CN105006149A - Traffic road condition estimation dynamic iteration method - Google Patents
Traffic road condition estimation dynamic iteration method Download PDFInfo
- Publication number
- CN105006149A CN105006149A CN201510406126.3A CN201510406126A CN105006149A CN 105006149 A CN105006149 A CN 105006149A CN 201510406126 A CN201510406126 A CN 201510406126A CN 105006149 A CN105006149 A CN 105006149A
- Authority
- CN
- China
- Prior art keywords
- section
- variance
- hourage
- vehicle
- 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.)
- Granted
Links
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic road condition estimation dynamic iteration method. According to the method, existing charging record data is utilized, the operation state of a road is reproduced through the dynamic iteration method including the step of calculating a shortest path of a vehicle driving in a road net aiming at each OD record; the driving state of the vehicle on each path section of the shortest path is inverted, and the flow and speed of each road section at each moment based on a uniform speed hypothesis are obtained; dynamic iteration inversion is carried out on all vehicle records; when a calculated variance f(x) is larger than or equal to a set variance threshold, the variance is adjusted by means of variance balancing, and dynamic iteration is carried out; and finally an inversion result is obtained. According to the invention, time is continuous, and by means of dynamic iteration, each tracing point in each time of iteration is adjusted in time and space, so that the rationality and the accuracy of the result of road operation state reproduction are ensured, and the road operation condition is monitored in real time.
Description
Technical field
The present invention relates to technical field of intelligent traffic, particularly relate to a kind of Dynamic iterations method highway state estimated according to history charge data.
Background technology
Along with the fast development of China's economy, the development of highway communication technology and the raising of the efficiency of management become most important.Freeway traffic system is typical complication system, and the complicacy of this system is based on the network structure of road.Effectively carrying out accurately tolerance to traffic route situation is the basis of Improving Expressway operation management level and service quality.
The topological structure of transportation network and the traffic parameter of road can reflect the performance of transportation network to a certain extent, but will from the performance of more fully angle estimator transportation network, then need combining transportation network topological structure and history in transportation network with current traffic flow conditions.The performance metric of transportation network mainly contains extensibility that the overall traffic efficiency of overall road network, the travel pattern of each ingredient (as import and export, section etc.), road passage capability show with volume of traffic increase and according to the environmental pollution of arithmetic for real-time traffic flow situation and the tolerance etc. of power consumption state.
At present, for understanding road grid traffic situation, the average velocity method of vehicle is usually adopted, namely according to 15 minutes for changing a point time window (time window), window distribution when every bar track is carried out, then statistical computation is carried out to the data in each window, obtain traffic.This existing method belongs to discreet static method, spatially obliterate the actual speed difference between each section, use discrete time slot in time, precision is become when reducing, statistical computation is also failed accurately conclude the due space-time position point of each data (vehicle OD), therefore, the accuracy adopting average velocity method to estimate road network traffic is not high.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, the present invention is based on traffic flow model knowledge, (inverting) traffic on road network is at that time inquired into according to the data of crossing vehicles passing in and out, a kind of traffic is specifically provided to estimate Dynamic iterations method, by Time Continuous, carry out the iterative computation linked, when making each iteration, each tracing point adjusts on space-time, by setting global optimization target and strict constraint condition, guarantee rationality and the accuracy of estimated result reproduction road operation conditions, Real-Time Monitoring road ruuning situation can be helped.
Technical scheme provided by the invention is:
A kind of traffic estimates Dynamic iterations method, and the method utilizes existing charge to record data, by the operation conditions of Dynamic iterations method reproduction road, specifically comprises the steps:
1) take out driving recording, comprise starting points all in road network and terminal OD record;
2) for every bar OD record, calculate the shortest path that this vehicle travels in road network, be made up of multiple section, be denoted as { Section
1, Section
2... Section
n;
3) based at the uniform velocity supposing, the moment { t that vehicle enters each section is calculated
1, t
2... t
n, the driving states of inverting vehicle on each section of this shortest path, obtains the flow based on each section each moment at the uniform velocity supposed and speed;
4) Dynamic iterations inverting is carried out to all vehicle registrations;
For the OD vehicle registration of system-wide net, calculate variance f (x) according to formula 1, judge whether variance f (x) meets the variance threshold values of setting;
F (x)=min (∑
id (T
i), if i ∈ S
non-free) (formula 1)
In formula 1, min () represents that optimization aim is minimum value; S
non-freeit is the atom section of all non-free stream; D (T
i) be variance computing formula D (x)=E (x
2)-E (X)
2, wherein, μ is the mean value of the hourage in this section, and X is the set of the hourage in this section; E (X) is the mean value of the hourage in this section; I is the numbering in section; T
ivector hourage of OD records all on i-th atom section;
When the variance f (x) calculated is less than the variance threshold values of setting, terminates Dynamic iterations inverting, enter step 5); When the variance f (x) calculated is more than or equal to setting variance threshold values, circulate as follows:
41) for each section in road network, the expectation intermediate value of the speed in this section is calculated according to weight allocation principle:
In formula 2, mt
iit is the intermediate value of the hourage in i-th section; t
ijthe hourage on i-th section is recorded in for a jth OD; T
jfor vector hourage that OD all on a jth atom section records; The vehicle journeys time is longer, and when calculating, weight is less;
42) record and step 41 for every bar OD) in the expectation intermediate value of section speed that obtains, according to re-allocation principle, adjust variance by variance equalization, make t
ijtowards with mt
idifference reduce direction carry out iteration:
T
ij=t
ij+ alpha* (mt
i-t
ij) (formula 3)
In formula 3, t
ijthe hourage on i-th section is recorded in for a jth OD; Mt
iit is the intermediate value of the hourage in i-th section; Alpha is coefficient, is determined by experience or actual conditions, and span is 0.01 ~ 0.1;
5) after cyclic process terminates, be recorded in the hourage be assigned in each section according to each OD, obtain inversion result, comprise the final speed in each section and link flow.
Dynamic iterations method is estimated for above-mentioned traffic, further,
Step 4) described variance threshold values specifically carries out setting and adjusting according to the vehicle number in section or different sections.In embodiments of the present invention, described variance threshold values is set as 200.
Step 41) described weight allocation principle refers to the shorter car of stroke, and its hourage is more reliable, and the weight of giving when calculating the expectation intermediate value of section speed is larger.
Step 42) the described variance equalization variance equalization that hourage of distributing in each section of its approach and section are expected when specifically vehicle OD being recorded last iteration.
Compared with prior art, the invention has the beneficial effects as follows:
Carry out estimating (inverting) for historical traffic road conditions, prior art adopts vehicle average velocity method mostly, the method is discreet static method, namely a point time window was changed by 15 minutes, window distribution when every bar track carries out, again data in each window are added up, therefore, the method has spatially obliterated the actual speed difference between each section, use discrete time slot in time, become precision when reducing, statistical computation is also failed accurately conclude the due space-time position point of each data (vehicle OD).
The present invention is based on traffic flow model knowledge, traffic on road network is at that time inquired into according to the data of crossing vehicles passing in and out, a kind of traffic is specifically provided to estimate Dynamic iterations method, Dynamic iterations side's ratio juris is by Time Continuous, carry out iterative computation in linkage, each tracing point of each iteration is adjusted on space-time, setting global optimization target and strict constraint condition, thus guarantee the rationality and the accuracy that reappear road operation conditions result, Real-Time Monitoring road ruuning situation can be helped.On this basis, further forecast analysis future trend situation, assists decision-making.
Accompanying drawing explanation
Fig. 1 is the FB(flow block) that traffic provided by the invention estimates Dynamic iterations method.
Fig. 2 is the FB(flow block) of Dynamic iterations inversion algorithm concrete steps provided by the invention.
Fig. 3 is the schematic diagram of road network in the embodiment of the present invention and shortest path map,
Wherein, the section in 1-circled portion is the vehicle shortest path in embodiment.
Embodiment
Below in conjunction with accompanying drawing, further describe the present invention by embodiment, but the scope do not limited the present invention in any way.
The invention provides a kind of Dynamic iterations method estimated for traffic, the method utilizes existing charge to record data, by the operation conditions of Dynamic iterations method reproduction road, can be Real-Time Monitoring road ruuning situation to offer help, on this basis, can further forecast analysis road future move towards situation, play the effect of aid decision making.
The Dynamic iterations method estimated for traffic specifically comprises the steps:
1) driving recording is taken out;
Take out all starting points and terminal (OD) record in road network;
2) for every bar OD record, the shortest path that this vehicle travels in road network is calculated;
For every bar OD record, according to the shortest path that its starting and terminal point calculates in road network, be made up of multiple section, be denoted as { Section
1, Section
2... Section
n;
3) based at the uniform velocity supposing, the driving states of inverting vehicle on each section of this shortest path, obtains the flow based on each section each moment at the uniform velocity supposed and speed;
According to its starting and terminal point time and the hypothesis that at the uniform velocity travels, calculate the moment { t that vehicle enters each section
1, t
2... t
n, then the flow Flow (Section in respective stretch corresponding moment
i, t
i) increase by 1, the speed Speed (Section in respective stretch corresponding moment
i, t
i) statistical sample amount increase by 1;
4) Dynamic iterations inverting is carried out to all vehicle registrations;
Carry out step 3 for all records) after described calculating, obtain variance f (x) by formulae discovery:
F (x)=min (∑
id (T
i), if i ∈ S
non-free) (formula 1)
In formula 1, min () represents that optimization aim is minimum value; S
non-freeit is the atom section of all non-free stream; D (T
i) be variance computing formula D (x)=E (x
2)-E (X)
2, wherein, μ is the mean value of the hourage in this section, and X is the set of the hourage in this section; E (X) is the mean value of the hourage in this section; I is the numbering in section; T
ivector hourage of OD records all on i-th atom section;
For the OD vehicle registration of system-wide net, according to formulae discovery variance f (x), judge whether variance f (x) meets setting threshold value; Threshold value rule of thumb carries out setting and adjusting with practical application; Particularly, threshold value has different selections according to the vehicle number in section or different sections.When the variance f (x) calculated is less than setting threshold value, terminates Dynamic iterations inverting, enter step 5); When the variance f (x) calculated is more than or equal to setting threshold value, circulate as follows:
41) for each section in road network, according to weight allocation principle (car that namely stroke is shorter, its hourage is more reliable, and the weight of giving when calculating intermediate value is larger), the expectation intermediate value of the speed in this section is calculated:
In formula 2, mt
iit is the intermediate value of the hourage in i-th section; t
ijthe hourage on i-th section is recorded in for a jth OD; T
jfor vector hourage that OD all on a jth atom section records; The vehicle journeys time is longer, and when calculating, weight is less;
42) for the expectation intermediate value of the section speed obtained in every bar OD record and previous step, the variance equalization that the hourage of distributing in each section of its approach when being according to re-allocation principle vehicle OD is recorded last iteration and section are expected.Variance equalization refers to that iteration is carried out in the direction that adjustment allows tij reduce towards the difference with mti:
T
ij=t
ij+ alpha* (mt
i-t
ij) (formula 3)
In formula 3, t
ijthe hourage on i-th section is recorded in for a jth OD; Mt
iit is the intermediate value of the hourage in i-th section; Alpha is coefficient, is determined by experience or actual conditions, and span is 0.01 ~ 0.1;
5) after cyclic process terminates, be recorded in the hourage be assigned in each section according to each OD, obtain inversion result, comprise the final speed in each section and link flow.
Below by example, the present invention is further described.
Example 1:
It is that vehicle enters and leaves the complete documentation of road network that the advantage of charge record data is mainly reflected in charge record, the important informations such as the time that content contains vehicle license plate, vehicle, vehicle enter and leave road network and website.Simply, suppose that all vehicles at the uniform velocity travel in road network, all vehicles select the shortest path of origin-to-destination to travel, so known vehicle enters, leaves website and the time of road network, then can extrapolate speed and the position of any time vehicle in road network of vehicle, namely residing section.Flow and the average velocity in each section can be counted further.Thus, just road operation conditions can be reappeared by the charge data of crossing vehicles passing in and out.
A part for Tu3Shi Anhui Province road network, collects the charge record of this part road network, performs and operates as follows:
1) for each vehicle registration, the shortest path in road network according to its starting point and endpoint calculation;
Shortest path is made up of multiple section, i.e. { Section
1, Section
2... Section
n, this shortest path has n section.According to starting point and endpoint calculation, the method for the shortest path in road network can adopt dijkstra's algorithm (Dijkstra's algorithm) to calculate acquisition at present, and as shown in Figure 3, the section in circled portion is the shortest path of this vehicle.
2) according to time of its starting point and terminal and the hypothesis that at the uniform velocity travels, to should n section { Section in shortest path
1, Section
2... Section
n, calculate the moment that vehicle enters each section, be denoted as { t
1, t
2... t
n;
Further calculating obtains the time of this car in each section;
Chronomere's precision is minute; In the present embodiment, t1=3min;
Signal code is as follows:
3) all records calculate complete after, then enter iterative inversion step, Fig. 2 is the FB(flow block) of Dynamic iterations inversion algorithm concrete steps, specifically performs following operation:
31) variance f (x) is obtained by variance computing formula (above formula 1); If the value of variance f (x) is less than or equal to the threshold value of setting, end operation;
Signal code is as follows:
In the present embodiment, setting threshold value is 200, and the value calculating variance f (x) is 243, and variance f (x) is greater than setting threshold value, enters following circulation, comprises step 32a) ~ 32b):
32a) for each section in road network, calculate the expectation intermediate value of the speed in this section according to weight allocation principle;
Weight allocation principle and the shorter car of stroke, its hourage is more reliable, and the weight of giving when calculating intermediate value is larger.The expectation intermediate value of the speed in this section is calculated by above-mentioned formula 2.In the present embodiment, the expectation intermediate value calculating the speed in first section is 2min;
32b) to record for every bar OD and the section speed intermediate value that obtains in previous step, when vehicle OD being recorded last iteration according to re-allocation principle its by way of hourage of each section distribution and the variance equalization expected of section;
Variance equalization adjusts particular by above-mentioned formula 3, and tij hourage allowing a jth OD be recorded on i-th section carries out iteration towards the poor direction reduced of the intermediate value mti of the hourage with i-th section; In the present embodiment, t
ij=3+0.1* (2-3)=2.7.
33) for the OD vehicle registration of system-wide net, variance f (x) is calculated according to formula 1; See whether f (x) meets the condition being less than threshold value.It is 190 that this step of the present embodiment calculates f (x), is less than threshold value 200, and circulation terminates;
Signal code is as follows:
34), after cyclic process terminates, be recorded in tij hourage be assigned in each section according to each OD, obtain final speed and link flow.
According to the final speed obtained and link flow, the real-time condition in more real road network can being obtained, providing sound assurance for further analyzing traffic conditions.
It should be noted that the object publicizing and implementing example is to help to understand the present invention further, but it will be appreciated by those skilled in the art that: in the spirit and scope not departing from the present invention and claims, various substitutions and modifications are all possible.Therefore, the present invention should not be limited to the content disclosed in embodiment, and the scope that the scope of protection of present invention defines with claims is as the criterion.
Claims (5)
1. traffic estimates a Dynamic iterations method, and the method utilizes existing charge to record data, by the operation conditions of Dynamic iterations method reproduction road, specifically comprises the steps:
1) take out driving recording, comprise starting points all in road network and terminal OD record;
2) for every bar OD record, calculate the shortest path that this vehicle travels in road network, be made up of multiple section, be denoted as { Section
1, Section
2... Section
n;
3) based at the uniform velocity supposing, the moment { t that vehicle enters each section is calculated
1, t
2... t
n, the driving states of inverting vehicle on each section of this shortest path, obtains the flow based on each section each moment at the uniform velocity supposed and speed;
4) Dynamic iterations inverting is carried out to all vehicle registrations;
For the OD vehicle registration of system-wide net, calculate variance f (x) according to formula 1, judge whether variance f (x) meets the variance threshold values of setting;
F (x)=min (∑
id (T
i), ifi ∈ S
non-free) (formula 1)
In formula 1, min () represents that optimization aim is minimum value; S
non-freeit is the atom section of all non-free stream; D (T
i) be variance computing formula D (x)=E (x
2)-E (X)
2, wherein, μ is the mean value of the hourage in this section, and X is the set of the hourage in this section; E (X) is the mean value of the hourage in this section; I is the numbering in section; T
ivector hourage of OD records all on i-th atom section;
When the variance f (x) calculated is less than the variance threshold values of setting, terminates Dynamic iterations inverting, enter step 5); When the variance f (x) calculated is more than or equal to setting variance threshold values, circulate as follows:
41) for each section in road network, the expectation intermediate value of the speed in this section is calculated according to weight allocation principle:
In formula 2, mt
iit is the intermediate value of the hourage in i-th section; t
ijthe hourage on i-th section is recorded in for a jth OD; T
jfor vector hourage that OD all on a jth atom section records; The vehicle journeys time is longer, and when calculating, weight is less;
42) record and step 41 for every bar OD) in the expectation intermediate value of section speed that obtains, according to re-allocation principle, adjust variance by variance equalization, make t
ijtowards with mt
idifference reduce direction carry out iteration:
T
ij=t
ij+ alpha* (mt
i-t
ij) (formula 3)
In formula 3, t
ijthe hourage on i-th section is recorded in for a jth OD; Mt
iit is the intermediate value of the hourage in i-th section; Alpha is coefficient, is determined by experience or actual conditions, and span is 0.01 ~ 0.1;
5) after cyclic process terminates, be recorded in the hourage be assigned in each section according to each OD, obtain inversion result, comprise the final speed in each section and link flow.
2. traffic estimates Dynamic iterations method as claimed in claim 1, it is characterized in that, step 4) described variance threshold values specifically carries out setting and adjusting according to the vehicle number in section or different sections.
3. traffic estimates Dynamic iterations method as claimed in claim 2, and it is characterized in that, described variance threshold values is set as 200.
4. traffic estimates Dynamic iterations method as claimed in claim 1, it is characterized in that, step 41) described weight allocation principle refers to the shorter car of stroke, and its hourage is more reliable, and the weight of giving during the expectation intermediate value of calculating section speed is larger.
5. traffic estimates Dynamic iterations method as claimed in claim 1, it is characterized in that, step 42) the described variance equalization variance equalization that hourage of distributing in each section of its approach and section are expected when specifically vehicle OD being recorded last iteration.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510406126.3A CN105006149B (en) | 2015-07-10 | 2015-07-10 | Traffic estimates Dynamic iterations method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510406126.3A CN105006149B (en) | 2015-07-10 | 2015-07-10 | Traffic estimates Dynamic iterations method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105006149A true CN105006149A (en) | 2015-10-28 |
| CN105006149B CN105006149B (en) | 2017-07-21 |
Family
ID=54378802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510406126.3A Expired - Fee Related CN105006149B (en) | 2015-07-10 | 2015-07-10 | Traffic estimates Dynamic iterations method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105006149B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993436A (en) * | 2017-11-22 | 2018-05-04 | 思建科技有限公司 | A kind of road condition predicting method and system based on OBD |
| CN110322054A (en) * | 2019-06-14 | 2019-10-11 | 中交第一公路勘察设计研究院有限公司 | A kind of optimization distribution method of highway section Traffic monitoring device |
| CN110617834A (en) * | 2019-10-31 | 2019-12-27 | 电子科技大学 | Shortest path planning method under Gaussian process road network |
| CN112837542A (en) * | 2020-12-30 | 2021-05-25 | 北京掌行通信息技术有限公司 | Method and device for counting traffic volume of highway section, storage medium and terminal |
| CN113223293A (en) * | 2021-05-06 | 2021-08-06 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113954868A (en) * | 2021-10-08 | 2022-01-21 | 南京航空航天大学 | Lane-level path planning method and system based on space-time traffic model |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4847772A (en) * | 1987-02-17 | 1989-07-11 | Regents Of The University Of Minnesota | Vehicle detection through image processing for traffic surveillance and control |
| CN101510357A (en) * | 2009-03-26 | 2009-08-19 | 美慧信息科技（上海）有限公司 | Method for detecting traffic state based on mobile phone signal data |
| WO2011126215A2 (en) * | 2010-04-09 | 2011-10-13 | 고려대학교 산학협력단 | Traffic flow control and dynamic path providing system linked with real-time traffic network structure control based on bidirectional communication function-combined vehicle navigation, and method thereof |
| CN103050009A (en) * | 2013-01-21 | 2013-04-17 | 北京世纪高通科技有限公司 | Method, device and system for providing dynamic traffic information |
-
2015
- 2015-07-10 CN CN201510406126.3A patent/CN105006149B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4847772A (en) * | 1987-02-17 | 1989-07-11 | Regents Of The University Of Minnesota | Vehicle detection through image processing for traffic surveillance and control |
| CN101510357A (en) * | 2009-03-26 | 2009-08-19 | 美慧信息科技（上海）有限公司 | Method for detecting traffic state based on mobile phone signal data |
| WO2011126215A2 (en) * | 2010-04-09 | 2011-10-13 | 고려대학교 산학협력단 | Traffic flow control and dynamic path providing system linked with real-time traffic network structure control based on bidirectional communication function-combined vehicle navigation, and method thereof |
| CN103050009A (en) * | 2013-01-21 | 2013-04-17 | 北京世纪高通科技有限公司 | Method, device and system for providing dynamic traffic information |
Non-Patent Citations (2)
| Title |
|---|
| 赵松 等: "高速公路路网实际交通流量推算方法", 《中国交通信息化》 * |
| 靳引利 等: "基于OD的高速公路断面交通流量推算方法", 《交通信息与安全》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107993436A (en) * | 2017-11-22 | 2018-05-04 | 思建科技有限公司 | A kind of road condition predicting method and system based on OBD |
| CN110322054A (en) * | 2019-06-14 | 2019-10-11 | 中交第一公路勘察设计研究院有限公司 | A kind of optimization distribution method of highway section Traffic monitoring device |
| CN110322054B (en) * | 2019-06-14 | 2023-04-28 | 中交第一公路勘察设计研究院有限公司 | Optimized layout method of road section traffic monitor |
| CN110617834A (en) * | 2019-10-31 | 2019-12-27 | 电子科技大学 | Shortest path planning method under Gaussian process road network |
| CN110617834B (en) * | 2019-10-31 | 2021-02-26 | 电子科技大学 | Shortest path planning method under Gaussian process road network |
| CN112837542A (en) * | 2020-12-30 | 2021-05-25 | 北京掌行通信息技术有限公司 | Method and device for counting traffic volume of highway section, storage medium and terminal |
| CN112837542B (en) * | 2020-12-30 | 2022-04-08 | 北京掌行通信息技术有限公司 | Method and device for counting traffic volume of highway section, storage medium and terminal |
| CN113223293A (en) * | 2021-05-06 | 2021-08-06 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113223293B (en) * | 2021-05-06 | 2023-08-04 | 杭州海康威视数字技术股份有限公司 | Road network simulation model construction method and device and electronic equipment |
| CN113954868A (en) * | 2021-10-08 | 2022-01-21 | 南京航空航天大学 | Lane-level path planning method and system based on space-time traffic model |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105006149B (en) | 2017-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105006149A (en) | Traffic road condition estimation dynamic iteration method | |
| CN108053645B (en) | Signal intersection periodic flow estimation method based on track data | |
| CN107146446B (en) | A kind of paths chosen method based on RFID data and Dynamic Vehicle source | |
| CN103903430B (en) | Dynamic fusion type travel time predicting method with multi-source and isomorphic data adopted | |
| CN102521989B (en) | Dynamic-data-driven highway-exit flow-quantity predicting method | |
| US7953544B2 (en) | Method and structure for vehicular traffic prediction with link interactions | |
| Cortes et al. | General-purpose methodology for estimating link travel time with multiple-point detection of traffic | |
| GB2599765A (en) | Vehicle traffic flow prediction method with missing data | |
| CN103927872B (en) | A kind ofly predict based on floating car data the method that multi-period journey time distributes | |
| CN105046956A (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN112489426A (en) | Urban traffic flow space-time prediction scheme based on graph convolution neural network | |
| CN105718750A (en) | Prediction method and system for vehicle travelling track | |
| CN106652441A (en) | Urban road traffic condition prediction method based on spatial-temporal data | |
| CN109767619B (en) | Intelligent networking pure electric vehicle running condition prediction method | |
| CN112185124B (en) | Method and device for predicting traffic state of whole road network | |
| CN106548258B (en) | Traffic air pollutant concentration prediction method and system based on meteorological conditions | |
| CN103440422A (en) | Bus behind-schedule recovering method based on arrival time predication with time window | |
| CN104021674A (en) | Method for rapidly and accurately forecasting travel time of vehicles for passing through road sections | |
| Mittal et al. | Network flow relations and travel time reliability in a connected environment | |
| CN110796876A (en) | Road section vehicle total number estimation method based on Kalman filtering | |
| CN112201037B (en) | Intersection arrival rate estimation method based on sampling trajectory data | |
| Zou et al. | City-level traffic flow prediction via LSTM networks | |
| Cipriani et al. | Traffic state estimation based on data fusion techniques | |
| Long et al. | Bi-scale car-following model calibration based on corridor-level trajectory | |
| Salim et al. | Estimation of average space headway under heterogeneous traffic conditions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20170721 Termination date: 20210710 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |