A method, system, device and medium for identifying potential growth areas in cities

Abstract

The present invention provides a method, system, device and medium for identifying potential urban growth areas. The method mainly includes the following steps: obtaining a number of radar images of urban buildings, extracting building patches of urban buildings according to the radar images; determining the spatial pattern index of urban buildings according to the patch density of the building patches; obtaining thermal data of population activities, and determining the spatiotemporal weighted population vitality index according to the thermal data and a time weight coefficient; determining the urban vitality index of the building area according to the interference measurement results between radar images and the spatiotemporal weighted population vitality index; and determining the potential urban growth area according to the urban vitality index of the building area and the spatial pattern index. The scheme can identify the potential growth area, avoid misjudgment of vitality areas with different spatiotemporal characteristics due to the dynamic changes of urban vitality, improve the accuracy of urban vitality area identification, and can be widely used in the field of image recognition technology.

Description

Technical Field

[0001] The present invention relates to the field of image recognition technology, and in particular to a method, system, device and medium for identifying potential growth areas in a city. Background Art

[0002] With the acceleration of urbanization, many cities have entered a period of unique urban space problems. Urban sprawl, housing vacancy, urban decline and other problems have become increasingly prominent, seriously restricting the sustainable development of cities. Urbanization is in the stage of transition from scale growth to connotation growth. Building a vibrant, creative and livable modern city is a common issue discussed by scholars in the fields of urban planning, geography, socioeconomics, etc. Research on the spatiotemporal vitality and growth potential of cities can provide new ways to optimize urban resource allocation, rationally plan urban expansion, and balance urban spatial structure.

[0003] At present, urban potential growth is still limited to theoretical research in the fields of economics and sociology, and there are few studies on quantitative analysis. Generally speaking, there are two characteristics of potential areas for urban growth: (1) low building density and scale; (2) low population vitality. The former represents a low degree of land use in the area; the latter represents an area with high building density and scale and low population vitality, indicating that the utilization of infrastructure resources in the area is poor.

[0004] In the relevant technical solutions, namely the relevant technical solutions for predicting and judging urban vitality, the main problems are as follows:

[0005] (1) The commuting patterns of urban populations cause the vitality of urban areas to fluctuate over time. Existing urban vitality detection methods are not able to correct the errors caused by such fluctuations, resulting in poor recognition accuracy and misjudgment of urban vitality areas.

[0006] (2) There is less attention paid to the relationship between urban vitality and urban potential growth, and there is a lack of reasonable evaluation of the status of urban construction and development to guide urban redevelopment products. Summary of the invention

[0007] In view of this, in order to at least partially solve one of the above-mentioned technical problems, an embodiment of the present invention aims to provide a more accurate method for identifying potential growth areas in a city based on the theory of urban vitality and smart growth, as well as a corresponding system, device and storage medium.

[0008] On the one hand, the technical solution of the present application provides a method for identifying potential growth areas in an urban area, comprising the following steps:

[0009] Acquire a number of radar images of urban buildings, and extract building patches of the urban buildings according to the radar images;

[0010] Determining the spatial pattern index of the urban buildings according to the patch density of the building patches;

[0011] Acquiring thermal data of population activities, and determining a spatiotemporal weighted population vitality index based on the thermal data and a time weight coefficient;

[0012] Determining the urban vitality index of the building area according to the building patches of the urban buildings and the time-space weighted population vitality index;

[0013] The potential growth area of ​​the city is determined by coupling the urban vitality index of the building area and the spatial pattern index.

[0014] In a feasible embodiment of the present application, the method further includes the following steps:

[0015] Get street view imagery;

[0016] generating a city perception score based on the street view image;

[0017] The city perception score, the building area urban vitality index and the spatial pattern index are subjected to pairwise correlation calculations, and the potential growth area of ​​the city is verified based on the correlation calculation results.

[0018] In a feasible embodiment of the present application, the step of acquiring a plurality of radar images of urban buildings and extracting building patches of the urban buildings according to the radar images includes:

[0019] Removing noise from the radar image by adaptive filtering;

[0020] Perform phase unwrapping on the denoised radar image and remove the flat ground effect;

[0021] Geo-reference the radar image after removing the flat ground effect;

[0022] The building patch map is obtained by interferometric measurement based on the geo-referenced radar image.

[0023] In a feasible embodiment of the present application, the interferometric measurement based on the geo-referenced radar image to obtain the building patch map includes:

[0024] According to the radar images acquired within a preset time period, at least two radar images are compared to obtain surface changes;

[0025] The interferometric measurement result is obtained according to the degree of the surface change.

[0026] In a feasible embodiment of the solution of the present application, before the step of obtaining the interferometric measurement result according to the degree of the surface change, the method further includes the following steps:

[0027] Acquiring a number of radar images according to a preset time interval;

[0028] Acquire precise orbit data of image acquisition, and perform orbit deviation correction on the radar image according to the precise orbit data;

[0029] The elevation data is obtained from the radar image after the orbit deviation correction, and the elevation data is the benchmark reference data for interferometric measurement.

[0030] In a feasible embodiment of the present application, the step of obtaining the thermal data of population activities and determining the spatiotemporal weighted population vitality index according to the thermal data and the time weight coefficient includes:

[0031] Get a heat map of population activity intensity;

[0032] Divide the population activity intensity heat map into grids, and divide it into preset time periods to obtain the time period heat average value in the grids;

[0033] The time weight coefficient is calculated based on the ratio of the thermal value of the time period to the total thermal value of the time period, and the spatiotemporal weighted population vitality index is calculated based on the average thermal value of the time period and the time weight coefficient.

[0034] In a feasible embodiment of the present application, the step of determining the spatial pattern index of the urban buildings according to the patch density of the building patches includes:

[0035] The building patches are divided into zones, and the patch density is obtained according to the ratio of the number of the building patches in each zone to the area of ​​the zone.

[0036] On the other hand, the technical solution of the present application also provides a system for identifying potential urban growth areas, the system comprising:

[0037] A building patch acquisition unit, used to acquire a number of radar images of urban buildings, and extract the building patches of the urban buildings according to the radar images;

[0038] A building data processing unit, used for determining the spatial pattern index of the urban buildings according to the patch density of the building patches;

[0039] A population data processing unit, used for acquiring thermal data of population activities, and determining a spatiotemporal weighted population vitality index according to the thermal data and a time weight coefficient;

[0040] A building area urban vitality index extraction unit is used to determine the building area urban vitality index according to the building patches of the urban buildings and the spatiotemporal weighted population vitality index;

[0041] Potential growth area identification unit: Determine the potential growth area of ​​the city by coupling the urban vitality index of the building area and the spatial pattern index.

[0042] On the other hand, the technical solution of the present application also provides a device for identifying potential growth areas in a city, the device comprising:

[0043] at least one processor;

[0044] at least one memory for storing at least one program;

[0045] When the at least one program is executed by the at least one processor, the at least one processor runs a method for identifying potential growth areas in a city as described in any one of the first aspects.

[0046] On the other hand, the technical solution of the present application also provides a storage medium, which stores a program executable by a processor. When the program executable by the processor is executed by the processor, it is used to execute a method for identifying potential growth areas in a city as described in any one of the first aspects.

[0047] The advantages and beneficial effects of the present invention will be partially given in the following description, and the other parts can be understood through the specific embodiments of the present invention:

[0048] The technical solution of this application is based on the theory of urban vitality and smart growth. By integrating population thermal big data and building data extracted from satellite data, a spatiotemporal vitality model of built-up areas is constructed. The detection results of urban built-up areas are combined with the level of urban population activity. The urban development status at the level of physical entities and socio-economic activities is comprehensively studied to identify potential growth areas. The solution also combines the time weight method to quantify the tidal effect of crowd activities, avoid misjudgment of vitality areas with different spatiotemporal characteristics due to the dynamic changes in urban vitality, and improve the accuracy of identifying urban vitality areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0050] Figure 1 A flowchart of the steps of a method for identifying potential growth areas in a city provided in the technical solution of this application;

[0051] Figure 2 A flowchart of the interferometric measurement steps provided in the technical solution of this application;

[0052] Figure 3 A potential growth area identification flow chart provided in the technical solution of this application;

[0053] Figure 4 This is a schematic diagram of the building patch extraction results in the technical solution of this application;

[0054] Figure 5 (a) is one of the schematic diagrams of the building space pattern provided in the technical solution of this application;

[0055] Figure 5 (b) is the second schematic diagram of the building space pattern provided in the technical solution of this application;

[0056] Figure 5 (c) is the third schematic diagram of the building space pattern provided in the technical solution of this application;

[0057] Figure 5 (d) is the fourth schematic diagram of the building space pattern provided in the technical solution of this application;

[0058] Figure 6 (a) is one of the urban population vitality distribution results provided in the technical solution of this application;

[0059] Figure 6 (b) is the second result of the urban population vitality distribution provided in the technical solution of this application;

[0060] Figure 6 (c) is the third result of the urban population vitality distribution provided in the technical solution of this application;

[0061] Figure 6 (d) is the fourth result of the urban population vitality distribution provided in the technical solution of this application;

[0062] Figure 7 This is a rendering of the building area vitality index in the embodiment of the technical solution of this application;

[0063] Figure 8 The potential growth area detection results and street view images of typical areas in the embodiment of the technical solution of this application. DETAILED DESCRIPTION

[0064] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way. The execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0065] Previous academic research pointed out that the concept of urban vitality refers to the social activities and activity venues, which are manifested in people's rich social activities, and urban space provides a good environment for them, which is the endogenous driving force of urban development; urban vitality is composed of three parts: street space, population activities and building area environment. In subsequent academic research, the concept of urban vitality has been enriched. For example, urban vitality is reflected in the concentration of population in a day. With the development of network and communication computing, multi-source geographic big data provides a rich data source for the study of urban vitality; for example, POI data, location check-in data and housing price data can be combined to explore the impact of urban expansion patterns of urban agglomerations on urban vitality; for example, the spatial distribution characteristics of London's vibrant areas can be identified using bus smart cards and social platform data, etc. Although there are a lot of studies on urban vitality at this stage and quite rich results have been achieved, there are still the following shortcomings: First, most studies tend to ignore the spatiotemporal dynamic characteristics of urban vitality, and there are few studies on urban spatiotemporal vitality; second, buildings are the basic components of cities, and there are few studies on the spatiotemporal vitality of urban built-up areas; third, there is less attention paid to the relationship between urban vitality and urban potential growth, which is of certain significance to reducing the inefficient and irrational spread of cities.

[0066] Based on the above content and the deficiencies in current research pointed out in the background technology, or the defects in related technical solutions, the research theoretical basis adopted by the technical solution of this application is the theory of smart urban growth; that is, a method of achieving compact, intensive and efficient urban expansion with the goal of improving the quality of life and coordinating the development of economy, culture, resources and environment.

[0067] Based on the aforementioned urban smart growth theory, on the one hand, the technical solution of this application proposes a method for identifying potential urban growth areas, such as Figure 1 As shown, the method may include steps S100-S500:

[0068] S100: Acquire several radar images of urban buildings, and extract building patches of the urban buildings according to the radar images.

[0069] Specifically in the embodiment, remote sensing data, i.e., radar images, are first obtained through satellite collection, and preprocessing is performed on the radar images to reduce errors and place the data in a unified spatial coordinate system, thereby obtaining patch images of urban building areas. After image preprocessing, the scheme performs interferometric measurement through radar images, and the obtained surveying and measurement results will also be used for subsequent urban vitality analysis and identification of potential growth areas. It should be noted that the acquisition of satellite remote sensing data in the embodiment of the present application can be achieved by using Sentinel-1A satellite data. The Sentinel-1A satellite uses a progressive scanning method (terrain observation by progressive scans, TOPS) during imaging. The imaging data type selected in the embodiment is single-view complex image (SLC), interferometric measurement wide-band mode (IW), with a resolution of 5m×20m, and VV polarization mode. This imaging mode combination has high accuracy for the detection of vertical objects and is suitable for extracting buildings.

[0070] In some feasible embodiments, the step S100 of acquiring a plurality of radar images of urban buildings and extracting the building patches of the urban buildings according to the radar images may include steps S110-S130:

[0071] S110, removing noise points in the radar image by adaptive filtering; specifically in the embodiment, Figure 2 As shown in the figure, noise in radar images can be removed by adaptive filtering.

[0072] S120, performing phase unwrapping on the denoised radar image to remove the flat ground effect; specifically in the embodiment, phase unwrapping is performed to obtain a true and accurate phase difference, and to lay a foundation for subsequent interferometric measurement.

[0073] S130, geo-registering the radar image after removing the flat ground effect; specifically in the embodiment, since the flat ground will reflect the radar wave in a mirror manner, interfering with the echo signal, removing the flat ground effect is very important for the accuracy of the solution. Finally, the embodiment performs interferometric measurement based on the radar image after geo-registration to obtain a building patch map.

[0074] Specifically, in some feasible embodiments, before the step S400 of determining the urban vitality index of the building area according to the interferometric measurement results between the radar images and the spatiotemporal weighted population vitality index, interferometric measurement steps S140-S150 may be included:

[0075] S140, comparing at least two radar images according to the plurality of radar images acquired within a preset time period to acquire surface changes;

[0076] S150. Obtain the interferometric measurement result according to the degree of the surface change.

[0077] Specifically in the embodiment, interferometric measurement monitors the surface changes by comparing the radar images taken at two time points. The higher the degree of change, the lower the coherence value γ. Urban features that do not change at two time points, that is, features with a coherence value γ higher than 0.5, are judged as built-up areas. The threshold value TV of the coherence value γ is set γ =0.5, and the area where γ>0.5 is the building area, and the binary coherence value γ is obtained. b . γ b Areas with a value of 1 represent buildings, and areas with a value of 0 represent non-buildings:

[0078]

[0079] In some feasible embodiments, before the step S150 of obtaining the interferometric measurement result according to the degree of the surface change, the method may include: Figure 2 As shown, the process of pre-processing in the data collection process may also be included, and the process includes steps S111-S113:

[0080] S111. Acquire a number of radar images according to a preset time interval. Specifically, in the embodiment, acquire two SLC synthetic aperture radar images of the application area by Sentinel 1A, and the imaging time interval between the two images is 12 days, that is, one satellite global operation cycle.

[0081] S112, obtaining precise orbit data of image acquisition, and performing orbit deviation correction on the radar image according to the precise orbit data; specifically in the embodiment, the embodiment can obtain precise orbit data to correct the deviation caused by the running orbit.

[0082] S113, obtaining elevation data from the radar image after the orbit deviation correction, the elevation data is the benchmark reference data for interferometric measurement; specifically in the embodiment, the implementation also needs to obtain SRTM V4 elevation data. The elevation data is the benchmark reference data for interferometric measurement of radar images.

[0083] S200: Determine the spatial pattern index of the urban buildings according to the patch density of the building patches.

[0084] Specifically in the embodiment, after the urban building area patch image is obtained in step S100, the spatial pattern index of the building area patch obtained by the embodiment is calculated, wherein the spatial pattern index can be characterized by patch density, and the patch density (PD) parameter measures the building quality.

[0085] In some feasible embodiments, the step S200 of determining the spatial pattern index of the urban buildings according to the patch density of the building patches can be specifically step S201:

[0086] S201, classifying the building patches, and obtaining the patch density according to the ratio of the number of the building patches in each classification to the area of ​​the partition.

[0087] Specifically in the embodiment, the patch density (PD) parameter is used to measure the building quality. A high PD value means that the building scale in the area is small, the density is small, and the landscape fragmentation is high, which means that the urban building environment in the area is not well developed; the calculation formula is:

[0088]

[0089] In the calculation formula, PD represents plaque density, N represents the number of type i plaques in the region, and A represents the total area of ​​the region.

[0090] S300, obtaining thermal data of population activities, and determining a spatiotemporal weighted population vitality index according to the thermal data and a time weight coefficient.

[0091] Specifically in the embodiment, the open-source population activity intensity heat map can be crawled through the corresponding resource information portal website, and then the heat average index is calculated based on the population activity intensity heat map, and then the time weight coefficient is calculated based on the heat data. The time weight refers to the ratio of the heat value in a certain period of time in a specified area to the heat value in the total period of time. The weight coefficient is completely data-driven, overcoming the subjective factors brought by the artificially given weight coefficient. On the basis of the calculated time weight coefficient, the spatiotemporal weighted population vitality index is further calculated.

[0092] In some feasible embodiments, the method obtains thermal data of population activities, and determines the spatiotemporal weighted population vitality index according to the thermal data and the time weight coefficient, including steps S310-S330:

[0093] S310. Obtain a heat map of population activity intensity.

[0094] Specifically in the implementation, the embodiment first obtains the accurate application area boundary file through the national geographic information resource directory system. The file format is shp. The longitude and latitude coordinates of the upper left corner and the lower right corner of the study area are obtained. Then, through the open map resource longitude and latitude API, the longitude and latitude obtained from the national geographic information resource directory are converted into the longitude and latitude in the coordinate system used by the required map resource port; then the html source code of the heat map module is obtained, and then the corresponding heat map is saved.

[0095] S320, dividing the population activity intensity heat map into grids, and dividing it according to preset time periods to obtain the time period heat average value in the grid;

[0096] Specifically in the embodiment, the thermal average value refers to the average thermal value of the grid (region) within a certain period of time, and its value is proportional to the population. The formula of the constructed index is:

[0097]

[0098] In this calculation formula It represents the average heat value of a region in period j, where j represents different time periods. When j=1, it represents the daytime period on weekdays; when j=2, it represents the nighttime period on weekdays; when j=3, it represents the daytime period on weekends; and when j=4, it represents the nighttime period on weekends. i represents the time, H ij It represents the thermal value of the area at time i in period j. The daytime period is from 7:00 to 17:00 (a total of 11 hours), and the nighttime period is from 18:00 to 24:00 (a total of 7 hours).

[0099] S330, calculating the time weight coefficient according to the ratio of the heat value of the time period to the total heat value of the time period, and then calculating the spatiotemporal weighted population vitality index according to the heat average value of the time period and the time weight coefficient;

[0100] Specifically in the embodiment, the time weight coefficient needs to be calculated first, and the whole day is divided into a daytime period of 7:00 to 17:00 (a total of 11 hours), and a nighttime period of 18:00 to 24:00 (a total of 7 hours), and a total of four time periods are divided: a weekday daytime period, a weekday nighttime period, a rest daytime period, and a rest day nighttime period. The time weight refers to the ratio of the thermal value of a specified area in a certain period to the thermal value of the total period, and its calculation formula is:

[0101]

[0102] In the calculation formula, j represents different time periods. When j=1, it represents the daytime period on weekdays; when j=2, it represents the nighttime period on weekdays; when j=3, it represents the daytime period on weekends; and when j=4, it represents the nighttime period on weekends. i represents the time, H ij Indicates the thermal value of the area at time i in period j. The weight coefficient in the embodiment is completely data-driven, overcoming the influence of subjective factors caused by artificially given weight coefficients.

[0103] Then, the time weight coefficients and thermal average index of the four time periods are comprehensively considered to obtain the spatiotemporal weighted population vitality index:

[0104]

[0105] Among them, VI represents the time-weighted population vitality index, represents the average thermal value of a region during period j, a j Represents the time weight index, and j represents different time periods.

[0106] S400, determining an urban building area vitality index 3 according to the building patches and the spatiotemporal weighted population vitality index.

[0107] Specifically, in the embodiment, the coherence value γ of the binarized building detection result obtained in step S100 is b , coupled with the spatiotemporal weighted population vitality index VI calculated in step S300, the urban vitality index of the building area is obtained:

[0108] VIb=VI×γ b ,(γ b ∈{0,1})

[0109] In the calculation formula, VIb represents the vitality index of the building area.

[0110] S500: Determine the potential growth area of ​​the city by coupling the urban vitality index of the building area and the spatial pattern index.

[0111] Specifically in the embodiment, Figure 3 As shown, the embodiment further couples the building quality PD value obtained in step S200 with the building area vitality index obtained in step S400. More specifically, after coupling in the embodiment, four branch selection results are generated:

[0112] The first type is high vitality and low PD value, which means that the population activity intensity in this area is high, the building scale is large and the density is high, and it is a well-built area.

[0113] The second type is high vitality and high PD value, which means that the population activity intensity in this area is high, but the building scale and density are small. It belongs to the area where the urban building infrastructure construction is imperfect, which drags down the social and economic development. This area should adopt a redevelopment strategy of strengthening infrastructure construction investment to match the high-intensity social and economic activities.

[0114] The third type is low vitality and low PD value, which means that the population activity intensity in this area is small, but the building scale is large and the density is high. It belongs to the area with complete urban building infrastructure construction, but low population activity intensity, resulting in waste of urban infrastructure resources. This area should adopt a redevelopment strategy of strengthening policy guidance, improving the level of social and economic activities in the region, and improving the utilization rate of facilities.

[0115] The fourth type is the area with low vitality and high PD value, which means that the population activity intensity in this area is small and the urban construction is insufficient. Most of this area is undeveloped wasteland, which should be reasonably planned to make full use of the land resources in the area.

[0116] In some optional embodiments, the method for identifying urban potential growth areas may further include a verification step, which may include steps S600-S800:

[0117] S600: Acquire a street view image.

[0118] Specifically in the embodiment, a street view image is first constructed, and based on the different areas identified in steps S200 and S400, sample points are selected, and the street view image of each sample point is obtained through the API port of the map resource; the data of each point is obtained in 4 scenes, and the field of view of each scene is 90°. After the construction is completed, geo-reference is required to establish a connection between the coordinate information of the street view sampling point and the acquired street view image, so that the street view image has geographic location information.

[0119] S700: Generate a city perception score according to the street view image.

[0120] Specifically in the embodiment, the social perception of citizens on street view images can be obtained, and the city perception scores of citizens for each image can be collected. Citizens will evaluate the urban landscape they see through three dimensions (pleasure level, development level and suitability for redevelopment). The degree of pleasure includes the perception of the comfort and relaxation level of the area and the willingness to stay and move in the area. The degree of development refers to the perception of the degree of development of the area. The suitability for redevelopment refers to the perception of the urgency of redevelopment in the area. The evaluation score is based on a percentage system, with 50 points being neutral, 50 points or more representing a positive attitude of the volunteer towards the dimension, and 50 points or less representing a negative attitude.

[0121] S800: performing correlation calculations on the city perception score, the building area urban vitality index, and the spatial pattern index in pairs, and verifying the potential growth area of ​​the city according to the correlation calculation results.

[0122] Specifically in the embodiment, the Pearson correlation method can be used to perform correlation calculations between the urban vitality index of the built-up area, the building space pattern index, and the urban perception score based on Baidu Street View, so as to verify the potential growth areas of the city.

[0123] Combined with the drawings in the specification, the complete implementation process of the embodiment of the technical solution of the present application is described as follows:

[0124] like Figure 4 FIG. 4 shows the result of the building patch extraction module in step S100 of the embodiment. Figure 4In the figure, the black area represents water bodies and non-built-up areas, and the white area represents urban built-up areas.

[0125] like Figure 5 (a) to Figure 5 (d) shows the result of extracting the spatial pattern of the building area in step S200 of the embodiment. Figure 5 (a) to Figure 5 In (d), the larger the PD value, the closer it is to red, and the smaller the PD value, the closer it is to blue. The larger the PD value, the more unused land. For example, Figure 5 As shown in (a), the PD value of the area is high due to the large distance between buildings and low building density. Figure 5 As shown in (b), there are few buildings in the region, the proportion of building area to the total area is small, the buildings are scattered, and the unused land area is large, resulting in a high regional PD value; Figure 5 As shown in (c), the area has dense buildings, less unused land, and low regional PD value; Figure 5 As shown in (d), the average size of a single building in the area is large, there are many buildings, and the regional PD value is low.

[0126] like Figure 6 (a) to Figure 6 (d) shows the result of calculating the spatiotemporal weighted population vitality in step S300 of the embodiment. Figure 6 (a) and Figure 6 (b) It can be seen that within the main urban area, the population activity intensity at 8 am in most areas is lower than that at 3 pm, reflecting the tidal effect of urban population activities. The spatiotemporal weighted population vitality method takes into account the problem that the population activity intensity in the region fluctuates over time. Some new hot spots appear in the detection results, which are hot spots caused by thermal fluctuations due to regional functional characteristics, such as Figure 6 (d). However, these hot spots are not detected in the average thermal method, e.g. Figure 6 (C) shows the effectiveness of the embodiment method.

[0127] like Figure 7 As shown, the result of extracting urban vitality of building area in step S400 of the embodiment is shown. Figure 7 The building area vitality index reflects that the data of roads, water bodies, parks and green spaces in the urban area are effectively attenuated, and only the population vitality of the building area is retained, so as to accurately reflect the population vitality characteristics of the building area. Three typical sample areas are selected here for illustration: In areas with high development degree in the central urban area and high degree of mixing of buildings and green spaces, the advantage of high-resolution spatiotemporal vitality of the building area is mainly reflected in the precise control of the building area.

[0128] exist Figure 7For example, sample area A is a core business district in a certain urban area, with a shopping center as its center. Area A1 is a large urban green space; area A2 is the largest shopping center in the city, with a high concentration of population; area A3 is a high-end community with low building density and high green space coverage.

[0129] exist Figure 7 For example, sample area B is a road bridge. Satellite images show that the area is congested and has a lot of traffic. Congestion has a negative impact on urban development. In the detection of building area vitality, the congested section is removed together with some green spaces and roads to avoid misjudging the congested section as a high-vitality area in the city.

[0130] Sample area C is a park and a village in the northeast corner of the urban area. Area C1 is the park, which is a continuous urban park green space. Therefore, it appears as a continuous non-building area in the vitality monitoring of the built-up area. Area C2 is a village with an industrial park, but the building density, development level and vitality are low. The urban facade landscape is dilapidated and most of the buildings are small buildings that are not included in the plan. There is a large amount of undeveloped land. Therefore, in the vitality monitoring of the built-up area, it appears as a mixture of fragmented low-vitality building areas and non-building areas.

[0131] like Figure 8 The figure shows the result of the city perception ground verification in step S600 of the embodiment. Figure 8 It can be seen that in the method of using the coupling of urban vitality and PD value in the built-up area to detect the potential growth area of ​​the city, the detected potential growth areas of the city are high PD value low vitality areas and low PD value low vitality areas, that is, Figure 8 The red and orange areas in the figure. In contrast, the areas with low PD values ​​and high vitality, i.e. green areas, are well developed areas.

[0132] (Ⅰ) Village A is a typical area with high PD value and low vitality value. Figure 8 The red area is shown in the figure. The village is located on the edge of the main urban area. The building density is low, the average scale is small, and the construction is relatively random. It is a typical urban village area. It can be redeveloped through replanning and secondary development.

[0133] (Ⅱ) is a typical industrial area with low PD value and low vitality value. Figure 8 The orange-yellow area is shown in the figure. The hardware resources in this area are not fully utilized, resulting in a waste of resources. Compared with the construction of new urban hardware facilities, increasing the software resource investment in this area and improving the hardware utilization rate in the area can improve economic efficiency.

[0134] (III) Main roads, shown as green areas in Figure 8. This area is well planned, with high building density, large scale, good continuity, and full use of land, which has a good economic vitality.

[0135] (IV) Citizen Service Centers have high vitality. Figure 8 The green area is shown in the figure. This building provides most of the government services needed by citizens and is one of the most active areas in the city, with high vitality.

[0136] (V) Community B has the characteristics of high vitality and high PD value, and is also a potential development area. Figure 8 The blue area is shown in the figure. This community is a major rental housing concentration area, lacking large infrastructure such as schools. It is an area where infrastructure construction lags behind the needs of the population. In the urban redevelopment plan, the quality of regional urban construction and the quality of life of residents can be improved by building new infrastructure.

[0137] On the other hand, the technical solution of the present application also provides a system for identifying potential urban growth areas, the system comprising:

[0138] A building patch acquisition unit, used to acquire a number of radar images of urban buildings, and extract the building patches of the urban buildings according to the radar images;

[0139] A building data processing unit, used for determining the spatial pattern index of the urban buildings according to the patch density of the building patches;

[0140] A population data processing unit, used for acquiring thermal data of population activities, and determining a spatiotemporal weighted population vitality index according to the thermal data and a time weight coefficient;

[0141] The building area urban vitality index extraction unit is used to determine the building area urban vitality index according to the interference measurement results between the radar images and the spatiotemporal weighted population vitality index.

[0142] Potential growth area identification unit: Determine the potential growth area of ​​the city by coupling the urban vitality index of the building area and the spatial pattern index.

[0143] On the other hand, the technical solution of the present application also provides a device for identifying potential growth areas in a city; the device comprises:

[0144] At least one processor; at least one memory for storing at least one program; when the at least one program is executed by the at least one processor, the at least one processor runs a method for identifying potential growth areas in a city as described in the first aspect.

[0145] An embodiment of the present invention further provides a storage medium storing a corresponding execution program, which is executed by a processor to implement a method for identifying potential growth areas in a city in the first aspect.

[0146] From the above specific implementation process, it can be concluded that the technical solution provided by the present invention has the following advantages or strengths compared with the prior art:

[0147] ① High resolution: The spatial scale of detection can reach 10 meters, which can reflect the details of urban construction at the micro scale.

[0148] ② High timeliness: Baidu’s population thermal big data is collected in real time and processed in real time.

[0149] ③ High efficiency: Based on geographic positioning big data and remote sensing big data, the cost of data acquisition is low, which can save a lot of government funds; at the same time, it avoids the problem of traditional questionnaire surveys with too small data volume and insufficient statistical significance.

[0150] ④ High accuracy: It reduces the error caused by the "tidal effect" of crowd activities and achieves high-precision measurement of population activity intensity; it combines the physical characteristics of the city with the socio-economic characteristics to more comprehensively reflect the current status of urban development.

[0151] ⑤ High security: Demographic statistics in the form of big data can avoid large-scale contact between people.

[0152] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0153] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features can be integrated into a single physical device and / or software module, or one or more functions and / or features can be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0154] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, which can be embodied in any computer-readable medium for use by an instruction execution system, apparatus or device (such as a computer-based system, a system including a processor or other system that can fetch instructions from an instruction execution system, apparatus or device and execute instructions), or used in combination with these instruction execution systems, apparatuses or devices.

[0155] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0156] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0157] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for identifying potential urban growth areas, characterized in that: The following steps are involved: Acquire a number of radar images of urban buildings, and extract building patches of the urban buildings according to the radar images; Determining the spatial pattern index of the urban buildings according to the patch density of the building patches; Acquiring thermal data of population activities, and determining a spatiotemporal weighted population vitality index based on the thermal data and a time weight coefficient; Determining the urban vitality index of the building area according to the interferometric measurement results between the radar images and the spatiotemporal weighted population vitality index; Determine the potential growth area of ​​the city by coupling the urban vitality index of the building area and the spatial pattern index; wherein the step of determining the spatial pattern index of the urban building according to the patch density of the building patch includes: Divide the building patches into zones, and obtain the patch density according to the ratio of the number of the building patches in each zone to the floor area of ​​the zone; The step of obtaining the thermal data of population activities and determining the spatiotemporal weighted population vitality index according to the thermal data and the time weight coefficient comprises: Get a heat map of population activity intensity; Divide the population activity intensity heat map into grids, and divide it into preset time periods to obtain the time period heat average value in the grids; The time weight coefficient is calculated according to the ratio of the time period heat value to the total time period heat value, and the spatiotemporal weighted population vitality index is calculated according to the time period heat average value and the time weight coefficient; The step of determining the urban vitality index of the building area according to the interferometric measurement results between the radar images and the spatiotemporal weighted population vitality index comprises: The coherence value of the binarized interference measurement result is coupled with the spatiotemporal weighted population vitality index to obtain the urban vitality index of the building area.

2. A method for identifying urban potential growth areas according to claim 1, characterized in that: The method further comprises the following steps: Get street view imagery; generating a city perception score based on the street view image; The city perception score, the building area urban vitality index and the spatial pattern index are correlated and calculated, and the potential growth area of ​​the city is verified based on the relevant calculation results.

3. The method for identifying urban potential growth areas according to claim 1, characterized in that: The step of acquiring a plurality of radar images of urban buildings and extracting the building patches of the urban buildings according to the radar images comprises: Removing noise from the radar image by adaptive filtering; Perform phase unwrapping on the denoised radar image and remove the flat ground effect; Geo-reference the radar image after removing the flat ground effect; The building patch map is obtained by interferometric measurement based on the geo-referenced radar image.

4. The method for identifying urban potential growth areas according to claim 1, characterized in that: The step of obtaining the building patch map by interferometric measurement based on the georeferenced radar image includes: According to the radar images acquired within a preset time period, at least two radar images are compared to obtain surface changes; The interferometric measurement result is obtained according to the degree of the surface change.

5. A method for identifying urban potential growth areas according to claim 4, characterized in that: Before the step of obtaining the interferometric measurement result according to the degree of the surface change, the method further comprises the following steps: Acquiring a number of radar images according to a preset time interval; Acquire precise orbit data of image acquisition, and perform orbit deviation correction on the radar image according to the precise orbit data; The elevation data is obtained from the radar image after the orbit deviation correction, and the elevation data is the benchmark reference data for interferometric measurement.

6. A system for identifying urban potential growth areas, characterized in that: The system comprises: A building patch acquisition unit, used to acquire a number of radar images of urban buildings, and extract the building patches of the urban buildings according to the radar images; A building data processing unit, used for determining the spatial pattern index of the urban buildings according to the patch density of the building patches; A population data processing unit, used for acquiring thermal data of population activities, and determining a spatiotemporal weighted population vitality index according to the thermal data and a time weight coefficient; A building area urban vitality index extraction unit is used to determine the building area urban vitality index according to the building patches of urban buildings and the spatiotemporal weighted population vitality index; Potential growth area identification unit: determining the potential growth area of ​​the city by coupling the urban vitality index of the building area and the spatial pattern index; Wherein, the building data processing unit is specifically used for: Divide the building patches into zones, and obtain the patch density according to the ratio of the number of the building patches in each zone to the floor area of ​​the zone; The population data processing unit is specifically used for: Get a heat map of population activity intensity; Divide the population activity intensity heat map into grids, and divide it into preset time periods to obtain the time period heat average value in the grids; The time weight coefficient is calculated according to the ratio of the time period heat value to the total time period heat value, and the spatiotemporal weighted population vitality index is calculated according to the time period heat average value and the time weight coefficient; The building area urban vitality index extraction unit is specifically used for: The coherence value of the binarized interference measurement result is coupled with the spatiotemporal weighted population vitality index to obtain the urban vitality index of the building area.

7. A device for identifying potential urban growth areas, characterized in that: include: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor runs a method for identifying potential growth areas in a city as described in any one of claims 1-5.

8. A storage medium storing a program executable by a processor, characterized in that: The processor-executable program is used to run a method for identifying potential growth areas in a city as described in any one of claims 1-5 when executed by the processor.

Images