KR20170065898A - Method for predicting possibility of a traffic accident occurrence on road and device for the same - Google Patents

Method for predicting possibility of a traffic accident occurrence on road and device for the same Download PDF

Info

Publication number
KR20170065898A
KR20170065898A KR1020150172245A KR20150172245A KR20170065898A KR 20170065898 A KR20170065898 A KR 20170065898A KR 1020150172245 A KR1020150172245 A KR 1020150172245A KR 20150172245 A KR20150172245 A KR 20150172245A KR 20170065898 A KR20170065898 A KR 20170065898A
Authority
KR
South Korea
Prior art keywords
traffic accident
link
reference link
traffic
occurrence
Prior art date
Application number
KR1020150172245A
Other languages
Korean (ko)
Inventor
정연식
Original Assignee
한국교통연구원
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 한국교통연구원 filed Critical 한국교통연구원
Priority to KR1020150172245A priority Critical patent/KR20170065898A/en
Publication of KR20170065898A publication Critical patent/KR20170065898A/en

Links

Images

Classifications

    • G06Q50/30—
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/161—Decentralised systems, e.g. inter-vehicle communication
    • G08G1/163—Decentralised systems, e.g. inter-vehicle communication involving continuous checking
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/16—Anti-collision systems
    • G08G1/166—Anti-collision systems for active traffic, e.g. moving vehicles, pedestrians, bikes

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Operations Research (AREA)
  • Tourism & Hospitality (AREA)
  • Traffic Control Systems (AREA)

Abstract

Discloses a technology for calculating and providing information on the possibility of a traffic accident occurring in a specific time zone in the future from a specific link on the road. For this purpose, a prediction model for predicting the probability of a traffic accident on the specific link can be learned. At this time, learning of the predictive model can be performed using information that can be acquired from other links existing upstream and downstream of the specific link.

Description

TECHNICAL FIELD The present invention relates to a method for predicting the occurrence of a traffic accident caused by deterioration of weather on a road,

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a computing technology, and more particularly, to a technique for calculating a possibility of a traffic accident on a road based on collected traffic information.

It can be expected that the probability of a traffic accident on the road will be affected by several factors. For example, the values of the traffic accident occurrence point and the traffic flow at the upstream and downstream thereof, the weather situation at the traffic accident occurrence point and its upstream and downstream, the traffic accident occurrence point, and the geometrical shape of the roads in the upstream and downstream thereof have.

Information on the past and present weather conditions can be obtained from a server of the meteorological office, values relating to the traffic flow can be obtained through the police agency and a private traffic information service company, and values relating to the geometric shape of the road Can be obtained from the road management authority. Further, future information on the above-described values can be obtained as a predicted value according to a predetermined prediction algorithm.

Information on the occurrence of a traffic accident in a specific road section in the past can be obtained through the police agency and the transportation insurance company. However, there is a problem that it is difficult to obtain a predicted value for the possibility of a traffic accident in the future in the specific road section.

The present invention provides a technique for calculating the possibility of a traffic accident on a specific link on a road in a future specific time period. The present invention also provides a technique for providing a possibility of a traffic accident in the front when the vehicle is traveling on the road.

In the present invention, a prediction model can be learned to predict a possibility of a traffic accident on a specific link of a road. At this time, learning of the predictive model can be performed using information that can be acquired from other links existing upstream and downstream of the specific link.

A traffic information providing method according to an aspect of the present invention is a traffic information providing method in which a server provides traffic information to a vehicle, the method comprising the steps of: receiving information on a current position of the vehicle; estimating Calculating a reference link and a time that is expected to reach the reference link, calculating information about a possibility of a traffic accident in the reference link during a future time period including the expected time, And providing the vehicle with information about the possibility of a traffic accident.

The step of calculating includes the steps of preparing a prediction model having a possibility of occurrence of a traffic accident by time in the reference link as a dependent variable and having one or more variables as independent variables, Obtaining a value of the one or more variables in a reference link and assigning the value of the one or more obtained variables to the prediction model to determine a probability of a traffic accident on the reference link in the future time period And a step of calculating a value with respect to < RTI ID = 0.0 >

Here, the at least one variable may be a value related to at least one of traffic volume, speed, linearity, gradient, number of lanes, speed limit, average annual traffic volume, and weather conditions.

And the prediction model is a binomial logit model in which the dependent variable is determined by a linear equation of the independent variables.

The prediction model may include at least one reference link, one or more upstream links positioned upstream in reference to the reference link, and one or more downstream links located downstream in reference to the reference link 'A traffic accident occurrence in each link' and 'a value for one or more variables' acquired for each of a plurality of links, and 'whether or not a traffic accident occurred in each link' and The 'one or more variables' may be obtained for a plurality of times.

A method for predicting the occurrence of a traffic accident according to an aspect of the present invention is a method for predicting a possibility of a traffic accident in a specific time zone on a reference link of a road, Preparing data defining one or more upstream links located upstream in reference to a reference link and a plurality of links including one or more downstream links located downstream in reference to the reference link; And preparing a predictive model having at least one variable for each link as an input variable and having the possibility of occurrence of the traffic accident on the reference link as an output variable, The prediction model is learned using a 'case of occurrence of a traffic accident on each link' and 'one or more variables' .

Wherein, by assigning to the input variable of the learned prediction model the value predicted to have the one or more variables for a future time period with respect to the reference link, And outputting the possibility of occurrence of a traffic accident.

An apparatus for calculating the likelihood of a traffic accident according to an aspect of the present invention includes a road, a reference link, one or more upstream links positioned upstream in reference to the reference link, And calculating a probability of occurrence of a traffic accident in a specific time zone on the reference link by dividing the link into a plurality of links including one or more downstream links, A data acquiring section for acquiring a value relating to at least one of a linearity, a gradient, a number of lanes, a speed limit, an average annual traffic volume, and a weather condition as variables and acquiring a past traffic accident occurrence for the plurality of links, . The calculation unit may include a step of preparing a predictive model having a variable in the plurality of links as an input variable and having the possibility of occurrence of the traffic accident in the reference link as an output variable, And a step of learning the predictive model using 'the occurrence of a traffic accident in each link' and the 'one or more variables' acquired for each of the links.

At this time, the calculation unit may assign the predicted value of the one or more variables to the input variable of the learned prediction model with respect to the reference link during a future time period, And outputting the possibility of the traffic accident in the link.

And the data obtaining unit obtains a value relating to at least one of the traffic volume, the speed, the linearity of the road, the gradient, the number of lanes, the speed limit, the average annual traffic volume, And acquiring the information through the network.

In this case, the information providing unit may further include an information providing unit configured to provide the output possibility of the traffic accident occurrence to a vehicle expected to pass through the reference link during the future time period.

According to the present invention, it is possible to provide a technique for calculating the probability of occurrence of a traffic accident on a specific link on a road in a specific time period of the future. And, when the vehicle is traveling on the road, it is possible to provide a technique for providing a possibility of a traffic accident in the front.

FIG. 1 is a view for explaining a concept of defining roads by dividing them into a plurality of links according to an embodiment of the present invention. Referring to FIG.
FIG. 2 is a table showing traffic accident information collected on a specific date, and indicates whether or not a traffic accident occurred at each time in each defined link.
FIG. 3 illustrates an example of an equation according to an embodiment of the present invention showing a probability of a traffic accident occurring at a reference link (link0) at a specific time, and a method for obtaining coefficients of this equation.
4 is a flowchart showing a method of determining coefficients of the equation shown in FIG. 3 according to an embodiment of the present invention.
5 is a flowchart illustrating a method for calculating the probability of occurrence of a traffic accident at a future time point on a specific reference link using the formula determined through the algorithm of FIG. 4 according to an embodiment of the present invention.
6 is a flowchart showing a method for providing a possibility of a traffic accident in front of a specific vehicle running on the road according to an embodiment of the present invention.
FIG. 7 is a table showing an example of data prepared for calculating an equation about the possibility of a traffic accident at a specific time in the link (link-1) 9 in FIG.

Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. However, the present invention is not limited to the embodiments described herein, but may be implemented in various other forms. The terminology used herein is for the purpose of understanding the embodiments and is not intended to limit the scope of the present invention. Also, the singular forms as used below include plural forms unless the phrases expressly have the opposite meaning.

The method for estimating the probability of occurrence of a traffic accident according to an embodiment of the present invention can be performed through the following steps.

First, at step S10, as shown in Figs. 1A and 1B, a road section 100 having a specific length can be defined by dividing it into a plurality of links 8-12. The length of each link may be a predetermined value.

One of the plurality of links shown in FIG. 1 may be selected and referred to as a " reference link ". At this time, the direction in which the vehicle enters the " reference link " is referred to as the upstream direction, and the direction in which the vehicle advances may be referred to as the downstream direction. The link existing in the upstream direction may be referred to as an upstream link, and the link existing in the downstream direction may be referred to as a downstream link. For example, in FIG. 1, when a link 10 is used as a reference link, a link 8 is linked to an upstream link, and a link Downstream link.

Next, in step S20, as shown in FIG. 2, information on whether or not a traffic accident has occurred in each defined link and information on variables in each link can be collected on a time-by-time basis. Here, the time may be defined as one hour unit (ex: H 00: 0 to 01:00) as illustrated in FIG. 2, but may be defined to have a different time length. The meaning of the above-mentioned 'variable' will be explained together with step S40 below.

Information on the occurrence of the traffic accident can be provided by the traffic accident probability analysis server 1 through the network from the traffic information holding server 2.

The traffic information holding server 2 can acquire traffic accident information, road geometry information, and traffic information through a police agency, a traffic insurance company, a road management agency, and / or a private traffic information service company, Information can be obtained.

The traffic accident probability analysis server 1 and the traffic information holding server 2 may be separated from each other or may be installed together in one apparatus.

Next, in step S30, the traffic accident probability analysis server 1 can construct a table as shown in Fig. 2 by using the information on the traffic accidents provided. For example, if a traffic accident occurred only between 22:00 and 23:00 on Jan. 1, 2015, and a traffic accident occurred on the link (link 0) 10, the table may be configured as shown in FIG.

In the column of the table of Fig. 2, two links (link + 1, link + 2) (11, 12) coming along the traveling direction of the vehicle centered on a link (link0) -2) (9, 8) are displayed. In the row of the table in Fig. 2, there are displayed 24 time periods in which a day is divided into units of one hour. Therefore, 5 * 24 = 120 cells are shown in the table of FIG. Each cell may have a link corresponding to each cell and whether or not a traffic accident has occurred in the time. Here, the link (link 0) 10 may be referred to as a 'reference link' hereinafter. Each row of the table of Fig. 2 is denoted by index i (i = 1 to 24), and each column is denoted by index j (j = 1 to 5).

The table shown in Fig. 2 relating to the reference link (link0) 10 may be configured for a plurality of blades.

Next, in step S40, the traffic accident probability analysis server 1 may calculate a coefficient of a mathematical expression indicating a probability of occurrence of a traffic accident at a specific time on the reference link (link 0) 10.

The above equation can be given as shown in FIG. 3 (a). 3 (a) shows an example of an equation according to an embodiment of the present invention for calculating the probability of occurrence of a traffic accident on a reference link (link 0) at a specific time zone. Hereinafter, the mathematical expression shown in FIG. 3 (a) will be referred to as "mathematical expression 1". When the coefficients a, b, and c of Equation 1 are determined using past accident information in which the occurrence time and position are variously distributed, the probability of a traffic accident occurring at the reference link (link 0) Can be calculated.

In Equation (1), y i, j on the left side indicates the possibility of a traffic accident at time (i) and link (j), and may have a value between 0 and 1.

In Equation (1), xk i, j on the right side represents the value of the kth variable corresponding to the time (i) and the link (j) (k is a natural number). The variable xk may be, but is not limited to, traffic volume, speed, linearity, gradient, number of lanes, speed limit, average daily traffic volume, and weather conditions. In FIG. 3 (a), the case where k has only values of 1, 2, and 3 is illustrated, but the maximum value of k may have a larger value according to the embodiment. The variable may have been collected in step S20.

For example, the first variable x1 i, j may mean the amount of traffic at time (i) and link (j). And the second variable x2 i, j can mean precipitation at time (i) and link (j). And the third variable, x3 i, j, can represent the road gradient at the link (j). For example, the road gradient may mean the curvature of the road or the inclination of the road. The third variable is not a value that varies with time, but can be regarded as a variable in that it can have different values for each link. Other possible parameters may exist, but the present invention is not limited in any way by the specific examples of these parameters.

As another variable, for example, the fourth variable may be further considered. This fourth variable x4 i, j can mean road controllability at time (i) and link (j). For example, when the link (j) includes an intersection or a crosswalk, there is a possibility that the road is controlled due to a periodic signal change of the traffic light. Such road control possibilities can be provided based on the flashing period of the traffic lights in the corresponding section.

Now, with reference to FIG. 3 (b), a method of calculating a coefficient to obtain the values of the coefficients a, b, and c will be described.

According to an embodiment of the present invention, the coefficient calculation method may be implemented by a binary logit model.

According to an embodiment of the present invention, a value related to occurrence of an accident corresponding to each cell (i, j) in the table shown in FIG. 2 is substituted into y i, j in Equation 1 , Can be substituted into xk i, j in Equation (1). Here, the 'value relating to occurrence of an accident' described above has a definite value of 0 or 1 since it relates to a fact of a past definite traffic accident. The value of the occurrence of the accident and the value of the kth variable described above may be a value that has already been determined since it is a collection of facts already existing in the past.

Such variable assignment can be performed for all 120 cells shown in Table 1. [ As a result, a total of 120 equations can be obtained as shown in Fig. 3 (b). The indeterminate values in the 120 equations are the three coefficients a, b, and c. This coefficient can be determined by applying the maximum likelihood method. That is, if the values of the variables presented in the invention exist in all time zones and roads, the same processing can be performed for all traffic accidents that occurred in the past. By using all values created as shown in FIG. 2 (b) By applying the estimation method, the optimal values of a, b, and c can be determined.

In the above, the optimal values of a, b, and c are determined using the data collected during a single day. However, optimal values of a, b, and c may be determined using data collected for a plurality of days.

Next, in step S50, the mathematical expression indicating the probability of occurrence of a traffic accident by time in the reference link (link 0) 10 can be determined using the determined optimum values a, b, and c.

For example, if it is determined that a, b, and c have 1.3, 3.4, and 0.8, y i, j = 1.3 x i i, j + 3.4 x 2 i, j + 0.8 x 3 i, j As shown in FIG.

4 is a flowchart illustrating an algorithm for determining an equation for predicting the probability of occurrence of a traffic accident over time in a reference link according to an embodiment of the present invention. This flowchart includes steps S10 to S50 described above.

So far, we have shown how to use the data collected in the past to determine the mathematical formulas needed to predict the future.

A method according to an embodiment of the present invention for predicting the probability of a traffic accident at the reference link (link 0) 10 will now be described using the determined formula.

In step S110, the traffic accident probability analysis server 1 may prepare a mathematical expression indicating the probability of occurrence of a traffic accident over time on the reference link (link 0) 10. This equation may be a formula determined according to the algorithm of FIG. 4 described above.

Next, in step S120, the traffic accident probability analysis server 1 receives the values of the variables at the future time (i) on the reference link (link0) 10 from the variable providing server 2 . The variables may be variables included in the equation. The variable provision server 2 obtains from the sensors attached to the vehicle traveling on the road some of the values for the variables obtained from other servers, the other obtained from the traffic surveillance camera can do. The values of the variables in the time (i) of 'future' in the reference link (link0) 10 may be replaced with the current values closest to the 'future', and the values of ' Lt; / RTI > The algorithm for predicting the values of the variables in the 'future' time (j) may be provided using a technique already disclosed or may be separately created, so that the scope of the present invention is not limited thereto.

Next, in step S130, the traffic accident probability analysis server 1 substitutes the values of the supplied variables into the determined equation, and calculates the link 0 (link 0) in the future time (i) The value y ij can be calculated with respect to the probability of occurrence of a traffic accident.

Hereinafter, a method for providing a possibility of a traffic accident in front of a specific vehicle running on the road according to an embodiment of the present invention will be described with reference to FIG.

In step S210, the traffic accident probability analysis server 1 may receive information on the position of the first vehicle 5 from the first vehicle 5. [ At this time, the traffic accident probability analysis server 1 may further receive information on the traveling direction of the first vehicle 5, or may determine the traveling direction itself using information on the received position.

Hereinafter, it can be assumed that the first vehicle 5 is located on the link (link-1) 9 described above.

In step S220, the traffic accident probability analysis server 1 can determine the time zone at which the first vehicle 5 reaches the reference link link0 and the reference link link0 at which the first vehicle 5 will arrive in the near future. For example, if the first vehicle 5 is located on the current link (link-1) 9, the current time may be the time corresponding to the time index i = 22 in FIG. At this time, the time at which the first vehicle 5 reaches the reference link (link 0) 10 may be determined according to the speed of the first vehicle 5. It may be determined that the time at which the first vehicle 5 reaches the reference link link0 10 is the time corresponding to the time index i = 23 in Fig.

In step S230, the traffic accident probability analysis server 1 uses an algorithm according to an embodiment of the present invention for predicting the probability of a traffic accident in the reference link (link 0) 10 described in FIG. 5, Information about the likelihood of a traffic accident occurring on the reference link (link 0) 10 while the first vehicle 5 passes through the reference link (link 0) 10. Here, the possibility of the occurrence of the traffic accident does not necessarily mean only the possibility that the first vehicle 5 is subject to a traffic accident, but means that the possibility that at least one vehicle existing in the reference link (link 0) .

In step S240, the traffic accident probability analysis server 1 may provide the first vehicle 5 with information about the possibility of a traffic accident occurring ahead of the first vehicle 5 passing through it.

FIG. 7 is a table showing an example of data prepared for calculating an equation about the possibility of a traffic accident at a specific time in the link (link-1) 9 in FIG.

In the table of Fig. 7, the reference link may be defined as being a link (link-1) (9). At this time, using the data included in the table of FIG. 7, it is possible to complete the mathematical expression indicating the probability of occurrence of a traffic accident by time in the reference link (link-1) 9.

Since the data included in the tables shown in FIG. 2 and FIG. 7 are different from each other, the mathematical expression indicating the probability of occurrence of a traffic accident by time in the reference link (link 0) It may be different from the mathematical expression indicating the possibility of an accident.

For some road sections, information on whether or not a traffic accident occurred may not be obtained. As a result, it may not be possible to generate an optimal traffic accident occurrence prediction equation for the part of the road section using the algorithm according to the embodiment of the present invention described with reference to FIG. In this case, it is possible to select another road section having a gradient condition similar to the above-mentioned road section. If the above equation can be established for the other road section, the determined equation may be applied to the certain road section.

The above equation shows an example of a prediction model for calculating the probability of a traffic accident in a specific reference link in a future specific time zone. The predictive model may be provided as a neural network model such as a BPN (Back Propagation Network) or a Deep Learning model. And thus is not limited by the specific example of the prediction model of the present invention. The prediction model may be a learning model that can be learned by learning data. The learning data may consist of information and variables regarding whether or not a traffic accident occurred in the past. The process of deriving the optimal value according to the binomial logit model described above can also be regarded as a kind of learning process. It can be understood that the independent variable and the dependent variable of the equation used in the binomial logit model described above are input and output variables of the predictive model, respectively. The prediction model can be learned by inputting the learning data collected in advance in the input variable and the output variable of the prediction model.

It will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the essential characteristics thereof. The contents of each claim in the claims may be combined with other claims without departing from the scope of the claims.

Claims (11)

A traffic information providing method in which a server provides traffic information to a vehicle,
Receiving information about a current location of the vehicle;
Determining a reference link for which the vehicle is expected to arrive in the future and a time when it is expected to reach the reference link;
Calculating information about a possibility of a traffic accident in the reference link during a future time period including the expected time; And
Providing information on the possibility of the traffic accident to the vehicle
/ RTI >
How to provide traffic information. The method according to claim 1,
Wherein the calculating step comprises:
Preparing a predictive model having a possibility of a traffic accident occurring by time in the reference link as a dependent variable and having one or more variables as independent variables;
Obtaining a value of the one or more variables in the reference link predicted for the future time period; And
Calculating a value relating to the probability of occurrence of a traffic accident in the reference link in the future time period by substituting the value of the obtained one or more variables into the prediction model;
/ RTI >
How to provide traffic information. The traffic information providing method according to claim 2, wherein the one or more variables are values relating to at least one of a traffic volume, a speed, a linearity, a gradient, a number of lanes, a speed limit, an average annual traffic volume, . 3. The method of claim 2, wherein the prediction model is a binomial logit model in which the dependent variable is determined by a linear equation of the independent variables. 3. The method of claim 2,
The prediction model may include:
And a plurality of links constituted by the reference link, one or more upstream links positioned upstream in reference to the reference link, and one or more downstream links located downstream in reference to the reference link, And the value of 'one or more variables' is used in the past, 'whether a traffic accident occurred in each link'
The 'traffic accident occurrence in each link' and the 'one or more variables' are obtained for a plurality of times,
How to provide traffic information. A method for estimating the likelihood of occurrence of a traffic accident in a specific time interval on a reference link of a road,
The road including a plurality of links including one or more upstream links located upstream in reference to the reference link and one or more downstream links located downstream in reference to the reference link, Preparing data defined by dividing the data; And
Preparing a predictive model having one or more variables related to each link as input variables and having the possibility of occurrence of the traffic accident in the reference link as an output variable; And
Learning the predictive model using 'the occurrence of a traffic accident in each link' and the 'one or more variables' acquired for each of the plurality of links in the past;
/ RTI >
A method for predicting the probability of a traffic accident. The method according to claim 6,
By assigning to the input variable of the learned predictive model a value that is predicted to have the one or more variables during a future time period with respect to the reference link, Further comprising the step of:
A method for predicting the probability of a traffic accident. A road is divided into a plurality of links including a reference link, one or more upstream links located upstream in the direction of the reference link, and one or more downstream links located downstream of the reference link An apparatus for calculating a probability of occurrence of a traffic accident in a specific time zone on the reference link,
A value of at least one of a traffic volume, a speed, a linearity, a gradient, a number of lanes, a speed limit, an average annual traffic volume, and weather conditions for a plurality of links is obtained as a variable, A data acquisition unit for acquiring the occurrence of a traffic accident; And
Calculating section;
/ RTI >
The calculation unit may calculate,
Preparing a predictive model having a variable in the plurality of links as an input variable and having the possibility of occurrence of the traffic accident in the reference link as an output variable; And
Learning the predictive model using 'the occurrence of a traffic accident in each link' and the 'one or more variables' acquired for each of the plurality of links in the past;
Lt; / RTI >
A device for calculating the likelihood of a traffic accident. 9. The method according to claim 8, wherein the calculation unit assigns, to the input variable of the learned prediction model, a value predicted to have the one or more variables for a future time period with respect to the reference link, And outputting the possibility of occurrence of the traffic accident on the reference link during a predetermined period of time. The method according to claim 8, wherein the data obtaining unit obtains a value relating to at least one of the traffic volume, the speed, the linearity of the road, the gradient, the number of lanes, the speed limit, Through the network from the device of the traffic accident occurrence probability calculating unit. The traffic accident occurrence probability calculation device according to claim 9, further comprising an information providing unit configured to provide the output possibility of the traffic accident occurrence to a vehicle expected to pass through the reference link during the future time period, .
KR1020150172245A 2015-12-04 2015-12-04 Method for predicting possibility of a traffic accident occurrence on road and device for the same KR20170065898A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
KR1020150172245A KR20170065898A (en) 2015-12-04 2015-12-04 Method for predicting possibility of a traffic accident occurrence on road and device for the same

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
KR1020150172245A KR20170065898A (en) 2015-12-04 2015-12-04 Method for predicting possibility of a traffic accident occurrence on road and device for the same

Publications (1)

Publication Number Publication Date
KR20170065898A true KR20170065898A (en) 2017-06-14

Family

ID=59218138

Family Applications (1)

Application Number Title Priority Date Filing Date
KR1020150172245A KR20170065898A (en) 2015-12-04 2015-12-04 Method for predicting possibility of a traffic accident occurrence on road and device for the same

Country Status (1)

Country Link
KR (1) KR20170065898A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190048823A (en) * 2017-10-31 2019-05-09 주식회사 건영이엔씨 System and method for creating road risk index using deep learning
KR20200013274A (en) * 2018-07-24 2020-02-07 주식회사 건영이엔씨 Method for evaluating road safety and apparatus for executing the method
KR20200099966A (en) 2019-02-14 2020-08-25 고려대학교 산학협력단 Method and apparatus for learning based on data including nominal data
CN111859291A (en) * 2020-06-23 2020-10-30 北京百度网讯科技有限公司 Traffic accident recognition method, device, equipment and computer storage medium
CN112233428A (en) * 2020-10-10 2021-01-15 腾讯科技（深圳）有限公司 Traffic flow prediction method, traffic flow prediction device, storage medium and equipment
CN115565373A (en) * 2022-09-22 2023-01-03 中南大学 Real-time risk prediction method, device, equipment and medium for highway tunnel accident

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20190048823A (en) * 2017-10-31 2019-05-09 주식회사 건영이엔씨 System and method for creating road risk index using deep learning
KR20200013274A (en) * 2018-07-24 2020-02-07 주식회사 건영이엔씨 Method for evaluating road safety and apparatus for executing the method
KR20200099966A (en) 2019-02-14 2020-08-25 고려대학교 산학협력단 Method and apparatus for learning based on data including nominal data
CN111859291A (en) * 2020-06-23 2020-10-30 北京百度网讯科技有限公司 Traffic accident recognition method, device, equipment and computer storage medium
US11328600B2 (en) 2020-06-23 2022-05-10 Beijing Baidu Netcom Science And Technology Co., Ltd. Method and apparatus for identifying traffic accident, device and computer storage medium
CN112233428A (en) * 2020-10-10 2021-01-15 腾讯科技（深圳）有限公司 Traffic flow prediction method, traffic flow prediction device, storage medium and equipment
CN112233428B (en) * 2020-10-10 2023-09-22 腾讯科技（深圳）有限公司 Traffic flow prediction method, device, storage medium and equipment
CN115565373A (en) * 2022-09-22 2023-01-03 中南大学 Real-time risk prediction method, device, equipment and medium for highway tunnel accident
CN115565373B (en) * 2022-09-22 2024-04-05 中南大学 Expressway tunnel accident real-time risk prediction method, device, equipment and medium

Similar Documents

Publication Publication Date Title
KR20170065898A (en) Method for predicting possibility of a traffic accident occurrence on road and device for the same
CN107945507B (en) Travel time prediction method and device
CN109670277B (en) Travel time prediction method based on multi-mode data fusion and multi-model integration
Anand et al. Data fusion-based traffic density estimation and prediction
Kumar et al. Short-term traffic flow prediction using seasonal ARIMA model with limited input data
CN107844848B (en) Regional pedestrian flow prediction method and system
US11222532B2 (en) Traffic control support system, traffic control support method, and program recording medium
KR20150128712A (en) Lane-level vehicle navigation for vehicle routing and traffic management
Loulizi et al. Steady‐State Car‐Following Time Gaps: An Empirical Study Using Naturalistic Driving Data
CN104899663A (en) Data prediction method and apparatus
CN102346964A (en) Real-time jam prediction and intelligent management system for road traffic network area
Aron et al. Traffic indicators, accidents and rain: some relationships calibrated on a French urban motorway network
Bharadwaj et al. Deriving capacity and level-of-service thresholds for intercity expressways in India
Schnitzler et al. Combining a Gauss-Markov model and Gaussian process for traffic prediction in Dublin city center.
CN116431923A (en) Traffic travel prediction method, equipment and medium for urban road
CN111862583B (en) Traffic flow prediction method and device
CN104169986A (en) Method for model construction for a travel-time database
Pandey et al. Assessment of Level of Service on urban roads: a revisit to past studies.
JP6885063B2 (en) Information processing equipment, information processing systems, and programs
CN111582527A (en) Travel time estimation method and device, electronic equipment and storage medium
Anagnostopoulos et al. Predicting Roundabout Lane Capacity using Artificial Neural Networks.
US20230349706A1 (en) Computational model for creating personalized routes based at least in part upon predicted total cost of claim frequency or severity
Axer et al. Signal timing estimation based on low frequency floating car data
JP6628700B2 (en) Weather information forecasting device and power demand forecasting device
Louah et al. Traffic operations at an entrance ramp of a suburban freeway first results