KR102497041B1 - Intelligent traffic light system - Google Patents

Abstract

The present invention relates to an intelligent right turn traffic light system, and more specifically, to an intelligent right turn traffic light system, which self-recognizes and analyzes traffic conditions, road environment, and pedestrian status of intersections and adjacent roads, and outputs a right turn signal suitable therefor, thereby minimizing the risk of traffic accidents between right-turning vehicles and pedestrians on adjacent roads, at the same time, can prevent traffic congestion due to the unconditional stop of right-turning vehicles by flexibly determining whether or not to turn right based on intelligent situation judgment.

Description

Intelligent right turn signal light system {INTELLIGENT TRAFFIC LIGHT SYSTEM}

The present invention relates to an intelligent right-turn traffic light system, and more particularly, by self-recognizing and analyzing the traffic conditions of intersections and adjacent roads, the road environment, the pedestrian status, etc. Regarding an intelligent right-turn traffic light system that minimizes the risk of traffic accidents between pedestrians and at the same time flexibly determines whether or not to turn right based on intelligent situation judgment to prevent traffic congestion due to unconditional stop of right-turning vehicles will be.

Pedestrian traffic accidents caused by right-turning vehicles are one of the major causes of vehicle-to-pedestrian accidents. According to the National Police Agency and Korea Road Traffic Authority, a total of 212 pedestrians were killed and 13,150 were injured due to right-turning vehicles over the three years from 2018 to 2020. The number of pedestrian deaths per 100,000 people in Korea is 2.5, which is 2.3 times higher than the average of OECD member countries, and most of these accidents are known to be caused by right-turning vehicles.

Among these right turn accidents, 126 pedestrians died while crossing the road, accounting for 59.4% of the total deaths. It is known to be three times as many.

In response to this situation, the government has amended the Enforcement Rules of the Road Traffic Act (enforced on January 22, 2023) to clarify the duty to stop when making a right turn at an intersection when the traffic light is red. However, despite the revision of the law, the fact that the driver can decide whether to slow down or stop depending on the presence or absence of pedestrians at the crosswalk when the vehicle signal ahead is green, and the fact that the driver's attention is still immature in a right turn situation, etc. However, it is insufficient to prevent traffic accidents caused by right-turning vehicles.

Even in the past, some traffic light-related technologies with a technical focus on responding to right-turning vehicles have been disclosed. As in the following patent documents, a traffic light capable of separately displaying a right turn signal has been disclosed. However, since these traffic lights are merely to visualize the right turn signal more clearly to the driver of the right turn vehicle, there is a problem in that they cannot actively cope with road conditions or the presence or absence of pedestrians.

(Patent Document) Patent Publication No. 10-2015-0100190 (published on September 2, 2015) "Intersection traffic light displaying right turn entry warning signal for vehicles turning right"

The present invention has been made to solve the above problems,

The present invention self-recognizes and analyzes traffic conditions of intersections and adjacent roads, road environment, pedestrian status, etc., and outputs an appropriate right-turn signal based on this, thereby suppressing traffic accidents between right-turning vehicles and pedestrians on nearby roads as much as possible. The purpose is to provide an intelligent right turn traffic light system.

The present invention self-recognizes and analyzes the traffic conditions of intersections and adjacent roads, road environment, pedestrian status, etc., independently determines the risk of traffic accidents at intersections and adjacent roads, and flexibly determines right turn signal availability depending on the situation, thereby reducing right-turning vehicles The purpose of the present invention is to provide an intelligent right-turn traffic light system that can prevent traffic congestion due to unconditional stop of the vehicle.

The present invention is an intelligent right turn signal light system that can further suppress traffic accidents between right turning vehicles and pedestrians on nearby roads by visually and aurally outputting and alerting pedestrians of intersections and adjacent roads with warning signals according to vehicle entry. It aims to provide

On the other hand, other objects not specified in the present invention will be additionally considered within the range easily inferred from the following problem solving means, effects and detailed description of the invention.

The present invention is implemented by an embodiment having the following configuration in order to achieve the above object.

According to one embodiment of the present invention, the intelligent right turn traffic light system according to the present invention includes a photographing means for obtaining an image or video by photographing traffic conditions, road environment, and pedestrian status of an intersection and adjacent roads, and a right turn road at an intersection. It includes a traffic light unit installed in and a control unit for controlling the traffic light unit, and the traffic light unit includes a body unit and a signal unit formed on one side of the body unit and outputting a signal under the control of the control unit, and the control unit includes the photographing unit. It is characterized in that the signal unit is controlled based on at least one of traffic conditions of intersections and adjacent roads, road environments, and pedestrian conditions acquired from the means.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the controller includes: a data acquisition unit that acquires image or image information of an intersection and an adjacent road in association with the photographing means; A data detection unit that reads the image or video information obtained from the acquisition unit and analyzes and detects the traffic conditions, road environment, and pedestrian status of the intersection and adjacent roads, and the intersection and adjacent roads based on the data detected by the data detection unit It is characterized in that it includes a risk determination unit for calculating and determining the degree of traffic danger, a traffic light control unit for controlling the traffic light unit according to the judgment of the risk determination unit, and a setting unit for managing the control unit.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the data acquisition unit includes a camera interlocking module that collects image or video information from the photographing means in real time, and an intersection where the traffic light system is installed. and a pre-processing module for collecting and recognizing background information of adjacent roads, and a correction module for correcting obstruction factors such as weather changes, shadows, and minor signal failures of intersections and adjacent roads.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the data detection unit detects signal control information of the walking signal in conjunction with one or more walking signals installed in an intersection and an adjacent road. A signal detection module, and a road environment detection module for detecting the road environment of an intersection and an adjacent road based on the image or image information acquired by the data acquisition unit, and an intersection and adjacent road based on the image or image information acquired by the data acquisition unit. It is characterized in that it includes an object detection module for detecting a stationary or moving object on the road.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the road environment detection module comprises: a weather information detection module for detecting weather conditions of intersections and adjacent roads; and time information for detecting time information. It is characterized in that it includes an information detection module, and a peripheral environment detection module for detecting the presence or absence of parking vehicles and street vendors at intersections and adjacent roads.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the object detection module comprises: an object discrimination module for determining an object element from the image or image information acquired by the data acquisition unit; An object recognition information acquisition module that acquires any one or more information of the speed, size, shape, or movement type of the object element determined by the object discrimination module, and the type of each object element based on the information acquired from the object recognition information acquisition module It is characterized in that it includes an object type determination module that discriminates and classifies.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the risk determination unit extracts one or more risk factors from the detection information of the intersection and adjacent roads detected by the data detection unit. module, and a code-assigning module that assigns a risk criterion code based on one or more risk factors extracted from the risk factor extraction module, and discriminates risk types of intersections and adjacent roads based on the risk criterion code assigned from the code-assigning module It is characterized in that it includes a risk type determination module that does.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the risk factor extraction module extracts a first risk factor from signal control information of one or more walking signals installed at intersections and adjacent roads. A first risk factor extraction module, a second risk factor extraction module for extracting a second risk factor from the road environment of intersections and adjacent roads, and a third risk factor for extracting object information from stationary or moving object information at intersections and adjacent roads It is characterized in that it includes a third risk factor extraction module and a fourth risk factor extraction module that classifies the area of the intersection and adjacent roads into a plurality of sections and extracts a fourth risk factor according to each section.

According to another embodiment of the present invention, in the intelligent right turn traffic light system according to the present invention, the traffic light control unit includes a control method determination module for determining a control method of the traffic light unit according to the degree of traffic risk determined by the risk determination unit; and , and a signal output control module for controlling the signal output of the traffic light unit according to the determination of the control method determination module.

According to another embodiment of the present invention, in the intelligent right turn signal light system according to the present invention, the setting unit includes a control setting module for managing general settings such as on/off of the control unit, the data acquisition unit, and the data acquisition unit. It is characterized by including an algorithm setting module that sets and manages matters necessary for calculation, analysis, and judgment of the detection unit and traffic light control unit, and a risk determination setting module that sets and manages matters necessary for the determination of the risk determination unit.

The present invention has the following effects by adopting the means for solving the problems disclosed above.

The present invention self-recognizes and analyzes traffic conditions of intersections and adjacent roads, road environment, pedestrian status, etc., and outputs an appropriate right-turn signal based on this, thereby suppressing traffic accidents between right-turning vehicles and pedestrians on nearby roads as much as possible. There is an effect of providing an intelligent right turn traffic light system.

The present invention self-recognizes and analyzes the traffic conditions of intersections and adjacent roads, road environment, pedestrian status, etc., independently determines the risk of traffic accidents at intersections and adjacent roads, and flexibly determines right turn signal availability depending on the situation, thereby reducing right-turning vehicles There is an effect of providing an intelligent right turn traffic light system that can prevent traffic congestion due to the unconditional stop of the vehicle.

The present invention is an intelligent right turn signal light system that can further suppress traffic accidents between right turning vehicles and pedestrians on nearby roads by visually and aurally outputting and alerting pedestrians of intersections and adjacent roads with warning signals according to vehicle entry. has the effect of providing

On the other hand, even effects that are not explicitly mentioned in the present invention can be treated as described in this specification if they are effects that can be derived within a reasonably inferable range in the description of the entire specification, such as the detailed description below.

1 is a diagram showing a traffic light unit of an intelligent right turn traffic light system according to an embodiment of the present invention.
2 is a view showing another form of a traffic light unit in an intelligent right turn traffic light system according to an embodiment of the present invention.
3 is a diagram showing a traffic light unit of an intelligent right turn traffic light system according to another embodiment of the present invention;
4 is a diagram schematically illustrating the concept of an intersection and an adjacent road where an intelligent right turn traffic light system according to the present invention is installed;
5 is a view showing each section of a right turn access route in more detail at an intersection and an adjacent road where an intelligent right turn traffic light system according to the present invention is installed.
6 is a block diagram showing the configuration of a control unit of an intelligent right turn traffic light system according to the present invention.
Figure 7 is a block diagram showing the configuration of the data acquisition unit of Figure 6
Figure 8 is a block diagram showing the configuration of the data detection unit of Figure 6
Figure 9 is a block diagram showing the configuration of the risk determination unit of Figure 6
Figure 10 is a block diagram showing the configuration of the traffic light control unit of Figure 6
Figure 11 is a block diagram showing the configuration of the setting unit of Figure 6

Hereinafter, preferred embodiments of the intelligent right turn traffic light system according to the present invention will be described in detail with reference to the accompanying drawings. In the following description of the present invention, if it is determined that a detailed description of a known function or configuration may unnecessarily obscure the subject matter of the present invention, the detailed description thereof will be omitted. Throughout the specification, when a part "includes" a certain component, it means that it may further include other components without excluding other components unless otherwise stated, and also described in the specification. Terms such as "...unit" and "...module" mean a unit that processes at least one function or operation, which may be implemented as hardware or software or a combination of hardware and software.

Unless otherwise defined, all terms (including technical and scientific terms) used in this specification may be used in a meaning commonly understood by those of ordinary skill in the art to which the present invention belongs. In addition, terms defined in commonly used dictionaries are not interpreted ideally or excessively unless explicitly specifically defined.

1 to 11, the intelligent right turn traffic light system according to an embodiment of the present invention is described, the intelligent right turn traffic light system captures traffic conditions of intersections and adjacent roads, road environment, and pedestrian conditions to produce images or videos. A right turn traffic light system including a photographing means 300 for acquiring, a traffic light unit 200 installed at a right turn road at an intersection, and a control unit 100 for controlling the traffic light unit 200, wherein the traffic light unit 200 includes a body part 210 and a signal part 220 formed on one side of the body part 210 and outputting a signal under the control of the control part 100, and the control part 100 is the photographing unit 300 It is characterized in that the signal unit 220 is controlled based on at least one of traffic conditions of intersections and adjacent roads obtained from ), road environment, and pedestrian status.

The photographing means 300 means overall means for obtaining images or images by capturing traffic conditions, road environments, and pedestrian conditions of an intersection and adjacent roads where an intelligent right turn traffic light system is installed according to an embodiment of the present invention. do. Preferably, in an intersection, an area where a right-turning vehicle enters an intersection (hereinafter referred to as 'first area (A)'), an area corresponding to a road corresponding to a vehicle's path after turning right at an intersection and an area corresponding to its adjacent sidewalk (hereinafter referred to as the '2-1 area (B)'), the area corresponding to the road facing the 2-1 area (B) and the center line and the sidewalk adjacent thereto (hereinafter referred to as the '2-2 area (hereinafter referred to as '2-1 area (B)') C)') refers to all means capable of acquiring images and images for an area including ', and such a means of filming may mean one or more closed-circuit televisions (CCTVs) installed at an intersection or nearby. Alternatively, it may mean a photographing means such as a camera provided by itself in the intelligent right turn traffic light system according to the present invention.

The traffic light unit 200 is installed at a right turn corner of an intersection, and means a configuration that expresses a signal to guide right turn vehicles to right turn. As shown in FIG. 1, the traffic light unit 200 includes a main body 210 in which a circuit is embedded and surrounded by a housing, and is formed on one side of the main body 210 to control the control unit 100. It includes a signal unit 220 that outputs a signal according to the signal, and may further include a holding unit that additionally supports the body unit as needed. On the other hand, the signal unit 220 may output a signal for permitting entry of a right turning vehicle in a simple red/green light method or a method in which → and X are marked thereon, but it is not necessarily limited thereto, and those skilled in the art can arbitrarily appropriate matters. can be selected and employed.

Meanwhile, the traffic light unit 200 may further include a driver attention unit 230 that alerts the right-turning vehicle to pedestrians in addition to the signal unit 220 for informing the right-turning vehicle whether or not to turn right. Preferably, the driver's attention alerting unit 230 may adopt a means for visually alerting the driver, and as shown in FIG. 2, an electronic display board capable of calling attention to pedestrians with text may be used. However, it is not necessarily limited thereto, and those skilled in the art can arbitrarily select and employ appropriate ones.

On the other hand, the traffic light unit 200, in addition to displaying a signal for guiding right-turning vehicles to whether or not to turn right, provides pedestrians located on the sidewalk of the 2-1 area (B) or 2-2 area (C). A configuration capable of notifying whether or not a right-turning vehicle enters or whether attention may be further included may be further included. This will be described later.

The control unit 100 refers to a configuration that controls the signal unit 220 based on at least one of traffic conditions of intersections and adjacent roads, road environments, and pedestrian conditions obtained from the photographing unit 300 . To this end, as shown in FIGS. 6 to 11, the control unit 100 includes a data acquisition unit 110 that acquires image or image information of an intersection and an adjacent road in association with the photographing means 300, and the data acquisition unit 110. A data detection unit 120 that reads the image or video information acquired from the acquisition unit 110 and analyzes and detects at least one of traffic conditions, road environments, and pedestrian conditions of the intersection and adjacent roads; and the data detection unit 120 ) based on the analyzed and detected data, the risk determination unit 130 calculates and determines the degree of traffic risk of the intersection and adjacent roads, and controls the traffic light unit 200 according to the judgment of the risk determination unit 130. It may include a traffic light control unit 140 and a setting unit 150 that manages the control unit 100.

The data acquisition unit 110 is a component that acquires image or image information of an intersection and an adjacent road in association with the photographing means 300, and the data acquisition unit 110 is an image or video from the photographing means 300. A camera interlocking module 111 that collects information in real time, a pre-processing module 112 that collects and recognizes background information of the intersection and adjacent roads where the traffic light system is installed, A correction module 113 for correcting obstacles such as signal failure may be included.

The camera interworking module 111 means a component that collects image or video information from the photographing means 300 in real time. As described above, the photographing unit 300 may refer to a CCTV already installed at an intersection. In the case of intersections, there are many cases where CCTVs are installed for the purpose of cracking down on speeding/signal violations, grasping traffic conditions, and cracking down on illegal parking. The intelligent right turn traffic light system according to an embodiment of the present invention can control signals based on images or videos of CCTVs already installed at intersections. Therefore, the camera interlocking module 111 interlocks with the photographing means 300 already installed at the intersection separately from the intelligent right turn traffic light according to an embodiment of the present invention, and images or videos collected from the photographing means 300 Corresponds to a configuration for acquiring in real time. For this interworking, the photographing means 300 and the control unit 100 may be connected in various ways, wired or wireless.

On the other hand, the photographing means 300 may mean a photographing means 300 such as a camera built into the right turn traffic light system of the present invention rather than a means such as a CCTV previously installed at an intersection. In this case, the camera interworking module 111 can be understood as a component that acquires images or videos in real time from the built-in camera.

The pre-processing module 112 refers to a component that collects and recognizes background information of an intersection and an adjacent road where an intelligent right turn traffic light system according to the present invention is installed. This is a pre-processing process in terms of technology such as decoding of input images or videos, initialization of background information (roads, lanes, sidewalks, structures, buildings, etc.) corresponding to the surveillance area of the installed CCTV, and recognition and collection of background information. It may include all pre-processing processes in terms of data, such as, etc., and any method is not particularly limited as long as it is a known technique for achieving this purpose. The pre-processing module 112 may store the acquired background information and provide reference data for comparison or comparison with images or images acquired in real time.

The correction module 113 refers to a component that corrects obstacle factors such as weather changes at intersections and adjacent roads, generation of shadows, and slight signal disturbances. The correction module 113 uses a known background modeling technique such as a Gaussian Mixture (MoG) algorithm to minimize obstacles or influencing factors such as shadows, shadows, and changes in illuminance from the background information obtained from the preprocessing module 112. etc. can be used. In addition, a known digital correction algorithm or the like can be used to solve problems in terms of signal processing, such as signal problems. Finally, in the correction module 113, from images or images of intersections and adjacent roads collected in real time, obstacles due to weather, time, signal failure, etc. are minimized to perform detection of a moving object from a background image as easily as possible. can support

The data detection unit 120 includes a walking signal detection module 121 for detecting signal control information of the walking signal P in conjunction with one or more walking signals P installed at an intersection and an adjacent road, and the data acquisition unit ( Road environment detection module 122 for detecting the road environment of intersections and adjacent roads based on the image or image information obtained in 110), and intersections and adjacent roads based on the image or image information obtained in the data acquisition unit 110 may include an object detection module 123 for detecting a stationary or moving object.

The walking signal detection module 121 refers to a component that detects signal control information of the walking signal P in conjunction with one or more walking signals P installed at an intersection and an adjacent road. When a vehicle turns right at an intersection, a crosswalk located on the right turn path in the first area (A), formed in the form of a traffic 'island' between the first area (A) and the 2-1 area (B) It is common to pass through any one or more of the crosswalks leading to the waiting area for crossing or the crosswalks located on the right turn path in area 2-1 (B), which are crosswalks located on the right turn vehicle progress path and turn right. It corresponds to an important factor in signal control. Therefore, when walking signals P corresponding to the corresponding crosswalks are installed, signal control information of the walking signals P can be detected and used for signal control. To this end, the walking signal detection module 121 may be interlocked with the signal control means of the walking signals P in various ways, wired or wireless.

The road environment detection module 122 refers to a component that detects road environments of intersections and adjacent roads based on image or image information acquired by the data acquisition unit 110 . To this end, the road environment detection module 122 includes a weather information detection module 122A for detecting weather conditions near intersections and adjacent roads, a time information detection module 122B for detecting time information, and illegal parking on the roadside. A peripheral environment detection module 122C for detecting the existence of vehicles, street vendors, etc. may be included.

The weather information detection module 122A is a component that detects weather conditions near intersections and adjacent roads, and detects whether the weather conditions near intersections and adjacent roads are clear or bad weather. The weather information detection module 122A may detect a weather situation using a known screen analysis technique, or may detect a weather situation in conjunction with a server that can update weather-related information in real time, and these or It can be achieved by a combination of additional weather information detection methods.

The time information detection module 122B is a component that detects the current time, and means a component that detects in real time the time of the site where the intelligent right turn traffic light system according to an embodiment of the present invention is installed, which is a known method. can be achieved

The peripheral environment detection module 122C is a component that detects the existence of illegally parked cars, street vendors, etc. at intersections and adjacent roads, and the reference data acquired by the data acquisition unit 110 and images collected in real time or Image data is compared and contrasted to detect the existence of illegally parked vehicles or street vendors. To achieve this, a known image or image comparison algorithm may be used.

The object detecting module 123 refers to a component that detects a stationary or moving object at an intersection and an adjacent road based on image or image information acquired by the data acquisition unit 110 . To this end, the object detection module 123 includes an object discrimination module 123A for determining an object element in the image or video information acquired by the data acquisition unit 110, and an object determined by the object discrimination module 123A. An object recognition information acquisition module (123B) that acquires any one or more information of the element's speed, size, shape, and movement type, and the type of each object element is determined based on the information acquired by the object recognition information acquisition module (123B). , may include an object type determination module 123C for classifying.

The object discrimination module 123A means a component that determines object elements from the image or image information acquired by the data acquisition unit 110, wherein the object elements include cars, pedestrians, bicycles, kickboards, other animals, and street vendors. , Temporary structures, etc., and all objects that can be distinguished from stationary and moving objects. To this end, the object discrimination module 123A may utilize various well-known object extraction algorithms or techniques such as semantic segmentation.

The object recognition information acquisition module 123B refers to a component that acquires any one or more information among the speed, size, shape, and movement type of the object element determined by the object discrimination module 123A. The object recognition information acquisition module 123B 'tracks' the object elements determined by the object discrimination module 123A, thereby calculating and securing the size, position, speed, movement type, etc. of each object element. there is. To this end, the object recognition information acquisition module 123B may utilize various well-known object tracking algorithms or techniques such as a CAM (continuously Adaptive Mean) shift algorithm and optical flow.

The object type determination module 123C refers to a component that determines and classifies the type of each object element based on the information acquired by the object recognition information acquisition module 123B. To this end, the object type determination module 123C takes information such as the size, position, speed, and movement type of each object element obtained from the object recognition information acquisition module 123B as an input value, and uses an artificial neural network (ANN) Based on , information about the type of object (general pedestrian, electric kickboard, child, drunken person, handicapped, etc.) estimation information can be obtained as an output value. Any known method capable of predicting or estimating the type and behavior of an object based on the state of the detected object is not limited, and finally, the object type determination module 123C recognizes the type of each object. (Cars, street vendors, general pedestrians, personal mobility such as bicycles or electric kickboards, children, drunken passengers, disabled people, etc.) are identified and classified.

The risk determination unit 130 is a component that calculates and determines the degree of traffic risk of an intersection and an adjacent road based on the data analyzed and detected by the data detection unit 120. To this end, the risk determination unit 130 A risk factor extraction module 131 for extracting one or more risk factors from any one or more of detection information such as traffic conditions of intersections and adjacent roads, road environment, and pedestrian status detected by the data detection unit 120; A code assignment module 132 that assigns a risk criterion code based on one or more risk factors extracted by the factor extraction module 131, and a code assignment module 132 for determining intersections and adjacent roads based on the risk criterion code assigned by the code assignment module 132. A risk type determination module 133 for determining the risk type may be included.

The risk factor extraction module 131 extracts one or more risk factors from detection information of any one of the detection information such as traffic conditions of intersections and adjacent roads, road environment, and pedestrian status detected by the data detection unit 120 means composition. To this end, the risk factor extraction module 131 includes a first risk factor extraction module 131A for extracting a first risk factor from signal control information of one or more walking signals P installed at intersections and adjacent roads, intersections and A second risk factor extraction module (131B) extracting a second risk factor from the road environment of an adjacent road, and a third risk factor extraction module (131B) extracting a third risk factor from object information stopped or moving at an intersection and an adjacent road ( 131C), and a fourth risk factor extraction module 131D for classifying the area of the intersection and adjacent road into a plurality of sections and extracting a fourth risk factor according to each section.

The first risk factor extraction module 131A refers to a component that extracts a first risk factor from signal control information of one or more walking signals P installed at intersections and adjacent roads. The first risk factor extraction module 131A interlocks with the walking signal detection module 121 of the data detection unit 120 to obtain signal information or signal control information detected from a walking signal P installed at an intersection and an adjacent road. Through this, the first risk factor related to signal control can be extracted. Here, the first risk factor may refer to signal information output by the walking signal P in real time. Meanwhile, the first risk factor extraction module 131A may generate a real-time identification code based on the first risk factor. For example, when the walking signal P is outputting a green signal allowing pedestrians to cross, an identification code of 'G' corresponding to it can be generated in real time, and the walking signal P is a red signal. In case of outputting, it is possible to generate an identification code of 'R' corresponding to it in real time. In addition, one unit of the walking signal (P) is installed at a crosswalk located on a right turn path in the first area (A), and a crosswalk located on a right turn path in the 2-1 area (B). If one device is installed in , it detects each signal control information and outputs a green signal or a red signal, respectively, generating identification codes such as 'G1', 'R1', 'G2', and 'R2', respectively. can do.

The second risk factor extraction module 131B refers to a component that extracts a second risk factor from the road environment of intersections and adjacent roads. The second risk factor extraction module 131B interlocks with the road environment detection module 122 of the data detection unit 120, weather conditions near intersections and adjacent roads, current time, presence of illegally parked vehicles or street vendors on the roadside A second risk factor related to the back can be extracted. Here, the second risk factor may mean information about the presence or absence of bad weather, day/night classification, illegally parked vehicles, or existence of street vendors. Meanwhile, the second risk factor extraction module 131B may generate a real-time identification code based on the second risk factor. For example, when it is difficult to secure visibility due to heavy rain or a typhoon near an intersection and an adjacent road, or there is heavy snow or icy roads, an identification code of 'W' corresponding thereto can be generated in real time. On the other hand, when a time such as sunset or the like when securing a limited view arrives, an identification code of 'N' corresponding thereto may be generated. In addition, if there are additional obstacles such as illegally parked vehicles and street vendors on the side of the road on the right turn path that will restrict the visibility of right turn vehicles, an identification code of 'X' corresponding to them may be generated.

The third risk factor extraction module 131C refers to a configuration for extracting a third risk factor from information on objects that are stationary or moving at intersections and adjacent roads. The third risk factor extraction module 131C interworks with the object detection module 123 of the data detection unit 120, and the third risk factor associated with the information of each object element identified and determined in the roadside and sidewalk of the intersection and adjacent road risk factors can be extracted. Here, the third risk factor is information on each object element identified and determined by the object detection module 123, that is, a pedestrian identified and determined at an intersection, roadside of an adjacent road, and sidewalk showing a normal walking pattern. It may mean information about whether a person is a pedestrian, such as an elderly person, a child, or a drunken person, showing an abnormal gait pattern, or whether a person is riding a personal mobility vehicle such as a bicycle or an electric kickboard based on the shape, speed, and/or behavior pattern of an object. Meanwhile, the third risk factor extraction module 131C may generate a real-time identification code based on the third risk factor. For example, when a pedestrian with a normal walking pattern is detected, the identification code of 'P' is detected, when a pedestrian riding in the personal mobility is detected, an identification code of 'K', and when a pedestrian with an abnormal walking pattern is detected, 'I' The identification code of 'can be generated in real time.

The fourth risk factor extraction module 131D refers to a configuration that classifies the area of an intersection and an adjacent road into a plurality of sections and extracts a fourth risk factor according to each section. The fourth risk factor extraction module 131D interlocks with the road environment detection module 122 or the object detection module 123 of the data detection unit 120, and divides the road and adjacent sidewalk located on the right turn path into certain sections. , the entire compartment can be extracted as the fourth risk factor. Here, the fourth risk factor may refer to the entire specific section as described above. For example, as shown in FIG. Section B, the area of the sidewalk part in contact with the right turn path and connected to the crosswalk where pedestrians wait for crossing is Section C, the area of the sidewalk part across from Section C is Section E, the sidewalk part in contact with the right turn path Among the areas of , the area excluding the C area can be recognized and extracted as the D area, and the area of the sidewalk on the other side of the D area as the F area. On the other hand, the fourth risk factor extraction module (131D) may generate a real-time identification code based on the fourth risk factor, for example, when a pedestrian or the like is detected in the 'A' section, the identification code of 'A' , When no object is recognized in the A to F divisions, an identification code of 'O' can be generated in real time.

The code assignment module 132 refers to a configuration that assigns a risk criterion code based on one or more risk factors extracted by the risk factor extraction module 131 . Here, the one or more risk factors may mean the above-described real-time identification code. In this case, the code assignment module 132 may assign risk reference codes in real time based on real-time identification codes generated in real time.

For example, when a green signal is output from the walking signal P based on a certain point in time, the first risk factor extraction module 131A generates a real-time identification code of 'G'. At this time, when an object is identified on the crosswalk, the second risk factor extraction module (131B) generates a real-time identification code of 'A', and the third risk factor extraction module (131C) according to the type of the walking object Generate real-time identification codes such as 'P', 'K', and 'I'. On the other hand, when it is detected that there is heavy snowfall in the corresponding area and there is snow or ice on the road, the fourth risk factor extraction module 131D generates a real-time identification code of 'W'. In this case, the code assignment module 132 may generate a risk reference code by combining the real-time identification codes generated by the first risk factor extraction module 131A to the fourth risk factor extraction module 131D. For example, the real-time identification codes generated in the above example may form a combined code such as 'GAP-W', 'GAK-W', and 'GAI-W'.

Meanwhile, in the above example, if a pedestrian is detected in section C or section E, additionally 'GCP-W', 'GCK-W', 'GCI-W', 'GEP-W', 'GEK-W', 'GEI' Combination codes such as -W' can be formed. In this case, the code assignment module 132 may generate a risk reference code by selecting a priority among all combined code sets. For example, the priority of the identification codes generated by the fourth risk factor extraction module 131D is set based on alphabetical order from 'A' to 'F'. Therefore, when objects are detected on both the crosswalk and the adjacent sidewalk, all codes including real-time identification codes such as 'C' and 'E' except for 'A' are deleted according to the priority order. Meanwhile, the identification codes generated by the third risk factor extraction module 131C are prioritized in the order of 'I', 'K', and 'P'. Therefore, when both a normal pedestrian with a normal walking pattern and a drunken pedestrian with an abnormal walking pattern are detected in a crosswalk, all codes including real-time identification codes of 'P' or 'K' are erased. Therefore, in the case of the above example, the code of 'GAI-W' is selected and assigned as the risk criterion code in real time. The priority may be selected according to the risk of accident in entering the right-turning vehicle, and the manager may arbitrarily select and employ an appropriate item for selecting a specific code or assigning a priority.

The risk type determination module 133 refers to a component that determines the risk type of an intersection and an adjacent road based on the risk reference code assigned by the code assignment module 132 . As the risk reference code is assigned in real time by the code assignment module 132, the risk reference code is recognized and a risk type is selected in real time based on this. Danger types include, for example, the first hazard type that does not allow right turn signals and requires a pedestrian attention warning, the second hazard type that does not allow right turn signals but does not require a pedestrian attention warning, and the third hazard type that allows right turn signals but requires pedestrian attention warning It can be classified and selected as the 4th danger type, which allows the danger type, the right turn signal, and does not require a separate pedestrian attention warning. For example, if 'GA' is recognized in the above risk standard code, it is unconditionally the second risk type, if 'RA' is recognized, it is unconditionally the first risk type, and if 'GC' is recognized, 'GCI' is the second risk type. It can be classified as 2 risk type, 3 risk type for 'GCP', 4 risk type for 'RCP', and 3 risk type for 'RCP-W'. Based on the risk reference codes, it is possible to determine an appropriate risk type suitable for a corresponding road situation, thereby determining an appropriate degree of risk.

The traffic light control unit 140 refers to a configuration that controls the traffic light unit 200 according to the judgment of the risk determination unit 130 . To this end, the traffic light control unit 140 includes a control method determination module 141 for determining a control method of the traffic light unit 200 according to the degree of traffic risk determined by the risk determination unit 130, and the control method determination module It may include a signal output control module 142 for controlling the signal output of the traffic light unit according to the decision of (141).

The control method determination module 141 refers to a configuration that determines the control method of the traffic light unit 200 according to the degree of traffic risk determined by the risk determination unit 130 . As described above, the traffic risk level is based on the risk type determined by the risk type determination module 133, and may be determined according to the type of the risk type. Accordingly, the control method determination module 141 may determine a control method based on the real-time risk type determined by the risk type determination module 133 in conjunction with the risk type determination module 133 . For example, if the danger type determination module 133 determines the traffic danger type at a specific time as the first danger type, the control method determination module 141 signals the right turn entry prohibition signal from the traffic light unit 200 at that time accordingly. It is possible to determine a control method for simultaneously outputting a signal and a pedestrian attention signal. If the danger type determination module 133 determines the traffic danger type at a specific time as the third danger type, the control method determination module 141 signals a right turn entry possible signal at the traffic light unit 200 at that time accordingly. It is possible to determine a control method for simultaneously outputting a signal and a pedestrian attention signal.

The signal output control module 142 controls the signal output of the traffic light unit 200 according to the decision of the control method decision module 141, and the control method decision module 141 controls the signal output at a specific time point. When the control method of the unit 200 is determined, the control method determination module 141 can perform control of the traffic light unit 200 according to the corresponding method and control signal output. For example, if the control method determining module 141 determines the control method according to the first risk type as described above, the signal output control module 142 controls the traffic light unit 200 to control the signal unit 220 ) may output a right turn entry prohibition signal, and the driver attention alerting unit 230 may output a pedestrian alert signal.

The setting unit 150 is a component that manages the control unit 100. To this end, the setting unit 150 is a control setting module 151 that manages general settings such as on/off of the control unit 100. And, an algorithm setting module 152 for setting and managing matters necessary for calculation, analysis, and judgment of the data acquisition unit 110, data detection unit 120, risk determination unit 130 and traffic light control unit 140, It may include a risk determination setting module 153 for setting and managing matters necessary for the determination of the risk determination unit 130.

It refers to a configuration that manages matters corresponding to general settings in relation to traffic light control such as on/off of the setting unit 150 and the control unit 100.

The algorithm setting module 152 sets and manages algorithms, programs, etc. necessary for calculation, analysis, and judgment of the data acquisition unit 110, data detection unit 120, risk determination unit 130, and traffic light control unit 140. As a configuration, for example, the preprocessing module 112, the correction module 113, the road environment detection module 122, the object detection module 123, etc. can be used for preprocessing, analysis, postprocessing, object detection, etc. of images or videos. It may refer to a configuration that sets and manages existing algorithms or programs by performing operations such as insertion, installation, modification, and deletion.

The risk determination setting module 153 assigns real-time reference codes in the risk factor extraction module 131, code assignment module 132, and risk type determination module 133, code combination, prioritization between codes, risk It can refer to a configuration that sets and manages operations, formulas, and algorithms related to assignment of reference codes, classification and determination of risk types, insertion, modification, and deletion.

Hereinafter, an intelligent right turn traffic light system according to another embodiment of the present invention will be described. Hereinafter, descriptions of components common to those described above will be omitted.

As shown in FIG. 3 , an intelligent right turn traffic light system according to another embodiment of the present invention includes a photographing means 300 for acquiring images or images by photographing traffic conditions, road environments, and pedestrian conditions of intersections and adjacent roads, and , a traffic light unit 200 installed at a right turn lane of an intersection, and a control unit 100 that controls the traffic light unit 200, and the traffic light unit 200 includes a body unit 210 and the body unit 210 ) The signal unit 220 is formed on one side and outputs a signal under the control of the control unit 100, and the signal unit 220 is formed on the other side of the body unit 210 and pays attention to pedestrians under the control of the control unit 100. It is characterized in that it includes a pedestrian attention signal unit 240 for outputting a signal.

The pedestrian attention signal unit 240 is located on one side other than the one side where the signal unit 220 is formed in the main body 210, preferably the 2-1 area (B) or the 2-2 area (C). ) It means a configuration that is formed on one side of the direction looking at and outputs a caution signal to the pedestrian under the control of the control unit 100. To this end, the pedestrian attention signal unit 240 may include a visual notification unit 241 and an auditory notification unit 242.

The pedestrian caution signal unit 240 outputs a warning signal to the pedestrian under the control of the control unit 100 . The control unit 100 collects the image or video obtained from the photographing means 300 and the signal control information of the walking signal P through the configuration and coupling relationship as described above, and from this collects traffic conditions of intersections and adjacent roads. , road environment, pedestrian status, right-turning vehicle status approaching from the first area (A), etc. are detected, and based on this, the traffic risk level is calculated and determined, and the traffic light unit 200 is controlled. At this time, the risk determination unit 130 extracts risk factors in real time based on each detection information of the intersection and adjacent roads detected by the data detection unit 120, and assigns a real-time risk reference code based on the risk factors. , Based on this, the risk type of intersections and adjacent roads is determined in real time. As described above, the risk type can be classified and determined as the first risk type, the second risk type, the third risk type, and the fourth risk type, and the traffic light control unit 140 based on this, the traffic light unit ( 200), and at this time, the signal output control module 142 of the traffic light unit 200 can control the signal output of the pedestrian caution signal unit 240 together. However, the traffic light control unit 140 may control the signal output of the pedestrian caution signal unit 240 only when it detects an approaching vehicle turning right in the first area (A). To explain in more detail through an example based on the above criteria, for example, if the traffic risk type at a specific point in time is determined as the first risk type in the risk type determination module 133, the control method determination module 141 determines the corresponding At this point, the signal unit 220 simultaneously outputs a right turn entry prohibition signal and a pedestrian caution signal, and when an approaching right turn vehicle is detected in the first area (A), the pedestrian attention signal unit 240 simultaneously outputs the time It is possible to control the notification unit 241 and the auditory notification unit 242 to output a warning signal targeting pedestrians. If the danger type determination module 133 determines the traffic danger type at a specific time as the third danger type, the control method determination module 141 signals to allow right turn entry from the signal unit 220 at that time accordingly. and a pedestrian caution signal are simultaneously output, and when an approaching right-turning vehicle is detected in the first area (A), at the same time, the visual notification unit 241 of the pedestrian attention signal unit 240 displays a warning signal for pedestrians. can be controlled to output. On the other hand, if the danger type determination module 133 determines the traffic danger type at a specific time as the fourth danger type, the control method determination module 141 enters the right turn at the signal unit 220 at that time accordingly. Control is performed to output only enable signals, and the pedestrian attention signal unit 240 can be controlled not to output any signals. In this way, the control unit 100 controls the pedestrian attention signal unit 240 to interlock with the control of the signal unit 220 to output a signal for a right-turning vehicle entering the first area (A) and at the same time Signals associated with this can be output to pedestrians on nearby roads and sidewalks.

The visual notification unit 241 is a component that visually outputs a warning signal for entering a right-turning vehicle or crossing a pedestrian to a pedestrian, and is not particularly limited in any way as long as it is configured to generate a visual signal. For example, in FIG. As shown, it is possible to adopt a text-type electric signboard type configuration. The auditory notification unit 242 is a component that audibly outputs a warning signal for entering a right-turning vehicle to a pedestrian. The method is not particularly limited, and for example, a configuration such as outputting a human voice or mechanical sound or outputting a siren when entering a right-turning vehicle or crossing may be adopted.

In the above, the applicant has described various embodiments of the present invention, but such embodiments are only one embodiment for implementing the technical idea of the present invention, and no changes or modifications are made as long as the technical idea of the present invention is implemented. It should be construed as falling within the scope of the present invention.

100: control unit 200: traffic light unit 300: photographing means
210: body part 220: signal part 230: driver attention part
240: pedestrian warning signal unit 241: visual notification unit 242: auditory notification unit
110: data acquisition unit 120: data detection unit 130: risk judgment unit
140: traffic light control unit 150: setting unit
111: camera interlocking module 112: pre-processing module 113: correction module
121: pedestrian signal detection module 122: road environment detection module 123: object detection module
122A: weather information detection module 122B: time information detection module 122C: peripheral environment detection module
123A: object discrimination module 123B: object recognition information acquisition module 123C: object type determination module
131: risk factor extraction module 132: code assignment module 133: risk type determination module
131A: first risk factor extraction module 131B: second risk factor extraction module 131C: third risk factor extraction module 131D: fourth risk factor extraction module
141: control method determination module 142: signal output control module 151: control setting module
152: algorithm setting module 153: risk judgment setting module

Claims (10)

A photographing means for obtaining an image or video by photographing traffic conditions, road environments, and pedestrian conditions of intersections and adjacent roads;
A traffic light unit installed at the right turn corner of the intersection;
As a right turn traffic light system including a control unit for controlling the traffic light unit,
The traffic light unit includes a main body and a signal unit formed on one side of the main body and outputting a signal under the control of the controller,
The control unit includes a data acquisition unit that acquires image or image information of an intersection and an adjacent road in association with the photographing unit, and reads the image or image information obtained from the data acquisition unit to determine the traffic conditions of the intersection and adjacent roads, the road A data detection unit that analyzes and detects the environment and pedestrian status, and a risk determination unit that calculates and determines the degree of traffic risk of intersections and adjacent roads based on the data analyzed and detected by the data detection unit, and according to the judgment of the risk determination unit It includes a traffic light control unit for controlling the traffic light unit and a setting unit for managing the control unit,
The risk assessment department
A risk factor extraction module that extracts one or more risk factors from the detection information of intersections and adjacent roads detected by the data detection unit, and a code assignment module that assigns a risk standard code based on the one or more risk factors extracted from the risk factor extraction module. and a hazard type determination module for determining the hazard type of the intersection and adjacent roads based on the hazard reference code assigned by the code assignment module.
delete The method of claim 1, wherein the data acquisition unit
A camera interlock module that collects image or video information from the photographing means in real time, a pre-processing module that collects and recognizes background information of the intersection and adjacent road where the traffic light system is installed, weather change of the intersection and adjacent road, generation of shadows, An intelligent right turn signal light system comprising a correction module for correcting obstacles such as minor signal disturbances.
The method of claim 1, wherein the data detection unit
A walking signal detection module for detecting signal control information of the walking signal in conjunction with one or more walking signals installed in the intersection and adjacent roads, and the road environment of the intersection and adjacent roads based on the image or image information acquired by the data acquisition unit. An intelligent right turn signal light system comprising a road environment detection module for detecting and an object detection module for detecting a stationary or moving object at an intersection and an adjacent road based on the image or video information acquired by the data acquisition unit.
The method of claim 4, wherein the road environment detection module
A weather information detection module for detecting the weather conditions of intersections and adjacent roads, a time information detection module for detecting time information, and a surrounding environment detection module for detecting the existence of parking vehicles and street vendors at intersections and adjacent roads. Characterized in that, an intelligent right turn traffic light system.
The method of claim 4, wherein the object detection module
An object discrimination module for determining an object element from the image or video information acquired by the data acquisition unit, and an object recognition module for obtaining any one or more information of the speed, size, shape, or movement type of the object element determined by the object discrimination module. An intelligent right turn traffic light system comprising an information acquisition module and an object type determination module for discriminating and classifying the type of each object element based on the information acquired by the object recognition information acquisition module.
delete The method of claim 1, wherein the risk factor extraction module
A first risk factor extraction module for extracting a first risk factor from signal control information of one or more walking signals installed at an intersection and adjacent roads, and a second risk factor extraction module for extracting a second risk factor from the road environment of intersections and adjacent roads module, and a third risk factor extraction module that extracts a third risk factor from information on objects that are stationary or moving at intersections and adjacent roads, and classifies the area of intersections and adjacent roads into a plurality of sections, and the fourth risk according to each section. Characterized in that it comprises a fourth risk factor extraction module for extracting factors, intelligent right turn traffic light system
The method of claim 1, wherein the traffic light control unit
A control method determination module for determining the control method of the traffic light unit according to the degree of traffic risk determined by the risk determination unit, and a signal output control module for controlling the signal output of the traffic light unit according to the determination of the control method determination module. Features, intelligent right turn traffic light system.
The method of claim 1, wherein the setting unit
A control setting module that manages general settings of the control unit, an algorithm setting module that sets and manages matters necessary for calculation, analysis, and judgment of the data acquisition unit, data detection unit, and traffic light control unit, and An intelligent right turn traffic light system comprising a risk determination setting module for setting and managing matters.

Images