CN112148811B - Vehicle-mounted GPS track path compression method - Google Patents
Vehicle-mounted GPS track path compression method Download PDFInfo
- Publication number
- CN112148811B CN112148811B CN201910559113.8A CN201910559113A CN112148811B CN 112148811 B CN112148811 B CN 112148811B CN 201910559113 A CN201910559113 A CN 201910559113A CN 112148811 B CN112148811 B CN 112148811B
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- fitting
- road
- 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.)
- Active
Links
Images
Classifications
-
- 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
- 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
- G06F16/23—Updating
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/123—Traffic control systems for road vehicles indicating the position of vehicles, e.g. scheduled vehicles; Managing passenger vehicles circulating according to a fixed timetable, e.g. buses, trains, trams
Abstract
The invention discloses a vehicle-mounted GPS track path compression method which is used for storing massive point data returned by a vehicle terminal. According to the method, according to the sampling data of the vehicle-mounted terminal, the data comprises sampling time, longitude, latitude, vehicle direction, altitude, current vehicle speed and the like, and the steps of data preprocessing, data segmentation, same road section fusion, road section fitting, fitting data storage, database data updating and the like are performed on the sampling data. On the premise of accurately describing road change characteristics, the storage space of the database is effectively compressed. The method can be applied to a plurality of scenes such as track path compression, road scanning point data processing, lane line edge storage and the like. The method can be applied to all fields related to the discrete point fitting compression algorithm.
Description
Technical Field
The invention relates to a vehicle-mounted GPS track path compression method, in particular to a method for segmenting, fusing, fitting and decompressing GPS running track data acquired by a vehicle terminal. The method can be applied to a plurality of scenes such as track path compression, road scanning point data processing, lane line edge storage and the like. The method can be applied to all fields related to the discrete point fitting compression algorithm.
Background
With the mass increase of data collected by the vehicle terminals, the storage pressure on the database is gradually increased. Because the driving range of a vehicle driver is regional, a great deal of repeatability exists in data collected by a vehicle terminal along with the increment of time, and a great number of repeated points are stored in a database completely, so that not only is a great deal of storage space occupied, but also the characteristics of the current road cannot be accurately described.
The invention provides a compression scheme aiming at massive GPS data acquired by a vehicle-mounted terminal at present. By means of methods of data segmentation, data segmentation fusion, data fitting, data decompression and the like, the storage space of the vehicle track path database can be effectively compressed.
Disclosure of Invention
In order to solve the problem of storage of massive GPS data acquired by a vehicle terminal, the invention provides a scheme, which comprises the steps of data preprocessing, data segmentation, same road section fusion, road section fitting, fitting data storage, database data updating and the like of the sampled data of the vehicle-mounted terminal. The fitted data can be subjected to high-precision restoration of the point sequence according to precision requirements through decompression, and the storage space of the database is effectively compressed on the premise that the road change characteristics can be accurately described.
The technical scheme of the invention is as follows:
a vehicle-mounted GPS track path compression method is characterized by comprising the following steps:
step one, data preprocessing: reading GPS data information acquired by a terminal, and sequencing the data according to time to ensure the continuity of the data; for the redundancy of the local data of the vehicle caused by slow running or stagnation of the vehicle, the redundant data is removed by screening the vehicle speed; for the loss and the sudden change of the GPS data caused by the instability of signals and the influence of multipath effect when passing through a tunnel or a dense high-rise building, supplementing the lost data and removing the GPS sudden change data through comparing adjacent data points in a space domain; for the condition of overtaking or obstacle avoidance caused by the freedom of a vehicle driver during driving, removing vehicle direction mutation data by comparing adjacent data points in a time domain;
step two, data segmentation: performing time-domain adjacent equidistant r interpolation on data points after data preprocessing, calculating the curvature of each discrete point, obtaining curvature screening values 1/r and 1/(10 r) according to the interpolation distance r, segmenting the vehicle GPS track through the curvature screening values, and performing linear interpolation densification on the segmented data points;
step three, fusing the same road sections: combining every two sections of the section data after curvature segmentation, calculating the nearest distance between point points, setting a limit value of a point distance, and if a certain proportion of points of the shortest line section meet the limit value of the point distance, the two road sections are the same road section; if the point of the shortest line segment reaching a certain proportion meets the limit value of the point distance, the two road sections are the same road section; when distinguishing the road sections in different directions for merging, firstly comparing the direction values of the two road sections, if the direction values are basically the same, merging the two road sections into the same road section, otherwise, merging the two road sections into the opposite road section;
step four, road section fitting: fitting each subsection by using a polynomial of multiple degree for the data after subsection fusion; in order to avoid the phenomenon of fitting distortion caused by too fast slope increase between points, data is rotated to an optimal fitting angle; because the fault phenomenon occurs at the data connection position due to the sectional fitting, in order to ensure that the data connection position is continuous and smooth and meets the vehicle motion state, a cubic spline is used for fitting and smoothly connecting each section; for the ring-shaped road with less vehicle acquisition points after the data segmentation and fusion, adopting a fitting method of a fifth-order polynomial joint direction;
step five, data storage: numbering the fitting segments, and storing the initial longitude and latitude, the ending longitude and latitude, the front segment number, the rear segment number, the formula rotation angle and the fitting formula coefficient of the segments into a database;
step six, updating the database: and after the data collected in a time period is processed according to the steps and written into the database, decompressing and matching the data collected by the vehicle in the next time period with the data section of the stored database after the data is processed according to the steps from the first step to the third step, repeating the fourth step and updating the database.
Preferably, in the third step, the limit value is set according to the road width of the road.
Preferably, in the third step, if the limit set value of the point distance is smaller than the first threshold, the vehicle track fusion of different lanes on the same road is processed; and if the limit set value of the point distance is smaller than a second threshold value, processing vehicle track fusion of the same road, wherein the first threshold value is smaller than the second threshold value, and the first threshold value and the second threshold value are set according to specific data.
Preferably, in the second step, the curvature screening value is set according to specific data.
Preferably, in the third step, the certain proportion is 90%.
Preferably, the first threshold is 1m, and the second threshold is 10m.
Drawings
FIG. 1 is a general flow diagram of the present invention.
Fig. 2 is a vehicle running track curvature screening diagram.
Fig. 3 is a sectional view of a vehicle running track.
Fig. 4 is a vehicle travel track fitting diagram.
Fig. 5 is a diagram of the driving track of vehicles on the same road section.
FIG. 6 is a fitting graph of vehicle driving tracks in the same road section direction.
Detailed Description
In order to make the technical problems, technical solutions and advantages to be solved by the present invention clearer, the present invention will be described in detail below with reference to data of a week collected by a vehicle-mounted terminal of a vehicle.
Step one, data preprocessing: reading GPS data information acquired by a terminal, and sequencing the data according to time to ensure the continuity of the data; for the redundancy of local data of the vehicle caused by slow running or stagnation of the vehicle, screening the vehicle speed to remove the redundant data; for the loss and mutation of GPS data caused by the instability of signals and the influence of multipath effect when passing through a tunnel or a dense high-rise building, supplementing the lost data and removing the GPS mutation data by comparing adjacent data points in a spatial domain; in the case of overtaking or obstacle avoidance due to the freedom of the vehicle driver during driving, abrupt vehicle direction change data is removed by comparing adjacent data points in the time domain.
The vehicle-mounted GPS data is data returned by a vehicle terminal when a driver freely drives, and the acquisition time interval is 10s and comprises information such as acquisition time, longitude, latitude, direction, altitude, vehicle speed and the like.
(1) Data redundancy: because of the redundancy of GPS signals caused by the stagnation or low speed of the vehicle, the data with the vehicle speed less than 20km/h are rejected.
(2) Data exception: when a driver overtakes or avoids an obstacle, abnormal data are eliminated from a driving lane to another lane according to the direction mutation of adjacent points of a time domain.
(3) Data filling: and carrying out linear interpolation on data which are lost due to the fact that the vehicle passes through the tunnel or the signal-free road section according to the vehicle speed of data points at two ends of the data.
The points of the vehicle travel track curvature screening graph of fig. 2 are part of the data after data preprocessing.
Step two, data segmentation: and (3) performing time-domain adjacent equidistant r interpolation on the data points after data preprocessing, calculating the curvature of each discrete point, obtaining curvature screening values 1/r and 1/(10 r) according to the interpolation distance r, segmenting the vehicle GPS track through the curvature screening values, and performing linear interpolation densification on the segmented data points.
The road generally consists of a straight line and a curve, and the difference between the straight line and the curve is that the curvatures of data points are different, so the method for calculating the curvatures of three adjacent data points is used for road segmentation.
Calculating the curvature: since the time interval of the sampling points is 10s and the minimum vehicle speed is 20km/h, the shortest distance between two points is 55m, the distance between the points is not a fixed value, and fixed curvature screening cannot be used. The invention interpolates a calculation point p2 and two adjacent points, and calculates the curvature cur by taking points p1 and p3 which are at a distance r =10m from the p2 and utilizing an equilateral triangle theorem.
cur＝(2*√((p2-p1)^2-(p3-p1)^2))/(p2-p1)^2
Since p1 is distant from p2 by r =10m, the curvature is 1/r =0.1 when the corner is a right angle. The invention takes the curvature screening value of 0.1 to judge a right angle and 0.01 to judge a curve.
The points with darker colors in the vehicle driving track curvature screening graph in fig. 2 are points with curvature higher than 0.01, and the line segment between the two points in the vehicle driving track segmentation graph in fig. 3 is a divided road segment.
Step three, fusing the same road sections: combining every two sections of the section data after curvature segmentation, calculating the nearest distance between point points, setting a limit value of a point distance, and if 90% of points of the shortest line section meet the limit value of the point distance, the two road sections are the same road section; if 90% of points of the shortest line section meet the limit value of the point distance, the two road sections are the same road section; when distinguishing the road sections in different directions for merging, the direction values of the two road sections are compared firstly, if the direction values are basically the same, the two road sections are merged into the same road section, otherwise, the road sections are opposite.
The limit value is set according to the road width of the road. If the limit set value of the point distance is less than 1m, processing vehicle track fusion of different lanes on the same road; and if the limit set value of the point distance is less than 10m, processing vehicle track fusion of the same road.
Because the driving range of the vehicle driver is regional, a great deal of repeatability exists in data acquired by the vehicle terminal along with the increment of time, as shown in a vehicle driving track diagram of the same road section in fig. 5, the diagram is a road section diagram of multiple times of vehicle passing, and therefore the same road data needs to be fused.
(1) For the segment data after curvature segmentation, every two segments are combined with each other, and whether the difference of the directions is within 20 degrees is firstly compared. If within range, it is considered likely to be the same road segment, whereas it is unlikely to be the same road segment.
(2) And for the possible same roads, calculating the closest distance between the points, and if the distance between 90% of the shortest segment and the matching segment is less than 10m, considering that the data matching of the two segments can be fused.
Step four, road section fitting: fitting each subsection by using a polynomial of multiple degree for the data after subsection fusion; in order to avoid the phenomenon of fitting distortion caused by too fast slope increase between points, data is rotated to an optimal fitting angle; because the fault phenomenon occurs at the data connection position due to the sectional fitting, in order to ensure that the data connection position is continuous and smooth and meets the vehicle motion state, a cubic spline is used for fitting and smoothly connecting each section; for the ring-shaped road with less vehicle acquisition points after the data segmentation and fusion, adopting a fitting method of a fifth-order polynomial joint direction;
and expressing the data after segmentation fusion by using a mathematical formula on the basis of meeting the motion form of the data.
The segmented data is first rotated to place both the start and end points on the x-axis. And judging whether the segmented data is the ring-shaped data, namely one x value corresponds to a plurality of y values.
(1) If the data are not the circle data, the method uses a polynomial of multiple degrees to fit each segment, namely, the polynomial of 1 degree is fitted to the polynomial of 9 degree to fit the road section, the accuracy is higher than 90% within the error of 1m, and the fitting polynomial with the lowest fitting degree is the best fitting formula.
(2) If the data is the circle data, the invention adopts a fitting method of the fifth-order polynomial joint direction to ensure that the fitting form of the data accords with the vehicle motion state, the second derivative is 0, and the connection lines keep smooth.
(3) As the fault phenomenon occurs at the data connection position due to the sectional fitting, in order to ensure that the data connection position is continuous and smooth and meets the vehicle motion state, the invention uses cubic spline fitting to smoothly connect each section.
FIG. 4 is a fitting graph of a vehicle driving track of a vehicle part, and FIG. 6 is a fitting graph of a vehicle driving track in the same road section direction after data of the same road section track of the vehicle part are fused.
Step five, data storage: and numbering the fitting sections, and storing the initial longitude and latitude, the ending longitude and latitude, the front section number, the rear section number, the formula rotation angle and the fitting formula coefficient of the section into a database.
Step six, updating the database: and after the data collected in a time period is processed according to the steps and written into the database, the data collected by the vehicle in the later time period is decompressed and matched with the data section of the stored database after being processed according to the steps from the first step to the third step, and the fourth step is repeated and the database is updated.
The data collected by the vehicle is updated in real time, and the invention adopts one month to process the national data. Each process involves the fusion of old and new data.
Finally, it should be noted that: the above embodiment only illustrates one technical solution of the present disclosure, and although the present disclosure is described in detail by the accompanying drawings and the like, it should be understood by those of ordinary skill in the art that: modifications of some embodiments or equivalent substitutions of some features can be made without departing from the design concept of the present disclosure, and the similar embodiments can still fall within the scope of the present claims.
Claims (6)
1. A vehicle-mounted GPS track path compression method is characterized by comprising the following steps:
step one, data preprocessing: reading GPS data information acquired by a terminal, and sequencing the data according to time to ensure the continuity of the data; for the redundancy of local data of the vehicle caused by slow running or stagnation of the vehicle, screening the vehicle speed to remove the redundant data; for the loss and mutation of GPS data caused by the instability of signals and the influence of multipath effect when passing through a tunnel or a dense high-rise building, the lost data is supplemented and the GPS mutation data is removed by comparing adjacent data points in a spatial domain; for the condition of overtaking or obstacle avoidance caused by the freedom of a vehicle driver during driving, removing vehicle direction mutation data by comparing adjacent data points in a time domain;
step two, data segmentation: performing time-domain adjacent equidistant r interpolation on data points after data preprocessing, calculating the curvature of each discrete point, obtaining curvature screening values 1/r and 1/(10 r) according to the interpolation distance r, segmenting the vehicle GPS track through the curvature screening values, and performing linear interpolation densification on the segmented data points;
step three, fusing the same road sections: combining every two sections of the section data after curvature segmentation, calculating the nearest distance between point points, setting a limit value of a point distance, and if a certain proportion of points of the shortest line section meet the limit value of the point distance, the two road sections are the same road section; if the point of the shortest line segment reaching a certain proportion meets the limit value of the point distance, the two road sections are the same road section; when distinguishing the road sections in different directions for merging, firstly comparing the direction values of the two road sections, if the direction values are basically the same, merging the two road sections into the same road section, otherwise, merging the two road sections into the opposite road section;
step four, road section fitting: fitting each subsection by using a polynomial of multiple degree for the data after subsection fusion; in order to avoid the phenomenon of fitting distortion caused by too fast slope increase between points, data is rotated to an optimal fitting angle; because the fault phenomenon occurs at the data connection position due to the sectional fitting, in order to ensure that the data connection position is continuous and smooth and meets the vehicle motion state, a cubic spline is used for fitting and smoothly connecting each section; for the ring-shaped road with less vehicle acquisition points after the data segmentation and fusion, adopting a fitting method of a fifth-order polynomial joint direction;
step five, data storage: numbering the fitting segments, and storing the initial longitude and latitude, the ending longitude and latitude, the front segment number, the rear segment number, the formula rotation angle and the fitting formula coefficient of the segments into a database;
step six, updating the database: and after the data collected in a time period is processed according to the steps and written into the database, decompressing and matching the data collected by the vehicle in the next time period with the data section of the stored database after the data is processed according to the steps from the first step to the third step, repeating the fourth step and updating the database.
2. The vehicle-mounted GPS track path compression method as claimed in claim 1, wherein in the third step, the limit value is set according to the road width of the road.
3. The vehicle-mounted GPS track path compression method according to claim 2, characterized in that in the third step, if the limit set value of the point distance is smaller than a first threshold value, the vehicle track fusion of different lanes on the same road is processed; and if the limit set value of the point distance is smaller than a second threshold value, processing vehicle track fusion of the same road, wherein the first threshold value is smaller than the second threshold value, and the first threshold value and the second threshold value are set according to specific data.
4. The vehicle-mounted GPS track path compression method according to claim 1, wherein in the second step, the curvature screening value is set according to specific data.
5. The vehicle-mounted GPS trajectory path compression method according to claim 1, wherein in the third step, the certain proportion is 90%.
6. The vehicle-mounted GPS trajectory path compression method according to claim 3, wherein the first threshold is 1m and the second threshold is 10m.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910559113.8A CN112148811B (en) | 2019-06-26 | 2019-06-26 | Vehicle-mounted GPS track path compression method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910559113.8A CN112148811B (en) | 2019-06-26 | 2019-06-26 | Vehicle-mounted GPS track path compression method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112148811A CN112148811A (en) | 2020-12-29 |
| CN112148811B true CN112148811B (en) | 2023-01-10 |
Family
ID=73869692
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910559113.8A Active CN112148811B (en) | 2019-06-26 | 2019-06-26 | Vehicle-mounted GPS track path compression method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112148811B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112683286A (en) * | 2021-03-16 | 2021-04-20 | 季华实验室 | Method and system for establishing topological road network map, storage medium and electronic equipment |
| CN114841679B (en) * | 2022-06-29 | 2022-10-18 | 陕西省君凯电子科技有限公司 | Intelligent management system for vehicle running data |
| CN116578891B (en) * | 2023-07-14 | 2023-10-03 | 天津所托瑞安汽车科技有限公司 | Road information reconstruction method, terminal and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050237A (en) * | 2014-05-23 | 2014-09-17 | 北京中交兴路信息科技有限公司 | Road surveying and mapping method and road surveying and mapping system |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| WO2018219522A1 (en) * | 2017-06-01 | 2018-12-06 | Robert Bosch Gmbh | Method and apparatus for producing a lane-accurate road map |
| CN109215347A (en) * | 2018-10-22 | 2019-01-15 | 北京航空航天大学 | A kind of traffic data quality control method based on crowdsourcing track data |
| CN109870713A (en) * | 2019-01-08 | 2019-06-11 | 武汉众智鸿图科技有限公司 | A kind of GPS track curve generation method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US11144578B2 (en) * | 2015-10-28 | 2021-10-12 | International Business Machines Corporation | High performance and efficient multi-scale trajectory retrieval |
-
2019
- 2019-06-26 CN CN201910559113.8A patent/CN112148811B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104050237A (en) * | 2014-05-23 | 2014-09-17 | 北京中交兴路信息科技有限公司 | Road surveying and mapping method and road surveying and mapping system |
| CN106227726A (en) * | 2016-06-30 | 2016-12-14 | 北京航空航天大学 | A kind of path extraction method based on track of vehicle data |
| WO2018219522A1 (en) * | 2017-06-01 | 2018-12-06 | Robert Bosch Gmbh | Method and apparatus for producing a lane-accurate road map |
| CN107702716A (en) * | 2017-08-31 | 2018-02-16 | 广州小鹏汽车科技有限公司 | A kind of unmanned paths planning method, system and device |
| CN109215347A (en) * | 2018-10-22 | 2019-01-15 | 北京航空航天大学 | A kind of traffic data quality control method based on crowdsourcing track data |
| CN109870713A (en) * | 2019-01-08 | 2019-06-11 | 武汉众智鸿图科技有限公司 | A kind of GPS track curve generation method and device |
Non-Patent Citations (3)
| Title |
|---|
| An Online Trajectory Compression System Applied to Resource-Constrained GPS Devices in Vehicles;Yan Ding;《IEEE Xplore》;20181231;第1-3页 * |
| 基于排序树索引的轨迹压缩方法;林树宽;《东北大学学报》;20170807;第918-922页 * |
| 路网感知的在线轨迹压缩方法;左一萌;《软件学报》;20180425;第734-755页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112148811A (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112148811B (en) | Vehicle-mounted GPS track path compression method | |
| CN111862659B (en) | GPS track data matching and complementing method | |
| CN109186617B (en) | Method and system for automatically generating lane-level topological relation based on visual crowdsourcing data and memory | |
| EP3805703A1 (en) | Movement track reconstruction method and device, storage medium, and electronic device | |
| CN110008872B (en) | Road network extraction method combining vehicle track and remote sensing image | |
| CN107784084B (en) | Road network generation method and system based on vehicle positioning data | |
| WO2018219522A1 (en) | Method and apparatus for producing a lane-accurate road map | |
| WO2023274229A1 (en) | Vehicle trajectory deviation correction method and apparatus, and electronic device | |
| CN110174110B (en) | Map corresponding method and device, electronic equipment and computer readable medium | |
| CN103092948B (en) | A kind of super expressway shape restorative procedure being applied to Floating Car Trace Formation | |
| CN110286671B (en) | Automatic driving vehicle path generation method based on clothoid curve | |
| CN105528955A (en) | Method and device for generating road network | |
| CN108180921B (en) | AR-HUD navigation system using GPS data and navigation method thereof | |
| CN109297501B (en) | Method for automatically generating double-line network by GIS single-line network | |
| CN112818075B (en) | Road network completion method and device, electronic equipment and readable storage medium | |
| CN111177934B (en) | Method, apparatus and storage medium for reference path planning | |
| CN113822190B (en) | Factory road network data fitting method and device, electronic equipment and storage medium | |
| CN112465925A (en) | Method and device for processing lane line for simulation test | |
| CN110913345B (en) | Section passenger flow calculation method based on mobile phone signaling data | |
| EP3944193A1 (en) | Calibration device and calibration method | |
| JP2007072011A (en) | Device for creating road network data, method for creating road network data, and data structure of road network data | |
| CN111551185A (en) | Method for adding traffic lane | |
| CN116028561A (en) | High-precision map format conversion method, device and storage medium | |
| CN115326055A (en) | Method and device for rasterizing track line of surface mine road | |
| CN115731527A (en) | Road boundary detection method, apparatus, computer device and storage medium |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 710201 Jingwei Industrial Zone, Xi'an economic and Technological Development Zone, Shaanxi, China Applicant after: Shaanxi Automobile Group Co.,Ltd. Address before: 710201 Jingwei Industrial Zone, Xi'an economic and Technological Development Zone, Shaanxi, China Applicant before: SHAANXI AUTOMOBILE GROUP Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |