Artificial intelligence traffic control device and method based on Internet of Vehicles

Abstract

The invention is suitable for the technical field of traffic control systems, and particularly relates to an artificial intelligence traffic control device and method based on the Internet of Vehicles, and the method comprises the steps: obtaining a traffic control request; the received traffic control requests are counted, and whether interaction control is carried out or not is judged according to a current traffic light preset switching scheme; receiving vehicle interaction information, performing image acquisition, and determining a lane where a vehicle is located; and counting the number of vehicles in each lane in the current road, and determining traffic light switching time according to the number of vehicles. When congestion occurs, the vehicle interaction information sent by the vehicles is received, and the vehicles in the lanes are photographed to determine the number of the vehicles in each lane, so that the turn-on time and the switching time of the traffic lights in each direction are calculated, and the traffic lights in each direction can be switched in the congestion. The purpose of self-adaptive adjustment is achieved according to the passing demand of the vehicle, and the passing efficiency is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of traffic control systems, and particularly relates to an artificial intelligence traffic control device and method based on the Internet of Vehicles. Background Art

[0002] The Internet of Vehicles refers to that in-vehicle devices on vehicles effectively utilize all vehicle dynamic information in the information network platform through wireless communication technology to provide different functional services during vehicle operation. It can be found that the Internet of Vehicles exhibits the following characteristics: the Internet of Vehicles can ensure the distance between vehicles and reduce the probability of vehicle collision accidents; the Internet of Vehicles can help vehicle owners with real-time navigation and improve the traffic operation efficiency through communication with other vehicles and network systems.

[0003] Traffic control uses modern communication facilities, signal devices, sensors, monitoring equipment and computers to accurately organize and regulate the running vehicles so that they can run safely and smoothly. Traffic control is divided into static management and dynamic management, and traffic control is the dynamic management among them.

[0004] In the current traffic light control process, the changes of traffic lights are controlled through a preset program. Therefore, the change interval is fixed and cannot be actively adjusted according to the vehicle conditions on each road. Summary of the Invention

[0005] The purpose of the embodiments of the present invention is to provide an artificial intelligence traffic control method based on the Internet of Vehicles, aiming to solve the problem that the changes of traffic lights are controlled through a preset program, the change interval is fixed, and it cannot be actively adjusted according to the vehicle conditions on each road.

[0006] The embodiments of the present invention are implemented as follows. An artificial intelligence traffic control method based on the Internet of Vehicles, the method includes:

[0007] Obtain a traffic control request;

[0008] Count the received traffic control requests, and determine whether to perform interactive control according to the preset traffic light switching scheme;

[0009] Receive vehicle interaction information, perform image acquisition according to the traffic control request, and determine the lane where the vehicle is located according to the image acquisition result and the vehicle interaction information, where the vehicle interaction information at least includes vehicle forward direction information;

[0010] Count the number of vehicles in each lane on the current road, and determine the traffic light switching time according to the number of vehicles.

[0011] Preferably, the step of counting the received traffic control requests and determining whether to perform interactive control according to the preset traffic light switching scheme specifically includes

[0012] Record each received traffic control request, and the recorded information includes at least time information;

[0013] Query the preset traffic light switching scheme to determine the traffic light switching cycle;

[0014] Count the received traffic control requests within each traffic light switching cycle, and determine whether to perform interactive control according to the congestion situation.

[0015] Preferably, the step of receiving vehicle interaction information, performing image acquisition according to the traffic control request, and determining the lane where the vehicle is located according to the image acquisition result and the vehicle interaction information specifically includes:

[0016] Receive the vehicle interaction information according to the traffic control request;

[0017] When a new traffic control request is received, immediately perform image acquisition once to obtain the image acquisition result;

[0018] Query the traffic directions of each lane on the current road, and determine the destinations of each vehicle according to the image acquisition result.

[0019] Preferably, the step of counting the number of vehicles in each lane on the current road and determining the traffic light switching time according to the number of vehicles specifically includes:

[0020] Count the number of vehicles in each lane on the current road, and determine the number of vehicles that can pass per unit time in each traffic direction according to the historical traffic data;

[0021] Calculate the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction;

[0022] Adjust the preset traffic light switching scheme according to the passing time to determine the traffic light switching time.

[0023] Preferably, when the traffic light switching time is lower than the traffic light switching time in the original preset traffic light switching scheme, the preset traffic light switching scheme shall prevail.

[0024] Preferably, when performing image acquisition, if an image corresponding to the traffic control request cannot be acquired, the traffic control request shall be discarded.

[0025] Another object of the embodiments of the present invention is to provide an artificial intelligence traffic control device based on the vehicle network, and the device includes:

[0026] Request acquisition module, used to acquire traffic control requests;

[0027] Control determination module, used to count the received traffic control requests and determine whether to perform interactive control according to the preset traffic light switching scheme;

[0028] Vehicle information statistics module, used to receive vehicle interaction information, perform image acquisition according to traffic control requests, and determine the lane where the vehicle is located according to the image acquisition results and vehicle interaction information. The vehicle interaction information at least includes vehicle forward direction information;

[0029] Switching time adjustment module, used to count the number of vehicles in each lane on the current road and determine the traffic light switching time according to the number of vehicles;

[0030] It also includes the monitoring and prediction of traffic congestion status. According to the characteristics of traffic status parameter data obtained from various single data sources and the change trend of these traffic data when the traffic congestion degree changes, the AID algorithm is used to achieve the rapid and accurate monitoring of traffic congestion status and estimate its possible future duration and spatial diffusion evolution trend;

[0031] The calculation formula of the AID algorithm is:

[0032]

[0033]

[0034]

[0035] I p (t) is the traffic parameter combination variable of vehicle detector p at the t-th time interval; q p (t) is the traffic flow of vehicle detector p at the t-th time interval; h p (t) is the average headway of vehicle detector p at the t-th time interval; n is the time window width of data analysis;

[0036] and are respectively the predicted values of q p (t) and h p (t).

[0037] Preferably, the control determination module includes

[0038] Data recording unit, used to record each received traffic control request, and the recorded information at least includes time information;

[0039] Data query unit, used to query the preset traffic light switching scheme and determine the traffic light switching cycle;

[0040] A congestion determination unit, configured to count the received traffic control requests within each traffic light switching cycle, and determine whether to perform interactive control according to the congestion situation.

[0041] Preferably, the vehicle information statistics module includes:

[0042] An information receiving unit, configured to receive vehicle interaction information according to the traffic control request;

[0043] An image acquisition unit, configured to immediately perform image acquisition once a new traffic control request is received, and obtain an image acquisition result;

[0044] A vehicle information recognition unit, configured to query the traffic directions of each lane on the current road, and determine the destinations of each vehicle according to the image acquisition result.

[0045] Preferably, the switching time adjustment module includes:

[0046] A vehicle statistics unit, configured to count the number of vehicles in each lane on the current road, and determine the number of vehicles that can pass per unit time in each traffic direction according to historical traffic data;

[0047] A passing time calculation unit, configured to calculate the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction;

[0048] A scheme adjustment unit, configured to adjust the preset traffic light switching scheme according to the passing time, and determine the traffic light switching time.

[0049] An artificial intelligence traffic control method based on the vehicle network provided by an embodiment of the present invention determines whether there is congestion on the current road according to the traffic control requests sent by vehicles. When congestion occurs, it receives the vehicle interaction information sent by vehicles, and takes pictures of the vehicles in the lane to determine the number of vehicles in each lane, and then calculates the lighting time and switching time of traffic lights in each direction accordingly, achieving the purpose of adaptive adjustment according to the passing needs of vehicles during congestion, and improving the passing efficiency. Description of the Drawings

[0050] Figure 1 It is a flowchart of an artificial intelligence traffic control method based on the vehicle network provided by an embodiment of the present invention;

[0051] Figure 2 It is a flowchart of the step of counting the received traffic control requests and determining whether to perform interactive control according to the current preset traffic light switching scheme provided by an embodiment of the present invention;

[0052] Figure 3Flowchart of the steps for receiving vehicle interaction information provided by an embodiment of the present invention, collecting images according to traffic control requests, and determining the lane in which the vehicle is located based on the image collection results and vehicle interaction information;

[0053] Figure 4 Flowchart of the steps for counting the number of vehicles in each lane on the current road provided by an embodiment of the present invention and determining the traffic light switching time based on the number of vehicles;

[0054] Figure 5 Architecture diagram of an artificial intelligence traffic control device based on the vehicle networking provided by an embodiment of the present invention;

[0055] Figure 6 Architecture diagram of a control determination module provided by an embodiment of the present invention;

[0056] Figure 7 Architecture diagram of a vehicle information statistics module provided by an embodiment of the present invention;

[0057] Figure 8 Architecture diagram of a switching time adjustment module provided by an embodiment of the present invention. Detailed implementation manners

[0058] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. 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.

[0059] It can be understood that the terms "first", "second", etc. used in the present application may be used herein to describe various elements, but unless otherwise specified, these elements are not limited by these terms. These terms are only used to distinguish one element from another. For example, without departing from the scope of the present application, the first xx script may be referred to as the second xx script, and similarly, the second xx script may be referred to as the first xx script.

[0060] Traffic control uses modern communication facilities, signal devices, sensors, monitoring equipment and computers to accurately organize and regulate the running vehicles so that they can run safely and smoothly. Traffic control is divided into static management and dynamic management, and traffic control is the dynamic management among them. In the current traffic light control process, the changes of traffic lights are controlled through preset programs. Therefore, the change interval is fixed and cannot be actively adjusted according to the vehicle conditions on each road.

[0061] The present invention determines whether there is a congestion situation on the current road by the traffic control request sent by the vehicle. When congestion occurs, it receives the vehicle interaction information sent by the vehicle and takes pictures of the vehicles in the lane to determine the number of vehicles in each lane, and then calculates the lighting time and switching time of the traffic lights in each direction accordingly, achieving the purpose of adaptive adjustment according to the traffic demand of the vehicles during congestion and improving the traffic efficiency.

[0062] As Figure 1 shown, it is a flowchart of an artificial intelligence traffic control method based on the vehicle networking provided by an embodiment of the present invention. The method includes:

[0063] S100, obtaining a traffic control request.

[0064] In this step, when obtaining a traffic control request, when congestion occurs at a traffic light intersection during vehicle passage, a traffic control request is sent out wirelessly. The wireless communication can be Bluetooth communication or Wifi communication. A corresponding wireless communication receiving device is set at the intersection for receiving the traffic control request.

[0065] S200, counting the received traffic control requests and determining whether to perform interaction control according to the preset switching scheme of the current traffic lights.

[0066] In this step, the received traffic control requests are counted. By counting the traffic control requests, the number of vehicles in the current road that can control the traffic lights is determined. According to the number of vehicles in the lane and the preset switching scheme of the current traffic lights, it is determined whether the current preset switching scheme of the traffic lights is suitable for the traffic demand of the current lane. For example, at an intersection, the green light time in both the east-west direction and the north-south direction is 20 seconds, and the number of vehicles that need to pass in the east-west direction is twice the number of vehicles that need to communicate in the north-south direction. Obviously, a green light time of 20 seconds for both is not suitable. Thus, it can be determined that the current traffic lights need to be interactively controlled.

[0067] S300, receiving vehicle interaction information, performing image acquisition according to the traffic control request, and determining the lane where the vehicle is located according to the image acquisition result and the vehicle interaction information. The vehicle interaction information at least includes vehicle forward direction information.

[0068] In this step, vehicle interaction information is received, and when interactive control is performed, traffic control information is sent to all vehicles. After receiving the information, the vehicle re-issues the traffic control request and uploads the vehicle interaction information. The vehicle interaction information can at least reflect the current vehicle's direction of travel and the vehicle's license plate number. The movement of each vehicle can be determined based on the vehicle's direction of travel contained in the vehicle interaction information. In this way, it is possible to avoid collecting vehicle interaction information sent by vehicles in the target lane, so as to avoid erroneous collection. After receiving the information, image acquisition is performed. Each time a vehicle interaction information is received, a group of images will be collected, and the position of each vehicle will be determined through the image, so as to facilitate the counting of the number of vehicles in each lane. When performing image acquisition, if the image corresponding to the traffic control request cannot be collected, the traffic control request will be discarded.

[0069] S400, counting the number of vehicles in each lane of the current road, and determining the traffic light switching time according to the number of vehicles.

[0070] In this step, the number of vehicles in each lane of the current road is counted. Before the statistics are performed, the lanes included in the current road are counted. For example, if there is a left-turn lane, two straight lanes and a right-turn lane, the vehicle position is determined based on the collected image. Specifically, it can also be divided into the first lane, the second lane...the Nth lane, and then determined according to the direction of travel of each lane, so as to obtain the corresponding number of vehicles in each direction of travel by statistics. Then, the green light on time of each direction in the traffic light can be adjusted accordingly. For example, in the preset switching scheme of the traffic light, the straight green light time in the east-west direction and the north-south direction is 20 seconds. In the current time, the number of vehicles going straight in the east-west direction is twice the number of vehicles going straight in the north-south direction. Then, the lighting time of the corresponding straight green light in the east-west direction is adjusted to 40 seconds, so that the number of vehicles matches the green light time to avoid congestion.

[0071] like Figure 2 As shown, as a preferred embodiment of the present invention, the step of counting the received traffic control requests and determining whether to perform interactive control according to the current traffic light preset switching scheme specifically includes:

[0072] S201, recording each received traffic control request, where the recorded information at least includes time information.

[0073] In this step, each received traffic control request is recorded in chronological order, and the time when each traffic control request is received is recorded, that is, the recorded information includes time information.

[0074] S202, query the preset traffic light switching plan and determine the traffic light switching cycle.

[0075] In this step, the traffic light preset switching scheme is queried. The traffic light preset switching scheme records the lighting switching time of each traffic light. The traffic light preset switching scheme is used when no interactive control is performed. Therefore, the current traffic light switching cycle can be obtained by querying.

[0076] S203, counting the traffic control requests received in each traffic light switching cycle, and determining whether to perform interactive control according to the congestion situation.

[0077] In this step, the traffic control requests received in each traffic light switching cycle are counted. In historical data, the maximum number of vehicles that can pass through each traffic light switching cycle is known. For example, 30 vehicles can pass through in one cycle, and more than 30 traffic control requests are received in the current traffic light switching cycle, which means that vehicles cannot pass through at one time in the current traffic light switching cycle. If the traffic light switching cycle is not changed, congestion will gradually occur.

[0078] like Figure 3 As shown, as a preferred embodiment of the present invention, the steps of receiving vehicle interaction information, performing image acquisition according to a traffic control request, and determining the lane in which the vehicle is located according to the image acquisition result and the vehicle interaction information specifically include:

[0079] S301: Receive vehicle interaction information according to a traffic control request.

[0080] In this step, the vehicle interaction information is received according to the traffic control request. There is a corresponding relationship between the traffic control request and the vehicle interaction information. When it is determined that interactive control is required, all traffic control requests received before are discarded, and then a new traffic control request is received, and then the vehicle interaction information is received. In order to avoid erroneous reception, the vehicle interaction information uses the direction information as the head and the license plate number as the tail. The direction of the vehicle can be determined based on the head information, and the identity of the vehicle can be determined based on the tail information, so as to avoid one vehicle sending multiple vehicle interaction information.

[0081] S302, when a new traffic control request is received, image acquisition is immediately performed to obtain image acquisition results.

[0082] S303, querying the travel direction of each lane of the current road, and determining the destination of each vehicle according to the image acquisition result.

[0083] In this step, when a new traffic control request is received, it is necessary to determine the location of the current vehicle. Therefore, a photo is taken immediately to capture the vehicles on the road, and the license plate numbers included in the vehicle interaction information are used for identification to determine the lanes in which the vehicles corresponding to the license plate numbers in the image are located. Then, through statistics, the destination and the lane in which each vehicle is located can be determined.

[0084] As Figure 4 shown, as a preferred embodiment of the present invention, the step of counting the number of vehicles in each lane within the current road and determining the traffic light switching time according to the number of vehicles specifically includes:

[0085] S401, count the number of vehicles in each lane within the current road, and determine the number of vehicles that can pass through per unit time in each traffic direction according to the historical traffic data.

[0086] In this step, when counting the number of vehicles in each lane within the current road, if there are multiple lanes in a road, then count according to the traffic direction of each lane. For example, there are 20 vehicles waiting to turn left and 25 vehicles waiting to go straight, etc. By querying the historical data, the number of vehicles that can pass through per unit time in each traffic direction can be obtained.

[0087] S402, calculate the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass through per unit time in each direction.

[0088] S403, adjust the preset traffic light switching scheme according to this passing time to determine the traffic light switching time;

[0089] It also includes the monitoring and prediction of traffic congestion states. According to the characteristics of traffic state parameter data obtained from various single data sources and the changing trends of these traffic data when the traffic congestion degree changes, the AID algorithm is used to achieve the rapid and accurate monitoring of traffic congestion states, and estimate its possible future duration and spatial diffusion and evolution trends;

[0090] The calculation formula of the AID algorithm is:

[0091]

[0092]

[0093]

[0094] I p (t) is the traffic parameter combination variable of vehicle detector p at the t-th time interval; q p (t) is the traffic flow of vehicle detector p at the t-th time interval; h p(t) is the average headway of vehicle detector p in the t-th time interval; n is the width of the time window for data analysis;

[0095] and are the predicted values of q p (t) and h p (t) respectively.

[0096] In this step, the required passing time is calculated according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction. Then, the finally determined traffic light switching time should be greater than this passing time, so as to ensure that all vehicles can pass through the intersection during a traffic light switching cycle. Of course, when the traffic flow is too large, it is impossible to improve the passing efficiency by changing the traffic light switching cycle. Therefore, a maximum value needs to be set for the traffic light switching cycle. When the passing time exceeds the maximum value, the maximum value is used as the traffic light switching cycle.

[0097] As Figure 5 shown, it is an artificial intelligence traffic control device based on the vehicle networking provided by an embodiment of the present invention. The device includes:

[0098] A request acquisition module 100, which is used to acquire traffic control requests.

[0099] In this device, the request acquisition module 100 acquires traffic control requests. When vehicles are passing and there is congestion at a traffic light intersection, a traffic control request is sent out wirelessly. The wireless communication can be Bluetooth communication or Wifi communication. A corresponding wireless communication receiving device is set at the intersection to receive traffic control requests.

[0100] A control determination module 200, which is used to count the received traffic control requests and determine whether to perform interactive control according to the preset switching scheme of the current traffic light.

[0101] In this device, the control determination module 200 counts the received traffic control requests. By counting the traffic control requests, the number of vehicles in the current road that have the ability to control the traffic signal is determined. According to the number of vehicles in the lane and the preset switching scheme of the current traffic light, it is determined whether the current preset switching scheme of the traffic light is suitable for the passing requirements of the current lane. For example, at an intersection, the green light time in both the east-west direction and the north-south direction is 20 seconds, and the number of vehicles that need to pass in the east-west direction is twice the number of vehicles that need to communicate in the north-south direction. Then obviously, a green light time of 20 seconds for both is not suitable, and it can be determined that the current traffic light needs to be interactively controlled.

[0102] The vehicle information statistics module 300 is used to receive vehicle interaction information, perform image acquisition according to traffic control requests, and determine the lane where the vehicle is located according to the image acquisition results and the vehicle interaction information, wherein the vehicle interaction information at least includes vehicle forward direction information.

[0103] In the present device, the vehicle information statistics module 300 receives vehicle interaction information, and when performing interactive control, sends traffic control information to all vehicles. After receiving the information, the vehicle re-issues the traffic control request and uploads the vehicle interaction information. The vehicle interaction information can at least reflect the current vehicle's direction of travel and the vehicle's license plate number. The movement of each vehicle can be determined based on the vehicle's direction of travel contained in the vehicle interaction information, so that the vehicle interaction information sent by the vehicle in the target lane can be avoided to avoid erroneous collection. After receiving the information, image acquisition is performed. Each time a vehicle interaction information is received, a group of images will be collected. The position of each vehicle is determined by the image, so as to facilitate the statistics of the number of vehicles in each lane. When performing image acquisition, if the image corresponding to the traffic control request cannot be collected, the traffic control request is discarded.

[0104] The switching time adjustment module 400 is used to count the number of vehicles in each lane of the current road and determine the traffic light switching time according to the number of vehicles.

[0105] In the present device, the switching time adjustment module 400 counts the number of vehicles in each lane of the current road. Before the statistics are performed, the lanes included in the current road are counted. For example, if there is a left-turn lane, two straight lanes and a right-turn lane, the vehicle position is determined based on the collected image. Specifically, it can also be divided into the first lane, the second lane...the Nth lane, and then determined based on the direction of travel of each lane, so as to obtain the corresponding number of vehicles in each direction of travel by statistics. Then, the green light on time of each direction in the traffic light can be adjusted accordingly. For example, in the preset switching scheme of the traffic light, the straight green light time in the east-west direction and the north-south direction is 20 seconds. In the current time, the number of vehicles going straight in the east-west direction is twice the number of vehicles going straight in the north-south direction. Then, the lighting time of the corresponding straight green light in the east-west direction is adjusted to 40 seconds, so that the number of vehicles matches the green light time to avoid congestion.

[0106] like Figure 6 As shown, as a preferred embodiment of the present invention, the control determination module 200 includes

[0107] The data recording unit 201 is used to record each received traffic control request, and the recorded information at least includes time information.

[0108] In this module, the data recording unit 201 records each received traffic control request, records them in chronological order, and records the moment when each traffic control request is received, that is, the recorded information includes time information.

[0109] The data query unit 202 is used to query the preset traffic light switching scheme and determine the traffic light switching period.

[0110] In this module, the data query unit 202 queries the preset traffic light switching scheme. The switching times of each traffic signal are recorded in the preset traffic light switching scheme. The preset traffic light switching scheme is used when there is no interactive control. Therefore, the current traffic light switching period can be obtained through query.

[0111] The congestion determination unit 203 is used to count the received traffic control requests within each traffic light switching period and determine whether to perform interactive control according to the congestion situation.

[0112] In this module, the congestion determination unit 203 counts the received traffic control requests within each traffic light switching period. In the historical data, the maximum number of vehicles that can pass through each traffic light switching period is known. For example, within one period, 30 vehicles can pass through. If the number of received traffic control requests within the current traffic light switching period is more than 30, it means that within the current traffic light switching period, the vehicles cannot pass through at one time. If the traffic light switching period is not changed, congestion will gradually occur.

[0113] As Figure 7 shown, as a preferred embodiment of the present invention, the vehicle information statistics module 300 includes:

[0114] The information receiving unit 301 is used to receive vehicle interaction information according to the traffic control request.

[0115] In this module, the information receiving unit 301 receives vehicle interaction information according to the traffic control request. There is a corresponding relationship between the traffic control request and the vehicle interaction information. When it is determined that interactive control is required, all the previously received traffic control requests are discarded, and then new traffic control requests are received, and then vehicle interaction information is received. To avoid mis-reception, the vehicle interaction information has the direction information as the head and its license plate number as the tail. The vehicle's orientation can be determined according to the head information, and the vehicle identity can be determined according to the tail information, avoiding a vehicle sending multiple vehicle interaction information.

[0116] The image acquisition unit 302 is used to immediately perform image acquisition once when a new traffic control request is received, and obtain the image acquisition result.

[0117] The vehicle information recognition unit 303 is used to query the traffic directions of each lane on the current road and determine the destinations of each vehicle according to the image acquisition results.

[0118] In this module, when a new traffic control request is received, it is necessary to determine the position of the current vehicle. Therefore, a photo is taken immediately to capture the vehicles on the road, and the vehicle license plate number included in the vehicle interaction information is recognized to determine the lane where the vehicle corresponding to the license plate number in the image is located. Then, through statistics, the destination and the lane where each vehicle is located can be determined.

[0119] As Figure 8 shown, as a preferred embodiment of the present invention, the switching time adjustment module 400 includes:

[0120] The vehicle statistics unit 401 is used to count the number of vehicles in each lane on the current road and determine the number of vehicles that can pass per unit time in each traffic direction according to the historical traffic data.

[0121] In this module, the vehicle statistics unit 401 counts the number of vehicles in each lane on the current road. If there are multiple lanes on a road, the statistics are carried out according to the traffic directions of each lane. For example, there are 20 vehicles waiting to turn left and 25 vehicles waiting to go straight, etc. By querying the historical data, the number of vehicles that can pass per unit time in each traffic direction can be obtained.

[0122] The passing time calculation unit 402 is used to calculate the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction.

[0123] The scheme adjustment unit 403 is used to adjust the preset traffic light switching scheme according to the passing time and determine the traffic light switching time.

[0124] In this module, the required passing time is calculated according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction. Then, the finally determined traffic light switching time should be greater than this passing time to ensure that all vehicles can pass through the intersection within a traffic light switching cycle. Of course, when the traffic flow is too large, it is impossible to improve the traffic efficiency by changing the traffic light switching cycle. Therefore, a maximum value needs to be set for the traffic light switching cycle. When the passing time exceeds the maximum value, the maximum value is used as the traffic light switching cycle.

[0125] It should be understood that although the steps in the flowcharts of the embodiments of the present invention are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in each embodiment may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or sub-steps or stages of other steps.

[0126] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memories can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memories can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0127] The technical features of the above-described embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.

[0128] The above-described embodiments merely represent several implementation manners of the present invention. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several variations and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the appended claims.

[0129] The foregoing is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. An artificial intelligence traffic control method based on the vehicle networking, characterized in that, The method includes: Obtaining a traffic control request; Counting the received traffic control requests, and determining whether to perform interactive control according to the preset traffic light switching scheme; Receiving vehicle interaction information, collecting images according to the traffic control request, and determining the lane where the vehicle is located based on the image collection result and the vehicle interaction information, where the vehicle interaction information at least includes vehicle forward direction information; Counting the number of vehicles in each lane on the current road, and determining the traffic light switching time according to the number of vehicles; 2. The artificial intelligence traffic control method based on the vehicle networking according to claim 1, wherein The step of counting the received traffic control requests and determining whether to perform interactive control according to the preset traffic light switching scheme specifically includes Recording each received traffic control request, and the recorded information at least includes time information; Querying the preset traffic light switching scheme to determine the traffic light switching period; Counting the received traffic control requests within each traffic light switching period, and determining whether to perform interactive control according to the congestion situation; 3. The artificial intelligence traffic control method based on the vehicle networking according to claim 1, wherein The step of receiving vehicle interaction information, collecting images according to the traffic control request, and determining the lane where the vehicle is located based on the image collection result and the vehicle interaction information specifically includes: Receiving the vehicle interaction information according to the traffic control request; When a new traffic control request is received, immediately perform image collection once to obtain an image collection result; Querying the traffic directions of each lane on the current road, and determining the destinations of each vehicle based on the image collection result; 4. The artificial intelligence traffic control method based on the vehicle networking according to claim 1, wherein, The step of counting the number of vehicles in each lane on the current road and determining the traffic light switching time according to the number of vehicles specifically includes: Counting the number of vehicles in each lane on the current road, and determining the number of vehicles that can pass per unit time in each traffic direction according to historical traffic data; Calculating the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction; Adjusting the preset traffic light switching scheme according to the passing time to determine the traffic light switching time; It also includes the monitoring and prediction of traffic congestion status. According to the characteristics of traffic status parameter data obtained from various single data sources and the change trends of these traffic data when the traffic congestion degree changes, the AID algorithm is used to achieve the rapid and accurate monitoring of traffic congestion status, and estimate its possible future duration and spatial diffusion evolution trend; The calculation formula of the AID algorithm is: I p (t) is the combined traffic parameter variable of vehicle detector p in the t-th time interval; q p (t) is the traffic flow of vehicle detector p in the t-th time interval; h p (t) is the average headway of vehicle detector p in the t-th time interval; n is the time window width for data analysis; and are the predicted values of q p (t) and h p (t), respectively.

5. The artificial intelligence traffic control method based on the vehicle networking according to claim 1, wherein When the traffic light switching time is lower than the traffic light switching time in the original preset traffic light switching scheme, the preset traffic light switching scheme shall prevail.

6. The artificial intelligence traffic control method based on the vehicle networking according to claim 1, wherein When collecting images, if an image corresponding to the traffic control request cannot be collected, the traffic control request shall be discarded.

7. An artificial intelligence traffic control device based on the vehicle networking, characterized in that, The device includes: A request acquisition module for obtaining traffic control requests; A control determination module for counting the received traffic control requests and determining whether to perform interactive control according to the preset traffic light switching scheme; A vehicle information statistics module for receiving vehicle interaction information, collecting images according to the traffic control request, and determining the lane where the vehicle is located based on the image collection result and the vehicle interaction information, where the vehicle interaction information at least includes vehicle forward direction information; The switching time adjustment module is used to count the number of vehicles in each lane of the current road and determine the traffic light switching time according to the number of vehicles.

8. The artificial intelligence traffic control device based on the vehicle networking according to claim 7, wherein The control and determination module includes a data recording unit, which is used to record each received traffic control request, and the recorded information at least includes time information; a data query unit, which is used to query the preset traffic light switching scheme and determine the traffic light switching period; a congestion determination unit, which is used to count the received traffic control requests in each traffic light switching period and determine whether to perform interactive control according to the congestion situation.

9. The artificial intelligence traffic control device based on the vehicle networking according to claim 7, characterized in that The vehicle information statistics module includes: an information receiving unit, which is used to receive vehicle interaction information according to the traffic control request; an image acquisition unit, which is used to immediately perform an image acquisition when a new traffic control request is received to obtain an image acquisition result; a vehicle information recognition unit, which is used to query the traffic directions of each lane of the current road and determine the destinations of each vehicle according to the image acquisition result.

10. The artificial intelligence traffic control device based on the vehicle networking according to claim 7, characterized in that, The switching time adjustment module includes: a vehicle statistics unit, which is used to count the number of vehicles in each lane of the current road and determine the number of vehicles that can pass per unit time in each traffic direction according to the historical traffic data; a passing time calculation unit, which is used to calculate the required passing time according to the number of vehicles in the lane and the number of vehicles that can pass per unit time in each direction; a scheme adjustment unit, which is used to adjust the preset traffic light switching scheme according to the passing time and determine the traffic light switching time.

Images