CN108765946B - Lane group traffic demand prediction method based on red light running automatic recording system data - Google Patents
Lane group traffic demand prediction method based on red light running automatic recording system data Download PDFInfo
- Publication number
- CN108765946B CN108765946B CN201810558335.3A CN201810558335A CN108765946B CN 108765946 B CN108765946 B CN 108765946B CN 201810558335 A CN201810558335 A CN 201810558335A CN 108765946 B CN108765946 B CN 108765946B
- Authority
- CN
- China
- Prior art keywords
- period
- vehicle
- travel time
- vehicles
- time
- 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
- 238000000034 method Methods 0.000 title claims abstract description 17
- 238000011144 upstream manufacturing Methods 0.000 claims description 23
- 238000004364 calculation method Methods 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000012216 screening Methods 0.000 claims description 4
- 238000005516 engineering process Methods 0.000 claims description 2
- 238000005259 measurement Methods 0.000 claims description 2
- 238000001514 detection method Methods 0.000 abstract description 11
- 230000007547 defect Effects 0.000 abstract description 3
- 238000005457 optimization Methods 0.000 abstract description 3
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 230000001939 inductive effect Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 229920006395 saturated elastomer Polymers 0.000 description 1
- 238000011895 specific detection Methods 0.000 description 1
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
- 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
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
-
- 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
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
- G08G1/0175—Detecting movement of traffic to be counted or controlled identifying vehicles by photographing vehicles, e.g. when violating traffic rules
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a lane group traffic demand prediction method based on red light running automatic recording system data. Firstly, acquiring the travel time of a road section through license plate matching; secondly, determining the travel time change rate of each period; then determining the virtual period duration corresponding to each period; and finally, measuring and calculating the number of the driven vehicles in each period and calculating the traffic demand of the lane group. The invention overcomes two defects based on coil detection in the prior art: the supersaturated traffic demand cannot be detected or the difference between different lane groups cannot be distinguished, and a technical basis is provided for the fine optimization of signal control.
Description
Technical Field
The invention relates to a method for predicting traffic demands of lane groups, in particular to a method for predicting traffic demands of lane groups based on data of an automatic red light running recording system, and belongs to the field of intelligent traffic research.
Background
Traffic demand is one of the basic parameters for traffic management and control. Accurate and reliable traffic demands are the premise and the basis for signal optimization, and the implementation effect of a signal scheme is directly determined. The existing control systems are all based on fixed detection equipment, such as a coil detector, a microwave detector, a video detector and the like, count the number of vehicles passing through a specific detection section in a unit time period, and regard the number of vehicles as traffic demands for traffic management and control.
At present, the arrangement positions of the fixed detection equipment are of two types, namely the fixed detection equipment is arranged at the position of an outlet channel at the upstream of a road section, and the fixed detection equipment is arranged at the position of an inlet channel at the downstream of the road section. Aiming at the first type of arrangement positions, the detector can actually detect the number of vehicles passing through the cross section in unit time, namely the actual traffic demands, but cannot identify the steering attributes of the vehicles at the downstream intersection and cannot distinguish the traffic demands of the divided lanes; for the second type of arrangement positions, the detector can distinguish the steering phases, but in an oversaturated state, part of actually arriving vehicles cannot normally pass through the downstream intersection, the number of the passing vehicles in unit time is smaller than the actual traffic demand, and the risk that the traffic demand is seriously underestimated exists.
In recent years, red light running automatic recording systems are successively arranged in major cities of China, and the system arranges video detection equipment at a position about 20 meters behind a stop line of an entrance lane and can record license plates of vehicles and time information when the vehicles pass through the stop line. The vehicle travel time information can be obtained through corresponding matching of the recorded data of the two intersections on the upstream and downstream of the road section. For a specific road section, the travel time is closely related to the traffic demand, and the larger the demand is, the higher the average travel time in a unit time interval is inevitably, and the smaller the travel time change rate between the front vehicle and the rear vehicle is inevitably. The real-time traffic demand of the lane group can thus be estimated with the travel time data of each elementary cell, using the signal cycle duration as an evaluation unit.
The invention can be directly applied to the field of traffic control, estimates the traffic demand of the lane group by utilizing the data of the automatic red light running recording system which is increasingly popularized at present, and provides a technical basis for upgrading and modifying the existing traffic control system. Meanwhile, the method realizes the information multiplexing of the red light running automatic recording system data, reduces the dependence of the urban traffic control system on the traditional detection equipment such as a ground induction coil and microwaves, and reduces the operation and maintenance cost of the whole traffic control system.
Disclosure of Invention
Aiming at the defects of the prior art, the invention provides a lane group traffic demand prediction method based on red light running automatic recording system data.
The basic idea of the invention is as follows: the traffic demand increase is a direct cause for inducing the deterioration of the traffic state, and for the downstream entrance lane of a specific road section, the larger the average travel time and the smaller the travel time change rate in the passing vehicle in the cycle are, the worse the traffic state is, and a fixed relationship exists between the average travel time and the travel time change rate in the passing vehicle in the cycle and the traffic demand. Meanwhile, as the centers of a plurality of road sections are arranged at the entrances and exits of the units, the vehicles entering and exiting the units can influence the traffic demand, the automatic red light running recording system cannot detect the related information of the vehicles, and certain errors may exist in the calculation of the average travel time. To account for the effects of this portion of the vehicle, the present invention utilizes the rate of change of travel time per unit period to estimate traffic demand.
And the driven-off vehicles of a certain lane group of the downstream approach in the period i are driven in from the upstream intersection in a certain time period range, and the ratio of the number of the driven-off vehicles to the time period range is the traffic demand of the period i. Meanwhile, the driving-in time interval and the signal period have a one-to-one correspondence relationship, and the driving-in time interval can be regarded as a virtual period of the driving-out vehicle driving into the upstream road section. Considering that the red light running automatic recording system has the detection missing phenomenon, the number of the vehicles which are automatically detected by the system and leave may be smaller, and the change rate of the travel time can be used for correction. Therefore, the traffic demand prediction method for the lane group based on the red light running automatic recording system data mainly comprises the following steps: (1) acquiring the travel time of the road section through license plate matching; (2) determining a time of flight rate of change for each cycle; (3) determining the virtual period duration corresponding to each period; (4) and measuring the number of the driven vehicles in each period and calculating the traffic demand of the lane group.
The invention has the beneficial effects that: the invention overcomes two defects based on coil detection in the prior art: the supersaturated traffic demand cannot be detected or the difference between different lane groups cannot be distinguished, and a technical basis is provided for the fine optimization of signal control. Meanwhile, the method does not need to add any detection equipment, reduces the degree of dependence on traditional ground sensing coils, microwaves and other section detection equipment while realizing system data multiplexing such as red light running automatic recording and the like, is the development direction of future traffic signal control, and provides a certain technical support for upgrading and updating of a signal control system.
Drawings
FIG. 1 is a flow chart of an algorithm implementation process;
FIG. 2 is a vehicle license plate matching traffic flow relationship diagram;
FIG. 3 travel time rate of change calculation principle
Fig. 4 shows a relationship between a virtual cycle and a blocked vehicle entrance period and a free-passing vehicle entrance period.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The basic steps of the invention are as follows:
c1, extracting data of the automatic red light running recording system of the upstream and downstream intersections by a network topological structure aiming at a certain entrance lane group, and calculating the road section travel time passing through the lane group by using a license plate matching technology.
And c2, estimating the vehicle travel time change rate influenced by the retardation according to the travel time data of the vehicle in the cycle.
c3, extracting the maximum travel time and the minimum travel time of the vehicle driving away from the upstream intersection in the period, namely the time information of the vehicle driving into the upstream road section, and calculating the virtual period duration.
c4, calculating the number of vehicles driving in the period according to the travel time change rate, and further calculating the vehicle arrival rate, namely the traffic demand according to the number of vehicles driving in the virtual period and the virtual period duration.
The process of step c1 includes:
c11, determining the corresponding upstream and downstream intersections of the specific lane group p according to the network topology structure.
c12, extracting the information of the license plate and the information of the driving time of the vehicle which drives away from the downstream intersection through the lane group p by using the automatic red light running recording system, and recording the information as the database 1.
c13, extracting the license plate information of the vehicle entering the lane group p and the driving-off time information of the upstream intersection by using the red light running automatic recording system, recording the information as a database 2, and including three traffic flows of straight driving, left-turning driving and right-turning driving, as shown in fig. 2.
c14, calculating the road section travel time of the driven vehicle through the license plate matching of the databases 1 and 2; let a be any vehicle leaving the lane group p, taAnd t'aIs the time information corresponding to the vehicle a in the databases 1 and 2, the travel time of the vehicle a is:
Ta＝ta-t′a(1-a)
in the formula, TaThe travel time of the vehicle on the road segment to which the lane group p belongs is expressed in seconds.
Step c2 includes:
c21, assuming that the current cycle is i, and m samples are in total in the i cycle, the sample set of the travel time is:
Ti＝[Ti,1,Ti,2,…,Ti,m](1-b)
in the formula, TiRun-time samples of period i, Ti,mThe travel time of the mth vehicle driving away from the vehicle in the unit of seconds is the i period.
In the sample travel time, if the individual travel time is not greater than the free stream travel time, it indicates that the vehicle is free to pass through in cycle i without being retarded by it; further, if there are samples within a period i that have a travel time that is not greater than the free stream travel time, then the period is in an unsaturated state, otherwise the period is in an oversaturated state. The free passing vehicle travel time is equal, the change rate is 0, and the traffic demand is irrelevant. Therefore, the influence of free passage through the vehicle should be eliminated when determining the travel time change rate.
c22, assuming that n total obstructed travel time samples in the period i are provided, namely m sample data, the front n are obstructed vehicles, and the rear (m-n) is a free passing vehicle, the travel time change rate can be obtained by a least square method:
in the formula, SiAs a time of flight within the period iThe chemical conversion rate is dimensionless; t is ti,jAt the time of the cycle i when the jth vehicle is driving into the road section upstream.
Specifically, when the period i is in a saturated state, the value of n is 0. The principle of step c22 is shown in fig. 3.
The process of step c3 includes:
c31 screening the maximum travel time T in the period ii,maxDetermining the driving time of the vehicle with the maximum travel time at the upstream intersection in the period i, and recording the driving time as ti,max。
c32, recording the time when the first free passing vehicle and the last free passing vehicle drive into the upstream of the road section as t respectively for m-n free passing vehicles in the period ii,n+1And ti,m。
c33 screening the maximum travel time T in the period ii,maxThe time t at which the first and last free passing vehicles pass upstream of the route sectioni,n+1And ti,mCalculating the length of the entering time period of the part of the vehicle which is influenced by the signal lamp retardation and the length of the entering time period of the part which is not influenced by the signal lamp retardation within the period i:
ci,1＝ti,n+1-ti,max(1-d)
ci,2＝ti,m-ti,n+1(1-e)
in the formula, ci,1And ci,2The length of the entering time interval of the part of the vehicle which is driven away in the period i and influenced by the signal lamp retardation and the length of the entering time interval of the part which is not influenced by the signal lamp retardation are respectively expressed in seconds.
In step c33, ci,1、ci,2And ciThe relationship between them is shown in fig. 4.
c34, using c in step c33i,1And ci,2Calculating the virtual period duration by the following calculation formula:
ci＝ci,1+ci,2(1-f)
in the formula, ciThe unit is the virtual period duration corresponding to the period i, and the unit is second.
The process of step c4 includes:
c41 according to traffic wave theoryFrom the rate of change of travel time SiMeasurement and calculation time period ci,1Number of vehicles driven inside:
in the formula, Qi,1Is ci,1The number of the vehicles driven away in a time period is in units of vehicles; k is a radical ofjamIs the congestion density in units of vehicles/meter; u. offIs the free flow velocity in meters per second; u. ofwThe unit is the wave velocity of the starting wave in meters/second; in application, kjam、ufAnd uwThe values are fixed values, the fluctuation is small in different periods, and the fluctuation can be determined through actual observation.
c42, assuming that the arrival rate of vehicles in the same virtual period, i.e. the traffic demand, is uniform, i.e. segment ci,1And ci,2If the arrival rates of the vehicles in the period i are equal, the total number of the vehicles which leave in the period i can be estimated, and the expression is as follows:
in the formula, QiThe number of vehicles which leave the downstream stop line in the period i is the unit of the vehicle.
c43, according to the concept of traffic demand, the ratio of the total number of vehicles driven away in the period i to the virtual period is the traffic demand corresponding to the period, namely:
in the formula, qiThe traffic demand for cycle i is given in units of vehicles/second.
Example (b):
taking the license plate data of two intersections of a certain road section of a certain city and the timestamp data when a vehicle passes through a stop line as an example. The data is 16:10:00 to 17:10:00, the time interval is 5 minutes, and the specific implementation flow is shown in figure 1.
1. Calculating the travel time of the road section passing through the lane group
Extracting the license plate information and the driving-off time information of the vehicles driving off the downstream intersection through the lane group p, and recording the information as a database 1; extracting the license plate information of the vehicle entering the lane group p and the driving-off time information of the upstream intersection, and recording the information as a database 2, wherein the specific distribution is shown in fig. 2; and calculating the road section travel time of the driving vehicle through the license plate matching of the databases 1 and 2.
2. Estimating vehicle travel time rate of change affected by hysteresis
The total number of samples m in the current i period, n blocked travel time samples, and the travel time sample set is: t isi＝[Ti,1,Ti,2,…,Ti,m]. The travel time change rate can be obtained by the following formula:
the effect of free passage through the vehicle should be eliminated when determining the travel time rate of change, the principle being shown in fig. 3.
3. Calculating virtual cycle duration
Calculating the length of the entering time period of the part of the vehicle which is influenced by the signal lamp retardation and the length of the entering time period of the part which is not influenced by the signal lamp retardation within the period i by the following formula:
ci,1＝ti,m+1-ti,max
ci,2＝ti,n-ti,m+1
the length of the entering time period of the part of the vehicle which is influenced by the signal lamp retardation and the length c of the entering time period of the part which is not influenced by the signal lamp retardation in the period ii,1、ci,2The relationship between them is shown in fig. 4. Calculating the virtual period duration ci。
4. Calculating vehicle arrival rate, i.e. traffic demand
The time period c is measured by the following formulai,1Number of vehicles driven inside:
and (4) the traffic demand is uniform, and the total number of vehicles driven away in the period i is estimated. And calculating the traffic demand corresponding to the period, wherein the formula is as follows:
the results are obtained as shown in the following table.
The table results show that the relative error of the invention is 16.19%, the accuracy requirement of traffic control is met, and the practical value of the invention is demonstrated.
Claims (2)
1. The lane group traffic demand prediction method based on the red light running automatic recording system data is characterized by comprising the following steps of:
c1, extracting data of the automatic red light running recording system of the upstream and downstream intersections by a network topological structure aiming at a certain entrance lane group, and calculating the road section travel time passing through the lane group by using a license plate matching technology;
c2, estimating the change rate of the vehicle travel time influenced by the retardation according to the travel time data of the vehicle in the cycle;
c3, extracting the maximum travel time and the minimum travel time of the vehicle driving away from the upstream intersection in the period, namely the time information of the vehicle driving into the upstream road section, and calculating the virtual period duration;
c4, calculating the number of vehicles driving away in a period according to the travel time change rate, and further calculating the arrival rate of the vehicles according to the number of vehicles driving into the virtual period and the virtual period duration;
step c1 specifically includes:
c11, determining the corresponding upstream and downstream intersections of the lane group p according to the network topology structure;
c12, extracting the license plate information and the driving-away time information of the vehicles driving away from the downstream intersection through the lane group p by using the red light running automatic recording system, and recording the information as a first database;
c13, extracting the license plate information of the vehicle entering the lane group p and the driving-away time information of the upstream intersection by using a red light running automatic recording system, recording the information as a second database, and containing three streams of straight driving, left-turning driving and right-turning driving;
c14, calculating the road section travel time of the driven vehicle through the matching of the license plates of the two databases; let a be any vehicle leaving the lane group p, taAnd t'aThe time information corresponding to the vehicle a in the first database and the second database is the following, and the travel time of the vehicle a is as follows:
Ta＝ta-t′a(1-a)
in the formula, TaThe travel time of the vehicle on the road section to which the lane group p belongs is second;
step c2 specifically includes:
c21, assuming that the current cycle is i, and m samples are in total in the i cycle, the sample set of the travel time is:
Ti＝[Ti,1,Ti,2,…,Ti,m](1-b)
in the formula, TiRun-time samples of period i, Ti,mThe travel time of the mth vehicle driving away from the vehicle in the i period is second;
c22, assuming that n total obstructed travel time samples in the period i are provided, namely m sample data, the front n are obstructed vehicles, and the rear (m-n) is a free passing vehicle, obtaining the travel time change rate by using a least square method:
in the formula, SiThe travel time change rate in the period i is dimensionless; t is ti,jThe time when the jth vehicle drives into the upstream of the road section in the period i;
step c3 specifically includes:
c31 screening the maximum travel time T in the period ii,maxDetermining the maximum travel time vehicle crossing upstream in the period iThe entry time of the fork entry is denoted ti,max；
c32, recording the time when the first free passing vehicle and the last free passing vehicle drive into the upstream of the road section as t respectively for m-n free passing vehicles in the period ii,n+1And ti,m；
c33 screening the maximum travel time T in the period ii,maxThe time t at which the first and last free passing vehicles pass upstream of the route sectioni,n+1And ti,mCalculating the length of the entering time period of the part of the vehicle which is influenced by the signal lamp retardation and the length of the entering time period of the part which is not influenced by the signal lamp retardation within the period i:
ci,1＝ti,n+1-ti,max(1-d)
ci,2＝ti,m-ti,n+1(1-e)
in the formula, ci,1And ci,2The length of the entering time interval of the part of the vehicle which is driven away in the period i and influenced by the signal lamp retardation and the length of the entering time interval of the part which is not influenced by the signal lamp retardation are respectively, and the unit is second;
c34, using c in step c33i,1And ci,2Calculating the virtual period duration by the following calculation formula:
ci＝ci,1+ci,2(1-f)
in the formula, ciThe unit is the virtual period duration corresponding to the period i, and the unit is second;
step c4 specifically includes:
c41 determining the travel time change rate S according to the traffic wave theoryiMeasurement and calculation time period ci,1Number of vehicles driven inside:
in the formula, Qi,1Is ci,1The number of the vehicles driven away in a time period is in units of vehicles; k is a radical ofjamIs the congestion density in units of vehicles/meter; u. offIs the free flow velocity in meters per second; u. ofwThe unit is the wave velocity of the starting wave in meters/second;
c42. assume vehicle arrival rate in the same virtual period, i.e., segment ci,1And ci,2If the arrival rates of the vehicles in the period i are equal, estimating the total number of the vehicles driven away in the period i, wherein the expression is as follows:
in the formula, QiThe number of vehicles driving away from the downstream stop line in the period i is the unit of the vehicle;
c43, according to the concept of traffic demand, the ratio of the total number of vehicles driven away in the period i to the virtual period is the traffic demand corresponding to the period, namely:
in the formula, qiThe traffic demand for cycle i is given in units of vehicles/second.
2. The method for predicting the traffic demand of the lane group based on the data of the automatic red light running recording system as claimed in claim 1, wherein: in step c2, the effect of free passage through the vehicle is rejected in determining the rate of change of travel time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810558335.3A CN108765946B (en) | 2018-06-01 | 2018-06-01 | Lane group traffic demand prediction method based on red light running automatic recording system data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810558335.3A CN108765946B (en) | 2018-06-01 | 2018-06-01 | Lane group traffic demand prediction method based on red light running automatic recording system data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108765946A CN108765946A (en) | 2018-11-06 |
| CN108765946B true CN108765946B (en) | 2020-06-16 |
Family
ID=64002164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810558335.3A Active CN108765946B (en) | 2018-06-01 | 2018-06-01 | Lane group traffic demand prediction method based on red light running automatic recording system data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765946B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6587778B2 (en) * | 1999-12-17 | 2003-07-01 | Itt Manufacturing Enterprises, Inc. | Generalized adaptive signal control method and system |
| JP2003272084A (en) * | 2002-03-15 | 2003-09-26 | Foundation For The Promotion Of Industrial Science | Travel duration predicting device and method |
| CN101046919A (en) * | 2006-10-12 | 2007-10-03 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
| CN101739814A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | SCATS coil data-based traffic state online quantitative evaluation and prediction method |
| CN103473926A (en) * | 2013-09-11 | 2013-12-25 | 无锡加视诚智能科技有限公司 | Gun-ball linkage road traffic parameter collection and rule breaking snapshooting system |
| CN104851287A (en) * | 2015-04-15 | 2015-08-19 | 浙江大学 | Method for urban road link travel time detection based on video detector |
| US9752886B2 (en) * | 2013-06-27 | 2017-09-05 | Sap Se | Mobile trip planner and live route update system |
-
2018
- 2018-06-01 CN CN201810558335.3A patent/CN108765946B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6587778B2 (en) * | 1999-12-17 | 2003-07-01 | Itt Manufacturing Enterprises, Inc. | Generalized adaptive signal control method and system |
| JP2003272084A (en) * | 2002-03-15 | 2003-09-26 | Foundation For The Promotion Of Industrial Science | Travel duration predicting device and method |
| CN101046919A (en) * | 2006-10-12 | 2007-10-03 | 华南理工大学 | Visual evaluating method for urban traffic system state based on traffic flow phase character istic and its application |
| CN101739814A (en) * | 2009-11-06 | 2010-06-16 | 吉林大学 | SCATS coil data-based traffic state online quantitative evaluation and prediction method |
| US9752886B2 (en) * | 2013-06-27 | 2017-09-05 | Sap Se | Mobile trip planner and live route update system |
| CN103473926A (en) * | 2013-09-11 | 2013-12-25 | 无锡加视诚智能科技有限公司 | Gun-ball linkage road traffic parameter collection and rule breaking snapshooting system |
| CN104851287A (en) * | 2015-04-15 | 2015-08-19 | 浙江大学 | Method for urban road link travel time detection based on video detector |
Non-Patent Citations (2)
| Title |
|---|
| Dynamic demand estimation and prediction for traffic urban networks adopting new data sources;Stefano Carrese 等;《TRANSPORTATION RESEARCH》;20170527;正文全文 * |
| 基于神经网络的小时间粒度交通流预测模型;姚志洪 等;《交通运输系统工程与信息》;20170228;第17卷(第1期);正文全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108765946A (en) | 2018-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108492562B (en) | Intersection vehicle track reconstruction method based on fixed point detection and electric warning data fusion | |
| CN108765981B (en) | Lane-dividing real-time queuing length prediction method | |
| Ma et al. | Lane-based saturation degree estimation for signalized intersections using travel time data | |
| CN109272756B (en) | Method for estimating queuing length of signal control intersection | |
| CN106781563B (en) | A kind of city expressway intersection public transport priority signal coordinating timing method | |
| US8279086B2 (en) | Traffic flow monitoring for intersections with signal controls | |
| KR101385057B1 (en) | Prediction of urban congestion using ITS based data | |
| CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
| CN106571029B (en) | A kind of method and apparatus of vehicle queue length detection | |
| CN101777259B (en) | Method for acquiring mean delay of urban road junction | |
| CN108847042A (en) | A kind of traffic information dissemination method and device | |
| CN113380027B (en) | Intersection traffic state parameter estimation method and system based on multi-source data | |
| US11798408B2 (en) | Green wave speed determination method, electronic device and storage medium | |
| CN101894461A (en) | Method for predicting travel time on urban ground level roads | |
| CN111275975B (en) | Method and device for acquiring intersection turning flow data and storage medium | |
| CN113380036B (en) | Queuing length calculation method based on electronic police data | |
| CN111383453B (en) | Traffic signal control on-line simulation and real-time tracking feedback system and operation method | |
| CN113593222B (en) | Multi-source data supported traffic control diagnosis method | |
| CN112116813B (en) | State recognition model establishing method, road traffic state recognition method and road traffic state recognition device | |
| CN112201061B (en) | Intersection timing scheme estimation method based on electric police checkpoint data | |
| CN108022015B (en) | Method for correcting traffic capacity of left-turning motor vehicle | |
| JP2003085687A (en) | Device for estimating time required for traveling between intersections | |
| CN108765946B (en) | Lane group traffic demand prediction method based on red light running automatic recording system data | |
| CN112419751B (en) | Signalized intersection lane queuing length estimation method based on single-section electric alarm data | |
| Krogh et al. | Trajectories for novel and detailed traffic information |
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 |