Traffic light control method and device based on joint simulation

Abstract

The embodiment of the invention discloses a traffic light control method and device based on joint simulation. A specific embodiment of the method comprises the following steps: acquiring a traffic flow video of a road intersection; performing bus identification on the traffic stream video to obtain bus identification information; in response to determining that an identification timestamp included in the bus identification information is in a time period of a corresponding green light phase and the bus running state represents a vehicle advancing state, determining a corresponding bus passing duration based on the bus identification information; in response to the determined time period when the bus passing duration exceeds the green light phase, determining a corresponding green light prolonged duration based on a preset maximum green light duration; in response to determining that the green light prolonged duration meets the delay condition, adjusting a green light phase according to the green light prolonged duration to obtain an adjusted green light phase; and controlling the corresponding traffic light according to the adjusted traffic light phase. The implementation mode can improve the overall traffic efficiency of the road network.

Description

Technical Field

[0001] The embodiments disclosed herein relate to the fields of traffic light control technology, image recognition technology, and computer technology, and specifically to a traffic light control method and apparatus based on co-simulation. Background Technology

[0002] Traffic light control is a technology designed to prioritize the passage of buses. Currently, traffic light control strategies for bus priority are categorized into three types: passive priority control, active priority control, and real-time priority control. Passive priority control is a static signal optimization method based on historical traffic data. Its core lies in using long-term accumulated bus operation patterns and intersection traffic characteristics to pre-set a fixed signal timing scheme. This strategy does not rely on real-time detection technology; it can generate periodic priority signal plans through offline analysis. Its main problem is the lack of dynamic adaptability. Because this strategy does not rely on real-time detection technology, the signal timing cannot respond to short-term fluctuations in traffic flow, potentially resulting in buses not receiving effective priority when they actually arrive at the intersection. Especially during periods of significant traffic demand change (such as morning and evening rush hours), fixed timing schemes can easily lead to wasted green light time or increased bus delays. Furthermore, this strategy typically employs static green wave coordination or phase extension mechanisms, making it difficult to adapt to changes in bus schedules or sudden traffic events, which may have a significant negative impact on the efficiency of non-bus vehicles. Secondly, proactive priority control responds to bus priority requests in real time through detection equipment. Its strategy relies on highly reliable vehicle-to-infrastructure communication and detection systems (such as RFID, GPS, or induction coils), resulting in high hardware deployment and maintenance costs. In practical applications, detection equipment is susceptible to severe weather or electromagnetic interference; communication delays or malfunctions can cause priority requests to fail. More significantly, this strategy faces coordination challenges in multi-line, high-density bus networks: when multiple priority requests conflict, traditional logic struggles to dynamically weigh the priorities of different lines, potentially leading to "priority competition" and reducing overall system efficiency. Furthermore, proactive priority typically employs single-point optimization (such as green light extension or phase insertion), lacking coordinated control of adjacent intersections, which may transfer delays to downstream nodes. In corridors with high bus frequency, overuse of proactive priority control strategies can lead to a surge in queues for other vehicles, negating the benefits of bus priority. Thirdly, real-time priority control achieves second-level decision-making through dynamic optimization algorithms (such as model predictive control or reinforcement learning), but its technical barriers and operating costs far exceed those of other strategies. This strategy requires the integration of high-precision traffic flow detection, low-latency communication, and a high-performance computing platform; failure in any of these components can lead to control failure. For example, missing or noisy data from sensing devices can cause misjudgments in the optimization model, while the short-term decision-making characteristics of the algorithm itself may ignore long-term traffic state evolution, resulting in a "local optimum but global suboptimal" problem. In complex road networks, real-time optimization also needs to handle multi-objective conflicts (such as balancing minimizing bus delays with the efficiency of private vehicle traffic), and existing algorithms struggle to balance real-time performance with solution accuracy.Furthermore, the system's deployment heavily relies on continuous debugging by a professional team and must address parameter sensitivity issues under different traffic scenarios. In road sections with low saturation or low public transport usage, the marginal benefits of real-time priority may not cover its high operation and maintenance costs, limiting its widespread adoption.

[0003] Therefore, current public transport priority control strategies still have significant limitations in terms of adaptability and refinement. Most systems still rely on static timetables or fixed priority triggering mechanisms, making it difficult to effectively cope with the spatiotemporal heterogeneity and random disturbances of urban traffic flow. Traditional methods struggle to achieve Pareto optimality between control costs and dynamic response capabilities, and due to the lack of systematic consideration of long-term control effects, they often lead to frequent fluctuations in signal timing or damage to the overall traffic efficiency of the road network. Summary of the Invention

[0004] The summary portion of this disclosure is intended to provide a brief overview of the concepts, which will be described in detail in the detailed description portion. This summary portion is not intended to identify key or essential features of the claimed technical solutions, nor is it intended to limit the scope of the claimed technical solutions.

[0005] Some embodiments of this disclosure propose a traffic light control method and apparatus based on co-simulation to solve the technical problems mentioned in the background section above.

[0006] In a first aspect, some embodiments of this disclosure provide a traffic light control method based on co-simulation. The method includes: acquiring a traffic flow video at a road intersection; performing bus identification on the traffic flow video to obtain bus identification information, wherein the bus identification information includes an identified bus identifier, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp; in response to determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, determining a corresponding bus passage duration based on the bus identification information; in response to determining that the bus passage duration exceeds the time period of the green light phase, determining a corresponding green light extension duration based on a preset maximum green light duration, wherein the maximum green light duration corresponds to the identification timestamp, and the maximum green light duration is generated based on co-simulation of historical traffic flow video and traffic data at the road intersection; in response to determining that the green light extension duration meets a delay condition, adjusting the green light phase according to the green light extension duration to obtain an adjusted green light phase; and controlling the corresponding traffic light according to the adjusted traffic light phase.

[0007] Secondly, some embodiments of this disclosure provide a traffic light control device based on co-simulation. The device includes: an acquisition unit configured to acquire traffic flow video at a road intersection; a bus identification unit configured to perform bus identification on the traffic flow video to obtain bus identification information, wherein the bus identification information includes an identified bus identifier, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp; and a first determination unit configured to, in response to determining that the identification timestamp included in the bus identification information is within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement state, determine the bus identification information based on the bus identification information. The system comprises: a first unit for identifying the bus travel time; a second unit for determining the green light phase; a third unit for determining the green light extension time based on a preset maximum green light duration, wherein the maximum green light duration corresponds to the identification timestamp and is generated by joint simulation of historical traffic flow video and traffic data of the intersection; an adjustment unit for adjusting the green light phase based on the green light extension time to obtain the adjusted green light phase, in response to determining that the green light extension time meets the delay condition; and a traffic light control unit for controlling the corresponding traffic light based on the adjusted traffic light phase.

[0008] Thirdly, some embodiments of this disclosure provide an electronic device, including: one or more processors; and a storage device having one or more programs stored thereon, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any implementation of the first aspect above.

[0009] Fourthly, some embodiments of this disclosure provide a computer-readable medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the method described in any of the implementations of the first aspect above.

[0010] The various embodiments of this disclosure have the following beneficial effects: the traffic light control method based on co-simulation of some embodiments of this disclosure can improve the overall traffic efficiency of the road network. Specifically, the reason for the reduction in the overall traffic efficiency of the generated road network is that the current bus priority control strategy still has significant limitations in terms of adaptability and refinement. Most systems still rely on static timetables or fixed priority triggering mechanisms, which are difficult to effectively cope with the spatiotemporal heterogeneity and random disturbances of urban traffic flow. Traditional methods are difficult to achieve Pareto optimality between control cost and dynamic response capability, and due to the lack of systematic consideration of long-term control effects, they often lead to frequent fluctuations in signal timing or damage to the overall traffic efficiency of the road network. Based on this, the traffic light control method based on co-simulation of some embodiments of this disclosure first acquires traffic flow video at the road intersection. Then, bus identification is performed on the traffic flow video to obtain bus identification information, which includes the identified bus logo, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp. Here, identification can be used to determine whether a bus has entered the road intersection. Next, in response to determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, the corresponding bus travel duration is determined based on the bus identification information. Here, determining the bus travel duration can be used to determine whether the bus meets the passage conditions. Then, in response to determining that the bus travel duration exceeds the time period of the green light phase, a corresponding green light extension duration is determined based on a preset maximum green light duration. This maximum green light duration corresponds to the identification timestamp and is generated based on a joint simulation of historical traffic flow videos and traffic data from the road intersection. Here, generating the green light extension duration can be used to appropriately extend the green light duration, thereby improving bus passage efficiency. Then, in response to determining that the green light extension duration meets the delay conditions, the green light phase is adjusted according to the green light extension duration to obtain the adjusted green light phase. Finally, the corresponding traffic lights are controlled according to the adjusted traffic light phase. Here, considering the lack of long-term control effects in the system, the maximum green light duration generated by co-simulation is introduced as a reference. This ensures that the generated traffic light extension duration meets the current traffic demand at the intersection, thus avoiding negative impacts on other vehicles. Furthermore, the traffic light phases can be adjusted appropriately to control the traffic lights and improve the overall traffic efficiency of the road network. Attached Figure Description

[0011] The above and other features, advantages, and aspects of the embodiments of this disclosure will become more apparent from the accompanying drawings and the following detailed description. Throughout the drawings, the same or similar reference numerals denote the same or similar elements. It should be understood that the drawings are schematic, and elements are not necessarily drawn to scale.

[0012] Figure 1 This is a flowchart of some embodiments of the traffic light control method based on co-simulation according to the present disclosure;

[0013] Figure 2 This is a flowchart of the bus priority strategy evaluation process at signalized intersections based on SUMO-Python co-simulation.

[0014] Figure 3 These are schematic diagrams of some embodiments of a traffic light control device based on co-simulation according to the present disclosure;

[0015] Figure 4 This is a schematic diagram of the structure of an electronic device suitable for implementing some embodiments of the present disclosure. Detailed Implementation

[0016] Embodiments of this disclosure will now be described in more detail with reference to the accompanying drawings. While some embodiments of this disclosure are shown in the drawings, it should be understood that this disclosure can be implemented in various forms and should not be construed as limited to the embodiments set forth herein. Rather, these embodiments are provided to provide a more thorough and complete understanding of this disclosure. It should be understood that the accompanying drawings and embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of protection of this disclosure.

[0017] It should also be noted that, for ease of description, only the parts relevant to the invention are shown in the accompanying drawings. Unless otherwise specified, the embodiments and features described in this disclosure can be combined with each other.

[0018] It should be noted that the concepts of "first" and "second" mentioned in this disclosure are used only to distinguish different devices, modules or units, and are not used to limit the order of functions performed by these devices, modules or units or their interdependencies.

[0019] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0020] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0021] This disclosure will now be described in detail with reference to the accompanying drawings and embodiments.

[0022] Figure 1 A flowchart 100 is shown, illustrating some embodiments of a co-simulation-based traffic light control method according to this disclosure. The co-simulation-based traffic light control method includes the following steps:

[0023] Step 101: Obtain video of traffic flow at the road intersection.

[0024] In some embodiments, the executor of the traffic light control method based on co-simulation (e.g., a computing device) can acquire traffic flow video at road intersections via wired or wireless means. Specifically, traffic flow video at road intersections can be acquired through road surveillance cameras. Here, the traffic flow video can be road surveillance video corresponding to a specific entrance direction of the road intersection (e.g., a southbound entrance).

[0025] It should be noted that the aforementioned wireless connection methods may include, but are not limited to, 3G / 4G / 5G connections, WiFi connections, Bluetooth connections, WiMAX connections, Zigbee connections, UWB (Ultra Wide Band) connections, and other currently known or future wireless connection methods.

[0026] It should be noted that the aforementioned computing devices can be either hardware or software. When the computing device is hardware, it can be implemented as a distributed cluster consisting of multiple servers or terminal devices, or as a single server or a single terminal device. When the computing device is software, it can be installed on the hardware devices listed above. It can be implemented as, for example, multiple software programs or software modules used to provide distributed services, or as a single software program or software module. No specific limitations are made here.

[0027] Step 102: Perform bus identification on the traffic flow video to obtain bus identification information.

[0028] In some embodiments, the aforementioned executing entity can perform bus identification on the aforementioned traffic flow video to obtain bus identification information. This bus identification information includes the identified bus sign, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp. Here, bus coordinates can represent the current location of the bus. Specifically, bus coordinates can be latitude and longitude coordinates, or three-dimensional coordinates in a map coordinate system. The bus operating status can be used to indicate whether the bus is moving forward or stationary. The identification timestamp can be the time point at which the bus sign was identified.

[0029] Additionally, when performing bus identification on traffic flow videos, if no bus identifier is detected in the video image, the bus identification information can be empty. In this case, no further processing is required.

[0030] In some optional implementations of certain embodiments, the aforementioned executing entity performs bus identification on the aforementioned traffic flow video to obtain bus identification information, including:

[0031] Step S1: Extract frames from the traffic flow video to obtain a traffic flow image group. The traffic flow video can be extracted at preset frame extraction intervals to obtain the traffic flow image group.

[0032] Step S2 involves performing vehicle recognition on the aforementioned traffic flow image group to generate a traffic flow recognition information group. This traffic flow recognition information includes: target detection bounding boxes, bus identification symbols, license plate numbers, and corresponding recognition timestamps. Here, the YOLOv8 (You Only Look Once Version 8) algorithm can be used as the recognition algorithm to perform vehicle recognition on the aforementioned traffic flow image group to generate the traffic flow recognition information group.

[0033] Step S3: Based on a pre-set bus operation database, the aforementioned traffic flow identification information group is filtered to obtain target traffic flow information. The bus operation database can be pre-constructed for traffic flow information at various road intersections at different time periods. Therefore, the bus operation data in the bus operation database can include the bus schedule, license plate number, and travel time period of each road intersection. Here, firstly, preliminary traffic flow information is selected from the initial traffic flow information group that includes target detection boxes larger than a preset threshold, or whose target detection boxes are located at a preset image detection line (e.g., a horizontal line located at one-third of the way down the image's vertical axis) as target traffic flow information. Filtering the target detection boxes helps select relatively clear and complete traffic flow images and corresponding traffic flow identification information from the traffic flow video. Then, bus operation data consistent with the aforementioned road intersections and identification timestamps can be selected from the bus operation database as target operation data. Secondly, by using the license plate number and travel time period in the target operation data, it can be determined whether there is preliminary traffic flow information with the same license plate number at the above-mentioned road intersection in the current time period. In this way, the traffic flow identification information group can be filtered to obtain the target traffic flow information.

[0034] Specifically, considering the possibility of missed or false bus detections, or the detection of similar vehicles not belonging to a bus route, a pre-set bus operation database is used to compare the number of buses that can pass through the current intersection during the current time period. This allows for the accurate selection of the corresponding vehicle flow identification information from the vehicle flow identification information group as the target vehicle flow information.

[0035] In addition, the bus operation database can be generated through the following steps:

[0036] First, precise geometric parameters (e.g., number of lanes, lane width, turning radius) of each intersection's approach lanes are collected using specialized equipment such as laser rangefinders. Infrastructure data, including existing signal timing schemes, is also obtained through on-site surveys. Then, based on a combination of video detection and manual counting, traffic flow data is collected primarily during three characteristic time periods: morning peak (e.g., 7:30-8:30), off-peak (e.g., 10:00-11:00), and evening peak (e.g., 17:30-18:30). Finally, bus location and operation data are integrated to establish a bus operation database containing elements such as route direction, departure intervals, and arrival times.

[0037] Step S4: Obtain the bus coordinates, bus operating status, bus speed, and bus acceleration corresponding to the target traffic flow information. This can be achieved by establishing a communication connection with the aforementioned bus network terminal or bus management system. Furthermore, the bus operating status can be simultaneously identified during image recognition of the traffic flow image.

[0038] Step S5: The bus coordinates, bus operating status, bus speed, bus acceleration, and target traffic flow information are determined as bus identification information.

[0039] Step 103: In response to determining that the identification timestamp included in the bus identification information is within the time period of the corresponding green light phase, and that the bus operation status represents the vehicle's forward movement status, the corresponding bus passage duration is determined based on the bus identification information.

[0040] In some embodiments, the executing entity may, in response to determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, determine the corresponding bus travel time based on the bus identification information. Specifically, determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase can indicate that when the bus is identified from the traffic flow image, the traffic light at the bus's entrance is in a green light phase (i.e., within a green light period). The bus operating status representing the vehicle's forward movement can indicate that the bus is moving and entering the road intersection.

[0041] In some optional implementations of certain embodiments, the execution entity, in response to determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, determines the corresponding bus travel duration based on the bus identification information, including:

[0042] Step S1: Determine the bus travel distance based on the distance between the bus coordinates in the bus identification information and the preset intersection travel coordinates. The preset intersection travel coordinates can be the coordinates of the middle position of the intersection or the lane stop line of the bus's current lane. Therefore, the distance between the bus coordinates and the preset intersection travel coordinates can be determined as the bus travel distance. Here, the bus travel distance represents the minimum distance the bus needs to travel to ensure it enters (or passes) the intersection.

[0043] Step S2: Determine the corresponding bus travel time based on the bus travel distance, the bus speed value, and the bus acceleration value in the bus identification information. Specifically, the travel time required for the bus to travel the aforementioned distance at the given bus acceleration and speed values ​​can be determined using a speed-distance formula.

[0044] Step 104: In response to determining the time period during which the bus travel time exceeds the green light phase, determine the corresponding green light extension time based on the preset maximum green light duration.

[0045] In some embodiments, the executing entity may, in response to determining that the bus travel time exceeds the green light phase for a certain period, determine a corresponding green light extension duration based on a preset maximum green light duration. The period during which the bus travel time exceeds the green light phase indicates that the bus, traveling at its current speed, is insufficient to pass through the intersection within the green light time.

[0046] In some optional implementations of certain embodiments, in response to determining that the bus travel time exceeds the time period of the green light phase, the execution entity determines a corresponding green light extension duration based on a preset maximum green light duration, including:

[0047] Step S1: Obtain the remaining green light duration for the aforementioned green light phase. This remaining green light duration can be obtained from the traffic light control terminal.

[0048] Step S2: Determine the corresponding green light extension time based on the bus travel time, the remaining green light time, and the preset maximum green light time. The corresponding traffic light extension time can be determined using the following formula: Traffic light extension time = min(Bus travel time - Remaining green light time, Maximum green light time).

[0049] Optionally, before adjusting the green light phase according to the green light extension duration to obtain the adjusted green light phase in response to determining that the green light extension duration meets the delay condition, the method further includes:

[0050] In response to the determination that the extended green light duration is greater than or equal to the bus travel time, and that the extended green light duration is less than or equal to the preset maximum green light duration, the extended green light duration is determined to meet the delay conditions. Specifically, an extended green light duration greater than or equal to the bus travel time indicates that the bus can pass through the intersection within the green light period. An extended green light duration less than or equal to the preset maximum green light duration indicates that the total extended green light duration is within a reasonable range and will not significantly affect the passage of vehicles in other directions at the intersection.

[0051] Step 105: In response to determining that the green light extension duration meets the delay condition, the green light phase is adjusted according to the green light extension duration to obtain the adjusted green light phase.

[0052] In some embodiments, the executing entity may, in response to determining that the extended green light duration meets the delay condition, adjust the green light phase according to the extended green light duration to obtain an adjusted green light phase. Specifically, the extended green light duration may be added to the time corresponding to the green light phase to increase its remaining green light duration, thus obtaining the adjusted green light phase.

[0053] Step 106: Control the corresponding traffic lights according to the adjusted traffic light phases.

[0054] In some embodiments, the aforementioned executing entity can control the corresponding traffic lights based on the adjusted traffic light phases. Specifically, it can control the green light display time and countdown timer based on the remaining green light duration of the adjusted traffic light phase. Simultaneously, the time periods corresponding to the phases of traffic lights in other directions at the road intersection are synchronously shifted backward.

[0055] Optionally, the maximum green light duration mentioned above is generated through the following steps:

[0056] Step S1: Obtain historical traffic flow videos of the aforementioned road intersection at different preset time periods. These historical traffic flow videos can be videos of the road intersection during historical time periods.

[0057] For example, different preset time periods may include: the morning peak preset time period is 7:30-8:30, the off-peak preset time period is 10:00-11:00, and the evening peak preset time period is 17:30-18:30.

[0058] Step S2 involves collecting traffic data at the aforementioned road intersection using data acquisition equipment. This equipment may include, but is not limited to, traffic cameras, laser rangefinders, etc., for collecting traffic data at the road intersection. Examples include the number of lanes, lane width, and turning radius.

[0059] Step S3 involves setting detection lines in the video frames of each historical traffic flow video and performing video frame recognition on the historical traffic flow videos to generate traffic flow information. This can be achieved using the aforementioned recognition algorithm to perform video frame recognition on the historical traffic flow videos. The traffic flow information may also include statistical information on road vehicle traffic. For example, the number of vehicles passing through a lane at a road entrance direction during a certain time period. This allows for the determination of traffic flow data for different preset time periods, different road entrance directions, and different lanes. Here, traffic flow data includes vehicle arrival volume and lane saturation capacity. Vehicle arrival volume represents the number of motor vehicles arriving within a traffic light phase. Lane saturation capacity represents the maximum stable traffic flow that can pass through a lane during a continuous green light period.

[0060] Step S4: Based on the above traffic flow information and traffic data, generate the above maximum green light duration.

[0061] In practice, the maximum green light duration is the upper limit of the continuous green light time for a certain phase, and it is adjusted according to the specific situation of the intersection and traffic demand. For example, the maximum green light duration for main roads (high-flow direction) is usually 60-90 seconds, while that for secondary roads (low-flow direction) is usually shorter, at 30-40 seconds. The minimum green light duration for main roads should not be less than 15 seconds, and for secondary roads or inductive signal control, it should not be less than 8 seconds. Here, for a preset time period for a certain lane in a certain road entrance direction at a road intersection, the corresponding maximum green light duration can be determined by the following steps: the green light time calculated using the Webster method is taken as the optimal green light time, and the value of 1.5 to 2 times the optimal green light time is rounded down to the nearest integer as the corresponding maximum green light duration. In addition, the maximum green light duration should be within the above-mentioned duration constraints.

[0062] Optionally, the aforementioned implementing entity may also include the following steps:

[0063] Step S1: In response to determining that the identification timestamp included in the bus identification information is not within the corresponding green light phase, determine the time interval of the corresponding dedicated green light phase for buses. The time interval where the identification timestamp is not within the corresponding green light phase indicates that the traffic light in the bus lane is not green. Next, the time interval of the corresponding dedicated green light phase for buses can be determined through the following steps: First, verify the time constraint Δt ≥ 60s (Δt represents the time interval since the last dedicated bus phase). If the condition is met, immediately terminate the current traffic light phase and start the dedicated bus phase (i.e., switch the traffic light phase of the bus lane from other phases to a green light phase). The dedicated green light phase for buses = [max(estimated bus passage time, minimum green light duration + green interval), min(estimated bus passage time, maximum green light duration of the dedicated bus phase + green interval)]. This calculation method ensures that the dedicated phase duration for buses meets both the bus traffic demand and the basic constraints of intersection signal timing. After the dedicated phase ends, the signal controller resumes the next phase of the original phase sequence. If the time constraint is not met, the current phase continues to operate. As an example, the maximum green light duration for a dedicated bus phase is usually short, generally 15-30 seconds. For example, 25 seconds could be used here. Additionally, the green interval is the time interval between the end of the green light of one phase and the start of the green light of the next phase, including the yellow light time and the all-red time, to clear vehicles from the intersection conflict zone. Green interval = yellow light time + all-red time. The yellow light time is fixed at three seconds, and the all-red time = intersection length / vehicle transit time (usually taken as 10 m / s).

[0064] Step S2: In response to determining that the aforementioned time interval is greater than or equal to a preset interval threshold, the corresponding traffic light is controlled according to the aforementioned bus-specific green light phase. Wherein, a time interval greater than or equal to the preset interval threshold is defined as Δt ≥ 60s.

[0065] Optional, see Figure 2 The flowchart shown is for evaluating bus priority strategies at signalized intersections based on SUMO-Python co-simulation. A detailed intersection simulation model can be built using the SUMO (Simulation of Urban Mobility) platform. The road network is rigorously drawn based on measured data using Netedit tools to ensure that parameters such as lane configuration and geometric alignment are consistent with actual conditions, thereby testing the effectiveness of different strategies under various scenarios.

[0066] Specifically, firstly, a bus priority signal control strategy is designed based on an intelligent network environment. Here, the control strategy can be implemented as shown in steps 101-106 above. Then, traffic data and traffic flow information collected from on-site surveys of the intersection are analyzed to obtain traffic information for the road intersection. Next, vehicle detection equipment is built using an intelligent network environment. For example, laser rangefinders and the aforementioned computing devices are deployed. Then, the existing signal configuration scheme for the intersection is parameterized by combining various data to construct an intersection model. Here, relevant parameters are entered into the SUMO traffic signal configuration file to obtain the road network file (*.net.xml) for intersection simulation. Based on traffic flow survey data, traffic flow files (*.rou.xml) are set for three different time periods: morning peak, off-peak, and evening peak. The road network file, traffic flow file, and control information are integrated by editing the configuration file (*.sumocfg), and the simulation time is set for simulation operation (sumo-gui), thereby outputting the corresponding maximum green light duration. Then, the set bus priority signal (traffic light) control strategy is combined (as shown in steps 101-106 above). Simultaneously, a dynamic signal control module based on the TraCI (Traffic Control Interface) interface can be implemented. A control module written in Python can be used to perform the following simulation test: For example, when a bus is detected, the current traffic light phase is determined. If it is a green light phase, a command is sent using the TraCI interface to extend the green light time; if it is a non-green light phase, a dedicated bus phase is inserted if the condition "more than 60 seconds have passed since the last dedicated bus phase" is met; otherwise, the existing phase is maintained.

[0067] Next, based on the simulation results, scripts for various detection parameters are written for simulation testing. For example, the simulation test scenario is as follows:

[0068] Scenario A: For a regular road intersection without a dedicated bus lane, a signal cycle is 90 seconds. The north-south green light and the east-west green light are each 40 seconds, the yellow light is 3 seconds, and the all-red light is 2 seconds. Regardless of whether a bus arrives or not, the duration of each phase remains unchanged, and no green light phase adjustment is made.

[0069] Scenario B: This scenario applies a bus priority strategy at signalized intersections on ordinary roads without dedicated bus lanes (i.e., the implementation methods described in steps 101-106 above).

[0070] Example 1: When a bus arrives at a signalized intersection, the green light for both the north and south sides has 10 seconds remaining. The bus needs 15 seconds to pass through the intersection. Therefore, the green light is extended by 5 seconds (less than the maximum green light duration for the bus-only phase).

[0071] Example 2: If a bus arrives during the east-west green light period and 70 seconds have passed since the last priority phase, it should immediately switch to the north-south green light period.

[0072] Scenario C: This scenario involves applying a bus priority strategy at signalized intersections on roads with dedicated bus lanes (i.e., applying the implementation methods described in steps 101-106 above). The application is the same as in Examples 1 and 2 of Scenario B.

[0073] Here, both Scenario B and Scenario C apply the bus priority strategy at signalized intersections, the difference being that Scenario B has no dedicated bus lane, while Scenario C does. These scenario settings can be used to determine the merits of each strategy in an intersection simulation model. Specifically, all simulation data obtained at different times under Scenario A constitutes Result A; similarly, simulations under Scenario B and Scenario C yield Result B and Result C, respectively. Finally, a comparative analysis of the parameters in Result A, Result B, and Result C reveals that, whether comparing parameters within the same time period or comparing the average values ​​of parameters across the three time periods, the results clearly demonstrate the applicability and optimization effect of the bus priority signal control strategy (Scenario B and Scenario C). For example, Result B and Result C both show reduced average bus delay time, fewer stops, and reduced pollution emissions. Therefore, through the above implementation method, long-term traffic flow data of road intersections and systematic consideration of control effects can be introduced, so that the signal timing (i.e. traffic light phase) can be varied within a reasonable range, achieving Pareto optimality (maximum green light duration) between control cost and dynamic response capability, thereby improving the overall traffic efficiency of the road network.

[0074] The various embodiments of this disclosure have the following beneficial effects: the traffic light control method based on co-simulation of some embodiments of this disclosure can improve the overall traffic efficiency of the road network. Specifically, the reason for the reduction in the overall traffic efficiency of the generated road network is that the current bus priority control strategy still has significant limitations in terms of adaptability and refinement. Most systems still rely on static timetables or fixed priority triggering mechanisms, which are difficult to effectively cope with the spatiotemporal heterogeneity and random disturbances of urban traffic flow. Traditional methods are difficult to achieve Pareto optimality between control cost and dynamic response capability, and due to the lack of systematic consideration of long-term control effects, they often lead to frequent fluctuations in signal timing or damage to the overall traffic efficiency of the road network. Based on this, the traffic light control method based on co-simulation of some embodiments of this disclosure first acquires traffic flow video at the road intersection. Then, bus identification is performed on the traffic flow video to obtain bus identification information, which includes the identified bus logo, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp. Here, identification can be used to determine whether a bus has entered the road intersection. Next, in response to determining that the identification timestamp included in the bus identification information falls within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, the corresponding bus travel duration is determined based on the bus identification information. Here, determining the bus travel duration can be used to determine whether the bus meets the passage conditions. Then, in response to determining that the bus travel duration exceeds the time period of the green light phase, a corresponding green light extension duration is determined based on a preset maximum green light duration. This maximum green light duration corresponds to the identification timestamp and is generated based on a joint simulation of historical traffic flow videos and traffic data from the road intersection. Here, generating the green light extension duration can be used to appropriately extend the green light duration, thereby improving bus passage efficiency. Then, in response to determining that the green light extension duration meets the delay conditions, the green light phase is adjusted according to the green light extension duration to obtain the adjusted green light phase. Finally, the corresponding traffic lights are controlled according to the adjusted traffic light phase. Here, considering the lack of long-term control effects in the system, the maximum green light duration generated by co-simulation is introduced as a reference. This ensures that the generated traffic light extension duration meets the current traffic demand at the intersection, thus avoiding negative impacts on other vehicles. Furthermore, the traffic light phases can be adjusted appropriately to control the traffic lights and improve the overall traffic efficiency of the road network.

[0075] Further reference Figure 3 As an implementation of the methods shown in the above figures, this disclosure provides some embodiments of a traffic light control device based on co-simulation. These device embodiments are similar to... Figure 1Corresponding to the method embodiments shown, this co-simulation-based traffic light control device can be specifically applied to various electronic devices.

[0076] like Figure 3 As shown, a traffic light control device 300 based on co-simulation in some embodiments includes: an acquisition unit 301, a bus identification unit 302, a first determination unit 303, a second determination unit 304, an adjustment unit 305, and a traffic light control unit 306. The acquisition unit 301 is configured to acquire traffic flow video at a road intersection; the bus identification unit 302 is configured to perform bus identification on the traffic flow video to obtain bus identification information, wherein the bus identification information includes the identified bus logo, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp; the first determination unit 303 is configured to, in response to determining that the identification timestamp included in the bus identification information is within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, determine the corresponding bus passage time based on the bus identification information; the second... The determining unit 304 is configured to, in response to determining that the bus travel time exceeds the green light phase, determine a corresponding green light extension duration based on a preset maximum green light duration, wherein the maximum green light duration corresponds to the identification timestamp and is generated based on joint simulation of historical traffic flow video and traffic data of the road intersection; the adjusting unit 305 is configured to, in response to determining that the green light extension duration meets the delay condition, adjust the green light phase according to the green light extension duration to obtain an adjusted green light phase; the traffic light control unit 306 is configured to control the corresponding traffic light according to the adjusted traffic light phase.

[0077] It is understandable that the units described in the co-simulation-based traffic light control device 300 are related to the reference... Figure 1 The steps in the described method correspond to each other. Therefore, the operations, features, and beneficial effects described above for the method also apply to the traffic light control device 300 based on co-simulation and the units contained therein, and will not be repeated here.

[0078] The following is for reference. Figure 4 It illustrates a schematic diagram of the structure of an electronic device (such as a computing device) suitable for implementing some embodiments of the present disclosure. Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality or scope of the embodiments of this disclosure. Figure 4As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The memory may include a non-volatile storage medium and internal memory. The non-volatile storage medium may store an operating system and a computer program. The computer program includes program instructions that, when executed, cause the processor to perform any of the methods described above. The processor provides computational and control capabilities to support the operation of the entire computer device. The internal memory provides an environment for the execution of the computer program in the non-volatile storage medium; when executed by the processor, the computer program causes the processor to perform any of the methods described above. The network interface is used for network communication, such as sending assigned tasks. Those skilled in the art will understand that... Figure 4 The structure shown is merely a block diagram of a portion of the structure related to the present disclosure and does not constitute a limitation on the computer device to which the present disclosure is applied. A specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0079] It should be understood that the processor can be a Central Processing Unit (CPU), but it can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among these, a general-purpose processor can be a microprocessor or any conventional processor.

[0080] In one embodiment, the processor is configured to run a computer program stored in a memory to perform the following steps: acquiring a traffic flow video of a road intersection; performing bus identification on the traffic flow video to obtain bus identification information, wherein the bus identification information includes the identified bus identifier, bus coordinates, bus operating status, bus speed value, bus acceleration value, and identification timestamp; in response to determining that the identification timestamp included in the bus identification information is within the time period of the corresponding green light phase, and that the bus operating status represents the vehicle's forward movement, determining the corresponding bus passage duration based on the bus identification information; in response to determining that the bus passage duration exceeds the time period of the green light phase, determining the corresponding green light extension duration based on a preset maximum green light duration, wherein the maximum green light duration corresponds to the identification timestamp, and the maximum green light duration is generated based on a joint simulation of historical traffic flow video and traffic data of the road intersection; in response to determining that the green light extension duration meets the delay condition, adjusting the green light phase according to the green light extension duration to obtain an adjusted green light phase; and controlling the corresponding traffic lights according to the adjusted traffic light phase.

[0081] This disclosure also provides a computer-readable storage medium storing a computer program, the computer program including program instructions, and the method implemented when the program instructions are executed can be referred to the various embodiments of the methods described above.

[0082] The aforementioned computer-readable storage medium may be an internal storage unit of the computer device described in the foregoing embodiments, such as the hard disk or memory of the computer device. Alternatively, the aforementioned computer-readable storage medium may be an external storage device of the computer device, such as a plug-in hard disk, SmartMedia Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the computer device.

[0083] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0084] The above description is merely a selection of preferred embodiments of this disclosure and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of the invention involved in the embodiments of this disclosure is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the above-described inventive concept. For example, technical solutions formed by substituting the above-described features with (but not limited to) technical features with similar functions disclosed in the embodiments of this disclosure.

Claims

1. A traffic light control method based on joint simulation, characterized by, The method comprises: acquiring a vehicle flow video of a road intersection; performing bus identification on the vehicle flow video to obtain bus identification information, wherein the bus identification information comprises an identified bus identifier, bus coordinates, a bus running state, a bus speed value, a bus acceleration value, and an identification timestamp; in response to determining that the identification timestamp included in the bus identification information is within a time period of a corresponding green light phase and that the bus running state represents a vehicle forward running state, determining a corresponding bus passing time length based on the bus identification information; in response to determining that the bus passing time length exceeds the time period of the green light phase, determining a corresponding green light extension time length based on a preset maximum green light time length, wherein the maximum green light time length corresponds to the identification timestamp, and the maximum green light time length is generated based on joint simulation of historical vehicle flow videos and traffic data of the road intersection; in response to determining that the green light extension time length satisfies a delay condition, adjusting the green light phase according to the green light extension time length to obtain an adjusted green light phase; controlling a corresponding traffic light according to the adjusted red-green light phase.

2. The method of claim 1, wherein, The method further comprises: in response to determining that the identification timestamp included in the bus identification information is not within a time period of a corresponding green light phase, determining a time interval of a corresponding bus-only green light phase; in response to determining that the time interval is greater than or equal to a preset interval threshold, controlling a corresponding traffic light according to the bus-only green light phase.

3. The method of claim 1, wherein, The bus identification on the vehicle flow video to obtain bus identification information comprises: frame extraction on the vehicle flow video to obtain a vehicle flow image group; vehicle identification on the vehicle flow image group to generate a vehicle flow identification information group, wherein the vehicle flow identification information comprises a target detection frame, a bus identifier, a license plate number, and a corresponding identification timestamp; screening of the vehicle flow identification information group based on a preset bus running database to obtain target vehicle flow information; acquisition of bus coordinates, a bus running state, a bus speed value, and a bus acceleration value corresponding to the target vehicle flow information; determination of the bus coordinates, the bus running state, the bus speed value, the bus acceleration value, and the target vehicle flow information as the bus identification information.

4. The method of claim 1, wherein, The determination of the corresponding bus passing time length based on the bus identification information in response to the determination that the identification timestamp included in the bus identification information is within the time period of the corresponding green light phase and that the bus running state represents the vehicle forward running state comprises: determination of a bus travel distance based on a distance value between the bus coordinates in the bus identification information and preset intersection passing coordinates; determination of the corresponding bus passing time length based on the bus travel distance, the bus speed value, and the bus acceleration value in the bus identification information.

5. The method of claim 1, wherein, The determination of the corresponding green light extension time length based on the preset maximum green light time length in response to the determination that the bus passing time length exceeds the time period of the green light phase comprises: acquisition of a remaining green light time length of the green light phase; According to the bus passing time, the remaining green light time and the preset maximum green light time, a corresponding green light extension time is determined.

6. The method of claim 1, wherein, Before the green light phase is adjusted according to the green light extension time to obtain an adjusted green light phase, the method further comprises: In response to determining that the green light extension time is greater than or equal to the bus passing time and the green light extension time is less than or equal to the preset maximum green light time, it is determined that the green light extension time meets the delay condition.

7. The method of claim 6, wherein, The maximum green light time is generated by the following steps: Obtain historical traffic videos of the road intersection in different preset time periods; Collect traffic data of the road intersection through a data collection device; Set a detection line in each video frame of the historical traffic videos, and perform video frame recognition on the historical traffic videos to generate traffic information; Based on the traffic information and the traffic data, the maximum green light time is generated.

8. A traffic light control device based on joint simulation, characterized by, Comprise: An acquisition unit configured to acquire a traffic video of a road intersection; A bus identification unit configured to identify a bus in the traffic video to obtain bus identification information, wherein the bus identification information includes an identified bus identifier, bus coordinates, a bus running state, a bus speed value, a bus acceleration value and an identification timestamp; A first determination unit configured to, in response to determining that the identification timestamp included in the bus identification information is within a time period of a corresponding green light phase and the bus running state represents a vehicle forward running state, determine a corresponding bus passing time based on the bus identification information; A second determination unit configured to, in response to determining that the bus passing time exceeds the time period of the green light phase, determine a corresponding green light extension time based on a preset maximum green light time, wherein the maximum green light time corresponds to the identification timestamp, and the maximum green light time is generated based on joint simulation of historical traffic videos and traffic data of the road intersection; An adjustment unit configured to, in response to determining that the green light extension time meets a delay condition, adjust the green light phase according to the green light extension time to obtain an adjusted green light phase; A traffic light control unit configured to control a corresponding traffic light according to the adjusted traffic light phase.

9. An electronic device, comprising: Comprise: One or more processors; A storage device having one or more programs stored thereon, When the one or more programs are executed by the one or more processors, the one or more processors implement the method of any one of claims 1-7.

10. A computer readable medium characterized by A computer program is stored thereon, wherein the program is executed by a processor to implement the method of any one of claims 1-7.

Images