CN113724279B - System, method, equipment and storage medium for automatically dividing traffic cells into road networks - Google Patents
System, method, equipment and storage medium for automatically dividing traffic cells into road networks Download PDFInfo
- Publication number
- CN113724279B CN113724279B CN202111279227.0A CN202111279227A CN113724279B CN 113724279 B CN113724279 B CN 113724279B CN 202111279227 A CN202111279227 A CN 202111279227A CN 113724279 B CN113724279 B CN 113724279B
- Authority
- CN
- China
- Prior art keywords
- formula
- traffic
- pixel
- image
- longitude
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/187—Segmentation; Edge detection involving region growing; involving region merging; involving connected component labelling
Abstract
The application discloses a system, a method, equipment and a storage medium for automatically dividing traffic cells in a road network, and belongs to the technical field of intelligent traffic. The method solves the problems that the existing technology for automatically dividing the traffic cells has the defects that the boundaries of the divided traffic cells are far from the real roads, excessive input data are required to be provided, and the technology is difficult to apply to the actual model building process. The method comprises the following steps: the method comprises the steps of road network buffer zone creation, coordinate information recording, buffer zone central axis skeleton extraction, topological network generation, minimum basic ring search, traffic cell division and traffic cell combination. The method and the device form a new topological network by extracting the road skeleton, divide the districts based on the urban basic map layer, are high in calculation speed, simple in input data, good in generalization capability, capable of quickly dividing urban traffic districts and low in human input. The method integrates the road network framework extraction, framework-to-topology, minimum basic loop search and area space analysis algorithms, and provides a set of complete system and method.
Description
Technical Field
The present invention relates to a system, a method, a device and a storage medium for automatically dividing traffic cells, and more particularly, to a system, a method, a device and a storage medium for automatically dividing traffic cells in a road network based on an image technology, and belongs to the technical field of intelligent traffic.
Background
The traffic model technology is an important theoretical support basis of the traffic industry, and can provide important data support for planning and construction of cities. The division of the traffic cells is an important part in the construction process of the traffic model, whether the division of the traffic cells is reasonable or not is directly related to the accuracy of the built traffic model, then the division of the traffic cells is a relatively complicated process, a large amount of labor work is consumed, and in order to simplify the complexity of the division of the traffic cells, a plurality of methods for automatically dividing the traffic cells are proposed by engineers. One part of the technology is based on urban road network and land use property, the other part of the technology is based on massive urban traffic data, and the cell division is determined from the aspect of statistical analysis, the former is basically based on the partition division performed by the Delaunay triangulation network, the difference between the cell boundary and the real road is large, the parameter significance in the division process is not obvious and is difficult to be understood by a user, and the latter has high requirement on the requirement of input data and higher use cost.
The two closest schemes exist in the prior art, namely, a traffic road network based on a Voronoi diagram automatically divides traffic cells; the second is automatic division of urban road network traffic cells based on a spatial statistical analysis method.
(1) Voronoi diagram-based traffic road network automatic traffic district division
A Voronoi diagram, also called Thiessen polygon or Dirichlet diagram, is composed of a set of continuous polygons made up of perpendicular bisectors connecting two adjacent point lines. The method comprises the steps of extracting all road nodes, creating a Delaunay triangulation network according to a point set, then establishing a Voronoi polygon of a dual graph to form an initial traffic cell, then taking water system greenbelts into consideration, and carrying out merging and superposition analysis according to an area threshold value to generate a final traffic cell division result.
The main limitations of this approach are represented in the following areas: urban road classes are not considered because the primary road network can only become the boundary of a traffic cell and secondary road networks such as branches etc. should become intra-cell roads.
(2) Urban road network traffic cell automatic division based on space statistical analysis method
At present, the method is mainly based on a spatial clustering analysis method to carry out automatic division of traffic cells, and the traffic cells with similar traffic characteristics are mined through a large amount of real-time data and historical data.
The main disadvantages of the method are that: the method needs a large amount of complete traffic data, has high cost and low efficiency, and the divided traffic cell boundary is far from the real road, has high input requirement on users, is not suitable to be used as a general tool and is suitable for special research.
In summary, the main disadvantages of the existing traffic zone division are as follows:
(1) urban road grades are not considered;
(2) a large amount of complete traffic data is needed, the cost is high, the efficiency is low, and the boundary of the divided traffic cell is far away from the real road; is not suitable for being used as a general tool but is suitable for special research;
(3) the input requirements for the user are too high;
(4) the method is difficult to apply to the actual model building process, is a non-standardized tool, and is only suitable for special research.
Disclosure of Invention
In view of the above, the present application provides a system, a method, a device and a storage medium for automatically dividing a road network into traffic cells, so as to reduce labor investment cost in a traffic cell division process, improve cell division efficiency and simplify user input, and only a user is required to provide an urban road network to automatically divide the traffic cells, thereby solving the problems that the boundary of the divided traffic cells is far from a real road, excessive input data is required to be provided, and the traffic cells are difficult to be applied in an actual model building process in the existing technical scheme for automatically dividing the traffic cells, so that a standardized tool is constructed based on the technical scheme of the present application, and the standardized tool can be applied in the traffic cell division work in a large scale.
The technical scheme of the application is realized as follows:
the first scheme is as follows: a system for automatically dividing traffic cells of a road network based on image technology comprises:
the road network buffer zone creating module is used for merging the road networks of the complex roads, converting the linear vector graph into a surface domain vector graph and storing the surface domain vector graph into a binary image format;
the coordinate information recording module is used for calculating the longitude and latitude span of the unit pixel of the binary image;
the buffer area central axis skeleton extraction module extracts a main line outline of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image;
the topological network generating module is used for acquiring a topological network based on the skeleton image;
a minimum basic ring searching module which searches the minimum basic ring of the topological network by adopting a greedy algorithm;
the traffic zone division module is used for performing space cutting on a surface domain vector graph (street layer) based on the minimum basic torus layer to obtain a primary traffic zone surface layer file;
and the traffic cell merging module is used for forming a small-area traffic cell at the boundary of the street image layer after space cutting, merging the small-area traffic cell into an adjacent traffic cell and obtaining a final traffic cell surface layer file.
Scheme II: a method for automatically dividing traffic cells in a road network based on image technology comprises the following steps:
step one, the road network buffer zone is established,
merging the road networks of the complex roads, converting the linear vector graphics into surface domain vector graphics, and storing the surface domain vector graphics into a binary image format;
step two, recording the coordinate information,
calculating the longitude and latitude span of the unit pixel of the binary image;
step three, extracting the skeleton in the buffer area,
extracting a main line contour of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image;
step four, generating the topological network,
establishing a circle of 0 analysis value pixels as a protective layer based on the skeleton image, performing equivalent filling according to the analysis value of the identification unit pixels, marking the positions of nodes in the binary image, tracking the connection pixels among the nodes, recording line layer information, and restoring the obtained pixel coordinates of the topological network into longitude and latitude coordinates;
step five, searching a minimum basic ring,
searching a minimum basic ring of the topological network by adopting a greedy algorithm;
step six, dividing the traffic cell,
performing space cutting on a surface domain vector graph (a street layer) based on the minimum basic torus layer to obtain a primary traffic cell surface layer file;
step seven, merging the traffic districts,
and after space cutting, forming a small-area traffic cell at the boundary of the street map layer, and merging the small-area traffic cell into the adjacent traffic cell to obtain a final traffic cell surface file.
Further, the step one, the road network buffer area creation, specifically includes the steps of:
the road network with complex roads has N traffic lines, and the input-based road network
Creating a buffer for each link object
Converting the linear vector graph into polygonal surface field vector graph, and combiningThen, a face object is obtained
(ii) a Recording the maximum longitude of all geometric points in a surface vector graphicmax_lonMaximum latitudemax_latMinimum latitudemin_latMinimum longitude, minimum longitudemin_lonAnd then storing the area vector graphics as a binary image.
Further, in the second step, coordinate information is recorded, and the specific steps are as follows:
the obtained binary image is a matrix, the value of the element of the matrix is 0 or 1, and the minimum row index of the 1 value in the matrix is foundmin_row_index、Maximum row indexmax_row_index、Minimum column indexmin_col_index、Maximum column indexmax_ col_index，Then cutting the matrix, wherein the purpose of the cutting is to remove the peripheral zero elements of the matrix so as to correctly record the longitude and latitude spanned by the unit pixel, and the number of the row pixels of the current matrix after cutting is recorded asrow_pixel_num，The number of the column pixels iscol_pixel_num，The longitude spanned by the unit pixel in the longitude direction islng_para，The unit pixel in the latitude direction spans the latitude oflat_para，Calculating according to a formula I and a formula II, and using the obtained matrix as input data of skeleton extraction;
Further, in the third step, the extraction of the skeleton in the buffer area specifically comprises the following steps:
each element in the binary image represents a pixel, the value of the pixel is 0 or 1, the pixel with the value of 1 forms an image, and the pixel with the value of 0 is blank;
firstly, defining a pixel point of a binary imageP 1Neighborhood in eight directions ofNorth direction isP 2In the northeast of the yearP 3In the east directionP 4In the east-south direction isP 5In the south directionP 6In the southwest direction ofP 7In the western directionP 8In the northwest direction ofP 9；
Secondly, iterative computation is carried out, each iteration is divided into two sub-items, and in the first sub-iteration, if a pixel pointP 1If the conditions of formula 3 and formula 4 are satisfied, the pixel point is determinedP 1Is deleted;
Formula III
Number of non-0 neighbors, formula four
Is an ordered collection
The number of the 01 patterns is equal to or less than the number of the six patterns if any one of the conditions of the three formulas to the six formulas is not satisfied
Pixel pointP 1Is not deleted;
in the second sub-iteration, formula three and formula four are unchanged, and formula five and formula six are replaced by formula seven and formula eight, as follows:
The solution of formula seven and formula eight is
Or
Or
And is
Pixel point removedP 1At the east or south or northwest corner of the image, the pixel points deleted in the second sub-iterationP 1At the northwest or southeast corner;
and obtaining a skeleton image after multiple iterations.
Further, in the fourth step, a topology network is generated, and the specific steps are as follows:
1) adding a circle of 0-value pixels around the skeleton image as a protective layer of the image;
2) if a certain pixel value is originally 0, the pixel value is still 0 after iteration;
3) if there is some non-0 pixel PiAnd B (P)i) If not, the analysis value of the pixel point is 1, and the pixel point is represented as a pixel in the middle section of the skeleton image;
4) if there is some non-0 pixel PiAnd B (P)i) If not equal to 2, the analysis value of the pixel point is made to be 2, and the pixel point is represented as an end point and an intersection point of the skeleton image;
5) then sequentially traversing pixel points with the analysis value of 2, carrying out equivalent filling, and marking the positions of end points and intersection points (the end points and the intersection points are collectively called as nodes) in the skeleton image;
6) and finally, tracking the connecting pixels among the nodes, sequentially recording the line layer information of the nodes, and restoring the obtained coordinates of the topological network into longitude and latitude coordinates, wherein the coordinates are pixel coordinates.
Further, in the fifth step, a minimum basic ring is searched in the generated topology network, and the specific steps are as follows:
1) finding the shortest path among all the vertexes of each undirected graph in the topological network;
2) for each vertexvAnd each side (x，y) Creating a loop set:
P(v，x) To representv,xThe shortest path between P: (v，y) To representv，yThe shortest path therebetween;
3) sorting the loops in the loop set according to the weight;
4) and finding the minimum basic ring in the loop set by adopting a greedy algorithm.
Further, the seventh step, merging the traffic zones, specifically comprises the steps of:
after the vertex sequence of the minimum basic ring (the vertex sequence is a sequence formed by a plurality of vertexes) is obtained, the vertex sequence can be converted into surface layer data by combining longitude and latitude coordinates:
further, the seventh step, merging the traffic zones, specifically comprises the steps of:
let K number of surface areas in the street map layer as
；
After the basic surface domain vector graphics (street layer) are spatially cut based on the minimum basic ring surface layer,
therein is provided withZ iA traffic cell, the preliminarily divided traffic cells are collected into
，
Representing the jth initial traffic cell divided by the ith base surface area, and setting the area threshold value asarea_ threshold；
The merging rule is as follows:
for (repetition)
：
Finding out preliminarily divided traffic districts
，
Screening area is less than or equal toarea_thresholdThe traffic cell (S) in (b) is set as a set of indexes of the screened traffic cells (S), and the traffic cells at this time constitute a set
；
For 
(this loop is nested in the upper loop):
in that
If there are more than one, the matching area is the largest, then it will beAnd merging the small-area traffic cells into the adjacent traffic cells to obtain the final traffic cell surface file. The design mechanism ensures that the cells are only merged in the same basic surface layer, namely, the traffic cells crossing the basic surface layer (street layer) can not be generated.
And the second scheme is realized based on the first scheme and the system.
The third scheme is as follows: an electronic device comprising a processor and a memory for storing a computer program capable of running on the processor,
wherein the processor is configured to execute the steps of the method of scheme two when running the computer program.
And the scheme is as follows: a storage medium having stored thereon a computer program which, when executed by a processor, carries out the steps of the method of solution two.
The application has beneficial effects that:
according to the method, the traffic districts are still divided based on the road network, in order to keep the characteristic that 'main roads serve as the boundaries of the traffic districts', a new topological network is formed by extracting a road framework, then the districts are divided based on the urban basic map layer, the calculation speed is high, the input data is simple, the generalization capability is good, a traffic modeler can be rapidly helped to divide the urban traffic districts, and the manpower investment in division work can be greatly simplified. Has the main effects that:
1) providing a feasible method for automatically dividing traffic cells based on a road network;
2) the method integrates the road network framework extraction, framework-to-topology, minimum basic loop search and area space analysis algorithms, and provides a set of complete system and method;
3) different roads are supported to use different radiuses to create buffer areas, and therefore the frameworks of the multi-line roads can be effectively extracted;
4) the method has the advantages of less needed basic data, clear parameter meaning and high running speed, and can be standardized into a model tool.
Drawings
Other features, objects and advantages of the present application will become more apparent upon reading of the following detailed description of non-limiting embodiments thereof, made with reference to the accompanying drawings in which:
fig. 1 is a block diagram of a system for automatically dividing a road network into traffic cells according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for automatically dividing a road network into traffic cells according to a second embodiment of the present application;
FIG. 3 is a flowchart of a second method refinement in the present application;
fig. 4 is a schematic diagram of obtaining a boundary longitude and latitude in the second embodiment of the present application;
FIG. 5 is a block diagram of a pixel point in the second embodiment of the present applicationP 1The eight neighborhood diagram of (1);
FIG. 6 is a schematic diagram of a pixel sequence formed in the second embodiment of the present application;
FIG. 7 is a schematic diagram of a second embodiment of the present application before performing a spatial segmentation on (street layer) based on a minimum basic ring layer;
fig. 8 is a schematic diagram illustrating a space cut (street layer) based on a minimum basic ring layer in the second embodiment of the present application;
fig. 9 is a schematic diagram of a second embodiment of the present application after merging of traffic cells;
fig. 10 is a schematic diagram of a Shenzhen road network as a segmentation road network and a street map layer as a basic map layer in the second embodiment of the present application;
FIG. 11 is a skeleton network topology diagram of Shenzhen road network in the second embodiment of the present application;
fig. 12 is a schematic diagram of a traffic cell map layer obtained by final partitioning of the Shenzhen road network in the second embodiment of the present application;
fig. 13 is a schematic structural diagram of an electronic device of the present application;
fig. 14 is a schematic flow chart illustrating a merging process of traffic zones according to a second embodiment of the present application;
fig. 15 is a diagram illustrating an example of image skeleton extraction in the second embodiment of the present application.
Detailed Description
The present application will be described in further detail with reference to the following drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the relevant application and are not limiting of the application. It should be noted that, for the convenience of description, only the portions relevant to the application are shown in the drawings.
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present application will be described in detail below with reference to the embodiments with reference to the attached drawings.
The symbols associated with the examples are as follows:
| link i | ith link multi-segment object in road network |
| link_buffer_polygon i | Buffer area generated by ith link object |
| merged_polygon | All the combined link _ buffer _ polygon area |
| max_lon、min_lon | Maximum longitude, minimum longitude |
| max_lat、min_lat | Maximum latitude and minimum latitude |
| max_row_index、min_row_index | Maximum line index, minimum line index |
| max_col_index、min_col_index | Maximum column index, minimum column index |
| row_pixel_num | Number of line pixels |
| col_pixel_num | Number of column pixels |
| lng_para | Longitude spanned by unit pixel in longitude direction |
| lat_para | Latitude spanned by unit pixel in latitude direction |
| P i | Value of ith pixel (or ith pixel object) |
| B(P i ) | Number of non-0 neighborhoods of ith pixel point |
| A(P i ) | Number of 01 patterns in ordered set |
| base_region i | Ith base surface area object |
| initial_taz ij | J initial traffic district divided by i basic surface area layer |
| small_taz ij | The j-th area divided by the ith basic surface area layer is smaller than the initial traffic cell of the threshold value |
| area_threshold | Area threshold |
Example one
The embodiment of the present application provides a system for automatically dividing a traffic cell in a road network based on an image technology (see fig. 1), including:
the road network buffer zone creating module is used for merging the road networks of the complex roads, converting the linear vector graph into a surface domain vector graph and storing the surface domain vector graph into a binary image format;
the coordinate information recording module is used for calculating the longitude and latitude span of the unit pixel of the binary image;
the buffer area central axis skeleton extraction module extracts a main line outline of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image;
the topological network generating module is used for acquiring a topological network based on the skeleton image;
a minimum basic ring searching module which searches the minimum basic ring of the topological network by adopting a greedy algorithm;
the traffic zone division module is used for performing space cutting on the street layer based on the minimum basic ring surface layer to obtain a preliminary traffic zone surface layer file;
and the traffic cell merging module is used for forming a small-area traffic cell at the boundary of the street image layer after space cutting, merging the small-area traffic cell into an adjacent traffic cell and obtaining a final traffic cell surface layer file.
Example two
The second embodiment of the present application provides a method for automatically dividing a road network into traffic cells based on an image technology (see fig. 2 to 9), and the method specifically includes:
s1, road network buffer creation,
the creation of the buffer zone has a more important influence on the rationality of the division of the cell, and the main purposes of the step are as follows:
1) complex roads such as overpasses and multi-line express roads are combined, and the central lines of the roads can be conveniently extracted;
2) and converting the linear file into a face area file to be stored in a picture format as an input file for extracting the skeleton image.
The method comprises the following specific steps:
the road network with complex roads has N traffic lines, and the input-based road network
The road network information only needs to contain geometric information, and a buffer area is created for each link object
Converting the linear vector graph into polygonal surface domain vector graph, merging to obtain a surface domain object
(ii) a Recording the maximum longitude of all geometric points in a surface vector graphicmax_lonMaximum latitudemax_latMinimum latitudemin_latMinimum longitude, minimum longitudemin_lonAnd then storing the area vector graphics as a binary image. See figure 4 for border latitude and longitude.
S2, recording the coordinate information,
after the vector file is binarized, only the pixel coordinates are obtained, and in order to restore the geographic coordinates in the subsequent steps, the longitude and latitude span of the unit pixel needs to be calculated.
Calculating the latitude and longitude span of the unit pixel of the binary image to be used as input data for extracting the skeleton image;
the method comprises the following specific steps:
the obtained binary image is a matrix, the value of the element of the matrix is 0 or 1, and the minimum row index of the 1 value in the matrix is foundmin_row_index、Maximum row indexmax_row_index、Minimum column indexmin_col_index、Maximum column indexmax_ col_index，Then, the pixel is cut, and the purpose of the cutting is to remove the peripheral zero elements of the matrix so as to correctly record the longitude and latitude spanned by the unit pixelThe number of row pixels of the current matrix after cutting is recorded asrow_pixel_num，The number of the column pixels iscol_pixel_num，The longitude spanned by the unit pixel in the longitude direction islng_para，The unit pixel in the latitude direction spans the latitude oflat_para，Calculating according to a formula I and a formula II, and using the obtained matrix as input data of skeleton extraction;
S3, extracting the skeleton in the buffer area,
the skeleton extraction is a morphological problem under a graphics branch, and the intuitive understanding is to extract a main line contour of a target image, namely to extract a central pixel contour of the target on the image, wherein the thinned target has a single-layer pixel width.
Extracting a main line contour of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image;
the method comprises the following specific steps:
a binary map may be defined by a matrix M, each element of which is defined by a binary valuem ij Representing one pixel, the pixel has a value of 0 or 1, the pixel having a value of 1 constitutes an image, the road net pixel of the black portion has a value of 1, and the pixel of the white portion has a value of 0. In the skeletonization process of the image, all pixel points belonging to the skeleton are deleted, and iterative computation is needed to complete the process;
firstly, defining a pixel point of a binary imageP 1Is the neighborhood in eight directions (see fig. 5), the north direction isP 2In the northeast of the yearP 3In the east directionP 4In the east-south direction isP 5In the south directionP 6In the southwest direction ofP 7In the western directionP 8In the northwest direction ofP 9；
Secondly, iterative computation is carried out, each iteration is divided into two sub-items, and in the first sub-iteration, if a pixel pointP 1If the conditions of formula 3 and formula 4 are satisfied, the pixel point is determinedP 1Is deleted;
Formula III
Number of non-0 neighbors, formula four
Is an ordered collection
The number of the 01 patterns is equal to or less than the number of the six patterns if any one of the conditions of the three formulas to the six formulas is not satisfied
Pixel pointP 1Is not deleted;
with respect to the description of the 01 mode number (see fig. 6), the pixel sequence values formed are:
0（P2）1（P3）0（P4）0（P5）1（P6）0（P7）0（P8）0（P9），
at this time
=2。
In the second sub-iteration, formula three and formula four are unchanged, and formula five and formula six are replaced by formula seven and formula eight, as follows:
The solution of formula seven and formula eight is
Or
Or
And is
Pixel point removedP 1At the east or south or northwest corner of the image, the pixel points deleted in the second sub-iterationP 1At the northwest or southeast corner;
and obtaining a skeleton image after multiple iterations.
S4, topology network generation,
establishing a circle of 0 analysis value pixels as a protective layer based on the skeleton image, performing equivalent filling according to the analysis value of the identification unit pixels, marking the positions of nodes in the binary image, tracking the connection pixels among the nodes, recording line layer information, and restoring the obtained pixel coordinates of the topological network into longitude and latitude coordinates;
generating a topological network, which comprises the following specific steps:
1) adding a circle of 0-value pixels around the skeleton image to serve as a protective layer;
2) the pixel point with the pixel value of 0 is still 0;
3) if a certain non-0 pixel has two non-0 pixels in eight neighborhoods, the pixel is marked as 1 and represents a pixel in the middle section in the skeleton image;
4) if the number of non-0 pixels in the eight neighborhoods of a certain non-0 pixel is not 2 (such as 1, 3 and the like), identifying the pixel as an analysis value 2, representing the pixels of the end points and the intersection points in the skeleton image;
5) then, sequentially traversing the pixels with the analysis value of 2, performing equivalent filling, and marking the positions of nodes (the nodes are the general names of end points and intersection points) in the skeleton image;
6) and finally, tracking the connecting pixels among the nodes, recording the line layer information of the connecting pixels, and restoring the obtained coordinates of the topological network into longitude and latitude coordinates, wherein the coordinates are pixel coordinates.
S5, finding the minimum basic loop,
after extracting the topology file of the road skeleton, the network needs to be searched for the minimum basic ring, and the search algorithm is as follows:
for an undirected graph G (V, E) (the weight of the edge is positive number), setting the number of the edges in the graph as m and the number of the nodes as n;
searching a minimum basic ring, and specifically comprising the following steps:
1) finding the shortest path among all the vertexes of each undirected graph in the topological network;
2) for each vertexvAnd each side (x，y) Creating a loop set:
P(v，x) To representv,xThe shortest path between P: (v，x) To representv，xThe shortest path between P: (v，y) To representv，yThe shortest path therebetween;
3) sorting the loops in the loop set according to the weight;
4) and finding the minimum basic ring in the loop set by adopting a greedy algorithm.
S6, dividing the traffic district,
performing space cutting on the street map layer based on the minimum basic ring surface layer to obtain a preliminary traffic cell surface layer file;
s7, traffic cell merging (see fig. 14),
due to the close distance between the boundaries of the part of roads and the basic street layer, after the street layer is divided by using the road network, more cells with small areas are formed at the boundaries of the street layer, and the part of cells should be merged into the adjacent traffic cells. Merging traffic districts, which comprises the following steps:
let K number of surface areas in the street map layer as
；
After the street layers are spatially cut based on the minimum basic ring surface layer (see fig. 7 before cutting, fig. 8 after cutting, fig. 9 after merging optimization, for the convenience of understanding, only partial layers are used for partitioning and illustration),
therein is provided withZ iA traffic cell, the preliminarily divided traffic cells are collected into
，
Representing the jth initial traffic cell belonging to the ith basic surface area, and setting the area threshold value asarea_threshold；
The merging rule is as follows:
for (repetition)
：
Finding out preliminarily divided traffic districts
，
Screening area is less than or equal toarea_thresholdThe traffic cell (S) in (b) is set as a set of indexes of the screened traffic cells (S), and the traffic cells at this time constitute a set
；
For 
：
In that
Find the cell adjacent to the current traffic cell, if there are more than one, the matching area is the largest, then merge the traffic cells with small area into its adjacent traffic cells (initial _ taz in fig. 8)1-2And initial _ taz2-2And if the area is smaller than the threshold value, combining the area with the parent image layer) to obtain the final traffic cell surface file.
The merged traffic cell layer file is shown in fig. 9.
In the example, a shenzhen road network is used as a segmentation road network, a street map layer is used as a basic map layer (see fig. 10), a skeleton network topology generated by the method is shown in fig. 11, and a finally divided traffic cell map layer is shown in fig. 12.
EXAMPLE III
An electronic device according to a third embodiment of the present application is shown in fig. 13 as a general-purpose computing device. Components of the electronic device may include, but are not limited to: one or more processors or processing units, a memory for storing a computer program capable of running on the processor, a bus connecting the various system components (including the memory, the one or more processors or processing units).
Wherein the one or more processors or processing units are configured to execute the steps of the method according to the second embodiment when the computer program is run. The type of processor used includes central processing units, general purpose processors, digital signal processors, application specific integrated circuits, field programmable gate arrays or other programmable logic devices, transistor logic devices, hardware components, or any combination thereof.
Where a bus represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
Example four
A fourth embodiment of the present application provides a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method according to the second embodiment.
It should be noted that the storage media described herein can be computer readable signal media or storage media or any combination of the two. A storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples of storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present application, a storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device. In this application, however, the storage medium may comprise a propagated data signal with the computer-readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A storage medium may also be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to: wireless, wire, fiber optic cable, RF, etc., or any suitable combination of the foregoing.
The technical key points of the application are emphasized:
1. extracting a central axis skeleton in a buffer area;
2. a topological network generation method;
3. the method integrates the road network framework extraction, framework-to-topology, minimum basic loop search and area space analysis algorithms, and provides a set of complete system and method and python source code implementation.
Abbreviations and key terms in this application are defined as follows:
(1) traffic model
The traffic model is a mathematical model combination reflecting the internal rules of the traffic system, is described in the forms of numbers, graphs, images, videos and the like, integrates various subject theories such as traffic engineering, sociology, demographics, economics, statistics, behaviourology, informatics and the like, and provides an important quantitative analysis technology for supporting decisions of various stages such as traffic policy and planning, construction and investment, operation and management and the like by using a mathematical method and computer software and hardware equipment.
(2) Urban traffic model
The urban traffic model is a series of mathematical models for analyzing urban traffic to reveal and reflect the intrinsic laws of the traffic system. The degree of thoroughness of the urban traffic analysis will determine the quality of the model. The current traffic model is an explanation of the current situation of a city, and the planning traffic model is a judgment of future development of the city, namely, an interpretation of city planning.
(3) Traffic community
In urban traffic research, in order to link the generation and attraction of traffic demands with socioeconomic indexes of a certain area, a traffic distribution diagram between traffic cells for the traffic demands to flow on the space is shown, and in order to simulate the traffic flow on a road network by using a traffic distribution theory, a city is divided into a plurality of traffic cells under the conditions that an administrative division is not broken, and the land property and the traffic characteristics of the traffic regions are kept consistent as much as possible.
(4) Binary image
The binary image means that there are only two gray levels in the image, that is, the gray value of any pixel in the image is 0 or 1, which represents black and white respectively.
(5) Image skeleton extraction
The image skeleton extraction can be intuitively understood as: after the non-skeleton redundant pixel points in the digital image are identified through a certain algorithm rule, the non-skeleton redundant pixel points are deleted, and only skeleton pixel points are reserved, for example, see fig. 15. Under a complex multiline road scene, skeleton extraction is very useful for road simplification.
(6) Surface area object and multi-segment line object
The surface area object (POLYGON) and the multi-segment line object (LINESTRING) are used for describing space geographic information elements, one surface area object is expressed as a two-dimensional plane area in visualization software, one multi-segment line object is expressed as a multi-break-point broken line in the visualization software and is used for simulating a real road network, and the two objects store coordinate information, so that space operations such as merging, breaking, splitting and the like can be carried out.
The above-mentioned embodiments are provided to further explain the purpose, technical solutions and advantages of the present application in detail, and it should be understood that the above-mentioned embodiments are only examples of the present application and are not intended to limit the scope of the present application, and any modifications, equivalents, improvements and the like made on the basis of the technical solutions of the present application should be included in the scope of the present application.
Claims (9)
1. A system for automatically dividing traffic cells in a road network is characterized by comprising the following steps:
the road network buffer zone creating module is used for merging the road networks of the complex roads, converting the linear vector graph into a surface domain vector graph and storing the surface domain vector graph into a binary image format;
the coordinate information recording module is used for calculating the longitude and latitude span of the unit pixel of the binary image;
the buffer area central axis skeleton extraction module extracts a main line outline of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image; the method specifically comprises the following steps:
each element in the binary image represents a pixel, the value of the pixel is 0 or 1, the pixel with the value of 1 forms an image, and the pixel with the value of 0 is blank;
firstly, defining a pixel point of a binary imageP 1Is a neighborhood of eight directions, north isP 2In the northeast of the yearP 3In the east directionP 4In the east-south direction isP 5In the south directionP 6In the southwest direction ofP 7In the western directionP 8In the northwest direction ofP 9；
Secondly, iterative computation is carried out, each iteration is divided into two sub-items, and in the first sub-iteration, if a pixel pointP 1If the conditions of formula three and formula four are satisfied, the pixel point isP 1Is deleted;
Formula III
Number of non-0 neighbors, formula four
Is an ordered collection𝑃2,𝑃3,𝑃4,𝑃5,𝑃6,𝑃7,𝑃8,𝑃9The number of the 01 patterns is equal to or less than the number of the six patterns if any one of the conditions of the three formulas to the six formulas is not satisfied
Pixel pointP 1Is not deleted;
in the second sub-iteration, formula three and formula four are unchanged, and formula five and formula six are replaced by formula seven and formula eight, as follows:
The solution of formula seven and formula eight is
Or
Or
And is
Pixel point removedP 1At the east or south or northwest corner of the image, the pixel points deleted in the second sub-iterationP 1At the northwest or southeast corner;
obtaining a skeleton image after multiple iterations;
the topological network generating module is used for acquiring a topological network based on the skeleton image;
a minimum basic ring searching module which searches the minimum basic ring of the topological network by adopting a greedy algorithm;
the traffic zone division module is used for performing space cutting on the surface domain vector graph based on the minimum basic torus layer to obtain a preliminary traffic zone surface layer file;
and the traffic cell merging module is used for forming a small-area traffic cell at the boundary of the street image layer after space cutting, merging the small-area traffic cell into an adjacent traffic cell and obtaining a final traffic cell surface layer file.
2. A method for automatically dividing traffic cells in a road network is characterized by comprising the following steps:
step one, the road network buffer zone is established,
merging the road networks of the complex roads, converting the linear vector graphics into surface domain vector graphics, and storing the surface domain vector graphics into a binary image format;
step two, recording the coordinate information,
calculating the longitude and latitude span of the unit pixel of the binary image;
step three, extracting the skeleton in the buffer area,
extracting a main line contour of the binary image through iterative computation according to the longitude and latitude span of the unit pixel of the binary image to obtain a skeleton image; the method specifically comprises the following steps:
each element in the binary image represents a pixel, the value of the pixel is 0 or 1, the pixel with the value of 1 forms an image, and the pixel with the value of 0 is blank;
firstly, defining a pixel point of a binary imageP 1Is a neighborhood of eight directions, north isP 2In the northeast of the yearP 3In the east directionP 4In the east-south direction isP 5In the south directionP 6In the southwest direction ofP 7In the western directionP 8In the northwest direction ofP 9；
Secondly, iterative computation is carried out, each iteration is divided into two sub-items, and in the first sub-iteration, if a pixel pointP 1If the conditions of formula three and formula four are satisfied, the pixel point isP 1Is deleted;
Formula III
Number of non-0 neighbors, formula four
Is an ordered collection𝑃2,𝑃3,𝑃4,𝑃5,𝑃6,𝑃7,𝑃8,𝑃9The number of the 01 patterns is equal to or less than the number of the six patterns if any one of the conditions of the three formulas to the six formulas is not satisfied
Pixel pointP 1Is not deleted;
in the second sub-iteration, formula three and formula four are unchanged, and formula five and formula six are replaced by formula seven and formula eight, as follows:
The solution of formula seven and formula eight is
Or
Or
And is
Pixel point removedP 1At the east or south or northwest corner of the image, the pixel points deleted in the second sub-iterationP 1At the northwest or southeast corner;
obtaining a skeleton image after multiple iterations;
step four, generating the topological network,
establishing a circle of 0 analysis value pixels as a protective layer based on the skeleton image, performing equivalent filling according to the analysis value of the identification unit pixels, marking the positions of nodes in the binary image, tracking the connection pixels among the nodes, recording line layer information, and restoring the obtained pixel coordinates of the topological network into longitude and latitude coordinates;
step five, searching a minimum basic ring,
searching a minimum basic ring of the topological network by adopting a greedy algorithm;
step six, dividing the traffic cell,
performing space cutting on the surface domain vector graph based on the minimum basic torus layer to obtain a primary traffic cell surface layer file;
step seven, merging the traffic districts,
and after space cutting, forming a small-area traffic cell at the boundary of the street map layer, and merging the small-area traffic cell into the adjacent traffic cell to obtain a final traffic cell surface file.
3. The method for automatically dividing traffic cells of road network according to claim 2, wherein said step one, road network buffer zone creation, comprises the specific steps of:
the road network with complex roads has N traffic lines, and the input-based road network
Creating a buffer for each link object
Converting the linear vector graph into polygonal surface domain vector graph, merging to obtain a surface domain object
(ii) a Recording the maximum longitude of all geometric points in a surface vector graphicmax_lonMaximum latitudemax_latMinimum latitudemin_latMinimum longitude, minimum longitudemin_lonAnd then storing the area vector graphics as a binary image.
4. The method for automatically dividing traffic cells according to claim 3, wherein in the second step, the coordinate information is recorded, and the specific steps are as follows:
the obtained binary image is a matrix, the value of the element of the matrix is 0 or 1, and the minimum row index of the 1 value in the matrix is foundmin_ row_index、Maximum row indexmax_row_index、Minimum column indexmin_col_index、Maximum column indexmax_col_ index，Then cutting the matrix, wherein the purpose of the cutting is to remove the peripheral zero elements of the matrix so as to correctly record the longitude and latitude spanned by the unit pixel, and the number of the row pixels of the current matrix after cutting is recorded asrow_pixel_num，The number of the column pixels iscol_pixel_num，The longitude spanned by the unit pixel in the longitude direction islng_para，The unit pixel in the latitude direction spans the latitude oflat_para，Calculating according to a formula I and a formula II, and using the obtained matrix as input data of skeleton extraction;
5. The method for automatically dividing traffic cells according to the road network of claim 4, wherein the step four, the generation of topology network, comprises the following specific steps:
1) adding a circle of 0-value pixels around the skeleton image as a protective layer of the image;
2) if a certain pixel value is originally 0, the pixel value is still 0 after iteration;
3) if there is some non-0 pixel PiAnd B (P)i) If not, the analysis value of the pixel point is 1, and the pixel point is represented as a pixel in the middle section of the skeleton image;
4) if there is some non-0 pixel PiAnd B (P)i) If not equal to 2, the analysis value of the pixel point is made to be 2, and the pixel point is represented as an end point and an intersection point of the skeleton image;
5) then sequentially traversing pixel points with the analysis value of 2, carrying out equivalent filling, and marking the positions of end points and intersection points (the end points and the intersection points are collectively called as nodes) in the skeleton image;
6) and finally, tracking the connecting pixels among the nodes, sequentially recording the line layer information of the nodes, and restoring the obtained coordinates of the topological network into longitude and latitude coordinates, wherein the coordinates are pixel coordinates.
6. The method for automatically dividing traffic cells according to the road network of claim 5, wherein said step five, searching the minimum basic ring in the generated topology network, specifically comprises the steps of:
1) finding the shortest path among all the vertexes of each undirected graph in the topological network;
2) for each vertexvAnd each side (x，y) Creating a loop set:
P(v，x) To representv，xThe shortest path between P: (v，y) To representv，yThe shortest path therebetween;
3) sorting the loops in the loop set according to the weight;
4) and finding the minimum basic ring in the loop set by adopting a greedy algorithm.
7. The method for automatically dividing traffic cells according to claim 6, wherein said step seven, merging traffic cells, comprises the following specific steps:
after the vertex sequence of the minimum basic ring is obtained, the vertex sequence can be converted into surface layer data by combining longitude and latitude coordinates:
further, the seventh step, merging the traffic zones, specifically comprises the steps of:
let K number of surface areas in the street map layer as
；
After the basic surface domain vector graphics are spatially cut based on the minimum basic torus layer,
therein is provided withZ iA traffic cell, the preliminarily divided traffic cells are collected into
，
Representing the jth initial traffic cell divided by the ith base surface area, and setting the area threshold value asarea_threshold；
The merging rule is as follows:
For
：
finding out preliminarily divided traffic districts
，
Screening area is less than or equal toarea_thresholdThe traffic cell (S) in (b) is set as a set of indexes of the screened traffic cells (S), and the traffic cells at this time constitute a set
；
For 
：
In that
If there are a plurality of cells adjacent to the current traffic cell, the matching area is the largest, and then the traffic cells with small areas are merged into the adjacent traffic cells to obtain the final traffic cell surface file.
8. An electronic device, characterized in that: comprising a processor and a memory for storing a computer program capable of running on the processor,
wherein the processor is adapted to perform the steps of the method of any one of claims 2 to 7 when running the computer program.
9. A storage medium having a computer program stored thereon, the computer program, when being executed by a processor, performing the steps of the method of any one of claims 2 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111279227.0A CN113724279B (en) | 2021-11-01 | 2021-11-01 | System, method, equipment and storage medium for automatically dividing traffic cells into road networks |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111279227.0A CN113724279B (en) | 2021-11-01 | 2021-11-01 | System, method, equipment and storage medium for automatically dividing traffic cells into road networks |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113724279A CN113724279A (en) | 2021-11-30 |
| CN113724279B true CN113724279B (en) | 2022-03-18 |
Family
ID=78686131
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111279227.0A Active CN113724279B (en) | 2021-11-01 | 2021-11-01 | System, method, equipment and storage medium for automatically dividing traffic cells into road networks |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113724279B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114547827B (en) * | 2022-04-26 | 2022-09-23 | 深圳市城市交通规划设计研究中心股份有限公司 | Infrastructure group running state evaluation method, electronic device and storage medium |
| CN114898013B (en) * | 2022-07-15 | 2022-11-22 | 深圳市城市交通规划设计研究中心股份有限公司 | Traffic isochronous ring generation method, electronic device and storage medium |
| CN115424446B (en) * | 2022-11-03 | 2023-02-14 | 深圳市城市交通规划设计研究中心股份有限公司 | Road network topology simplification method for traffic organization evaluation |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN105139434A (en) * | 2015-08-11 | 2015-12-09 | 长沙迪迈数码科技股份有限公司 | Automatic construction method and system for road network of open mine |
| CN110119740A (en) * | 2019-03-06 | 2019-08-13 | 东南大学 | A method of it is extracted from complicated urban road network and simplifies topological relation |
| CN110309248A (en) * | 2019-06-26 | 2019-10-08 | 东南大学 | A method of the traffic route network based on Voronoi diagram divides traffic zone automatically |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7447588B1 (en) * | 2007-07-16 | 2008-11-04 | Wenshine Technology Ltd. | Method and system for partitioning a continental roadway network for an intelligent vehicle highway system |
| CN102801154B (en) * | 2011-05-27 | 2014-11-26 | 国际商业机器公司 | Method and device for extracting backbone topology structure of power grid |
| CN109948477B (en) * | 2019-03-06 | 2022-05-13 | 东南大学 | Method for extracting road network topology points in picture |
-
2021
- 2021-11-01 CN CN202111279227.0A patent/CN113724279B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101751777A (en) * | 2008-12-02 | 2010-06-23 | 同济大学 | Dynamic urban road network traffic zone partitioning method based on space cluster analysis |
| CN105139434A (en) * | 2015-08-11 | 2015-12-09 | 长沙迪迈数码科技股份有限公司 | Automatic construction method and system for road network of open mine |
| CN110119740A (en) * | 2019-03-06 | 2019-08-13 | 东南大学 | A method of it is extracted from complicated urban road network and simplifies topological relation |
| CN110309248A (en) * | 2019-06-26 | 2019-10-08 | 东南大学 | A method of the traffic route network based on Voronoi diagram divides traffic zone automatically |
Non-Patent Citations (2)
| Title |
|---|
| 城市道路网络交通小区划分方法研究;李晓丹等;《计算机工程与应用》;20090211(第05期);第19-22页 * |
| 基于路网的城市子区域提取技术研究;宋雪涛等;《地理空间信息》;20060131(第06期);第101-102、105页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113724279A (en) | 2021-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113724279B (en) | System, method, equipment and storage medium for automatically dividing traffic cells into road networks | |
| Chen et al. | Automatic building information model reconstruction in high-density urban areas: Augmenting multi-source data with architectural knowledge | |
| Chen et al. | A methodology for automated segmentation and reconstruction of urban 3-D buildings from ALS point clouds | |
| CN110021072B (en) | Holographic mapping-oriented multi-platform point cloud intelligent processing method | |
| CN113723715B (en) | Method, system, equipment and storage medium for automatically matching public transport network with road network | |
| CN110992473A (en) | Tree branch modeling method and system based on vehicle-mounted laser scanning point cloud | |
| CN115661374B (en) | Rapid retrieval method based on space division and model voxelization | |
| Guilbert et al. | Terrain generalisation | |
| CN112528508A (en) | Electromagnetic visualization method and device | |
| Ortega et al. | Generating 3D city models from open LiDAR point clouds: Advancing towards smart city applications | |
| Yang et al. | Complementarity of historic building information modelling and geographic information systems | |
| CN107818338B (en) | Method and system for building group mode identification facing map synthesis | |
| Yang et al. | A map‐algebra‐based method for automatic change detection and spatial data updating across multiple scales | |
| She et al. | 3D building model simplification method considering both model mesh and building structure | |
| Hu et al. | Geometric feature enhanced line segment extraction from large-scale point clouds with hierarchical topological optimization | |
| Guo et al. | Study on landscape architecture model design based on big data intelligence | |
| CN115937461A (en) | Multi-source fusion model construction and texture generation method, device, medium and equipment | |
| Borisov et al. | An automated process of creating 3D city model for monitoring urban infrastructures | |
| Zhou et al. | Automated extraction of 3D vector topographic feature line from terrain point cloud | |
| CN114661744B (en) | Terrain database updating method and system based on deep learning | |
| CN114445574B (en) | Method, device and equipment for converting GeoJSON data format into three-dimensional GLB format | |
| Lei et al. | Automatic identification of street trees with improved RandLA-Net and accurate calculation of shading area with density-based iterative α-shape | |
| Mao et al. | City object detection from airborne Lidar data with OpenStreetMap‐tagged superpixels | |
| Shirowzhan et al. | Spatial big data, BIM and advanced GIS for smart transformation: city, infrastructure and construction | |
| Vasin et al. | Geometric modeling of raster images of documents with weakly formalized description of objects |
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 |