CN109118773A - A kind of traffic accidents methods of risk assessment - Google Patents
A kind of traffic accidents methods of risk assessment Download PDFInfo
- Publication number
- CN109118773A CN109118773A CN201811156908.6A CN201811156908A CN109118773A CN 109118773 A CN109118773 A CN 109118773A CN 201811156908 A CN201811156908 A CN 201811156908A CN 109118773 A CN109118773 A CN 109118773A
- Authority
- CN
- China
- Prior art keywords
- traffic
- section
- accident
- speed
- 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
- 206010039203 Road traffic accident Diseases 0.000 title claims abstract description 71
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012502 risk assessment Methods 0.000 title claims abstract description 25
- 238000004458 analytical method Methods 0.000 claims description 49
- 238000012417 linear regression Methods 0.000 claims description 14
- 230000009466 transformation Effects 0.000 claims description 7
- 238000007619 statistical method Methods 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 abstract description 3
- 238000013461 design Methods 0.000 description 6
- 239000006185 dispersion Substances 0.000 description 5
- 238000013210 evaluation model Methods 0.000 description 5
- 230000001419 dependent effect Effects 0.000 description 4
- 238000012806 monitoring device Methods 0.000 description 3
- 238000011144 upstream manufacturing Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 208000015181 infectious disease Diseases 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000002265 prevention Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009863 impact test Methods 0.000 description 1
- 239000003595 mist Substances 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Analytical Chemistry (AREA)
- Game Theory and Decision Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to traffic safety technology fields for this, disclose a kind of traffic accidents methods of risk assessment, it include: to establish street accidents risks assessment models, traffic flow data is obtained according to the current concrete condition for implementing section, parameter calibration is carried out according to the current traffic flow data for implementing section, it determines the corresponding street accidents risks assessment models in current implementation section, determines the current street accidents risks value implemented at each pile No. in section based on this model.Based on traffic accidents methods of risk assessment provided by the invention, can the street accidents risks to highway effectively assessed, there is stronger operability.
Description
Technical field
The present invention relates to traffic safety technology field more particularly to a kind of traffic accidents methods of risk assessment.
Background technique
In recent years, increasing substantially with Freeway Traffic Volume, traffic congestion and traffic accident on highway
Again and again occur.How to carry out street accidents risks evaluation and accident prevention to highway is particularly important.
Currently, have the method for some assessment road traffic accident risks, and inventors have found that these methods are reason mostly
By the exploratory development of aspect, evaluation model design is excessively idealized, and is difficult to realize in a practical situation, in actual traffic administration
Middle operability is not very strong.For example, Meng Xianghai et al. proposition invades time (Post Encroachment based on rear car
Time, PET) methods of risk assessment, headstock after the PET in this method refers to the vehicle in confluence area during lane changing
The difference of the time of infection thread is left in the time of portion's arrival infection thread and front truck tail portion, and the data that this method requires are excessively microcosmic, and
And it is very high to the required precision of data.For another example, Wang Xiaofei et al. propose based on risk of collision exponent pair grade separation entrance area row
The method that vehicle risk is evaluated, the factor that the evaluation model in this method considers mainly include that collide may property coefficient, collision
Car speed is poor, target lane is with 5 factors such as speed, acceleration, fore-aft vehicle spacing of the vehicle in collision of speeding, and these
Parameter is often difficult to obtain in actual operation.
To sum up, it is badly in need of a kind of street accidents risks appraisal procedure suitable for highway actual environment at present.
Summary of the invention
In view of this, the present invention provides a kind of traffic accidents methods of risk assessment, it is suitable for height by establishing
The street accidents risks assessment models of fast highway actual environment, using the model can street accidents risks to highway into
Row effectively assessment, has stronger operability.
In order to achieve the above objectives, the embodiment of the present invention adopts the following technical scheme that
In a first aspect, providing a kind of traffic accidents methods of risk assessment, comprising:
Establish street accidents risks assessment models: F=CV A·qB·vi C·(1+p)D, wherein F indicates street accidents risks
Value, CVIndicate the speed coefficient of variation, viIndicate that specific rate, q indicate traffic saturation degree, p indicates truck combination ratio, A, B, C, D table
Show assessment models parameter;
Logarithmic transformation is carried out to the street accidents risks assessment models, obtains corresponding multiple linear regression model: ln
(F)=Aln (CV)+Bln(q)+Cln(vi)+Dln(1+p);
It obtains the current at least M for implementing section and plays traffic accident data, and determine the wherein corresponding vehicle of every traffic accident
The fast coefficient of variation, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value;Wherein, M is positive integer;
By the corresponding speed coefficient of variation of every traffic accident, specific rate, traffic saturation degree, truck combination ratio and friendship
Interpreter's event value-at-risk obtains M group sample data as one group of sample data;
Parameter calibration is carried out to the multiple linear regression model according to the M group sample data, determines parameter A, B, C, D
Value, and then obtain currently implementing the corresponding street accidents risks assessment models in section;
Implement the corresponding street accidents risks assessment models in section according to current, determines current implement at each pile No. in section
Street accidents risks value.
Second aspect, a kind of traffic accidents methods of risk assessment, comprising:
Establish street accidents risks assessment models: F=CV A·qB·vi C·(1+p)D, wherein F indicates street accidents risks
Value, CVIndicate the speed coefficient of variation, viIndicate that specific rate, q indicate traffic saturation degree, p indicates truck combination ratio, A, B, C, D table
Show assessment models parameter;
Logarithmic transformation is carried out to the street accidents risks assessment models, obtains corresponding multiple linear regression model: ln
(F)=Aln (CV)+Bln(q)+Cln(vi)+Dln(1+p);
Traffic conflict statistical analysis, the corresponding speed variation lines of statistics each analysis unit are carried out to current section of implementing
Number, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value, and by the corresponding vehicle of each analysis unit
The fast coefficient of variation, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value are as one group of sample data;
Parameter calibration is carried out to the multiple linear regression model according to the sample data, determines parameter A, B, C, D
Value, and then obtain currently implementing the corresponding street accidents risks assessment models in section;
Implement the corresponding street accidents risks assessment models in section according to current, determines current implement at each pile No. in section
Street accidents risks value.
In traffic accidents methods of risk assessment provided by the invention, it is suitable for highway reality by establishing
The street accidents risks assessment models of environment, and traffic flow data, Jin Ergen are obtained according to the current concrete condition for implementing section
Parameter calibration is carried out according to the current traffic flow data for implementing section, determines and currently implements the corresponding street accidents risks assessment in section
Model finally determines the current street accidents risks value implemented at each pile No. in section based on this model.Based on provided by the invention
Traffic accidents methods of risk assessment, can the street accidents risks to highway effectively assessed, have compared with
Strong operability.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of flow diagram of traffic accidents methods of risk assessment provided in an embodiment of the present invention;
Fig. 2 is the process signal of another traffic accidents methods of risk assessment provided in an embodiment of the present invention
Figure;
Fig. 3 is the hourly traffic volume figure of certain highway in example provided in an embodiment of the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Fig. 1 show a kind of process signal of traffic accidents methods of risk assessment provided in an embodiment of the present invention
Figure, the street accidents risks assessment that this method is suitable for having the highway of history casualty data and traffic flow data.
As shown in Figure 1, traffic accidents methods of risk assessment provided in an embodiment of the present invention the following steps are included:
S101, street accidents risks assessment models: F=C are establishedV A·qB·vi C·(1+p)D。
Wherein, F indicates street accidents risks value, CVIndicate the speed coefficient of variation, q indicates traffic saturation degree, viIt indicates than speed
Degree, p indicate truck combination ratio, and A, B, C, D indicate assessment models parameter, and the above parameter is positive number.
It should be noted that the above-mentioned street accidents risks assessment models that the embodiment of the present invention is established are based primarily upon two sides
Consider in face --- the seriousness of a possibility that accident occurs and accident.
Wherein, a possibility that accident occurring can be characterized by the dispersion degree of speed and the saturation degree of traffic flow.
It generally, for the dispersion degree of speed, is expressed using speed standard deviation, but the size of standard deviation is usually and average
The size of value has certain relationship, and average speed is higher, and its dispersion degree is also bigger, its lower dispersion degree of average speed
It is lower.Therefore, for the variable that average level is different or measurement unit is different, it is discrete that its should not be directly compared with standard deviation
Degree.For this purpose, the speed coefficient of variation (Coefficient of Variation) can be used to compare data discrete degree, to disappear
Except too big or data dimension the different influences of measurement scale difference between different data, the dispersion degree of speed is characterized,
And the coefficient of variation is bigger, and expression speed scattering degree is bigger.In addition, then can directly be utilized for the degree of saturation of traffic flow
Traffic saturation degree characterizes.Traffic saturation degree is the characterization of traffic intensity, can characterize the size of the magnitude of traffic flow.According to highway work
Definition in journey technical standard (B01-2014 JTG), traffic saturation degree is the ratio between the volume of traffic and the benchmark traffic capacity, wherein high
The fast highway benchmark traffic capacity refers to corresponding maximum hourly traffic volume under Pyatyi service level.
For the seriousness of accident, by a large amount of vehicle impact testing data analysis found that when impact velocity is higher
And vehicle mass it is larger when, the seriousness degree of accident is higher.This is because the kinetic energy in the moment automobile of collision can turn
Become other form of energy in collision process, and kinetic energy when vehicle collides can indicate are as follows:M, that is, table
Show that vehicle mass, v indicate car speed.Based on this, the embodiment of the present invention is characterized using specific rate and truck combination ratio
The seriousness degree of accident.Wherein, specific rate is the ratio of average vehicle speed and 120km/h, and 120km/h is that China's high speed is public
Road Maximum speed limit.Truck combination ratio, that is, truck combination accounts for the ratio of vehicle fleet, and truck combination refers to that loading capacity is greater than 20 tons
Lorry.
S102, logarithmic transformation is carried out to street accidents risks assessment models, obtains corresponding multiple linear regression model: ln
(F)=Aln (CV)+Bln(q)+Cln(vi)+Dln(1+p)。
S103, the current at least M for implementing section traffic accident data are obtained, and determines that wherein every traffic accident is corresponding
The speed coefficient of variation, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value.
Wherein, M is positive integer.
A kind of specific implementation of the embodiment of the present invention in step S103, obtains the current at least M for implementing section and rises and hand over
Logical casualty data, can specifically include:
The current history casualty data and traffic flow data for implementing section is collected, according to the current history accident for implementing section
Data and traffic flow data obtain the current at least M for implementing section and play traffic accident data.
Wherein, every traffic accident data include accident occur for the previous period in by place where the accident occurred vehicle number,
The vehicle number n being had damage in vehicle and speed and accident.That is, the traffic flow data of place where the accident occurred upstream.Specifically,
The pile No. position of every accident can be determined according to accident record data, obtain accident pile No. position upstream (being no more than 1 kilometer)
The traffic flow data of (specifically can be within 5 minutes) in for the previous period occurs in accident for traffic flow measuring frequency section.It is so-called
Traffic flow measuring frequency section, refers to study the traffic condition in certain a road section, cuts the section of going out perpendicular to the section.Observation warp
The traffic flow conditions of the section are crossed, you can learn that the traffic condition in the section.Specifically, it will usually choose detection coil, thunder
It reaches, the position where the monitoring devices such as microwave and video is as measuring frequency section.
In addition, it is necessary to explanation, history casualty data can specifically be obtained from road administration department or traffic police department, and
Need to reject the data of the traffic accident occurred under the conditions of wherein adverse weather (including rain, snow, mist etc.) and due to driver
The casualty datas such as the data, such as fatigue driving, drink-driving of traffic accident caused by itself, finally obtain normal traffic item
Traffic flow data and casualty data under part, under the conditions of normal meteorological.In addition, it is contemplated that the accuracy of risk evaluation model parameter
And under actual conditions traffic accident data acquisition difficulty, need obtain at least 500 traffic accident data.
A kind of specific implementation of the embodiment of the present invention in step S103, determines the corresponding speed of every traffic accident
The coefficient of variation, specific rate, traffic saturation degree, truck combination ratio, specifically include:
The vehicle number and speed in for the previous period by place where the accident occurred occurs according to accident, every traffic is calculated
Speed standard deviation σ and speed average value in accident
According to speed standard deviation and speed average value, the first preset formula is utilized:Determine every traffic accident
Corresponding speed coefficient of variation CV;
According to speed average value, the second preset formula is utilized:Determine the corresponding specific rate of every traffic accident
vi;
The vehicle number and vehicle in for the previous period by place where the accident occurred occurs according to accident, is calculated in one hour
By the total wheel traffic Q of traffic accident spot, third preset formula is utilized:Determine that every traffic accident is corresponding
Traffic saturation degree q;In formula, C indicates the corresponding maximum hourly traffic volume of the road of Pyatyi service level.
The quantity P for counting truck combination in every traffic accident, utilizes the 4th preset formula:It determines
The corresponding truck combination ratio p of every traffic accident;In formula, N indicates that accident occurs in for the previous period by place where the accident occurred
Vehicle number.
Wherein, it should be noted that accident occur for the previous period in by place where the accident occurred the volume of traffic be converted to it is small
Hourly capacity is the total wheel traffic Q for passing through traffic accident spot in one hour.As an example it is assumed that accident occurs first 5 points
The volume of traffic of the vehicle by place where the accident occurred in clock is 50pcu, then Q is 50 × 12=600pcu/h.Wherein, it is counting
When the volume of traffic in for the previous period by place where the accident occurred occurs for calculation accident, need to be converted to corresponding work as according to specific vehicle
Car number is measured, specifically how to convert and belongs to general knowledge known in this field, the embodiment of the present invention repeats no more this.
In addition, it may also be noted that the specific value of the corresponding maximum hourly traffic volume C of the road of Pyatyi service level
It is related with current expressway design speed.Specifically, according to the note of " highway technical standard (JTG B01-2014) "
It carries, when expressway design speed is 120km/h, the maximum hourly traffic volume under Pyatyi service level is 2200 [pcu/ (h 〃
ln)];When expressway design speed is 100km/h, the maximum hourly traffic volume under Pyatyi service level is 2100 [pcu/
(h〃ln)];When expressway design speed is 80km/h, the maximum hourly traffic volume under Pyatyi service level is 2000
[pcu/(h〃ln)].In a kind of specific implementation of the embodiment of the present invention, in step S103, determine that every traffic accident is corresponding
Street accidents risks value, specifically include:
The vehicle in for the previous period by haveing damage in the vehicle number N and accident of place where the accident occurred occurs according to accident
Number n, determines the corresponding street accidents risks value of every traffic accident
S104, by the corresponding speed coefficient of variation of every traffic accident, specific rate, traffic saturation degree, truck combination ratio
And street accidents risks value obtains M group sample data as one group of sample data.
S105, parameter calibration is carried out to multiple linear regression model according to M group sample data, determines parameter A, B, C, D
Value, and then obtain currently implementing the corresponding street accidents risks assessment models in section.
Specifically, currently used Software of Data Statistics, such as SPSS can be used, the calibration of implementation model parameter.Calibration
In the process, the independent variable of model and the relationship of dependent variable are as shown in table 1.The calculating of data is corresponding with every traffic accident in table 1
One group of sample data be a computing unit, calculate separately independent variable numerical value corresponding with dependent variable, carry out related join later
Several staking-out works.
Table 1
S106, implement the corresponding street accidents risks assessment models in section according to current, determine and currently implement each stake in section
Street accidents risks value at number.
That is, obtaining the current real-time traffic flow data implemented at each pile No. in section, determine by the corresponding speed of each pile No.
These data are substituted into the current traffic accident for implementing section by the coefficient of variation, specific rate, traffic saturation degree, truck combination ratio
The street accidents risks value at each pile No. can be obtained in risk evaluation model.Street accidents risks value is bigger, indicates at the pile No.
The probability that traffic accident occurs is higher.So, the biggish place of road section traffic volume accident risk value can currently implemented
It is preferential to lay monitoring device and alarming device, to monitor and warn vehicular traffic.
To sum up, it in traffic accidents methods of risk assessment provided in an embodiment of the present invention, is applicable in by establishing
Logarithm change is carried out in the street accidents risks assessment models of highway actual environment, and then to street accidents risks assessment models
It changes, obtains corresponding multiple linear regression model, and obtain the current at least M for implementing section and play traffic accident data, according to working as
The preceding at least M for implementing section plays traffic accident data, determines the corresponding street accidents risks assessment models in current implementation section, most
Determine the current street accidents risks value implemented at each pile No. in section based on this model afterwards.Height based on the embodiment of the present invention
Fast road traffic accident methods of risk assessment, can the street accidents risks to highway effectively assessed, have relatively strong
Operability.
Street accidents risks appraisal procedure based on the highway that the embodiments of the present invention provide, can be to there is history thing
Therefore the highway of data and traffic flow data carries out street accidents risks assessment.However, in practical applications, casualty data is past
Toward being difficult to obtain or casualty data the level of detail is inadequate, just it is difficult to establish corresponding comment according to traffic accident data at this time
Estimate model and carries out risk assessment.
In view of this, the embodiment of the invention provides another traffic accidents methods of risk assessment, it is suitable for
The situation for implementing section history casualty data can not be obtained, Fig. 2 show the flow diagram of this method.
As shown in Fig. 2, traffic accidents methods of risk assessment provided in an embodiment of the present invention, including following step
It is rapid:
S201, street accidents risks assessment models: F=C are establishedV A·qB·vi C·(1+p)D。
Wherein, F indicates street accidents risks value, CVIndicate the speed coefficient of variation, viIndicate that specific rate, q indicate traffic saturation
Degree, p indicate truck combination ratio, and A, B, C, D indicate assessment models parameter.
S202, logarithmic transformation is carried out to street accidents risks assessment models, obtains corresponding multiple linear regression model: ln
(F)=Aln (CV)+Bln(q)+Cln(vi)+Dln(1+p)。
If S203, current section of implementing have shooting video there are traffic flow data but without history casualty data
Condition then determines the shooting period according to the current historical traffic flow data for implementing section, using unmanned plane when shooting section to working as
Preceding implementation section carries out video capture, carries out traffic conflict statistical analysis to current section of implementing based on captured video, determines
The corresponding speed coefficient of variation of each analysis unit, specific rate, traffic saturation degree, truck combination ratio and street accidents risks
Value;If currently implementing section there are traffic data but without history casualty data, and video can not be shot, then according to current real
The traffic data for applying section establishes the current virtual road model for implementing section using traffic simulation method, based on current real
The virtual road model for applying section carries out traffic conflict analysis, determines the corresponding speed coefficient of variation of each analysis unit, than speed
Degree, traffic saturation degree, truck combination ratio and street accidents risks value.
Wherein, traffic conflict refers under observable condition, two or more road users are in same time, sky
Between it is upper close to each other, if wherein a side takes improper traffic behavior, such as conversion direction, changes speed, suddenly parking, remove
Non- another party also accordingly takes hedging behavior, otherwise, it may occur that the phenomenon that collision.
Specifically, if currently implementing section there are traffic flow data but without history casualty data, and view can be shot
Frequently, then software or artificial side can be utilized later by video capture (as shot using currently a popular unmanned plane)
Legally constituted authority meter traffic conflict data establish street accidents risks assessment models with this.When being shot, need according to current real
The concrete condition for applying section chooses shooting section.For example, can be according to the actual needs siting of manager, or in typical case
Carry out shooting in section (places such as main-inlet of straightway, curved section, main line).In addition, the length in shooting section should be not less than
500m, it is contemplated that the clear coverage of video camera is limited, can also set up two video cameras simultaneously and be shot.Meanwhile it shooting
Time must not be less than 60 hours, for example, shoot 30 hours in flat peak phase on daytime, be divided into 10 groups of shootings, every group 3 hours, on peak
Phase shoots 30 hours, is divided into 10 groups of shootings, every group 3 hours.In addition, it is contemplated that the accuracy of model, to the higher situation of risk
The Serious conflicts number of accurate modeling, statistics must not be less than 1000 times.If Serious conflicts number is less, needs to continue to extend and clap
Take the photograph the time.Wherein, peak period refers to the period composed by a hourly traffic volume maximum hour and its each one hour of front and back,
The flat peak phase refers to the period composed by a hourly traffic volume the smallest hour and its front and back each hour.
If currently implementing section there are traffic data but without history casualty data, and video can not be shot, then utilized
The method of traffic simulation establishes virtual road model according to design document, and inputs the current traffic data for implementing section,
It is final to obtain colliding data.The situation refers mainly to the road in planning, construction period, does not put into actual operation, the volume of traffic also
Data are obtained in the planning stage by prediction, and the traffic data includes that type of vehicle and each type vehicle are corresponding
Vehicle number can be reported to obtain by the engineering feasibility study of project.In the case of this kind, the Serious conflicts sum of statistics must not lack
In 1000 times.Wherein, the foundation about virtual road model, it is microcosmic imitative using VISSIM more popular currently on the market etc.
True software, to vehicle on expressway with speeding on to simulate, to establish virtual road model.
In addition, it is necessary to explanation, the time span unit of traffic conflict statistical analysis specifically can be 20 minutes, i.e., often
20 minutes as an analytical unit progress data statistics.Why with 20 minutes be an analytical unit, allow in reality
In the situation of border, especially in the lesser situation of the volume of traffic, traffic conflict data can be less, thus by analytical unit setting compared with
It is long.Certainly, can also flexible setting according to the actual situation, the present invention is not especially limit this.
In a kind of specific implementation of the embodiment of the present invention, in step S203, the corresponding vehicle of each analysis unit is determined
The fast coefficient of variation, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value, specifically include:
The vehicle number and speed in section middle position by analysis in each analysis unit are counted, and then speed is calculated
Standard deviation sigma and speed average value
According to speed standard deviation and speed average value, the first preset formula is utilized:Determine each analysis list
The corresponding speed coefficient of variation C of memberV;
According to speed average value, the second preset formula is utilized:Determine the corresponding specific rate of each analysis unit
vi;
The vehicle for counting section middle position by analysis in each analysis unit, according in each analysis unit through excessive
The vehicle number and vehicle for analysing section middle position are calculated in one hour through the total wheel traffic Q in analysis section, utilize third
Preset formula:Determine the corresponding traffic saturation degree q of each analysis unit;Wherein, C indicates the road of Pyatyi service level
Corresponding maximum hourly traffic volume;
The quantity P for counting the truck combination in section middle position by analysis in each analysis unit, it is default using the 4th
Formula:Determine the corresponding truck combination ratio p of each analysis unit;Wherein, N indicates each analysis unit
In section middle position by analysis vehicle number.
It should be noted that analysis section refers to the section selected during obtaining traffic conflict data.
In a kind of specific implementation of the embodiment of the present invention, in step S203, the corresponding friendship of each analysis unit is determined
Interpreter's event value-at-risk, specifically includes:
The quantity s for counting Serious conflicts in each analysis unit, according to the quantity s of Serious conflicts and section by analysis
The vehicle number N in middle position determines the corresponding street accidents risks value of each analysis unit
Wherein, it should be noted that traffic conflict is divided into general conflict and Serious conflicts.Serious conflicts refer to that traffic participates in
Psychological pressure is quite big when person perceives danger, it is necessary to and quickly take effective urgent danger prevention behavior to be just avoided that accident, from
Dangerous criminal is to taking the very short traffic conflict of the time of hedging behavior.In highway, traffic conflict is divided into conflict of knocking into the back
Conflict with lane change.For conflict of knocking into the back, generally knocks into the back and conflict with the division limits for conflict of seriously knocking into the back with collision time (Time
To Collision, TTC) subject to, TTC is less than 2s and belongs to Serious conflicts, and TTC is greater than 2s and belongs to general conflict.TTC refers to
Two adjacent vehicles of front and back (rear car speed be higher than front truck) necessary evade behavior and collide required if do not taken
Time;For lane change conflict, the division limits of general lane change conflict and serious lane change conflict are subject to PET, and PET is less than 2s and belongs to
In Serious conflicts, PET is greater than 2s and belongs to general conflict.
S204, by the corresponding speed coefficient of variation of each analysis unit, specific rate, traffic saturation degree, truck combination ratio
And street accidents risks value is as one group of sample data.
S205, parameter calibration is carried out to multiple linear regression model according to sample data, determines taking for parameter A, B, C, D
Value, and then obtain currently implementing the corresponding street accidents risks assessment models in section.
Similar, currently used Software of Data Statistics, such as SPSS, the calibration of implementation model parameter can be used.It is calibrated
Cheng Zhong, the independent variable of model and the relationship of dependent variable are referring to aforementioned table 1.The calculating of data is corresponding with every each analytical unit in table 1
One group of sample data be a computing unit, calculate separately independent variable numerical value corresponding with dependent variable, carry out related join later
Several staking-out works.
S206, implement the corresponding street accidents risks assessment models in section according to current, determine and currently implement each stake in section
Street accidents risks value at number.
That is, obtaining the current real-time traffic flow data implemented at each pile No. in section, determine by the corresponding speed of each pile No.
These data are substituted into the current traffic accident for implementing section by the coefficient of variation, specific rate, traffic saturation degree, truck combination ratio
The street accidents risks value at each pile No. can be obtained in risk evaluation model.Street accidents risks value is bigger, indicates at the pile No.
The probability that traffic accident occurs is higher.So, the biggish place of road section traffic volume accident risk value can currently implemented
It is preferential to lay monitoring device and alarming device, to monitor and warn vehicular traffic.
Illustratively, it is given below with concrete case to traffic accidents risk provided in an embodiment of the present invention
Appraisal procedure is further described:
By taking domestic certain interchange exit region as an example, the section two-way six-lane, desin speed 120km/
h.Due to not being collected into traffic accident data, video capture is carried out using unmanned plane, obtains and shunts nose to upstream 500m
Traffic flow running rate in range.Specific step is as follows:
(1) video capture range 500m is determined, according to actual landform and shooting image definition, required for making rational planning for
Number of cameras;According to on-the-spot test as a result, plan is shot using two unmanned planes.
(2) live video is shot, and is guaranteed that image effect is clear, can clearly be recognized the operating status of vehicle.In order to guarantee
The accuracy of final mask parameter as far as possible shoots different traffic flow modes, including flat peak phase and peak period
Traffic flow modes.
(3) by one day, the hourly traffic volume on daytime (8:00-17:00) draws histogram, really according to the sequence of time
Determine the peak and minimum value of hourly traffic volume.It is clear as it can be seen that only selection progress on daytime in order to guarantee to shoot the vehicle in video
Video capture.
(4) according to the peak of hourly traffic volume and minimum value, determine shooting time: as can be seen from FIG. 3, the volume of traffic is minimum
3 hours (i.e. the 11:00-14:00) of value corresponding time previous hour and latter hour are the flat peak phase, flat peak phase shooting 10
Group adds up to 30 hours;The previous hour of volume of traffic peak and 3 hours (i.e. the 14:00-17:00) of latter hour are peak
Phase, peak period shoot 10 groups, add up to 30 hours.In this way, being marked according to 60 hours videos that the flat peak phase always shoots with peak period
Rational method.It is shot under the conditions of weather is good, is not considered the influence of bad weather condition.
(5) in order to guarantee the accuracy of model parameter, data volume is the bigger the better, therefore can prolong when conditions permit
The time of long video shooting, to obtain more traffic conflict data, but the shortest video capture time must not be small less than 60
When.
(6) in addition, it is contemplated that the accuracy of model, to the higher situation accurate modeling of risk, the Serious conflicts number of statistics
It must not be less than 1000 times.If Serious conflicts number is less, continue to extend shooting time.Table 2 show partial data statistics
As a result.
While counting colliding data, acquisition shoots the Vehicle Speed in section middle position, vehicle number and vehicle
The Serious conflicts number in road section scope is observed in type, acquisition.
Table 2
Second step, parameter calibration:
Firstly, to the carry out Logarithm conversion of street accidents risks assessment models:
Ln (F)=Aln (CV)+Bln(q)+Cln(vi)+Dln (1+p),
On this basis, the work that is further processed of data is completed, table 1 above-mentioned is shown in specific requirement.
Then, carry out parameter calibration using current prevalence data statistical software Spss to work, solving model parameter A, B,
C、D。
The parameter model result finally demarcated in present case is as follows:
F=CV -0.52·q5.07·vi 10.04·(1+p)-2.18。
Third, risk assessment:
According to above-mentioned model solution as a result, in conjunction with existing traffic flow data (detection coil, microwave and view on highway
The equipment such as frequency), the value of independent variable is calculated, obtains the value-at-risk of same path difference pile No., risk is carried out from high to low
Arrangement, calculated result are as shown in table 3:
Table 3
Pile No. | Risk ranking |
K3+000 | 1 |
K2+000 | 2 |
K7+000 | 3 |
K4+000 | 4 |
K9+000 | 5 |
K6+000 | 6 |
K1+000 | 7 |
K8+000 | 8 |
K5+000 | 9 |
… | … |
In conclusion passing through foundation in traffic accidents methods of risk assessment provided in an embodiment of the present invention
It is carried out pair suitable for the street accidents risks assessment models of highway actual environment, and then to street accidents risks assessment models
Transformation of variables obtains corresponding multiple linear regression model, and obtains the current traffic conflictcount for implementing section as the case may be
According to, determine therefrom that the corresponding street accidents risks assessment models in current implementation section, it is finally determining based on this model currently to implement
Street accidents risks value at each pile No. in section.Traffic accidents risk assessment side based on the embodiment of the present invention
Method, can the street accidents risks to highway effectively assessed, have stronger operability.
Those of ordinary skill in the art will appreciate that: realize that all or part of the steps of above method embodiment can pass through
The relevant hardware of program instruction is completed, and program above-mentioned can be stored in a computer readable storage medium, the program
When being executed, step including the steps of the foregoing method embodiments is executed;And storage medium above-mentioned includes: ROM, RAM, magnetic disk or light
The various media that can store program code such as disk.
The above description is merely a specific embodiment, but scope of protection of the present invention is not limited thereto, any
Those familiar with the art in the technical scope disclosed by the present invention, can easily think of the change or the replacement, and should all contain
Lid is within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (7)
1. a kind of traffic accidents methods of risk assessment characterized by comprising
Establish street accidents risks assessment models: F=CV A·qB·vi C·(1+p)D, wherein F indicates street accidents risks value, CV
Indicate the speed coefficient of variation, q indicates traffic saturation degree, viIndicate that specific rate, p indicate truck combination ratio, A, B, C, D expression are commented
Estimate model parameter;
Logarithmic transformation is carried out to the street accidents risks assessment models, obtains corresponding multiple linear regression model: ln (F)=
Aln(CV)+Bln(q)+Cln(vi)+Dln(1+p);
It obtains the current at least M for implementing section and plays traffic accident data, and determine that the corresponding speed of wherein every traffic accident becomes
Different coefficient, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value;Wherein, M is positive integer;
By the corresponding speed coefficient of variation of every traffic accident, specific rate, traffic saturation degree, truck combination ratio and traffic thing
Therefore value-at-risk obtains M group sample data as one group of sample data;
Parameter calibration is carried out to the multiple linear regression model according to the M group sample data, determines taking for parameter A, B, C, D
Value, and then obtain currently implementing the corresponding street accidents risks assessment models in section;
Implement the corresponding street accidents risks assessment models in section according to current, determines the current traffic implemented at each pile No. in section
Accident risk value.
2. the method according to claim 1, wherein the current at least M for implementing section of the acquisition plays traffic thing
Therefore data, comprising:
The current history casualty data and traffic flow data for implementing section is collected, according to the current history casualty data for implementing section
And traffic flow data, it obtains the current at least M for implementing section and plays traffic accident data;
Wherein, every traffic accident data include that the interior vehicle number by place where the accident occurred, vehicle for the previous period occur for accident
And the vehicle number n being had damage in speed and accident.
3. the method according to claim 1, wherein the corresponding speed variation lines of every traffic accident of the determination
Number, specific rate, traffic saturation degree, truck combination ratio, comprising:
The vehicle number and speed in for the previous period by place where the accident occurred occurs according to accident, every traffic accident is calculated
In speed standard deviation σ and speed average value
According to the speed standard deviation and the speed average value, the first preset formula is utilized:Determine every traffic thing
Therefore corresponding speed coefficient of variation CV;
According to the speed average value, the second preset formula is utilized:Determine the corresponding specific rate of every traffic accident
vi;
The vehicle number and vehicle in for the previous period by place where the accident occurred occurs according to accident, is calculated in one hour and passes through
The total wheel traffic Q of traffic accident spot, utilizes third preset formula:Determine the corresponding traffic of every traffic accident
Saturation degree q;Wherein, C indicates the corresponding maximum hourly traffic volume of the road of Pyatyi service level;
The quantity P for counting truck combination in every traffic accident, utilizes the 4th preset formula:Determine every friendship
The corresponding truck combination ratio p of interpreter's event;Wherein, N indicates that the vehicle in for the previous period by place where the accident occurred occurs for accident
Number.
4. according to the method described in claim 2, it is characterized in that, the corresponding traffic accident wind of every traffic accident of the determination
Danger value, comprising:
The interior vehicle number n by haveing damage in the vehicle number N and accident of place where the accident occurred for the previous period occurs according to accident,
Determine the corresponding street accidents risks value of every traffic accident
5. a kind of traffic accidents methods of risk assessment characterized by comprising
Establish street accidents risks assessment models: F=CV A·qB·vi C·(1+p)D, wherein F indicates street accidents risks value, CV
Indicate the speed coefficient of variation, viIndicate that specific rate, q indicate traffic saturation degree, p indicates truck combination ratio, and A, B, C, D expression are commented
Estimate model parameter;
Logarithmic transformation is carried out to the street accidents risks assessment models, obtains corresponding multiple linear regression model: ln (F)=
Aln(CV)+Bln(q)+Cln(vi)+Dln(1+p);
If currently implementing section there are traffic flow data but without history casualty data, and has video capture condition, then basis
The current historical traffic flow data for implementing section determines the shooting period, using unmanned plane when shooting section to it is current implement section into
Row video capture carries out traffic conflict statistical analysis to current section of implementing based on captured video, determines each analysis unit
The corresponding speed coefficient of variation, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value;
If currently implementing section there are traffic data but without history casualty data, and video can not be shot, then according to current
The traffic data for implementing section establishes the current virtual road model for implementing section, based on current using traffic simulation method
The virtual road model for implementing section carries out traffic conflict analysis, determines the corresponding speed coefficient of variation of each analysis unit, ratio
Speed, traffic saturation degree, truck combination ratio and street accidents risks value;
By the corresponding speed coefficient of variation of each analysis unit, specific rate, traffic saturation degree, truck combination ratio and traffic thing
Therefore value-at-risk is as one group of sample data;
Parameter calibration is carried out to the multiple linear regression model according to the sample data, determines the value of parameter A, B, C, D,
And then it obtains currently implementing the corresponding street accidents risks assessment models in section;
Implement the corresponding street accidents risks assessment models in section according to current, determines the current traffic implemented at each pile No. in section
Accident risk value.
6. according to the method described in claim 5, it is characterized in that, the corresponding speed variation lines of the determining each analysis unit
Number, specific rate, traffic saturation degree, truck combination ratio and street accidents risks value, comprising:
The vehicle number and speed in section middle position by analysis in each analysis unit are counted, and then vehicle speed standard is calculated
Poor σ and speed average value
According to the speed standard deviation and the speed average value, the first preset formula is utilized:Determine each analysis
The corresponding speed coefficient of variation C of unitV;
According to the speed average value, the second preset formula is utilized:Determine the corresponding specific rate of each analysis unit
vi;
The vehicle for counting section middle position by analysis in each analysis unit, according to road by analysis in each analysis unit
The vehicle number and vehicle in section middle position are calculated in one hour through the total wheel traffic Q in analysis section, default using third
Formula:Determine the corresponding traffic saturation degree q of each analysis unit;Wherein, C indicates the road pair of Pyatyi service level
The maximum hourly traffic volume answered;
The quantity P for counting the truck combination in section middle position by analysis in each analysis unit, utilizes the 4th preset formula:Determine the corresponding truck combination ratio p of each analysis unit;Wherein, N indicates to pass through in each analysis unit
Analyze the vehicle number in section middle position.
7. according to the method described in claim 5, it is characterized in that, the corresponding traffic accident wind of the determining each analysis unit
Danger value, comprising:
The quantity s of Serious conflicts in each analysis unit is counted, according to the quantity s of Serious conflicts and by analysis among section
The vehicle number N of position determines the corresponding street accidents risks value of each analysis unit
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811156908.6A CN109118773B (en) | 2018-09-30 | 2018-09-30 | A kind of traffic accidents methods of risk assessment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811156908.6A CN109118773B (en) | 2018-09-30 | 2018-09-30 | A kind of traffic accidents methods of risk assessment |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109118773A true CN109118773A (en) | 2019-01-01 |
CN109118773B CN109118773B (en) | 2019-10-01 |
Family
ID=64857154
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811156908.6A Active CN109118773B (en) | 2018-09-30 | 2018-09-30 | A kind of traffic accidents methods of risk assessment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109118773B (en) |
Cited By (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110348129A (en) * | 2019-07-12 | 2019-10-18 | 山西省交通规划勘察设计院有限公司 | A kind of highway overpass bridge anticollision fender system design method |
CN111598482A (en) * | 2020-05-26 | 2020-08-28 | 中国国家铁路集团有限公司 | Railway transportation safety assessment method and device and computer equipment |
CN112037513A (en) * | 2020-09-01 | 2020-12-04 | 清华大学 | Real-time traffic safety index dynamic comprehensive evaluation system and construction method thereof |
CN112365707A (en) * | 2020-09-22 | 2021-02-12 | 合肥工业大学 | Evaluation method and system for traffic patrol service of unmanned aerial vehicle |
CN112435458A (en) * | 2019-06-21 | 2021-03-02 | 北京航空航天大学 | Emergency simulation method for unmanned aerial vehicle on highway under traffic accident |
CN112562337A (en) * | 2020-12-10 | 2021-03-26 | 之江实验室 | Expressway real-time traffic accident risk assessment method based on deep learning |
CN113345224A (en) * | 2021-05-20 | 2021-09-03 | 河南硕翔信息技术有限公司 | Highway data high efficiency storage system based on computer vision |
WO2021203972A1 (en) * | 2020-11-19 | 2021-10-14 | 平安科技(深圳)有限公司 | Risk prevention method, apparatus and device based on collision model, and storage medium |
CN113780783A (en) * | 2021-09-01 | 2021-12-10 | 苏交科集团股份有限公司 | Automatic analysis method for risk degree of road traffic safety accident |
CN113920726A (en) * | 2021-09-30 | 2022-01-11 | 东南大学 | Multi-source risk overlapping and grading method for traffic operation of large-scale movable road |
CN114241753A (en) * | 2021-12-03 | 2022-03-25 | 东南大学 | Road safety evaluation method and system based on multi-dimensional influence factors |
CN114492544A (en) * | 2022-04-15 | 2022-05-13 | 腾讯科技(深圳)有限公司 | Model training method and device and traffic incident occurrence probability evaluation method and device |
CN114973648A (en) * | 2022-04-11 | 2022-08-30 | 长安大学 | Expressway high-risk section identification method based on meteorological responsivity |
CN115762140A (en) * | 2022-11-01 | 2023-03-07 | 山东高速集团有限公司 | Highway traffic accident risk prediction method considering variable heterogeneity |
WO2023151034A1 (en) * | 2022-02-11 | 2023-08-17 | 华为技术有限公司 | Traffic condition detection method, readable medium and electronic device |
CN116739354A (en) * | 2023-08-14 | 2023-09-12 | 深圳市城市交通规划设计研究中心股份有限公司 | Road safety risk assessment index calculation method, electronic equipment and storage medium |
CN116959248A (en) * | 2023-07-22 | 2023-10-27 | 同济大学 | Expressway accident risk optimization method based on interactive self-interpretation model |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937421A (en) * | 2009-07-03 | 2011-01-05 | 上海大潮电子技术有限公司 | Method for collecting real-time operation information of vehicle for operation security risk assessment |
CN103093620A (en) * | 2013-01-07 | 2013-05-08 | 东南大学 | Determination method of motor vehicle traffic conflict number based on conflict traffic flow characteristics |
CN106355883A (en) * | 2016-10-20 | 2017-01-25 | 同济大学 | Risk evaluation model-based traffic accident happening probability acquiring method and system |
CN106897826A (en) * | 2017-02-23 | 2017-06-27 | 吉林大学 | A kind of street accidents risks appraisal procedure and system |
CN108109379A (en) * | 2018-01-26 | 2018-06-01 | 东南大学 | A kind of expressway exit ring road region security evaluation method |
-
2018
- 2018-09-30 CN CN201811156908.6A patent/CN109118773B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101937421A (en) * | 2009-07-03 | 2011-01-05 | 上海大潮电子技术有限公司 | Method for collecting real-time operation information of vehicle for operation security risk assessment |
CN103093620A (en) * | 2013-01-07 | 2013-05-08 | 东南大学 | Determination method of motor vehicle traffic conflict number based on conflict traffic flow characteristics |
CN106355883A (en) * | 2016-10-20 | 2017-01-25 | 同济大学 | Risk evaluation model-based traffic accident happening probability acquiring method and system |
CN106897826A (en) * | 2017-02-23 | 2017-06-27 | 吉林大学 | A kind of street accidents risks appraisal procedure and system |
CN108109379A (en) * | 2018-01-26 | 2018-06-01 | 东南大学 | A kind of expressway exit ring road region security evaluation method |
Non-Patent Citations (3)
Title |
---|
CHU ZHAOMING 等: "A Study on the Evaluation Method of the Freeway Traffic Accidents Forewarning System", 《2010 INTERNATIONAL CONFERENCE ON OPTOELECTRONICS AND IMAGE PROCESSING》 * |
王海鹏 等: "基于车型比例的速度离散与交通事故率关系研究", 《青岛理工大学学报》 * |
胡功宏 等: "高速公路交通流实时安全性评价", 《安全与环境学报》 * |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112435458B (en) * | 2019-06-21 | 2022-03-11 | 北京航空航天大学 | Emergency simulation method for unmanned aerial vehicle on highway under traffic accident |
CN112435458A (en) * | 2019-06-21 | 2021-03-02 | 北京航空航天大学 | Emergency simulation method for unmanned aerial vehicle on highway under traffic accident |
CN110348129A (en) * | 2019-07-12 | 2019-10-18 | 山西省交通规划勘察设计院有限公司 | A kind of highway overpass bridge anticollision fender system design method |
CN111598482A (en) * | 2020-05-26 | 2020-08-28 | 中国国家铁路集团有限公司 | Railway transportation safety assessment method and device and computer equipment |
CN111598482B (en) * | 2020-05-26 | 2023-08-08 | 中国国家铁路集团有限公司 | Railway transportation safety assessment method and device and computer equipment |
CN112037513A (en) * | 2020-09-01 | 2020-12-04 | 清华大学 | Real-time traffic safety index dynamic comprehensive evaluation system and construction method thereof |
CN112365707A (en) * | 2020-09-22 | 2021-02-12 | 合肥工业大学 | Evaluation method and system for traffic patrol service of unmanned aerial vehicle |
WO2021203972A1 (en) * | 2020-11-19 | 2021-10-14 | 平安科技(深圳)有限公司 | Risk prevention method, apparatus and device based on collision model, and storage medium |
CN112562337A (en) * | 2020-12-10 | 2021-03-26 | 之江实验室 | Expressway real-time traffic accident risk assessment method based on deep learning |
CN113345224A (en) * | 2021-05-20 | 2021-09-03 | 河南硕翔信息技术有限公司 | Highway data high efficiency storage system based on computer vision |
CN113780783A (en) * | 2021-09-01 | 2021-12-10 | 苏交科集团股份有限公司 | Automatic analysis method for risk degree of road traffic safety accident |
CN113920726A (en) * | 2021-09-30 | 2022-01-11 | 东南大学 | Multi-source risk overlapping and grading method for traffic operation of large-scale movable road |
US11887472B2 (en) | 2021-12-03 | 2024-01-30 | Southeast University | Method and system for evaluating road safety based on multi-dimensional influencing factors |
US20230215270A1 (en) * | 2021-12-03 | 2023-07-06 | Southeast University | Method and system for evaluating road safety based on multi-dimensional influencing factors |
CN114241753A (en) * | 2021-12-03 | 2022-03-25 | 东南大学 | Road safety evaluation method and system based on multi-dimensional influence factors |
CN114241753B (en) * | 2021-12-03 | 2022-11-01 | 东南大学 | Road safety evaluation method and system based on multi-dimensional influence factors |
WO2023151034A1 (en) * | 2022-02-11 | 2023-08-17 | 华为技术有限公司 | Traffic condition detection method, readable medium and electronic device |
CN114973648A (en) * | 2022-04-11 | 2022-08-30 | 长安大学 | Expressway high-risk section identification method based on meteorological responsivity |
CN114973648B (en) * | 2022-04-11 | 2024-03-19 | 长安大学 | Expressway high-risk road section identification method based on meteorological responsiveness |
CN114492544A (en) * | 2022-04-15 | 2022-05-13 | 腾讯科技(深圳)有限公司 | Model training method and device and traffic incident occurrence probability evaluation method and device |
CN114492544B (en) * | 2022-04-15 | 2022-07-26 | 腾讯科技(深圳)有限公司 | Model training method and device and traffic incident occurrence probability evaluation method and device |
CN115762140A (en) * | 2022-11-01 | 2023-03-07 | 山东高速集团有限公司 | Highway traffic accident risk prediction method considering variable heterogeneity |
CN115762140B (en) * | 2022-11-01 | 2024-06-07 | 山东高速集团有限公司 | Expressway traffic accident risk prediction method considering variable heterogeneity |
CN116959248A (en) * | 2023-07-22 | 2023-10-27 | 同济大学 | Expressway accident risk optimization method based on interactive self-interpretation model |
CN116959248B (en) * | 2023-07-22 | 2024-04-05 | 同济大学 | Expressway accident risk optimization method based on interactive self-interpretation model |
CN116739354A (en) * | 2023-08-14 | 2023-09-12 | 深圳市城市交通规划设计研究中心股份有限公司 | Road safety risk assessment index calculation method, electronic equipment and storage medium |
CN116739354B (en) * | 2023-08-14 | 2024-02-27 | 深圳市城市交通规划设计研究中心股份有限公司 | Road safety risk assessment index calculation method, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
CN109118773B (en) | 2019-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109118773B (en) | A kind of traffic accidents methods of risk assessment | |
WO2020244288A1 (en) | Method and apparatus for evaluating truck driving behaviour based on gps trajectory data | |
CN106355883A (en) | Risk evaluation model-based traffic accident happening probability acquiring method and system | |
CN110020797A (en) | The evaluation method of automatic Pilot test scene based on perception defect | |
Goyani et al. | Investigation of traffic conflicts at unsignalized intersection for reckoning crash probability under mixed traffic conditions | |
CN109002622B (en) | Method for estimating overall load response of large-span bridge under random traffic flow effect | |
CN104294720A (en) | Method for evaluating safety of expressway design scheme | |
CN113160593A (en) | Mountain road driving safety early warning method based on edge cloud cooperation | |
CN106530714A (en) | Secondary traffic accident time prediction method based on traffic flow data | |
CN112735139A (en) | Device and method for checking potential safety hazards of common roads | |
CN109598937A (en) | A kind of detection of road curve safe speed and alarming device and method | |
CN110738591A (en) | Method for calculating traffic safety benefit of climbing lane based on tendency value matching | |
Ataelmanan et al. | Examination of lane changing duration time on expressway | |
CN117238139B (en) | Real-time road condition early warning system based on meteorological data | |
Kang et al. | An analysis of characteristics of heavy vehicle behavior at roundabouts in Japan | |
CN116001800B (en) | Vehicle driving risk information acquisition method and device, electronic equipment and medium | |
CN116753938A (en) | Vehicle test scene generation method, device, storage medium and equipment | |
CN113192340B (en) | Method, device, equipment and storage medium for identifying highway construction vehicles | |
CN115909542A (en) | Automatic driving vehicle testing method and testing field based on expected functional safety | |
Liu et al. | Construction of driving behavior scoring model based on obd terminal data analysis | |
CN108417050A (en) | A kind of excess speed event real-time detecting method based on continuous hypervelocity GPS track point | |
CN114565155A (en) | Road safety testing method and device, electronic equipment and storage medium | |
DE102019218111A1 (en) | Method for generating location information on relevant road sections for the detection of wrong-way trips and method for detecting wrong-way trips | |
Leong et al. | Impact of measurement methods on the development of freeflow speed estimation model for basic segment expressways in Malaysia | |
CN115410072B (en) | Method and system for testing video event detection algorithm |
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 | ||
CB03 | Change of inventor or designer information | ||
CB03 | Change of inventor or designer information |
Inventor after: Liu Jianbei Inventor after: Ma Xiaolong Inventor after: Wu Mingxian Inventor after: Wang Zuo Inventor after: Chi Gandu Inventor before: Liu Jianbei Inventor before: Ma Xiaolong Inventor before: Chi Gandu |
|
GR01 | Patent grant | ||
GR01 | Patent grant |