CN109979198B - Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data - Google Patents
Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data Download PDFInfo
- Publication number
- CN109979198B CN109979198B CN201910274934.7A CN201910274934A CN109979198B CN 109979198 B CN109979198 B CN 109979198B CN 201910274934 A CN201910274934 A CN 201910274934A CN 109979198 B CN109979198 B CN 109979198B
- Authority
- CN
- China
- Prior art keywords
- speed
- road
- expressway
- vehicle
- express way
- 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
- 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
- G08G1/052—Detecting movement of traffic to be counted or controlled with provision for determining speed or overspeed
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data, and the method comprises the following steps of 10) acquiring floating vehicle data near an expressway; step 20) dividing speed calculation units; step 30) distinguishing express way data and auxiliary way data; step 40) calculating the speed discreteness of the express way; step 50) modeling and analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics; step 60) provides a road network traffic safety service level evaluation method based on speed discreteness. The urban expressway vehicle speed discrete identification method explores factors influencing speed discrete characteristics in road facility characteristics, and provides an expressway traffic safety service level evaluation method by combining average speed and speed discreteness.
Description
Technical Field
The invention belongs to the field of urban expressway traffic safety prediction and management, and particularly relates to an urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data.
Background
With the vigorous development of national economy and the continuous improvement of travel demand, the holding quantity of motor vehicles is steadily increased in recent years. The number of vehicles has increased without similar explosive updates or growth of road traffic infrastructure, traffic management, etc.
The speed dispersion can reflect the speed difference among different vehicles or the speed change of the same vehicle, and the existing research shows that the speed dispersion is closely related to traffic safety, so the speed dispersion is selected as the measuring standard of the traffic safety.
In addition, previous studies on speed dispersion have generally employed experimental methods to employ a certain number of vehicles to perform data acquisition on a specific road, and the time and space coverage is not perfect. The popularization of the application of the GPS provides great convenience for solving the problem. The existing research shows that when the number of taxis accounts for 4% -6% of the traffic flow, the traffic condition of the road section where the taxis are located can be obtained through the taxis, the travel of the taxis is generally not limited by time, and the covered space range can reach the whole road network, so that the taxis can be used as floating taxis, and the GPS data of the floating taxis can be used as reliable data sources.
Disclosure of Invention
The technical problem is as follows: the technical problem to be solved by the invention is as follows: the urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data is provided. The speed dispersion distribution characteristic analysis method utilizes floating car data to calculate average speed and speed dispersion, analyzes influence factors on the speed dispersion in road facility characteristics, and provides an express way traffic safety service level evaluation method based on the average speed and the speed dispersion.
The technical scheme is as follows: in order to solve the technical problem, the invention adopts an urban expressway speed discrete identification method based on large-scale floating car data, which comprises the following steps:
step 10) acquiring floating car data near the express way: dividing the express way into a plurality of road sections according to the dividing principle that all the road sections are similar in property and the belonging length interval is [ x1, x2] m; acquiring floating car data of the area where the express way is located, and importing the floating car data and the divided express way section data into the same GIS graph; establishing a buffer area of a section of the express way, judging floating car data which spatially fall in the range of the buffer area as GPS points generated by vehicles running near the express way, and respectively storing the screened floating car data according to the section of the express way for subsequent calculation;
step 20) dividing speed calculation units: on each road section, judging the vehicle to which the GPS point belongs by using the attribute of the vehicle ID of the GPS point, and dividing the same vehicle track into a plurality of track chains by using the interval of t minutes between adjacent track points as critical time so as to eliminate the possibility that the same vehicle only judges to be a trip once when driving into the same road section for many times;
step 30) distinguishing the expressway and the auxiliary road data: because the traffic flow presents different characteristics in the peak period and the peak-balancing period, the research time period is divided into 3 parts, namely 7:00-9:00 of the early peak, 16:30-19:30 of the late peak and 12:00-14:00 of the peak-balancing period; calculating the average speed of each track chain, namely the speed sum of all adjacent point intervals is divided by the number of intervals, and endowing the average speed to each track point in the track chain, so as to obtain a peak and a flat distribution diagram of the track point speed according to the average speed; theoretically, the speed distribution of the expressway and the auxiliary road is in unimodal normal distribution, so that the speed distribution diagram is in a 'bimodal' form, the valley of the bimodal is the critical position of the intersection of the speeds of the expressway and the auxiliary road, the bimodal is selected as the critical speed for distinguishing the expressway and the auxiliary road data, and the results are stored according to road sections;
step 40) calculating the speed discreteness of the express way: the speed discreteness is divided into a road section unit and a vehicle unit, the standard deviation is adopted for the index taking the road section as the unit, and the acceleration noise is adopted for the index taking the vehicle as the unit;
step 50) modeling and analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics: carrying out field investigation or referring to an electronic map, and counting road facility characteristics of each road section; explaining the cause of the dependent variable, namely the speed discreteness; in the two speed dispersion indexes, the value integral of the acceleration noise is near 0, the logarithm of the value integral is required to be taken, and information which can be further utilized is expanded; the standard deviation of the road speed is directly adopted without further processing; respectively establishing a linear model and a logarithm-linear model, and selecting a better model from the linear model and the logarithm-linear model to further analyze influence factors of the speed discreteness of the expressway;
step 60) provides an express way traffic safety service level evaluation method based on speed discreteness: the speed dispersion can reflect the speed difference among vehicles or the speed change of the same vehicle in the driving process, key information about the safety level of the express way is provided, the key information and the average speed are selected as service level evaluation indexes, two-dimensional K-means clustering is adopted to realize service level evaluation, and the traffic safety service level of the road section is divided into n levels according to the relative values of the average speed and the speed dispersion in a clustering result.
Wherein the content of the first and second substances,
in the step 10), the floating car data must contain fields such as a car ID, GPS point generation time and longitude and latitude of the floating car.
In the step 10), the section for dividing the length of the road section, x1The value is 500, x2The value is 1000.
In the step 10), the buffer radius of the buffer area of the express way section is 100 meters.
In the step 20), the critical time for dividing the trajectory chain is selected to be 5 minutes.
In the step 50), the basis of the better model is selected as the fitting degree of the model, namely the R square, the F value and the t value of each variable.
In the step 50), the selected road facility characteristics comprise three categories of road line types, separation conditions and surrounding environments.
In the step 40), in calculating the dispersion of the speed of the expressway, the calculation formula of the standard deviation is a formula in statistics:
std denotes standard deviation, m is number of track links on road section, viFor the speed of each of the trajectory chains,
is the average speed of the track chain on the road section.
Step 40) calculating the speed dispersion of the express way, wherein the acceleration noise is defined as the acceleration change experienced by a certain vehicle in the traffic flow: suppose G1、G2、G3……GnN points, V, forming the trajectory chain12、V23、V34……V(n-1)nIs the speed between two points, T12、T23、T34……T(n-1)nFor the time between two points, T being the total time that this trajectory chain extends, then delV123、delV234、delV345……delV(n-2)(n-1)nRepresenting the change in velocity between two GPS point intervals, the time required to produce this change is also in delT123、delT234、delT345……delT(n-2)(n-1)nThe value is obtained by averaging two time intervals, namely:
since the velocity is not continuously recorded, the "acceleration noise" of the track chain cannot be obtained by an integral method, and an approximate accumulation process is required, wherein the formula is as follows, and the symbolic meaning is the same as that of the preceding formula:
has the advantages that: compared with the prior art, the technical scheme of the invention has the following beneficial effects:
1. the raw data is easy to obtain. The speed and the speed discreteness are obtained through floating car data, and manpower and material resources required by a static detection method or a traditional dynamic detection method are eliminated; the speed discreteness is adopted as the index for traffic safety, and the problems of sample deviation and the like hidden by incomplete traffic accident data are solved.
2. The expressway data screening method is convenient and effective. Theoretically, the speed distribution of the expressway and the auxiliary road is in unimodal normal distribution, so that the speed distribution graph after the two groups of data are mixed is in a 'bimodal' form, and the valley of the bimodal is the critical position of the speed intersection of the expressway and the auxiliary road. By utilizing the characteristic, the critical speed of the express way vehicle and the auxiliary way vehicle is judged and distinguished through the vehicle speed distribution diagram, and the express way GPS point screening method is established by taking the speed as a standard.
3. The evaluation method for the traffic safety service level of the express way is simple and easy to implement. Under the condition of no traffic flow data, the traffic safety service level of the expressway is measured by speed discreteness, the relationship between the traffic safety service level and the expressway is established, the two-dimensional K-means clustering is adopted to complete, and the result visibility is strong.
Drawings
Fig. 1 is a morning-evening peak velocity profile of the present invention.
Fig. 2 is a flat peak velocity profile of the present invention.
Fig. 3 is a graph of flat-peak clustering results.
Fig. 4 is a flow chart of the present invention.
Detailed Description
The technical solution of the present invention will be further described in detail with reference to the accompanying drawings and examples.
As shown in fig. 1, fig. 2 and fig. 3, the method for discretely identifying the speed of the urban expressway based on the large-scale floating car data comprises the following steps:
step 10) acquiring floating car data near the express way: the express way is divided into a plurality of road sections according to the dividing principle that all the road sections are similar in property and the belonging length interval is [ x1, x2] m. And acquiring floating car data of the region where the express way is located, and importing the floating car data and the divided express way network data into the same GIS graph. And establishing a buffer area of the section of the express way, and judging floating car data which spatially fall in the range of the buffer area as GPS points generated by vehicles running near the express way. And respectively storing the screened floating car data according to road sections for subsequent calculation.
In the step 10), the length interval of the divided road sections is [500,1000] m, and the radius of the buffer area of the road section is 100 m. The floating car data must contain fields such as vehicle ID, GPS point generation time and latitude and longitude, to obtain the distance and time of travel and calculate speed. The expressway network data needs to be obtained by deleting other irrelevant roads in the whole road network, and meanwhile, the tunnel part does not fall into the research range because the GPS data points cannot be normally generated when the vehicle runs in the tunnel.
Step 20) dividing speed calculation units: on each road section, the vehicle to which the point belongs is judged by the attribute of the vehicle ID of the GPS point. Meanwhile, the interval of t minutes between adjacent track points is taken as critical time, the same vehicle track is divided into a plurality of track chains, and the possibility that the same vehicle only judges to be a trip when the same vehicle drives into the same road section for a plurality of times is eliminated.
In step 20), the critical time for dividing the track chain is selected to be 5 minutes. If the limit of critical time is not adopted, the same vehicle drives into the same road section for multiple times, the interval time between the driving time and the driving time is counted as running time, and the speed is too low. The critical time selection standard is formulated according to the road section length and the express way speed limit, and the vehicle can be ensured to drive through the distance of the road section length within the critical time limit.
Step 30) distinguishing the expressway and the auxiliary road data: since the traffic flow exhibited different characteristics at peak and peak-average times, the study period was divided into 3 parts, early peak (7:00-9:00), late peak (16:30-19:30) and peak-average (12:00-14:00), respectively. The average speed of each track chain, i.e. the sum of the speeds of all adjacent point intervals divided by the number of intervals, is calculated and assigned to each track point in the track chain. Based on the above, the velocity distribution diagram (divided into high peak and flat peak) of the trace point is calculated. Theoretically, the speed distribution of the expressway and the auxiliary road is in unimodal normal distribution, the speed distribution diagram is in a 'bimodal' form, the valley of the bimodal is the critical position where the speeds of the expressway and the auxiliary road meet, the bimodal valley is selected as the critical speed for screening the expressway data, and the results are stored according to road sections.
Step 40) calculating the speed discreteness of the express way: the speed dispersion is divided into a road section unit and a vehicle unit. The standard deviation is used for the index in units of road sections, and the "acceleration noise" is used for the index in units of vehicles.
The calculation formula of the standard deviation is a formula in statistics:
std denotes standard deviation, m is number of track links on road section, viFor the speed of each of the trajectory chains,
is the average speed of the track chain on the road section.
"acceleration noise" is defined as the change in acceleration experienced by a vehicle in the traffic flow: suppose G1、G2、G3……GnN points, V, forming the trajectory chain12、V23、V34……V(n-1)nIs the speed between two points, T12、T23、T34……T(n-1)nFor the time between two points, T being the total time that this trajectory chain extends, then delV123、delV234、delV345……delV(n-2)(n-1)nRepresenting the change in velocity between two GPS point intervals, the time required to produce this change is also in delT123、delT234、delT345……delT(n-2)(n-1)nIs expressed by two timesThe inter-interval averaging is carried out, namely:
since the velocity is not continuously recorded, the "acceleration noise" of the track chain cannot be obtained by an integral method, and an approximate accumulation process is required, wherein the formula is as follows, and the symbolic meaning is the same as that of the preceding formula:
step 40), the derivation of the calculation formula of "accelerated noise" is described in the literature "Traffic Dynamics: Analysis of stability in Car fouling" Herman R, Montrol E, et al, 1959.Operation Research.
Step 50) modeling and analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics: and carrying out field investigation or referring to an electronic map to count the road facility characteristics of each road section. The cause of the dependent variable, namely the speed discreteness, is explained. In the two speed dispersion indexes, the value integral of the acceleration noise is near 0, the logarithm of the value integral is required to be taken, and information which can be further utilized is expanded; and the standard deviation of the road speed is directly adopted without further processing. And respectively establishing a linear model and a logarithmic-linear model, and selecting a better model from the linear model and the logarithmic-linear model to further analyze influence factors of the speed discreteness of the expressway.
In step 50), the road facility characteristics comprise three main categories of road line types, separation conditions and surrounding environments. The road line type comprises the length of a road section, the number of lanes of the road section, whether the road section is a flat curve or not and the like; the separation conditions include a median banding type and the like; the surrounding environment includes the land property, the number of entrances and exits, the number of secondary access points, and the like. The road section length is read through the GIS, and other characteristics need to be obtained through field investigation or an electronic map.
Step 60) provides a road network traffic safety service level evaluation method based on speed discreteness: the speed dispersion can reflect the speed difference among vehicles or the speed change of the same vehicle in the driving process, key information about the safety level of the express way is provided, the key information and the average speed are selected as service level evaluation indexes, two-dimensional K-means clustering is adopted to realize service level evaluation, and the traffic safety service level of the road section is divided into n levels according to the relative values of the average speed and the speed dispersion in a clustering result. n is preferably 4, i.e. class 4 service level: the level 1 is that the average speed and the standard deviation of the speed are both high, the vehicles run freely, the mutual influence is hardly generated, and the driver can freely select the speed on the basis of meeting the speed limit. And 2, the average speed is reduced, the mutual influence among vehicles is gradually enhanced, the speeds are relatively close, and the traffic flow is stable. At level 3, the average speed is further reduced, but the speeds between vehicles are less balanced and the traffic flow is still more stable. And 4, the average speed and the standard deviation of the speed are lower, the traffic flow is not smooth, and the traffic flow can be unstable.
The urban expressway speed discrete identification method based on large-scale floating vehicle data is divided into two parts: analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics, and providing a road network traffic safety service level evaluation method based on speed discreteness. These two parts are premised on the calculation of the speed of the highway and the speed dispersion.
The velocity calculation is in units of a trajectory chain. And after the average speed of all GPS points on the track chain is obtained, counting the speed distribution map of all GPS points to determine the critical speed and screen out the points on the express way. The velocity dispersion adopts two indexes: the road section is taken as a unit and the vehicle is taken as a unit, namely the standard deviation of the speed of the road section and the acceleration noise of the single vehicle. And selecting one with better fitting degree in subsequent modeling analysis.
And analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics, and respectively adopting a linear model and a logarithmic-linear model for the two speed discrete indexes so as to fully utilize the information in the two speed discrete indexes.
The evaluation of the traffic safety service level of the express way based on the speed discreteness takes the dependent variable and the average speed of the person with better fitting degree in the two models as indexes, and the traffic safety service level is divided by adopting K-means two-dimensional clustering.
Examples
The invention is further explained by taking the Nanjing inner loop express way as a research carrier and combining the floating car data of the taxi in the Nanjing city.
The inner circus west line is in the construction period of 'overhead tunnel change' in the research period, does not belong to the normal traffic state, and is excluded from the research range together with the tunnel part. According to the division standard, the normal road section is divided into 15 sections, and a buffer area is established by taking 100 meters as a radius.
67126 pieces of data were extracted in the GIS using a buffer. The critical speed of screening the express way data is determined to be 20km/h through the speed distribution diagram (figure 1 and figure 2). After screening, 1744 quick track points, 3067 flat peaks and 5276 late peaks of 15 road sections in the early peak period are obtained.
The modeling finds that the fitting degree of the standard deviation of the road speed is better than the acceleration noise. Taking a flat peak model as an example, all variables are obvious, and the existence (bus _ stop) of a secondary road bus station in the variables has the largest influence on speed discreteness.
TABLE 1
Based on the method, in the urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data, the standard deviation of the vehicle speed of a road section is selected as another index besides the average speed. The service level of the road is dynamically changed, the time span of research is considered to be reduced, and the road traffic safety service level of each time period is described as accurately as possible: on the basis of the original study, division of the study period was performed at 15-minute intervals, resulting in 120(15 × 8) samples. And performing K-means clustering analysis to obtain the traffic safety service level of each road section.
The evaluation results of the road sections can be seen from fig. 3, and the numerical labels in the figure are the corresponding grades. In more than 50% of cases, the traffic flow is in a stable state (in levels 1, 2 and 3), and the road traffic safety service level is better and is consistent with the reality. The method of the invention has practical engineering application value.
Claims (4)
1. A method for discretely identifying urban expressway vehicle speed based on large-scale floating vehicle data is characterized by comprising the following steps of:
step 10) acquiring floating car data near the express way: dividing the express way into a plurality of road sections according to the dividing principle that all the road sections are similar in property and the belonging length interval is [ x1, x2] m; acquiring floating car data of the area where the express way is located, and importing the floating car data and the divided express way section data into the same GIS graph; establishing a buffer area of a section of the express way, judging floating car data which spatially fall in the range of the buffer area as GPS points generated by vehicles running near the express way, and respectively storing the screened floating car data according to the section of the express way for subsequent calculation;
step 20) dividing speed calculation units: on each road section, judging the vehicle to which the GPS point belongs by using the attribute of the vehicle ID of the GPS point, and meanwhile, dividing the same vehicle track into a plurality of track chains by using the interval of t minutes between adjacent track points as critical time so as to eliminate the possibility that the same vehicle only judges to be a trip once when driving into the same road section for many times;
step 30) distinguishing the expressway and the auxiliary road data: because the traffic flow presents different characteristics in the peak period and the peak-balancing period, the research time period is divided into 3 parts, namely 7:00-9:00 of the early peak, 16:30-19:30 of the late peak and 12:00-14:00 of the peak-balancing period; calculating the average speed of each track chain, namely the speed sum of all adjacent point intervals is divided by the number of intervals, and endowing the average speed to each track point in the track chain, so as to obtain a peak and a flat distribution diagram of the track point speed according to the average speed; theoretically, the speed distribution of the expressway and the auxiliary road is in unimodal normal distribution, so that the speed distribution diagram is in a 'bimodal' form, the valley of the bimodal is the critical position of the intersection of the speeds of the expressway and the auxiliary road, the bimodal is selected as the critical speed for distinguishing the expressway and the auxiliary road data, and the results are stored according to road sections;
step 40) calculating the speed discreteness of the express way: the speed discreteness is divided into a road section unit and a vehicle unit, the standard deviation is adopted for the index taking the road section as the unit, and the acceleration noise is adopted for the index taking the vehicle as the unit;
step 50) modeling and analyzing the influence of the road facility characteristics on the speed discrete space distribution characteristics: carrying out field investigation or referring to an electronic map, and counting road facility characteristics of each road section; explaining the cause of the dependent variable, namely the speed discreteness; in the two speed dispersion indexes, the value integral of the acceleration noise is near 0, the logarithm of the value integral is required to be taken, and information which can be further utilized is expanded; the standard deviation of the road speed is directly adopted without further processing; respectively establishing a linear model and a logarithm-linear model, and selecting a better model from the linear model and the logarithm-linear model to further analyze influence factors of the speed discreteness of the expressway;
step 60) provides an express way traffic safety service level evaluation method based on speed discreteness: the speed dispersion can reflect the speed difference among vehicles or the speed change of the same vehicle in the driving process, key information about the safety level of the express way is provided, the speed dispersion and the average speed are selected as service level evaluation indexes, two-dimensional K-means clustering is adopted to realize service level evaluation, and the traffic safety service level of the road section is divided into n levels according to the relative values of the average speed and the speed dispersion in a clustering result;
in the step 10), the floating car data must contain a car ID, GPS point generation time and latitude and longitude fields;
in the step 20), the critical time for dividing the track chain is selected to be 5 minutes;
in the step 50), the basis of selecting a better model is the model fitting degree, namely R2F value and t value for each variable;
in the step 40), in calculating the dispersion of the speed of the expressway, the calculation formula of the standard deviation is a formula in statistics:
std denotes standard deviation, m is number of track links on road section, viFor the speed of each of the trajectory chains,
the average speed of the track chain on the road section is obtained;
step 40) calculating the speed dispersion of the express way, wherein the acceleration noise is defined as the acceleration change experienced by a certain vehicle in the traffic flow: suppose G1、G2、G3……GnN points, V, forming the trajectory chain12、V23、V34……V(n-1)nIs the speed between two points, T12、T23、T34……T(n-1)nFor the time between two points, T being the total time that this trajectory chain extends, then delV123、delV234、delV345……delV(n-2)(n-1)nRepresenting the change in velocity between two GPS point intervals, the time required to produce this change is also in delT123、delT234、delT345……delT(n-2)(n-1)nIt is expressed by averaging two time intervals, namely:
since the velocity is not continuously recorded, the "acceleration noise" of the track chain cannot be obtained by an integral method, and an approximate accumulation process is required, wherein the formula is as follows, and the symbolic meaning is the same as that of the preceding formula:
2. the method for discretely identifying the speed of the urban expressway based on the large-scale floating car data according to claim 1, wherein in the step 10), the interval for dividing the length of the road section x1The value is 500, x2The value is 1000.
3. The method for discretely identifying the speed of the urban expressway based on the large-scale floating car data according to claim 1, wherein in the step 10), the buffer radius of the buffer area of the expressway section is 100 meters.
4. The method for discretely identifying the speed of the urban expressway according to the large-scale floating vehicle data as recited in claim 1, wherein the selected road facility characteristics in the step 50) comprise three categories, namely a road line type, a separation condition and a surrounding environment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274934.7A CN109979198B (en) | 2019-04-08 | 2019-04-08 | Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274934.7A CN109979198B (en) | 2019-04-08 | 2019-04-08 | Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109979198A CN109979198A (en) | 2019-07-05 |
| CN109979198B true CN109979198B (en) | 2021-07-09 |
Family
ID=67083277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910274934.7A Active CN109979198B (en) | 2019-04-08 | 2019-04-08 | Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109979198B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112382090A (en) * | 2020-11-11 | 2021-02-19 | 北京百度网讯科技有限公司 | Method, apparatus, device and storage medium for outputting information |
| CN113192342B (en) * | 2021-04-27 | 2022-03-22 | 中山大学 | Method for determining percentage vehicle speed of urban road in free flow state based on floating vehicle data |
| CN113971882A (en) * | 2021-10-14 | 2022-01-25 | 武汉工程大学 | Database-based traffic flow data analysis system and method and electronic equipment |
Family Cites Families (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6662141B2 (en) * | 1995-01-13 | 2003-12-09 | Alan R. Kaub | Traffic safety prediction model |
| CN100456335C (en) * | 2006-10-12 | 2009-01-28 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
| CN101710449A (en) * | 2009-12-04 | 2010-05-19 | 吉林大学 | Traffic flow running rate recognizing method based on bus GPS data |
| CN103632540B (en) * | 2012-08-20 | 2015-11-25 | 同济大学 | Based on the major urban arterial highway traffic circulation information processing method of floating car data |
| CN104978492A (en) * | 2015-07-09 | 2015-10-14 | 彩虹无线（北京）新技术有限公司 | Safety driving evaluation method based on telematics data flow |
| US9558660B1 (en) * | 2015-07-31 | 2017-01-31 | Here Global B.V. | Method and apparatus for providing state classification for a travel segment with multi-modal speed profiles |
| CN105261212B (en) * | 2015-09-06 | 2018-06-19 | 中山大学 | A kind of trip space-time analysis method based on GPS data from taxi map match |
| US9595191B1 (en) * | 2015-11-12 | 2017-03-14 | Lytx, Inc. | Traffic estimation |
| CN106600958B (en) * | 2016-11-29 | 2019-05-17 | 北京掌行通信息技术有限公司 | Dynamic road condition expression and device |
| CN108242147B (en) * | 2016-12-27 | 2020-06-16 | 杭州海康威视***技术有限公司 | Traffic road condition estimation method, device and system |
| US20180286224A1 (en) * | 2017-04-04 | 2018-10-04 | Gregory Brodski | System and method of traffic survey, traffic signal retiming and traffic control |
| CN107067722B (en) * | 2017-04-24 | 2020-04-21 | 中国汽车技术研究中心 | Method for constructing vehicle running condition |
| CN107067729A (en) * | 2017-06-30 | 2017-08-18 | 广东工业大学 | A kind of urban road traffic safety state evaluating method |
| CN107248283B (en) * | 2017-07-18 | 2018-12-28 | 北京航空航天大学 | A kind of urban area road network evaluation of running status method considering section criticality |
| CN109035758B (en) * | 2018-05-20 | 2021-01-15 | 北京工业大学 | Urban road network intersection congestion identification method based on floating car data grid mapping |
| CN109360418B (en) * | 2018-10-31 | 2021-02-12 | 同济大学 | Urban expressway service level grading method based on vehicle speed discrete characteristics |
| CN109544932B (en) * | 2018-12-19 | 2021-03-19 | 东南大学 | Urban road network flow estimation method based on fusion of taxi GPS data and gate data |
-
2019
- 2019-04-08 CN CN201910274934.7A patent/CN109979198B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN109979198A (en) | 2019-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107330217B (en) | Mesoscopic oil consumption prediction method based on RBFNN | |
| CN109979198B (en) | Urban expressway vehicle speed discrete identification method based on large-scale floating vehicle data | |
| CN111612670B (en) | Method, device and computer equipment for constructing emission list of motor vehicle | |
| CN104700646A (en) | Online GPS data based abnormal taxi track real-time detection method | |
| CN108062857B (en) | Prediction technique for cab-getter's trip purpose | |
| Jin et al. | Assessment of expressway traffic safety using Gaussian mixture model based on time to collision | |
| CN106846806A (en) | Urban highway traffic method for detecting abnormality based on Isolation Forest | |
| Aziz et al. | Identifying and characterizing truck stops from GPS data | |
| CN105913668A (en) | Directional fake-licensed car detection method based on vast traffic data statistics | |
| CN111047179A (en) | Vehicle transportation efficiency analysis method based on frequent pattern mining | |
| Zhai et al. | Comparative analysis of drive-cycles, speed limit violations, and emissions in two cities: Toronto and Beijing | |
| CN106126637A (en) | A kind of vehicles classification recognition methods and device | |
| Zhang et al. | An improved method for evaluating eco-driving behavior based-on speed-specific vehicle-specific power distributions | |
| CN108665084A (en) | A kind of prediction technique and system to driving risk | |
| He et al. | [Retracted] Visualization and Analysis of Mapping Knowledge Domain of Heterogeneous Traffic Flow | |
| CN111444286B (en) | Long-distance traffic node relevance mining method based on trajectory data | |
| CN113379162B (en) | Method for estimating running quantity of motor vehicle on rural highway | |
| CN116061953A (en) | Truck dangerous driving behavior discrimination evaluation method based on driving track data | |
| CN107248282A (en) | The method for obtaining road running status grade | |
| CN113393011A (en) | Method, apparatus, computer device and medium for predicting speed limit information | |
| Hu et al. | Evaluating Bicycling Environments with Trajectory Data on Shared Bikes: A Case Study of Beijing | |
| CN117238131B (en) | Traffic flow characteristic analysis method in Internet of vehicles environment | |
| Xu et al. | Fast Safety Assessment and Correction Framework for Maintenance Work Zones | |
| CN113903169B (en) | Traffic optimization method and device, electronic equipment and storage medium | |
| CN117037466A (en) | Expressway traffic state determining method and system based on portal 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 |