Signal lamp automatic control method for road plane intersection, electronic device and storage medium

Abstract

The invention relates to the technical field of traffic signal control, and provides an automatic signal lamp control method for a road plane intersection, an electronic device and a storage medium. When the road plane intersection has an exit meeting the congestion condition, determining the predicted congestion time length of the current exit target area according to the traffic flow data, and obtaining the remaining time length of the signal lamp at the j-th entrance corresponding to the current exit target area in the current signal period from the turn-on of the green light, and performing classification decision according to the size relationship between the predicted congestion duration and the residual duration. According to the invention, the method achieves the precise and automatic control of the entrance signal lamp according to the exit traffic state, prevents the exit congestion from extending to the plane intersection, does not cause the traffic congestion in other smooth directions, greatly improves the traffic capacity of the road plane intersection, and is wide in application prospect and social value.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic signal control, and in particular to an automatic control method for signal lights at a road level intersection, an electronic device and a storage medium. Background Art

[0002] Traffic congestion is one of the serious problems facing cities. In particular, urban intersections are often the starting point of congestion, such as intersections adjacent to highway interchanges and expressway entrances and exits, and intersections at both ends of urban cross-river passages. The use of signal light control can improve the orderliness of intersections and reduce traffic congestion. With the increase in traffic volume, congestion in the downstream sections of some intersections will spread to the intersection. If the signal timing controlled by the signal light is not reasonably adjusted, or there is no restriction on the passage of cars in the blocked direction, the vehicles in that direction will be blocked from the road section to the intersection, and vehicles in other directions will not be able to pass through the intersection, causing the entire intersection to be blocked, and then spread to the upstream sections, forming regional traffic congestion. The cause of this congestion is the congestion of the downstream section of the intersection. If the signal light of the intersection is not reasonably modified, the congestion will develop into the intersection, and the congestion will not be prevented from spreading to the entire intersection, causing traffic in all directions to be in a state of congestion.

[0003] In the prior art, there have been many studies on congestion at planar intersections, but they are mainly concentrated in the following three methods: the first method is to control the entrances of all planar intersections with red lights to restrict vehicle entry after congestion occurs in the planar intersection (corresponding to the physical area); the second method is to increase the timing of signal lights at the planar intersection to increase the green light time of the corresponding congested phase according to the traffic congestion level of the entrance section; the third method is to deploy radars at each entrance and exit, and adopt an adaptive control system based on timely traffic flow data, such as a holographic intersection. The defect of this type of intersection is that when congestion occurs, the information is conveyed to the traffic police, and the traffic police need to go to the scene to direct and clear the congestion to eliminate the congestion.

[0004] Among them, the plane intersection is divided into functional area and physical area. The first method is to determine and eliminate the congestion based on the vehicles in the physical area of ​​the plane intersection. This method is to restrict the entry of vehicles from all entrances after the plane intersection is completely blocked. Only when all vehicles in the physical area of ​​the plane intersection, that is, the central area, have exited, can the entrance vehicles be released. If there is no intervention by the traffic police, this method is likely to cause long-term congestion of the plane intersection, seriously lose the traffic capacity of the plane intersection, and further increase the scope of traffic congestion.

[0005] The second method is to simply increase the timing of traffic lights to increase the green light time in the corresponding congested phase. This method will increase the waiting time for traffic on roads in other directions, which will easily lead to congestion on roads in other directions and finally cause regional congestion.

[0006] In view of this, it is necessary to propose a method, an electronic device and a storage medium for automatically controlling traffic lights at a road intersection to solve or at least alleviate the above-mentioned defects. Summary of the invention

[0007] The main purpose of the present invention is to provide a method, an electronic device and a storage medium for automatically controlling signal lights at a road level intersection, so as to solve the problem in the prior art that road level intersections are prone to traffic jams and seriously lose the traffic capacity of the level intersection.

[0008] To achieve the above object, the present invention provides a method for automatically controlling a signal light at a road intersection, comprising the following steps: S1, at the first time node of the beginning of the current signal cycle, obtaining traffic flow data of each exit target area of ​​the road level intersection in the previous signal cycle, and judging whether the road level intersection has an exit that meets the congestion condition according to the traffic flow data; S2, when the road intersection has an exit that meets the congestion condition, determining the estimated congestion duration of the current exit target area according to the traffic flow data ; S3, obtain the remaining time for the signal light at the jth entrance corresponding to the current exit target area to turn on the green light in the current signal cycle ; Where j≥1, the initial value of j is 1, and j is a positive integer; S4, determine the remaining time Is it shorter than the expected congestion duration? ; If yes, go to step S51~S54, if no, go to step S55; S51, obtaining the standard green light on time of the signal light at the jth entrance corresponding to the current exit target area , and calculate the expected congestion duration and remaining time The difference between , and then calculate the standard green light opening time Sum and Difference The difference between ; S52, judge the difference Whether it is greater than the minimum setting duration of the green light; S53, in the difference When the green light duration is greater than the minimum setting duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to , and at the second time node at the end of the current signal cycle, the green light duration is increased from Restore to the standard green light on time ; S54, in the difference When the green light duration is less than or equal to the minimum set duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to the red light duration, and the green light duration is restored to the standard green light duration at the third time node at the end of the current signal cycle. ; S55, determining that the current exit target area is in a non-congested state when the traffic light at the j-th entrance corresponding to the current exit target area is green, and maintaining the current traffic light cycle of the traffic light at the j-th entrance corresponding to the current exit target area to continue running; S6, assign j+1 to j and return to step S3.

[0009] Preferably, the step S1 specifically includes the following steps: S11, at the first time node of the beginning of the current signal cycle, obtaining the traffic flow image data of each exit target area of ​​the road plane intersection collected by the image acquisition component in the previous signal cycle; wherein the image acquisition component includes a plurality of image acquisition devices corresponding to the exit target areas one by one, and the image acquisition devices are arranged above the exit target areas and are used to collect road image data of the exit target areas; S12, determining the average vehicle queue length of the corresponding exit target area in the previous signal cycle according to the traffic flow image data collected by each image acquisition device; wherein the exit target area is a rectangular area, the proximal edge line is the import stop line corresponding to the exit, the two side edges are the road edges on both sides of the exit road, the starting position of the queue is the distal edge line corresponding to the proximal edge line, and the vehicle queue length is the extension length of the vehicle from the distal edge line toward the proximal edge line; S13, determining whether the road intersection has an exit with an average vehicle queue length greater than a preset length; S14, when the road intersection has an exit with an average vehicle queue length greater than a preset length, obtaining an average vehicle speed in the current exit target area in the previous signal cycle, and obtaining the number of head-to-tail distances between two adjacent vehicles in the current exit target area in the previous signal cycle that are less than a preset distance; S15, determining whether the average vehicle speed is less than a preset speed, and determining whether the number is greater than a preset value; S16, when both of the average vehicle speed being less than a preset speed and the number being greater than a preset value are established at the same time, it is determined that the current exit target area meets the congestion condition, and it is determined that the road level intersection has an exit that meets the congestion condition.

[0010] Preferably, the step S15 further includes the following steps: S17, when neither the average vehicle speed is less than a preset speed nor the number is greater than a preset value, it is determined that the current exit target area does not meet the congestion condition, and it is determined that the road level intersection does not have an exit that meets the congestion condition.

[0011] Preferably, the step S13 further includes the following steps: S18: When the road intersection does not have an exit with an average vehicle queue length greater than a preset length, it is determined that the road intersection does not have an exit that meets the congestion condition.

[0012] Preferably, the step S12 specifically includes the following steps: S121, extracting an effective road area image of a road image in the traffic flow image data; wherein the traffic flow image data includes a plurality of road images taken at preset time intervals; S122, determining the corresponding vehicle queue length according to the valid road area image; S123, using the formula Determine the average vehicle queue length of the corresponding exit target area in the previous signal cycle ; Where N is the number of road images of traffic flow image data, is the length of the vehicle queue corresponding to the i-th road image.

[0013] Preferably, the step S2 specifically includes the following steps: Using formula Determine the expected congestion duration for the current exit target area ;in, , , , To calculate the coefficient, is the average vehicle speed in the current exit target area during the previous signal cycle, It is the number of times the head-to-tail distance between two adjacent vehicles in the current exit target area during the previous signal cycle is less than the preset distance.

[0014] Preferably, the remaining time in step S3 Obtained through the following steps: Using formula Get the remaining time ;in, is the start time when the green light of the signal light at the jth entrance corresponding to the current exit target area is turned on in the current signal cycle, The first time node at the beginning of the current signal cycle.

[0015] Preferably, the second time node and the third time node are the same moment.

[0016] The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned method for automatically controlling signal lights at a road intersection.

[0017] The present invention also provides a storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for automatically controlling signal lights at a road intersection.

[0018] Compared with the prior art, the present invention has the following beneficial effects: The present invention provides a method, electronic device and storage medium for automatically controlling traffic lights at a road intersection. By acquiring traffic flow data of each exit target area of ​​the road intersection in the previous signal cycle, when the road intersection has an exit that meets the congestion condition, the estimated congestion duration of the current exit target area is determined according to the traffic flow data, and the remaining time from the green light turning on of the traffic light at the jth entrance corresponding to the current exit target area in the current signal cycle is acquired, and a classification decision is made according to the relationship between the estimated congestion duration and the remaining duration. The present application realizes precise and automated control of the import traffic lights according to the exit traffic status, avoids the extension of the exit congestion to the intersection, and does not cause traffic congestion in other unobstructed directions, greatly improves the traffic capacity of the road intersection, can effectively alleviate urban traffic congestion, improve the traffic efficiency of the intersection, and reduce the occurrence of traffic accidents, and has broad application prospects and social value. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying creative work.

[0020] Figure 1 It is a schematic diagram of a flow chart in one embodiment of the present invention; Figure 2This is a flowchart of the specific steps included in step S1 in one embodiment of the present invention; Figure 3 A schematic diagram of the signal cycle of a traffic light at a road intersection before optimization using the solution of the present application; Figure 4 A software simulation diagram of a road intersection before optimization using the solution of the present application; Figure 5 A schematic diagram of the signal cycle of a traffic light at a road intersection after being optimized using the solution of the present application; Figure 6 It is a software simulation diagram of a road intersection after being optimized using the solution of the present application.

[0021] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0022] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] In the present invention, the descriptions involving "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0025] Please refer to the attached Figure 1 to Figure 2 In one embodiment of the present invention, a method for automatically controlling a signal light at a road intersection comprises the following steps: S1, at the first time node of the beginning of the current signal cycle, obtaining traffic flow data of each exit target area of ​​the road level intersection in the previous signal cycle, and judging whether the road level intersection has an exit that meets the congestion condition according to the traffic flow data; It can be understood that a road intersection refers to a location where two or more roads intersect at the same plane, such as a cross, T-shaped, Y-shaped intersection, etc.; an exit target area refers to a specific area within a road intersection that a vehicle enters after leaving the intersection, such as a rectangular area starting from the stop line at the exit and extending forward along the road. By detecting and analyzing the traffic flow data in this area, it is determined whether the corresponding exit target area meets the congestion condition; traffic flow data includes information such as traffic flow, vehicle speed, vehicle distance, and vehicle type, which is used to evaluate the traffic conditions and operating efficiency of road intersections and exit target areas. Traffic flow data can be obtained through sensor technology, vision, and other means. The signal lights (traffic lights) at the road intersections are usually operated according to the set signal cycle. The present application obtains the traffic flow data of each exit target area of ​​the road intersection in the previous signal cycle at the first time node of the current signal cycle, for example, the moment when the previous signal cycle just enters the next signal cycle. The collected traffic flow data is used to analyze each exit target area of ​​the road intersection to determine whether there is an exit that meets the preset congestion conditions. If so, that is, there is congestion at the road intersection, and corresponding traffic management measures need to be taken to alleviate it.

[0026] S2, when the road intersection has an exit that meets the congestion condition, determining the estimated congestion duration of the current exit target area according to the traffic flow data When it is determined that there is an exit that meets the congestion conditions at the road intersection, the acquired traffic flow data is used to predict the length of time the current exit target area will remain congested through the specific embodiments described below or through historical data analysis, traffic flow model simulation or real-time data monitoring.

[0027] S3, obtain the remaining time for the signal light at the jth entrance corresponding to the current exit target area to turn on the green light in the current signal cycle ; Where j≥1, the initial value of j is 1, and j is a positive integer; It should be noted that a certain exit in a road intersection generally corresponds to multiple entrances. For example, for a cross intersection, a certain exit corresponds to the first entrance for going straight, the second entrance for turning left, and the third entrance for turning right. In order to indicate the situation of multiple entrances, the present application uses variable j for identification. As a preferred example, since right-turning vehicles enter the exit, even if the exit is blocked, right-turning vehicles will not enter the middle physical area of ​​the road intersection, and will not block the middle physical area of ​​the road intersection. Therefore, the right-turn entrance can be ignored; Furthermore, the remaining time in step S3 Obtained through the following steps: Using formula Get the remaining time ;in, is the start time when the green light of the signal light at the jth entrance corresponding to the current exit target area is turned on in the current signal cycle, It is the first time node at the beginning of the current signal cycle. It is understandable that within a signal cycle, the green light turn-on time of a certain signal light can be directly determined, and the first time node can be the moment when the next signal cycle just begins from the previous signal cycle. Therefore, the remaining time of a certain signal light before the green light turns on can be directly determined through this formula, and the remaining time plays an important reference role in whether to adjust and optimize the green light turn-on time in the future.

[0028] S4, determine the remaining time Is it shorter than the expected congestion duration? ; If yes, go to step S51~S54, if no, go to step S55; S51, obtaining the standard green light on time of the signal light at the jth entrance corresponding to the current exit target area , and calculate the expected congestion duration and remaining time The difference between , and then calculate the standard green light opening time Sum and Difference The difference between ; Specifically, the green light standard opening time This duration is preset and can be a standard applicable time determined based on factors such as the geometric design of the intersection, traffic flow, road speed limit, etc. For example, the standard green light opening duration can be used during non-congested periods. For example, the standard green light duration of a traffic light at a certain entrance is set to 30 seconds, and this time is adjusted in a targeted manner when congestion occurs; Difference Estimated congestion duration and remaining time The difference between can be used to determine whether the current exit target area is in a congested state when the traffic light at the jth entrance turns green. If it is in a congested state, how much congestion time is left when the green light turns on, or whether it is in a non-congested state (unblocked state). Difference Green light standard opening time Sum and Difference The difference between them can determine the relationship between the green light setting time and the remaining congestion time of the exit when the green light is turned on, so as to carry out automatic control; S52, judge the difference Whether it is greater than the minimum setting duration of the green light; S53, in the difference When the green light duration is greater than the minimum setting duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to , and at the second time node at the end of the current signal cycle, the green light duration is increased from Restore to the standard green light on time ; It should be noted that the minimum green light duration is set to ensure the normal passage of pedestrians and vehicles. For example, the minimum green light duration of the traffic light at a certain entrance is set to 15s. When it is greater than the minimum green light duration, it means that when the congestion state of the exit target area changes to a non-congested state, there is still a green light time, and this green light time is greater than the minimum green light duration. At this time, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to , compared with the original green light standard opening time , the green light duration is adjusted to When , the green light time is shortened, which can not only ensure that the exit target area will not be blocked, but also release a certain number of vehicles at the jth entrance, greatly improving the traffic capacity of the road intersection.

[0029] At the second time point at the end of the current signal cycle, the green light duration is changed from Restore to the standard green light on time In order to facilitate the automatic control of the next signal cycle, the second time node can be the moment when the current signal cycle just ends, which is equivalent to timely reset. When entering the next signal cycle, the above steps are used again for analysis, judgment and control.

[0030] S54, in the difference When the green light duration is less than or equal to the minimum set duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to the red light duration, and the green light duration is restored to the standard green light duration at the third time node at the end of the current signal cycle. ; It is understandable that the difference When it is less than or equal to the minimum set green light duration, it means that when the congestion state of the exit target area changes to a non-congestion state, the green light duration still has a green light time, and this green light time is less than the minimum set green light duration, which cannot guarantee the normal passage of pedestrians and vehicles. At this time, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to the red light duration, that is, vehicles at the jth entrance are prohibited from passing, so as to avoid further aggravating the congestion of the current exit target area, which is conducive to eliminating congestion at road intersections and the current exit target area. As a preferred example, the second time node and the third time node are the same moment. At the third time node at the end of the current signal cycle, the green light duration is restored to the standard green light on duration. , which is equivalent to timely resetting. When entering the next signal cycle, the above steps are used again to analyze, judge and control.

[0031] S55, determining that the current exit target area is in a non-congested state when the traffic light at the j-th entrance corresponding to the current exit target area is green, and maintaining the current traffic light cycle of the traffic light at the j-th entrance corresponding to the current exit target area to continue running; In the remaining time Greater than or equal to the expected congestion duration That is, when the traffic light at the jth entrance turns green, the current exit target area has been relieved by itself and has changed from a congested state to a non-congested state. At this time, the current traffic light cycle of the traffic light at the jth entrance corresponding to the current exit target area can be maintained to continue running, that is, the vehicle at the jth entrance can be released, which greatly improves the traffic capacity of the road intersection.

[0032] S6, assign j+1 to j and return to step S3.

[0033] Combined with the above, the current export target area usually corresponds to multiple imports, so j+1 is assigned to j, the value of variable j is updated to increase by 1, and the next import is analyzed, judged, and controlled according to the above steps.

[0034] In addition, if there are multiple exits that meet the congestion conditions, the conditions of other exits are the same as the current exit, and the above steps can be followed.

[0035] In the present application, by obtaining the traffic flow data of each exit target area of ​​the road intersection in the previous signal cycle, when the road intersection has an exit that meets the congestion conditions, the estimated congestion duration of the current exit target area is determined according to the traffic flow data, and the remaining time of the signal light at the jth entrance corresponding to the current exit target area before the green light turns on in the current signal cycle is obtained, and a classification decision is made according to the relationship between the estimated congestion duration and the remaining duration. The present application realizes precise and automated control of the import signal lights according to the exit traffic status, avoids the extension of the exit congestion to the intersection, and does not cause traffic congestion in other unobstructed directions, greatly improving the traffic capacity of the road intersection, and has broad application prospects and social value.

[0036] like Figure 2 As shown, as a preferred implementation, step S1 specifically includes the following steps: S11, at the first time node of the beginning of the current signal cycle, obtaining the traffic flow image data of each exit target area of ​​the road plane intersection collected by the image acquisition component in the previous signal cycle; wherein the image acquisition component includes a plurality of image acquisition devices corresponding to the exit target areas one by one, and the image acquisition devices are arranged above the exit target areas and are used to collect road image data of the exit target areas; The image acquisition component includes a plurality of image acquisition devices, each exit target area is provided with an image acquisition device corresponding thereto, and the image acquisition device is installed above each exit target area to capture a complete picture of vehicles in the exit target area exiting the intersection, so as to obtain traffic flow image data of the exit target area; S12, determining the average vehicle queue length of the corresponding exit target area in the previous signal cycle according to the traffic flow image data collected by each image acquisition device; wherein the exit target area is a rectangular area, the proximal edge line is the import stop line corresponding to the exit, the two side edges are the road edges on both sides of the exit road, the starting position of the queue is the distal edge line corresponding to the proximal edge line, and the vehicle queue length is the extension length of the vehicle from the distal edge line toward the proximal edge line; As a preferred implementation, the step S12 specifically includes the following steps: S121, extracting an effective road area image of a road image in the traffic flow image data; wherein the traffic flow image data includes a plurality of road images taken at preset time intervals; S122, determining the corresponding vehicle queue length according to the valid road area image; S123, using the formula Determine the average vehicle queue length of the corresponding exit target area in the previous signal cycle ; Where N is the number of road images of traffic flow image data, is the length of the vehicle queue corresponding to the i-th road image.

[0037] Specifically, from the traffic flow image data containing multiple road images, the effective road area in each image is extracted. The effective road area is preferably the part of the image that actually contains road information, excluding unnecessary background or interference images. The traffic flow image data is obtained by continuously shooting by an image acquisition device (such as a camera) within a preset time interval. Each image captures the traffic conditions on the road at a certain moment. The preset time interval can be fixed, for example, once per second.

[0038] The length of the vehicle queue can be obtained by extracting the length of the queued vehicles in the effective road area image. This part can be determined by mature technical means and will not be elaborated here; each road image corresponds to a vehicle queue length at a corresponding moment, so the above formula can be used to calculate the average vehicle queue length of the exit target area in the previous signal cycle .

[0039] S13, determining whether the road intersection has an exit with an average vehicle queue length greater than a preset length; S14, when the road intersection has an exit with an average vehicle queue length greater than a preset length, obtaining an average vehicle speed in the current exit target area in the previous signal cycle, and obtaining the number of head-to-tail distances between two adjacent vehicles in the current exit target area in the previous signal cycle that are less than a preset distance; It should be noted that when there is an exit with an average vehicle queue length greater than the preset length at a road intersection, for example, the length of the exit target area is 30m and the preset length is 15m, if the average vehicle queue length exceeds 15m, further judgment is required. If it does not exceed 15m, it means that there are fewer vehicles downstream and it is not in a congested state. Similarly, the vehicle speed can be obtained by obtaining the distance and time interval of the same vehicle in two images, and the number of vehicles in each image can also be obtained, so the average vehicle speed of the current exit target area in the previous signal cycle can be determined; the head-to-tail distance between two adjacent vehicles can also be directly obtained through mature image algorithms, which will not be repeated here, so the number of head-to-tail distances between two adjacent vehicles in the current exit target area in the previous signal cycle that is less than the preset distance can be obtained.

[0040] S15, determining whether the average vehicle speed is less than a preset speed, and determining whether the number is greater than a preset value; S16, when both of the average vehicle speed being less than a preset speed and the number being greater than a preset value are established at the same time, it is determined that the current exit target area meets the congestion condition, and it is determined that the road level intersection has an exit that meets the congestion condition.

[0041] It is worth noting that when the vehicle speed is fast (for example, greater than the preset speed), the distance between the head and tail of the vehicles is small, which means that many vehicles are passing through the intersection quickly at this time, and the distance between the head and tail of the vehicles is large, which means that a few vehicles are passing through the intersection at a faster speed. In these two cases, since the average vehicle speed is fast, the intersection is smooth and there is no need to intervene in the green light operation time of the exit in that direction. When the vehicle speed is slow and the distance between the head and tail of the vehicles at the intersection is small (for example, less than the preset threshold), it means that a large number of vehicles are congested at the intersection and need to be cleared in time; when the vehicle speed is low and the distance between the head and tail of the vehicles is large, it means that many vehicles are driving at a low speed at the intersection. This situation is called slow movement. Since the intersection is not congested, vehicles can use the yellow light buffer time to exit the intersection, so there is no need to guide them.

[0042] Furthermore, the step S15 further includes the following steps: S17, when neither the average vehicle speed is less than a preset speed nor the number is greater than a preset value, it is determined that the current exit target area does not meet the congestion condition, and it is determined that the road level intersection does not have an exit that meets the congestion condition.

[0043] Furthermore, the step S13 further includes the following steps: S18: When the road intersection does not have an exit with an average vehicle queue length greater than a preset length, it is determined that the road intersection does not have an exit that meets the congestion condition.

[0044] As a preferred implementation, step S2 specifically includes the following steps: Using formula Determine the expected congestion duration for the current exit target area ;in, , , , To calculate the coefficient, is the average vehicle speed in the current exit target area during the previous signal cycle, It is the number of times the head-to-tail distance between two adjacent vehicles in the current exit target area during the previous signal cycle is less than the preset distance.

[0045] It is worth noting that the estimated congestion duration is the dependent variable, the average vehicle speed The slower the traffic, the more congested it is. The more there are, the more congested it is. When the average queue length is longer, the more congested it is. , , , In order to calculate the coefficient, multiple sets of historical data can be obtained in advance, including the average vehicle speed historical data set, the average vehicle speed historical data set, the number historical data set, and the actual recorded congestion duration, so the corresponding coefficient can be obtained by least squares method, gradient descent method or neural network training. , , , Based on this formula, the average vehicle speed in the current signal cycle can be determined ,quantity When the average vehicle queue length Then you can get the estimated congestion duration of the current exit target area. , so that the expected congestion duration can be quickly determined, facilitating subsequent decision-making.

[0046] As a preferred example, 5 sets of historical data are shown in Table 1 below: The present invention also provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the above-mentioned method for automatically controlling signal lights at a road intersection.

[0047] The present invention also provides a storage medium, wherein the storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned method for automatically controlling a signal light at a road level intersection are implemented. It can be understood that when the computer program is executed by the processor, the above-mentioned method for automatically controlling a signal light at a road level intersection is implemented, so all embodiments of the above-mentioned method are applicable to the storage medium, and can achieve the same or similar beneficial effects.

[0048] In order to facilitate those skilled in the art to further understand the technical solution of the present application, the present application also provides the following specific examples for illustration: In this application, PTV-VISSIM software was used to conduct traffic simulation at the signal-controlled intersection of Xiangya Road and Furong North Road in the Xiangya Road Tunnel Project.

[0049] The intersection of Xiangya Road and Furong North Road is located in the old city of Changsha. It is surrounded by high-traffic land such as Xiangya Hospital and Fuxing Shopping Mall. It is also the first level intersection between the main exit of Xiangya Road Tunnel and the ground road. It is always congested. The west exit section is often congested and extends to the intersection. This time, the signal cycle of the intersection was optimized by using the traffic signal automatic control technology of this application through PTV-VISSIM software, and the effects before and after optimization were compared.

[0050] First, determine whether the road intersection has an exit that meets the congestion conditions. According to the simulation of the current traffic flow data before optimization, the west intersection is at a D-level service level and is in a congested state.

[0051] According to the simulation operation, the traffic flow data of the west exit is read to determine the expected congestion duration, as shown in Table 2 below: Get the remaining time before the east entrance traffic light turns green in the current signal cycle is 33.75s. From this we can determine the remaining time Shorter than expected congestion duration (33.75s<37.75s).

[0052] Calculate the difference: = - =37.75-33.75=4s, = - =34-4=30s From this, we can judge that the difference is greater than the minimum setting time of the green light, which is 15s.

[0053] Therefore, the green light duration of the east entrance is adjusted to , that is 30s.

[0054] In the same way, the timing of the left turn at the south entrance is optimized to 28s. For details, please refer to the attached Figures 3 to 6 It can be seen that after the overall optimization, the congestion state of the west exit no longer extends to the intersection.

[0055] The above are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereto. Any equivalent structure or equivalent process transformation made by using the contents of the specification and drawings of the present invention, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for automatically controlling a signal light at a road intersection, characterized in that: The following steps are involved: S1, at the first time node of the beginning of the current signal cycle, obtaining traffic flow data of each exit target area of ​​the road level intersection in the previous signal cycle, and judging whether the road level intersection has an exit that meets the congestion condition according to the traffic flow data; S2, when the road intersection has an exit that meets the congestion condition, determining the estimated congestion duration of the current exit target area according to the traffic flow data ; S3, obtain the remaining time for the signal light at the jth entrance corresponding to the current exit target area to turn on the green light in the current signal cycle ; Where j≥1, the initial value of j is 1, and j is a positive integer; S4, determine the remaining time Is it shorter than the expected congestion duration? ; If yes, go to step S51~S54, if no, go to step S55; S51, obtaining the standard green light on time of the signal light at the jth entrance corresponding to the current exit target area , and calculate the expected congestion duration and remaining time The difference between , and then calculate the standard green light opening time Sum and Difference The difference between ; S52, judge the difference Whether it is greater than the minimum setting duration of the green light; S53, in the difference When the green light duration is greater than the minimum setting duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to , and at the second time node at the end of the current signal cycle, the green light duration is increased from Restore to the standard green light on time ; S54, in the difference When the green light duration is less than or equal to the minimum set duration of the green light, the green light duration of the signal light at the jth entrance corresponding to the current exit target area is adjusted to the red light duration, and the green light duration is restored to the standard green light duration at the third time node at the end of the current signal cycle. ; S55, determining that the current exit target area is in a non-congested state when the traffic light at the j-th entrance corresponding to the current exit target area is green, and maintaining the current traffic light cycle of the traffic light at the j-th entrance corresponding to the current exit target area to continue running; S6, assign j+1 to j and return to step S3.

2. The method for automatically controlling traffic lights at a road intersection according to claim 1, characterized in that: The step S1 specifically includes the following steps: S11, at the first time node of the beginning of the current signal cycle, obtaining the traffic flow image data of each exit target area of ​​the road plane intersection collected by the image acquisition component in the previous signal cycle; wherein the image acquisition component includes a plurality of image acquisition devices corresponding to the exit target areas one by one, and the image acquisition devices are arranged above the exit target areas and are used to collect road image data of the exit target areas; S12, determining the average vehicle queue length of the corresponding exit target area in the previous signal cycle according to the traffic flow image data collected by each image acquisition device; wherein the exit target area is a rectangular area, the proximal edge line is the import stop line corresponding to the exit, the two side edges are the road edges on both sides of the exit road, the starting position of the queue is the distal edge line corresponding to the proximal edge line, and the vehicle queue length is the extension length of the vehicle from the distal edge line toward the proximal edge line; S13, determining whether the road intersection has an exit with an average vehicle queue length greater than a preset length; S14, when the road intersection has an exit with an average vehicle queue length greater than a preset length, obtaining an average vehicle speed in the current exit target area in the previous signal cycle, and obtaining the number of head-to-tail distances between two adjacent vehicles in the current exit target area in the previous signal cycle that are less than a preset distance; S15, determining whether the average vehicle speed is less than a preset speed, and determining whether the number is greater than a preset value; S16, when both of the average vehicle speed being less than a preset speed and the number being greater than a preset value are established at the same time, it is determined that the current exit target area meets the congestion condition, and it is determined that the road level intersection has an exit that meets the congestion condition.

3. The automatic control method of traffic lights at a road intersection according to claim 2 is characterized in that: The step S15 further includes the following steps: S17, when neither the average vehicle speed is less than a preset speed nor the number is greater than a preset value, it is determined that the current exit target area does not meet the congestion condition, and it is determined that the road level intersection does not have an exit that meets the congestion condition.

4. The method for automatically controlling traffic lights at a road intersection according to claim 3, characterized in that: The step S13 further includes the following steps: S18: When the road intersection does not have an exit with an average vehicle queue length greater than a preset length, it is determined that the road intersection does not have an exit that meets the congestion condition.

5. The method for automatically controlling traffic lights at a road intersection according to claim 2, characterized in that: The step S12 specifically includes the following steps: S121, extracting an effective road area image of a road image in the traffic flow image data; wherein the traffic flow image data includes a plurality of road images taken at preset time intervals; S122, determining the corresponding vehicle queue length according to the valid road area image; S123, using the formula Determine the average vehicle queue length of the corresponding exit target area in the previous signal cycle ; Where N is the number of road images of traffic flow image data, is the length of the vehicle queue corresponding to the i-th road image.

6. The method for automatically controlling traffic lights at a road intersection according to claim 5, characterized in that: The step S2 specifically includes the following steps: Using formula Determine the expected congestion duration for the current exit target area ;in, , , , To calculate the coefficient, is the average vehicle speed in the current exit target area during the previous signal cycle, It is the number of times the head-to-tail distance between two adjacent vehicles in the current exit target area during the previous signal cycle is less than the preset distance.

7. The method for automatically controlling traffic lights at a road intersection according to claim 1, characterized in that: The remaining time in step S3 Obtained through the following steps: Using formula Get the remaining time ;in, is the start time when the green light of the signal light at the jth entrance corresponding to the current exit target area is turned on in the current signal cycle, The first time node at the beginning of the current signal cycle.

8. The method for automatically controlling traffic lights at a road intersection according to claim 1, characterized in that: The second time node and the third time node are the same moment.

9. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the method for automatically controlling traffic lights at a road intersection as described in any one of claims 1 to 8.

10. A storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method for automatically controlling traffic lights at a road intersection as claimed in any one of claims 1 to 8 are implemented.

Images