CN112382095B - Urban expressway traffic state estimation method based on multi-source data fusion - Google Patents
Urban expressway traffic state estimation method based on multi-source data fusion Download PDFInfo
- Publication number
- CN112382095B CN112382095B CN202011347319.3A CN202011347319A CN112382095B CN 112382095 B CN112382095 B CN 112382095B CN 202011347319 A CN202011347319 A CN 202011347319A CN 112382095 B CN112382095 B CN 112382095B
- Authority
- CN
- China
- Prior art keywords
- data
- flow
- traffic
- speed
- formula
- 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
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses an urban expressway traffic state estimation method based on multi-source data fusion, which belongs to the field of traffic control and management, and comprises the steps of firstly collecting flow and speed data detected by an expressway detector, preprocessing the data, and performing space-time fusion matching on the multi-source data by using an ArcGIS platform; then, establishing a travel vehicle speed estimation model according to the flow data; secondly, standardizing the data, and performing weighted cluster analysis on the data by determining the flow and speed weights; thirdly, establishing a congestion probability model; and finally, predicting the traffic state of the acquired real-time data according to the weighted clustering and the congestion probability.
Description
Technical Field
The invention belongs to the field of traffic control and management, and particularly relates to an urban expressway traffic state estimation method based on multi-source data fusion.
Background
How to realize accurate estimation of traffic states is a precondition for effective traffic organization management and control, and becomes an important direction and a research hotspot of traffic management research. In urban roads, urban expressways share a large number of urban trips, and in order to estimate traffic states of the urban expressways, traffic data of the urban expressways are generally acquired by a traffic management department through traffic data investigation equipment. Devices can be divided into two broad categories depending on the type: the device belongs to fixed equipment such as a fixed detector, a video collector, a traffic survey station and the like, and the device belongs to mobile equipment mainly comprising a floating car detector and the like. In consideration of the problem of equipment cost, the conventional video collector and the floating car detector are mostly used for traffic investigation in scientific research experiments, and a fixed detector is mostly installed on a part of a highway section to acquire traffic data under daily conditions. How to estimate the traffic state of the express way through data monitored by a fixed detector is a key problem of the research of the invention.
At present, two main problems exist in the estimation of the traffic flow state of the expressway, namely: because the monitored data can not avoid missing or abnormal values, how to process the data by a simpler method with strong operability, and the multi-source data has the problem of unmatched data in time or space, the multi-source data needs to be processed in the same way by a data fusion method; considering the cost of the monitor, the number of detectors arranged on one express way is not too large, the detectors are mainly arranged on the road section of the express way and near the incoming and outgoing ramps, the section traffic volume and the vehicle speed within a time interval of 5s are obtained, and how to estimate the current traffic state of the whole express way by using limited section historical data and measured data;
aiming at the problems, the invention carries out data preprocessing on historical data acquired by a detector, estimates the speed of a road section travel according to cross section flow data, determines the weight coefficients of the speed and the flow after carrying out data standardization processing, and establishes a weighted cluster analysis model and a congestion probability model to estimate the traffic state.
The document retrieval of the prior art finds that a multi-directional highway and an urban intersection are estimated aiming at the traffic state, but the highway is more safe, the traffic flow at the urban intersection is complex, and the state estimation method aiming at the multi-source data fusion of the expressway is relatively less.
Disclosure of Invention
The technical problem is as follows: aiming at the problem of urban expressway multi-source data fusion, the invention provides an expressway traffic state estimation method based on data fusion.
The technical scheme is as follows: in order to solve the technical problem, the invention provides an urban expressway traffic state estimation method based on multi-source data fusion, which comprises the following steps:
step 1: acquiring historical data collected by a detector, wherein the historical data comprises: traffic data of the entrance and the exit of the ramp of the expressway, vehicle speed data and flow data of the section of the road section.
Step 2: the method comprises the steps of obtaining a threshold range of flow data and a threshold range of vehicle speed by analyzing historical data, judging whether the historical data has an abnormal value or not, correcting the abnormal value, smoothing the data, and performing space-time matching on the multisource traffic data by using an ArcGIS platform.
And step 3: and estimating the speed of the road section travel according to the flow data of the ramp entrance and exit and the road section flow data.
And 4, step 4: and (4) carrying out standardization processing on the data, determining weight coefficients of speed and flow, and carrying out cluster analysis on historical data.
And 5: and (4) estimating the road congestion through a congestion probability model, and estimating the traffic state of the express way together with the clustering analysis in the step 4.
Step 6: and acquiring real-time traffic flow parameters for state estimation.
The step 2 comprises the following steps:
step 21: determining outliers of the flow data and velocity data by equation (1):
0≤Qt≤C·t·f (1)
in the formula: qtF represents the correction coefficient of the flow, C represents the road traffic capacity, and t represents the observation time.
The threshold range of vehicle speed is determined by equation (2):
0≤v≤vmax·f′ (2)
in the formula: v. ofmaxRepresenting the speed limit of the expressway and f' representing the correction parameter of the speed.
Smoothing the data by equations (3) - (6):
Et=ω·εt+(1-ω)·Et-1 (3)
At=ω·|εt|+(1-ω)·At-1 (4)
in the formula EtAnd AtDenotes smoothing error and smoothing absolute error, ω denotes weight coefficient, qtWhich represents the actual measured value at the time t,represents the predicted value, epsilon, at time t-1tError representing measured and predicted values, StIs a smoothed value for the t period.
Step 22: performing space matching on the data, firstly determining detailed longitude and latitude information according to the equipment ID and the installation position, converting the longitude and latitude information into plane coordinate axis information and importing the plane coordinate axis information into ArcGIS software; in time matching, according to different acquisition time intervals of detectors at different positions, data are converted into data in the same acquisition period through data processing, and fusion time ranges of different data are determined.
In the step 3, the road section travel speed is estimated according to the flow data of the ramp entrance and exit and the road section flow data, and the method comprises the following steps:
step 31: the urban expressway is segmented into a plurality of road sections, data fitting is carried out through a nonlinear least square method, time functions U (t) and D (t) of the number of upstream vehicles and downstream vehicles are respectively determined, and the average travel time is obtained by utilizing an inverse triangle idea, as shown in formulas (7) to (9):
N=U(t2)-U(t1) (8)
in the formula, U (t)2) And D (t)1) Respectively representing all vehicle numbers of upstream and downstream position points of a certain road section; n represents the total number of arriving vehicles within the acquisition time interval.
In the formula (I), the compound is shown in the specification,an estimated value of the link travel time is represented, and L represents the link length.
In the step 4, the data is standardized, the weighting coefficients of speed and flow are determined, and the historical data is subjected to cluster analysis, which comprises the following steps:
step 41: the data is normalized by a formula and processed,
in the formulaAndare all intermediate variables, qiIndicates the flow rate, viRepresenting the speed, xiAnd yiIndicating the flow and velocity after the normalization process.
Step 42: considering that the data of the flow and the speed have fluctuation and the data have correlation, the weighting coefficients of the speed and the flow are determined by an objective weighting method and are shown in a formula.
In the formula rijRepresenting the correlation coefficient of i and j, cjAnd deltajIs an intermediate variable, wjM is the number of indices.
Step 43: and (4) calculating to obtain clustering centers under different traffic states through clustering and repeated iteration according to the weight obtained in the step (52).
Step 44: determining the current traffic state by calculating the distance between each state center and the real-time data sample, as shown in the formula:
whereinI-th cluster center c representing velocityi,vAnd the jth velocity sample xj,vDistance between, ωvAnd ωqAre weights for speed and flow characteristic parameters.
In the step 5, the road congestion is estimated through the congestion probability model, and the estimation of the traffic state of the express way is performed together with the cluster analysis in the step 4, and the method comprises the following steps:
step 51: calculating the probability of the interruption (traffic jam) of the traffic flow in the next time interval according to the traffic flow speed and the traffic volume condition of the road section in the current time interval by a formula (17), and evaluating the jam probability of the road section:
in the formula: q (veh/h/ln) is the vehicle throughput per lane per hour; c (veh/h/ln) is the capacity, i.e. the traffic capacity, since traffic capacity is influenced by a number of factorsThe method comprises the following steps: weather, the number of vehicles on the upstream and the downstream, road conditions and the proportion of vehicle types, and obtaining the traffic capacity value in the same state through analyzing historical data; p (c ≦ q) is the probability that the capacity is less than the observed flow; q. q.siIs the traffic flow observed at interval i, which represents the traffic flow before the speed drop; k is a radical ofiMeans q is not less than qiThe number of time intervals of (c); diMeans that the traffic flow reaches qiNumber of time intervals when each congestion is considered individually, di1 is ═ 1; b is the congestion interval { B1,B2,..
Step 52: and performing parameter estimation on the congestion probability distribution through a maximum likelihood function, wherein the likelihood function is shown as a formula:
in the formula: f. ofc(qi) Is a statistical density function of the capacity c; fc(qi) Is the cumulative distribution function of the capacity c; n represents the number of time intervals; deltai1, including an unexamined object within time interval i; deltaiWhen 0, the non-censored object is not included in the time interval i.
Has the advantages that: compared with the prior art, the invention has the following advantages:
under the condition of multi-source data fusion, the method estimates the traffic state through a weighted cluster analysis model and a congestion probability model, and overcomes the problem that a single model is inaccurate in estimation.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
Detailed Description
The present invention is described in further detail below with reference to examples, but the embodiments of the present invention are not limited thereto. The embodiments of the present invention are not limited to the examples described above, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and they are included in the scope of the present invention.
Example 1:
step 1: acquiring historical data collected by a detector, wherein the historical data comprises: traffic data of the entrance and the exit of the ramp of the expressway, vehicle speed data and flow data of the section of the road section.
Step 2: the method comprises the steps of obtaining a threshold range of flow data and a threshold range of vehicle speed by analyzing historical data, judging whether the historical data has an abnormal value or not, correcting the abnormal value, smoothing the data, and performing space-time matching on the multisource traffic data by using an ArcGIS platform.
And step 3: and estimating the speed of the road section travel according to the flow data of the ramp entrance and exit and the road section flow data.
And 4, step 4: and (4) carrying out standardization processing on the data, determining weight coefficients of speed and flow, and carrying out cluster analysis on historical data.
And 5: and (4) estimating the road congestion through a congestion probability model, and estimating the traffic state of the express way together with the clustering analysis in the step 4.
Step 6: and acquiring real-time traffic flow parameters for state estimation.
The step 2 comprises the following steps:
step 21: determining outliers of the flow data and velocity data by equation (1):
0≤Qt≤C·t·f (1)
in the formula: qtF represents the correction coefficient of the flow, C represents the road traffic capacity, and t represents the observation time.
The threshold range of vehicle speed is determined by equation (2):
0≤v≤vmax·f′ (2)
in the formula: v. ofmaxRepresenting the speed limit of the expressway and f' representing the correction parameter of the speed.
Smoothing the data by equations (3) - (6):
Et=ω·εt+(1-ω)·Et-1 (3)
At=ω·|εt|+(1-ω)·At-1 (4)
in the formula EtAnd AtDenotes smoothing error and smoothing absolute error, ω denotes weight coefficient, qtWhich represents the actual measured value at the time t,represents the predicted value, epsilon, at time t-1tError representing measured and predicted values, StIs a smoothed value for the t period.
Step 22: performing space matching on the data, firstly determining detailed longitude and latitude information according to the equipment ID and the installation position, converting the longitude and latitude information into plane coordinate axis information and importing the plane coordinate axis information into ArcGIS software; in time matching, according to different acquisition time intervals of detectors at different positions, data are converted into data in the same acquisition period through data processing, and fusion time ranges of different data are determined.
In the step 3, the road section travel speed is estimated according to the flow data of the ramp entrance and exit and the road section flow data, and the method comprises the following steps:
step 31: the urban expressway is segmented into a plurality of road sections, data fitting is carried out through a nonlinear least square method, time functions U (t) and D (t) of the number of upstream vehicles and downstream vehicles are respectively determined, and the average travel time is obtained by utilizing an inverse triangle idea, as shown in formulas (7) to (9):
N=U(t2)-U(t1) (8)
in the formula, U (t)2) And D (t)1) Respectively representing all vehicle numbers of upstream and downstream position points of a certain road section; n represents the total number of arriving vehicles within the acquisition time interval.
In the formula (I), the compound is shown in the specification,an estimated value of the link travel time is represented, and L represents the link length.
In the step 4, the data is standardized, the weighting coefficients of speed and flow are determined, and the historical data is subjected to cluster analysis, which comprises the following steps:
step 41: the data is normalized by a formula and processed,
in the formulaAndare all intermediate variables, qiIndicates the flow rate, viRepresenting the speed, xiAnd yiIndicating the flow and velocity after the normalization process.
Step 42: considering that the data of the flow and the speed have fluctuation and the data have correlation, the weighting coefficients of the speed and the flow are determined by an objective weighting method and are shown in a formula.
In the formula rijRepresenting the correlation coefficient of i and j, cjAnd deltajIs an intermediate variable, wjM is the number of indices.
Step 43: and (4) calculating to obtain clustering centers under different traffic states through clustering and repeated iteration according to the weight obtained in the step (52).
Step 44: determining the current traffic state by calculating the distance between each state center and the real-time data sample, as shown in the formula:
whereinI-th cluster center c representing velocityi,vAnd the jth velocity sample xj,vDistance between, ωvAnd ωqAre weights for speed and flow characteristic parameters.
In the step 5, the road congestion is estimated through the congestion probability model, and the estimation of the traffic state of the express way is performed together with the cluster analysis in the step 4, and the method comprises the following steps:
step 51: calculating the probability of the interruption (traffic jam) of the traffic flow in the next time interval according to the traffic flow speed and the traffic volume condition of the road section in the current time interval by a formula (17), and evaluating the jam probability of the road section:
in the formula: q (veh/h/ln) is the vehicle throughput per lane per hour; c (veh/h/ln) is the capacity, i.e., capacity, since capacity is affected by a number of factors, including: weather, the number of vehicles on the upstream and the downstream, road conditions and the proportion of vehicle types, and obtaining the traffic capacity value in the same state through analyzing historical data; p (c ≦ q) is the probability that the capacity is less than the observed flow; q. q.siIs the traffic flow observed at interval i, which represents the traffic flow before the speed drop; k is a radical ofiMeans q is not less than qiThe number of time intervals of (c); diMeans that the traffic flow reaches qiNumber of time intervals when each congestion is considered individually, di1 is ═ 1; b is the congestion interval { B1,B2,..
Step 52: and performing parameter estimation on the congestion probability distribution through a maximum likelihood function, wherein the likelihood function is shown as a formula:
in the formula: f. ofc(qi) Is a statistical density function of the capacity c; fc(qi) Is the cumulative distribution function of the capacity c; n represents the number of time intervals; deltai1, including an unexamined object within time interval i; deltaiWhen 0, the non-censored object is not included in the time interval i.
Claims (1)
1. A multi-source data fusion urban expressway traffic state estimation method is characterized by comprising the following steps:
step 1: acquiring historical data collected by a detector, wherein the historical data comprises: traffic data of the ramp entrance and exit of the expressway, vehicle speed data and flow data of the section of the road section;
step 2: analyzing historical data to obtain an abnormal data threshold range of flow data and an abnormal data threshold range of vehicle speed, judging whether the historical data has an abnormal value or not, correcting the abnormal value, smoothing the data, and performing space-time matching on the multisource traffic data by using an ArcGIS platform;
and step 3: estimating the speed of the road section travel according to the flow data of the ramp entrance and exit and the flow data of the section cross section;
and 4, step 4: standardizing the data, determining weight coefficients of speed and flow, and performing cluster analysis on historical data;
and 5: estimating road congestion through a congestion probability model, and estimating the traffic state of the expressway together with the clustering analysis in the step 4;
step 6: acquiring real-time traffic flow parameters for state estimation;
the step 2 comprises the following steps:
step 21: determining outliers of the flow data and velocity data by equation (1):
0≤Qt≤C·t·f (1)
in the formula: qtF is the traffic volume, f is the correction coefficient of the traffic volume, C is the road traffic capacity, and t is the observation time;
the threshold range of vehicle speed is determined by equation (2):
0≤v≤vmax·f′ (2)
in the formula: v denotes velocity, vmaxThe speed limit value of the express way is represented, and f' represents a correction parameter of the speed;
smoothing the data by equations (3) - (6):
Et=ω·εt+(1-ω)·Et-1 (3)
At=ω·|εt|+(1-ω)·At-1 (4)
in the formula: etAnd AtDenotes smoothing error and smoothing absolute error, ω denotes weight coefficient, qtWhich represents the actual measured value at the time t,represents the predicted value, epsilon, at time t-1tError representing measured and predicted values, StA smoothed value for a period t;
step 22: performing space matching on the data, firstly determining detailed longitude and latitude information according to the equipment ID and the installation position, converting the longitude and latitude information into plane coordinate axis information and importing the plane coordinate axis information into ArcGIS software; in time matching, according to different acquisition time intervals of detectors at different positions, converting the acquisition time intervals into data of the same acquisition period through data processing, and determining fusion time ranges of different data;
in the step 3, the speed of the road section travel is estimated according to the flow data, and the method comprises the following steps:
step 31: the urban expressway is segmented into a plurality of road sections, data fitting is carried out through a nonlinear least square method, time functions U (t) and D (t) of the number of upstream vehicles and downstream vehicles are respectively determined, and the average travel time is obtained through an inverse function, as shown in formulas (7) to (9):
N=U(t2)-U(t1) (8)
in the formula (I), the compound is shown in the specification,U(t2) And D (t)1) Respectively representing all vehicle numbers of upstream and downstream position points of a certain road section; n represents the total number of arriving vehicles within the collection time interval;
in the formula (I), the compound is shown in the specification,an estimated value representing a link travel time, L representing a link length;
in the step 4, the data are standardized, the weight coefficients of speed and flow are determined, and historical data are subjected to cluster analysis, and the method comprises the following steps;
step 41: the data is normalized by a formula and processed,
in the formulaAndare all intermediate variables, qiIndicates the flow rate, viRepresenting the speed, xiAnd yiThe flow and the speed after the standardization treatment are shown;
step 42: considering that the data of the flow and the speed have fluctuation and the data have correlation, the weight coefficient of the speed and the flow determined by an objective weighting method is shown as the formula:
in the formula rijRepresenting the correlation coefficient of i and j, cjAnd deltajIs an intermediate variable, wjM is the number of indexes;
step 43: and (4) calculating to obtain clustering centers under different traffic states by clustering and repeated iteration according to the weight obtained in the step (42):
step 44: determining the current traffic state by calculating the distance between each state center and the real-time data sample, as shown in the formula:
whereinI-th cluster center c representing velocityi,vAnd the jth velocity sample xj,vDistance between, ωvAnd ωqWeights for speed and flow characteristic parameters;
the step 5 comprises the following steps:
step 51: according to the traffic flow speed and the traffic volume condition of the road section in the current time interval, calculating the probability of traffic jam of the traffic flow in the next time interval through a formula (17), and evaluating the jam probability of the road section:
in the formula: q is the vehicle throughput per lane per hour, with the unit veh/h/ln; c is the capacity, the unit is veh/h/ln, namely the traffic capacity; p (c ≦ q) is the probability that the capacity is less than the observed flow; q. q.siIs the traffic flow observed at interval i, which represents the traffic flow before the speed drop; k is a radical ofiMeans q is not less than qiThe number of time intervals of (c); diMeans that the traffic flow reaches qiNumber of time intervals when each congestion is considered individually, di1 is ═ 1; b is the congestion interval { B1,B2,.. };
step 52: and performing parameter estimation on the congestion probability distribution through a maximum likelihood function, wherein the likelihood function is shown as a formula:
in the formula: f. ofc(qi) Is a statistical density function of the capacity c; fc(qi) Is the cumulative distribution function of the capacity c; n represents the number of time intervals; deltai1, including an unexamined object within time interval i; deltaiWhen 0, the non-censored object is not included in the time interval i.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011347319.3A CN112382095B (en) | 2020-11-26 | 2020-11-26 | Urban expressway traffic state estimation method based on multi-source data fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011347319.3A CN112382095B (en) | 2020-11-26 | 2020-11-26 | Urban expressway traffic state estimation method based on multi-source data fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112382095A CN112382095A (en) | 2021-02-19 |
CN112382095B true CN112382095B (en) | 2021-09-10 |
Family
ID=74588518
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011347319.3A Active CN112382095B (en) | 2020-11-26 | 2020-11-26 | Urban expressway traffic state estimation method based on multi-source data fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112382095B (en) |
Families Citing this family (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113345225B (en) * | 2021-05-24 | 2023-04-11 | 郑州航空工业管理学院 | Method and system for predicting real-time road conditions of front road of logistics vehicle based on V2V communication |
CN113435658B (en) * | 2021-07-09 | 2024-04-30 | 江南大学 | Traffic flow prediction method based on space-time fusion correlation and attention mechanism |
CN113506440B (en) * | 2021-09-08 | 2021-11-30 | 四川国蓝中天环境科技集团有限公司 | Traffic state estimation method for multi-source data fusion under Lagrange coordinate system |
CN114005275B (en) * | 2021-10-25 | 2023-03-14 | 浙江交投高速公路运营管理有限公司 | Highway vehicle congestion judging method based on multi-data source fusion |
CN114093171B (en) * | 2022-01-21 | 2022-05-06 | 杭州海康威视数字技术股份有限公司 | Traffic running state monitoring method and device based on multi-source data fusion |
CN114582130B (en) * | 2022-03-15 | 2022-09-27 | 合肥工业大学 | Expressway multiphase traffic state identification method |
CN114862011B (en) * | 2022-04-29 | 2023-04-07 | 上海理工大学 | Road section time-interval traffic demand estimation method considering congestion state |
CN114999162B (en) * | 2022-08-02 | 2022-10-21 | 北京交研智慧科技有限公司 | Road traffic flow obtaining method and device |
CN115496301B (en) * | 2022-11-14 | 2023-04-07 | 广州市交通规划研究院有限公司 | Land utilization and traffic collaborative evaluation method oriented to homeland space planning |
CN116935654B (en) * | 2023-09-15 | 2023-12-01 | 北京安联通科技有限公司 | Smart city data analysis method and system based on data distribution value |
CN117058887B (en) * | 2023-10-12 | 2023-12-22 | 深圳市中智车联科技有限责任公司 | Urban traffic data acquisition method, device, equipment and medium |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101650876B (en) * | 2009-08-26 | 2011-07-06 | 重庆大学 | Method for obtaining average speed of traffic flow of urban road sections |
CN103927887B (en) * | 2014-03-18 | 2016-01-27 | 西北工业大学 | In conjunction with array FPGA traffic status prediction and the control system of discrete-velocity model |
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 |
US10922965B2 (en) * | 2018-03-07 | 2021-02-16 | Here Global B.V. | Method, apparatus, and system for detecting a merge lane traffic jam |
CN109410586B (en) * | 2018-12-13 | 2020-06-05 | 中南大学 | Traffic state detection method based on multi-metadata fusion |
CN111311907B (en) * | 2020-02-13 | 2021-05-28 | 北京工业大学 | Identification method for uncertain basic graph parameter identification based on cellular transmission model |
-
2020
- 2020-11-26 CN CN202011347319.3A patent/CN112382095B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN112382095A (en) | 2021-02-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112382095B (en) | Urban expressway traffic state estimation method based on multi-source data fusion | |
CN109544932B (en) | Urban road network flow estimation method based on fusion of taxi GPS data and gate data | |
CN114783183B (en) | Traffic situation algorithm-based monitoring method and system | |
CN104658252B (en) | Method for evaluating traffic operational conditions of highway based on multisource data fusion | |
CN111882869B (en) | Deep learning traffic flow prediction method considering adverse weather | |
CN104778837A (en) | Multi-time scale forecasting method for road traffic running situation | |
CN102081846A (en) | Expressway charge data track matching based traffic state recognition method | |
CN104809877A (en) | Expressway site traffic state estimation method based on feature parameter weighted GEFCM algorithm | |
CN111583628B (en) | Road network heavy truck traffic flow prediction method based on data quality control | |
CN113159374B (en) | Data-driven urban traffic flow rate mode identification and real-time prediction early warning method | |
CN111724590B (en) | Highway abnormal event occurrence time estimation method based on travel time correction | |
CN116631186B (en) | Expressway traffic accident risk assessment method and system based on dangerous driving event data | |
CN113436433B (en) | Efficient urban traffic outlier detection method | |
CN104794895A (en) | Multisource traffic information fusion method for expressways | |
CN110197586A (en) | A kind of express highway section congestion detection method based on multi-source data | |
CN116597642A (en) | Traffic jam condition prediction method and system | |
CN113256014B (en) | Intelligent detection system for 5G communication engineering | |
CN107730882B (en) | Road congestion prediction system and method based on artificial intelligence | |
CN111583649B (en) | Method for predicting characteristic parameters of traffic flow by using RFID (radio frequency identification) space-time data | |
CN110704789B (en) | Population dynamic measurement and calculation method and system based on 'urban superconcephalon' computing platform | |
JP2003303390A (en) | Travel time prediction method, device and program | |
CN112382087B (en) | Traffic jam prediction method | |
CN109859499B (en) | Traffic flow detection system and detection method thereof | |
CN117854285B (en) | Storm water road section identification method considering urban hydrology and traffic flow characteristics | |
CN113345220B (en) | Highway inspection vehicle tracking and prediction analysis system |
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 |