Traffic signal lamp control method and system based on artificial intelligence, medium and equipment

Abstract

The invention discloses a traffic signal lamp control method and system based on artificial intelligence, a medium and equipment. The method comprises the following steps: a traffic flow detection step: collecting traffic data of motor vehicles, non-motor vehicles and pedestrians in real time; a data analysis step: analyzing the collected data based on an AI algorithm, and generating a dynamic signal timing scheme; emergency vehicle priority: collecting emergency vehicle passing data, and controlling signal lamps of corresponding intersections; a pedestrian priority step: dynamically adjusting a pedestrian signal lamp time period according to pedestrian data detected in the traffic flow detection step at night; according to the method, the traffic flow detection step, the data analysis step, the emergency vehicle priority step, the pedestrian priority step and the AI prediction step are designed, so that the signal lamp timing can be intelligently adjusted according to the real-time traffic condition, and the traffic flow detection step, the data analysis step, the emergency vehicle priority step, the pedestrian priority step and the AI prediction step are integrated. Therefore, traffic jam is effectively relieved, and traffic efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the field of traffic light control, and particularly to a traffic signal control method, system, medium and device based on artificial intelligence. Background Art

[0002] With the acceleration of the urbanization process, the problem of traffic congestion has become increasingly serious. The traditional traffic signal control method has been difficult to meet the needs of modern urban traffic management. Traditional traffic signal control mainly relies on fixed time intervals or preset traffic flow patterns. In the face of complex and changeable traffic conditions, this method often fails to make timely and effective adjustments, resulting in traffic congestion and low efficiency. Therefore, it is particularly important to develop a method that can intelligently adjust the signal control strategy according to the actual situation. Summary of the Invention

[0003] The technical problem solved by the present invention is to provide an artificial intelligence-based traffic signal control method that can adapt to complex traffic scenarios and improve the overall traffic efficiency.

[0004] The technical solution adopted by the present invention to solve its technical problems is: an artificial intelligence-based traffic signal control method, including the following steps:

[0005] Traffic flow detection step: Real-time collect motor vehicle, non-motor vehicle and pedestrian flow data through cameras, radars and geomagnetic sensors;

[0006] Data analysis step: Analyze the collected data based on AI algorithms to generate a dynamic signal timing plan;

[0007] Emergency vehicle priority step: Collect emergency vehicle passing data and control the signal lights at corresponding intersections to change to passing lights;

[0008] Pedestrian priority step: Set a night time period, and dynamically adjust the pedestrian signal time period according to the pedestrian data detected in the traffic flow detection step at night;

[0009] AI prediction step: Analyze historical traffic data through an AI model, predict congestion events, and adjust the signal timing in advance.

[0010] Furthermore: In the traffic flow detection step, specifically:

[0011] Collect motor vehicle, non-motor vehicle and pedestrian flow data through multi-source data fusion technology;

[0012] Identify traffic scenarios and classify and detect vehicles;

[0013] Adopt deep learning algorithms to process traffic flow data in real time, identify abnormal events and trigger an emergency response mechanism.

[0014] Furthermore, the emergency vehicle priority step is specifically as follows:

[0015] Identify the behavior of emergency vehicles through AI vision technology and modify the signal lights at the current intersection to become passing lights.

[0016] Collect the routes of emergency vehicles and dynamically adjust the signal light timing at subsequent intersections.

[0017] Furthermore, the pedestrian priority step is specifically as follows:

[0018] Set the waiting time threshold for pedestrians to cross the street. When the detected waiting time of pedestrians exceeds this threshold, automatically extend the green light time of the pedestrian signal light;

[0019] During the night time period, adjust the cycle of the pedestrian signal light according to the dynamic changes in pedestrian flow data;

[0020] Optimize the signal light timing strategy through the pedestrian crossing behavior characteristics.

[0021] Furthermore, the AI prediction step is specifically as follows:

[0022] Combine historical traffic data and real-time traffic data to train the AI prediction model;

[0023] Adjust the signal light timing in advance according to the prediction results;

[0024] Classify the predicted congestion events and formulate corresponding signal light adjustment strategies according to the event levels.

[0025] Furthermore, it also includes a traffic signal light fault detection step, specifically as follows: Monitor the working state of the signal lights, compare the working state of the signal lights with the actual set state, and detect whether there are faults in the signal lights; If a fault is detected, immediately trigger the alarm mechanism and take over the control right of the faulty signal lights through the backup signal light control system.

[0026] Furthermore, in the traffic signal light fault detection step, there is also a fault type judgment step, specifically as follows: Judge the fault type through the abnormal information of the working state of the signal lights, provide corresponding fault handling suggestions, and at the same time upload the fault information, fault handling suggestions and fault handling results to the traffic management cloud platform in real time.

[0027] The present invention discloses an artificial intelligence-based traffic signal control system, including a traffic flow detection module, a data analysis module, an emergency vehicle priority module, a pedestrian priority module, and an AI prediction module;

[0028] The traffic flow detection module is used to collect real-time traffic flow data of motor vehicles, non-motor vehicles and pedestrians through cameras, radars and geomagnetic sensors;

[0029] The data analysis module is used to analyze the collected data based on AI algorithms and generate a dynamic signal timing plan;

[0030] The emergency vehicle priority module is used to collect the passing data of emergency vehicles and control the signal lights at corresponding intersections to change to passing lights;

[0031] The pedestrian priority module is used to set a night time period, and the night time period dynamically adjusts the pedestrian signal light time period according to the pedestrian data detected in the traffic flow detection step;

[0032] The AI prediction module is used to analyze historical traffic data through an AI model, predict events such as traffic accidents and congestion, and adjust the signal light timing in advance.

[0033] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned traffic signal control method based on artificial intelligence are realized.

[0034] The present invention also discloses a computer device, including a processor, a communication interface, a memory and a communication bus. Among them, the processor, the communication interface and the memory complete mutual communication through the communication bus; among them:

[0035] The memory is used to store a computer program;

[0036] The processor is used to execute the steps of the above-mentioned traffic signal control method based on artificial intelligence by running the program stored on the memory.

[0037] The beneficial effects of the present invention are:

[0038] 1. Through the design of the traffic flow detection step, data analysis step, emergency vehicle priority step, pedestrian priority step and AI prediction step in the present invention, the signal light timing can be intelligently adjusted according to the real-time traffic conditions, thereby effectively alleviating traffic congestion and improving traffic efficiency.

[0039] 2. Through the traffic signal fault detection step, signal light faults can be detected and processed in time, ensuring the continuous and stable operation of traffic signal lights, and reducing traffic chaos and safety hazards caused by signal light faults. The implementation of the fault detection step further improves the reliability and safety of the entire traffic signal control system. Description of the Drawings

[0040] Figure 1Schematic flowchart of the AI - based traffic signal control method according to the embodiments of the present application.

[0041] Figure 2 Schematic framework diagram of the AI - based traffic signal control system according to the embodiments of the present application. Detailed implementation manners

[0042] To make the above - mentioned objects, features and advantages of the present invention more obvious and understandable, the following will describe the detailed implementation manners of the present invention with reference to the accompanying drawings.

[0043] As Figure 1 shown, the embodiments of the present application disclose an AI - based traffic signal control method, including the following steps:

[0044] Traffic flow detection step: Real - time collect the traffic data of motor vehicles, non - motor vehicles and pedestrians through cameras, radars and geomagnetic sensors;

[0045] Data analysis step: Analyze the collected data based on AI algorithms to generate a dynamic signal timing plan;

[0046] Emergency vehicle priority step: Collect the passing data of emergency vehicles and control the signal lights at corresponding intersections to change to passing lights;

[0047] Pedestrian priority step: Set a night time period, and dynamically adjust the pedestrian signal light period according to the pedestrian data detected in the traffic flow detection step during the night time period;

[0048] AI prediction step: Analyze historical traffic data through an AI model to predict congestion events and adjust the signal timing in advance.

[0049] During specific operations, first, the traffic flow detection step utilizes devices such as cameras, radars, and geomagnetic sensors to comprehensively and real-time monitor the flow data of motor vehicles, non-motor vehicles, and pedestrians. Next, the data analysis step activates AI algorithms to deeply mine and analyze the data collected in the traffic flow detection step. The AI algorithms can identify peak and trough periods of traffic flow, as well as the main composition of traffic flow during different time periods. Based on this information, the AI algorithms generate a set of dynamic signal timing plans. Then, in the emergency vehicle priority step, once an emergency vehicle (such as an ambulance, fire truck, etc.) is detected, the system immediately adjusts the signal timing at the corresponding intersections to ensure that the emergency vehicle can pass quickly and smoothly. During the night time, based on the pedestrian data detected in the traffic flow detection step, the timing and allocation of pedestrian signals are dynamically adjusted to ensure the safe passage of pedestrians. Finally, the AI prediction step uses AI models to perform in-depth learning on historical traffic data to predict possible future events such as congestion. Once these events are predicted, the system immediately adjusts the signal timing to divert traffic flow in advance, avoiding or reducing traffic accidents and congestion.

[0050] Therefore, through the design of the traffic flow detection step, data analysis step, emergency vehicle priority step, pedestrian priority step, and AI prediction step in the present invention, the signal timing can be intelligently adjusted according to the real-time traffic conditions, thereby effectively alleviating traffic congestion and improving traffic efficiency.

[0051] In this embodiment, in the traffic flow detection step, specifically:

[0052] Motor vehicle, non-motor vehicle, and pedestrian flow data are obtained through multi-source data fusion technology;

[0053] Traffic scene recognition and vehicle classification detection are carried out;

[0054] Deep learning algorithms are used to real-time process traffic flow data, identify abnormal events, and trigger an emergency response mechanism.

[0055] Specifically, when collecting data, information from multiple data sources such as cameras, radars, and geomagnetic sensors is integrated to achieve comprehensive and accurate monitoring of the traffic flow data of motor vehicles, non-motor vehicles, and pedestrians. At the same time, advanced image recognition and deep learning algorithms are adopted. By analyzing the images captured by the cameras in real time, the system can accurately identify different traffic scenarios, such as intersections, highways, etc., and classify vehicles in detail, such as cars, buses, trucks, etc. This helps to understand the composition of traffic flow more precisely. In addition, through the training and learning of historical data, the deep learning algorithm can identify the changing trends and abnormal events of traffic flow. Once an abnormal event is detected, such as a traffic accident, road construction, etc., the system will immediately trigger an emergency response mechanism and adjust the signal timing to cope with emergencies, thus ensuring smooth and safe traffic.

[0056] In this embodiment, the emergency vehicle priority step is specifically as follows:

[0057] Identify the behavior of emergency vehicles through AI vision technology and modify the signal lights at the current intersection to green lights for passage.

[0058] Collect the routes of emergency vehicles and dynamically adjust the signal timing of subsequent intersections.

[0059] Specifically, the system uses AI vision technology to analyze the images captured by the cameras in real time to accurately identify emergency vehicles, such as ambulances, fire trucks, etc. Once the appearance of an emergency vehicle is detected, the system will immediately adjust the signal timing at the current intersection and change the signal lights to green lights for passage to ensure that the emergency vehicle can pass quickly. At the same time, the system will collect the driving routes of emergency vehicles and, based on this information, dynamically adjust the signal timing of subsequent intersections to provide a clear driving path for emergency vehicles.

[0060] The above design can greatly improve the passing efficiency of emergency vehicles, ensure that in case of an emergency, the rescue force can reach the scene quickly, thus effectively reducing disaster losses and ensuring the safety of people's lives and property.

[0061] In this embodiment, the pedestrian priority step is specifically as follows:

[0062] Set a threshold for the waiting time of pedestrians crossing the street. When the detected waiting time of pedestrians exceeds this threshold, automatically extend the green light time of the pedestrian signal;

[0063] During the night period, adjust the cycle of the pedestrian signal according to the dynamic changes in pedestrian flow data;

[0064] Optimize the signal timing strategy based on the behavioral characteristics of pedestrians crossing the street.

[0065] Specifically, when the system detects that the waiting time of pedestrians at an intersection exceeds this threshold, it will automatically extend the green light time of the pedestrian signal to ensure that pedestrians can cross the road safely and smoothly. Especially during the night hours, due to the relatively low traffic flow, the system will flexibly adjust the cycle of the pedestrian signal according to the dynamic changes in pedestrian flow data to reduce the waiting time of pedestrians.

[0066] In this embodiment, the AI prediction step is specifically as follows:

[0067] Combining historical traffic data and real-time traffic data to train an AI prediction model;

[0068] Adjusting the signal timing in advance according to the prediction results;

[0069] Classifying the predicted congestion events and formulating corresponding signal adjustment strategies according to the event levels.

[0070] Specifically, the AI prediction step combines historical traffic data and real-time traffic data, and through advanced machine learning and deep learning algorithms, trains an accurate AI prediction model. This model can predict possible future traffic congestion events, including the location, time, and possible severity of congestion. Once these events are predicted, the system will immediately adjust the signal timing according to the prediction results, such as increasing the green light time in advance and reducing the red light time, etc., to divert the traffic flow and avoid or mitigate the occurrence of congestion. In addition, the system will also classify the predicted congestion events, such as slight congestion, moderate congestion, and severe congestion, etc., and formulate corresponding signal adjustment strategies according to the event levels.

[0071] In this embodiment, it also includes a traffic signal fault detection step, specifically: monitoring the working state of the signal lamp, comparing the working state of the signal lamp with the actual set state to detect whether there is a fault in the signal lamp; if a fault is detected, immediately trigger an alarm mechanism and take over the control right of the faulty signal lamp through the backup signal lamp control system. In the traffic signal fault detection step, it also includes a fault type judgment step, specifically: judging the fault type through the abnormal working state information of the signal lamp, providing corresponding fault handling suggestions, and uploading the fault information, fault handling suggestions, and fault handling results to the traffic management cloud platform in real time.

[0072] Specifically, the system obtains the working status data of traffic lights in real time, including key parameters such as the on / off status, brightness, and flashing frequency of traffic lights. Subsequently, the system compares the collected data with the actually set traffic light status. Through comparative analysis, the system can accurately determine whether there is a fault in the traffic light. Once a fault is found in the traffic light, the system will immediately trigger an alarm mechanism. For example, sending an alarm message to traffic management personnel. At the same time, to ensure the continuity and safety of traffic, the system will quickly activate the backup traffic light control system and take over the control right of the faulty traffic light.

[0073] In the present invention, by detecting faults in traffic lights, it is possible to promptly discover and handle traffic light faults, ensure the continuous and stable operation of traffic lights, and reduce traffic chaos and safety hazards caused by traffic light faults.

[0074] The present invention also discloses an artificial intelligence-based traffic light control system, including a traffic flow detection module, a data analysis module, an emergency vehicle priority module, a pedestrian priority module, and an AI prediction module;

[0075] The traffic flow detection module is used to collect traffic data of motor vehicles, non-motor vehicles, and pedestrians in real time through cameras, radars, and geomagnetic sensors;

[0076] The data analysis module is used to analyze the collected data based on AI algorithms and generate a dynamic signal timing plan;

[0077] The emergency vehicle priority module is used to collect the passing data of emergency vehicles and control the traffic lights at corresponding intersections to change to passing lights;

[0078] The pedestrian priority module is used to set a night time period, and the night time period dynamically adjusts the pedestrian traffic light time period according to the pedestrian data detected in the traffic flow detection step;

[0079] The AI prediction module is used to analyze historical traffic data through an AI model, predict events such as traffic accidents and congestion, and adjust the signal timing in advance.

[0080] In the present invention, through the design of the traffic flow detection step, data analysis step, emergency vehicle priority step, pedestrian priority step, and AI prediction step, it is possible to intelligently adjust the signal timing according to the real-time traffic conditions, thereby effectively alleviating traffic congestion and improving traffic efficiency.

[0081] The present invention also discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the above-mentioned artificial intelligence-based traffic light control method are implemented.

[0082] In addition, the computer-readable storage medium of this embodiment may adopt any combination of one or more readable storage media. Among them, the readable storage medium includes an electrical, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination of the above.

[0083] The present invention also discloses a computer device, including a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus. Specifically:

[0084] The memory is used to store a computer program.

[0085] The processor is used to execute the steps of the above-mentioned traffic signal control method based on artificial intelligence by running the program stored in the memory.

[0086] As an embodiment of the present invention, the communication bus mentioned in the above terminal may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0087] As an embodiment of the present invention, the communication interface is used for communication between the above terminal and other devices.

[0088] As an embodiment of the present invention, the memory may include a Random Access Memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located far from the aforementioned processor.

[0089] As an implementation manner of the present invention, the above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0090] The above-mentioned specific embodiments have further detailed the purpose, technical solution and beneficial effects of the present invention. It should be understood that the above are only specific embodiments of the present invention and are not used to limit the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A traffic signal control method based on artificial intelligence, characterized in that It includes the following steps: Traffic flow detection step: Real-time collection of motor vehicle, non-motor vehicle and pedestrian flow data through cameras, radars and geomagnetic sensors; Data analysis step: Analyze the collected data based on AI algorithms to generate a dynamic signal timing plan; Emergency vehicle priority step: Collect the passing data of emergency vehicles and control the signal lights at corresponding intersections to change to green lights; Pedestrian priority step: Set a night time period, and during the night time period, dynamically adjust the pedestrian signal light period according to the pedestrian data detected in the traffic flow detection step; AI prediction step: Analyze historical traffic data through an AI model, predict congestion events, and adjust the signal light timing in advance.

2. The traffic signal control method based on artificial intelligence according to claim 1, wherein, In the traffic flow detection step, specifically: Use multi-source data fusion technology for motor vehicle, non-motor vehicle and pedestrian flow data; Perform traffic scene recognition and vehicle classification detection; Use deep learning algorithms to process traffic flow data in real time, identify abnormal events and trigger an emergency response mechanism.

3. The traffic signal control method based on artificial intelligence according to claim 1, wherein, The emergency vehicle priority step, specifically: Use AI vision technology to identify the behavior of emergency vehicles and modify the signal lights at the current intersection to change to green lights. Collect the routes of emergency vehicles and dynamically adjust the signal light timing at subsequent intersections.

4. The traffic signal control method based on artificial intelligence according to claim 1, characterized in that The pedestrian priority step: specifically: Set a threshold for the pedestrian waiting time at crosswalks. When the detected pedestrian waiting time exceeds this threshold, automatically extend the green light time of the pedestrian signal; During the night time period, adjust the pedestrian signal light cycle according to the dynamic changes in pedestrian flow data; Optimize the signal light timing strategy through the characteristics of pedestrian crossing behavior.

5. The traffic signal control method based on artificial intelligence according to claim 1, characterized in that, The AI prediction step, specifically: Combine historical traffic data and real-time traffic data to train an AI prediction model; Adjust the signal light timing in advance according to the prediction results; Classify the predicted congestion events and formulate corresponding signal light adjustment strategies according to the event levels.

6. The traffic signal control method based on artificial intelligence according to claim 1, characterized in that It also includes a traffic signal light fault detection step, specifically: Monitor the working status of the signal lights, compare the working status of the signal lights with the actual set status, and detect whether there are faults in the signal lights; If a fault is detected, immediately trigger an alarm mechanism and take over the control right of the faulty signal lights through a backup signal light control system.

7. The traffic signal control method based on artificial intelligence according to claim 6, characterized in that, In the traffic signal light fault detection step, there is also a fault type judgment step, specifically: Judge the fault type through the abnormal information of the working status of the signal lights, provide corresponding fault handling suggestions, and at the same time upload the fault information, fault handling suggestions and fault handling results to the traffic management cloud platform in real time.

8. An artificial intelligence-based traffic signal control system, characterized in that: It includes a traffic flow detection module, a data analysis module, an emergency vehicle priority module, a pedestrian priority module, and an AI prediction module; The traffic flow detection module is used to real-time collect motor vehicle, non-motor vehicle and pedestrian flow data through cameras, radars and geomagnetic sensors; The data analysis module is used to analyze the collected data based on AI algorithms to generate a dynamic signal timing plan; The emergency vehicle priority module is used to collect the passing data of emergency vehicles and control the signal lights at corresponding intersections to change to green lights; The pedestrian priority module is used to set a night time period, and the night time period dynamically adjusts the pedestrian signal light time period according to the pedestrian data detected in the traffic flow detection step; The AI prediction module is used to analyze historical traffic data through an AI model, predict events such as traffic accidents and congestion, and adjust the signal timing in advance.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the artificial intelligence-based traffic signal control method described in any one of claims 1 to 7 are implemented.

10. A computer device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus; where: The memory is used to store a computer program; The processor is used to execute the steps of the artificial intelligence-based traffic signal control method described in any one of claims 1 to 7 by running the program stored on the memory.

Images