KR20210096463A - Appartus for providing traffic information, method thereof and storage media storing a program for providing traffic information - Google Patents

Abstract

Embodiments relate to a traffic information providing device, to a traffic information providing method, and to a storage medium storing a program for providing traffic information. In one embodiment, the provided traffic information providing method includes the steps of: receiving and processing traffic data related to real-time traffic conditions; classifying the processed traffic data according to traffic conditions; searching for the classified traffic data from traffic information corresponding to a plurality of traffic conditions, and obtaining traffic signal control information corresponding to the searched traffic data; and providing the obtained traffic signal control information.

Description

A device for providing traffic information, a method for providing traffic information, and a storage medium for storing a program for providing traffic information

The following disclosure relates to an apparatus for providing traffic information, a method for providing traffic information, and a storage medium for storing a program for providing traffic information.

In general, signal control systems that control traffic flow are largely classified into three types.

The free operation system applies one signal system to one intersection, and operates independent signals regardless of changes in surrounding traffic conditions. This system is often used in small intersections where there are not many vehicles.

The coordinated operation system is a system that applies multiple signal indications together at multiple signal intersections, designs a signal section in response to surrounding traffic conditions, and links the signals at the intersection. Therefore, under this system, signals of a certain number of signal intersections are interlocked and controlled as a group.

An adaptive operation scheme is to collect data for a certain period of time and describe a signaling scheme optimized for it. It refers to a system that optimizes signals by installing multiple sensors around a signal intersection and collecting data in real time. Although this system is used limitedly at major intersections in downtown areas, it is not effective in resolving traffic congestion.

In this system, various sensors are used to collect real-time traffic data, but there is a problem in that it requires a lot of money to secure sufficient data for traffic signal optimization.

Since real-time traffic data is indirectly collected data, it contains many outliers, and therefore, when used for real-time control, it is difficult to obtain as large an effect as expected.

In addition, this system has a problem in that it is difficult to respond to various situational changes such as traffic abrupt situations, and as a result, it causes very frequent signal changes and converges to a signal section favorable to a specific direction at a specific intersection.

Currently, all of the above three methods are used to control traffic signals, but a TOD (Time to Day) method, which is a type of a coordinated operation system, is mainly used. This method refers to a method of researching traffic conditions in advance and providing traffic signals over time based on this.

However, although this method can secure reasonable operational efficiency in repetitive daily life, there is a problem in that the efficiency of traffic control decreases as time passes. Also, this method has a problem that it takes a lot of time to optimize the traffic signal again.

A real-time traffic signal control system has been introduced since the 1990s, but it is currently being used to a limited extent.

Since this traffic signal system uses noisy real-time data as a parameter for signal optimization, stable traffic control is impossible, and there are many problems in system operation such as convergence or diverging of the system by setting an objective function unilaterally.

Embodiments are intended to solve such a problem, and an object of the embodiment is to provide a traffic information providing device, a method for providing traffic information, and a method for providing traffic information that can perform optimal traffic control by accurately analyzing the traffic conditions of several intersections. It is to provide a storage medium for storing the program.

An object of the embodiment is to provide a traffic information providing device, a method for providing traffic information, and a storage medium for storing a program for providing traffic information, which can optimally control traffic signals within a short time and efficiently use a traffic signal system.

In one embodiment, the method includes: receiving and processing traffic data related to real-time traffic conditions; classifying the processed traffic data according to traffic conditions; searching for the classified traffic data from traffic information corresponding to a plurality of traffic conditions, and obtaining traffic signal control information corresponding to the searched traffic data; and providing the obtained traffic signal control information.

The classifying the processed traffic data according to traffic conditions may include classifying the processed traffic data into traffic data of a first traffic condition using a deep learning method according to traffic conditions.

The deep learning method may be a Convolutional Neural Network (CNN) algorithm.

When the classified traffic data of the first traffic condition is not searched, the traffic information may be updated by storing the traffic data of the first traffic condition as new traffic information of the traffic condition.

The traffic signal control information may include traffic signal control strategy information corresponding to traffic conditions according to the traffic information.

The traffic data related to the real-time traffic situation may include real-time vehicle speed data of a specific road section.

Another embodiment includes a preprocessor for receiving and processing traffic data related to real-time traffic conditions; a situation classification unit for classifying the processed traffic data according to traffic conditions; an information acquisition unit that searches for the classified traffic data from traffic information corresponding to a plurality of traffic conditions and obtains traffic signal control information corresponding to the searched traffic data; and a signal control unit providing the obtained traffic signal control information.

The situation classifying unit may classify the processed traffic data into traffic data of the first traffic situation by using a deep learning method according to the traffic situation.

When the classified traffic data of the first traffic situation is not searched, the situation classifying unit may update pre-stored information using the traffic data of the first traffic situation as traffic information of the new traffic situation.

Another embodiment includes receiving and processing traffic data related to real-time traffic conditions; classifying the processed traffic data according to traffic conditions; searching for the classified traffic data from traffic information corresponding to a plurality of traffic conditions, and obtaining traffic signal control information corresponding to the searched traffic data; and a storage medium storing a program for providing traffic information, providing the obtained traffic signal control information.

According to the following exemplary embodiment, it is possible to perform optimal traffic control by accurately analyzing the traffic conditions of several intersections.

According to the following embodiments, it is possible to optimally control a traffic signal within a short time and efficiently use a traffic signal system.

1 is a view showing an embodiment of a method for providing traffic information according to the present invention;
2 is a view showing an embodiment of an apparatus for providing traffic information according to the present invention;
3 is a view showing an example of controlling a traffic signal according to an embodiment of the present invention;
4 is a diagram illustrating an example of a situation classification unit according to an embodiment;
5 is a diagram illustrating an example of generating a polygon image from traffic data of an intersection

Detailed embodiments are disclosed below with reference to the accompanying drawings.

1 is a view showing an embodiment of a method for providing traffic information according to the present invention.

Receives traffic data related to real-time traffic conditions, and performs processing necessary for subsequent procedures, such as pre-processing of the received traffic data (S100).

The received traffic data includes traffic data related to traffic congestion, such as section travel speed. The received traffic data can obtain information such as section passage speed from devices installed around the road, such as Road Side Equipment (RSE).

Such devices include various types of devices installed on the road for exchanging traffic information with terminals of a moving vehicle.

Receives traffic data including the speed of the vehicle on the road section, and performs pre-processing on the received traffic data for the following processing. For example, the received traffic data may be processed so that it can be used in the following process and the format of the data may be changed. The received traffic data may then be processed for appropriate processing.

The processed traffic data may be classified according to traffic conditions (S200).

For example, the processed traffic data may be classified as traffic data according to a traffic situation of a similar pattern among previously stored traffic conditions. For example, traffic data having a pattern most similar to the processed traffic data is searched for from the database. The processed traffic data may be classified into traffic data of the searched pattern.

The classified traffic data is searched for from traffic information corresponding to a plurality of traffic conditions, and traffic signal control information corresponding to the searched traffic data is obtained (S300).

A traffic situation corresponding to the classified traffic data may be found among a plurality of traffic situations. The database may store an optimal traffic signal control method corresponding to the traffic situation.

Accordingly, it is possible to obtain an optimal traffic signal control method for a traffic situation corresponding to the classified traffic data from the database.

It is possible to control the traffic signal by providing the obtained traffic signal control information (S400). By providing the traffic signal control information obtained from the database, it is possible to provide a traffic signal control method according to the traffic situation.

2 is a diagram illustrating an embodiment of an apparatus for providing traffic information according to the present invention.

An embodiment of the apparatus for providing traffic information will be described with reference to the disclosed drawings.

An embodiment of the apparatus for providing traffic information may include a preprocessor 100 , a situation classification unit 200 , an information acquisition unit 300 , and a signal control unit 400 .

The pre-processing unit 100 receives traffic data on traffic conditions and performs a pre-processing process necessary for traffic condition control on the received traffic data. The received traffic data includes traffic data related to traffic congestion, such as vehicle speed on each road. The roadside base station on the road may collect data on various road conditions, and the pre-processing unit 100 performs pre-processing on the traffic data obtained from such an on-road meter.

In this figure, RSE indicates a device for obtaining information on the road, and the information obtained on the road may be transmitted to a network and input to the preprocessor 100 .

The situation classifying unit 200 may classify the traffic data according to a pattern of the traffic data pre-processed by the pre-processing unit 100 .

The situation classifying unit 200 may classify traffic data according to a pattern stored in a database or classify a pattern of traffic data using a deep learning algorithm.

The situation classification unit 200 provides the classified traffic data, for example, may output a code corresponding to the classified traffic data.

A detailed embodiment of the situation classification unit 200 will be described below.

The information acquisition unit 300 may receive traffic data classified according to a pattern and acquire traffic control information corresponding to a similar pattern.

The information acquisition unit 300 stores traffic control information according to congestion or traffic conditions of target roads. The information acquisition unit 300 may store traffic control information corresponding to various traffic conditions.

The information acquisition unit 300 may store optimal signal systems for various traffic conditions, and the various signal systems may be stored in the form of codes output by the situation classification unit 300 .

The information acquisition unit 300 acquires traffic control information according to traffic conditions classified among the stored traffic control information.

The signal control unit 400 may provide the traffic control information obtained by the information acquisition unit 300 so that various traffic lights are linked or independently controlled according to a traffic pattern.

3 is a diagram illustrating an example of controlling a traffic signal according to an embodiment of the present invention. The traffic signal control information and method provided with reference to the disclosed drawings will be described as follows.

In this embodiment, some areas of Daejeon are displayed on the map to show an example of controlling traffic signals on an actual road. The lower part of the road represents the south, the upper part represents the north, and the number above the road represents the intersection.

In this drawing, on the map, number 1 is Gyeongseong Keunmaeul Intersection, 2 is Keunmaeul Intersection, 3 is Eunhasu Intersection, 4 is Blue Bird Intersection, 5 is Bangjuk Intersection, 6 is Government Complex Station Intersection, 7 is Prehistoric Relics Intersection, and 8 is Mannyeon. Three-way intersection, 9 illustrates the Mannyeon intersection, and 11 illustrates the Daedeok Bridge intersection.

The table next to the map is a diagram illustrating the signal control method of each intersection.

The number # in the table indicates the crossroads corresponding to the numbers on the map.

The order of 1, 2, 3, and 4 indicated at the top of the table indicates the order in which the traffic lights of the corresponding intersection operate. That is, it indicates a case in which the signal of the traffic light is changed while circulating in the order of 1 to 4, and it means that the traffic light at the crossroad allows the vehicle or pedestrian passage in the order of 1, 2, 3, and 4.

The arrows according to each signal sequence (number) indicate the direction in which vehicles on the road (solid line) or pedestrians on the crosswalk (dashed line) are permitted according to the green signal of the traffic light, respectively.

“Interlocking” in the left column of the table means that the traffic lights at each intersection operate in conjunction with each other.

The indication of the 1st/2nd number -> 3rd number in the left column inside the table indicates the standard of time to change the traffic light.

For example, the first number indicates the start time when the green traffic light in a specific direction of the crossroad is turned on in seconds, and the second number indicates the internal reference time at which the corresponding traffic light operates in seconds. indicates

The third number indicates the changed time when the start time corresponding to the first number is changed according to the embodiment.

The lower part of each table shows the traffic light control time according to the existing method and the control time of the corresponding traffic light optimized according to the embodiment.

For example, the signal control corresponding to the Gyeongseong Keunmaeul intersection is indicated in the table marked #1.

The Gyeongseong Keunmaeul intersection changes as the traffic lights cycle in the order of 1, 2, 3, and 4 indicated at the top of Table #1.

According to the existing method, 41/160 of the corresponding signal starts at the reference time 160 and 41 seconds.

However, according to the described embodiment, it indicates that the optimal signal start time starts at 106 seconds at the reference time 160 .

For example, in the case of the crossroads in Table #1, the first (1) traffic signal is a green signal that allows vehicles to pass simultaneously from north to south and east (solid line).

The solid line at the bottom of the cell where the first (1) traffic signal is displayed indicates that the traffic light is controlled to allow the vehicle to pass in the direction or the direction in which the vehicle is allowed to pass.

According to the conventional method, the first traffic signal lasts from 24 to 28 seconds (indicated by 28/24), but according to the embodiment, the optimized signal of this signal lasts for 18 seconds.

The second (2) traffic signal is a green signal (indicated by a solid line) to allow vehicles to pass in both directions, north and south. At the same time, green signals for pedestrian crossings parallel to vehicles are also permitted (shown by dashed lines) to allow pedestrian crossings to the north and south.

The second traffic signal described lasts for 82 seconds at reference time 76 (82/76), but according to an embodiment, it is an optimized signal duration to last for 70 seconds.

The third (3) traffic signal is a signal allowing left turn signals for vehicles from west to north (solid line), and a green signal for crosswalks west and east on roads not permitted for vehicles (dotted line).

The third traffic signal described lasts for 38 seconds at reference time 38 (38/38), but according to an embodiment, it is an optimal duration to last for 37 seconds.

The fourth (4) traffic signal, as a left turn signal for vehicles from east to south, lasted 22 seconds at 22 standard time. However, according to an embodiment, the optimization time of the fourth traffic signal is to last for 15 seconds.

Similarly, the signal control corresponding to the big village intersection is shown in the table of #2.

The signal at this crossroads previously started the first signal control at 66 seconds of the reference time 3 (66/3). According to the embodiment, it indicates that the signal control is optimal to start at 111 seconds.

The first control signal at this crossroads will allow vehicles from north to south and east. In addition, green signals are allowed for crosswalks in the north-south direction on roads that are not related to vehicle traffic. The first control signal lasted 31 seconds out of the reference time 36, the optimum duration of this control signal according to the embodiment is 28 seconds.

The second control signal is a signal that permits vehicle traffic and human foot traffic to the north and south. This signal lasted for 42 seconds at reference time 31, but according to an embodiment it is optimally for this signal to last for 28 seconds.

The third control signal at this crossroads is a signal that permits the passage of vehicles from the south to the north and west at the same time, and allows pedestrian crossings in the north-south direction at a crosswalk not related to vehicle traffic. This signal lasts for 31 seconds out of 28 of the reference time, but according to an embodiment, for 21 seconds, the optimization allowable time.

The fourth control signal is a signal to allow vehicles to pass from west to east and north and to use pedestrian crossings in the east-west direction on the opposite road where vehicles do not pass. This signal lasted for 32 seconds out of the reference time 31, but the duration of the optimal control signal according to the embodiment is 30 seconds.

The fifth control signal is a signal to allow vehicles to pass from east to west and south and to use pedestrian crossings in the east-west direction. This signal lasted for 34 seconds out of the reference time 34, but the optimal control signal according to the embodiment is one that lasts for 33 seconds.

Similarly as described above for traffic lights at intersections with other numbers, the signal system may be changed according to the optimal start time of the signal system and the optimal time allowed for road passage in each direction.

As described above, the embodiment may perform optimal signal control according to the classification of traffic conditions. According to an embodiment, it is possible to provide an optimal start time for starting a signal system of a traffic light and an optimal time for allowing signals in each direction at an intersection.

Accordingly, each traffic light can efficiently control the traffic situation by changing the start time of the signal system and the permitted time for vehicles on each road.

4 is a diagram illustrating an example of a situation classification unit according to an embodiment.

An example of the context classifier may include an image generator 210 and a deep learning processor 220 .

The image generator 210 receives the pre-processed traffic data and generates a polygon image corresponding to the intersection.

The polygon image generated based on the traffic data may include an intersection and have vertices in each road direction.

As illustrated in this figure, a polygon image is made to correspond to each intersection, and the image generator 210 generates polygon images corresponding to several intersections.

Generation of a polygon image corresponding to an intersection will be described later with reference to the drawings below.

The deep learning processing unit 220 may receive the polygon images generated by the image generation unit 210 as input, perform a deep learning algorithm, and accurately determine the congestion situation of the corresponding intersections based on the input polygon images.

The deep learning processing unit 220 determines and outputs the congestion situation corresponding to a plurality of intersections according to the result of performing the deep learning algorithm. The deep learning processing unit 220 may determine the congestion situation of a plurality of intersections and intuitively recognize the traffic situation of the road.

The deep learning processing unit 220 performs a deep learning algorithm using the generated polygonal image as input data. The deep learning algorithm may use a Convolutional Neural Network (CNN) algorithm, etc., and may modify the CNN algorithm or use any algorithm used in the deep learning algorithm.

The deep learning processing unit 220 may receive a polygonal image, and accurately determine the current traffic jam situation according to the received polygonal image.

The deep learning processing unit 220 may accurately determine not only the traffic congestion situation for a specific intersection, but also the congestion situation of several intersections that are interlocked and controlled.

5 illustrates an example of generating a polygon image from traffic data of an intersection. An example in which the image generator 210 generates a polygon image from traffic data of an intersection will be described with reference to this drawing.

In this figure, (a) shows an example of the principle of generating a polygon image using the degree of congestion among the traffic data on the intersection 10 of the road and the roads passing the intersection.

Line segments of east, west, north and south (represented by E, W, S, and N, respectively) passing through the intersection 10 correspond to roads leading to the intersection, respectively. This example exemplifies an intersection in which the directions of roads passing through the intersection 10 are east, west, south, and north for convenience of description.

The polygon image allows vertices to be created in the direction of the roads. Therefore, this polygon image has vertices in the east, west, south, and north directions.

The polygon image may have a maximum size when the degree of congestion of each road reaches a maximum (maximum traffic congestion), and may have a minimum size when the degree of congestion on each road is all minimum (minimum traffic congestion).

In other words, the polygonal image may be constructed such that the distances from the center of the polygonal image to the vertices are inversely proportional to vehicle speeds on the roads, respectively.

In this figure, (b) represents that the position of the vertex of the polygonal image changes according to the degree of congestion of the road in each direction from the intersection point.

For example, when the traffic congestion of the intersection and the road in the east direction is maximum, the vertex corresponding to the east direction is located farthest from the center of the polygon image.

For example, if the traffic jam at the intersection and the road in the south direction is congested, the vertex corresponding to the south direction is located between the maximum distance and the minimum distance from the center of the polygon image according to the degree of congestion.

The position of the vertex may be positioned in proportion to the degree of congestion on each road.

That is, the distance from the center of the polygon to the first vertex among the vertices may be proportional to the degree of traffic congestion of the first road corresponding to the center and the first vertex.

In the polygonal image, when the degree of traffic congestion on the first road among the roads is the maximum, the distance from the center of the polygonal image to the first vertex corresponding to the first road may be maximized.

In the polygonal image, when the degree of traffic congestion on the second road is the minimum, the distance from the center of the polygonal image to the second vertex corresponding to the second road may be minimized.

The construction method of the polygon image in the drawing is an example.

Polygon images can be created differently according to the intention of the operator. For example, when the traffic congestion on the road in each direction is maximum, a polygon image having a minimum size may be generated, and when the traffic congestion on the road in each direction is minimum, a polygon image having the maximum size may be generated.

In addition, the center of the polygon image does not necessarily have to be an intersection point, and if the polygon image includes the intersection point according to the shape and configuration of the intersection, an embodiment of the same concept can be configured sufficiently.

Therefore, according to the embodiment, it is possible to accurately analyze the traffic conditions of several intersections to perform optimal traffic control. In addition, it is possible to control traffic signals optimally in a short time and use the traffic signal system efficiently.

100: preprocessor
200: situation classification unit
300: Information Acquisition Department
400: signal control unit

Claims (13)

receiving and processing traffic data related to real-time traffic conditions;
classifying the processed traffic data according to traffic conditions;
searching for the classified traffic data from traffic information corresponding to a plurality of traffic conditions, and obtaining traffic signal control information corresponding to the searched traffic data; and
and providing the obtained traffic signal control information. The method of claim 1,
The step of classifying the processed traffic data according to traffic conditions is,
A traffic information providing method for classifying the processed traffic data into traffic data of a first traffic situation using a deep learning method according to traffic conditions. 3. The method of claim 2,
The deep learning method is a method of providing traffic information that is a Convolutional Neural Network (CNN) algorithm. 3. The method of claim 2,
When the traffic data of the classified first traffic condition is not searched,
A method of providing traffic information, storing the traffic data of the first traffic situation as traffic information of a new traffic situation and updating the traffic information. The method of claim 1,
The traffic signal control information,
A method of providing traffic information including traffic signal control strategy information corresponding to traffic conditions according to the traffic information. The method of claim 1,
Traffic data related to the real-time traffic situation,
A method of providing traffic information including vehicle speed data of a specific road section in real time. a preprocessor for receiving and processing traffic data related to real-time traffic conditions;
a situation classification unit for classifying the processed traffic data according to traffic conditions;
an information acquisition unit that searches for the classified traffic data from traffic information corresponding to a plurality of traffic conditions and obtains traffic signal control information corresponding to the searched traffic data; and
A traffic information providing device comprising a; a signal control unit for providing the obtained traffic signal control information. 8. The method of claim 7,
The situation classification unit,
A traffic information providing device for classifying the processed traffic data into traffic data of a first traffic situation by using a deep learning method according to traffic conditions. 9. The method of claim 8,
The deep learning method is a traffic information providing apparatus that is a Convolutional Neural Network (CNN) algorithm. 9. The method of claim 8,
The traffic information providing device is configured to update pre-stored information using the traffic data of the first traffic situation as traffic information of a new traffic situation when the classified traffic data of the first traffic situation is not searched for. 8. The method of claim 7,
The traffic signal control information,
Traffic information providing apparatus including traffic signal control strategy information corresponding to traffic conditions according to the traffic information.
8. The method of claim 7,
Traffic data related to the real-time traffic situation,
A traffic information providing device including vehicle speed data of a specific road section in real time. receiving and processing traffic data related to real-time traffic conditions; classifying the processed traffic data according to traffic conditions; searching for the classified traffic data from traffic information corresponding to a plurality of traffic conditions, and obtaining traffic signal control information corresponding to the searched traffic data; and a storage medium storing a program for providing traffic information, providing the obtained traffic signal control information.

Images