases, the dot density becomes non-uniform.
Since the automatically generated bandwidth of each type of road network data is different, according to the linear correlation between the total kernel density of each type of road network data and the population, when the bandwidth is between 2000 and 4000 meters, the fluctuation of the correlation coefficient of various road network data is minimal, and preferably, 3000 meters is selected as the bandwidth of the kernel density estimation of each type of road network data in the embodiment, so as to ensure that the correlation coefficient with the population data is relatively high and stable.
By usingPerforming kernel density estimation on each path of network data, wherein f (x, y) is density estimation at the position of (x, y), n is an observation value, and h is a bandwidth or smoothing parameter; d i Is the distance of the ith observation position of the (x, y) position,is a kernel function to satisfy the effect of 'distance attenuation'; preferably, the kernel function in this embodiment is a Quartic kernel function, and the kernel function may also be a Gaussian kernel function.
The principal component analysis is modified by the method of variable change
S304: establishing an initial matrix ofWherein x is ij The density sum of the jth type road network data of the ith town is represented;
s305: transforming the initial matrix to obtain a normalized matrix, in particular transforming the initial matrix X to Y = [ Y ] ij ] n×p WhereinThen, the Y is subjected to standardized transformation to obtain a standardized arrayWherein, S j respectively, the mean and standard deviation of the jth column in the Y array.
S306: calculating m values and m principal component components through the standardized matrix to obtain a decision matrix;
specifically, firstly, byCalculating the sample coefficients of the normalized matrix Z according to R-lambdai p The | =0 obtains the characteristic value, and p characteristic values lambda 1 are more than or equal to lambda 2 and more than or equal to 8230, and lambda p is more than or equal to lambda 0;
then, byDetermining the value of m to enable the cumulative contribution rate to reach more than 80%; for each λ j, j =1,2, \ 8230, m is according to Rb = λ j b obtaining the vectorThen find z i =(z i1 ,z i2 ,…,z ip ) T M principal component components of Deriving a decision matrixWherein u is i Is the principal component vector of the ith variable.
S307: and determining a weight model according to the decision matrix and constructing a comprehensive evaluation function so as to obtain the weight of each road network data.
Wherein, F 1 ,F 2 ,…,F m M principal components obtained after analysis; u. of ij Coefficients in the decision matrix; weight model and initial factor load f ij Satisfy the requirement of
On the basis, a comprehensive evaluation function is constructed, the comprehensive evaluation function is,
κ=λ 1 +λ 2 +…+λ m wherein a is 1 ,a 2 ,…a L I.e. the index w 1 ,w 2 ,…, w L The overall importance in the principal component;
As shown in fig. 6, in this embodiment, the weights of the highway data, the road main road data, the road secondary main road data, the road branch road data, the transportation track data and the auxiliary road data in shenzhen city are 0.2, 0.15, 0.08, 0.15, 0.21 and 0.2 in sequence; and generating a synthesized road network density map by superposing the road network data kernel density map and the weight of each road network data kernel density map. It follows that most road networks in Shenzhen city are concentrated in southwest region, especially in southern mountain region and Futian region, while road networks in north and south east are most sparse.
As shown in fig. 7, in the prior art, for the analysis of population data, a linear relationship is formed by observing a scatter diagram between the cumulative radiance value of the urban night light data and the general population of the village and the town, and a coefficient R is determined 2 0.67, but the linear relationship is not strong, and the urban night light data cannot detect the light data of the underground commercial streets and the underground traffic in consideration of the existence of the underground commercial streets and the underground traffic in the city, so that the light data pixels are lost, and the population data is underestimated.
As shown in FIG. 8, the coefficient R is determined in a linear relationship between the first human population and the overall population of the township 2 At 0.70, the linear relationship is still not strong, mainly because the population underestimation problem is not solved and is not suitable for the analysis of population data.
As shown in fig. 9, in addition to the population analysis, in order to more accurately analyze the population data, the first human residential area index is corrected using the road network data to solve the problem of population underestimation in the dense road network region, the average population density and the average road network density are regressed, the average population density and the average road network density are distributed by a power function and highly correlated, and the coefficient R is determined 2 And was 0.78.
Therefore, as shown in fig. 10, in the present embodiment, the first human residence index image is corrected by the road network density map to generate the second human residence index, specifically, by
Obtaining the second human residential district indicates that the second human residential district index corrected by the road network density map in this embodiment converges to a regression line more than that in the prior art, and determines the coefficient R 2 From 0.70 to 0.84, thereby increasing the accuracy of the demographic data analysis.
The Mean Relative Error (MRE) is used to quantify the mean oscillation amplitude reflecting the deviation between the estimated and measured values,the root mean square error divided by the average town population count (% RMSE) is used to measure the deviation between the estimated and actual values, reflect the accuracy of the simulation, evaluate the predictive power of each model, wherein, PE i Representing the estimated population, P, of the ith town i Representing the actual population of the ith town, n being the number of towns, M pop Is the average town population.
HSI | RAHSI | WorldPop | |
R 2 | 0.70 | 0.84 | 0.77 |
MRE(%) | 74.35 | 34.80 | 47.36 |
%RMSE | 83.26 | 42.29 | 54.15 |
As shown in the above table, when population data analysis is performed by using the first human residential area index, MRE and% RMSE are 74.35% and 83.26%, respectively, and the existence of underground commercial streets and underground traffic is not considered, so that the estimated population data of a dense area of several road networks in a city is underestimated.
Whereas in the technique given the first human population plot index, combining road network data and road network density maps based on population density, MRE and% RMSE were 34.80% and 42.29%, respectively, with a significant drop, and were lower than MRE =47.36% and% RMSE =54.15% of the WorldPop data set.
Preferably, as shown in fig. 11, fig. 11 shows a population density grid map in shenzhen city, the spatial resolution of which is 100m, in this embodiment, the population density map is generated according to the second human residence to assist in population data analysis, and preferably, when the population density map is generated, in order to eliminate the overall deviation of the second human residence index, the ratio of the actual total population divided by the estimated population is used as a correction factor. Therefore, shenzhen population is mainly concentrated in the midwest region, and the new region of Roc in the eastern region is the region with the least population; the southern Baoan region, the southern mountain region, the Futian region and the West Roohu region are densely populated areas.
Population density maps are generated based on the second human residence indications, which can be used for urban resource allocation, population research, decision making, and urban emergency response, and can also assist in urban risk management, for example, during a new coronary pneumonia epidemic, which can be an important database for government prevention and control efforts.
Compared with the prior art, the urban population data analysis method based on the multi-source remote sensing image and the road network data, provided by the invention, has the advantages that more details and more obvious spatial heterogeneity are provided for population data analysis due to the high resolution of the urban night lamp data and the correction of the road network density map generated by the road network data, the population data are analyzed according to the second human residence index, the human activities in the dense urban road network region can be clearly highlighted, the accuracy and precision of population data analysis are improved, and the method has great reference significance for urban management and urban resource allocation.
The invention further provides a computer-readable storage medium, which stores computer instructions, and when the computer instructions are executed by a processor, the method for analyzing the urban population data based on the multi-source remote sensing images and the road network data can be implemented.
In specific implementation, the computer-readable storage medium is a magnetic Disk, an optical Disk, a Read-only Memory (ROM), a Random Access Memory (RAM), a Flash Memory (Flash Memory), a Hard Disk (Hard Disk Drive, abbreviated as HDD), or a Solid-State Drive (SSD); the computer readable storage medium may also include a combination of memories of the above kinds.
The present invention further provides an electronic device, as shown in fig. 12, which includes at least one processor and a memory communicatively connected to the processor, wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the processor performs a method for analyzing urban population data based on multi-source remote sensing images and road network data as described in the above embodiments.
In particular, the number of processors may be one or more, and the processor may be a Central Processing Unit (CPU). The Processor may also be other general purpose processors, digital Signal Processors (DSPs), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, or a combination thereof. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory and the processor may be communicatively connected by a bus or other means, the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor, so that the processor executes the method for analyzing urban population data based on the multi-source remote sensing image and the road network data according to any one of the first embodiment or the second embodiment.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the scope of the technical solutions of the embodiments of the present invention.
Claims (5)
1. A city population data analysis method based on multi-source remote sensing images and road network data is characterized by comprising the following steps:
s100: obtaining urban night light data, vegetation data and road network data and carrying out data preprocessing;
s200: generating a first human residential area index image according to the urban night light data and the vegetation data;
s300: generating a road network density graph according to the road network data;
s400: correcting the first human residential zone index image by the road network density map to generate a second human residential zone index, the second human residential zone index being used for statistical analysis of population data;
the data preprocessing comprises projecting the urban night light data and the vegetation data to a horizontal-axis mercator system, and sampling the urban night light data and the vegetation data by using a bilinear interpolation algorithm to unify spatial resolution;
by usingPerforming radiation correction on the urban night light data, converting a digital value of the urban night light data into a radiation brightness value, and calculating a first human residential area index; wherein L is the radiance value in W/(m) 2 * sr μm), DN is the digital value of the pixel;
classifying the road network data and extracting road network central lines in the road network data;
the urban night light data is obtained through the Lopa A first remote sensing data, and the vegetation data is obtained through the aerospace bureau data information service center; acquiring the road network data through an open source map;
by usingGenerating a first human living area index image from the urban night light data and the vegetation data,
wherein EVI max Synthesizing a plurality of vegetation data by a maximum method; LJ nor For the normalized radiance value of the urban night light data,LJ max is the maximum value of radiance, LJ, of the urban night light data min The radiance of the urban night light data is maximumA small value;
the method for generating the road network density graph according to the road network data comprises the following steps:
s301: selecting a bandwidth and performing kernel density estimation on the road network data to generate a kernel density graph of the road network data;
s302: determining the weight of the road network data through principal component analysis;
s303: the kernel density map is overlapped with the weight to generate a road network density map;
2. The urban population data analysis method based on the multi-source remote sensing image and the road network data as claimed in claim 1, wherein the method comprises the following steps: the kernel density estimation is performed by estimating the density of points or lines by means of a mobile unit; selecting a bandwidth for determining the kernel density estimate based on the road network data and population data, the bandwidth ranging from 2000-4000 meters; by using
Performing kernel density estimation on each road network data to generate a kernel density map, wherein f (x, y) is density estimation at a (x, y) position, n is an observation value, and h is a bandwidth or smoothing parameter; d is a radical of i Is the distance of the ith observation position of the (x, y) position.
3. The urban population data analysis method based on the multi-source remote sensing image and the road network data as claimed in claim 2, wherein the weight of the road network data is determined through principal component analysis, and the method comprises the following steps:
s304: establishing an initial matrix;
s305: transforming the initial matrix to obtain a standardized matrix;
s306: calculating m values and m principal component components through the standardized matrix to obtain a decision matrix;
s307: and determining a weight model according to the decision matrix and constructing a comprehensive evaluation function so as to obtain the weight of each road network data.
4. A computer-readable storage medium characterized by: the computer readable storage medium stores computer instructions, and when executed by a processor, the computer implements a city population data analysis method based on multi-source remote sensing images and road network data according to any one of claims 1 to 3.
5. An electronic device, characterized in that: comprising at least one processor, and a memory communicatively coupled to the processor, wherein the memory stores instructions executable by the at least one processor, the instructions being executable by the at least one processor to cause the processor to perform a method for urban demographic data analysis based on multi-source remote sensing imagery and road network data according to any one of claims 1-3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010968786.1A CN112115844B (en) | 2020-09-15 | 2020-09-15 | Urban population data analysis method based on multi-source remote sensing image and road network data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010968786.1A CN112115844B (en) | 2020-09-15 | 2020-09-15 | Urban population data analysis method based on multi-source remote sensing image and road network data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112115844A CN112115844A (en) | 2020-12-22 |
CN112115844B true CN112115844B (en) | 2022-10-18 |
Family
ID=73802240
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010968786.1A Active CN112115844B (en) | 2020-09-15 | 2020-09-15 | Urban population data analysis method based on multi-source remote sensing image and road network data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112115844B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113688873B (en) * | 2021-07-28 | 2023-08-22 | 华东师范大学 | Vector road network generation method with visual interaction capability |
CN113610873B (en) * | 2021-10-09 | 2022-04-01 | 中国科学院地理科学与资源研究所 | Noctilucent remote sensing image data processing method and device |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229913A (en) * | 2017-05-23 | 2017-10-03 | 国家地理空间信息中心 | Density of population analysis system based on high score satellite remote sensing date combination building height |
CN108537265A (en) * | 2018-03-30 | 2018-09-14 | 中南大学 | Urban population spatial and temporal distributions method of estimation based on night lights remotely-sensed data |
CN108804394A (en) * | 2018-05-23 | 2018-11-13 | 河海大学 | A kind of construction method of city noctilucence total amount-urban population regression model |
CN108871286A (en) * | 2018-04-25 | 2018-11-23 | 中国科学院遥感与数字地球研究所 | The completed region of the city density of population evaluation method and system of space big data collaboration |
CN110704565A (en) * | 2019-09-27 | 2020-01-17 | 泉州师范学院 | Demographic data gridding modeling method based on remote sensing and GIS |
CN111626103A (en) * | 2020-04-13 | 2020-09-04 | 中国科学院城市环境研究所 | Urbanization gradient measurement method based on night light remote sensing image |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9230169B2 (en) * | 2013-08-29 | 2016-01-05 | Digitalglobe, Inc. | Generation of high resolution population density data sets through exploitation of high resolution overhead imagery data and low resolution population density data sets |
-
2020
- 2020-09-15 CN CN202010968786.1A patent/CN112115844B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107229913A (en) * | 2017-05-23 | 2017-10-03 | 国家地理空间信息中心 | Density of population analysis system based on high score satellite remote sensing date combination building height |
CN108537265A (en) * | 2018-03-30 | 2018-09-14 | 中南大学 | Urban population spatial and temporal distributions method of estimation based on night lights remotely-sensed data |
CN108871286A (en) * | 2018-04-25 | 2018-11-23 | 中国科学院遥感与数字地球研究所 | The completed region of the city density of population evaluation method and system of space big data collaboration |
CN108804394A (en) * | 2018-05-23 | 2018-11-13 | 河海大学 | A kind of construction method of city noctilucence total amount-urban population regression model |
CN110704565A (en) * | 2019-09-27 | 2020-01-17 | 泉州师范学院 | Demographic data gridding modeling method based on remote sensing and GIS |
CN111626103A (en) * | 2020-04-13 | 2020-09-04 | 中国科学院城市环境研究所 | Urbanization gradient measurement method based on night light remote sensing image |
Non-Patent Citations (4)
Title |
---|
人口数据空间化研究综述;柏中强等;《地理科学进展》;20131115(第11期);全文 * |
基于2种夜间灯光影像亮度修正指数的城市建成区提取研究;闫庆武等;《地球信息科学学报》;20200811(第08期);全文 * |
基于Landsat OLI影像及 NPP-VIIRS灯光数据的武汉市人口密度估算;王娇娇等;《地域研究与开发》;20191210;全文 * |
融合多源空间数据的城镇人口分布估算;朱守杰等;《地球信息科学学报》;20200811(第08期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN112115844A (en) | 2020-12-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Xu et al. | Urban morphology detection and computation for urban climate research | |
Esch et al. | World Settlement Footprint 3D-A first three-dimensional survey of the global building stock | |
Garousi‐Nejad et al. | Terrain analysis enhancements to the height above nearest drainage flood inundation mapping method | |
Equere et al. | Definition of a new morphological parameter to improve prediction of urban heat island | |
Ren et al. | Developing a rapid method for 3-dimensional urban morphology extraction using open-source data | |
Baigorria et al. | Assessment of erosion hotspots in a watershed: integrating the WEPP model and GIS in a case study in the Peruvian Andes | |
Karimi et al. | Pedestrian network map generation approaches and recommendation | |
Zhong et al. | Assessment of solar photovoltaic potentials on urban noise barriers using street-view imagery | |
Ermolaev et al. | Automated construction of the boundaries of basin geosystems for the Volga Federal District | |
CN112115844B (en) | Urban population data analysis method based on multi-source remote sensing image and road network data | |
Deng et al. | Street-level solar radiation mapping and patterns profiling using Baidu Street View images | |
Peeters | A GIS-based method for modeling urban-climate parameters using automated recognition of shadows cast by buildings | |
Liu et al. | Estimation of surface and near-surface air temperatures in arid northwest china using landsat satellite images | |
Wu et al. | Developing a data-fusing method for mapping fine-scale urban three-dimensional building structure | |
Sánchez-Aparicio et al. | Ener3DMap-SolarWeb roofs: A geospatial web-based platform to compute photovoltaic potential | |
Tang et al. | Capturing Li DAR‐Derived Hydrologic Spatial Parameters to Evaluate Playa Wetlands | |
Hjelmstad et al. | Propagation of radar rainfall uncertainties into urban pluvial flood modeling during the North American monsoon | |
Kumar et al. | A multi-layer perceptron–Markov chain based LULC change analysis and prediction using remote sensing data in Prayagraj district, India | |
Ru et al. | An extended SW-TES algorithm for land surface temperature and emissivity retrieval from ECOSTRESS thermal infrared data over urban areas | |
Gupta et al. | An innovative approach for retrieval of gridded urban canopy parameters using very high resolution optical satellite stereo | |
Chen et al. | DeepUrbanDownscale: A physics informed deep learning framework for high-resolution urban surface temperature estimation via 3D point clouds | |
Kazak et al. | Land use change in suburban zone: European context of urban sprawl | |
Chen et al. | Urban land surface temperature retrieval from high spatial resolution thermal infrared image using a modified split-window algorithm | |
Xu et al. | A framework for the evaluation of roof greening priority | |
CN115829163A (en) | Multi-mode integration-based runoff prediction method and system for middle and lower reaches of Yangtze river |
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 |