KR20220101535A - On-device real-time traffic signal control system based on deep learning - Google Patents

Abstract

A deep learning-based on-device real-time traffic control system is disclosed. A traffic control method performed in an electronic device according to an embodiment comprises the steps of: obtaining road information related to object information from road image data for each intersection through a deep learning-based object detection and tracking model; calculating a signal cycle for the intersection based on the obtained road information related to object information; determining whether there is a communication connection with a server; and transmitting the obtained road information related to object information and the calculated signal cycle to the server when it is determined that communication with the server is connected. A signal controller for each intersection may be controlled based on the road information related to object information and signal cycle information considering each intersection adjusted using the calculated signal cycle transmitted from the server. Accordingly, traffic signals can be controlled and operated more accurately and quickly.

Description

On-device real-time traffic control system based on deep learning {ON-DEVICE REAL-TIME TRAFFIC SIGNAL CONTROL SYSTEM BASED ON DEEP LEARNING}

The description below relates to a technology for controlling traffic signals using deep learning technology.

Traffic signal control system refers to a system that controls signals by analyzing data collected by vehicle detectors installed on roads and setting the most appropriate signal period and display for the actual traffic volume. The domestic signal control system is largely divided into general signal control, electronic signal control, and real-time signal control. Currently, in real-time signal control systems, a loop detector is generally used to determine the amount of traffic. A fatal disadvantage that can occur when using a loop detector to identify traffic is that only the partial characteristics where the loop detector is installed are utilized. This means that depending on the location of the detector, it is impossible to misjudg the road conditions differently or to deal with unexpected situations such as traffic accidents.

In addition to the loop detector, there are magnetic detectors, image detectors, and the like. Problems with image detectors currently used for traffic analysis include performance deviation due to external variables such as weather and low performance compared to other detectors. Recently, the performance of computer vision using deep learning has risen dramatically, and it has consistently high performance in various situations. As a result, the image detector using the deep learning model was able to supplement the shortcomings of the existing image detector. However, unlike previous computer vision models, the deep learning model basically requires a large amount of computation, so it requires a high-performance server. There is a privacy issue.

It is possible to provide a real-time traffic signal control system and method that controls the traffic volume optimized for road conditions in real time by grasping the deep learning model on-device.

A traffic control method performed in an electronic device includes: acquiring road information related to object information from road image data for an intersection through a deep learning-based object detection and tracking model; calculating a signal period for an intersection based on road information related to the obtained object information; determining whether there is a communication connection with the server; and transmitting road information related to the obtained object information and the calculated signal period to a server as it is determined that communication with the server is connected, wherein in the traffic control method, the object received from the server The signal controller of each intersection may be controlled based on information-related road information and signal period information considering each intersection adjusted using the calculated signal period.

The acquiring includes collecting road image data for an intersection photographed from a photographing device installed at each intersection, and inputting the collected road image data for the intersection into the deep learning-based object detection and tracking model, and Extracting road information related to object information from the image data for the collected intersection using a deep learning-based object detection and tracking model, and de-identifying road information related to the extracted object information can

The acquiring may include recognizing the types of vehicles from the collected road image data for the intersection, tracking the position change of the recognized vehicles, and passing the recognized vehicles per unit time on a road including each intersection. The method may include extracting road information related to object information including a traffic volume and a saturation degree indicating a occupancy occupied by the recognized vehicles on a road including the respective intersections.

In the calculating step, the current time is calculated based on the traffic volume of the road including the intersection per unit time through the road information related to the obtained object information, and the traffic volume of the road including the intersection, and the calculated current time road Comparing the information with the road information of the current time before the calculated current time, calculating the current time for the intersection through a process of assigning a weight and a subtraction value to the road including the intersection may be included.

In the calculating step, if there are vehicles remaining after the calculated current time based on the calculated current time through the saturation of the road including the intersection, a weight is assigned to the vehicle within the calculated current time. When the intersections are empty, a subtraction value is given, and the calculated current time road information is compared with the road information of the current current time before the calculated current time. It may include the step of calculating the present time for

In the determining step, when it is determined that communication with the server will not be connected, operating the signal controller so that the traffic light is controlled based on the calculated signal period through communication between the electronic device and the signal controller The signal controller may receive the calculated signal period from the electronic device and operate a traffic light through the received signal period.

The server collects road information for the minimum control unit area composed of intersections, calculates the number of vehicles entering and leaving each intersection through the number of vehicles going straight, left and right turns, and taking into account the entering and leaving vehicles Thus, weights are reflected in the current time of the intersection and adjacent intersections, and offset time and signal period information of each intersection can be calculated based on the intersection.

When the number of vehicles departing from the adjacent intersection in the direction of the intersection in the server exceeds a preset criterion, weight is given to the current time of road information including the intersection, and the traffic volume of the adjacent intersection and the amount of entry and saturation of the intersection The offset time may be adjusted in consideration of .

The server may reduce the offset time when the entrance amount and saturation of the intersection are equal to or greater than a preset standard, and increase the offset time when the entry amount and saturation of the intersection are less than or equal to the preset reference.

An electronic device for traffic control includes: an acquisition unit configured to acquire road information related to object information from road image data for each intersection through a deep learning-based object detection and tracking model; a signal calculating unit for calculating a signal period for an intersection based on the obtained road information related to the object information; a communication determination unit for determining whether a communication connection with the server is present; and a data transmitter configured to transmit road information related to the obtained object information and the calculated signal period to a server as it is determined that communication with the server is connected, and road information related to the object information transmitted from the server And the signal controller of each intersection may be controlled based on the signal period information considering each intersection adjusted using the calculated signal period.

By controlling the signal period using road information related to de-identified object information, privacy for each vehicle can be protected.

Even when the network is disconnected, it is possible to independently control the signal controller at the intersection by calculating the signal period for the intersection through the deep learning operation in the edge terminal.

By calculating the signal period for each intersection in the server using the road information and signal period transmitted from the edge terminal, the signal period in consideration of the influence of the adjacent intersection can be operated.

After calculating the signal period for an intersection at the edge terminal, the server can control and operate traffic signals more accurately and quickly by optimizing the signal period with an adjacent intersection for each intersection.

1 is a view for explaining the configuration of a traffic control system according to an embodiment.
2 is a view for explaining a traffic control operation in a traffic control system according to an embodiment.
3 is a diagram for explaining a configuration of a minimum control unit according to an embodiment.
4 is a block diagram illustrating the configuration of an edge terminal according to an embodiment.
5 is a flowchart illustrating a traffic control method in an edge terminal according to an embodiment.
6 is an example for explaining an operation of acquiring road information related to object information through a deep learning-based object detection and tracking model, according to an embodiment.
7 is a flowchart illustrating an operation of controlling signal period information in a server according to an embodiment.
8 is an example for describing an object detection model according to an embodiment.
9 and 10 are examples for describing a tracking model according to an embodiment.

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings.

1 is a diagram for explaining the configuration of a traffic control system according to an embodiment.

The traffic control system is for controlling on-device real-time traffic signals based on deep learning, and may include an electronic device 100 , a server 110 , a signal controller 120 , and a photographing device 130 . The traffic control system may be composed of a field unit and a server.

For example, the electronic device 100 , the signal controller 120 , and the photographing device 130 may be installed and operated in the field. The field unit may include devices installed on the road site including each intersection.

The electronic device 100 may be a device for collecting and analyzing traffic information in the field. In this case, the electronic device 100 may analyze traffic information on the intersection by using data related to the road including the intersection. The electronic device 100 may transmit and receive data through wired/wireless communication with the signal controller 120 and the photographing device 130 . Hereinafter, the electronic device 100 will be described as an edge device.

The edge terminal 100 may receive road image data of the intersection through the photographing device 130, and road information related to object information using a deep learning-based object detection and tracking model from the received road image data of the intersection can be extracted. The edge terminal 100 may de-identify data related to personal information from road information related to the extracted object information. The edge terminal 100 may transmit de-identified data (road information related to object information) to the server 110 . At this time, the edge terminal 100 collects and analyzes road image data received from the photographing device 130 at the site, and then transmits the data to the server 100 , so the server 100 data for each intersection It is possible to control signal information faster than to collect and analyze each. In addition, it is possible to prevent data transmitted and received from the server 100 from being interrupted in the middle or from being analyzed using wrong data.

The server 110 may exist in a place other than the field, and may receive data transmitted from the edge terminal 100 and generate an optimized signal cycle for each intersection. The server 110 may transmit the generated signal period to each signal controller 120 .

The signal controller 120 may refer to a device that controls a signal cycle of a traffic light associated with each intersection. A traffic light may be operated based on a signal period controlled through the signal controller 120 .

The photographing device 130 may photograph a road including each intersection. In this case, the photographing device 130 may be installed at a specific location to photograph a road including an intersection. The photographing device 130 may correspond to at least one camera for photographing a road including an intersection, a CCTV including a camera function, and the like. For example, at least one or more cameras may take pictures in different directions, but some areas may overlap each other. Alternatively, the image may be photographed using a camera capable of 360-degree rotation.

In the embodiment, the edge terminal 100, the signal controller 120, and the photographing device 130 are configured for each intersection so that the road including each intersection is photographed and analyzed, and the analyzed signal cycle is transmitted to the signal controller 120 can be Accordingly, the signal controller 120 may reflect the signal cycle to the traffic light associated with the intersection.

According to one embodiment, it is possible to run on-device in a mobile or SBC (Single Board Computer) rather than a high-performance server by dramatically reducing the amount of computation without degrading the performance of the deep learning model through lightweight technology. . By using this, the problem of cost and personal information can be solved because road information that has undergone de-identification from on-device is transmitted to the server.

2 is a view for explaining a traffic control operation in a traffic control system according to an embodiment.

In FIG. 2, the CCTV 130 will be described as an example of a photographing device. As a road including an intersection is photographed by the CCTV 130 , road image data may be acquired. Road image data obtained by photographing a road in real time by the CCTV 130 may be collected, and the photographed road image data may be accumulated for a preset period. The road image data collected from the CCTV 130 may be transmitted to the edge terminal 100 . For example, road image data collected from the CCTV 130 may be transmitted in real time or periodically/aperiodically.

The edge terminal 100 may receive road image data from the CCTV 130 . The edge terminal 100 may recognize object information from road image data using a deep learning-based object detection and tracking model. 6, 8, 9, and 10 are examples for explaining an operation of acquiring road information related to object information through a deep learning-based object detection and tracking model. The road image data 601 may be input to the deep learning-based object detection and tracking model 600 . The deep learning-based object detection and tracking model 600 refers to a model for detecting an object from the road image data 601 and tracking a change in the position of the detected object. The deep learning-based object detection and tracking model 600 is a model configured for object detection and tracking, and may be trained using a data set for object detection and tracking. In an embodiment, the road image data 601 may be input to the deep learning-based object detection and tracking model 600 trained using the data set. In this way, road information 602 related to object information may be obtained from the road image data 601 using the trained deep learning-based object detection and tracking model 600 . In this case, the road information 602 related to the object information may include object information detected from the road image data 601 and road information (eg, traffic volume) including the object information. For example, the type of vehicle (e.g., passenger car, truck, ambulance, forklift, motorcycle, or general vehicle such as passenger car, bus, truck, etc., special vehicle such as ambulance, police car, fire engine, etc. ), etc.) can be recognized and tracked. Also, roads can be recognized. In addition, the amount of traffic that vehicles pass per unit time on the road, the degree of saturation indicating the occupancy of the road by vehicles, etc. may be acquired as the road information 602 related to the object information. The traffic volume refers to the number of vehicles passing through a defined ROI (Region of Interest) per unit time. Saturation means (the number of vehicles that exist within a certain range)/(the number of vehicles that can be accommodated within that range). In this case, the number of vehicles existing within a specific range means the number of vehicles recognized by the camera within a continuous road entering the ROI area defined by one or more cameras.

In detail, the deep learning-based object detection and tracking model 600 may detect an object from road image data and acquire object information by tracking a change in the position of the object. For example, the object detection and tracking model 600 based on deep learning may include an object detection model and a tracking model, respectively, and may be configured in a combined form. In addition, it is configured in various forms to detect an object through the deep learning-based object detection and tracking model 600 , and the detected object may be tracked.

First, an object detection model will be described. 8 is an example for describing an object detection model according to an embodiment. Recently, due to the rapid growth of artificial intelligence and deep learning, the performance of computer vision has risen dramatically. The object detection model is largely divided into a 1-stage-based model and a 2-stage-based model. It refers to a model with the ability to classify the location and type of objects by learning rules within unstructured data, such as images, where it is difficult to define a probability distribution.

The 1-stage-based model performs localization to find the location of an object and classification to classify what an object is, and representative models such as YOLO and SSD exist. It is an efficient structure than the two-stage-based model, and it shows high speed, but has relatively low performance.

In the two-stage-based model, the region proposal step is first performed in localization to find the location of an object, and then the classification step is performed to search the type of object. The model exists. It has higher performance than the 1-stage-based model, but has the disadvantage of being slow due to a more complex structure.

9 and 10 are examples for describing a tracking model according to an embodiment. The object tracking model is a field that has been studied for a long time in computer vision and image processing, and is a field that tracks a change in the position of a specific object in a video image. In the existing object tracking field, there have been methods such as Point Tracking and Kernel Tracking, but with the rapid growth of deep learning recently, models using deep learning are being actively studied. Broadly speaking, in the field of object tracking using deep learning, there are correlation filter-based and Siamese network-based.

Referring to FIG. 9 , an example of a correlation filter-based object tracking operation is illustrated. In the correlation filter-based field, it is a method of tracking an object by finding a part that has a high correlation with a target object with features extracted with a deep learning model.

Referring to FIG. 10 , it is an example illustrating a Siamese network-based object tracking operation. A Siamese network is a network that extracts features with a convolutional network to compare the similarity of two images in the deep learning field. to be.

The edge terminal 100 may recognize object information from road image data using a deep learning-based object detection and tracking model. The edge terminal 100 may acquire road information related to object information. The edge terminal 100 may proceed with de-identification of personal information-related data such as license plate and vehicle model. For example, the edge terminal 100 may perform special processing such as mosaic and blur on personal information-related data among road information related to object information, and may perform encryption on personal information-related data. In this way, de-identification may proceed through special processing such as mosaic, blur, and encryption. In other words, some data may be de-identified in a private form with respect to road information related to object information.

The edge terminal 100 may calculate an optimized signal period for an intersection based on road information related to object information. The edge terminal 100 may determine the amount of traffic on the road including the intersection per unit time. For example, it is possible to determine the amount of vehicle traffic per 15 seconds. The edge terminal 100 may calculate the current time based on the amount of traffic on the road including the intersection. When the edge terminal 100 is a road (intersection) on which the vehicle remains after the current time through saturation, the edge terminal 100 may give weight to the current time for the road. The edge terminal 100 may give a subtraction value to the current time for the road when all vehicles pass through the saturation and the road is empty within the current time. The edge terminal 100 may give weights and subtractions to the roads within the intersection through understanding the increase/decrease in state tax by comparing the current time with road information (eg, traffic volume, saturation) of the previous current time based on the current time. The edge terminal 100 may calculate the optimized display time for the intersection by using the weight and the subtraction calculated with respect to the existing display time. Accordingly, the edge terminal 100 may calculate the signal period for the intersection based on the current time.

Existing signal information of each intersection can be identified. For example, the existing period is 150 seconds, the existing display time may be configured as 70 seconds, 25 seconds, 25 seconds, 30 seconds, respectively. In addition, the minimum time and the maximum time including the first appearance (30, 105), the two manifestations (130, 35), the three manifestations (13, 40), and the four manifestations (15, 50) for each manifestation may be set. . The number of passing vehicles per unit time of the intersection may be calculated. If the unit time is 15 seconds and the amount of traffic per unit time is 5, the amount of traffic per unit time of a three-lane road can be derived from 5*3 by 15. The saturation of the intersection can be calculated. When the maximum number of detected vehicles in the ROI is 15 and the number of detected vehicles is 5, the saturation can be derived as 5/15=33%. The current time may be calculated by considering the traffic volume and saturation in the existing signal information. The traffic volume for each prefecture may be calculated (for example, 30 units in 1 prefecture, 15 cars in 2 counties, 15 cars in 3 counties, 25 cars in 4 counties). In addition, the degree of saturation for each manifestation may be calculated (eg, 50% for 1st display, 0% for 2nd display, 10% for 3rd display, 30% for 4th display). Also, a priority for each prefecture may be set based on the amount of traffic (eg, 1st prefecture, 2nd prefecture 3rd priority, 3rd prefecture 3rd priority, 4th prefecture 2nd priority). In addition, a weight value for each appearance may be set based on the priority. Each display time can be adjusted based on saturation. For example, the display time of a road (intersection) with a saturation of 50% to 100% or more is +10 seconds, the display time of a road (intersection) with a saturation of 0% to 50% or more is +5 seconds, and a road with a saturation of 0%. (Intersection) display time can be adjusted to -5 seconds. Accordingly, the existing display time is 70, 25, 25, 30, and the existing period is 150 seconds to the new display time 82, 20, 26, 37, the new period can be adjusted to 165. The above-mentioned operation may be repeatedly performed, and new current time and period information may be transmitted to the server.

The edge terminal 100 may transmit road information and calculated signal information related to the de-identified object information to the server 110 . In addition, the edge terminal 100 may transmit the calculated signal period to the signal controller 120 . The edge terminal 100 may operate the signal controller 120 through communication between the edge terminal 100 and the signal controller 120 when communication with the server is not smooth due to a network problem.

The server 110 may receive road information related to the de-identified object information and the calculated signal period from the edge terminal 100 . The server 110 may calculate a signal period for each intersection by using the road information related to the de-identified object information and the calculated signal period. In detail, the server 110 may optimize the signal period information for each intersection by receiving road information related to the de-identified object information for each intersection and the calculated signal period.

Referring to FIG. 7 , in step 710 , the server 110 may calculate the offset time and signal period information of each intersection by collecting road information and signal period related to object information for a plurality of intersections. The server 110 may collect intersection road information of the minimum control unit area, which is a group consisting of intersections having a similar traffic pattern. The server 110 may calculate the number of vehicles entering and leaving each intersection based on the number of vehicles going straight, left, and right in order to consider the influence of adjacent roads. The server 110 may reflect the weight to the current time of the adjacent intersection in consideration of the vehicle entering and leaving the vehicle. The server 110 may calculate the offset time and signal period information of each intersection based on the important intersection in the minimum control unit. The server 110 may assign a weight to the current time for a corresponding intersection when there are many vehicles departing from an adjacent intersection in the direction of a specific intersection more than a preset criterion.

In step 720 , the server 110 may adjust the offset time according to the amount of traffic at each intersection, the amount of entry into an adjacent intersection for each intersection, and saturation. The server 110 may reduce the offset time if the entry amount and saturation level are high, and increase the offset time if the entry amount and saturation level are small, so that the entering vehicles can smoothly pass through the intersection without stopping.

In step 730 , the server 110 may transmit signal period information in consideration of the influence on each intersection to each signal controller 120 through adjustment. The server 110 may transmit the calculated signal period information to the signal controller 120 for each intersection. The signal controller 120 may receive a signal period from the edge terminal 100 or the server 110 . The signal controller 120 may reflect the received signal period to the traffic light. According to an embodiment, since it is affected by an adjacent intersection, information on each intersection is transmitted to the server, enabling operation of a signal cycle in consideration of the influence of an adjacent intersection.

For example, the server 110 may adjust the display time in consideration of the adjacent intersection. New current time and period information for each intersection may be received. For example, the current display time (70, 25, 25, 30) for the intersection A was adjusted to the new display time (80, 20, 26, 37), and the period information that was 150 may be adjusted to 165, and at the intersection B It can be seen that the display time (40, 35, 45, 25) is adjusted to the new display time (65, 40, 55, 40). The server 110 may adjust the current time and period information associated with adjacent intersections. For example, the server 110 adjusts the display time (82, 20, 26, 37 -> 85, 21, 28, 42), period information (165->176) for the intersection A, and displays the display for the intersection B Time (65, 40, 55, 40 -> 62, 36, 48, 35) and period information (200 -> 181) can be adjusted. The server 110 may transmit a current time in consideration of an adjacent intersection to each intersection. The server 110 may transmit the current time for each intersection to each signal controller 120 . For example, the server 110 transmits the final display time (85, 21, 28, 42) and period information 176 of the intersection A to the signal controller 120 for the intersection A, and the signal controller for the intersection B It is possible to transmit the final display time (62, 36, 48, 35) and period information (181) of the intersection B to (120).

3 is a diagram for explaining a configuration of a minimum control unit according to an embodiment.

Currently, the real-time signal controller has a disadvantage in that it has to be adjusted by a human in the control center or repeatedly send a signal cycle for each time based on a TOD (Time of Day) plan. In order to solve this problem, the embodiment enables optimized signal control by reflecting road information in real time.

The minimum control unit may mean a group of at least one or more intersections by identifying geographic characteristics at the National Police Agency, the Road Traffic Authority, and the like. At least one intersection may be grouped as a minimum control unit in a specific area according to geographical characteristics. For example, the farther you go out of an urban area, the less you may be affected by vehicles. Accordingly, it can be divided into important intersections that are heavily influenced by traffic, semi-important intersections that are less affected by traffic, and non-important intersections that are not affected by traffic.

In addition, the present time will be described. Display time means to provide vehicles to pass as a whole at the intersection, and signal commands such as straight ahead, left turn, and right turn based on a specific location (the direction of the road at a specific location) are called display. For example, if the first display is straight forward, the second display is a left turn, and the third display is a right turn, when all of the respective displays are progressed, this is called a signal cycle.

4 is a block diagram for explaining the configuration of an edge terminal according to an embodiment, and FIG. 5 is a flowchart for explaining a traffic control method in an edge terminal according to an embodiment.

The processor of the edge terminal 100 may include an acquisition unit 410 , a period calculation unit 420 , a communication determination unit 430 , and a data transmission unit 440 . The components of such a processor may be representations of different functions performed by the processor according to a control instruction provided by a program code stored in the vehicle control device. The processor and components of the processor may control the edge terminal to perform steps 510 to 541 included in the traffic control method of FIG. 5 . In this case, the processor and the components of the processor may be implemented to execute instructions according to the code of the operating system included in the memory and the code of at least one program.

The processor may load the program code stored in the file of the program for the traffic control method into the memory. For example, when a program is executed in the edge terminal, the processor may control the edge terminal to load the program code from the program file into the memory according to the control of the operating system. At this time, each of the acquisition unit 410 , the period calculation unit 420 , the communication determination unit 430 , and the data transmission unit 440 executes a command of a corresponding portion of the program code loaded in the memory to perform subsequent steps 510 to 541) may be different functional representations of the processor.

In step 510 , the acquisition unit 410 may acquire road information related to object information from road image data for each intersection through a deep learning-based object detection and tracking model. Acquisition unit 410 collects road image data for intersections photographed from a photographing device installed at each intersection, inputs the collected road image data for intersections into the deep learning-based object detection and tracking model, and deep learning It is possible to extract road information related to object information from the collected image data for an intersection using the based object detection and tracking model, and de-identify road information related to the extracted object information. The acquisition unit 410 recognizes the types of vehicles from the collected road image data for the intersection, tracks the position change of the recognized vehicles, and recognizes the amount of traffic that the recognized vehicles pass per unit time on a road including each intersection. It is possible to extract road information related to object information including saturation indicating the occupancy occupied by the vehicles on the road including each intersection.

In operation 520, the period calculator 420 may calculate a signal period for the intersection based on the obtained road information related to the object information. The period calculator 420 calculates the current time based on the traffic volume of the road including the intersection per unit time and the traffic volume of the road including the intersection per unit time through the road information related to the obtained object information, and the calculated current time road information The current time for the intersection can be calculated through the process of assigning weights and subtractions to the road including the intersection by comparing with the road information of the current time before the calculated current time. If there are vehicles remaining after the current time calculated based on the current time calculated through the saturation of the road including the intersection, the period calculator 420 gives weights, and the vehicles are empty within the calculated current time. If there is, a subtraction value is given, and the current time for the intersection is compared with the calculated current time road information and the calculated current time road information before the calculated current time. can be calculated.

In step 530 , the communication determination unit 430 may determine whether communication is connected with the server. For example, the communication determination unit 430 may transmit the calculated signal period for the intersection to the server in determining whether communication is connected. When the calculated signal period for the intersection is transmitted to the server, it can be determined that communication with the server is connected. can judge Alternatively, the communication determination unit 430 may check the communication condition to determine whether communication is connected with the server.

In step 540 , the data transmitter 440 may transmit road information related to the obtained object information and the calculated signal period to the server as it is determined that communication with the server is connected. Accordingly, the signal controller of each intersection may be controlled based on the road information related to the object information transmitted from the server and the signal period information in consideration of each intersection calculated using the calculated signal period. In step 541 , the data transmitter 440 may operate a signal controller to control the traffic lights based on a signal period calculated through communication between the electronic device (edge terminal) and the signal controller.

The device described above may be implemented as a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, devices and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA). , a programmable logic unit (PLU), microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. The processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that may include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

The software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or device, to be interpreted by or to provide instructions or data to the processing device. may be embodied in The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

As described above, although the embodiments have been described with reference to the limited embodiments and drawings, various modifications and variations are possible by those skilled in the art from the above description. For example, the described techniques are performed in a different order than the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (10)

In the traffic control method performed in an electronic device,
obtaining road information related to object information from road image data for an intersection through a deep learning-based object detection and tracking model;
calculating a signal period for an intersection based on road information related to the obtained object information;
determining whether there is a communication connection with the server; and
Comprising the step of transmitting road information related to the obtained object information and the calculated signal period to a server as it is determined that communication with the server is connected,
The signal controller of each intersection is controlled based on the road information related to the object information received from the server and the signal period information considering each intersection adjusted using the calculated signal period.
Traffic control method, characterized in that. According to claim 1,
The obtaining step is
Collects road image data for an intersection taken from a photographing device installed at each intersection, inputs the collected road image data for the intersection into the deep learning-based object detection and tracking model, and detects the deep learning-based object and extracting road information related to object information from the collected image data on the intersection using a tracking model, and de-identifying road information related to the extracted object information.
A traffic control method comprising a. 3. The method of claim 2,
The obtaining step is
Recognizing the types of vehicles from the collected road image data for the intersection, tracking the position change of the recognized vehicles, the amount of traffic that the recognized vehicles pass per unit time on a road including each intersection, the recognized vehicle extracting road information related to object information including saturation indicating the occupancy occupied by vehicles on the road including the respective intersections;
A traffic control method comprising a. According to claim 1,
The calculating step is
The current time is calculated based on the traffic volume of the road including the intersection per unit time and the traffic volume of the road including the intersection per unit time through the road information related to the obtained object information, and the calculated current time road information and the calculated current time Comparing with the road information of the current time before the time, calculating the current time for the intersection through the process of assigning weights and subtractions to the road including the intersection
A traffic control method comprising a. 5. The method of claim 4,
The calculating step is
Based on the calculated current time through the saturation of the road including the intersection, if there are vehicles remaining after the calculated current time, weight is given, and if the vehicles are empty within the calculated current time, subtraction The current time for the intersection is calculated through the process of assigning a value and assigning a weight and a subtraction value to the road including the intersection by comparing the calculated road information of the current time with the road information of the current time before the calculated current time step to do
A traffic control method comprising a. According to claim 1,
The determining step is
operating the signal controller to control the traffic lights based on the calculated signal period through communication between the electronic device and the signal controller when it is determined that communication with the server will not be connected
including,
The signal controller receives the calculated signal period from the electronic device, and operates a traffic light through the received signal period.
Traffic control method, characterized in that. According to claim 1,
The server collects road information for the minimum control unit area composed of intersections, calculates the number of vehicles entering and leaving each intersection through the number of vehicles going straight, left and right turns, and taking into account the entering and leaving vehicles In this way, the weight is reflected in the current time of the intersection and the adjacent intersection, and the offset time and signal period information of each intersection are calculated based on the intersection.
Traffic control method, characterized in that. 8. The method of claim 7,
When the number of vehicles departing from the adjacent intersection in the direction of the intersection exceeds a preset standard, weight is given to the current time of road information including the intersection, and the traffic volume of the adjacent intersection, the amount of entry into the intersection, and saturation are considered to adjust the offset time
Traffic control method, characterized in that. 9. The method of claim 8,
When the amount of entry and saturation of the intersection are greater than or equal to preset standards, the offset time is reduced, and when the amount of entry and saturation of the intersection are less than or equal to the preset standards, the offset time is increased.
Traffic control method, characterized in that. In the electronic device for traffic control,
an acquisition unit for acquiring road information related to object information from road image data for each intersection through a deep learning-based object detection and tracking model;
a signal calculating unit for calculating a signal period for an intersection based on road information related to the obtained object information;
a communication determination unit for determining whether a communication connection with the server is present; and
When it is determined that communication with the server is connected, the data transmitter transmits road information related to the obtained object information and the calculated signal period to the server.
including,
and a signal controller of each intersection is controlled based on road information related to the object information transmitted from the server and signal period information in consideration of each intersection adjusted using the calculated signal period.

Images