CN109979197A - Freeway traffic time map construction method based on fused data, system - Google Patents
Freeway traffic time map construction method based on fused data, system Download PDFInfo
- Publication number
- CN109979197A CN109979197A CN201910270545.7A CN201910270545A CN109979197A CN 109979197 A CN109979197 A CN 109979197A CN 201910270545 A CN201910270545 A CN 201910270545A CN 109979197 A CN109979197 A CN 109979197A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- average speed
- measured
- speed
- station
- 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
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Devices For Checking Fares Or Tickets At Control Points (AREA)
Abstract
The present invention provides a kind of freeway traffic time map construction method based on fused data, system, the traffic condition of highway is predicted by freeway traffic data (video monitoring data and the current data of charge station), excavate and improve to the maximum extent the utilization rate of freeway traffic data, and fully considered the duration of traffic flow, be conducive to the accuracy for improving prediction;In addition, transport development situation is the decision-making foundation that traffic administration person implements control, traffic management department's science can be helped, active, made a policy to wisdom, wisdom traffic is advantageously implemented.
Description
Technical field
The present invention relates to field of intelligent transportation technology more particularly to a kind of freeway traffic times based on fused data
Map constructing method, system.
Background technique
Ended for the end of the year 2017, China's highway up to 13.65 ten thousand kilometers, ranks first in the world, and it is public to have accounted for global high speed
The half of road mileage open to traffic.Freeway Infrastructure is built in terms of promoting Chinese society economic development, has been played to Guan Chong
Guiding, the basic supporting role wanted and service effectiveness.
China's express highway intelligent, informationization obtained construction energetically and still in lasting progress, it is contemplated that city in 2023
Field scale will be close to 90,000,000,000 yuan.And the main two subsystems of express highway intelligent system are: intelligent toll system and security protection
Monitoring system.According to incompletely statistics, whole nation highway supervisor at different levels and operating division have disposed the video monitoring for having built 8 Wan Yulu
Resource, national charge station totally 25505 (are free of Hong Kong, Macao and Taiwan: deriving from Baidu map).
With the continuous expansion of China's Free Way Networking operating mileage being continuously increased with operation management coverage area, people
Higher expectation is proposed to transport science and techonologies, it is desirable to traffic can step into the epoch of intelligent traffic, grasp highway
Correct prediction is made to the vehicle flowrate in highway future on the basis of flow, is that China carries out transport development, steps into intelligence
Change the essential condition of field of traffic.Become a research hotspot of intelligent transportation field for the prediction of the magnitude of traffic flow, it is quasi-
True ground prediction result can carry out traffic control for traffic management department and provide decision and support.
As a large amount of traffic video equipment are laid along highway and are come into operation and networking charging system, hand in real time
The current data of logical video data and charge station are transferred to freeway traffic regulation department incessantly, and traffic data is in explosive
Increase, along with the decision for relying primarily on people to the analytical judgment of vision signal in the past, so that China's freeway management and clothes
The problem of business, is increasingly prominent.The problems such as sensing capability of freeway net is insufficient, and traffic forecast early warning means are short of is badly in need of taking on a new look.
The current data of traffic video monitoring data and charge station are made full use of, for freeway management person from passively in management
Information is collected into actively monitoring, realizes that policymaker is changed from Passive Management to active, humanized way to manage, to improve
The travelling of express highway pavement traffic traffic efficiency and traveler is experienced, and just more seems important.
Summary of the invention
Freeway traffic time map construction method provided by the invention based on fused data, system, mainly solve
The technical issues of be: the traffic noise prediction of highway how is more accurately predicted.
In order to solve the above technical problems, the present invention provides a kind of freeway traffic time map system based on fused data
System, comprising: charge station supervises subsystem, road supervision subsystem and traffic situation predicting subsystem;
Charge station's supervision subsystem is included in the toll station set up at each entrance of targeted cache highway, described
Toll station includes identification module, logging modle, data analysis module and the first memory module, and the identification module is for knowing
It Jing Guo not the license plate of each vehicle of the toll station, vehicle;The logging modle is for recording when entering the station of each vehicle
Between, the outbound time;The data analysis module be used for the license plate based on each vehicle, realize to each vehicle enter the station with
Outbound tracking, and the running time of each vehicle is calculated separately, and receive according to the running time of the vehicle and the vehicle pull-in
Take the distance between website and outbound toll station, calculates the first average speed of the vehicle;And for identical charge of entering the station
Website, and each vehicle of identical outbound toll station, identical toll station and the identical outbound toll station of entering the station
It is counted for adjacent toll station according to the first average speed of each vehicle and the corresponding vehicle of each vehicle
All vehicles under same model, in the second average speed of target road section;The target road section is the identical charge of entering the station
Section between website and the identical outbound toll station;First memory module is for storing the described of each vehicle
License plate, the vehicle, the time of entering the station, the outbound time, first average speed and second average speed;
The road supervision subsystem includes the one or more video monitorings laid on the way in the targeted cache highway
Point, image processing module and the second memory module, each video surveillance point effectively monitor in region for acquiring it in real time
Traffic video image;Described image processing module is used to be based on the collected traffic video image of the video surveillance point, meter
Calculate the bicycle speed of each vehicle and the average speed of the third of each vehicle in effective monitoring region of each video surveillance point
Degree;Second memory module is for storing the traffic video image, the bicycle speed, the third average speed;
The traffic situation predicting subsystem includes setting module, the first acquisition module, the second acquisition module, processing module
And building module, the setting module originate observation time point t0, rolling forecast for receiving external setting instruction with setting
Cycle T and predicted time t;
Described first, which obtains module, is used to obtain according to the rolling forecast cycle T from charge station supervision subsystem
The vehicle currently to enter the station from each toll station as the first vehicle to be measured, and obtains and the described first vehicle vehicle to be measured
And matched second average speed of driving direction, and using matched second average speed as first object speed V1;
Described second obtains module, for obtaining from road supervision subsystem each according to the rolling forecast cycle T
Its currently collected described bicycle speed for effectively monitoring each vehicle in region of the video surveillance point, the third are average
The third average speed of speed and the downstream visual monitoring point adjacent with the video surveillance point, by the video surveillance point
Current collected its effectively monitors each vehicle in region as the second vehicle to be measured;And based on the bicycle speed, described
The third average speed of third average speed and the adjacent downstream visual monitoring point, determines the described second vehicle to be measured
Second target velocity V2;
The processing module, for each first vehicle to be measured and each second vehicle to be measured to be presently in position
It sets, is loaded into the traffic network of the targeted cache highway, and be based on the first object speed V1, predict each described the
First operating range S1 of one vehicle to be measured after predicted time t is based on the second target velocity V2, prediction each described second
Second operating range S2 of the vehicle to be measured after predicted time t;
The building module, for corresponding to the traffic network of the targeted cache highway according to the first operating range S1
Described first vehicle to be measured is loaded into the first object position by middle place first object position, according to second traveling
Second target position where distance S2 is corresponded in the traffic network of the targeted cache highway loads the described second vehicle to be measured
To second target position, to generate freeway traffic time map.
Optionally, the toll station further includes first direction prediction module, logical for obtaining the described first vehicle to be measured
The current record of the last history of the toll station is crossed, if the last time history passage is recorded as the toll station
As entering the station, then by the outbound driving direction passed through as this of the last current record of history;If described
The last history is current to be recorded as the toll station as outbound, then entering the station the last current record of history
The driving direction passed through as this.
Optionally, the toll station further includes second direction prediction module, logical for obtaining the described first vehicle to be measured
The current record of history for crossing the toll station walks the probability of happening of different directions, choosing according to the current record statistics of the history
Select driving direction corresponding to probability of happening maximum, the driving direction passed through as this.
Optionally, the second acquisition module is for judging whether the third average speed of the downstream visual monitoring point is deposited
, if so, the size relation of the third average speed of the third average speed and the downstream visual monitoring point is calculated, according to
The size relation and the bicycle speed calculate the second target velocity V2;If not, using the bicycle speed as
The second target velocity V2.
Optionally, the second acquisition module is used to exist in the third average speed for judging the downstream visual monitoring point
When, the first difference of the third average speed of the bicycle speed and the downstream visual monitoring point is calculated, it is poor described first
When value is greater than 0, the average value of the third average speed of the bicycle speed and the downstream visual monitoring point is calculated, as described
Second target velocity V2;When first difference is less than or equal to 0, using the bicycle speed as second target velocity
V2。
Optionally, the second acquisition module is used to exist in the third average speed for judging the downstream visual monitoring point
When, the third average speed of the downstream visual monitoring point and the first ratio of the third average speed are calculated, by described
Weighing factor of one ratio as the described second vehicle future travel speed to be measured, calculates the bicycle speed and the influence is weighed
Product between weight, as the second target velocity V2.
Optionally, the second acquisition module is used to exist in the third average speed for judging the downstream visual monitoring point
When, the absolute value of the second difference of the third average speed of the third average speed and the downstream visual monitoring point is calculated,
And the second ratio of the absolute value Yu the third average speed is calculated, it is less than or equal to preset threshold in second ratio
When, using the bicycle speed as the second target velocity V2;When second ratio is greater than the preset threshold, calculate
Mean value between the bicycle speed and the third average speed of the downstream visual monitoring point, as second target velocity
V2。
Optionally, the second acquisition module is used to exist in the third average speed for judging the downstream visual monitoring point
When, directly calculate the equal of the bicycle speed of the described second vehicle to be measured and the third average speed of the downstream visual monitoring point
Value, as the second target velocity V2.
Optionally, the traffic situation predicting subsystem further includes alarm module, each after predicted time t for determining
The vehicle density in section is monitored, and is alerted when the vehicle density reaches default vehicle density threshold value.
The present invention also provides a kind of freeway traffic time map system constituting method based on fused data, comprising:
Setting starting observation time point t0, rolling forecast cycle T and predicted time t;
According to the rolling forecast cycle T, the vehicle currently to enter the station from each toll station is obtained from charge station's supervision subsystem
, as the first vehicle to be measured, and obtain and the average speed of the described first vehicle vehicle and driving direction matched second to be measured
Degree, and using matched second average speed as first object speed V1;
According to the rolling forecast cycle T, from road supervision subsystem obtain each video surveillance point it is currently collected its
Bicycle speed, third average speed and the downstream adjacent with the video surveillance point of each vehicle effectively in monitoring region
Currently collected its of the video surveillance point is effectively monitored each vehicle in region by the third average speed of video surveillance point
As the second vehicle to be measured;And based on the bicycle speed, the third average speed and the adjacent downstream visual prison
The third average speed for controlling point, determines the second target velocity V2 of the described second vehicle to be measured;
Each first vehicle to be measured and each second vehicle to be measured are presently in position, are loaded into the target
In the traffic network of highway, and it is based on the first object speed V1, predicts each first vehicle to be measured in prediction
Between the first operating range S1 after t, be based on the second target velocity V2, predict each second vehicle to be measured in predicted time
The second operating range S2 after t;
First object position where being corresponded in the traffic network of the targeted cache highway according to the first operating range S1
It sets, the described first vehicle to be measured is loaded into the first object position, the mesh is corresponded to according to the second operating range S2
The second target position where in the traffic network of highway is marked, the described second vehicle to be measured is loaded into second target position
It sets, to generate freeway traffic time map.
The beneficial effects of the present invention are:
The freeway traffic time map construction method based on fused data that there is provided according to the present invention, system, pass through
Freeway traffic data (video monitoring data and the current data of charge station) predict the traffic condition of highway, send out
The utilization rate of freeway traffic data is dug and improved to the maximum extent, and has fully considered the duration of traffic flow, favorably
In the accuracy for improving prediction;In addition, transport development situation is the decision-making foundation that traffic administration person implements control, can help to hand over
Logical administrative department's science, makes a policy to wisdom at active, is advantageously implemented wisdom traffic.
Detailed description of the invention
Fig. 1 is a kind of freeway traffic time map system structure diagram of the embodiment of the present invention one;
Fig. 2 is another freeway traffic time map system structure diagram of the embodiment of the present invention one;
Fig. 3 is the schematic diagram of the freeway traffic time map of the embodiment of the present invention one;
Fig. 4 is the freeway traffic time map construction method flow diagram of the embodiment of the present invention two.
Specific embodiment
In order to make the objectives, technical solutions, and advantages of the present invention clearer, below by specific embodiment knot
Closing attached drawing, invention is further described in detail.It should be appreciated that specific embodiment described herein is only used to explain this
Invention, is not intended to limit the present invention.
Embodiment one:
In order to realize the Accurate Prediction to freeway traffic operation conditions, to provide traffic control to traffic administration part
With dredge decision, support, the present embodiment provides a kind of scheme of freeway traffic time map system, it is high at present to pass through fusion
The current data of the monitoring point video data of fast network of highways and charge station, realize the prediction to future prediction time traffic condition,
And it is online that predictive information is loaded into highway, forms freeway traffic time map, freeway traffic time map
Refer to the variation tendency that traffic condition shows on road network at any time, is based on the time map, the backstage of traffic management department
Administrative staff can intuitively learn the wagon flow distribution situation of future prediction time, convenient for making alarm, control prediction scheme in time, with
Alleviate traffic congestion, improve the treatment effeciency of anomalous event, realizes wisdom traffic.
Referring to Figure 1, Fig. 1 is freeway traffic time map system structure diagram provided in this embodiment, the height
Fast highway communication time map system 100, including charge station's supervision subsystem 110, road supervision subsystem 120 and traffic state
Gesture predicting subsystem 130;Wherein
Charge station's supervision subsystem 110 is included in the toll station set up at each entrance of targeted cache highway, described
Toll station includes identification module 111, logging modle 112, data analysis module 113 and the first memory module 114.
In the present embodiment, the section that targeted cache highway can be predicted according to actual needs is chosen, and actual needs is pre-
The section of survey for example can be the section etc. that traffic condition compares congestion.It is complete that targeted cache highway can be a certain fastlink
Journey, or all fastlinks in whole city in part of section or certain city are chosen, or all expressways in the whole nation
Section.
Identification module 111 is for identification by the license plate of each vehicle of toll station, vehicle;Wherein vehicle includes but unlimited
In kart, jubilee wagen, medium-sized client, marquee account, medium truck, large-sized truck etc..
Logging modle 112 is used to record time of entering the station, the outbound time of each vehicle by toll station.
Data analysis module 113 is used for the license plate based on each vehicle, and realization chases after entering the station for each vehicle with outbound
Track, and calculate separately the running time of each vehicle, and according to the running time of the vehicle and the vehicle pull-in toll station with
Distance between outbound toll station calculates the first average speed of the vehicle.It refers to as shown in table 1 below:
Table 1
Data analysis module 113 is also used to, for the identical toll station that enters the station, and each vehicle of identical outbound toll station
, and the identical toll station that enters the station outbound toll station identical as this is adjacent toll station, according to the first of each vehicle
Average speed and the corresponding vehicle of each vehicle count all vehicles under same model, and second in target road section is average
Speed.Target road section is the section between the identical toll station that enters the station outbound toll station identical as this.
Optionally, data analysis module 113 is also used to count different automobile types at times in the second average speed of target road section
Degree.Such as daytime, evening, peak and non-peak or other typical period of time.Prediction result can be made more accurate in this way.
By taking above-mentioned table 1 as an example, it is assumed that toll station TOLL1 and TOLL2 is adjacent toll station, data analysis module 113
Based on the current data of history, second average speed of the available kart in target road section (section of TOLL1 to TOLL2)
Degree are as follows: 100km/h+83km/h=91.5km/h.
In practical application, for it is identical enter the station toll station and the vehicle of the same vehicle of identical outbound toll station compared with
More, practical the second average speed being calculated more can accurately reflect the average speed of the vehicle.
First memory module 114 is used to store through the license plate of each vehicle of toll station, vehicle, the time of entering the station, outbound
Time, the first average speed and the second average speed.
Toll station further includes first direction prediction module 115, refers to Fig. 2, and first direction prediction module 115 is used for
The last history current record of first vehicle to be measured by the toll station is obtained, if the last history passage is recorded as
The toll station is as entering the station, then by the outbound driving direction passed through as this of the current record of the last time history;If
The last history passage is recorded as the toll station as conduct of entering the station that is outbound, then recording the last time history passage
This driving direction passed through.
For example, when the vehicle to enter the station from toll station TOLL1 " Shanghai A1234* " being currently used as the first vehicle to be measured, direction
History current record of the available vehicle the last time of prediction module 115 by toll station TOLL1, the toll station
TOLL1 may be outbound, it is also possible to it enters the station, when the last time is entered the station from toll station TOLL1, then this vehicle
Current direction is probably identical as last passage direction, i.e., travels to last outbound direction;If the last time be from
Toll station TOLL1 is outbound, then this enters the station from toll station TOLL1, it is more likely that be sail go back to former destination, namely
The enter the station direction running current to the last time, to return to former destination.It, can be accurate pre- to a certain extent based on which
The driving direction of the first vehicle to be measured is surveyed, but can not be completely secured.
In practical application, when first vehicle to be measured passes through record there is no the history by the toll station, then may be used
In a manner of taking and determine at random, to determine this driving direction.Or it is determined using existing other modes.
The present embodiment also provides a kind of prediction technique of driving direction: toll station further includes second direction prediction module
116, for obtaining history current record of first vehicle to be measured by the toll station, walked not according to the current record statistics of history
Equidirectional probability of happening selects driving direction corresponding to probability of happening maximum, the driving direction passed through as this.
The current record of the first vehicle history to be measured is counted, its traveling rule is determined, determines this walking different directions
Probability is simultaneously allocated;Such as the number to enter the station from this charge station is 10 times, wherein being for 9 times to walk the direction A, then this walks the side A
To probability be 90%, wherein 1 time is walked the direction B, this this probability for walking the direction B is 10%.It can choose the conduct of the direction A at this time
This driving direction.If rule is unobvious, then determines driving direction with current record of the last history;Remember again or not
Record is then randomly assigned.
Optionally, a monitoring camera can be set at the ring road shunting entered after toll station, accurately to capture the
The driving direction of one vehicle to be measured.
Road supervision subsystem 120 include the one or more video surveillance points 121 laid on the way in targeted cache highway,
Image processing module 122 and the second memory module 123.
Each video surveillance point 121 for acquiring respectively the traffic video image in effectively monitoring region in real time.
Image processing module 122 is used to be based on the collected traffic video image of video surveillance point 121, calculates each video prison
The bicycle speed of each vehicle in the effectively monitoring region of control point 121, and the third by each vehicle in its effectively monitoring region
Average speed.
Optionally, the current collected video image frame of video surveillance point 121 is obtained according to rolling forecast cycle T, and
The former frame (being actually not limited to former frame) of the current video picture frame, due in front of and after frames image there may be more vehicles,
Therefore it needs to identify the corresponding relationship of vehicle in the vehicle and a later frame image in previous frame image, namely needs to realize vehicle
Tracking, to can just accurately obtain the bicycle speed of each vehicle to be measured.
Optionally, it is based on former frame and current frame image, the registration of vehicle image is obtained, car tracing may be implemented.
Two vehicle picture registration degrees are higher, show more to be likely to be same vehicle.Then, it is based in the two field pictures of front and back, the vehicle to be measured
The movement of locating pixel position determines its practical moving distance;According to video camera Image Acquisition frame per second, two can be determined
Time difference (i.e. traveling time) between frame image, thus according to practical moving distance, traveling time, can be calculated this to
The bicycle speed of measuring car.
In the case where the monitoring point is calculated, after the bicycle speed of each first vehicle to be measured, can be obtained each under the monitoring point
The third average speed of first vehicle to be measured.Assuming that there are three the first vehicles to be measured, bicycle speed difference under the monitoring point
For a1, a2 and a3, then the third average speed of each vehicle is (a1+a2+a3)/3 under the monitoring point.
It, completely can be with it should be understood that the mode of the bicycle speed of above-mentioned calculating first vehicle to be measured is not limited to this
Using existing other modes, as long as can determine the bicycle speed of each first vehicle to be measured.
It should be noted that the first vehicle to be measured is not present when in the currently active monitoring region of video surveillance point 121
When, processing can be marked.
Second memory module 123 is used to store the traffic video image of the acquisition of video surveillance point 121, each first vehicle to be measured
Bicycle speed, third average speed.
Traffic situation predicting subsystem 130 includes that setting module 131, first obtains the acquisition module 133 of module 132, second,
Processing module 134 and building module 135.
Wherein, setting module 131 originates observation time point t0, rolling forecast for receiving external setting instruction with setting
Cycle T and predicted time t.
The targeted cache highway predicted for needs, it is contemplated that monitored point lays the influence of spacing, usual phase on road network
There are blind area of monitoring between adjacent monitoring point, the vehicle in the blind area of monitoring can not just be supervised by this two adjacent monitoring point
It controls.Therefore when constructing freeway traffic time map, will because of omitting these vehicles being in monitoring blind area,
Leading to constructed freeway traffic time map, there are large errors.For this purpose, the present embodiment is seen by presetting starting
Time point t0 is surveyed, to reduce the influence of this error.Specifically, the selected principle of starting observation time point t0 is: targeted cache
The vehicle least moment on highway controls the influence that the error of original state predicts vehicle density to greatest extent.For example, selection
3 points of morning as starting observation time point t0.
Rolling forecast cycle T can be according to system process performance, the monitoring data amount of targeted cache highway or traffic pipe
Reason department demand is flexibly set, if system process performance is higher, monitoring data amount is smaller, and rolling forecast cycle T then can be with
It is set as smaller, keeps pre- measured frequency higher, improve forecasting accuracy;On the contrary, if system process performance is lower, monitoring data amount compared with
Greatly, then the problem of rolling forecast cycle T needs are arranged relatively large, avoid system from handling overload, lead to paralysis.
Rolling forecast cycle T is for example set as 1 second, 10 seconds, 1 minute, 5 minutes, 10 minutes etc..
First, which obtains module 132, is used for according to rolling forecast cycle T, from charge station's supervision subsystem 110 obtain currently from
The vehicle that each toll station enters the station as the first vehicle to be measured, and obtains the vehicle and driving direction with the first vehicle to be measured
Matched second average speed, and using matched second average speed as first object speed V1.
It is counted at times in the second average speed for different automobile types, then matched second average speed also needs
Consider the locating period.For example Monday peak should be with reference to peak period history Monday with the second average speed of vehicle.
It should be noted that the current data of charge station's supervision available history of subsystem 110, obtain different automobile types in mesh
Mark second average speed in section.Such as kart, (such as toll station TOLL1 is extremely for target road section in one direction
TOLL2 the second average speed) be 91.5km/h, another direction target road section (such as toll station TOLL1 to charge
Website TOLL3) the second average speed be 90km/h.When the vehicle of the first vehicle to be measured to enter the station from toll station TOLL1
For kart, and when driving direction is TOLL1, then the first acquisition module 132 is assured that and first vehicle to be measured
Matched second average speed is 91.5km/h.
It should be understood that a usual toll station is there are two driving direction, but the present embodiment is to this and with no restrictions,
When there are multiple driving directions, charge station supervises subsystem 110, this needs to record according to history is current, determines and arrives different vehicles
The second average speed of type in all directions.First to obtain module 132 same, it is only necessary to according to the vehicle of the first vehicle to be measured with
And driving direction, that is, it can determine and (also needed when counting at times with the vehicle in matched second average speed of the driving direction
Know present period).
Second obtains module 133, for obtaining each video prison from road supervision subsystem 120 according to rolling forecast cycle T
Bicycle speed of its current collected each vehicle effectively in monitoring regions of control point 121, third average speed and with the view
The third average speed of the adjacent downstream visual monitoring point in frequency monitoring point has current collected its of the video surveillance point 121
Each vehicle in effect monitoring region is as the second vehicle to be measured;And based on its bicycle speed, third average speed and this is adjacent
Downstream visual monitoring point third average speed, determine the second target velocity V2 of the second vehicle to be measured.
Optionally, the second acquisition module 133 is used to judge that the third average speed of the downstream visual monitoring point whether there is,
If it is present calculating the big of the 121 third average speed of video surveillance point and the third average speed of downstream visual monitoring point
Small relationship calculates the second target speed of the second vehicle to be measured according to the size relation and the bicycle speed of the second vehicle to be measured
Spend V2;If third average speed is not present in adjacent downstream video surveillance point, show effective monitoring region of the downstream monitoring point
It is interior that vehicle to be measured is not present, it can be considered that the respective stretch traffic status ratio of downstream visual monitoring point is smoothly, therefore can
Using by the bicycle speed of second vehicle to be measured as the second target velocity V2, for predicting.
The third average speed of this video surveillance point 121 can reflect the currently active monitoring section of this video surveillance point 121
Vehicle pass-through situation in domain, and the third average speed of downstream visual monitoring point adjacent thereto, also can reflect the downstream
Video surveillance point effectively monitors the vehicle pass-through situation in region.The continuity characteristic for having comprehensively considered traffic flow, in conjunction with current
Traffic status and downstream traffic status can make prediction result more accurate to obtain the second target velocity for prediction.
Optionally, the second acquisition module 133 in the third average speed for judging the adjacent downstream video surveillance point for depositing
When, directly bicycle speed and the third average speed of the adjacent downstream video surveillance point of the second vehicle to be measured of calculating is equal
Value, as the second target velocity V2.
Optionally, the second acquisition module 133 is used in the presence of judging the third average speed of the downstream visual monitoring point,
The first difference for calculating the bicycle speed of the second vehicle to be measured and the third average speed of downstream visual monitoring point, in the first difference
When greater than 0, i.e., when size relation is greater than the third average speed of adjacent downstream monitoring point for the bicycle speed of the second vehicle to be measured,
The average value of its bicycle speed and the third average speed of the downstream visual monitoring point is calculated, the average value is to be measured as second
Second target velocity V2 of vehicle;The first difference be less than or equal to 0 when, i.e., size relation be the second vehicle to be measured bicycle speed
Less than or equal to adjacent downstream monitoring point third average speed when, show that downstream road section is relatively more unobstructed, will not be to this video
The passage of the vehicle to be measured of the second of monitoring point 121 produces bigger effect, therefore using its bicycle speed as the second target velocity
V2。
Optionally, the second acquisition module 133 in the third average speed for judging the adjacent downstream video surveillance point for depositing
When, calculate the first ratio of the third average speed of the downstream visual monitoring point and the third average speed of this video surveillance point
Value, using first ratio as the weighing factor of the second vehicle future travel speed to be measured, calculates its bicycle speed and the influence
Product between weight, as the second target velocity V2.
Optionally, the second acquisition module 133 in the third average speed for judging the adjacent downstream video surveillance point for depositing
When, calculate the second difference of the third average speed of this video surveillance point and the third average speed of the downstream visual monitoring point
Absolute value, and calculate the second ratio of the third average speed of the absolute value and this video surveillance point, be less than in the second ratio
When equal to preset threshold, show section locating for section traffic status locating for this video surveillance point and adjacent downstream video surveillance point
Traffic status is suitable, at this time using the bicycle speed of the second vehicle to be measured as the second target velocity V2;It is greater than in the second ratio pre-
If when threshold value, showing that current road segment differs more with the traffic status of downstream road section or current road segment passage is smooth, downstream is gathered around
Stifled or current road segment congestion, downstream are smooth;The bicycle speed and the downstream visual monitoring point of the second vehicle to be measured are calculated at this time
Third average speed between mean value, using the mean value as the second target velocity V2.
Wherein, preset threshold can flexible setting according to the actual situation, such as be set as 5%, 10%, 20% etc..
Processing module 134 is loaded into for each first vehicle to be measured and each second vehicle to be measured to be presently in position
In the traffic network of targeted cache highway, and it is based on first object speed V1, predicts the first vehicle to be measured after predicted time t
First operating range S1 is based on the second target velocity V2, predicts second operating range of second vehicle to be measured after predicted time t
S2。
Wherein S1=V1*t;S2=V2*t.First vehicle to be measured generally there are more, due to the toll station that enters the station is different,
Driving direction difference or vehicle difference etc., corresponding first object speed V1 is generally different;Equally, for each second
Vehicle to be measured, due to the of its bicycle speed, the third average speed of this video surveillance point and adjacent downstream video surveillance point
Three average speeds are different, and corresponding second target velocity V2 may also be different.
Module 135 is constructed, for correspond in the traffic network of targeted cache highway place the according to the first operating range S1
Corresponding first vehicle to be measured is loaded into the first object position by one target position;Target is corresponded to according to the second operating range S2
Second target position where in the traffic network of highway, is loaded into second target position for corresponding second vehicle to be measured,
To generate freeway traffic time map.
Optionally, with continued reference to Fig. 2, traffic situation predicting subsystem 130 can also include alarm module 136, for true
It is scheduled on the vehicle density respectively monitored in section after predicted time t, and reaches default vehicle density threshold value when progress in vehicle density
Alarm.It should be understood that vehicle density refers to the vehicle flowrate on unit length section.
Optionally, with continued reference to Fig. 2, traffic situation predicting subsystem 130 can also include display module 137, for opening up
Show freeway traffic time map.
Shown in Figure 3, Fig. 3 is the schematic diagram of freeway traffic time map provided in this embodiment:
For the first vehicle A1 to be measured, after predicted time t, prediction will drive to position K1 ' (the first mesh from position K1
Cursor position);For the second vehicle A2 to be measured, after predicted time t, prediction will drive to position K2 ' (the second mesh from position K2
Cursor position).By the traffic time map, first is that the Accurate Prediction to traffic condition is realized, in addition with traffic time map
Form be shown, it is simple and clear.
Freeway traffic time map system provided in this embodiment, according to the monitoring point video of current freeway net
The current data of data and charge station, realize to the building of freeway traffic time map and estimating for vehicle density, base
In the freeway traffic time map, traffic management department can very easily recognize, any time in predicted time t
The traffic traffic status of targeted cache highway;Meanwhile being shown in the form of traffic time map, it is more intuitive, clear.
Embodiment two:
Embodiment on the basis of the above embodiment 1, a kind of freeway traffic time map construction method is provided,
Fig. 4 is referred to, this method mainly includes the following steps:
S401, setting starting observation time point t0, rolling forecast cycle T and predicted time t.
S402, according to rolling forecast cycle T, obtain the vehicle currently to enter the station from each toll station from charge station's supervision subsystem
, as the first vehicle to be measured, and the vehicle and matched second average speed of driving direction with the first vehicle to be measured are obtained,
And using matched second average speed as first object speed V1.
Optionally, the last history current record of first vehicle to be measured by the toll station is obtained, if nearest one
The current toll station that is recorded as of secondary history is as entering the station, then by the outbound as this passage of the current record of the last history
Driving direction;The toll station is recorded as outbound if the last history is current, is remembered the last history is current
The driving direction passed through as this that enters the station of record.
In practical application, when first vehicle to be measured passes through record there is no the history by the toll station, then may be used
In a manner of taking and determine at random, to determine this driving direction.Or it is determined using existing other modes.
It should be noted that the current data of the available history of charge station's supervision subsystem, obtain different automobile types in target
Second average speed in section.Such as kart, (such as toll station TOLL1 is extremely for target road section in one direction
TOLL2 the second average speed) be 91.5km/h, another direction target road section (such as toll station TOLL1 to charge
Website TOLL3) the second average speed be 90km/h.When the vehicle of the first vehicle to be measured to enter the station from toll station TOLL1
For kart, and when driving direction is TOLL2, then be assured that with it is the second of first vehicle match to be measured average
Speed is 90km/h.
S403, according to rolling forecast cycle T, from road supervision subsystem obtain each video surveillance point it is currently collected its
Bicycle speed, third average speed and the downstream view adjacent with the video surveillance point of each vehicle effectively in monitoring region
The third average speed of frequency monitoring point, using the video surveillance point it is currently collected its effectively monitoring region in each vehicle as
Second vehicle to be measured;And it is flat based on the third of its bicycle speed, third average speed and the adjacent downstream visual monitoring point
Equal speed determines the second target velocity V2 of the second vehicle to be measured.
Optionally, the third based on its bicycle speed, third average speed and the adjacent downstream visual monitoring point is flat
Equal speed determines that the second target velocity V2 of the second vehicle to be measured includes:
Judge that the third average speed of the adjacent downstream video surveillance point whether there is, if it is present calculating the video
The size relation of the third average speed of monitoring point third average speed and the adjacent downstream video surveillance point, is closed according to the size
The bicycle speed of system and the second vehicle to be measured calculates the second target velocity V2 of the second vehicle to be measured;If adjacent downstream regards
Third average speed is not present in frequency monitoring point, shows that vehicle to be measured is not present in effective monitoring region of the downstream monitoring point, because
This can consider the respective stretch traffic status ratio of downstream visual monitoring point smoothly, therefore can be by second vehicle to be measured
Bicycle speed is as the second target velocity V2, for predicting.
The third average speed of this video surveillance point can reflect in the currently active monitoring region of this video surveillance point
Vehicle pass-through situation, and the third average speed of downstream visual monitoring point adjacent thereto also can reflect adjacent downstream view
Frequency monitoring point effectively monitors the vehicle pass-through situation in region.The continuity influencing characterisitic for having comprehensively considered traffic flow, in conjunction with working as
Preceding traffic status and downstream traffic status can make prediction result more to obtain the second target velocity V2 for prediction
Accurately.
Optionally, in the presence of judging the third average speed of the adjacent downstream video surveillance point, directly calculate second to
The mean value of the third average speed of the bicycle speed and adjacent downstream video surveillance point of measuring car, as the second target velocity
V2。
Optionally, in the presence of judging the third average speed of the adjacent downstream video surveillance point, the average speed of third is calculated
First difference of degree and the third average speed of the adjacent downstream video surveillance point, when the first difference is greater than 0, i.e. size relation
When being greater than the third average speed of adjacent downstream monitoring point for the third average speed of the second vehicle to be measured, show downstream road section phase
To congestion, certain influence can be generated on the passage in the second vehicle future to be measured, in order to guarantee the accuracy of prediction, by calculating it
The average value of the third average speed of bicycle speed and the adjacent downstream video surveillance point, using the average value as second to measuring car
The second target velocity V2.
When the first difference is less than or equal to 0, i.e., size relation is that the third average speed of the second vehicle to be measured is less than or equal to
When the third average speed of adjacent downstream monitoring point, show that downstream road section is relatively more unobstructed, it will not be to this video surveillance point
The passage of second vehicle to be measured produces bigger effect, therefore directly using its bicycle speed as the second target velocity V2.
Optionally, in the presence of judging the third average speed of the adjacent downstream video surveillance point, the adjacent downstream is calculated
First ratio of the third average speed of the third average speed and this video surveillance point of video surveillance point makees first ratio
For the weighing factor of the second vehicle future travel speed to be measured, the product between its bicycle speed and the weighing factor is calculated, is made
For the second target velocity V2.
Optionally, in the presence of judging the third average speed of the adjacent downstream video surveillance point, this video monitoring is calculated
The absolute value of second difference of the third average speed of the third average speed and downstream visual monitoring point of point, and calculate this absolutely
To the second ratio of value and third average speed, when the second ratio is less than or equal to preset threshold, by the list of the second vehicle to be measured
Vehicle speed is as the second target velocity V2;When the second ratio is greater than preset threshold, the bicycle speed of the second vehicle to be measured is calculated
Mean value between the third average speed of the downstream visual monitoring point, using the mean value as the second target velocity V2.
Wherein, preset threshold can flexible setting according to the actual situation, such as be set as 5%, 10%, 20% etc..
It should be noted that the execution sequence of step S402 and S403 are not intended to limit, the two can parallel processing.
S404, each first vehicle to be measured and each second vehicle to be measured are presently in position, are loaded into targeted cache public affairs
In the traffic network on road, and be based on first object speed V1, predict the first vehicle to be measured after predicted time t first traveling away from
From S1, it is based on the second target velocity V2, predicts second operating range S2 of second vehicle to be measured after predicted time t.
Wherein S1=V1*t;S2=V2*t.First vehicle to be measured generally there are more, due to the toll station that enters the station is different,
Driving direction difference or vehicle difference etc., each first corresponding first object speed V1 of vehicle to be measured are usually difference
's;Equally, vehicle to be measured for each second, due to its bicycle speed, the third average speed of this video surveillance point and adjacent
The third average speed of downstream visual monitoring point is different, and corresponding second target velocity V2 is likely to be different.
S405, place first object position in the traffic network of targeted cache highway is corresponded to according to the first operating range S1,
First vehicle to be measured is loaded into the first object position, the traffic road of targeted cache highway is corresponded to according to the second operating range S2
Second target position where in net, is loaded into second target position for the second vehicle to be measured, when generating freeway traffic
Between map.
Obviously, those skilled in the art should be understood that each module of aforementioned present invention or each step can be with general
Computing device realizes that they can be concentrated on a single computing device, or be distributed in constituted by multiple computing devices
On network, optionally, they can be realized with the program code that computing device can perform, it is thus possible to be stored in
It is performed by computing device in computer storage medium (ROM/RAM, magnetic disk, CD), and in some cases, it can be with not
The sequence being same as herein executes shown or described step, or they are fabricated to each integrated circuit modules, or
Person makes multiple modules or steps in them to single integrated circuit module to realize.So the present invention is not limited to appoint
What specific hardware and software combines.
The above content is specific embodiment is combined, further detailed description of the invention, and it cannot be said that this hair
Bright specific implementation is only limited to these instructions.For those of ordinary skill in the art to which the present invention belongs, it is not taking off
Under the premise of from present inventive concept, a number of simple deductions or replacements can also be made, all shall be regarded as belonging to protection of the invention
Range.
Claims (10)
1. a kind of freeway traffic time map system based on fused data, which is characterized in that the freeway traffic
Time map system includes charge station's supervision subsystem, road supervision subsystem and traffic situation predicting subsystem;
Charge station's supervision subsystem is included in the toll station set up at each entrance of targeted cache highway, the charge
Website includes identification module, logging modle, data analysis module and the first memory module, and the identification module passes through for identification
Cross license plate, the vehicle of each vehicle of the toll station;The logging modle is used to record the time of entering the station of each vehicle, goes out
It stands the time;The data analysis module be used for the license plate based on each vehicle, realize to each vehicle enter the station with it is outbound
Tracking, and calculate separately the running time of each vehicle, and according to the running time of the vehicle and the vehicle pull-in charge station
Distance between point and outbound toll station, calculates the first average speed of the vehicle;And for the identical toll station that enters the station,
And each vehicle of identical outbound toll station, the identical toll station that enters the station are adjacent with the identical outbound toll station
Toll station counts identical vehicle according to the first average speed of each vehicle and the corresponding vehicle of each vehicle
All vehicles under type, in the second average speed of target road section;The target road section be it is described it is identical enter the station toll station with
Section between the identical outbound toll station;First memory module be used for store each vehicle the license plate,
The vehicle, the time of entering the station, the outbound time, first average speed and second average speed;
The road supervision subsystem includes one or more video surveillance points, the figure laid on the way in the targeted cache highway
As processing module and the second memory module, each video surveillance point is used to acquire it in real time and effectively monitors the traffic in region
Video image;Described image processing module is used to be based on the collected traffic video image of the video surveillance point, calculates
The bicycle speed of each vehicle and the average speed of the third of each vehicle in effective monitoring region of each video surveillance point
Degree;Second memory module is for storing the traffic video image, the bicycle speed, the third average speed;
The traffic situation predicting subsystem include setting module, first obtain module, second obtain module, processing module and
Module is constructed, the setting module originates observation time point t0, rolling forecast period for receiving external setting instruction with setting
T and predicted time t;
Described first, which obtains module, is used to obtain from charge station supervision subsystem current according to the rolling forecast cycle T
The vehicle to enter the station from each toll station, as the first vehicle to be measured, and obtain with the described first vehicle vehicle to be measured and
Matched second average speed of driving direction, and using matched second average speed as first object speed V1;
Described second obtains module, for obtaining from road supervision subsystem each described according to the rolling forecast cycle T
Its currently collected described bicycle speed for effectively monitoring each vehicle in region of video surveillance point, the average speed of the third
The third average speed of degree and the downstream visual monitoring point adjacent with the video surveillance point, the video surveillance point is worked as
Preceding collected its effectively monitors each vehicle in region as the second vehicle to be measured;And based on the bicycle speed, described the
The third average speed of three average speeds and the adjacent downstream visual monitoring point determines the of the described second vehicle to be measured
Two target velocity V2;
The processing module, for each first vehicle to be measured and each second vehicle to be measured to be presently in position,
Be loaded into the traffic network of the targeted cache highway, and be based on the first object speed V1, prediction each described first to
First operating range S1 of the measuring car after predicted time t is based on the second target velocity V2, predicts that each described second is to be measured
Second operating range S2 of the vehicle after predicted time t;
The building module, for corresponding to institute in the traffic network of the targeted cache highway according to the first operating range S1
In first object position, the described first vehicle to be measured is loaded into the first object position, according to second operating range
Second target position where S2 is corresponded in the traffic network of the targeted cache highway, is loaded into institute for the described second vehicle to be measured
The second target position is stated, to generate freeway traffic time map.
2. freeway traffic time map system as described in claim 1, which is characterized in that the toll station further includes
First direction prediction module, for obtaining the last history current note of described first vehicle to be measured by the toll station
It records, if the last time history is current to be recorded as the toll station as entering the station, the last history is passed through
The outbound driving direction passed through as this of record;If the last time history passage is recorded as the toll station
As the driving direction passed through as this that enters the station that is outbound, then recording the last history passage.
3. freeway traffic time map system as described in claim 1, which is characterized in that the toll station further includes
Second direction prediction module, for obtaining history current record of described first vehicle to be measured by the toll station, according to
The current record statistics of the history walks the probability of happening of different directions, selects driving direction corresponding to probability of happening maximum, makees
The driving direction passed through for this.
4. freeway traffic time map system as claimed in claim 2 or claim 3, which is characterized in that described second obtains mould
Block is for judging that the third average speed of the downstream visual monitoring point whether there is, if so, calculating the third average speed
It is fast according to the size relation and the bicycle with the size relation of the third average speed of the downstream visual monitoring point
Degree calculates the second target velocity V2;If not, using the bicycle speed as the second target velocity V2.
5. freeway traffic time map system as claimed in claim 2 or claim 3, which is characterized in that described second obtains mould
Block is used in the presence of judging the third average speed of the downstream visual monitoring point, calculates the bicycle speed and the downstream
First difference of the third average speed of video surveillance point calculates the bicycle speed and institute when first difference is greater than 0
The average value for stating the third average speed of downstream visual monitoring point, as the second target velocity V2;In first difference
When less than or equal to 0, using the bicycle speed as the second target velocity V2.
6. freeway traffic time map system as claimed in claim 4, which is characterized in that described second, which obtains module, uses
It is flat in the third in the presence of judging the third average speed of the downstream visual monitoring point, calculating the downstream visual monitoring point
First ratio of equal speed and the third average speed, using first ratio as the described second vehicle future travel to be measured
The weighing factor of speed calculates the product between the bicycle speed and the weighing factor, as second target velocity
V2。
7. freeway traffic time map system as claimed in claim 4, which is characterized in that described second, which obtains module, uses
In in the presence of judging the third average speed of the downstream visual monitoring point, the third average speed and the downstream are calculated
The absolute value of second difference of the third average speed of video surveillance point, and calculate the absolute value and the third average speed
The second ratio, when second ratio is less than or equal to preset threshold, using the bicycle speed as second target speed
Spend V2;When second ratio is greater than the preset threshold, the bicycle speed and the downstream visual monitoring point are calculated
Mean value between third average speed, as the second target velocity V2.
8. freeway traffic time map system as claimed in claim 2 or claim 3, which is characterized in that described second obtains mould
Block is used in the presence of judging the third average speed of the downstream visual monitoring point, directly calculates the described second vehicle to be measured
The mean value of the third average speed of bicycle speed and the downstream visual monitoring point, as the second target velocity V2.
9. freeway traffic time map system as claimed in claim 2 or claim 3, which is characterized in that the traffic situation is pre-
Surveying subsystem further includes alarm module, for determining the vehicle density respectively monitored in section after predicted time t, and in the vehicle
Current density is alerted when reaching default vehicle density threshold value.
10. a kind of freeway traffic time map construction method based on fused data characterized by comprising
Setting starting observation time point t0, rolling forecast cycle T and predicted time t;
According to the rolling forecast cycle T, the vehicle currently to enter the station from each toll station is obtained from charge station's supervision subsystem, is made
For the first vehicle to be measured, and obtain with the described first matched second average speed of vehicle vehicle and driving direction to be measured, and
Using matched second average speed as first object speed V1;
According to the rolling forecast cycle T, from road supervision subsystem obtain each video surveillance point it is currently collected its effectively
Monitor bicycle speed, third average speed and the downstream visual adjacent with the video surveillance point of each vehicle in region
The third average speed of monitoring point, using the video surveillance point it is currently collected its effectively monitoring region in each vehicle as
Second vehicle to be measured;And based on the bicycle speed, the third average speed and the adjacent downstream visual monitoring point
Third average speed, determine the second target velocity V2 of the described second vehicle to be measured;
Each first vehicle to be measured and each second vehicle to be measured are presently in position, are loaded into the targeted cache
In the traffic network of highway, and it is based on the first object speed V1, predicts each first vehicle to be measured after predicted time t
The first operating range S1, be based on the second target velocity V2, predict each second vehicle to be measured after predicted time t
Second operating range S2;
First object position where being corresponded in the traffic network of the targeted cache highway according to the first operating range S1, will
First vehicle to be measured is loaded into the first object position, corresponds to the targeted cache according to the second operating range S2
Second target position where in the traffic network of highway, is loaded into second target position for the described second vehicle to be measured, with
Generate freeway traffic time map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910270545.7A CN109979197B (en) | 2019-04-04 | 2019-04-04 | Method and system for constructing highway traffic time map based on fusion data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910270545.7A CN109979197B (en) | 2019-04-04 | 2019-04-04 | Method and system for constructing highway traffic time map based on fusion data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109979197A true CN109979197A (en) | 2019-07-05 |
CN109979197B CN109979197B (en) | 2021-01-29 |
Family
ID=67082993
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910270545.7A Active CN109979197B (en) | 2019-04-04 | 2019-04-04 | Method and system for constructing highway traffic time map based on fusion data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109979197B (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161120A (en) * | 2019-12-20 | 2020-05-15 | 华为技术有限公司 | Bayonet position determining method and bayonet management device |
CN111445714A (en) * | 2020-04-09 | 2020-07-24 | 安徽皖通科技股份有限公司 | Predictable severe weather analysis method for expressway |
CN111882858A (en) * | 2020-06-01 | 2020-11-03 | 重庆大学 | Method for predicting queuing length of expressway abnormal events based on multi-source data |
CN114884847A (en) * | 2022-06-14 | 2022-08-09 | 广东通立数据服务有限公司 | Monitoring system and method for highway network operation |
CN115240431A (en) * | 2022-09-20 | 2022-10-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Real-time online simulation system and method for traffic flow of highway toll station |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1611918A (en) * | 2003-10-28 | 2005-05-04 | 日本先锋公司 | Device, system and method for reporting a traffic condition and program and recording medium |
CN103838772A (en) * | 2012-11-26 | 2014-06-04 | 香港生产力促进局 | Multi-source traffic data fusion method |
CN104408921A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Traffic flow predicting method based on traffic simulation |
CN104658252A (en) * | 2015-02-10 | 2015-05-27 | 交通运输部科学研究院 | Method for evaluating traffic operational conditions of highway based on multisource data fusion |
CN107591002A (en) * | 2017-09-21 | 2018-01-16 | 电子科技大学 | A kind of freeway traffic parameter real-time estimation method based on distribution type fiber-optic |
CN107895392A (en) * | 2017-11-21 | 2018-04-10 | 许沛茹 | A kind of method for drafting of time map |
CN109118764A (en) * | 2018-09-03 | 2019-01-01 | 山东交通学院 | A kind of car networking communication system based on ZigBee |
CN109446881A (en) * | 2018-09-05 | 2019-03-08 | 重庆大学 | A kind of express highway section Traffic State Detection Method based on isomeric data |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9595191B1 (en) * | 2015-11-12 | 2017-03-14 | Lytx, Inc. | Traffic estimation |
-
2019
- 2019-04-04 CN CN201910270545.7A patent/CN109979197B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1611918A (en) * | 2003-10-28 | 2005-05-04 | 日本先锋公司 | Device, system and method for reporting a traffic condition and program and recording medium |
CN103838772A (en) * | 2012-11-26 | 2014-06-04 | 香港生产力促进局 | Multi-source traffic data fusion method |
CN104408921A (en) * | 2014-11-28 | 2015-03-11 | 江苏物联网研究发展中心 | Traffic flow predicting method based on traffic simulation |
CN104658252A (en) * | 2015-02-10 | 2015-05-27 | 交通运输部科学研究院 | Method for evaluating traffic operational conditions of highway based on multisource data fusion |
CN107591002A (en) * | 2017-09-21 | 2018-01-16 | 电子科技大学 | A kind of freeway traffic parameter real-time estimation method based on distribution type fiber-optic |
CN107895392A (en) * | 2017-11-21 | 2018-04-10 | 许沛茹 | A kind of method for drafting of time map |
CN109118764A (en) * | 2018-09-03 | 2019-01-01 | 山东交通学院 | A kind of car networking communication system based on ZigBee |
CN109446881A (en) * | 2018-09-05 | 2019-03-08 | 重庆大学 | A kind of express highway section Traffic State Detection Method based on isomeric data |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111161120A (en) * | 2019-12-20 | 2020-05-15 | 华为技术有限公司 | Bayonet position determining method and bayonet management device |
CN111445714A (en) * | 2020-04-09 | 2020-07-24 | 安徽皖通科技股份有限公司 | Predictable severe weather analysis method for expressway |
CN111882858A (en) * | 2020-06-01 | 2020-11-03 | 重庆大学 | Method for predicting queuing length of expressway abnormal events based on multi-source data |
CN114884847A (en) * | 2022-06-14 | 2022-08-09 | 广东通立数据服务有限公司 | Monitoring system and method for highway network operation |
CN115240431A (en) * | 2022-09-20 | 2022-10-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Real-time online simulation system and method for traffic flow of highway toll station |
CN115240431B (en) * | 2022-09-20 | 2023-02-10 | 深圳市城市交通规划设计研究中心股份有限公司 | Real-time online simulation system and method for traffic flow of highway toll station |
Also Published As
Publication number | Publication date |
---|---|
CN109979197B (en) | 2021-01-29 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109979197A (en) | Freeway traffic time map construction method based on fused data, system | |
CN104778834B (en) | Urban road traffic jam judging method based on vehicle GPS data | |
CN102819954B (en) | Traffic region dynamic map monitoring and predicating system | |
CN112489433B (en) | Traffic congestion analysis method and device | |
Li et al. | Identifying important variables for predicting travel time of freeway with non-recurrent congestion with neural networks | |
CN111915887A (en) | Integration and processing system and method based on multi-source heterogeneous traffic data | |
CN103247177A (en) | Large-scale road network traffic flow real-time dynamic prediction system | |
CN113053114B (en) | Dynamic prediction and inspection method for exit station and exit time of illegal vehicles on highway | |
CN102024330A (en) | Intelligent traffic signal control system, method and equipment based on high-definition video technology | |
CN104157139A (en) | Prediction method and visualization method of traffic jam | |
CN106408984B (en) | Urban traffic flow induction system based on Internet of things | |
CN109655107A (en) | Air quality monitoring method, device, vehicle and computer readable storage medium | |
Rehena et al. | Towards a framework for context-aware intelligent traffic management system in smart cities | |
CN105139463A (en) | Big data urban road pricing method and system | |
CN109872013A (en) | Freeway traffic time map construction method, apparatus and system | |
CN102024331A (en) | Intelligent traffic signal control system | |
CN105160867A (en) | Traffic information prediction method | |
CN114241762A (en) | Data acquisition and analysis system is synthesized to wisdom urban traffic based on thing networking | |
CN109816978B (en) | Regional group traffic guidance system and method considering dynamic response behaviors of drivers | |
Sundaresan et al. | Artificial intelligence and machine learning approaches for smart transportation in smart cities using blockchain architecture | |
Dahiya et al. | A study of speed-density functional relations for varying spatiotemporal resolution using Zen Traffic Data | |
CN117546218A (en) | Distributed multitasking machine learning for traffic prediction | |
Zou et al. | City-level traffic flow prediction via LSTM networks | |
CN105139328B (en) | Hourage real-time predicting method and device towards license plate identification data | |
CN104183150B (en) | Vehicle-mounted monomer road traffic state discriminating gear and method |
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 | ||
CB02 | Change of applicant information |
Address after: 401120 12th floor, building 11, No.106, west section of Jinkai Avenue, Yubei District, Chongqing Applicant after: Chongqing tongtochi Information Technology Co., Ltd Address before: 401120 12th floor, building 11, No.106, west section of Jinkai Avenue, Yubei District, Chongqing Applicant before: CHONGQING TONGJI TONLEA INFORMATION TECHNOLOGY Co.,Ltd. |
|
CB02 | Change of applicant information | ||
GR01 | Patent grant | ||
GR01 | Patent grant |