CN108920481B - Road network reconstruction method and system based on mobile phone positioning data - Google Patents
Road network reconstruction method and system based on mobile phone positioning data Download PDFInfo
- Publication number
- CN108920481B CN108920481B CN201810361223.9A CN201810361223A CN108920481B CN 108920481 B CN108920481 B CN 108920481B CN 201810361223 A CN201810361223 A CN 201810361223A CN 108920481 B CN108920481 B CN 108920481B
- Authority
- CN
- China
- Prior art keywords
- road
- network
- data set
- road network
- points
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000012549 training Methods 0.000 claims abstract description 45
- 238000013145 classification model Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 8
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract description 8
- 238000010586 diagram Methods 0.000 claims description 13
- 230000008569 process Effects 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 5
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 2
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000010276 construction Methods 0.000 description 8
- 238000000605 extraction Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000007635 classification algorithm Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/02—Services making use of location information
- H04W4/029—Location-based management or tracking services
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Signal Processing (AREA)
- Health & Medical Sciences (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Traffic Control Systems (AREA)
Abstract
A road network reconstruction method and system based on mobile phone positioning data comprises the following steps: acquiring an original data set, wherein the original data set comprises a training data set and a prediction data set; the original data set is track points obtained according to mobile phone positioning data; respectively constructing and combining features of the training data set and the prediction data set by using two dimensions of time and density, and generating a training set and a prediction set; using the generated training set to obtain a sampling point classification model based on an algorithm in machine learning; applying the learned classification model to a prediction set, and dividing track points into road points and non-road points; constructing roads for the identified road points based on the constrained Delaunay triangulation network; and modifying the road center line according to the topological relation, thereby completing the reconstruction of the road network. The invention provides a high-quality new way for producing and updating a fine road network, which provides technical support for a seamless navigation technology, particularly a fine road network, and enlarges the coverage range of a path navigation service.
Description
Technical Field
The invention relates to a space-time trajectory data mining technology, in particular to a road network reconstruction method and system based on mobile phone positioning data, and belongs to the field of geographic information systems and intelligent traffic research.
Background
Roads are important infrastructures of cities, and how to supplement and update urban road data in time in the rapid urban development process so as to keep the accuracy, timeliness and perfection degree of the urban road data is a difficult problem to be solved urgently. The scale of residential communities in cities is continuously enlarged, the internal road network of the residential communities becomes increasingly fine and complex, but the information fineness of the existing community-level roads is not sufficient or even lost, so that a blind area exists in the navigation of details outside the interior of the residential community, and a great obstacle is caused to the development of an outdoor seamless navigation technology. Meanwhile, the road network structure information is the core content of the basic data of the electronic map, and is the data basis of the electronic map for realizing the navigation function and the intelligent traffic system, so that the accurate and timely updating of the urban fine road network is an important problem (the urban fine road network refers to the cell-level branch inside each closed cell in the city).
With the great improvement of the convenience of acquiring the multi-source track data and the updating real-time performance of the multi-source track data, a large amount of track data containing space-time information can be easily acquired by both academic circles and industrial circles, so that the road network extraction method based on the space-time track data becomes possible. At present, there are two main road network automatic extraction methods: one is to extract road information from vehicle-mounted GPS track data; and the other method is to extract road network information based on the high-resolution remote sensing image. However, the existing road network extraction method mainly focuses on the research of main roads in cities, and the fine road network of the urban cell level is often ignored. The remote sensing image has long imaging distance and large coverage range, and simultaneously has insufficient capacity of depicting fine information of different spatial scales, and the processing method based on the data only can better solve the information extraction of a common main road and cannot finally solve the problem of construction of a fine road network; in addition, the inside of building ranges such as schools and communities limits the acquisition of the GPS track data to a certain extent, and the pedestrian movement track data has strong randomness and low sampling frequency, and includes various types of ground objects such as roads, buildings and squares, so that it is difficult to extract a road network based on the movement track data.
Disclosure of Invention
The invention aims to solve the technical problem of insufficient road fineness and partial loss in the existing community road network, provides a refined road network extraction method, and can conveniently and accurately complete the construction work of a refined road network. The method comprises the steps of converting a road network reconstruction problem based on large-scale pedestrian data into two classification problems of road points and non-road points, firstly constructing a feature set by using different combinations of two dimensions of time and density to generate a training set, then learning a sampling point classification model by using a random forest algorithm, then dividing the data set by using the classification model to obtain a road point set, and finally constructing roads and extracting road center lines for the identified road point set by using a constraint Delaunay triangulation network so as to complete construction of a refined road network in a closed area. Which comprises the following steps:
step 1) obtaining an original data set, wherein the original data set comprises a training data set and a prediction data set; the original data set is track points obtained according to mobile phone positioning data;
step 2) respectively constructing and combining features of the training data set and the prediction data set by using two dimensions of time and density, and then generating the training set and the prediction set;
step 3) using the generated training set to obtain a sampling point classification model based on algorithm learning in machine learning;
step 4) applying the learned classification model to a prediction set, and dividing track points into road points and non-road points;
step 5) constructing roads for the identified road points based on the constrained Delaunay triangulation network;
and 6) modifying the road center line according to the topological relation, thereby completing the reconstruction of the road network.
Further, in the road network reconstructing method based on mobile phone positioning data of the present invention, the training data set in step 1 is obtained according to the following manner: the method comprises the steps of obtaining distribution modes of track points in a plurality of closed cells, and selecting a plurality of non-overlapping small-scale areas with different track point distribution modes to form a training data set.
Further, in the road network reconstructing method based on mobile phone positioning data of the present invention, the density characteristic value in step 2 includes: and performing Delaunay triangulation on the training data set by combining the time dimension, wherein the average length of all adjacent triangle sides connected by each trace point is equal to the average length of all adjacent triangle sides connected by each trace point.
Further, in the road network reconstructing method based on mobile phone positioning data of the present invention, the density characteristic value in step 2 includes: and constructing a Voronoi diagram for the training data set by combining the time dimension, wherein the reciprocal of the area of a polygon in the Voronoi diagram corresponding to each track point.
Further, in the road network reconstruction method based on mobile phone positioning data of the present invention, the specific steps of time and density two-dimensional feature construction and combination in step 2 are as follows:
by analyzing the behavior pattern of people, a feature space is constructed based on the space-time density distribution difference of roads and non-roads in a closed cell, namely, the aggregative difference of the space-time distribution of the track points is expressed by combining three geometric features, namely the number of the track points in a buffer area, the length of the adjacent triangle sides based on a constrained Delaunay triangulation network and the area of a polygon in a Voronoi diagram, with the time dimension; and constructing a classifier based on the feature sets established by the three different geometric dimension control conditions to identify the road points.
Further, in the road network reconstruction method based on mobile phone positioning data of the present invention, the learning algorithm in step 3 includes a random forest and a support vector machine.
Further, in the road network reconstruction method based on the mobile phone positioning data, for the track point data in the training data set, the corresponding OSM data is used, a line buffer area is generated according to a certain radius based on the incomplete road network data in the OSM, the track point mark falling in the buffer area is 1, the track point mark falling outside the buffer area is 0, and based on the mark, the track point in the training data set is divided into two types of road points and non-road points to be used as label data in the subsequent training of the machine learning model.
Further, in the road network reconstructing method based on mobile phone positioning data of the present invention, the step 5 specifically includes:
constructing a constrained Delaunay triangulation network by using a road point set formed by the road points extracted in the step 4, dividing triangles in the triangulation network into 3 classes according to the number of adjacent triangles, respectively corresponding to an entrance of a road, a trunk of the road and a road intersection, respectively processing the triangles, and extracting a road center line, wherein the specific implementation process is as follows:
constructing a constrained Delaunay triangulation network on the identified road point set, and dividing triangles in the triangulation network into 3 types: only one side is provided with an adjacent triangle which is an A type, two sides are provided with an adjacent triangle which is a B type, three sides are provided with adjacent triangles which are a C type, the A type triangle is connected with the midpoint of the only adjacent side and the opposite vertex of the midpoint, the B type triangle is connected with the midpoints of two adjacent sides, the C type triangle is connected with the gravity center and the midpoints of three sides, in the searching and connecting process, the C type triangle is searched firstly and is terminated at the A type triangle or the C type triangle, and one side of the network is obtained until the C type triangle is processed; and searching from the triangle of the A class and ending at the triangle of the A class to obtain all the edges, thereby forming the road central line network.
Further, in the road network reconstructing method based on mobile phone positioning data of the present invention, the step 6 specifically includes:
optimizing and perfecting a road center line, and straightening the road center line near an intersection so as to finish the reconstruction of a fine road network of a closed area, wherein the specific processing mode is as follows:
for the arc road network near the intersection, cutting straight lines with a certain length from the intersection, comparing angles of the cut remaining lines, connecting the two lines into one line when the angles of the two lines meet a certain range, and obtaining an intersection point as a node of the network when the intersection is a crossroad, so as to finally form the road network, thereby completing the reconstruction of the road network of the closed area.
The invention also provides a road network reconstruction system based on mobile phone positioning data for solving the technical problem, and the road network reconstruction method based on the mobile phone positioning data is adopted for road network reconstruction.
According to the method and the system for reconstructing the road network based on the mobile phone positioning data, the track data are mined and analyzed according to the behavior pattern of people and the space-time density characteristics, semantic information contained in a large amount of sparse mobile phone positioning data is utilized, a novel method for constructing a refined road network by using the mobile phone positioning data is provided, the updating efficiency of the traditional road network can be improved, the maintenance cost is reduced, the time for extracting the road network is greatly shortened, and a novel mode is provided for solving the problems of imperfection and missing of cell-level road information.
Drawings
The invention will be further described with reference to the accompanying drawings and examples, in which:
FIG. 1 is a flow chart of a method of the present invention;
FIG. 2 is a schematic diagram of the present invention calculating the area of each polygon in a Voronoi diagram;
fig. 3 is a schematic diagram of calculating the average length of the triangle side adjacent to the track point in the Delaunay triangulation network according to the present invention.
Detailed Description
For a more clear understanding of the technical features, objects and effects of the present invention, embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
The invention relates to a road network reconstruction method based on mobile phone positioning data, which is used for carrying out fine processing on a road network. Firstly, analyzing distribution patterns of track points in a plurality of closed cells, then selecting a plurality of small-range areas with representative distribution patterns in different cells to construct a training data set, classifying the rest parts into a prediction data set, and meanwhile, manually classifying the track point data in the training data set into two types of road points and non-road points as label values of training data; feature construction and combination is performed using two dimensions of time and density, where the time dimension can be achieved by dividing a day into 7 different periods (6:00-8:00, 08:00-12:00, 12:00-14:00, 14:00-17:00, 17:00-20:00, 20:00-24:00, 24:00-06:00), and in terms of density, features can be constructed from three angles: combining all the characteristics and the label values corresponding to the track points based on the number of the track points in the buffer area, the area of each polygon based on the Voronoi diagram and the average length of the adjacent triangle sides of each track point based on the constraint Delaunay triangulation network to form a training set; learning a sampling point classification model based on a random forest algorithm in a classification algorithm by using the generated training set; then, applying the learned classification model to a prediction data set to identify road points and non-road points in the predicted track point data to obtain a road point set; and finally, extracting the center line of the road by using a constrained Delaunay triangulation network on the road point set, and completing the construction of a refined road network in the closed cell.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
As shown in fig. 1, fig. 1 is a flowchart of a method for refining road network reconstruction based on mobile phone positioning data, the method includes the following steps:
step 1, obtaining an original data set, wherein the original data set comprises a training data set and a prediction data set; the original data set is track points obtained according to mobile phone positioning data. Preferably, a plurality of non-overlapping small-scale areas with different track point distribution modes are selected from the original data set to form a training data set, and the rest track point data are divided into a prediction data set; meanwhile, for the track point data in the training data set, manual classification is needed, and the track point data are divided into two types, namely road points and non-road points, and are used as label data in the subsequent training of a machine learning model.
The embodiment is realized as follows:
for the original data set, firstly analyzing the distribution situation of the trace points in the original data set, and selecting a plurality of different distribution modes from different spatial regions, such as: the method comprises the following steps of (1) combining trace point data in various distribution modes into a training data set by central aggregation distribution, strip-shaped distribution, irregular discrete distribution and the like, and dividing the rest trace point data into a prediction data set; meanwhile, for the track point data in the training data set, corresponding OSM data can be used, a line buffer area is generated according to a certain radius based on incomplete road network data in the OSM, the track point mark falling in the buffer area is 1, the track point mark falling outside the buffer area is 0, and based on the mark, the track points in the training data set are divided into two types of road points and non-road points and serve as label data in the subsequent training of a machine learning model.
The radius of the line buffer area can be determined according to the average radius of the branch circuits of the cell level in the city, and the radius of the road inside the cell is generally within 8 meters.
And 2, completing construction and combination of the feature set by using two dimensions of time and density for the training data set and the prediction data set respectively, and then generating the training set and the prediction set. Where the time dimension can be divided into 7 different periods of time by dividing a day, features can be constructed from three angles in terms of density: the number of the track points in the buffer area, the area of each polygon based on the Voronoi diagram and the average length of the adjacent triangle side of each track point based on the constraint Delaunay triangulation network are combined, all the characteristics and the label value corresponding to each track point are combined, and a training set is formed.
The specific construction process is as follows:
according to the travel rule of people, on the time dimension, one day is divided into 7 time intervals which are 06:00-08:00, 8:00-12:00, 12:00-14:00, 14:00-17:00, 17:00-20:00, 20:00-24:00 and 24:00-06:00 respectively; in terms of density, the buffer radius takes 3 different values according to the road conditions: 8m, 12m and 16m, performing pairwise feature combination on the radiuses of the 3 buffer areas and the 7 time periods to construct 21 features, wherein the 21 features are used for representing the density value of a certain track point in a specific time period, and the radius is 8/12/16 meters, and a quantization formula is as follows:
wherein, Radius ═ {6,8,12}, Point ═ P1,P2,....,Pn}，Time＝{(6,8),(8,12),(12,14),(14,17),(17,20),(20,24),(0,6)}，
Is shown during the time period TaLower, trace point PiAt a radius RbThe number of the track points included in the range, and the combination of different time periods and different radius characteristics are shown in the following table:
then, according to 7 different time periods, dividing the training data set into 7 parts, respectively constructing a corresponding Voronoi diagram and a constraint Delaunay triangulation network, calculating the area of each polygon in the diagram aiming at the constructed Voronoi diagram, and then calculating the reciprocal of the area, wherein as shown in FIG. 2, the invention is a part of the Voronoi diagram, the area of the polygon R corresponding to the track point P needs to be calculated, and the reciprocal of the area is combined with the time dimension to be used as 7 characteristics for expressing the neighborhood density of the track point, and the calculation formula is as follows:
in the above-mentioned formula,
representing point PiThe area of the corresponding polygon; then, for the constrained Delaunay triangulation, the average length of the adjacent triangle edge of each trace point is calculated, and as shown in fig. 3, the average length of all the adjacent edges of the trace point P is calculated, and is combined with the time dimension to serve as the other 7 characteristics for expressing the neighborhood density of the trace point, the calculation formula is as follows:
in the above formula, Neighbor _ P represents the point PiSet of all neighboring points, L representing a neighboring pointThe distances between them, such as a, b, c, d, e, f, g, h in fig. 3; and finally, combining the 35 features and the corresponding label values in the step one to generate a training set.
And 3, learning a sampling point classification model in the data set on the basis of adjusting partial parameters in the algorithm by using the generated training set and based on a RandomForestClassifier module in a Python machine learning package scimit-lean.
And 4, applying a sampling point classification model learned based on the training set to the prediction data set to identify road points and non-road points in the predicted track point data and extracting a road point set.
Step 5, constructing a constrained Delaunay triangulation network by using the road point set extracted in the step 4, dividing the triangles in the triangulation network into 3 classes according to the number of adjacent triangles, respectively corresponding to the entrance and exit of the road, the trunk of the road and the road intersection, respectively processing the triangles, and extracting the center line of the road, wherein the specific implementation process is as follows:
constructing a constrained Delaunay triangulation network on the identified road point set, and dividing triangles in the triangulation network into 3 types: only one side is provided with an adjacent triangle which is an A type, two sides are provided with an adjacent triangle which is a B type, three sides are provided with adjacent triangles which are a C type, the A type triangle is connected with the midpoint of the only adjacent side and the opposite vertex of the midpoint, the B type triangle is connected with the midpoints of two adjacent sides, the C type triangle is connected with the gravity center and the midpoints of three sides, in the searching and connecting process, the C type triangle is searched firstly and is terminated at the A type triangle or the C type triangle, and one side of the network is obtained until the C type triangle is processed; and searching from the triangle of the A class and ending at the triangle of the A class to obtain all the edges, thereby forming the road central line network.
And 6, optimizing and perfecting the center line of the road, and straightening the center line of the road near the intersection so as to finish the reconstruction of a fine road network of the closed area, wherein the specific treatment mode is as follows:
for the arc road network near the intersection, cutting straight lines with a certain length from the intersection, comparing angles of the cut remaining lines, connecting the two lines into one line when the angles of the two lines meet a certain range, and obtaining an intersection point as a node of the network when the intersection is a crossroad, so as to finally form the road network, thereby completing the reconstruction of the fine road network of the closed area.
While the present invention has been described with reference to the embodiments shown in the drawings, the present invention is not limited to the embodiments, which are illustrative and not restrictive, and it will be apparent to those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention as defined in the appended claims.
Claims (5)
1. A road network reconstruction method based on mobile phone positioning data is characterized by comprising the following steps:
step 1) obtaining an original data set, wherein the original data set comprises a training data set and a prediction data set; the original data set is track points obtained according to mobile phone positioning data;
step 2) respectively constructing and combining features of a training data set and a prediction data set by using two dimensions of time and density, and then generating the training set and the prediction set, wherein the time dimension is realized by dividing one day into 7 different time periods;
the specific steps of constructing and combining the features by using two dimensions of time and density are as follows: by analyzing the behavior pattern of people, a feature space is constructed based on the space-time density distribution difference of roads and non-roads in a closed cell, and the aggregative difference of the space-time distribution of the track points is expressed by combining three geometric features, namely the number of the track points in a buffer area, the length of the adjacent triangle sides based on a constrained Delaunay triangulation network and the area of a polygon in a Voronoi diagram, with the time dimension; constructing a classifier based on feature sets established by combining the three different geometric features and 7 different time periods to identify road points;
step 3) using the generated training set to obtain a sampling point classification model based on algorithm learning in machine learning;
step 4) applying the learned classification model to a prediction set, and dividing track points into road points and non-road points;
step 5) constructing the identified road points based on the constrained Delaunay triangulation network, which specifically comprises the following steps:
and (3) constructing a constrained Delaunay triangulation network by using a road point set formed by the road points extracted in the step (4), dividing the triangles in the triangulation network into 3 types according to the number of adjacent triangles, respectively corresponding to the entrance and exit of the road, the trunk of the road and the road intersection, respectively processing the triangles, and extracting the center line of the road, wherein the specific implementation process is as follows:
constructing a constrained Delaunay triangulation network on the identified road point set, and dividing triangles in the triangulation network into 3 types: only one side is provided with an adjacent triangle which is an A type, two sides are provided with an adjacent triangle which is a B type, three sides are provided with adjacent triangles which are a C type, the A type triangle is connected with the midpoint of the only adjacent side and the opposite vertex of the midpoint, the B type triangle is connected with the midpoints of two adjacent sides, the C type triangle is connected with the gravity center and the midpoints of three sides, in the searching and connecting process, the C type triangle is searched firstly and is terminated at the A type triangle or the C type triangle, and one side of the network is obtained until the C type triangle is processed; searching from the triangle of the A class and ending at the triangle of the A class to obtain all the edges so as to form a road central line network;
step 6) modifying the road center line according to the topological relation, thereby completing the reconstruction of the road network, which specifically comprises the following steps:
optimizing and perfecting the center line of the road, straightening the center line of the road near the intersection, and finishing the reconstruction of a fine road network of the closed area, wherein the specific treatment mode is as follows:
for the arc road network near the intersection, cutting straight lines with a certain length from the intersection, comparing angles of the cut remaining lines, connecting the two lines into one line when the angles of the two lines meet a certain range, and obtaining an intersection point as a node of the network when the intersection is a crossroad, so as to finally form the road network, thereby completing the reconstruction of the road network of the closed area.
2. Road network reconstruction method based on mobile phone positioning data according to claim 1,
the training data set in the step 1 is obtained according to the following mode: the method comprises the steps of obtaining distribution modes of track points in a plurality of closed cells, and selecting a plurality of non-overlapping small-scale areas with different track point distribution modes to form a training data set.
3. The method for reconstructing a road network based on mobile phone positioning data as claimed in claim 1, wherein said learning algorithm in step 3 comprises random forest, support vector machine.
4. The road network reconstruction method based on the mobile phone positioning data as claimed in claim 1, characterized in that for the trace point data in the training data set, corresponding OSM data is used, a line buffer area is generated according to a certain radius based on incomplete road network data in OSM, the trace point mark falling in the buffer area is 1, the trace point mark falling outside the buffer area is 0, based on this, the trace point in the training data set is divided into two types of road point and non-road point, which are used as the label data in the subsequent training of the machine learning model.
5. A road network reconstruction system based on mobile phone positioning data, characterized in that the road network reconstruction method based on mobile phone positioning data of any one of claims 1-4 is adopted to perform road network reconstruction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810361223.9A CN108920481B (en) | 2018-04-20 | 2018-04-20 | Road network reconstruction method and system based on mobile phone positioning data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810361223.9A CN108920481B (en) | 2018-04-20 | 2018-04-20 | Road network reconstruction method and system based on mobile phone positioning data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108920481A CN108920481A (en) | 2018-11-30 |
| CN108920481B true CN108920481B (en) | 2020-11-27 |
Family
ID=64404350
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810361223.9A Expired - Fee Related CN108920481B (en) | 2018-04-20 | 2018-04-20 | Road network reconstruction method and system based on mobile phone positioning data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108920481B (en) |
Families Citing this family (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109684384B (en) * | 2018-12-29 | 2023-03-28 | 太原科技大学 | Trajectory data space-time density analysis system and analysis method thereof |
| CN109934865B (en) * | 2019-03-12 | 2020-11-27 | 重庆市勘测院 | Road network central line extraction method |
| CN110008872B (en) * | 2019-03-25 | 2021-04-06 | 浙江大学 | Road network extraction method combining vehicle track and remote sensing image |
| CN110096535B (en) * | 2019-05-16 | 2021-06-29 | 北京航空航天大学 | Elastic traffic propagation mode mining method based on elastic triangle theory |
| CN110633342B (en) * | 2019-07-29 | 2022-06-17 | 武汉光庭信息技术股份有限公司 | Lane topology network generation method |
| CN110580388B (en) * | 2019-08-28 | 2023-04-07 | 北方工业大学 | Channel network extraction method based on crowd-sourced trajectory data |
| CN110688958A (en) * | 2019-09-28 | 2020-01-14 | 中国测绘科学研究院 | Intersection identification method based on GoogleLeNet neural network |
| CN110988880B (en) * | 2019-12-12 | 2021-09-07 | 南京莱斯电子设备有限公司 | Geographic information extraction and target tracking method based on SMR target track |
| CN111833630B (en) * | 2019-12-31 | 2022-06-17 | 北京嘀嘀无限科技发展有限公司 | Method and device for determining data release position, storage medium and electronic equipment |
| CN111426329B (en) * | 2020-03-12 | 2021-10-22 | 深圳小库科技有限公司 | Road generation method and device, computer equipment and storage medium |
| CN112013862B (en) * | 2020-07-31 | 2022-06-17 | 深圳大学 | Pedestrian network extraction and updating method based on crowdsourcing trajectory |
| SG10202007346XA (en) | 2020-08-01 | 2020-10-29 | Grabtaxi Holdings Pte Ltd | Processing apparatus and method for generating route navigation data |
| CN112566025B (en) * | 2020-12-10 | 2021-10-01 | 南京市城市与交通规划设计研究院股份有限公司 | Bus passenger flow source destination identification method and device, electronic equipment and storage medium |
| CN113008251B (en) * | 2021-02-22 | 2022-11-25 | 湖南大学 | Digital map updating method for unstructured roads in closed area |
| CN112598724B (en) * | 2021-03-01 | 2021-06-01 | 武大吉奥信息技术有限公司 | Improved TIN-based vector data center line extraction method |
| CN113052084A (en) * | 2021-03-26 | 2021-06-29 | 中国地质大学（武汉） | Community-level vector road network extraction method based on mobile phone positioning data |
| CN117891892B (en) * | 2024-03-14 | 2024-05-31 | 南京师范大学 | Forest guard track optimization method based on historical patrol data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069824A (en) * | 2015-08-11 | 2015-11-18 | 中南大学 | GPS data based automatic construction method and system for open-pit mine road network |
| CN106528740A (en) * | 2016-11-04 | 2017-03-22 | 中科宇图科技股份有限公司 | Delaunay triangular net-based road center line extraction method |
| CN106778605A (en) * | 2016-12-14 | 2017-05-31 | 武汉大学 | Remote sensing image road net extraction method under navigation data auxiliary |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8229176B2 (en) * | 2008-07-25 | 2012-07-24 | Navteq B.V. | End user image open area maps |
-
2018
- 2018-04-20 CN CN201810361223.9A patent/CN108920481B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105069824A (en) * | 2015-08-11 | 2015-11-18 | 中南大学 | GPS data based automatic construction method and system for open-pit mine road network |
| CN106528740A (en) * | 2016-11-04 | 2017-03-22 | 中科宇图科技股份有限公司 | Delaunay triangular net-based road center line extraction method |
| CN106778605A (en) * | 2016-12-14 | 2017-05-31 | 武汉大学 | Remote sensing image road net extraction method under navigation data auxiliary |
Non-Patent Citations (2)
| Title |
|---|
| 基于众源轨迹数据的道路中心线提取;杨伟 等;《地理与地理信息科学》;20160515;第32卷(第3期);第1页、第3页 * |
| 运用约束Delaunay三角网从众源轨迹线提取道路边界;杨伟 等;《测绘学报》;20170215;第46卷(第2期);第237-240页、第243页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108920481A (en) | 2018-11-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108920481B (en) | Road network reconstruction method and system based on mobile phone positioning data | |
| CN108710875B (en) | A kind of take photo by plane road vehicle method of counting and device based on deep learning | |
| WO2018068653A1 (en) | Point cloud data processing method and apparatus, and storage medium | |
| WO2022141911A1 (en) | Roadside sensing unit-based method for quick recognition of dynamic target point cloud and point cloud segmentation | |
| CN106228808B (en) | City expressway travel time prediction method based on Floating Car space-time grid data | |
| CN102521973B (en) | A kind of mobile phone switches the road matching method of location | |
| CN102496034B (en) | High-spatial resolution remote-sensing image bag-of-word classification method based on linear words | |
| CN109189949B (en) | A kind of population distribution calculation method | |
| CN107247938A (en) | A kind of method of high-resolution remote sensing image City Building function classification | |
| CN107067781B (en) | GIS road black spot map generation method for advanced driving assistance system application | |
| CN108961758A (en) | A kind of crossing broadening lane detection method promoting decision tree based on gradient | |
| Tang et al. | Exploring urban travel patterns using density-based clustering with multi-attributes from large-scaled vehicle trajectories | |
| CN113505842B (en) | Automatic urban building extraction method suitable for large-scale regional remote sensing image | |
| CN110472999B (en) | Passenger flow mode analysis method and device based on subway and shared bicycle data | |
| CN115482355A (en) | Many-source data driven LOD 2-level city building model enhanced modeling algorithm | |
| CN113806419B (en) | Urban area function recognition model and recognition method based on space-time big data | |
| Li et al. | Fusing taxi trajectories and RS images to build road map via DCNN | |
| CN103500329A (en) | Street lamp automatic extraction method based on vehicle-mounted moving laser scanning point cloud | |
| Zheng et al. | Background noise filtering and clustering with 3D LiDAR deployed in roadside of urban environments | |
| CN111539432A (en) | Method for extracting urban road by using multi-source data to assist remote sensing image | |
| CN116129066A (en) | Automatic driving high-precision map model based on digital twin and high-precision static map manufacturing method | |
| CN113932821B (en) | Track map matching method based on continuous window average direction characteristics | |
| CN106021499B (en) | Construction land classification method and device based on volunteer geographic information | |
| CN111414878A (en) | Method and device for social attribute analysis and image processing of land parcel | |
| CN109800903A (en) | A kind of profit route planning method based on taxi track data |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201127 |