KR102493981B1 - Apparatus and Method for Predicting Traffic Congestion - Google Patents

Abstract

A traffic congestion prediction device and method has an effect of predicting traffic congestion in a small area rather than in an entire city to accurately analyze and prevent causes of congestion. The present invention has the effect of estimating the congestion state of a city through calculation and analysis of the traffic congestion index in a small area and using it as data for planning and configuring road traffic.

Description

Traffic congestion prediction apparatus and method {Apparatus and Method for Predicting Traffic Congestion}

The present invention relates to an apparatus and method for predicting traffic congestion, and more particularly, to an apparatus and method for predicting traffic congestion that can prevent the cause of congestion by predicting traffic congestion in a small area rather than the entire city.

Traffic congestion is becoming a serious problem facing large and growing cities, hindering urban growth, extending commute times and increasing accident frequency.

Traffic congestion has increased dramatically in recent years due to the growing economy, uncontrolled urban migration, desire for private travel, outdated transport infrastructure and inadequate transport management policies.

Traffic congestion is a global phenomenon affecting all large and growing cities worldwide. The main causes of traffic congestion are infrastructure, traffic accidents, bad weather, bottlenecks in road maintenance and construction activities, lack of public transport, lack of traffic jams, signal timing, lack of parking spaces, presence of large vehicles and special events.

In order to effectively improve urban congestion, many approaches have been proposed to quantify a city's Traffic Congestion Index (TCI) and its correlation coefficient.

The calculation and analysis of the traffic congestion index can be used to estimate the condition of a city, plan and organize road traffic for traffic managers, and make rational decisions for travelers.

However, these studies all refer to city-level TCI, which is a normalized value for large cities. Since the TCI of the entire city is an average value over a wide area, there is a problem in that accurate TCI information for small cities cannot be provided.

The accumulation of congestion in these small areas is one of the reasons for the increase in congestion in cities.

In practice, since the normalized city-level TCI for large cities is difficult to reflect the TCI of small areas, the traffic congestion index becomes inaccurate, and thus, there is a problem that it cannot be applied to planning and configuring road traffic.

Korean Registered Patent No. 10-1671245

In order to solve this problem, an object of the present invention is to provide a traffic congestion prediction apparatus and method capable of preventing the cause of congestion by predicting traffic congestion in a small area rather than the entire city.

In addition, an object of the present invention is to provide a traffic congestion prediction apparatus and method for determining the effect of population density on TCI by analyzing the correlation between population density and TCI value.

Traffic congestion prediction device according to the characteristics of the present invention for achieving the above object,

Road traffic data, including map data received from an external server, is captured by dividing a small area rather than the entire city into predetermined sub-areas, and each road in the sub-area is divided based on traffic volume information of the road traffic data. an image processing process for determining a congestion level for and displaying a specific color on the map data according to the determined congestion level; and

Free road length (F _length ), slow road length (S _length ), and jam road length (J _length ) are calculated using the color displayed in each subregion, and the traffic congestion index (Traffic It is characterized in that it includes a control unit that calculates the congestion index (TCI) using Equation 1 below.

[Equation 1]

Here, F _length is the length of the road marked in green in each subregion, S _length is the length of the road marked in yellow in each subregion, J _length is the length of the road marked in red in each subregion, Total length of the road is the length of the entire road.

Traffic congestion prediction method according to the features of the present invention,

capturing, by an image processing process, road traffic data including map data received from an external server by dividing a small area rather than the entire city into predetermined sub-regions;

determining, by the image processing process, a congestion level for each road in the divided lower area based on traffic volume information of the road traffic data, and displaying a specific color on the map map data according to the determined congestion level; ;

calculating, by a control unit, a length of a free road (F _length ), a length of a slow road (S _length ), and a length of a jam road (J _length ) using the color displayed in each lower region;

Calculating a traffic congestion index (TCI) of each sub-region using Equation 1 below; and

The controller calculates a TCI value by Equation 1 as many as the number (N) of images of each subregion captured during a predetermined time interval in the image processing process, and calculates an average TCI value by Equation 2 below. It is characterized in that it includes the step of doing.

[Equation 1]

Here, F _length is the length of the road marked in green in each subregion, S _length is the length of the road marked in yellow in each subregion, J _length is the length of the road marked in red in each subregion, Total length of the road is the length of the entire road.

Traffic congestion prediction device according to the features of the present invention,

Road traffic data, including map data received from an external server, is captured by dividing a small area rather than the entire city into predetermined sub-areas, and each road in the sub-area is divided based on traffic volume information of the road traffic data. an image processing process for determining a congestion level for and displaying a specific color on the map data according to the determined congestion level; and

Free road length (F _length ), slow road length (S _length ), and jam road length (J _length ) are calculated using the color displayed in each subregion, and the traffic congestion index (Traffic A control unit for calculating the congestion index (TCI) using Equation 1 below,

The control unit calculates a TCI value by Equation 1 as many as the number (N) of images of each subregion captured during a predetermined time interval in the image processing process, and calculates an average TCI value by Equation 2 below. Classified into four groups based on the calculated average TCI value: high congestion (TCI > 120), congestion (80 < TCI ≤ 120), normal (40 ≤ TCI < 80), and free (TCI < 40) , In case of high congestion, dark red, in case of congestion, normal red, in case of normal, yellow, and in case of free, green are set.

[Equation 1]

Here, F _length is the length of the road marked in green in each subregion, S _length is the length of the road marked in yellow in each subregion, J _length is the length of the road marked in red in each subregion, Total length of the road is the length of the entire road.

[Equation 2]

Here, N is the sum of the number of subregion images captured during a certain time interval.

According to the configuration described above, the present invention has an effect of predicting traffic congestion in a small area rather than the entire city to accurately analyze and prevent the cause of congestion.

The present invention has the effect of estimating the congestion state of a city through calculation and analysis of the traffic congestion index in a small area and using it as data for planning and organizing road traffic.

1 is a diagram showing the configuration of a traffic congestion prediction system using a regional traffic congestion index according to an embodiment of the present invention.
2 is a block diagram briefly showing the internal configuration of a traffic congestion predicting device according to an embodiment of the present invention.
3 is a flowchart illustrating a method for predicting traffic congestion according to an embodiment of the present invention.
4 is a diagram showing map map data displaying average TCI values during weekdays according to an embodiment of the present invention.
5 is a diagram showing a correlation between population density and TCI according to an embodiment of the present invention.

Throughout the specification, when a certain component is said to "include", it means that it may further include other components without excluding other components unless otherwise stated.

Since the TCI of the entire city is an average value over a large area, accurate TCI information for small cities cannot be provided. The accumulation of congestion in these small towns is one of the reasons for the increase in congestion in cities.

The present invention provides a method for calculating the congestion index of a small area and confirms the effect of population density on the Traffic Congestion Index (TCI).

The calculation and analysis of the traffic congestion index is used to estimate the condition of the city, plan and organize road traffic for traffic managers, and make rational decisions for travelers. The present invention shows the correlation between TCI values and population density.

1 is a diagram showing the configuration of a traffic congestion prediction system using a regional traffic congestion index according to an embodiment of the present invention, and FIG. 2 is a block diagram briefly showing the internal configuration of a traffic congestion prediction device according to an embodiment of the present invention. 3 is a flowchart showing a traffic congestion prediction method according to an embodiment of the present invention, FIG. 4 is a diagram showing map map data displaying average TCI values during weekdays according to an embodiment of the present invention, and FIG. 5 Is a diagram showing the correlation between population density and TCI according to an embodiment of the present invention.

A traffic congestion prediction system 100 using a regional traffic congestion index according to an embodiment of the present invention includes a plurality of traffic congestion prediction devices 110, a road traffic information providing server 130, and a traffic management server 140.

The road traffic information providing server 130 transmits road traffic data to the traffic congestion prediction device 110 through the communication network 120 through wireless communication. Here, the road traffic data may include various information necessary for road traffic, such as road environment information, traffic volume information, traffic situation information, and map data.

Each traffic congestion prediction device 110 includes a traffic data receiver 111, an image processing process 112, a controller 113, a storage unit 114, and a display unit 115.

The traffic data receiving unit 111 receives road traffic data including map data from the external road traffic information providing server 130 every 3 minutes and stores it in the storage unit 114 .

The image processing process 112 captures the road traffic data received from the traffic data receiver 111 by dividing the small area into predetermined lower areas (S100).

Here, the small area includes a small area of the city rather than the entire city.

The image processing process 112 determines a congestion level for each divided sub-area based on the traffic volume information of the road traffic data, displays a specific color on the map data according to the determined congestion level, and stores the information in the storage unit 114. Save (S110).

Here, in terms of color, the congestion level is represented by a jam state in the case of red, a slow state in the case of yellow, and a free state in the case of green.

Determination of the congestion level can be divided into a jam state, a slow state, and a free state for each predetermined range based on traffic volume information.

As shown in FIG. 4 , for example, in the map map data, a photographed image of the Incheon city area is divided into 25 sub-regions.

In each subregion, each road can be marked with a color (red, yellow, green) representing the level of congestion.

For example, the captured image of the Incheon city area is divided into 25 sub-regions in the map data of the specific region, and the names are designated as follows.

As shown in FIG. 4 , the control unit 113 calculates the free road length (F _length ), slow road length (S _length ) and jam road length (J _length ) using the color displayed in each lower region. .

The control unit 113 calculates a traffic congestion index (TCI) of each lower region (specific region) using Equation 1 below (S120).

Here, F _length is the length of the road marked in green in each subregion, S _length is the length of the road marked in yellow in each subregion, J _length is the length of the road marked in red in each subregion, Total length of the road represents the total length of the road.

The value of TCI ranges from 0 (all road networks in free state) to 300 (all road networks in jam state).

The controller 113 calculates the average TCI value during the time interval corresponding to the total number of images (N) by Equation 2 below. The total number of images is the sum of the number of images of the subregion captured during a certain time interval in the image processing process 112 .

여기서, N은 일정한 시간 간격 동안의 캡처된 하부 지역의 이미지 개수의 총합임.

Here, N is the sum of the number of subregion images captured during a certain time interval.

The controller 113 calculates the population density of each subregion by Equation 3 below.

where a1, a2, an are the parts of the administrative region in percent (%), and d1, d2, dn are the population densities of the sub-regions.

The population density of each sub-region is shown in Table 1 below.

The control unit 113 calculates the TCI value of each subregion (Equation 1), and calculates the TCI value of each subregion in the image processing process 112 to calculate the number of images of the subregion captured during a certain time interval. The average TCI value is calculated for each subregion by performing as many times as possible (Equation 2, S130).

The control unit 113 transmits map map data displaying the congestion level and average TCI value of the road 117 in each subregion by time and by date to the traffic management server 140 through the communication network 120 .

The traffic management server 140 receives map data displaying the congestion level and average TCI value of the road 117 in each subregion by time and by day in each region from the plurality of traffic congestion prediction devices 110, and receives the map data. Using the same data, traffic congestion in a small sub-area of each region can be predicted, and based on this, traffic congestion in the entire city can be predicted.

The traffic management server 140 estimates a congestion state in a city through calculation and analysis of a traffic congestion index in a small area, and may use it as data for planning and configuring road traffic.

As another embodiment, each traffic congestion prediction device 110 uses map data indicating the congestion level and average TCI value of the road 117 in each sub-region of the corresponding small-scale sub-area of each sub-region. traffic congestion can be predicted.

Each of the traffic congestion prediction devices 110 estimates a congestion state in a city through calculation and analysis of a traffic congestion index in a small area, and may be used as data for planning and configuring road traffic.

In the final image of the map data output to the display unit 115, a first color indicating a congestion level is displayed for each road 117 in each lower region, and a second color is displayed according to the average TCI value according to a preset congestion degree range. may be set, and the average TCI value may be displayed in the circle 116 in which the set second color is displayed.

The data set used for analysis contains images from October 1 to October 7, 2019, and includes 4 working days, 2 weekend days, and 1 holiday day.

The controller 113 sets different colors according to a preset congestion range based on the calculated average TCI value.

More specifically, the control unit 113 calculates high congestion (TCI > 120), congestion (80 < TCI ≤ 120), normal (40 ≤ TCI < 80), and free (TCI < 40) based on the calculated average TCI value. It is classified into four groups, and high congestion, dark red, congestion, normal red, normal, yellow, and free, green are set.

The controller 113 displays the average TCI value in a specific shape (eg, circle) 116 of the set color and displays it on the upper left of the map data of each subregion (S140).

As shown in FIG. 4, the control unit 113 displays each road 117 in a color (red, yellow, green) representing a congestion level, and adds an average TCI value classified by color to each sub-region. and output to the display unit 115.

In the final image of the map data output to the display unit 115, a first color indicating a congestion level is displayed for each road 117 in each lower region, and a second color is displayed according to the average TCI value according to a preset congestion degree range. may be set, and the average TCI value may be displayed in the circle 116 in which the set second color is displayed.

While the overall average TCI value for the working day is 102.23, the TCI distribution of the sub-region is between 4.61 in R14 and 147.5 in R33, as shown in FIG.

The average TCI value for weekends and holidays was 95.56, but the TCI distribution ranged from 4.11 in R41 to 139.7 in R33 as shown in Table 2 below.

Each subregional identity of a small area (eg, Incheon City) is more meaningful than the TCI of the entire city.

Referring to FIG. 4 , it can be seen that 10 of the 25 sub-areas are always in a congested area on weekdays, and 8 out of 25 sub-areas are always in a congested level during weekends or holidays in Table 2.

Incheon City Hall is located in the R33 sub-region, showing the highest TCI and population density.

5 shows the relationship between the traffic congestion index and population density, and shows a positive correlation, and the correlation is 82.36%.

Subregion R15 serves as an outlier with a population density of 8,774/km ² , and therefore has a high value of TCI on Sunday and Tuesday.

As shown in Fig. 5, since the population density of each subregion is fixed, the TCI value varies according to the day of the week, causing multiple Y-axis values for the same X-axis.

The present invention analyzes the TCI value of small scale, compares it with the average TCI value of the whole city, it is not beneficial to calculate the TCI value of the whole city to reduce congestion, and it is more beneficial to calculate the TCI value for a small area. do.

It can be seen that the congestion of each sub-area correlates 82% with the population density of the area during weekdays or weekends.

TCI for small areas is more informative than whole-city level TCI values, and there is a close relationship between TCI values and population density.

As described above, the embodiments of the present invention are not implemented only through devices and/or methods, and may be implemented through programs for realizing functions corresponding to the configurations of the embodiments of the present invention, recording media on which the programs are recorded, and the like. And, such an implementation can be easily implemented by an expert in the technical field to which the present invention belongs from the description of the above-described embodiment.

Although the embodiments of the present invention have been described in detail above, the scope of the present invention is not limited thereto, and various modifications and improvements made by those skilled in the art using the basic concept of the present invention defined in the following claims are also included in the scope of the present invention. that fall within the scope of the right.

100: traffic congestion prediction system
110: traffic congestion predictor
111: traffic data receiver
112: image processing process
113: control unit
114: storage unit
115: display unit
120: communication network
130: road traffic information providing server
140: traffic management server

Claims (9)

Road traffic data, including map data received from an external server, is captured by dividing a small area rather than the entire city into predetermined sub-areas, and each road in the sub-area is divided based on traffic volume information of the road traffic data. an image processing process for determining a congestion level for and displaying a specific color on the map data according to the determined congestion level; and
Slow road length (S _length ) and jam road length (J _length ) are calculated respectively using the color displayed in each subregion, and the traffic congestion index (TCI) of each subregion is as follows Including a control unit that calculates using Equation 1,
The control unit calculates a TCI value by Equation 1 as many as the number (N) of images of each subregion captured during a predetermined time interval in the image processing process, and calculates an average TCI value by Equation 2 below. do,
The control unit classifies into four groups based on the calculated average TCI value: high congestion (TCI > 120), congestion (80 < TCI ≤ 120), normal (40 ≤ TCI < 80), and free (TCI < 40) In case of high congestion, dark red, in case of congestion, normal red, in case of normal, yellow, and in case of free, set green,
The controller displays a first color indicating a congestion level for each road in each sub-area, sets the average TCI value to a second color according to a preset congestion range, and displays the second color in a circle displayed with the set second color. A traffic congestion prediction device characterized in that the average TCI value is displayed on the map data output to the display unit.
[Equation 1]

Here, S _length is the length of the road marked in yellow in each subregion, J _length is the length of the road marked in red in each subregion, and Total length of the road is the length of the entire road.
[Equation 2]

Here, N is the sum of the number of subregion images captured during a certain time interval. delete delete delete delete delete delete delete delete

Images