CN111260521B - A method, device, intelligent terminal and storage medium for acquiring city boundaries - Google Patents

Abstract

The invention discloses a city boundary acquisition method, a city boundary acquisition device, an intelligent terminal and a storage medium. The method comprises the following steps: acquiring a road cross point set according to road network data, constructing a quadtree for road cross points in the point set, and storing one road cross point for each leaf node of the quadtree; calculating a density value according to the geometric information of the rectangle corresponding to the leaf node, and classifying the rectangle corresponding to the leaf node according to the density value; and carrying out non-transregional fusion Dissolve processing on the classified rectangles according to the topological relation of photographic adjacency to obtain city boundaries. The invention improves the spatial quadtree index processing method for spatial information of urban big data and clusters according to the nonlinear density characteristics of the type of data. Compared with the traditional urban data clustering method, the method does not need to set parameters in advance, and is high in speed and high in expandability.

Description

A method, device, intelligent terminal and storage medium for acquiring city boundaries

technical field

The present invention relates to the technical field of spatial data analysis, in particular to a method, device, intelligent terminal and storage medium for acquiring city boundaries.

Background technique

Urban computing refers to the use of computer technology to mine valuable information from urban multi-source heterogeneous big data and explore the scientific laws inherent in the city, so as to better serve human life and promote the efficient and healthy operation of the city.

A city represents an area where human living is highly concentrated. An accurate description of the city boundary can help the government monitor the disorderly expansion of the urban construction area and coordinate the relationship between the planning of urban residents' travel and the allocation of public facilities, contributing to the sustainable development of the city. Therefore, it is an important part of urban calculation.

Currently, the boundaries of cities are determined by local authorities or governments, and this top-down approach may differ from real human-occupied areas. In addition, some technologies define the boundaries of cities through methods such as information entropy method, breaking point analysis method, and remote sensing luminous lamp interpretation. Strong, it is difficult to be accurate and objective 2. The data structure (such as triangular surface) relied on to define the scope is very inefficient to construct, and the ideal result cannot be obtained when the amount of data is large.

Therefore, the prior art still needs to be improved and developed.

Contents of the invention

In view of the above deficiencies in the prior art, the purpose of the present invention is to provide a method, device, intelligent terminal and storage medium for acquiring city boundaries, aiming at solving the problems of low efficiency and strong subjectivity in the prior art for dividing the city boundaries.

The technical scheme that the present invention adopts for solving the problems of the technologies described above is as follows:

In a first aspect, an embodiment of the present invention provides a method for obtaining a city boundary, the method comprising:

Acquiring a road intersection set according to the road network data, constructing a quadtree for the road intersections in the road intersection set, each leaf node of the quadtree stores one road intersection;

Calculate the density value according to the geometric information of the rectangle corresponding to each leaf node, and divide the rectangle corresponding to each leaf node into a target-type rectangle and a background-type rectangle according to the density value; the density value is the reciprocal of the area of said rectangle;

According to the adjacent topological relationship, non-cross-regional fusion processing is performed on the classified object class rectangles to obtain the city boundary.

The method for obtaining the city boundary, wherein, the construction of the quadtree, the specific construction process:

Calculating the outer envelope rectangles of all road intersections, and using the outer envelope rectangles as root nodes;

Generate a quadtree full of N in depth, and calculate the relationship between each road intersection and the leaf node rectangle, and save the rectangle with the number of points≤1 in the leaf node rectangle; the N is a natural number greater than 1 and less than 9;

For each rectangle whose number of points is greater than 1, independently generate a quadtree until the number of points in all leaf node rectangles ≤ 1, and save these rectangles; integrate all rectangles with a number of points ≤ 1, and end.

The method for obtaining the city boundary, wherein, the step calculates a density value according to the geometric information of the rectangle corresponding to the leaf node, and divides the rectangle corresponding to the leaf node into a target rectangle and a background rectangle according to the density value. Rectangle-like, specifically:

Use formula (1) to divide all rectangles into two parts: target rectangle and background rectangle

Among them, d is the segmentation threshold of the target and the background, σ _w is the difference between the density value of the target and the background, w ₀ is the proportion of the target points in the image, σ ₀ is the variance of the target points in the image proportion, and w ₁ is the proportion of the background points in the image , σ ₁ is the variance of the proportion of background points in the image; extract all the rectangular information in the target class.

The method for obtaining the city boundary, wherein, the step performs non-cross-region fusion processing on the classified target rectangles according to the adjacent topological relationship to obtain the city boundary, wherein the non-cross-region fusion processing includes the steps of:

Starting from any rectangle in the classified target class rectangles, filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles into a preset set;

Traverse each adjacent rectangle, repeat the steps to filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles in the preset collection until there are no new adjacent rectangles;

Eliminate common sides of all rectangles in the set, generate city boundaries, end.

The method for obtaining city boundaries, wherein the N is 7.

In a second aspect, a device for acquiring city boundaries, the device includes:

A quadtree construction unit, configured to obtain a road intersection set according to road network data, and construct a quadtree for road intersections in the road intersection set, each leaf node of the quadtree stores one road intersection;

The rectangle classification unit calculates a density value according to the geometric information of the rectangle corresponding to each leaf node, and divides the rectangle corresponding to each leaf node into a target class and a background class according to the density value; the density The value is the reciprocal of the area of the rectangle;

The processing unit is configured to perform non-cross-region fusion processing on the classified object class rectangles according to the adjacent topological relationship to obtain the city boundary.

The device, wherein the quadtree construction unit includes:

a calculation subunit, configured to calculate the outer envelope rectangles of all road intersections, and use the outer envelope rectangles as the root node;

Generate subunits, generate a full quadtree with a depth of N, and calculate the relationship between each road intersection and the leaf node rectangle, and save the rectangle with the number of points in the leaf node rectangle ≤ 1; the N is a natural number greater than 1 and less than 9 ;

The storage sub-unit is used to independently generate a quadtree for each rectangle whose number of points is greater than 1, until the number of points in all leaf node rectangles is ≤1, and save these rectangles; integrate all rectangles with a number of points ≤1, and end.

The device, wherein the processing unit includes:

The self-screening unit is used to start from any rectangle in the classified target class rectangles, filter out the adjacent rectangles with the rectangle, and store the adjacent rectangles in the preset set;

The traversing subunit is used to traverse each adjacent rectangle, repeat the steps to filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles in the preset collection until there are no new adjacent rectangles;

Eliminate self-units for eliminating common sides of all rectangles in the set, generating city boundaries, end.

In the third aspect, the embodiment of the present invention also provides an intelligent terminal, including a memory, and one or more programs, wherein one or more programs are stored in the memory, and configured to be executed by one or more processors The one or more programs include methods for performing the methods described above.

In a fourth aspect, the embodiment of the present invention further provides a non-transitory computer-readable storage medium, and when instructions in the storage medium are executed by a processor of the electronic device, the electronic device can execute the method as described above.

Beneficial effects of the present invention: the present invention quickly clusters road intersections across the country and generates urban boundary range methods by establishing a spatial quadtree, which can accurately describe and can help the government monitor whether the urban construction area is expanding out of order and coordinate the planning of the city The relationship between residents' travel and the configuration of public facilities is of great significance to the sustainable development of cities.

Description of drawings

Fig. 1 is a flowchart of a preferred embodiment of the method for acquiring city boundaries provided by the present invention.

FIG. 2 is a flow chart of step S100 of a preferred embodiment of the method for acquiring city boundaries provided by the present invention.

Fig. 3 is a functional schematic diagram of the smart terminal provided by the present invention.

Detailed ways

In order to make the object, technical solution and advantages of the present invention more clear and definite, the present invention will be further described in detail below with reference to the accompanying drawings and examples. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

Due to the division and acquisition of city boundaries in the prior art, the following methods are often used:

The first is the planning and setting of relevant departments. Using this method of planning and setting is highly subjective, and the obtained city boundaries are different from the actual city boundaries. The second is to rely on data information, through methods such as information entropy method, breakpoint analysis method, and remote sensing luminous lamp interpretation. These methods rely on very low data structure construction efficiency when defining the scope. desired result.

In order to solve the above technical problems, in the embodiment of the present invention, when it is necessary to define the boundary of a certain city, the national road network data or the road network data of the province where the city is located can be obtained first. According to the above road network data, the road intersection points (road intersection points) are analyzed, the road intersection points are brought together to form a point set, and then a full quadtree is constructed for the road intersection points, so that each of the quadtrees A leaf node only stores a corresponding road intersection point. Calculate the area of the rectangle corresponding to the leaf node, so as to calculate the point density value, and classify the corresponding rectangle according to the point density value. The classification can be divided into two categories, such as target (city), background (non-city), namely The points in the point set can be divided into object class and background class according to the point density value. Perform non-cross-regional fusion Dissolve on the rectangles in the target class according to the adjacent topological relationship to obtain the city boundary.

The invention establishes a spatial quadtree, quickly clusters road intersections across the country and generates a method of urban boundaries, which can accurately describe and help the government monitor whether the urban construction area is expanding out of order and coordinate the planning of urban residents' travel and public facility configuration. The relationship between them is of great significance to the sustainable development of cities.

For example, if the user wants to define the boundary of Shenzhen, he only needs to use the road network data of the whole country or Guangdong Province to obtain the road intersection point set, and then follow the above steps to generate the boundaries of all cities in Guangdong or the whole country (including Shenzhen) . Since the city boundary represents the relatively concentrated area of human activities, in order to determine the boundary of a city, it is necessary to select a larger area to define it. Otherwise, if only the road intersections in Shenzhen are used, the result will not be the city boundary of Shenzhen, but the boundaries of various districts in Shenzhen.

Various non-limiting embodiments of the present invention will be described in detail below in conjunction with the accompanying drawings.

exemplary method

Referring to Fig. 1, the present embodiment provides a method for acquiring city boundaries, comprising the following steps:

Step 100: Obtain a road intersection set according to the road network data, construct a quadtree for the road intersections in the road intersection set, and store one road intersection in each leaf node of the quadtree.

Specifically, road network data is mainly road network data, and can also be combined with railway network data. The above-mentioned road network data can be collected through big data. The specific acquisition of road network data can be any of the existing technologies. method, as long as it can meet the needs. The road intersections are analyzed from the known road network data, each intersection in the road network data is recorded as a point, and all road intersection points obtained form a point set. Construct a quadtree for all points in the point set.

In this embodiment, the road intersection set in the road network is obtained because the density of road intersections reflects the construction of urban infrastructure, and the actual spatial development of urban land can be effectively determined by clustering them.

Referring to Fig. 2, in step S100, the construction step of quadtree is:

S110. Calculate the outer envelope rectangles of all road intersections, and use the outer envelope rectangles as a root node;

S120. Generate a full quadtree with a depth of N, and calculate the relationship between each road intersection and the leaf node rectangle, and save the rectangle with the number of points in the leaf node rectangle≤1; the N is a natural number greater than 1 and less than 9;

S130. For each rectangle with a number of points greater than 1, independently generate a quadtree until the number of points in all leaf node rectangles is ≤1, and save these rectangles; integrate all rectangles with a number of points ≤1, and end.

Specifically, usually the full quadtree structure is often used in geospatial division to visualize spatial information of different scales (such as raster slices), but the disadvantages of this method are obvious. Generally speaking, the map level ranges from the global scale to the street scale as many as 15-20 layers. If it is constructed in a full quadtree, the number of rectangles required to reach the sixteenth layer is as high as 5 billion, and the space occupied is as high as several terabytes. , often beyond the processing capabilities of the computer's memory. The present invention adopts the quadtree construction method of first breadth and then depth, specifically, first generates a full quadtree of N layers (such as 7-9 layers) by a breadth-first method, and stores it in the last layer of child nodes Spatial entity information, and then perform depth-first recursive recursion on the area containing more elements in the child nodes until there is only one spatial element. In order to avoid the imbalance of the quadtree structure and the waste of storage space, the geographic entity information is stored in the smallest rectangular node that completely contains it, not in its parent node, and each geographic entity is only stored once in the tree. Avoid wasting storage space.

In this embodiment, the constructed quadtree is a full quadtree with a depth of 7, wherein the number of full quadtree nodes in the 7th layer is 16384, and subsequent steps can be carried out smoothly on the basis of this layer, if four The fork tree has a depth of 9 layers, and the required memory is about 32G.

S200. Calculate a density value according to the geometric information of the rectangle corresponding to each leaf node, and divide the rectangle corresponding to each leaf node into a target-type rectangle and a background-type rectangle according to the density value; the density The value is the reciprocal of the area of the rectangle in question.

Step S200 is specifically, regard each rectangle as a pixel, calculate the density value (1/rectangle area) corresponding to each point as the pixel value to calculate the threshold, and the threshold is the maximum between-class variance (common

The result calculated by formula 1). Formula (1) is as follows:

Among them, d is the segmentation threshold of the target and the background, σ _w is the difference between the density value of the target and the background, w ₀ is the proportion of the target points in the image, σ ₀ is the variance of the target points in the image proportion, and w ₁ is the proportion of the background points in the image , σ ₁ is the variance of the proportion of background points in the image;

When the pixel value is less than the pixel threshold calculated by the formula (1), it means that the rectangle is the target, and when the pixel value is greater than the pixel threshold calculated by the formula (1), it means that the rectangle is the background, that is, by using the above method to extract Information about all rectangles in the foreground class. Because it is a two-class classification, after all the rectangle information of the foreground class, the background rectangle information can also be obtained.

S300. Perform non-cross-region fusion processing on the classified rectangles according to adjacent topological relationships to obtain city boundaries.

Specifically, non-cross-region fusion Dissolve processing is performed on the classified rectangles according to the topological relationship, where Dissolve processing refers to the fusion of adjacent (co-edge) target rectangles. The process is as follows: in the foreground class rectangle, start from any rectangle to find The rectangles adjacent to this rectangle are stored in the specified collection, each adjacent rectangle is traversed, and the above steps are repeated until there are no new adjacent rectangles. Eliminate the common sides of all rectangles in the set to form a new polygon, and the resulting new polygon is the city boundary.

Based on the above embodiments, the present invention also provides a smart terminal, the functional block diagram of which can be shown in FIG. 3 . The intelligent terminal includes a processor, a memory, a network interface, a display screen and a temperature sensor connected through a system bus. Wherein, the processor of the smart terminal is used to provide calculation and control capabilities. The memory of the smart terminal includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the smart terminal is used to communicate with external terminals through a network connection. When the computer program is executed by the processor, a method for acquiring city boundaries is realized. The display screen of the smart terminal may be a liquid crystal display screen or an electronic ink display screen, and the temperature sensor of the smart terminal is pre-set inside the smart terminal to detect the current operating temperature of the internal device.

Those skilled in the art can understand that the functional block diagram shown in Figure 3 is only a block diagram of a part of the structure related to the solution of the present invention, and does not constitute a limitation on the intelligent terminal to which the solution of the present invention is applied. The specific intelligent terminal More or fewer components than shown in the figures may be included, or certain components may be combined, or have a different arrangement of components.

In one embodiment, an intelligent terminal is provided, including a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be executed by one or more processors. One or more programs contain instructions for:

Acquiring a road intersection set according to the road network data, constructing a quadtree for the road intersections in the road intersection set, each leaf node of the quadtree stores one road intersection;

calculating a density value according to the geometric information of the rectangle corresponding to each leaf node, and classifying the rectangle corresponding to the leaf node according to the density value; the density value is the reciprocal of the area of the rectangle;

The classified rectangles are processed by non-cross-regional fusion according to the adjacent topological relationship to obtain the city boundary.

Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be implemented through computer programs to instruct related hardware, and the computer programs can be stored in a non-volatile computer-readable memory In the medium, when the computer program is executed, it may include the processes of the embodiments of the above-mentioned methods. Wherein, any reference to memory, storage, database or other media used in the various embodiments provided by the present invention may include non-volatile and/or volatile memory. Nonvolatile memory can include read only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Chain Synchlink DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

To sum up, the present invention discloses a method, a device, an intelligent terminal and a storage medium for acquiring a city boundary. The method includes: obtaining a road intersection set according to road network data, constructing a quadtree for the road intersections in the point set, each leaf node of the quadtree stores one road intersection; according to the Calculate the density value of the geometric information of the rectangle corresponding to the leaf node, and classify the rectangle corresponding to the leaf node according to the density value; the density value is the reciprocal of the area of the rectangle; the classified rectangle according to The adjacent topological relationship is processed by non-cross-region fusion Dissolve to obtain the city boundary. The invention improves the spatial quadtree index processing method for urban big data spatial information, and performs clustering according to the nonlinear density feature of this type of data. Compared with the traditional clustering method of urban data, this method does not need to set parameters in advance, and is fast and scalable, which can effectively help to mine the nonlinear spatial laws of urbanization or human urban activities.

It should be understood that the application of the present invention is not limited to the above examples, and those skilled in the art can make improvements or transformations according to the above descriptions, and all these improvements and transformations should belong to the protection scope of the appended claims of the present invention.

Claims (7)

1. A method for acquiring city boundaries, characterized in that said method comprises steps: Acquiring a road intersection set according to the road network data, constructing a quadtree for the road intersections in the road intersection set, each leaf node of the quadtree stores one road intersection; Calculate the density value according to the geometric information of the rectangle corresponding to each leaf node, and divide the rectangle corresponding to each leaf node into a target-type rectangle and a background-type rectangle according to the density value; the density value is the reciprocal of the area of said rectangle; Perform non-cross-regional fusion processing on the classified object class rectangles according to the adjacent topological relationship to obtain the city boundary; The step calculates a density value according to the geometric information of the rectangle corresponding to the leaf node, and divides the rectangle corresponding to the leaf node into a target-type rectangle and a background-type rectangle according to the density value, specifically: Use formula (1) to divide all rectangles into two parts: target rectangle and background rectangle

Among them, d is the segmentation threshold of the target and the background, σ _w is the difference between the target and background density values, w ₀ is the proportion of the target points in the image, σ ₀ is the variance of the target points in the image proportion, w ₁ is the background point in the image proportion , σ ₁ is the variance of the proportion of background points in the image; extract all the rectangle information in the target class; Said step carries out non-cross-regional fusion processing to the classified object class rectangle according to the adjacent topological relationship, and obtains the city boundary, and said non-cross-regional fusion processing comprises steps: Starting from any rectangle in the classified target class rectangles, filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles into a preset set; Traverse each adjacent rectangle, repeat the steps to filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles in the preset collection until there are no new adjacent rectangles; Eliminate common sides of all rectangles in the set, generate city boundaries, end. 2. The city boundary acquisition method according to claim 1, characterized in that, said construction quadtree, the specific construction steps are: Calculating the outer envelope rectangles of all road intersections, and using the outer envelope rectangles as root nodes; Generate a quadtree full of N in depth, and calculate the relationship between each road intersection and the leaf node rectangle, and save the rectangle with the number of points≤1 in the leaf node rectangle; the N is a natural number greater than 1 and less than 9; For each rectangle whose number of points is greater than 1, independently generate a quadtree until the number of points in all leaf node rectangles ≤ 1, and save these rectangles; integrate all rectangles with a number of points ≤ 1, and end. 3. The method for acquiring city boundaries according to claim 2, wherein said N is 7. 4. A city boundary acquisition device, characterized in that the device comprises: A quadtree construction unit, configured to obtain a road intersection set according to road network data, and construct a quadtree for road intersections in the road intersection set, each leaf node of the quadtree stores one road intersection; The rectangle classification unit calculates a density value according to the geometric information of the rectangle corresponding to each leaf node, and divides the rectangle corresponding to the leaf node into a target-type rectangle and a background-type rectangle according to the density value; the density The value is the reciprocal of the area of the rectangle; The processing unit is used to perform non-cross-regional fusion processing on the classified target class rectangles according to the adjacent topological relationship to obtain the city boundary; The rectangle classification unit includes: using formula (1) to divide all rectangles into two parts: object class rectangle and background class rectangle

Among them, d is the segmentation threshold of the target and the background, σ _w is the difference between the target and background density values, w ₀ is the proportion of the target points in the image, σ ₀ is the variance of the target points in the image proportion, w ₁ is the background point in the image proportion , σ ₁ is the variance of the proportion of background points in the image; extract all the rectangle information in the target class; The processing unit includes: The self-screening unit is used to start from any rectangle in the classified target class rectangles, filter out the adjacent rectangles with the rectangle, and store the adjacent rectangles in the preset set; The traversing subunit is used to traverse each adjacent rectangle, repeat the steps to filter out the adjacent rectangles to the rectangle, and store the adjacent rectangles in the preset collection until there are no new adjacent rectangles; The elimination subunit is used to eliminate the common sides of all the rectangles in the set to generate the city boundary, and end. 5. The device according to claim 4, wherein the quadtree construction unit comprises: A calculation subunit is used to calculate the outer envelope rectangles of all road intersections, and use the outer envelope rectangles as the root node; Generate subunits, generate a full quadtree with a depth of N, and calculate the relationship between each road intersection and the leaf node rectangle, and save the rectangle with the number of points in the leaf node rectangle ≤ 1; the N is a natural number greater than 1 and less than 9 ; The storage sub-unit is used to independently generate a quadtree for each rectangle whose number of points is greater than 1, until the number of points in all leaf node rectangles is ≤1, and save these rectangles; integrate all rectangles with a number of points ≤1, and end. 6. An intelligent terminal, characterized in that it includes a memory, and one or more programs, wherein one or more programs are stored in the memory, and are configured to be executed by one or more processors. More than one program is included for performing the method according to any one of claims 1-3. 7. A storage medium, wherein when the instructions in the storage medium are executed by a processor of the electronic device, the electronic device is enabled to execute the method according to any one of claims 1-3.

Images