CN110400461B - Road network change detection method - Google Patents
Road network change detection method Download PDFInfo
- Publication number
- CN110400461B CN110400461B CN201910659719.9A CN201910659719A CN110400461B CN 110400461 B CN110400461 B CN 110400461B CN 201910659719 A CN201910659719 A CN 201910659719A CN 110400461 B CN110400461 B CN 110400461B
- Authority
- CN
- China
- Prior art keywords
- intersection
- track data
- data points
- vehicle track
- road
- 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
- 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
- G08G1/0108—Measuring and analyzing of parameters relative to traffic conditions based on the source of data
- G08G1/0112—Measuring and analyzing of parameters relative to traffic conditions based on the source of data from the vehicle, e.g. floating car data [FCD]
-
- 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
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Remote Sensing (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
A road network change detection method belongs to the technical field of intelligent traffic. The method comprises step S01, collecting vehicle track data points, and sorting by time; step S02, calculating the difference value of two vehicle track data points adjacent in time, and determining and reserving the vehicle track data points for turning at the intersection; step S03, clustering vehicle track data points turning at the intersection, and identifying urban intersections and intersection types; and step S04, comparing the intersection information obtained in the step S03 with the intersection information on the map, and sending a road change signal to the gate end of the mapping department when judging that the new road and the lost road exist, so that the mapping department can update the road network map. The invention has comprehensive detection information, can find not only newly added roads but also lost roads, and really realizes real-time detection of road network change.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and particularly relates to a road network change detection method.
Background
The updating period of the electronic map is generally long, for example, the GOOGLE map electronic map is generally updated once a year, and the Baidu map can be updated once a half year, but the updating period is far from the requirement of the user. As is known, the speed of urbanization in china is fast, roads are updated frequently, new roads are continuously repaired and put into use, and some roads disappear due to area planning or real estate development. However, the conventional map network updating method requires a surveying and mapping institute to send a special detection vehicle to the urban network for detection, and the method is time-consuming and requires a large amount of manpower. The method is also difficult to identify because roads in the remote sensing image are possibly blocked by buildings or trees, and the image processing and calculation cost is high.
In recent years, experts in China propose to find new roads based on floating car track data, and firstly, a car road matching algorithm is used. For example, the invention patent application cn201610458509.x discloses a method for selecting a K-means initial clustering center for taxi track data, which is characterized in that a road network matched with a taxi is arranged, and then a newly added road is detected according to whether a large number of vehicle tracks are not matched with the road network of a map. The method can really detect the newly added road in real time by using the vehicle track data, and can find whether the newly added road exists every day. However, the method firstly needs a complex vehicle-road matching algorithm (i.e. matching from a track to a road), and at present, only new roads can be found, and the timely finding of lost roads cannot be achieved.
Disclosure of Invention
The invention provides a road network change detection method aiming at the problems in the prior art, which can find new or lost roads in real time so as to be used by a surveying and mapping department end to effectively detect the roads in time and complete real-time map updating.
The invention is realized by the following technical scheme:
the invention provides a road network change detection method, which comprises the following steps:
step S01, collecting vehicle track data points and sequencing the data points according to time;
step S02, calculating the difference value of two vehicle track data points adjacent in time, and determining and reserving the vehicle track data points for turning at the intersection;
step S03, clustering vehicle track data points turning at the intersection, and identifying urban intersections and intersection types;
and step S04, comparing the intersection information obtained in the step S03 with the intersection information on the map, and sending a road change signal to the gate end of the mapping department when judging that the new road and the lost road exist, so that the mapping department can update the road network map.
The invention can find not only newly added roads but also disappeared roads according to the vehicle running track data of one day, thereby really realizing real-time detection of road network change. In addition, the method does not need to match the vehicle track data to the road network, thereby greatly reducing the calculation cost and improving the calculation speed. When the method is used for detecting that new roads or lost roads exist, the method gives an alarm to relevant geographic mapping departments, and the geographic mapping departments can send mapping vehicles to the new roads or lost roads for detection and verification according to the provided detection result, so that the mapping departments can be purposeful, and manpower, material resources and time are greatly reduced. Once the probe measures a changed road, real-time map updates may be provided day to day.
Preferably, the vehicle trajectory data point in step S01 includes GPS coordinates, driving speed, driving angle, and time.
Preferably, the step S02 includes:
step S21, calculating the running speed difference, the running angle difference and the time difference of two vehicle track data points adjacent in time;
step S22, when the driving speed difference, the driving angle difference and the time difference respectively meet the intersection turning conditions, determining that the vehicle track data point is the vehicle track data point of the intersection turning, otherwise, determining that the vehicle track data point does not belong to the vehicle track data point of the intersection turning;
and step S23, filtering the vehicle track data points which do not belong to the turn at the intersection and keeping the vehicle track data points of the turn at the intersection.
Preferably, the intersection turning conditions are as follows: the running speed difference is 20-60 seconds; the difference of the driving angles is larger than 90 degrees; the distance between two temporally adjacent vehicle trajectory data points exceeds 100 meters.
Preferably, the distance between two adjacent vehicle track data points in time is obtained by calculating GPS coordinates.
Preferably, the step S03 includes:
step S31, clustering vehicle track data points turning at the intersection based on a density clustering algorithm;
and step S32, automatically identifying urban intersections and intersection types according to a clustering algorithm, wherein the intersection types comprise crossroads, X-shaped intersections, Y-shaped intersections, annular intersections and T-shaped intersections.
Preferably, the step S04 includes:
step S41, acquiring the intersection information identified in step S32 and the intersection information on the map, wherein the intersection information comprises city intersections and intersection types;
and step S42, matching and comparing the intersection information identified in the step S32 with the intersection information on the map, and if a new road or a lost road exists, sending a road change signal to the door end of the mapping department.
Preferably, the condition that the newly added road exists comprises the newly added road junction and the change that the number of branches is increased in the shape of the road junction; the situations of the existence of the disappeared road comprise the reduction of the intersection and the change of the intersection shape with the branch reduction.
Preferably, the vehicle trajectory data point is a vehicle trajectory data point of a taxi.
Preferably, the vehicle trajectory data points are obtained by real-time detection of a vehicle equipped with a GPS.
The invention has the following beneficial effects:
the invention discloses a road network change detection method, which comprises the following steps:
1. the method has real-time performance, the traditional map is updated for 6 months to 1 year, the method can be updated in every day, and the updating is prompted in real time as long as the road network change is detected.
2, the calculation cost is low, the precision is high, the calculation cost for processing the remote sensing image is high, and the precision is low and the time is long because of the blockage of buildings or trees. The existing newly added road based on the track data of the floating car needs to be matched with the road network by track points at first, and the method does not need to be matched with the road. According to the method, the urban traffic intersection is detected through the driving direction change value of the taxi track data, so that the method is matched with the existing map, road network matching calculation is not needed, and accurate road network change can be realized.
And 3, the detection information is comprehensive, not only can newly added roads be found, but also lost roads can be found, and real-time detection of road network change is really realized.
4 the practicality is strong, can be used for the map to update in real time, and real-time navigation provides more real road network information for the user to practiced thrift driver's travel time, can practice thrift the cost, reduce exhaust emission, more can reduce the city and block up.
Drawings
Fig. 1 is a flow chart of a road network change detection method according to the present invention.
Detailed Description
The following are specific embodiments of the present invention and are further described with reference to the drawings, but the present invention is not limited to these embodiments.
Referring to fig. 1, a road network change detection method according to the present invention includes:
step S01, collecting vehicle track data points and sequencing the data points according to time;
step S02, calculating the difference value of two vehicle track data points adjacent in time, and determining and reserving the vehicle track data points for turning at the intersection;
step S03, clustering vehicle track data points turning at the intersection, and identifying urban intersections and intersection types;
and step S04, comparing the intersection information obtained in the step S03 with the intersection information on the map, and sending a road change signal to the gate end of the mapping department when judging that the new road and the lost road exist, so that the mapping department can update the road network map.
The vehicle track data points of the method are acquired in real time by using a vehicle provided with a GPS acquisition terminal. The vehicle collects a large amount of GPS track information during the driving process. Preferably, the vehicle selects a taxi, can travel on each road section of a city every day, and can master road information in real time.
The vehicle track data points in the step S01 include GPS coordinates, driving speed, driving angle, and time. Each taxi has its own license plate, and the license plate number is the ID of the corresponding vehicle. According to the time sequence, the vehicle track data points under the corresponding vehicle ID are arranged in time sequence to form the driving track. The driving track has non-linear motion tracks due to road limitation, such as intersection turning, turning deviation caused by lane change, driving turning deviation caused by road non-smoothness, driving turning deviation caused by position of driving destination and the like.
Due to the deviation of the above situations, if only the difference of the driving angles is detected to determine the vehicle track data point of the turn at the intersection, a detection error may occur, for example, if the vehicle track data point of the lane change during normal driving, the vehicle track data point of the parking lot, the vehicle track data point of the gas station, or other vehicle track data points not belonging to the turn at the intersection are considered, a statistical error may occur, and the addition or disappearance of the road cannot be effectively identified. For this reason, not only the difference in the travel angle but also other factors are taken into consideration.
Specifically, the step S02 includes:
step S21, calculating the running speed difference, the running angle difference and the time difference of two vehicle track data points adjacent in time;
step S22, when the driving speed difference, the driving angle difference and the time difference respectively meet the intersection turning conditions, determining that the vehicle track data point is the vehicle track data point of the intersection turning, otherwise, determining that the vehicle track data point does not belong to the vehicle track data point of the intersection turning;
and step S23, filtering the vehicle track data points which do not belong to the turn at the intersection and keeping the vehicle track data points of the turn at the intersection.
The intersection turning conditions are as follows: the running speed difference is 20-60 seconds; the difference of the driving angles is larger than 90 degrees; the distance between two temporally adjacent vehicle trajectory data points exceeds 100 meters. The special case can be eliminated only when the three conditions are met, and the vehicle track data points meeting the conditions are ensured to be the vehicle track data points of the turn at the intersection.
The running distance difference can be obtained by calculating through the Pythagorean theorem by using the GPS coordinates of two vehicle track data points, and can also be calculated by using the product of the running speed difference and the running time difference.
Specifically, the step S03 includes:
step S31, clustering vehicle track data points turning at the intersection based on a density clustering algorithm;
and step S32, automatically identifying urban intersections and intersection types according to a clustering algorithm, wherein the intersection types comprise crossroads, X-shaped intersections, Y-shaped intersections, annular intersections and T-shaped intersections.
The density-based clustering algorithm may employ a DBSCAN clustering algorithm. First, a circle is drawn with the center of each data point and the radius of eps. This circle is called the eps neighborhood of xi. Next, the points contained within this circle are counted. If the number of points inside a circle exceeds the density threshold MinPts, the center of the circle is marked as a core point, also called a core object. A point is said to be a boundary point if the number of points in the eps neighborhood of the point is less than the density threshold but falls within the neighborhood of the core point. Points that are neither core points nor boundary points are noise points. Third, all points in the eps neighborhood of core point xi are direct density through xi. Finally, if for xk, both xi and xj are made reachable by xk density, then xi and xj are said to be connected in density. Connecting together the density connected points forms our cluster. And forming all traffic intersections and intersection types of the urban road network after clustering. The traffic intersection and the intersection type form intersection information.
Specifically, the step S04 includes:
step S41, acquiring the intersection information identified in step S32 and the intersection information on the map, wherein the intersection information comprises city intersections and intersection types;
and step S42, matching and comparing the intersection information identified in the step S32 with the intersection information on the map, and if a new road or a lost road exists, sending a road change signal to the door end of the mapping department.
The situations of new roads include new intersections and the change of increased branches of the intersection shape. The situations of the existence of the disappeared road comprise the reduction of the intersection and the change of the intersection shape with the branch reduction. For example, when a straight intersection becomes an intersection, i.e., an intersection is newly added, the intersection is from nothing to there, and the intersection shape changes from one to many. The new road is considered to be added and the road change occurs. For example, when the crossroads are changed to T-shaped crossroads, the crossroad shape is reduced by one from multiple bars. The road is considered to be lost and the road change occurs. After the road change is judged, the road change signal (including intersection information and changed information) is sent to the door end of the mapping part, and the door end of the mapping part detects and confirms on the spot according to the intersection information. Once it is confirmed that the road is authentic, the measurement obtains the actual road shape and draws the road, and a map update prompt is issued.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the present invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.
Claims (3)
1. A road network change detection method is characterized by comprising the following steps:
step S01, collecting vehicle track data points and sequencing the data points according to time; the vehicle track data points comprise GPS coordinates, driving speed, driving angle and time;
step S02, calculating the difference value of two vehicle track data points adjacent in time, and determining and reserving the vehicle track data points for turning at the intersection; the method specifically comprises the following steps:
step S21, calculating the driving speed difference, the driving angle difference, the time difference and the distance of two vehicle track data points adjacent in time; the distance between two vehicle track data points adjacent to the time is obtained by calculating GPS coordinates;
step S22, when the driving speed difference, the driving angle difference and the distance respectively meet the intersection turning conditions, determining that the vehicle track data point is the vehicle track data point of the intersection turning, otherwise, determining that the vehicle track data point does not belong to the vehicle track data point of the intersection turning; the intersection turning conditions are as follows: the running speed difference is 20-60 seconds; the difference of the driving angles is larger than 90 degrees; the distance between two vehicle track data points adjacent in time exceeds 100 meters;
step S23, filtering vehicle track data points which do not belong to the turn at the intersection and reserving the vehicle track data points of the turn at the intersection;
step S03, clustering vehicle track data points turning at the intersection, and identifying urban intersections and intersection types; the method specifically comprises the following steps:
step S31, clustering vehicle track data points turning at the intersection based on a density clustering algorithm;
step S32, automatically identifying urban intersections and intersection types according to a clustering algorithm, wherein the intersection types comprise crossroads, X-shaped intersections, Y-shaped intersections, annular intersections and T-shaped intersections;
step S04, comparing the intersection information obtained in step S03 with the intersection information on the map, and sending a road change signal to the gate end of the mapping department when judging that the new road and the lost road exist, so that the mapping department can update the road network map; the method specifically comprises the following steps:
step S41, acquiring the intersection information identified in step S32 and the intersection information on the map, wherein the intersection information comprises city intersections and intersection types;
step S42, matching and comparing the intersection information identified in the step S32 with the intersection information on the map, and if a new road and a lost road exist, sending a road change signal to the door end of the mapping department; the situations of the newly added road comprise newly added intersections and the change of the increased branches of the intersection shape; the situations of the existence of the disappeared road comprise the reduction of the intersection and the change of the intersection shape with the branch reduction.
2. The road network change detection method according to claim 1, wherein said vehicle trajectory data points are vehicle trajectory data points of taxis.
3. The road network change detection method according to claim 1, wherein said vehicle trajectory data points are obtained by real-time detection of a vehicle equipped with a GPS.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910659719.9A CN110400461B (en) | 2019-07-22 | 2019-07-22 | Road network change detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910659719.9A CN110400461B (en) | 2019-07-22 | 2019-07-22 | Road network change detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110400461A CN110400461A (en) | 2019-11-01 |
| CN110400461B true CN110400461B (en) | 2021-01-12 |
Family
ID=68325284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910659719.9A Active CN110400461B (en) | 2019-07-22 | 2019-07-22 | Road network change detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110400461B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113012454A (en) * | 2019-12-20 | 2021-06-22 | 中移(上海)信息通信科技有限公司 | Map message, automatic driving method, device, equipment and medium |
| CN111127891B (en) * | 2019-12-27 | 2021-04-27 | 中国交通通信信息中心 | Road network checking method based on floating car track big data |
| CN113269964A (en) * | 2021-05-24 | 2021-08-17 | 哈尔滨翼成科技有限公司 | Lane dynamic demarcation method and equipment |
| CN116052453A (en) * | 2022-12-30 | 2023-05-02 | 广州小鹏自动驾驶科技有限公司 | Road junction determining method, device, electronic equipment and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957208A (en) * | 2010-09-09 | 2011-01-26 | 福建工程学院 | Method for discovering new road based on probe vehicle technology |
| CN102561121A (en) * | 2011-01-01 | 2012-07-11 | 谢志浩 | Now urban traffic network |
| CN105679027A (en) * | 2016-02-23 | 2016-06-15 | 衡阳师范学院 | Traffic road change condition statistic method |
| CN107170236A (en) * | 2017-06-14 | 2017-09-15 | 中山大学 | A kind of important intersection extracting method of road network based on floating car data |
| CN109215372A (en) * | 2018-10-15 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | Road network information update method, device and equipment |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104504897B (en) * | 2014-09-28 | 2017-10-31 | 北京工业大学 | A kind of analysis of intersection traffic properties of flow and vehicle movement Forecasting Methodology based on track data |
| CN105788273B (en) * | 2016-05-18 | 2018-03-27 | 武汉大学 | The method of urban intersection automatic identification based on low precision space-time trajectory data |
| CN106778605B (en) * | 2016-12-14 | 2020-05-05 | 武汉大学 | Automatic remote sensing image road network extraction method under assistance of navigation data |
| CN106840176B (en) * | 2016-12-28 | 2020-01-31 | 济宁中科先进技术研究院有限公司 | GPS time-space data increment road network real-time updating and track matching system |
-
2019
- 2019-07-22 CN CN201910659719.9A patent/CN110400461B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101957208A (en) * | 2010-09-09 | 2011-01-26 | 福建工程学院 | Method for discovering new road based on probe vehicle technology |
| CN102561121A (en) * | 2011-01-01 | 2012-07-11 | 谢志浩 | Now urban traffic network |
| CN105679027A (en) * | 2016-02-23 | 2016-06-15 | 衡阳师范学院 | Traffic road change condition statistic method |
| CN107170236A (en) * | 2017-06-14 | 2017-09-15 | 中山大学 | A kind of important intersection extracting method of road network based on floating car data |
| CN109215372A (en) * | 2018-10-15 | 2019-01-15 | 百度在线网络技术（北京）有限公司 | Road network information update method, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| 一种支持城市路网交通关系自动化的智能模型;陆锋 等;《测绘学报》;20091231;第38卷(第6期);第520-526页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110400461A (en) | 2019-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110400461B (en) | Road network change detection method | |
| CN109241069B (en) | Road network rapid updating method and system based on track adaptive clustering | |
| CN110276973B (en) | Automatic intersection traffic rule identification method | |
| CN111551958B (en) | Mining area unmanned high-precision map manufacturing method | |
| Wang et al. | Automatic intersection and traffic rule detection by mining motor-vehicle GPS trajectories | |
| CN102879003B (en) | GPS (global position system) terminal-based map matching method for vehicle position tracking | |
| CN100357987C (en) | Method for obtaining average speed of city rode traffic low region | |
| CN108961758B (en) | Road junction widening lane detection method based on gradient lifting decision tree | |
| CN107563566B (en) | Inter-bus-station operation time interval prediction method based on support vector machine | |
| CN107424410B (en) | A kind of accident detection method calculated based on route travel time | |
| CN103646187A (en) | Method for obtaining vehicle travel path and OD (Origin-Destination) matrix in statistic period | |
| US11085791B2 (en) | Method, apparatus, and computer program product for on-street parking localization | |
| CN109275121A (en) | A kind of Vehicle tracing method based on adaptive extended kalman filtering | |
| CN106097717B (en) | Signalized intersections based on the fusion of two class floating car datas are averaged transit time method of estimation | |
| Blazquez et al. | Simple map-matching algorithm applied to intelligent winter maintenance vehicle data | |
| CN107644549A (en) | A kind of parking stall identification and air navigation aid, board units, roadside unit and system | |
| CN107240264A (en) | A kind of non-effective driving trace recognition methods of vehicle and urban road facility planing method | |
| CN109147323A (en) | A kind of vehicle GPS data processing method for highway passenger and freight transportation indicator-specific statistics | |
| CN112530158B (en) | Road network supplementing method based on historical track | |
| CN109190811A (en) | A kind of car speed tracking based on adaptive extended kalman filtering | |
| CN103177585A (en) | Road turning average travel speed calculating method based on floating car data | |
| CN104900057A (en) | City expressway main and auxiliary road floating vehicle map matching method | |
| Pu et al. | Road intersection detection based on direction ratio statistics analysis | |
| CN115995151B (en) | Network vehicle-closing abnormal behavior detection method applied to city management | |
| CN114663992B (en) | Multisource data fusion expressway portal positioning method |
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 |