CN109887283A - A kind of congestion in road prediction technique, system and device based on bayonet data - Google Patents
A kind of congestion in road prediction technique, system and device based on bayonet data Download PDFInfo
- Publication number
- CN109887283A CN109887283A CN201910171067.4A CN201910171067A CN109887283A CN 109887283 A CN109887283 A CN 109887283A CN 201910171067 A CN201910171067 A CN 201910171067A CN 109887283 A CN109887283 A CN 109887283A
- Authority
- CN
- China
- Prior art keywords
- road
- congestion
- sequence
- behavioral characteristics
- bayonet data
- 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 kind of congestion in road prediction technique, system and devices based on bayonet data, and wherein method is the following steps are included: the behavioral characteristics for passing through a period road on bayonet data acquisition；In conjunction with the jam level of behavioral characteristics and preset congestion in road prediction model prediction subsequent time period road.The present invention passes through the behavioral characteristics of bayonet data acquisition road, and combine the jam situation of the subsequent time period of behavioral characteristics and congestion in road prediction model prediction road, the jam situation that can effectively and accurately predict traffic solves the problems, such as to cause forecasting inaccuracy true by artificial prediction；And the present invention can predict the traffic congestion situation in a wide range of area, improve forecasting efficiency, provide the efficiency of management of traffic management department and shorten the travel time of car owner and reduce Trip Costs, can be widely applied to field of intelligent transportation technology.
Description
Technical field
The present invention relates to field of intelligent transportation technology more particularly to a kind of congestion in road prediction sides based on bayonet data
Method, system and device.
Background technique
Currently, vehicle guaranteeding organic quantity constantly increases in city, and traffic pressure sharply increases, some areas traffic frequent occurrence
Congestion brings huge challenge for the unimpeded operational support of urban transportation, exacerbates the problem of management of traffic relevant departments, also gives vehicle
The appearance of masters brings inconvenience.In existing technology, predict to pass through generally by dependent on the subjective of people to his congestion is given
It tests, traffic congestion analyzes result inaccuracy, and can only realize the congestion forecast analysis in small range area, traffic forecast efficiency
Low, car owner's travel time increases, and Trip Costs are high.
Explanation of nouns:
Bayonet: safety inspection and monitoring bayonet and road traffic public security bayonet monitoring system including public security system setting,
Utilize advanced photoelectricity, computer, image procossing, pattern-recognition, the technologies such as WEB data access, to each of monitoring road surface
Front characteristic image, vehicle panoramic image and the road surface live video stream of motor vehicle carry out continuous round-the-clock real-time record, licence plate
Identifier carries out number plate of vehicle according to the image imaged and automatically identifies, and can be carried out vehicle dynamic and deploy to ensure effective monitoring and control of illegal activities and break rules and regulations to alarm,
It can be organic shared by each monitoring point information by police network.
Summary of the invention
In order to solve the above-mentioned technical problem, the object of the present invention is to provide one kind can be to traffic congestion feelings in a wide range of area
Prediction technique, system and the device of condition progress Accurate Prediction.
First technical solution of the present invention is:
A kind of congestion in road prediction technique based on bayonet data, comprising the following steps:
Pass through the behavioral characteristics of a period road on bayonet data acquisition；
In conjunction with the jam level of behavioral characteristics and preset congestion in road prediction model prediction subsequent time period road.
Further, further include the steps that establishing congestion in road prediction model, the step for establishing congestion in road prediction model
It is rapid specifically includes the following steps:
The bayonet data of road are obtained, and according to the information of vehicles of bayonet data acquisition multiple periods；
The behavioral characteristics sequence of road is obtained according to information of vehicles, and the static nature of road is obtained according to predetermined manner
Sequence；
It is gathered around in conjunction with the time that behavioral characteristics sequence, static nature sequence and preset jam level mark mode obtain road
Stifled sequence；
Binding time congestion sequence and preset algorithm establish congestion in road prediction model.
Further, the information of vehicles includes large car information of vehicles and compact car information of vehicles, described to be believed according to vehicle
Breath obtains the step for behavioral characteristics sequence of road, specifically includes the following steps:
The first vehicle flowrate and the first average speed of each period are calculated according to information of vehicles；
The second vehicle flowrate and the second average speed of the large car of each period are calculated according to large car information of vehicles, and
The third vehicle flowrate and third average speed of the compact car of each period are calculated according to compact car information of vehicles；
In conjunction with each hour the first vehicle flowrate, the first average speed, the second vehicle flowrate, the second average speed, third vehicle
Flow and third average speed obtain the behavioral characteristics sequence of road.
Further, the step for the static nature sequence that each road is obtained according to predetermined manner, specifically:
The attribute information of road is obtained, and attribute information and preset quantitative criteria is combined to obtain road static nature sequence
Column.
Further, the combination behavioral characteristics sequence, static nature sequence and preset jam level mark mode obtain
The step for time congestion sequence of road, specifically includes the following steps:
After behavioral characteristics sequence and static nature sequence are combined and be normalized, the spy of each period is obtained
Collection is closed；
After each characteristic set is marked according to preset jam level mark mode, time congestion sequence is obtained.
Further, the preset algorithm is Recognition with Recurrent Neural Network algorithm, the binding time congestion sequence and preset algorithm
The step for establishing congestion in road prediction model, specifically includes the following steps:
After binding time congestion sequence and Recognition with Recurrent Neural Network algorithm are trained congestion in road prediction model, obtain just
The congestion in road prediction model of beginning；
After being optimized using the method for cross-training to initial congestion in road prediction model, obtains final road and gather around
Stifled prediction model.
Further, the initial congestion in road prediction model specifically:
At=φ (S*WF+At-1*WA+b)
Wherein, the AtThe behavioral characteristics of subsequent time period are represented, the φ () represents neuron function, and the S is represented
Static nature, the At-1The behavioral characteristics of a upper period were represented, the WF represents road static nature in neuron function
Shared weight, the WA represent road behavioral characteristics weight shared in neuron function, and it is normal that the b represents bias term
Number.
Second technical solution of the present invention is:
A kind of congestion in road forecasting system based on bayonet data, comprising:
Characteristic module is obtained, for the behavioral characteristics by a period road on bayonet data acquisition；
Congestion prediction module, for predicting subsequent time period road in conjunction with behavioral characteristics and preset congestion in road prediction model
The jam level on road.
It further, further include model building module, the model building module includes information acquisition unit, feature acquisition list
Member, congestion marking unit and modeling unit；
The information acquisition unit is used to obtain the bayonet data of road, and according to bayonet data acquisition multiple periods
Information of vehicles；
The feature acquiring unit is used to obtain the behavioral characteristics sequence of road according to information of vehicles, and according to default side
The static nature sequence of formula acquisition road；
The congestion marking unit is used in conjunction with behavioral characteristics sequence, static nature sequence and preset jam level label
Mode obtains the time congestion sequence of road；
The modeling unit establishes congestion in road prediction model for binding time congestion sequence and preset algorithm.
Third technical solution of the present invention is:
A kind of congestion in road prediction meanss based on bayonet data, comprising:
At least one processor；
At least one processor, for storing at least one program；
When at least one described program is executed by least one described processor, so that at least one described processor is realized
A kind of above-mentioned congestion in road prediction technique based on bayonet data.
The beneficial effects of the present invention are: the present invention passes through the behavioral characteristics of bayonet data acquisition road, and combine dynamic special
Congestion in road prediction model of seeking peace predicts the jam situation of the subsequent time period of road, can effectively and accurately predict traffic
Jam situation solves the problems, such as to cause forecasting inaccuracy true by artificial prediction；And the present invention can be to the friendship in a wide range of area
Logical jam situation is predicted, forecasting efficiency is improved, and is provided the efficiency of management of traffic management department and is shortened going out for car owner
The row time and reduce Trip Costs.
Detailed description of the invention
Fig. 1 is a kind of step flow chart of the congestion in road prediction technique based on bayonet data of the present invention；
Fig. 2 is a kind of structural block diagram of the congestion in road forecasting system based on bayonet data of the present invention.
Specific embodiment
Embodiment one
As shown in Figure 1, present embodiments providing a kind of congestion in road prediction technique based on bayonet data, including following step
Suddenly
S1, pass through the behavioral characteristics of a period road on bayonet data acquisition.
S2, the jam level that subsequent time period road is predicted in conjunction with behavioral characteristics and preset congestion in road prediction model.
Speed when by the license plate number of the available vehicular traffic of bayonet, license plate type and crossing vehicle, the road
Behavioral characteristics include the features such as vehicle flowrate and speed, and after the behavioral characteristics for obtaining a upper period, behavioral characteristics are inputted road
Congestion prediction model predicts the features such as vehicle flowrate and the speed of subsequent time period, predicted congestion situation.The upper period and
Next time is continuous two periods, and the time cycle selects according to the actual situation；Such as: the upper period can be with
For a upper hour, next period can be next hour, for example a upper period is 7 points of the morning, then when next
Between section be 8 a.m.；Or a upper period is 7 a moment, then next period was 7 points two quarters.By combining dynamic special
Preset model of seeking peace predicts the jam situation of traffic, can be more smart due to combining more effective road parameters information
The jam situation of subsequent time period is predicted quasi-ly.In addition, due to being provided with more bayonet in city, it can be according to bayonet
Information predicts traffic condition, improves forecasting efficiency with carrying out a wide range of area, significantly more efficient to help to arrive traffic administration institute
Door is to the management of road and the line efficiency out of raising car owner.
Wherein, congestion in road prediction model is established by step A1~A4:
A1, the bayonet data for obtaining road, and according to the information of vehicles of bayonet data acquisition multiple periods；The vehicle
Information includes large car information of vehicles and compact car information of vehicles
A2, the behavioral characteristics sequence that road is obtained according to information of vehicles, and the static state according to predetermined manner acquisition road
Characteristic sequence；
A3, in conjunction with behavioral characteristics sequence, static nature sequence and preset jam level mark mode obtain road when
Between congestion sequence；
A4, binding time congestion sequence and preset algorithm establish congestion in road prediction model.
It when establishing model, needs to obtain data and serves as trained the set pair analysis model and be trained, obtain the card of time period
Bayonet data are carried out division extraction by mouth data, obtain the information of vehicles of multiple periods, for example obtain one day bayonet number
According to one day is divided into 24 hours, extracts the information of vehicles of daily hour respectively.Behavioral characteristics sequence is obtained according to information of vehicles
Column, behavioral characteristics in different time periods；The static nature sequence of road, such as the width ginseng of road are obtained according to predetermined manner
Several or road level parameters, obtain whether road attachment has public place building, such as school, market and hospital etc..Knot
Close the period in behavioral characteristics sequence and static nature sequence, and to the characteristic sequence of combination mark jam level after, obtain
Time congestion sequence in time series, binding time congestion sequence and preset algorithm training obtain congestion in road prediction model.
After establishing congestion in road prediction model, only the behavioral characteristics of a upper period need to be inputted congestion in road prediction model, it can be pre-
Survey the congestion in road situation of subsequent time period.
Specifically, the step for obtaining the behavioral characteristics sequence of road according to information of vehicles described in step A2 includes step
B1~B3:
B1, the first vehicle flowrate and the first average speed that each period is calculated according to information of vehicles；
B2, the second vehicle flowrate and the second average speed that the large car of each period is calculated according to large car information of vehicles,
And the third vehicle flowrate and third average speed of the compact car of each period are calculated according to compact car information of vehicles；
B3, the first vehicle flowrate in conjunction with each hour, the first average speed, the second vehicle flowrate, the second average speed, third
Vehicle flowrate and third average speed obtain the behavioral characteristics sequence of road.
The record of speed when bayonet can extract passing vehicle license plate number, license plate type and cross vehicle.According to license plate type
It can determine whether that vehicle is large car or compact car.Bayonet crosses the vehicle flowrate that vehicle number is road one hour record of past.It is all
Vehicle crosses the sum of bayonet speed and crosses vehicle quantity divided by corresponding, can obtain the average speed of corresponding group.Have in the present embodiment
Body, one day is divided into 24 hours, the average speed V of all vehicles of road of the road in each hour is extractedt, wherein t
It indicates the period, then extracts the average speed Vb of large car respectivelytWith small vehicle average speed Vst；24 were divided by one day
Hour, extract the vehicle flowrate Q of the road in each hourt, wherein t indicates the period, then extracts the wagon flow of large car respectively
Measure QbtWith the vehicle flowrate Qs of compact cart；Vehicle is finally obtained in the behavioral characteristics A of t momentt={ Vt,Vbt,Vst,Qt,Qbt,
Qst}。
Wherein, the step for static nature sequence of each road is obtained described in step A2 according to predetermined manner, specifically:
The attribute information of road is obtained, and attribute information and preset quantitative criteria is combined to obtain road static nature sequence.
In the present embodiment, the static nature of road is S={ s1, s2 ..., sn }, and wherein n indicates that the static state of road is special
Number of dimensions is levied, such as road is two-way traffic, then two-way traffic feature s1=2, other lanes record corresponding numerical value；Near roads
There is hospital, then road equipment feature s2=1 or near roads have school, then road equipment feature s2=2, can also be corresponding
Record the working and quitting time section of school；So analogize, obtains all static natures of road.Confirmation needs road to be used
Static nature number of dimensions and quantitative criteria extract road static nature S by standard.
Wherein, step A3 specifically includes step A31~A32:
A31, after behavioral characteristics sequence and static nature sequence are combined and be normalized, each period is obtained
Characteristic set.
A32, after each characteristic set is marked according to preset jam level mark mode, time congestion sequence is obtained
Column.
Behavioral characteristics sequence and static nature sequence are combined, and obtain each period after being normalized
Characteristic set, in this example specifically, feature F of the road in t momenttBy behavioral characteristics sequence At={ Vt, Vbt, Vst,
Qt, Qbt, QstAnd road static nature sequence S={ s1, s2 ..., sn } composition, i.e. Ft={ Vt, Vbt, Vst, Qt, Qbt, Qst,
S1, s2 ..., sn }, for characteristic set Ft={ Vt, Vbt, Vst, Qt, Qbt, Qst, s1, s2 ..., sn } and place is normalized
Reason, the feature that removal characteristic value is 0, while marker characteristic sequence, the characteristic set after being normalized；For each moment
Roadway characteristic Ft matches a corresponding jam situation opinion rating yt, finally obtain time congestion sequence.
Preset algorithm is Recognition with Recurrent Neural Network algorithm in the step A4, and the step A4 includes step A41~A42:
After A41, binding time congestion sequence and Recognition with Recurrent Neural Network algorithm are trained congestion in road prediction model, obtain
Obtain congestion in road prediction model initially.
A42, after optimizing using the method for cross-training to initial congestion in road prediction model, final road is obtained
Road congestion prediction model.
By roadway characteristic Ft={ Vt, Vbt, Vst, Qt, Qbt, Qst, s1, s2 ..., sn } with corresponding jam level ytSynthesis
Time congestion sequence inputting Recognition with Recurrent Neural Network model M in be trained, training mode yt=M (Ft-1), finally by friendship
Fork training obtains optimal model parameters, so that model M (F) has full accuracy for sample classification, to obtain higher pre-
Survey precision.
Specifically, in t moment, roadway characteristic Ft={ Vt, Vbt, Vst, Qt, Qbt, Qst, s1, s2 ..., sn }, wherein
Behavioral characteristics are At={ Vt, Vbt, Vst, Qt, Qbt, Qst, static nature is S={ s1, s2 ..., sn }, in circulation nerve net
Output of the circulation neuron about an example in network (RNN) are as follows:
At=φ (S*WF+At-1*WA+b)
Wherein, the AtThe behavioral characteristics of subsequent time period are represented, the φ () represents neuron function, and the S is represented
Static nature, the At-1The behavioral characteristics of a upper period were represented, the WF represents road static nature in neuron function
Shared weight, the WA represent road behavioral characteristics weight shared in neuron function, and it is normal that the b represents bias term
Number.By the road traffic and average speed and roadway characteristic of calculating last moment to subsequent time road traffic and averagely
The correlation of speed, the neural network after training can calculate road traffic and the average speed of subsequent time to predict
The jam level on road.
In conclusion a kind of having for congestion in road prediction technique based on bayonet data of the present embodiment is following beneficial to effect
Fruit:
(1), by the behavioral characteristics and static nature of bayonet data acquisition road, and combine congestion in road prediction model pre-
The jam situation for surveying the subsequent time period of road, can effectively and accurately predict the jam situation of traffic, solve by people
The true problem of forecasting inaccuracy is caused for prediction；And the present invention can predict the traffic congestion situation in a wide range of area, mention
High forecasting efficiency, the efficiency of management of traffic management department is provided and shorten the travel time of car owner and reduce trip at
This.
(2), various dimensions extraction is carried out to roadway characteristic, carries out static nature (lane, near roads including road respectively
Facility, the grade of road, road whether belong to the dimensions such as bridge) and behavioral characteristics it is (different for different periods on the same day
The vehicle flowrate and average speed of road) refinement and extraction, by training sample data carry out sample cross training, eliminated
Fitting problems improve classifier accuracy, greatly improve the accuracy of prediction.
(3), there is stronger expansion, as the road of acquisition is more comprehensive, by the way that more dimensional characteristics data are added,
With the Route coverage of extension bayonet, the accuracy rate of congestion prediction model can be further improved.
Embodiment two
As shown in Fig. 2, the present embodiment provides a kind of congestion in road forecasting systems based on bayonet data, comprising:
Characteristic module is obtained, for the behavioral characteristics by a period road on bayonet data acquisition；
Congestion prediction module, for predicting subsequent time period road in conjunction with behavioral characteristics and preset congestion in road prediction model
The jam level on road.
It is further used as preferred embodiment, further includes model building module, the model building module includes information
Acquiring unit, feature acquiring unit, congestion marking unit and modeling unit；
The information acquisition unit is used to obtain the bayonet data of road, and according to bayonet data acquisition multiple periods
Information of vehicles；
The feature acquiring unit is used to obtain the behavioral characteristics sequence of road according to information of vehicles, and according to default side
The static nature sequence of formula acquisition road；
The congestion marking unit is used in conjunction with behavioral characteristics sequence, static nature sequence and preset jam level label
Mode obtains the time congestion sequence of road；
The modeling unit establishes congestion in road prediction model for binding time congestion sequence and preset algorithm.
Above system by the behavioral characteristics and static nature of bayonet data acquisition road, and combines congestion in road to predict
The jam situation of the subsequent time period of model prediction road can effectively and accurately predict the jam situation of traffic, solve
The true problem of forecasting inaccuracy is caused by artificial prediction；And the present invention can carry out in advance the traffic congestion situation in a wide range of area
It surveys, improves forecasting efficiency, the efficiency of management of traffic management department is provided and shortens the travel time of car owner and reduce out
Row cost.
Embodiment three
The present embodiment provides a kind of congestion in road prediction meanss based on bayonet data, comprising:
At least one processor；
At least one processor, for storing at least one program；
When at least one described program is executed by least one described processor, so that at least one described processor is realized
A kind of congestion in road prediction technique based on bayonet data described in embodiment one.
Embodiment of the present invention method institute can be performed in a kind of congestion in road prediction meanss based on bayonet data of the present embodiment
A kind of congestion in road prediction technique based on bayonet data of offer, any combination implementation steps of executing method embodiment,
Have the corresponding function of this method and beneficial effect.
It is to be illustrated to preferable implementation of the invention, but the invention is not limited to the implementation above
Example, those skilled in the art can also make various equivalent variations on the premise of without prejudice to spirit of the invention or replace
It changes, these equivalent deformations or replacement are all included in the scope defined by the claims of the present application.
Claims (10)
1. a kind of congestion in road prediction technique based on bayonet data, which comprises the following steps:
Pass through the behavioral characteristics of a period road on bayonet data acquisition；
In conjunction with the jam level of behavioral characteristics and preset congestion in road prediction model prediction subsequent time period road.
2. a kind of congestion in road prediction technique based on bayonet data according to claim 1, which is characterized in that further include
The step of establishing congestion in road prediction model, described the step of establishing congestion in road prediction model specifically includes the following steps:
The bayonet data of road are obtained, and according to the information of vehicles of bayonet data acquisition multiple periods；
The behavioral characteristics sequence of road is obtained according to information of vehicles, and the static nature sequence of road is obtained according to predetermined manner
Column；
The time congestion sequence of road is obtained in conjunction with behavioral characteristics sequence, static nature sequence and preset jam level mark mode
Column；
Binding time congestion sequence and preset algorithm establish congestion in road prediction model.
3. a kind of congestion in road prediction technique based on bayonet data according to claim 2, which is characterized in that the vehicle
Information includes large car information of vehicles and compact car information of vehicles, the behavioral characteristics sequence that road is obtained according to information of vehicles
The step for column, specifically includes the following steps:
The first vehicle flowrate and the first average speed of each period are calculated according to information of vehicles；
Calculate the second vehicle flowrate and the second average speed of the large car of each period according to large car information of vehicles, and according to
Compact car information of vehicles calculates the third vehicle flowrate and third average speed of the compact car of each period；
In conjunction with each hour the first vehicle flowrate, the first average speed, the second vehicle flowrate, the second average speed, third vehicle flowrate,
The behavioral characteristics sequence of road is obtained with third average speed.
4. a kind of congestion in road prediction technique based on bayonet data according to claim 3, which is characterized in that described
The step for static nature sequence of each road is obtained according to predetermined manner, specifically:
The attribute information of road is obtained, and attribute information and preset quantitative criteria is combined to obtain road static nature sequence.
5. a kind of congestion in road prediction technique based on bayonet data according to claim 4, which is characterized in that the knot
Close behavioral characteristics sequence, static nature sequence and preset jam level mark mode obtain road time congestion sequence this
Step, specifically includes the following steps:
After behavioral characteristics sequence and static nature sequence are combined and be normalized, the feature set of each period is obtained
It closes；
After each characteristic set is marked according to preset jam level mark mode, time congestion sequence is obtained.
6. a kind of congestion in road prediction technique based on bayonet data according to claim 5, which is characterized in that described pre-
Imputation method is Recognition with Recurrent Neural Network algorithm, the binding time congestion sequence and preset algorithm establish congestion in road prediction model this
One step, specifically includes the following steps:
After binding time congestion sequence and Recognition with Recurrent Neural Network algorithm are trained congestion in road prediction model, obtain initial
Congestion in road prediction model；
After optimizing using the method for cross-training to initial congestion in road prediction model, it is pre- to obtain final congestion in road
Survey model.
7. a kind of congestion in road prediction technique based on bayonet data according to claim 6, which is characterized in that described first
The congestion in road prediction model of beginning specifically:
At=φ (S*WF+At-1*WA+b)
Wherein, the AtThe behavioral characteristics of subsequent time period are represented, the φ () represents neuron function, and the S represents static state
Feature, the At-1The behavioral characteristics of a upper period were represented, it is shared in neuron function that the WF represents road static nature
Weight, the WA represents road behavioral characteristics weight shared in neuron function, and the b represents bias term constant.
8. a kind of congestion in road forecasting system based on bayonet data characterized by comprising
Characteristic module is obtained, for the behavioral characteristics by a period road on bayonet data acquisition；
Congestion prediction module, for combining behavioral characteristics and preset congestion in road prediction model to predict subsequent time period road
Jam level.
9. a kind of congestion in road forecasting system based on bayonet data according to claim 8, which is characterized in that further include
Model building module, the model building module include information acquisition unit, feature acquiring unit, congestion marking unit and modeling
Unit；
The information acquisition unit is used to obtain the bayonet data of road, and according to the vehicle of bayonet data acquisition multiple periods
Information；
The feature acquiring unit is used to obtain the behavioral characteristics sequence of road according to information of vehicles, and is obtained according to predetermined manner
By way of the static nature sequence on road；
The congestion marking unit is used to combine behavioral characteristics sequence, static nature sequence and preset jam level mark mode
Obtain the time congestion sequence of road；
The modeling unit establishes congestion in road prediction model for binding time congestion sequence and preset algorithm.
10. a kind of congestion in road prediction meanss based on bayonet data characterized by comprising
At least one processor；
At least one processor, for storing at least one program；
When at least one described program is executed by least one described processor, so that at least one described processor realizes right
It is required that a kind of described in any item congestion in road prediction techniques based on bayonet data of 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171067.4A CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910171067.4A CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109887283A true CN109887283A (en) | 2019-06-14 |
| CN109887283B CN109887283B (en) | 2021-01-26 |
Family
ID=66931226
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910171067.4A Active CN109887283B (en) | 2019-03-07 | 2019-03-07 | Road congestion prediction method, system and device based on checkpoint data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109887283B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335466A (en) * | 2019-07-11 | 2019-10-15 | 青岛海信网络科技股份有限公司 | Traffic flow forecasting method and equipment |
| CN110428612A (en) * | 2019-07-05 | 2019-11-08 | 平安国际智慧城市科技股份有限公司 | Vehicle management-control method, device, computer equipment and storage medium |
| CN111341098A (en) * | 2020-02-18 | 2020-06-26 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN111341099A (en) * | 2020-02-27 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111798579A (en) * | 2020-07-29 | 2020-10-20 | 深圳市渝华发电子科技有限公司 | ETC portal frame-based highway congestion prediction method and system |
| WO2021169174A1 (en) * | 2020-02-29 | 2021-09-02 | 深圳壹账通智能科技有限公司 | Road congestion degree prediction method, apparatus, computer device, and readable storage medium |
| CN113535819A (en) * | 2021-07-15 | 2021-10-22 | 广州交信投科技股份有限公司 | Traffic situation perception analysis method and device, computer storage medium and terminal |
| CN113610304A (en) * | 2021-08-11 | 2021-11-05 | 北京京东乾石科技有限公司 | Congestion prediction method, device, equipment and storage medium |
| WO2022142418A1 (en) * | 2020-12-31 | 2022-07-07 | 深圳云天励飞技术股份有限公司 | Traffic performance index prediction method and device based on gis map information |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038478A (en) * | 2017-04-20 | 2017-08-11 | 百度在线网络技术（北京）有限公司 | Road condition predicting method and device, computer equipment and computer-readable recording medium |
| CN107085941A (en) * | 2017-06-26 | 2017-08-22 | 广东工业大学 | A kind of traffic flow forecasting method, apparatus and system |
| CN107240254A (en) * | 2017-08-02 | 2017-10-10 | 河北冀通慧达科技有限公司 | Traffic Forecasting Methodology and terminal device |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
-
2019
- 2019-03-07 CN CN201910171067.4A patent/CN109887283B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107038478A (en) * | 2017-04-20 | 2017-08-11 | 百度在线网络技术（北京）有限公司 | Road condition predicting method and device, computer equipment and computer-readable recording medium |
| CN107085941A (en) * | 2017-06-26 | 2017-08-22 | 广东工业大学 | A kind of traffic flow forecasting method, apparatus and system |
| CN107240254A (en) * | 2017-08-02 | 2017-10-10 | 河北冀通慧达科技有限公司 | Traffic Forecasting Methodology and terminal device |
| CN108269401A (en) * | 2018-01-30 | 2018-07-10 | 银江股份有限公司 | A kind of overpass traffic congestion Forecasting Methodology based on data-driven |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110428612A (en) * | 2019-07-05 | 2019-11-08 | 平安国际智慧城市科技股份有限公司 | Vehicle management-control method, device, computer equipment and storage medium |
| CN110428612B (en) * | 2019-07-05 | 2021-04-13 | 平安国际智慧城市科技股份有限公司 | Vehicle management and control method and device, computer equipment and storage medium |
| CN110335466A (en) * | 2019-07-11 | 2019-10-15 | 青岛海信网络科技股份有限公司 | Traffic flow forecasting method and equipment |
| CN111341098A (en) * | 2020-02-18 | 2020-06-26 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN111341098B (en) * | 2020-02-18 | 2021-07-27 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN111341099A (en) * | 2020-02-27 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111341099B (en) * | 2020-02-27 | 2022-05-10 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| WO2021169174A1 (en) * | 2020-02-29 | 2021-09-02 | 深圳壹账通智能科技有限公司 | Road congestion degree prediction method, apparatus, computer device, and readable storage medium |
| CN111798579B (en) * | 2020-07-29 | 2021-07-23 | 贵州汇联通电子商务服务有限公司 | ETC portal frame-based highway congestion prediction method and system |
| CN111798579A (en) * | 2020-07-29 | 2020-10-20 | 深圳市渝华发电子科技有限公司 | ETC portal frame-based highway congestion prediction method and system |
| WO2022142418A1 (en) * | 2020-12-31 | 2022-07-07 | 深圳云天励飞技术股份有限公司 | Traffic performance index prediction method and device based on gis map information |
| CN113535819A (en) * | 2021-07-15 | 2021-10-22 | 广州交信投科技股份有限公司 | Traffic situation perception analysis method and device, computer storage medium and terminal |
| CN113535819B (en) * | 2021-07-15 | 2023-02-28 | 广州交信投科技股份有限公司 | Traffic situation perception analysis method and device, computer storage medium and terminal |
| CN113610304A (en) * | 2021-08-11 | 2021-11-05 | 北京京东乾石科技有限公司 | Congestion prediction method, device, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109887283B (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109887283A (en) | A kind of congestion in road prediction technique, system and device based on bayonet data | |
| CN106652483B (en) | The method for laying traffic information test point in regional highway network using detection device | |
| CN106971534B (en) | Commuter characteristic analysis method based on number plate data | |
| Maghelal et al. | Walkability: A Review of Existing Pedestrian Indices. | |
| O’Connor et al. | Geo-temporal tracking and analysis of tourist movement | |
| CN109923575A (en) | Absolute and/or relative risk possibility the device and method of automatic traffic and driving mode identification and position measurement of correlation car accident | |
| Hussein et al. | Automated pedestrian safety analysis at a signalized intersection in New York City: Automated data extraction for safety diagnosis and behavioral study | |
| Wu et al. | An improved vehicle-pedestrian near-crash identification method with a roadside LiDAR sensor | |
| CN105513354A (en) | Video-based urban road traffic jam detecting system | |
| Fernández-Caballero et al. | Road-traffic monitoring by knowledge-driven static and dynamic image analysis | |
| CN109272175A (en) | A kind of data collection system and method based on Urban Migrant network | |
| CN107368931A (en) | Logistics distribution path dynamic programming method and system based on big data analytical technology | |
| Alver et al. | Evaluation of pedestrian critical gap and crossing speed at midblock crossing using image processing | |
| Vallejo-Borda et al. | Do attitudes and perceptions help to explain cycling infrastructure quality of service? | |
| CN107590999A (en) | A kind of traffic state judging method based on bayonet socket data | |
| Kong et al. | A fusion-based system for road-network traffic state surveillance: a case study of Shanghai | |
| CN117456482B (en) | Abnormal event identification method and system for traffic monitoring scene | |
| Tipakornkiat et al. | Determining an influencing area affecting walking speed on footpath: A case study of a footpath in CBD Bangkok, Thailand | |
| Pi et al. | Visual recognition for urban traffic data retrieval and analysis in major events using convolutional neural networks | |
| Ansariyar | Investigating the Car-Pedestrian Conflicts Based on an Innovative Post Encroachment Time Threshold (PET) Classification | |
| Lian et al. | Advances in estimating pedestrian measures through artificial intelligence: From data sources, computer vision, video analytics to the prediction of crash frequency | |
| CN109815933A (en) | A kind of multiaxle trucks automatic identification apparatus for obtaining evidence, system and method | |
| Zhou et al. | Spatial heterogeneity of urban illegal parking behavior: A geographically weighted Poisson regression approach | |
| JP7264028B2 (en) | Information providing system, information providing method, information terminal and information display method | |
| Zhang et al. | Machine learning and computer vision-enabled traffic sensing data analysis and quality enhancement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |