CN105160867A - Traffic information prediction method - Google Patents
Traffic information prediction method Download PDFInfo
- Publication number
- CN105160867A CN105160867A CN201510514548.2A CN201510514548A CN105160867A CN 105160867 A CN105160867 A CN 105160867A CN 201510514548 A CN201510514548 A CN 201510514548A CN 105160867 A CN105160867 A CN 105160867A
- Authority
- CN
- China
- Prior art keywords
- traffic
- vehicle
- time
- density
- real
- 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 information prediction method. The method includes the following steps that: the joint of more than two road traveling paths which are not in a crossroad and are located in an urban traffic map is selected, and the joint is adopted as a reference point, a point which is N metres before the reference point is a terminal point, and a point which is 2N metres behind the reference point is a starting point; the terminal point and the starting point are both provided with one automatic camera and a magnetic line of force, and the lenses of the cameras, facing the joint, perform photographing; measurement time is set, photographed pictures are uploaded to a remote database in the measurement time, and a remote control center calls the images from the database and performs image recognition on the images, so that vehicle density in the images can be obtained through statistics; real-time vehicle density is compared with preset comparison vehicle density, if the real-time vehicle density is lower than or equal to the comparison vehicle density, a message indicating that the traffic is smooth is outputted, and if the real-time vehicle density is higher than the comparison vehicle density, whether congestion exists can be judged according to vehicle speed. The traffic information prediction method of the invention has the advantages of simplicity, small amount of occupied data, simple and convenient computation, high precision and excellent prediction effect.
Description
Technical field
The present invention relates to a kind of traffic message Forecasting Methodology.
Background technology
Along with the development of social economy and communication, many traffic problems such as traffic congestion and traffic hazard are more and more serious, become global problem, method merely by building road and traffic setting can not solve trip difficult problem, current road traffic condition is just known before people wish to go out, to select the most effective traffic route and trip mode, so how rationally to set up traffic control and the inducible system of science become and solve this very corn of a subject place.
Realize traffic control and induction, key is the prediction to traffic behavior, namely real time traffic data information how is effectively utilized to remove the following traffic shape body in a short time of rolling forecast, and will predict the outcome to deliver in traffic information system and management system and go, effective information is in real time provided to traveler, help them better to carry out Trace predict, to shorten the travel time, reduce congested in traffic.
The prediction of traffic behavior needs a large amount of enquiry datas, quantitative basis is provided to the national economic evaluation of the configuration of the design of the setting of the determination of the prediction of prospect traffic volume, road type and grade, interchange, road Cross Section, transport services facility, traffic administration and control, programme and construction project and financial analysis etc., so for traffic programme improve and the science decision of construction project is laid a good foundation.
Traffic data is the basic data of traffic administration and induction research, comprises the three large parameters such as the flow of traffic flow, speed and occupation rate.Current traffic data be by dropping into a large amount of human and material resources, financial resources carry out on-site inspection and obtain, and therefore can not realize real-time investigation, but traffic data are in constantly developing and changing, the traffic data of interval investigation cannot support to predict needed for degree of accuracy.
A lot of to the theoretical research result in this field at present, but really to drop into and the technology applied in Practical Project is few, external more existing professional institutions develop corresponding forecasting software for this, but because city traffic network of China is too complicated huge, external software at home effect is not satisfactory; And the domestic Development and Production that there is no forecasting software.
Summary of the invention
The technical problem to be solved in the present invention is that prior art cannot provide traffic message forecast function accurately.
For solving the problems of the technologies described above, the technical solution used in the present invention is: traffic message Forecasting Methodology, comprise the following steps: 1) select non-crossroad in a urban traffic map, the joint of more than two road strokes, with this joint for reference point, N rice, front is terminal, and 2N rice, rear is starting point, delimits test section, described vehicle sails test section into from starting point, rolls test section away from from destination county; 2) respectively arrange an automatic camera and a magnetic line of force in starting point and destination county, the alignment lens joint place shooting of video camera, the frequency of shooting is 1 time per minute, and the magnetic line of force is sticked on the ground; 3) the initial value T1 of setting measurement time and end point values T2, within this period, by the picture uploading remote data base of shooting, remote control center is calling graph picture from database, image recognition is carried out to it, thus counts traffic density in image, be i.e. real-time vehicle density; When vehicle first time is by the magnetic line of force, the Hall element arranged in vehicle detects after magnetic signal to cab signal emitter high level signal, this cab signal emitter is started working, the detection signal of vehicle-mounted vehicle speed sensor is sent to remote control center by sender unit, when vehicle is again by the magnetic line of force, the Hall element arranged in vehicle detects that this cab signal emitter quits work to cab signal emitter high level signal after signal again; 4) in step 3) on basis, contrasted by real-time vehicle density and the contrast traffic density preset, if real-time density is less than or equal to contrast traffic density, it is unimpeded for namely exporting traffic conditions, if real-time density is higher than contrast traffic density, judge to continue step 5; 5) probability statistics are carried out to the car speed obtained in step 3), draw the vehicle speed range V1-V2 that in Measuring Time, probable value is the highest, calculate average velocity V=(V1+V2)/2 with this; As V > 30km/h, for unimpeded; As 20km/h≤V < 30km/h, for slightly crowded; As 10km/h≤V < 20km/h, for crowded; As 0km/h≤V < 10km/h, for seriously crowded; 6) repeated step 1-5 every one hour to measure, and set up historical traffic information according to this order and to block up curve, mapping is blocked up and the average velocity change curve in heavy congestion situation, and to last speed values point place's differentiate f'(x on this curve), f'(x) during >0, function is monotone increasing in this interval, and curve is uptrend, and namely traffic conditions takes a turn for the better to unimpeded direction; F'(x) during <0, function is monotone decreasing in this interval, and curve is downtrend, and namely traffic conditions continues to worsen to serious crowded direction; When f'(x)=0, continuation keeps by current traffic situation.
In traffic study now, in whole traffic route, craspedodrome road is often not easy to cause traffic congestion, the place of the traffic congestion the most easily caused all concentrates on two strands of track meets or separately locates, once these places get congestion, if can not current limliting in time, the follow-up vehicle flowrate poured in can cause generation of blocking up on a large scale very soon.The present invention selects each crossing to detect traffic, with strong points; The present invention has evaded in existing Forecasting Methodology and has carried out budget by the large parameter of the flow of traffic flow, speed and occupation rate three, only gather a traffic density vehicle average velocity in scope to be measured to predict, reduce the mathematical computations difficulty of prediction, reduce the difficulty of data acquisition, also reduce supervision center and the cost of googol according to storehouse is set, also reduce the intractability of control center to mass data; The present invention is by the calculating of curvature, and the gem-pure development trend embodying traffic in this area in a short time, for vehicle driving provides reference frame.In addition, first the present invention is roughly divided by traffic density and blocks up and unimpeded situation, for the situation that traffic density obviously can not result in blockage, directly stop judging, only reach the traffic behavior after certain level to traffic density to carry out accurately judging further, the data of foundation are the velocity standards that Ministry of Communications divides, thus, the content of the calculating of not only greatly simplifying, also very guaranteed to the degree of accuracy of data analysis, the fastest and the slowest speed is weeded out by the method for probability statistics, and select popular speed foundation as a comparison, ensure that the accuracy that data calculate and high specific aim, thus ensure that the effective of later stage prediction work.
Advantage of the present invention is: step is simple, take that data volume is little, computing is simple and convenient, precision is high, and prediction effect is good.
Embodiment
The technical solution used in the present invention is: traffic message Forecasting Methodology, comprise the following steps: 1) select non-crossroad in a urban traffic map, the joint of more than two road strokes, with this joint for reference point, N rice, front is terminal, 2N rice, rear is starting point, delimit test section, described vehicle sails test section into from starting point, rolls test section away from from destination county; 2) respectively arrange an automatic camera and a magnetic line of force in starting point and destination county, the alignment lens joint place shooting of video camera, the frequency of shooting is 1 time per minute, and the magnetic line of force is sticked on the ground; 3) the initial value T1 of setting measurement time and end point values T2, within this period, by the picture uploading remote data base of shooting, remote control center is calling graph picture from database, image recognition is carried out to it, thus counts traffic density in image, be i.e. real-time vehicle density; When vehicle first time is by the magnetic line of force, the Hall element arranged in vehicle detects after magnetic signal to cab signal emitter high level signal, this cab signal emitter is started working, the detection signal of vehicle-mounted vehicle speed sensor is sent to remote control center by sender unit, when vehicle is again by the magnetic line of force, the Hall element arranged in vehicle detects that this cab signal emitter quits work to cab signal emitter high level signal after signal again; 4) in step 3) on basis, contrasted by real-time vehicle density and the contrast traffic density preset, if real-time density is less than or equal to contrast traffic density, it is unimpeded for namely exporting traffic conditions, if real-time density is higher than contrast traffic density, judge to continue step 5; 5) probability statistics are carried out to the car speed obtained in step 3), draw the vehicle speed range V1-V2 that in Measuring Time, probable value is the highest, calculate average velocity V=(V1+V2)/2 with this; As V > 30km/h, for unimpeded; As 20km/h≤V < 30km/h, for slightly crowded; As 10km/h≤V < 20km/h, for crowded; As 0km/h≤V < 10km/h, for seriously crowded; 6) repeated step 1-5 every one hour to measure, and set up historical traffic information according to this order and to block up curve, mapping is blocked up and the average velocity change curve in heavy congestion situation, and to last speed values point place's differentiate f'(x on this curve), f'(x) during >0, function is monotone increasing in this interval, and curve is uptrend, and namely traffic conditions takes a turn for the better to unimpeded direction; F'(x) during <0, function is monotone decreasing in this interval, and curve is downtrend, and namely traffic conditions continues to worsen to serious crowded direction; When f'(x)=0, continuation keeps by current traffic situation.
In traffic study now, in whole traffic route, craspedodrome road is often not easy to cause traffic congestion, the place of the traffic congestion the most easily caused all concentrates on two strands of track meets or separately locates, once these places get congestion, if can not current limliting in time, the follow-up vehicle flowrate poured in can cause generation of blocking up on a large scale very soon.The present invention selects each crossing to detect traffic, with strong points.
Found by research, traffic density height in estimation range is exactly not necessarily block up, also to see the travelling speed of most of vehicle in highdensity vehicle group, when traffic congestion is very serious time, major part vehicle may can't walk any longer, there is the situation of speed of a motor vehicle convergence zero, therefore, there is no need have to judge real-time traffic condition by three large parameters, it can be zero in both cases that the speed of a motor vehicle only has, one there is not car completely, one does not walk completely, therefore, the present invention has evaded the flow by traffic flow in existing Forecasting Methodology, speed and the large parameter of occupation rate three carry out budget, only gather a traffic density vehicle average velocity in scope to be measured to predict, reduce the mathematical computations difficulty of prediction, reduce the difficulty of data acquisition, also reduce supervision center and the cost of googol according to storehouse is set, also reduce the intractability of control center to mass data, the present invention is by the calculating of curvature, and the gem-pure development trend embodying traffic in this area in a short time, for vehicle driving provides reference frame.In addition, first the present invention is roughly divided by traffic density and blocks up and unimpeded situation, for the situation that traffic density obviously can not result in blockage, directly stop judging, only reach the traffic behavior after certain level to traffic density to carry out accurately judging further, the data of foundation are the velocity standards that Ministry of Communications divides, thus, the content of the calculating of not only greatly simplifying, also very guaranteed to the degree of accuracy of data analysis, the fastest and the slowest speed is weeded out by the method for probability statistics, and select popular speed foundation as a comparison, ensure that the accuracy that data calculate and high specific aim, thus ensure that the effective of later stage prediction work.
Claims (1)
1. traffic message Forecasting Methodology, is characterized in that comprising the following steps:
1) select non-crossroad in a urban traffic map, the joint of more than two road strokes, with this joint for reference point, N rice, front is terminal, 2N rice, rear is starting point, delimit test section, described vehicle sails test section into from starting point, rolls test section away from from destination county;
2) respectively arrange an automatic camera and a magnetic line of force in starting point and destination county, the alignment lens joint place shooting of video camera, the frequency of shooting is 1 time per minute, and the magnetic line of force is sticked on the ground;
3) the initial value T1 of setting measurement time and end point values T2, within this period, by the picture uploading remote data base of shooting, remote control center is calling graph picture from database, image recognition is carried out to it, thus counts traffic density in image, be i.e. real-time vehicle density; When vehicle first time is by the magnetic line of force, the Hall element arranged in vehicle detects after magnetic signal to cab signal emitter high level signal, this cab signal emitter is started working, the detection signal of vehicle-mounted vehicle speed sensor is sent to remote control center by sender unit, when vehicle is again by the magnetic line of force, the Hall element arranged in vehicle detects that this cab signal emitter quits work to cab signal emitter high level signal after signal again;
4) in step 3) on basis, contrasted by real-time vehicle density and the contrast traffic density preset, if real-time density is less than or equal to contrast traffic density, it is unimpeded for namely exporting traffic conditions, if real-time density is higher than contrast traffic density, judge to continue step 5;
5) probability statistics are carried out to the car speed obtained in step 3), draw the vehicle speed range V1-V2 that in Measuring Time, probable value is the highest, calculate average velocity V=(V1+V2)/2 with this; As V > 30km/h, for unimpeded; As 20km/h≤V < 30km/h, for slightly crowded; As 10km/h≤V < 20km/h, for crowded; As 0km/h≤V < 10km/h, for seriously crowded;
6) repeated step 1-5 every one hour to measure, and set up historical traffic information according to this order and to block up curve, mapping is blocked up and the average velocity change curve in heavy congestion situation, and to last speed values point place's differentiate f'(x on this curve), f'(x) during >0, function is monotone increasing in this interval, and curve is uptrend, and namely traffic conditions takes a turn for the better to unimpeded direction; F'(x) during <0, function is monotone decreasing in this interval, and curve is downtrend, and namely traffic conditions continues to worsen to serious crowded direction; When f'(x)=0, continuation keeps by current traffic situation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510514548.2A CN105160867B (en) | 2015-08-20 | 2015-08-20 | Traffic message Forecasting Methodology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510514548.2A CN105160867B (en) | 2015-08-20 | 2015-08-20 | Traffic message Forecasting Methodology |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105160867A true CN105160867A (en) | 2015-12-16 |
CN105160867B CN105160867B (en) | 2017-06-16 |
Family
ID=54801706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510514548.2A Active CN105160867B (en) | 2015-08-20 | 2015-08-20 | Traffic message Forecasting Methodology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105160867B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105608892A (en) * | 2015-12-28 | 2016-05-25 | 中兴软创科技股份有限公司 | Real-time congestion early warning method and system |
CN106448156A (en) * | 2016-08-31 | 2017-02-22 | 广州地理研究所 | Automobile electronic identifier-based urban traffic operation state prediction method and device |
CN106469470A (en) * | 2016-08-31 | 2017-03-01 | 广州地理研究所 | Urban congestion charging method based on vehicle electron identifying and device |
WO2019042408A1 (en) * | 2017-09-04 | 2019-03-07 | 厦门物拓科技有限公司 | Real-time detection apparatus for refrigerator state, and refrigerator |
CN110431605A (en) * | 2017-03-15 | 2019-11-08 | 住友电气工业株式会社 | The estimation device and estimation method of computer program, the estimation device of car speed and estimation method and congested in traffic trend |
CN113870564A (en) * | 2021-10-26 | 2021-12-31 | 安徽百诚慧通科技有限公司 | Traffic jam classification method and system for closed road section, electronic device and storage medium |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5444442A (en) * | 1992-11-05 | 1995-08-22 | Matsushita Electric Industrial Co., Ltd. | Method for predicting traffic space mean speed and traffic flow rate, and method and apparatus for controlling isolated traffic light signaling system through predicted traffic flow rate |
CN1506919A (en) * | 2002-12-13 | 2004-06-23 | 乐金信世股份有限公司 | Traffic accidence monitoring method |
CN101872544A (en) * | 2010-06-12 | 2010-10-27 | 江苏省交通科学研究院股份有限公司 | Simple urban road congestion statistic evaluation method |
CN104778834A (en) * | 2015-01-23 | 2015-07-15 | 哈尔滨工业大学 | Urban road traffic jam judging method based on vehicle GPS data |
-
2015
- 2015-08-20 CN CN201510514548.2A patent/CN105160867B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5444442A (en) * | 1992-11-05 | 1995-08-22 | Matsushita Electric Industrial Co., Ltd. | Method for predicting traffic space mean speed and traffic flow rate, and method and apparatus for controlling isolated traffic light signaling system through predicted traffic flow rate |
CN1506919A (en) * | 2002-12-13 | 2004-06-23 | 乐金信世股份有限公司 | Traffic accidence monitoring method |
CN101872544A (en) * | 2010-06-12 | 2010-10-27 | 江苏省交通科学研究院股份有限公司 | Simple urban road congestion statistic evaluation method |
CN104778834A (en) * | 2015-01-23 | 2015-07-15 | 哈尔滨工业大学 | Urban road traffic jam judging method based on vehicle GPS data |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105608892A (en) * | 2015-12-28 | 2016-05-25 | 中兴软创科技股份有限公司 | Real-time congestion early warning method and system |
CN106448156A (en) * | 2016-08-31 | 2017-02-22 | 广州地理研究所 | Automobile electronic identifier-based urban traffic operation state prediction method and device |
CN106469470A (en) * | 2016-08-31 | 2017-03-01 | 广州地理研究所 | Urban congestion charging method based on vehicle electron identifying and device |
CN106469470B (en) * | 2016-08-31 | 2019-03-08 | 广州地理研究所 | Urban congestion charging method and device based on vehicle electron identifying |
CN110431605A (en) * | 2017-03-15 | 2019-11-08 | 住友电气工业株式会社 | The estimation device and estimation method of computer program, the estimation device of car speed and estimation method and congested in traffic trend |
WO2019042408A1 (en) * | 2017-09-04 | 2019-03-07 | 厦门物拓科技有限公司 | Real-time detection apparatus for refrigerator state, and refrigerator |
CN113870564A (en) * | 2021-10-26 | 2021-12-31 | 安徽百诚慧通科技有限公司 | Traffic jam classification method and system for closed road section, electronic device and storage medium |
CN113870564B (en) * | 2021-10-26 | 2022-09-06 | 安徽百诚慧通科技股份有限公司 | Traffic jam classification method and system for closed road section, electronic device and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN105160867B (en) | 2017-06-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105160867A (en) | Traffic information prediction method | |
US10352718B2 (en) | Discovering points of entry to a location | |
CN103985250B (en) | The holographic road traffic state vision inspection apparatus of lightweight | |
CN109544932A (en) | A kind of city road network flow estimation method based on GPS data from taxi Yu bayonet data fusion | |
US8930123B2 (en) | Systems and methods for determining traffic intensity using information obtained through crowdsourcing | |
CN112489433B (en) | Traffic congestion analysis method and device | |
CN104658252B (en) | Method for evaluating traffic operational conditions of highway based on multisource data fusion | |
US20180283895A1 (en) | Navigation system and method | |
WO2021129227A1 (en) | Traffic information processing method and device | |
CN107784835A (en) | Traffic behavior model prediction system and its Forecasting Methodology based on traffic data analyzing | |
WO2015051718A1 (en) | Dynamic track navigation method and cloud platform | |
CN107085944B (en) | Traffic data processing system and method | |
CN101964941A (en) | Intelligent navigation and position service system and method based on dynamic information | |
CN106652483A (en) | Method for arranging traffic information detection points in local highway network by utilizing detection device | |
CN105513394A (en) | Road condition obtaining method and road condition obtaining system | |
CN102136194A (en) | Road traffic condition detection device based on panorama computer vision | |
CN101739824A (en) | Data fusion technology-based traffic condition estimation method | |
KR101277007B1 (en) | Method for offering passing time of expresshighway passing auto mobile and system thereof | |
EP4079006B1 (en) | Methods and systems for generating traffic volume data | |
JP2015076077A (en) | Traffic volume estimation system,terminal device, traffic volume estimation method and traffic volume estimation program | |
CN101819719A (en) | Method for setting initial green light time based on pedestrian and bicycle group | |
CN109979197A (en) | Freeway traffic time map construction method based on fused data, system | |
Costanzo | An arduino based system provided with GPS/GPRS shield for real time monitoring of traffic flows | |
Dahiya et al. | A study of speed-density functional relations for varying spatiotemporal resolution using Zen Traffic Data | |
CN109166336B (en) | Real-time road condition information acquisition and pushing method based on block chain technology |
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 |