CN106530714B - A kind of secondary traffic accident time forecasting methods based on traffic flow data - Google Patents
A kind of secondary traffic accident time forecasting methods based on traffic flow data Download PDFInfo
- Publication number
- CN106530714B CN106530714B CN201611195855.XA CN201611195855A CN106530714B CN 106530714 B CN106530714 B CN 106530714B CN 201611195855 A CN201611195855 A CN 201611195855A CN 106530714 B CN106530714 B CN 106530714B
- Authority
- CN
- China
- Prior art keywords
- accident
- traffic
- time
- road
- upstream
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
Abstract
The secondary traffic accident time forecasting methods based on traffic flow data that the invention discloses a kind of obtain historical traffic casualty data；Original traffic accident is divided into take charge event, second accident and ordinary traffic accident；According to the upstream and downstream traffic of second accident, section, weather, temporal information preparation model variable；The prediction model of secondary traffic accident time of origin is established according to model variable；Will take charge thus road section information and traffic flow data time difference prediction model calculate, calculate second accident generation time, second accident generation before the time, processing take charge thus the scene of the accident；The present invention using Traffic flow detecting equipment obtain traffic flow parameter, real-time detection through street take charge thus when and second accident time difference, vehicle is regulated and controled with variable speed-limit, reduce second accident traffic accident generation.
Description
Technical field
The secondary traffic accident time forecasting methods based on traffic flow data that the present invention relates to a kind of, belong in traffic safety
Accident forecast field.
Background technique
In recent years, the particularly serious secondary traffic accident as caused by main traffic accident repeated, serious to have threatened the people
The security of the lives and property of the masses, to the work of road traffic safety management, more stringent requirements are proposed.Second accident generate because
It is known as very much, for example does not carry out vehicle position mark, danger is not set outside the larger distance of scene of the accident rear immediately
Caution sign for warning the vehicle that comes at accident rear, or is the traffic pipe after accident impact traffic flow conditions
Reason department is not dredged in time, so as to cause the generation of second accident.Draw in the wagon flow of the high speed of highway, through street
The traffic accident that traffic accident frequency is higher than ordinary highway is sent out, and if insufficient to traffic accident treatment experience, can also be led again
The generation of second accident is caused, often than one time traffic accident is even more serious for secondary traffic accident.Therefore, highway and fast is probed into
The reason of secondary traffic accident, occurs for fast road, while according to occurring principle, predicting secondary traffic accident and formulating corresponding emergency
Rescue strategies, it is very great to preventing highway second accident from playing the role of.
In traditional second accident prediction technique, there are the time of origin for much having studied event of taking charge, accident pattern, weather
And influence of the geometry feature to second accident probability of happening.But arithmetic for real-time traffic flow shape is thought in relatively small number of research
Condition, influence of the road geometry linear to second accident time of origin.The traffic flow of danger relevant to an accident and road
Linear situation may also promote the generation of second accident.
It is previous that prediction prevention is carried out to second accident using passive, static method, and if with the traffic flow acquired in real time
And the road alignment of script come judge second accident occur time, be just hopeful according to take charge thus be traffic believe
Breath, road conditions actively predict secondary traffic accident time of origin in real time, take real-time traffic control strategy secondary to take precautions against
The generation of accident.
Summary of the invention
Goal of the invention: in order to overcome the deficiencies in the prior art, the present invention provides a kind of based on high-precision traffic flow
And the method for the preventing secondary traffic accident time of origin of road alignment data, this method can be judged with arithmetic for real-time traffic flow
The most possible time of origin of second accident, the method so as to use dynamic traffic control actively predict secondary traffic in real time
Accident sets up caution notice and second accident is avoided to generate.
Technical solution: to achieve the above object, the technical solution adopted by the present invention are as follows:
A kind of secondary traffic accident time forecasting methods based on traffic flow data, comprising the following steps:
Step 10) obtains historical traffic casualty data,
The historical traffic casualty data that step 20) is obtained according to step 10) classifies traffic accident, event of respectively taking charge,
Second accident and ordinary traffic accident；Operating speed isoline method identifies second accident when classification；
Step 30) is classified according to the traffic accident of the obtained historical traffic casualty data of step step 10) and step 20)
Obtain the upstream and downstream traffic information of second accident；
The upstream and downstream traffic for the second accident that step 40) is obtained according to the traffic accident classification of step 20) and step 30)
Information preparation model variable；
Step 50) establishes the time prediction model of secondary traffic accident according to the model variable that step 40) prepares:
yi=a+b1x1+b2x2+…+bkxkFormula (1)
Wherein, yiRepresent i-th second accident distance take charge thus time logarithmic difference, wherein a indicate constant, b1,
b2...bkIndicate the coefficient of model variable, x1, x2...xkIndicate that model variable, k indicate model variable number；
Step 60) obtains the road section information for event of taking charge, road section information includes left and right circle when accident has occurred on highway
Road difference, whether supplemented by road, road width, acquisition take charge therefore traffic flow data of the section before accident generation occur；Utilize ring
Shape coil checker obtains real-time traffic flow data, and standard deviation, upstream and downstream 5 including 5 minutes vehicle occupancy rate of upstream are divided
The average value of clock time traffic flow, main duration of fault；
Step 70) will take charge thus road section information traffic flow data corresponding with its bring into step 50) time difference prediction
Model is calculated, and the time of second accident generation is predicted.
Further: further including the road section information and traffic flow data obtained according to step 60), in the second accident of prediction
Within time of origin T, regulate and control vehicle using the method for variable speed-limit, until terminating detection.
It is preferred: step 50) the time prediction model are as follows:
yi=4.701325+0.0068333x1i-0.0942883x2i+0.044625x3i+0.2053786x4i+
1.578892x5i-0.0167416x6i
Wherein, yiRepresent i-th second accident distance take charge thus time logarithmic difference, x1iIndicate duration, x2iIt indicates
The standard deviation of 5 minutes vehicle occupancy rate of upstream, x3iIndicate the average value of 5 minutes traffic flow of upstream and downstream, x4iIndicate left
Right ring road difference, x5iRoad supplemented by indicating whether, x6iIndicate road width.
It is preferred: in the step 10) traffic accident data include the date of occurrence of accident, the time, place, accident it is tight
Weight degree, accident pattern, pavement conditions, related vehicle, weather condition, lighting condition, the acquisition volume of traffic, speed and vehicle
Occupation rate.
Preferred: historical traffic casualty data is obtained by the annular detector being placed on road in the step 10)
, a ring coil detector is set at a certain distance on highway, accident is acquired by ring coil detector
Date, time, place, the severity of accident, accident pattern, pavement conditions, related vehicle, weather condition, illumination item
Part, the acquisition volume of traffic, speed and vehicle occupancy rate.
It is preferred: to obtain the upstream and downstream traffic information method of second accident in the step 30): matching each first
Then place where the accident occurred point extracts accident apart from nearest upstream ring coil detector and downstream ring coil detector
When before the upstream and downstream traffic information of 30 minutes traffic datas as second accident, the upstream and downstream traffic information of the second accident
The volume of traffic, speed and vehicle occupancy rate including upstream and downstream coil.
Preferred: model variable includes real-time traffic flow data, second accident feature, environmental aspect in the step 40)
And geometry feature, in which:
The real-time traffic flow data: the upstream and downstream traffic information of step 30) was closed with 5 minutes for time interval
And three the corresponding vehicle number of each accident, car speed and vehicle occupancy rate variables are calculated later between 5 minutes
Every interior average value, standard deviation；In view of the potential inaccuracy of declaration of an accident time of origin, final traffic flow data is extracted
Time is 9 minutes before accident occurs；
The second accident feature includes severity of injuries, accident occurrence type, traffic injury time section and event of taking charge
The section that time difference, pile No. be poor, second accident duration, accident occur；
The environmental aspect includes that weather condition, road surface condition, light are excellent；
The geometry feature includes number of track-lines, road surface width, lane width, shoulder width, road alignment, circle
Road number.
The present invention compared with prior art, has the advantages that
1. previous research when secondary traffic accident time prediction model is predicted in building, is that a consideration accident is special mostly
Sign, few consideration arithmetic for real-time traffic flow situations.The present invention has comprehensively considered arithmetic for real-time traffic flow situation, thing when choosing variable
Therefore the influence of feature, road circumstance state and geometry feature to secondary traffic accident probability of happening, so that the essence of model
Quasi- rate is higher.
2. the vehicle regulates and controls the road that method obtains real time traffic data and place where the accident occurred using Traffic flow detecting equipment
Route graphic data, real-time detection super expressway are taken charge after event, the most possible time of second accident are generated, by mentioning
Preceding sign-posting board, while dynamic traffic control method is used, reduce traffic accident.
Detailed description of the invention
Fig. 1 is flow diagram of the invention.
Specific embodiment
In the following with reference to the drawings and specific embodiments, the present invention is furture elucidated, it should be understood that these examples are merely to illustrate this
It invents rather than limits the scope of the invention, after the present invention has been read, those skilled in the art are to of the invention various
The modification of equivalent form falls within the application range as defined in the appended claims.
A kind of secondary traffic accident time forecasting methods based on traffic flow data, as shown in Figure 1, comprising the following steps:
Step 10) obtains historical traffic casualty data, traffic accident data include the date of occurrence of accident, the time, place,
The severity of accident, accident pattern, pavement conditions, related vehicle, weather condition, lighting condition, the acquisition volume of traffic, vehicle
The contents such as speed and vehicle occupancy rate.
Traffic accident data are obtained by the annular detector being placed on road, on highway at a certain distance (such as
0.8 mile) setting one ring coil detector, by ring coil detector acquire accident date of occurrence, the time, place,
The severity of accident, accident pattern, pavement conditions, related vehicle, weather condition, lighting condition, the acquisition volume of traffic, vehicle
Speed and vehicle occupancy rate.
The historical traffic casualty data that step 20) is obtained according to step 10) classifies traffic accident, event of respectively taking charge,
Second accident and ordinary traffic accident；The step for be related to the identification of secondary traffic accident, operating speed isogram when classification
Method identifies second accident.
Step 30) is classified according to the traffic accident of the obtained historical traffic casualty data of step step 10) and step 20)
Obtain the upstream and downstream traffic information of second accident.Method are as follows: match each place where the accident occurred point first apart from recently upper
Ring coil detector and downstream ring coil detector are swum, traffic data conduct in 30 minutes before then extracting when accident occurs
The upstream and downstream traffic information of second accident, the upstream and downstream traffic information of the second accident include the volume of traffic of upstream and downstream coil,
Speed and vehicle occupancy rate
The upstream and downstream traffic for the second accident that step 40) is obtained according to the traffic accident classification of step 20) and step 30)
Information preparation model variable, in terms of Selection Model variable considers following four.
(1) real-time traffic flow data: the upstream and downstream traffic information of step 30) was merged with 5 minutes for time interval,
Three the corresponding vehicle number of each accident, car speed and vehicle occupancy rate variables are calculated later in 5 minute time intervals
Interior average value, standard deviation (including difference of upstream, downstream and upstream and downstream)；It is potential in view of declaration of an accident time of origin
Inaccuracy, final traffic flow data extraction time are 9 minutes before accident occurs；
(2) second accident feature: including severity of injuries, accident occurrence type, traffic injury time section and event of taking charge
Time difference, pile No. be poor, the section that second accident duration, accident occur etc.；
(3) environmental aspect: including weather condition, road surface condition, light excellent (visibility) etc.；
(4) geometry feature: (it is including number of track-lines, road surface width, lane width, shoulder width, road alignment
No is curve), ring road number etc..
Step 50) establishes the time prediction model of secondary traffic accident according to the model variable that step 40) prepares:
yi=a+b1x1+b2x2+…+bkxkFormula (1)
Wherein, yiRepresent i-th second accident distance take charge thus time logarithmic difference, the time as unit of minute, a indicate
Constant, b1, b2...bkIndicate the coefficient of model variable, x1, x2...xkIndicate that model variable, k indicate model variable number；Model
Used in time logarithmic difference be dependent variable.Covariant is the variable chosen in step 40).By correlation test, gradually sieve
Variable is selected, so that all covariants of model are significant related to dependent variable.Final secondary traffic accident prediction model is such as formula (1)
Shown in equation.
It detects section and secondary traffic accident time of origin occurs, and regulate and control vehicle.When accident, ring have occurred on highway
Shape coil checker can obtain real-time traffic flow data, and these data are brought into secondary traffic accident time prediction model,
According to specific traffic flow, road alignment situation, to judge the time of secondary traffic accident generation.Before this time, traffic police
A scene of the accident should be handled in time, and takes real-time traffic control strategy, such as variable speed-limit, ramp metering rate, car networking control
Lower dynamic realtime regulation is made, to prevent the generation of secondary traffic accident.It is specific:
Step 60) obtains the road section information for event of taking charge, road section information includes left and right circle when accident has occurred on highway
Road difference, whether supplemented by road, road width, acquisition take charge therefore traffic flow data of the section before accident generation occur；Utilize ring
Shape coil checker obtains real-time traffic flow data, and standard deviation, upstream and downstream 5 including 5 minutes vehicle occupancy rate of upstream are divided
The average value of clock time traffic flow, main duration of fault；
Step 70) will take charge thus road section information traffic flow data corresponding with its bring into step 50) time difference prediction
Model is calculated, and the time of second accident generation is predicted, and the time before second accident generation, traffic police should be handled in time
The main scene of the accident.
Step 80) detects the traffic flow situation for taking charge therefore occurring section, and regulates and controls vehicle with the method for variable speed-limit；
Step 90) repeats step 80) according to the traffic flow situation and surface conditions for taking charge therefore occurring section, in prediction
Within second accident time of origin T, a regulation of driving a vehicle of being gone forward side by side using variable speed-limit, until terminating detection.The vehicle regulates and controls method
Traffic flow parameter is obtained using Traffic flow detecting equipment, when real-time detection through street takes charge former and the time of second accident
Difference regulates and controls vehicle with variable speed-limit, reduces second accident traffic accident and generates.
Example
Using on one 34 miles on California, USA I-5 highway of sections, from 2010 to 2015
The data acquired between year.Traffic accident total amount of data is 20709, and wherein common occurrences 19363 rise, event 561 of taking charge, secondary
Accident 785 rises.
By contoured velocity figure method sort out come three classes accident it is as shown in the table:
1 accidents classification result of table
Utilize the prediction model of multiple linear regression model building secondary traffic accident time of origin:
yi=4.701325+0.0068333x1i-0.0942883x2i+0.044625x3i+0.2053786x4i+
1.578892x5i-0.0167416x6iFormula (5)
yi--- Time, the time logarithmic difference (min) of i-th second accident and event of taking charge；
x1i--- Duration, duration (min)；
x2i--- AvgOcc1, the standard deviation (%) of 5 minutes vehicle occupancy rate of upstream；
x3i--- DevFlo12, the average value (/ 30s) of 5 minutes traffic flow of upstream and downstream；
x4i--- Difference, left and right ring road difference (a)；
x5i--- Road, if supplemented by (being is 1, is not for 0) in road；
x6i--- RoadWidth, road width (feet)；
Using above-mentioned linear regression model, excluded take charge thus with the second accident time difference 15 minutes thing
Therefore after data, relevant road and traffic flow data are brought into, examining model accuracy obtained is 82.138%.
The above is only a preferred embodiment of the present invention, it should be pointed out that: for the ordinary skill people of the art
For member, various improvements and modifications may be made without departing from the principle of the present invention, these improvements and modifications are also answered
It is considered as protection scope of the present invention.
Claims (6)
1. a kind of secondary traffic accident time forecasting methods based on traffic flow data, which is characterized in that utilize Traffic flow detecting
Equipment obtains the road alignment data of real time traffic data and place where the accident occurred, and real-time detection super expressway is taken charge former
Later, the most possible time of second accident is generated, comprising the following steps:
Step 10) obtains historical traffic casualty data,
The historical traffic casualty data that step 20) is obtained according to step 10) classifies traffic accident, respectively takes charge former, secondary
Accident and ordinary traffic accident；
Step 30) is classified according to the traffic accident of the obtained historical traffic casualty data of step step 10) and step 20) to be obtained
The upstream and downstream traffic information of second accident；
The upstream and downstream traffic information method of second accident is obtained in the step 30): matching each place where the accident occurred first
Point is apart from nearest upstream ring coil detector and downstream ring coil detector, 30 minutes before then extracting when accident occurs
Upstream and downstream traffic information of the traffic data as second accident, the upstream and downstream traffic information of the second accident includes upstream and downstream
The volume of traffic, speed and the vehicle occupancy rate of coil；
The upstream and downstream traffic information for the second accident that step 40) is obtained according to the traffic accident classification of step 20) and step 30)
Preparation model variable；
Step 50) establishes the time prediction model of secondary traffic accident according to the model variable that step 40) prepares:
yi=a+b1x1+b2x2+…+bkxkFormula (1)
Wherein, yiRepresent i-th second accident distance take charge thus time logarithmic difference, wherein a indicate constant, b1, b2…bkIt indicates
The coefficient of model variable, x1, x2…xkIndicate that model variable, k indicate model variable number；
Its time prediction model are as follows:
yi=4.701325+0.0068333x1i-0.0942883x2i
+0.044625x3i+0.2053786x4i+1.578892x5i-0.0167416x6i
Wherein, yiRepresent i-th second accident distance take charge thus time logarithmic difference, x1iIndicate duration, x2iIndicate upstream 5
The standard deviation of minutes vehicle occupancy rate, x3iIndicate the average value of 5 minutes traffic flow of upstream and downstream, x4iIndicate left and right circle
Road difference, x5iRoad supplemented by indicating whether, x6iIndicate road width；
Step 60) obtains the road section information for event of taking charge, road section information includes that left and right ring road is poor when accident has occurred on highway
Value, whether supplemented by the information such as road, road width；The real-time traffic before main accident section occurs is obtained using ring coil detector
Flow data, the average value of standard deviation, 5 minutes time traffic flow of upstream and downstream including 5 minutes vehicle occupancy rate of upstream,
Main duration of fault；
Step 70) will take charge thus road section information traffic flow data corresponding with its bring the time difference prediction model of step 50) into,
It is calculated, predicts the time of second accident generation.
2. the secondary traffic accident time forecasting methods based on traffic flow data according to claim 1, it is characterised in that: also
Including the road section information and traffic flow data obtained according to step 60), within the second accident time of origin T of prediction, utilize
The method of variable speed-limit regulates and controls vehicle, until terminating detection.
3. the secondary traffic accident time forecasting methods based on traffic flow data according to claim 1, it is characterised in that: institute
State date of occurrence, time, place that traffic accident data in step 10) include accident, the severity of accident, accident pattern,
Pavement conditions, related vehicle, weather condition, lighting condition, the acquisition volume of traffic, speed and vehicle occupancy rate.
4. the secondary traffic accident time forecasting methods based on traffic flow data according to claim 1, it is characterised in that: institute
Historical traffic casualty data is obtained by the annular detector being placed on road in the step 10) stated, every one on highway
A ring coil detector is arranged in set a distance, acquires accident date of occurrence, time, place, thing by ring coil detector
Therefore severity, accident pattern, pavement conditions, related vehicle, weather condition, lighting condition, acquisition the volume of traffic, speed
And vehicle occupancy rate.
5. the secondary traffic accident time forecasting methods based on traffic flow data according to claim 1, it is characterised in that: institute
Operating speed isoline method identification second accident when stating classification in step 20).
6. the secondary traffic accident time forecasting methods based on traffic flow data according to claim 1, it is characterised in that: institute
Stating model variable in step 40) includes real-time traffic flow data, second accident feature, environmental aspect and geometry feature,
Wherein:
The real-time traffic flow data: the upstream and downstream traffic information of step 30) was merged with 5 minutes for time interval, it
After calculate three the corresponding vehicle number of each accident, car speed and vehicle occupancy rate variables in 5 minute time intervals
Average value, standard deviation；In view of the potential inaccuracy of declaration of an accident time of origin, final traffic flow data extraction time
9 minutes before occurring for accident；
The second accident feature includes severity of injuries, accident occurrence type, traffic injury time section and main time of casualty
Difference, pile No. is poor, the second accident duration, accident generation section；
The environmental aspect includes that weather condition, road surface condition, light are excellent；
The geometry feature includes number of track-lines, road surface width, lane width, shoulder width, road alignment, ring road
Number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611195855.XA CN106530714B (en) | 2016-12-21 | 2016-12-21 | A kind of secondary traffic accident time forecasting methods based on traffic flow data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611195855.XA CN106530714B (en) | 2016-12-21 | 2016-12-21 | A kind of secondary traffic accident time forecasting methods based on traffic flow data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106530714A CN106530714A (en) | 2017-03-22 |
| CN106530714B true CN106530714B (en) | 2019-04-30 |
Family
ID=58340406
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611195855.XA Active CN106530714B (en) | 2016-12-21 | 2016-12-21 | A kind of secondary traffic accident time forecasting methods based on traffic flow data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106530714B (en) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108198415B (en) * | 2017-12-28 | 2019-07-05 | 同济大学 | A kind of city expressway accident forecast method based on deep learning |
| CN110264752A (en) * | 2019-05-22 | 2019-09-20 | 浙江吉利控股集团有限公司 | A kind of speed-limiting control method and device of urban transportation |
| CN111815967B (en) * | 2020-05-15 | 2022-07-01 | 中国市政工程华北设计研究总院有限公司 | Highway dynamic speed limit control method based on secondary traffic accident prevention |
| CN112233418B (en) * | 2020-09-27 | 2021-09-03 | 东南大学 | Secondary traffic accident prevention control method under intelligent network-connected mixed traffic flow environment |
| CN113963539B (en) * | 2021-10-19 | 2022-06-10 | 交通运输部公路科学研究所 | Highway traffic accident identification method, module and system |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204390499U (en) * | 2015-01-27 | 2015-06-10 | 李伟 | The warning device of a kind of highway preventing secondary accident and a chain of accident |
| CN104852970A (en) * | 2015-04-24 | 2015-08-19 | 公安部道路交通安全研究中心 | Highway traffic accident information issuing system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9390622B2 (en) * | 2013-04-16 | 2016-07-12 | International Business Machines Corporation | Performing-time-series based predictions with projection thresholds using secondary time-series-based information stream |
-
2016
- 2016-12-21 CN CN201611195855.XA patent/CN106530714B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN204390499U (en) * | 2015-01-27 | 2015-06-10 | 李伟 | The warning device of a kind of highway preventing secondary accident and a chain of accident |
| CN104852970A (en) * | 2015-04-24 | 2015-08-19 | 公安部道路交通安全研究中心 | Highway traffic accident information issuing system |
Non-Patent Citations (1)
| Title |
|---|
| "Real-time estimation of secondary crash likelihood on freeways";Chengcheng Xu,etl.;《Transport Research Part C：Emerging Techonolgies》;20161031(第71期);正文第2-4节，表3-4，图1 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106530714A (en) | 2017-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106530714B (en) | A kind of secondary traffic accident time forecasting methods based on traffic flow data | |
| CN106485922B (en) | Secondary traffic accident method for early warning based on high-precision traffic flow data | |
| CN105225500B (en) | A kind of traffic control aid decision-making method and device | |
| Pande et al. | Comprehensive analysis of the relationship between real-time traffic surveillance data and rear-end crashes on freeways | |
| CN104392610B (en) | Expressway based on distributed video traffic events coverage dynamic monitoring and controlling method | |
| CN104282161B (en) | The awkward district of a kind of signalized intersections based on real-time vehicle track control method | |
| CN110164132B (en) | Method and system for detecting road traffic abnormity | |
| CN108399743A (en) | A kind of vehicle on highway anomaly detection method based on GPS data | |
| CN102568206B (en) | Video monitoring-based method for detecting cars parking against regulations | |
| CN103646534A (en) | A road real time traffic accident risk control method | |
| JP2009126503A (en) | Driving evaluation device, driving evaluation system, computer program and driving evaluation method | |
| US20220383738A1 (en) | Method for short-term traffic risk prediction of road sections using roadside observation data | |
| CN103617734B (en) | Vehicle on highway based on time-histories feature safety traffic recognition methods | |
| CN106600950B (en) | A kind of secondary traffic accident prediction technique based on traffic flow data | |
| CN102360524B (en) | Automatic detection and confirmation method of dangerous traffic flow characteristics of highway | |
| CN103971519A (en) | System and method of using traffic conflicts for judging accident-prone sections | |
| CN112800166B (en) | Community correction object activity track supervision and early warning method, system and device | |
| Zhang et al. | Prediction of red light running based on statistics of discrete point sensors | |
| CN102157061A (en) | Keyword-statistic-based traffic event identifying method | |
| Anwari et al. | Investigating surrogate safety measures at midblock pedestrian crossings using multivariate models with roadside camera data | |
| Kuang et al. | A review of crash surrogate events | |
| CN114155710B (en) | Underground road confluence road section guiding control system and control method | |
| CN208271393U (en) | A kind of automatic patrol police's system of multifunctional high speed highway | |
| Jang et al. | An analysis system of pedestrian-vehicle interaction risk level using drone videos | |
| Zhang et al. | Use of field observations in developing collision-avoidance system for arterial red light running: Factoring headway and vehicle-following characteristics |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |