Intersection signal control method and apparatus for carrying out the same.

Abstract

A method for controlling a signal at an intersection according to one embodiment of the present disclosure includes the steps of: acquiring input data through a traffic condition collection device; predicting traffic condition information at a predetermined time point from the input data through a trained traffic condition prediction model - the predicted traffic condition information being related to at least one of a maximum number of waiting vehicles or a passing traffic volume -; calculating an optimal aspect of the target intersection based on the predicted traffic condition information; and controlling a signal at the target intersection based on the calculated optimal aspect.

Description

Technical Field

[0001] The present disclosure relates to a technology for signal control at intersections. Specifically, the present disclosure relates to a technology that utilizes artificial intelligence to predict traffic situation information and calculates an optimal display based on the prediction result. Furthermore, the present disclosure relates to a technology for controlling the signals at intersections based on the calculated optimal display.

Background Art

[0002] As artificial intelligence technology has developed, it has been utilized in various industrial fields. In particular, recently, research has been attracting attention for predicting future traffic information based on traffic information collected using a deep learning model and controlling signals.

[0003] Conventionally, based on the traffic volume information surveyed by an investigator on-site, the investigator directly determines which time periods have a large number of vehicles at each intersection and manually distributes signals to control traffic signals. However, the conventional signal control method has limitations in that it cannot reflect real-time traffic information and cannot eliminate traffic congestion because it controls signal distribution identically until the next survey. Furthermore, the conventional signal control method has a constraint in that it is inefficient and the accuracy cannot be guaranteed because signals are distributed manually by the investigator.

[0004] Therefore, there is a need for the development of a new method for predicting traffic situation information, a method for controlling signals at intersections, and a device for performing the same.

Summary of the Invention

Problems to be Solved by the Invention

[0005] One problem to be solved by the present disclosure is to provide a method for controlling signals at intersections for predicting the future traffic situation at intersections in real time and automatically optimizing the signals at intersections based on the prediction result, and an electronic device for performing the same.

[0006] The problems that this disclosure seeks to solve are not limited to those described above, and any problems not mentioned can be clearly understood by a person with ordinary skill in the art to which this disclosure pertains from this specification and the accompanying drawings. [Means for solving the problem]

[0007] A signal control method for an intersection according to one embodiment of the present disclosure may include the steps of: acquiring input data through a traffic condition collection device; predicting traffic condition information at a predetermined time after a predetermined period of time has elapsed from the input data through a trained traffic condition prediction model - the predicted traffic condition information is related to at least one of the maximum number of waiting vehicles or the volume of passing traffic; calculating the optimal indication for the target intersection based on the predicted traffic condition information; and controlling the signal for the target intersection based on the calculated optimal indication.

[0008] An electronic device according to one embodiment of the present disclosure may include a processor configured to acquire input data through a traffic condition collection device, predict traffic condition information at a predetermined time after a predetermined period of time has elapsed from the input data through a trained traffic condition prediction model, calculate the optimal indication for the target intersection based on the predicted traffic condition information, and control the signals at the intersection based on the calculated optimal indication.

[0009] The means of solving the problems of this disclosure are not limited to those described above, and any solutions not mentioned can be clearly understood by a person with ordinary skill in the art to which this disclosure pertains from this specification and the accompanying drawings. [Effects of the Invention]

[0010] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for performing the same can be provided, which can predict traffic condition information at a predetermined time after the analysis point has elapsed through a trained traffic condition prediction model.

[0011] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for carrying it out can be provided that, by distributing signals while considering the main flow direction of traffic at the intersection, the effect of controlling signals in a way that reduces congestion can be achieved.

[0012] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for carrying it out may be provided that enhances user convenience by allowing the user to visually confirm the simulated traffic situation, which is calculated using a traffic situation prediction model and the optimal indication, through a user interface.

[0013] The effects of this disclosure are not limited to those described above, and any effects not mentioned can be clearly understood by a person with ordinary skill in the art to which this disclosure pertains from this specification and the accompanying drawings. [Brief explanation of the drawing]

[0014] [Figure 1] This is a schematic diagram of an intersection signal control system according to one embodiment of the present disclosure. [Figure 2] This is a drawing illustrating the operation of an electronic device according to one embodiment of the present disclosure. [Figure 3] This is a flowchart illustrating a signal control method for an intersection according to one embodiment of the present disclosure. [Figure 4] This diagram illustrates how traffic condition information is predicted using a trained traffic condition prediction model according to one embodiment of the present disclosure. [Figure 5] This figure shows examples of input and output variables for a trained traffic condition prediction model according to one embodiment of the present disclosure. [Figure 6] This is a diagram illustrating one aspect of training a traffic condition prediction model according to one embodiment of the present disclosure. [Figure 7] This is a flowchart illustrating the steps for calculating the optimal indication of a target intersection according to one embodiment of the present disclosure. [Figure 8]A drawing for explaining an aspect of calculating an optimal display of a target intersection according to an embodiment of the present disclosure. [Figure 9] A drawing for explaining an aspect of a User Interface. [Figure 10] A drawing for explaining an aspect of a User Interface. [Figure 11] A drawing for explaining an aspect of a User Interface. [Figure 12] A drawing for explaining an aspect of a User Interface.

Mode for Carrying Out the Invention

[0015] The above-mentioned objects, features, and advantages of the present disclosure will become more apparent through the following detailed description related to the accompanying drawings. However, the present disclosure can be subjected to various modifications and can have various embodiments. Hereinafter, specific embodiments will be illustrated in the drawings and will be described in detail.

[0016] Throughout the specification, the same reference numerals generally indicate the same components. Also, components within the same scope of thought shown in the drawings of each embodiment that have the same function will be described using the same reference numerals, and duplicate explanations thereof will be omitted.

[0017] When it is determined that a specific description of a known function or configuration related to the present disclosure may unnecessarily obscure the gist of the present disclosure, the detailed description thereof will be omitted. Also, the numbers (for example, the first, the second, etc.) used in the description process of this specification are merely identification symbols for distinguishing one component from other components.

[0018] In addition, the suffixes "module" and "section" for the components used in the following embodiments are given or used interchangeably only for ease of specification writing, and do not have meanings or roles that are distinct from each other per se.

[0019] In the following embodiments, the singular forms include the plural forms as well, unless the context clearly dictates otherwise.

[0020] In the following embodiments, terms such as "include" or "have" mean that the features or components described in the specification exist, and do not preclude the possibility of adding one or more other features or components in advance.

[0021] In the drawings, for convenience of explanation, the size of components may be exaggerated or reduced. For example, the size and thickness of each component shown in the drawings are arbitrarily shown for convenience of explanation, and the present disclosure is not necessarily limited to what is shown.

[0022] When a particular embodiment can be implemented separately, the order of a particular process may be performed differently from the order described. For example, two processes described consecutively may be performed substantially simultaneously, or may proceed in an order opposite to the order described.

[0023] In the following embodiments, when components etc. are assumed to be connected, it includes not only the case where the components are directly connected, but also the case where components are indirectly connected with other components intervening therebetween.

[0024] For example, when components etc. are assumed to be electrically connected in this specification, it includes not only the case where components etc. are directly electrically connected, but also the case where components etc. are indirectly electrically connected with other components intervening therebetween.

[0025] A signal control method for an intersection according to one embodiment of the present disclosure may include the steps of: acquiring input data through a traffic condition collection device; predicting traffic condition information at a predetermined time after a predetermined period of time has elapsed from the input data through a trained traffic condition prediction model - the predicted traffic condition information is related to at least one of the maximum number of waiting vehicles or the volume of passing traffic; calculating the optimal indication for the target intersection based on the predicted traffic condition information; and controlling the signal for the target intersection based on the calculated optimal indication.

[0026] According to one embodiment of the present disclosure, the traffic situation prediction model is trained on a training dataset comprising traffic situation information at a first time point and traffic situation information at a second time point after a predetermined time has elapsed from the first time point, wherein the traffic situation information in the training dataset may include at least one of the following: maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic, as well as time information.

[0027] According to one embodiment of the present disclosure, the traffic situation prediction model is configured to output a predicted value related to the maximum number of waiting vehicles or the volume of passing traffic based on the traffic situation information at a first time point, and the parameters of the traffic situation prediction model may be updated and trained based on the difference between the predicted value and the traffic situation information at a second time point in the training dataset.

[0028] According to one embodiment of the present disclosure, the step of calculating the optimal indication for the target intersection may further include: a step of obtaining the main movement direction information of the target intersection by comparing the predicted maximum number of waiting vehicles in the straight direction of the target intersection with the predicted maximum number of waiting vehicles in the turning direction of the target intersection; a step of calculating the average number of waiting vehicles of the predicted maximum number of waiting vehicles in the straight direction and the predicted maximum number of waiting vehicles in the turning direction; and a step of allocating the indication time allocated to the turning direction to the indication time in the straight direction if the predicted maximum number of waiting vehicles in the straight direction is greater than the calculated average number of waiting vehicles.

[0029] According to one embodiment of the present disclosure, the input data may include at least one of the following: maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic, as well as time information.

[0030] According to one embodiment of the present disclosure, a computer-readable recording medium can be provided which stores a program for executing the signal control method for the intersection.

[0031] An electronic device according to one embodiment of the present disclosure may include a processor configured to acquire input data through a traffic condition collection device, predict traffic condition information at a predetermined time after a predetermined period of time has elapsed from the input data through a trained traffic condition prediction model, calculate the optimal indication for the target intersection based on the predicted traffic condition information, and control the signals at the intersection based on the calculated optimal indication.

[0032] The following description will refer to Figures 1 to 12 and will explain an intersection signal control method according to one embodiment of the present disclosure, an electronic device (or server, hereinafter referred to as the electronic device) for carrying it out, and / or an intersection signal control system.

[0033] Figure 1 is a schematic diagram of an intersection signal control system 10 according to one embodiment of the present disclosure.

[0034] An intersection signal control system 10 according to one embodiment of the present disclosure may include a traffic condition collection device 100, a client terminal 200, a traffic signal controller 300, and / or an electronic device 1000.

[0035] A traffic condition collection device 100 according to one embodiment of the present disclosure may include a device that collects any data related to an intersection, including a camera and / or a sensor. For example, the camera of the traffic condition collection device 100 may be implemented to acquire traffic video of a target intersection and transmit the acquired traffic video to an electronic device 1000 through an optional transmitting / receiving unit. For example, the sensor of the traffic condition collection device 100 may be implemented to acquire sensor signal data for a target intersection and transmit the acquired sensor signal data to an electronic device 1000 through an optional transmitting / receiving unit. For example, the traffic condition collection device 100 may be implemented to calculate at least one of the following at a given time for the intersection: maximum waiting vehicles, vehicle speed, through traffic volume, demand traffic volume, maximum waiting vehicles, and / or remaining waiting vehicles, based on the traffic video data and the sensor signal data, and transmit the calculated data to an electronic device 1000 through an optional transmitting / receiving unit.

[0036] An electronic device 1000 according to one embodiment of the present disclosure can predict the traffic conditions at a target intersection at a specific time after a certain period of time has elapsed since traffic video data and / or signal-sensitive data for the target intersection were acquired. Specifically, the electronic device 1000 may be configured to predict traffic conditions at a target intersection using a traffic condition prediction model that has been trained in the form of a deep learning neural network, and to control the signals at the target intersection by calculating the optimal indication based on the predicted traffic condition information.

[0037] A client terminal 200 according to one embodiment of the present disclosure can receive predicted traffic condition information, calculated optimal signal indication information, and / or signal control information for a target intersection from an electronic device 1000 through an arbitrary transmitting / receiving unit. Furthermore, the client terminal 200 can display the predicted traffic condition information and / or signal control information for a target intersection through an arbitrary output unit (e.g., a display). Furthermore, the client terminal 200 can receive requests to instruct the prediction of traffic condition information and / or requests to calculate the optimal signal indication for a target intersection through an arbitrary input unit (e.g., a touchpad, mouse, keyboard). On the other hand, the electronic device 1000 may be configured to perform operations such as predicting traffic condition information for a target intersection or calculating the optimal signal indication for a target intersection in response to requests from the client terminal 200.

[0038] A traffic signal controller 300 according to one embodiment of the present disclosure can receive signals for traffic signal control at a target intersection from an electronic device 1000 through any transmitting / receiving unit. At this time, the traffic signal controller 300 can perform an operation to control the signals at the target intersection based on the received signals.

[0039] An electronic device 1000 according to one embodiment of the present disclosure may include a transmitting / receiving unit 1100, a memory 1200, and a processor 1300.

[0040] The transmitting / receiving unit 1100 of the electronic device 1000 can communicate with any external device or external server. For example, the electronic device 1000 can acquire traffic video data and / or sensor signal data related to the target intersection from the traffic situation collection device 100 via the transmitting / receiving unit 1100. For example, the electronic device 1000 can acquire traffic video data of the target intersection from the camera of the traffic situation collection device 100 via the transmitting / receiving unit 1100. For example, the electronic device 1000 can acquire sensor signal data related to the target intersection from the sensor signal sensor of the traffic situation collection device 100 via the transmitting / receiving unit 1100. For example, the electronic device 1000 can acquire input data calculated from the traffic video data and / or sensor signal sensor of the traffic situation collection device 100 via the transmitting / receiving unit 1100. For example, the electronic device 1000 can receive, through the transmitting / receiving unit 1100, execution data for properly running a trained traffic situation prediction model, including structural information, hierarchical information, calculation information, and / or parameter information of the trained traffic situation prediction model. For example, the electronic device 1000 can transmit calculated optimal indication information to any external device, including a client terminal 200, or to any external server, through the transmitting / receiving unit 1100. For example, the electronic device 1000 can transmit signals for traffic signal control to any external device, including a traffic signal controller 300, or to any external server, through the transmitting / receiving unit 1100.

[0041] The electronic device 1000 can connect to a network via the transmitting / receiving unit 1100 to send and receive various types of data. The transmitting / receiving unit 1100 can broadly include wired and wireless types. Since wired and wireless types each have their own advantages and disadvantages, the electronic device 1000 may be equipped with both wired and wireless types simultaneously, depending on the circumstances. In the case of the wireless type, communication methods of the WLAN (Wireless Local Area Network) series, such as Wi-Fi, can be mainly used. Alternatively, in the case of the wireless type, cellular communication methods such as LTE and 5G series can be used. However, the wireless communication protocol is not limited to the examples given above, and any appropriate wireless communication method can be used. In the case of the wired type, LAN (Local Area Network) and USB (Universal Serial Bus) communication are typical examples, but other methods are also possible.

[0042] The memory 1200 of the electronic device 1000 can store various types of information. Various types of data can be stored in the memory 1200 temporarily or semi-permanently. Examples of memory 1200 include hard disk drives (HDDs), solid state drives (SSDs), flash memory, read-only memory (ROMs), and random access memory (RAMs). The memory 1200 can be provided in a form that is built into the electronic device 1000 or in a removable form. The memory 1200 can store various types of data necessary for the operation of the electronic device 1000, including operating systems (OS) for driving the electronic device 1000 and programs for operating each component of the electronic device 1000.

[0043] The processor 1300 can control the overall operation of the electronic device 1000. For example, the processor 1300 can control the overall operation of the electronic device 1000, including operations such as acquiring input data (described later), predicting traffic situation information at a predetermined time after a set period of time has elapsed from the input data through a trained traffic situation prediction model, calculating the optimal indication for the target intersection based on the predicted traffic situation information, and / or controlling the signals at the target intersection. Specifically, the processor 1300 can load and execute a program for the overall operation of the electronic device 1000 from the memory 1200. The processor 1300 can be embodied in hardware, software, or a combination thereof as an AP (Application Processor), CPU (Central Processing Unit), MCU (Microcontroller Unit), or similar device. In this case, the hardware may be provided in the form of an electronic circuit that processes electrical signals to perform control functions, and the software may be provided in the form of a program or code that drives the hardware circuit.

[0044] Figure 2 is a diagram illustrating the operation of an electronic device 1000 according to one embodiment of the present disclosure.

[0045] An electronic device 1000 according to one embodiment of the present disclosure can acquire input data calculated from traffic video data captured by the camera of the traffic condition collection device 100 of the target intersection and sensing signal data sensed by the sensing signal sensor of the traffic condition collection device 100, via a transmitting / receiving unit 1100. Specifically, the electronic device 1000 can acquire input data related to at least one of the following for the target intersection, obtained by analyzing the traffic video data and sensing signal data: maximum waiting vehicles per hour, vehicle movement speed, through traffic volume, demand traffic volume, maximum waiting vehicles, and / or remaining waiting vehicles. Here, through traffic volume may mean the number of vehicles that passed during one signal indication. Demand traffic volume may mean the number of vehicles obtained by adding through traffic volume and the number of remaining waiting vehicles. Maximum waiting vehicles may mean the number of vehicles in the lane with the most waiting vehicles before the signal changes from red to green. Remaining waiting vehicles may mean the number of vehicles that remain unable to pass immediately after the signal changes from green to red. On the other hand, "signal indication" can mean the time during which a green signal is displayed, indicating priority for a passable traffic flow or a group of vehicles or pedestrians in a traffic flow that can pass simultaneously. In the above description, the electronic device 1000 has been described as acquiring calculated input data through the transmitting / receiving unit 1100. However, this is merely an example, and the electronic device 1000 may be implemented to analyze traffic video data and sensor signal data using any algorithm and directly calculate the input data.

[0046] An electronic device 1000 according to one embodiment of the present disclosure can acquire execution data of a trained traffic situation prediction model through a transmitting / receiving unit 1100. Here, execution data can include any data necessary to properly execute the trained traffic situation prediction model, including structural information, hierarchical information, computation information, and / or parameter information of the trained traffic situation prediction model.

[0047] The model can perform the operation of predicting traffic condition information at a predetermined time after a set period of time has elapsed from the input data. More specifically, the electronic device 1000 can input input data including at least one of the following: maximum number of waiting vehicles, vehicle movement speed, traffic demand, and through traffic volume, along with time information, into the input layer of the trained traffic condition prediction model. At this time, the trained traffic condition prediction model can predict traffic condition information at a predetermined time after a set of time has elapsed from the point in time corresponding to the input data. At this time, the electronic device 1000 can obtain the predicted traffic condition information through the output layer of the trained traffic condition prediction model.

[0048] On the other hand, a traffic situation prediction model can be trained on a training dataset consisting of traffic situation information at a first time point (e.g., maximum number of waiting vehicles, vehicle speed, traffic demand, and / or through traffic) and traffic situation information at a second time point a predetermined time after the first time point (e.g., maximum number of waiting vehicles, vehicle speed, traffic demand, and / or through traffic). Specifically, the traffic situation prediction model can be configured to output predicted values ​​related to the maximum number of waiting vehicles or through traffic based on the traffic situation information at the first time point, and its parameters can be updated and trained based on the difference between the predicted values ​​and the traffic situation information at the second time point in the training dataset. For example, the traffic situation prediction model can be trained by updating its parameters to output predicted values ​​that approximate the traffic situation information at the second time point, using the second time point's traffic situation information as ground truth. Thus, a trained traffic situation prediction model can perform the task of predicting traffic situation information at a predetermined time after the time point corresponding to the input data, based on the input data.

[0049] The training method and / or inference process for the traffic situation prediction model will be explained in more detail in relation to Figures 4 to 6.

[0050] An electronic device 1000 according to one embodiment of the present disclosure can perform an operation to calculate the optimal indication of a target intersection based on predicted traffic condition information. More specifically, the electronic device 1000 can obtain the main direction of movement information of the target intersection by comparing predicted traffic condition information for a first direction (e.g., straight direction) of the target intersection with predicted traffic condition information for a second direction (e.g., turning direction) of the target intersection. Furthermore, the electronic device 1000 can calculate average traffic condition information of the predicted traffic condition information for the first direction (e.g., straight direction) and the predicted traffic condition information for the second direction. At this time, the electronic device 1000 can distribute the indication time of the target intersection by comparing the predicted traffic condition information for the first direction (e.g., straight direction) with the calculated average traffic condition information. The details of calculating the optimal indication of the target intersection will be described in more detail in relation to Figures 7 and 8.

[0051] An electronic device 1000 according to one embodiment of the present disclosure can perform an operation to control the signals of a target intersection based on a calculated optimal indication. For example, the electronic device 1000 may be embodied to control the signals of a target intersection based on indication times allocated to a first direction (e.g., straight direction) and a second direction (e.g., rotation direction) of the target intersection.

[0052] Furthermore, an electronic device 1000 according to one embodiment of the present disclosure may be configured to transmit signals for traffic signal control based on the optimal indication calculated by a traffic signal controller 300 via a transmitting / receiving unit 1100. The traffic signal controller can receive the signals for traffic signal control and control the signals at the target intersection based on the received signals.

[0053] Furthermore, an electronic device 1000 according to one embodiment of the present disclosure may be configured to transmit arbitrary information related to the traffic condition prediction result, including calculated optimal indication information, to a client terminal 200 via a transmitting / receiving unit 1100. Specifically, the electronic device 1000 may be configured to provide arbitrary information related to the traffic condition prediction result to the user through a user interface. The user interface will be described in more detail in relation to Figures 9 to 12.

[0054] In the following, with reference to Figures 3 to 12, the operation of the electronic device 1000 according to one embodiment of the present disclosure and the signal control method for intersections performed by the electronic device 1000 will be described in more detail. On the other hand, in describing the signal control method for intersections, some embodiments that overlap with the content previously described in relation to Figure 2 may be omitted. However, this is merely for the convenience of explanation and should not be interpreted restrictively.

[0055] Figure 3 is a flowchart showing a signal control method for an intersection according to one embodiment of the present disclosure.

[0056] An intersection signal control method according to one embodiment of the present disclosure may include the steps of: acquiring input data through a traffic condition collection device (S1000); predicting traffic condition information at a predetermined time after a predetermined period of time has elapsed from the input data through a trained traffic condition prediction model (S2000); calculating the optimal indication for the target intersection based on the predicted traffic condition information (S3000); and / or controlling the signals of the target intersection based on the calculated optimal indication (S4000).

[0057] In the step of acquiring input data through the traffic condition collection device (S1000), the electronic device 1000 can acquire input data from the traffic condition collection device 100 through the transmitting / receiving unit 1100 related to at least one of the following: the maximum number of waiting vehicles per hour at the target intersection, vehicle movement speed, through traffic volume, demand traffic volume, maximum number of waiting vehicles, and / or remaining waiting vehicles.

[0058] In the stage (S2000) where the trained traffic situation prediction model predicts traffic situation information at a predetermined time after a set period of time has elapsed from the input data, the electronic device 1000 can acquire execution data of the trained traffic situation prediction model through the transmitting / receiving unit 1100. Here, execution data can include any data necessary to properly execute the trained traffic situation prediction model, including structural information, hierarchical information, calculation information, and / or parameter information of the trained traffic situation prediction model.

[0059] Furthermore, in the stage (S2000) where the trained traffic condition prediction model predicts traffic condition information at a predetermined time after a set period of time has elapsed from the input data, the electronic device 1000 can perform the operation of predicting traffic condition information at a predetermined time after a set period of time has elapsed from the input data using the trained traffic condition prediction model.

[0060] Figure 4 is a diagram illustrating how traffic condition information is predicted using a trained traffic condition prediction model according to one embodiment of the present disclosure. Specifically, Figure 4(a) is a diagram illustrating how traffic condition information predicted through a trained traffic condition prediction model according to one embodiment of the present disclosure is obtained.

[0061] Specifically, the electronic device 1000 can input input data to the input layer of a trained traffic situation prediction model, including at least one of the following: maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic, along with time information. At this time, the trained traffic situation prediction model can calculate traffic situation information related to the maximum number of waiting vehicles (or waiting queue) and / or through traffic at a predetermined time after a time has elapsed from the point in time corresponding to the input data. At this time, the electronic device 1000 can obtain predicted traffic situation information related to the maximum number of waiting vehicles and / or through traffic at a predetermined time after a time has elapsed from the point in time corresponding to the input data through the output layer of the trained traffic situation prediction model.

[0062] Figure 4(b) is a graph comparing traffic information predicted through a trained traffic situation prediction model according to one embodiment of the present disclosure with actual traffic information.

[0063] Referring to Figure 4(b), it can be confirmed that the traffic information predicted through the trained traffic situation prediction model according to one embodiment of the present disclosure (e.g., queue prediction in Figure 4(b)) and the actual traffic information (e.g., actual queue length (meters) in Figure 4(b)) show similar trends. Furthermore, referring to Figure 4(b), it can be confirmed that the through traffic volume predicted through the trained traffic situation prediction model according to one embodiment of the present disclosure (e.g., through traffic volume prediction in Figure 4(b)) and the actual through traffic volume (e.g., actual through traffic volume (number of vehicles) in Figure 4(b)) show similar trends.

[0064] Figure 5 is a diagram illustrating examples of input and output variables of a trained traffic condition prediction model according to one embodiment of the present disclosure.

[0065] On the other hand, the input variables for the input data entered into the trained traffic situation prediction model can be set to at least one of the following: maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic, along with time information.

[0066] As an example, a trained traffic prediction model may be configured to take the maximum number of waiting vehicles, vehicle speed, traffic demand, through traffic, and / or a combination thereof, along with time information (e.g., a first time point), as input variables, and output the maximum number of waiting vehicles at a predetermined time after that time has elapsed (e.g., a second time point), as the output variable.

[0067] However, the input and output variables shown in Figure 5 are merely examples, and the form of the input and output variables can be set to any appropriate variables in order to achieve the objective of more accurately predicting future traffic conditions.

[0068] Figure 6 is a diagram illustrating one aspect of training a traffic condition prediction model according to one embodiment of the present disclosure.

[0069] A traffic condition prediction model according to one embodiment of the present disclosure may be trained on a training dataset containing multiple data (e.g., D1, D2-Dn in Figure 6) consisting of traffic condition information at a first time point and traffic condition information at a second time point after a predetermined time has elapsed from the first time point. Here, the traffic condition information at the first time point in the training dataset may include the maximum number of waiting vehicles at the intersection at the first time point, vehicle speed, traffic demand, through traffic, and / or combinations thereof, corresponding to the input variables of the traffic condition prediction model, as well as time information at the first time point. Furthermore, the traffic condition information at the second time point in the training dataset may include the maximum number of waiting vehicles at the intersection at the second time point in the traffic condition prediction model, vehicle speed, traffic demand, through traffic, and / or combinations thereof, as well as time information at the second time point.

[0070] More specifically, a traffic situation prediction model may be configured to output predicted values ​​related to the maximum number of vehicles waiting or through traffic volume based on traffic situation information at a first time point. In this case, the traffic situation prediction model may be trained by updating its parameters based on the difference between the predicted values ​​and traffic situation information at a second time point in the training dataset. For example, the traffic situation prediction model may be trained by updating its parameters to output predicted values ​​that approximate the actual maximum number of vehicles waiting based on the difference between the predicted values ​​related to the maximum number of vehicles waiting and the actual maximum number of vehicles waiting at a second time point in the training dataset (first ground truth). For example, the traffic situation prediction model may be trained by updating its parameters to output predicted values ​​that approximate the actual through traffic volume based on the difference between the predicted values ​​related to through traffic volume and the actual through traffic volume at a second time point in the training dataset (second ground truth).

[0071] On the other hand, although not shown in Figures 4 to 6, a trained traffic situation prediction model according to one embodiment of the present disclosure may consist of a first model for predicting traffic situation information for the straight-ahead direction at an intersection and a second model for predicting traffic situation information for the turning direction at an intersection.

[0072] As an example, the first model can be trained in a manner similar to that described above, using a training dataset consisting of traffic information for the straight-ahead direction at a first point in time at an intersection and traffic information for the straight-ahead direction at a second point in time, after a predetermined time has elapsed from the first point in time. In this case, the first model, once trained, can perform the task of predicting the maximum number of waiting vehicles and / or through traffic volume in the straight-ahead direction based on the input data for the straight-ahead direction at the target intersection.

[0073] For example, the second model can be trained in a similar manner to the one described above, using a training dataset consisting of traffic information for the direction of rotation at a first point in time (e.g., leftward rotation) and traffic information for the direction of rotation at a second point in time (e.g., leftward rotation) after a predetermined time has elapsed from the first point in time. In this case, the trained second model can perform the task of predicting the maximum number of waiting vehicles and / or through traffic for a given direction of rotation (e.g., leftward rotation) based on input data for the direction of rotation (e.g., leftward rotation) at the target intersection.

[0074] In the step of calculating the optimal indication for the target intersection based on predicted traffic information (S3000), the electronic device 1000 can perform the operation of calculating the optimal indication for the target intersection based on the predicted traffic information throughout the S2000 stage. For example, the electronic device 1000 can perform the operation of allocating the indication time at the target intersection at a first time point based on the predicted maximum number of waiting vehicles (or predicted waiting queue) and / or predicted through traffic volume throughout the S2000 stage, and calculate the optimal indication at a second time point.

[0075] In the following, the step (S3000) for calculating the optimal indication of a target intersection according to one embodiment of the present disclosure will be explained in more detail with reference to Figures 7 and 8. Figure 7 is a flowchart illustrating the step (S3000) for calculating the optimal indication of a target intersection according to one embodiment of the present disclosure. Figure 8 is a diagram illustrating one aspect of calculating the optimal indication of a target intersection according to one embodiment of the present disclosure.

[0076] The step of calculating the optimal indication for a target intersection according to one embodiment of the present disclosure (S3000) may further include the step of acquiring information on the main movement flow direction of the target intersection (S3100), the step of calculating the average number of waiting vehicles based on the predicted maximum number of waiting vehicles in the straight direction and the predicted maximum number of waiting vehicles in the turning direction (S3200), and the step of distributing the indication time allocated to the turning direction to the indication time in the straight direction if the predicted maximum number of waiting vehicles in the straight direction is greater than the calculated average number of waiting vehicles (S3300).

[0077] In the step of acquiring the main traffic flow direction information for the target intersection (S3100), the electronic device 1000 can acquire the main traffic flow direction information for the target intersection by comparing the predicted traffic situation information for the straight-ahead direction of the target intersection acquired through step S2000 with the predicted traffic situation information for the turning direction of the target intersection acquired through step S2000. For example, the electronic device 1000 can compare the predicted maximum number of waiting vehicles for the straight-ahead direction of the target intersection acquired through step S2000 (e.g., 19 vehicles in Figure 8(b)) with the predicted maximum number of waiting vehicles for the turning direction of the target intersection acquired through step S2000 (e.g., 6 vehicles in Figure 8(b)), and based on the comparison result, acquire the direction showing a larger maximum number of waiting vehicles (e.g., the straight-ahead direction in Figure 8) as the main traffic flow direction. On the other hand, Figure 8 describes the acquisition of the main traffic flow direction information based on the maximum number of waiting vehicles. However, this is merely an example, and the electronic device 1000 may be implemented to determine the main flow direction of traffic at the target intersection using any data, including predicted through traffic volume, existing indication time, and / or demand traffic volume, throughout the S2000 stage.

[0078] In the step of calculating the average number of waiting vehicles based on the predicted maximum number of waiting vehicles in the straight direction and the predicted maximum number of waiting vehicles in the turning direction (S3200), the electronic device 1000 may be implemented to calculate the average number of waiting vehicles at the target intersection based on the predicted maximum number of waiting vehicles in the straight direction and the predicted maximum number of waiting vehicles in the turning direction of the target intersection. For example, the electronic device 1000 may be implemented to calculate the average number of waiting vehicles at the target intersection (for example, 12.5 vehicles in Figure 8(b)) based on the predicted maximum number of waiting vehicles in the straight direction of the target intersection (for example, 19 vehicles in Figure 8(b)) and the predicted maximum number of waiting vehicles in the turning direction of the target intersection (for example, 6 vehicles in Figure 8(b)).

[0079] In the step (S3300) where the indication time allocated to the turning direction is distributed to the indication time in the straight direction if the predicted maximum number of waiting vehicles in the straight direction is greater than the calculated average number of waiting vehicles, the electronic device 1000 may be implemented to calculate the optimal indication for the target intersection by distributing the indication time allocated to the turning direction to the indication time in the straight direction if the predicted maximum number of waiting vehicles in the straight direction is greater than the average number of waiting vehicles calculated through step S3200. For example, if the predicted maximum number of waiting vehicles in the straight direction (e.g., 19 vehicles in Figure 8(b)) is greater than the average number of waiting vehicles at the target intersection calculated through step S3200 (e.g., 12.5 vehicles in Figure 8(b)), the electronic device 1000 may be implemented to calculate the optimal indication for the target intersection by distributing a portion of the indication time allocated to the turning direction to the indication time in the straight direction (e.g., distributing 6 seconds of the indication time in the turning direction in Figure 8(b) to the indication time in the straight direction). At this time, the indication time to be distributed (e.g., 6 seconds) may be determined based on the difference (e.g., a difference of 6.5 vehicles) between the maximum number of waiting vehicles predicted through step S2000 (e.g., 19 vehicles in the straight direction or 6 vehicles in the turning direction) and the average maximum number of vehicles at the target intersection calculated through step S3200 (e.g., 12.5 vehicles). For example, the indication time to be distributed may be determined by a value proportional to the difference (e.g., a difference of 6.5 vehicles) between the maximum number of waiting vehicles predicted through step S2000 (e.g., 19 vehicles in the straight direction or 6 vehicles in the turning direction) and the average maximum number of vehicles at the target intersection calculated through step S3200 (e.g., 12.5 vehicles). However, this is merely an example, and it may be implemented so that the indication time to be distributed to the indication time in the straight direction is calculated from the existing indication time in the turning direction using any appropriate method.

[0080] Referring again to Figure 3, an intersection signal control method according to one embodiment of the present disclosure may include a step (S4000) of controlling the signal of a target intersection based on a calculated optimal indication. In the step (S4000) of controlling the signal of a target intersection based on a calculated optimal indication, the electronic device 1000 may be embodied to control the signal of a target intersection based on the optimal indication calculated through step S3000. For example, the electronic device 1000 may control the signal of a target intersection based on the optimal indication calculated through step S3000, with a first indication for the straight-ahead direction (i.e., 94 seconds (existing indication (88 seconds) + proposed indication (6 seconds)) and a second indication for the turning direction (i.e., 29 seconds (existing indication (35 seconds) + proposed indication (-6 seconds))).

[0081] On the other hand, Figures 3 to 8 describe the electronic device 1000 as controlling the signals at the target intersection. However, this is merely for the sake of explanation, and the electronic device 1000 may be configured to transmit the calculated optimal indication to the traffic signal controller 300, which then controls the signals at the target intersection. Alternatively, the electronic device 1000 may be configured to transmit the calculated optimal indication to the client terminal 200, which then controls the signals at the target intersection based on the client's signal control request.

[0082] In the following, a user interface that may be provided to a client terminal 200 according to one embodiment of this disclosure will be described with reference to Figures 9 to 12. Figures 9 to 12 are diagrams illustrating one aspect of the user interface.

[0083] Referring to Figure 9, a user interface according to one embodiment of the present disclosure can obtain inputs through any input unit of the client terminal 200 (e.g., mouse, touchpad, keyboard, etc.) to select a type of traffic situation prediction model (e.g., the STGCN model, GraphWaveNet (GWNET) model, and STGCN-Cov model shown in Figure 9) and input variables for the traffic situation prediction model. Furthermore, the user interface can obtain inputs through any input unit of the client terminal 200 (e.g., mouse, touchpad, keyboard, etc.) to select the time to be predicted (e.g., 5 minutes later, 10 minutes later, 15 minutes later, 20 minutes later, (omitted) 60 minutes later, etc.).

[0084] At this time, the user interface may be provided to output predicted result information to the user through an optional output unit of the client terminal 200 (e.g., a display), based on the selected prediction model, input variables, and the time to be predicted. For example, the user interface may be provided to output prediction results for the prediction target (e.g., vehicle speed, through traffic volume, queue, etc. in Figure 9) to the user through an optional output unit of the client terminal 200. For example, the user interface may be provided to output information to the user about the training data used in the prediction model through an optional output unit of the client terminal 200. For example, the user interface may be provided to output information to the user about metrics indicating the performance of the prediction model (e.g., MAE value, RMSE value in Figure 9) through an optional output unit of the client terminal 200.

[0085] Referring to Figure 10, a user interface according to one embodiment of the present disclosure may be provided to the user by visualizing and outputting predicted result information through a traffic situation prediction model via an arbitrary output unit of the client terminal 200. For example, the user interface may be provided to the user by visualizing the predicted result information through a traffic situation prediction model on a map. More specifically, the user interface may display intersection icons representing intersections (e.g., M1 in Figure 10) on a map and display the degree of congestion at the intersections on the map based on the prediction results (e.g., roads at smooth intersections are displayed in a first hue (e.g., green), roads at congested intersections are displayed in a second hue (e.g., red), or roads at normal intersections are displayed in a third hue (e.g., yellow)) and provide this to the user. For example, the user interface may be provided to output to the user predicted result information through a traffic situation prediction model (e.g., average queue prediction value, average travel speed prediction value in Figure 10) and the prediction accuracy of the predicted result information (e.g., average queue prediction accuracy, average travel speed prediction accuracy in Figure 10).

[0086] Referring to Figure 11, a user interface according to one embodiment of the present disclosure may be provided to the user by outputting a table of predicted results information obtained through a traffic situation prediction model via an arbitrary output unit of the client terminal 200. For example, the user interface may provide the user with a table of the analysis date and time, intersection name, time (e.g., day of the week), direction of entry into the intersection, actual speed, predicted speed, prediction accuracy, actual queue, and / or predicted queue value, etc., obtained through an arbitrary output unit of the client terminal 200.

[0087] Referring to Figure 12, a user interface according to one embodiment of the present disclosure may be provided to the user via an optional output unit of the client terminal 200 to output a first map showing the current traffic conditions and a second map showing the traffic conditions simulated based on the proposed indications (for example, the traffic conditions when the proposed indications are applied 30 minutes or 60 minutes later). At this time, the user interface may be provided to the user via an optional output unit of the client terminal 200 to output the proposed indication values, the traffic volume (or queue) before and after the application of the simulation, and / or information on the effect of intersection improvement.

[0088] On the other hand, the information illustrated in Figures 9 to 12 is merely illustrative, and the user interface can be configured to provide users with any appropriate information in any appropriate format as needed.

[0089] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for performing the same can be provided, which can predict traffic condition information at a predetermined time after the analysis point has elapsed through a trained traffic condition prediction model.

[0090] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for carrying it out can be provided that, by distributing signals while considering the main flow direction of traffic at the intersection, the effect of controlling signals in a direction that reduces congestion can be achieved.

[0091] According to one embodiment of the present disclosure, a signal control method for an intersection and an electronic device for carrying it out may be provided that enhances user convenience by allowing the user to visually confirm the traffic situation, which is created by predicting result information using a traffic situation prediction model and calculating the optimal indication, through a user interface.

[0092] The various operations of the aforementioned electronic device 1000 may be stored in the memory 1200 of the electronic device 1000, and the processor 1300 of the electronic device 1000 may be provided to perform the operations stored in the memory 1200.

[0093] The features, structures, and effects described in the embodiments above are included in at least one embodiment of this disclosure and are not necessarily limited to just one embodiment. Furthermore, the features, structures, and effects exemplified in each embodiment can be combined or modified and implemented in other embodiments by a person with ordinary skill in the art to which the embodiment belongs. Therefore, the content related to such combinations and modifications should be interpreted as being included in the scope of this disclosure.

[0094] Furthermore, while the above description has focused on embodiments, these are merely illustrative examples and do not limit the disclosure. Those with ordinary skill in the art to which this disclosure belongs will understand that various modifications and applications not exemplified above are possible, without departing from the essential characteristics of these embodiments. In other words, each component specifically shown in the embodiments can be modified and implemented. Any differences related to such modifications and applications should be interpreted as being within the scope of this disclosure as defined by the attached claims. [Industrial applicability]

[0095] The aforementioned intersection signal control method and apparatus for carrying it out can be applied to the fields of traffic condition prediction and traffic signal control.

Claims

1. In a method in which an electronic device controls traffic signals at an intersection, The stage of acquiring input data through a traffic condition collection device; When a traffic situation prediction model used to predict traffic situation information, input variables of the input data to be input to the traffic situation prediction model, and the time to be predicted through the traffic situation prediction model are selected on the client terminal, the step of predicting traffic situation information at the selected time is performed based on the selected traffic situation prediction model, the selected input variables, and the selected time; A step of calculating the optimal traffic conditions for the target intersection based on the predicted traffic information; A step of receiving a signal control request from the client terminal, which is provided through the user interface with a calculated optimal indication, a first map displaying the current traffic situation, and a second map displaying the traffic situation at the selected time simulated based on the calculated optimal indication; and The step includes controlling the signal at the target intersection based on the calculated optimal indication as a response to the received signal control request, The input variables include a combination of the maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic volume, as well as time information, and the predicted traffic condition information is related to at least one of the maximum number of waiting vehicles and through traffic volume. The step of calculating the optimal indication for the aforementioned intersection is: A step of calculating the average number of waiting vehicles, which is the average of the predicted maximum number of waiting vehicles in the straight-ahead direction and the predicted maximum number of waiting vehicles in the turning direction of the target intersection; and A signal control method for an intersection, further comprising the step of allocating the indication time allocated to the turning direction to the indication time in the straight direction if the predicted maximum number of waiting vehicles in the straight direction is greater than the calculated average number of waiting vehicles.

2. The aforementioned traffic condition prediction model, It is trained on a training dataset consisting of traffic condition information at a first point in time and traffic condition information at a second point in time, after a predetermined time has elapsed since the first point in time. The traffic condition information in the learning dataset includes at least one of the maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic, as well as time information, according to claim 1, for the signal control method at an intersection.

3. The aforementioned traffic condition prediction model, It is configured to output a predicted value related to the maximum number of waiting vehicles or the volume of passing traffic based on the traffic condition information at the aforementioned first point in time. The traffic signal control method for an intersection according to claim 2, wherein the parameters of the traffic condition prediction model are updated and trained based on the difference between the predicted value and the traffic condition information at the second time point in the training dataset.

4. A computer-readable recording medium having a program stored on it that causes a computer to perform the method described in any one of claims 1 to 3.

5. In an electronic device for controlling traffic signals at an intersection, Input data is acquired through the traffic condition collection device. When a traffic situation prediction model used to predict traffic situation information, input variables of the input data input to the traffic situation prediction model, and the time to be predicted through the traffic situation prediction model are selected on the client terminal, the traffic situation information at the selected time is predicted based on the selected traffic situation prediction model, the selected input variables, and the selected time. Based on the predicted traffic conditions information, the optimal indication for the target intersection is calculated. The calculated optimal indication, a first map displaying the current traffic situation, and a second map displaying the traffic situation at the selected time simulated based on the calculated optimal indication are provided via a user interface to the client terminal upon receiving a signal control request. The processor is configured to control the signals at the target intersection based on the calculated optimal indication as a response to the received signal control request, The input variables include a combination of the maximum number of waiting vehicles, vehicle speed, traffic demand, and through traffic volume, as well as time information, and the predicted traffic condition information is related to at least one of the maximum number of waiting vehicles and through traffic volume. The processor calculates the optimal indication for the target intersection, The average number of waiting vehicles is calculated based on the predicted maximum number of waiting vehicles in the straight-ahead direction and the predicted maximum number of waiting vehicles in the turning direction of the aforementioned intersection. An electronic device configured to allocate the indication time allocated to the turning direction to the indication time in the straight direction when the predicted maximum number of waiting vehicles in the straight direction is greater than the calculated average number of waiting vehicles.

Images