Traffic control system based on road condition information
Through a traffic control system based on road conditions information, real-time collection and analysis of road information and adaptive adjustment of signal lights, the problem that the existing system cannot adjust according to real-time road conditions is solved, traffic management efficiency and traffic efficiency are improved, traffic congestion and vehicle commuting are reduced time.
Patent Information
- Application Number
- CN202411460835.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-18
- Publication Date
- 2024-11-29
AI Technical Summary
The existing traffic control system lacks flexibility and is difficult to adjust according to real-time road conditions, resulting in inefficient night traffic management and difficult to solve the problem of traffic congestion.
A traffic control system based on road condition information was designed, including road condition information collection module, traffic flow simulation module and dynamic adjustment module. By collecting and analyzing road information in real time, adaptively adjusting the time parameters of the signal lights and the vehicle passing order, the traffic flow is realized. accurate monitoring and regulation.
It improves road traffic efficiency, alleviates traffic congestion, shortens vehicle commuting time, enhances traffic management efficiency and level, and reduces the work burden of managers.
Smart Images

Figure CN119049308A_ABST
Abstract
Description
Technical Field
[0001] The invention discloses a traffic control system based on road condition information, belonging to the technical field of traffic control. Background Art
[0002] With the acceleration of urbanization worldwide, the size of cities continues to expand, and the population and number of vehicles are growing sharply. With the increase in the number of vehicles, the traffic capacity of urban roads has gradually reached saturation, and traffic pressure has increased year by year. Especially during rush hour and holidays, traffic congestion is particularly serious, causing great trouble to people's travel.
[0003] At present, the traffic control systems in most cities still rely on fixed signal light control and preset traffic rules. This system lacks flexibility and is difficult to flexibly adjust according to real-time road conditions, making it difficult to effectively solve the problem of traffic congestion. At night, due to the small number of vehicles at traffic intersections, traditional traffic control systems are difficult to flexibly adjust according to real-time road conditions. This leads to inefficient nighttime traffic management and is prone to traffic congestion and traffic accidents. The existing traffic control system lacks the ability to obtain and analyze real-time road condition information. This makes it impossible for the system to make intelligent adjustments according to real-time road conditions, thus affecting the efficiency and effectiveness of traffic management. Summary of the invention
[0004] The purpose of the present invention is to provide a traffic control system based on road condition information to solve the technical problem that the prior art cannot make real-time adjustments according to road conditions. To achieve the above purpose, the present invention proposes a traffic control system based on road condition information, and the specific scheme is as follows:
[0005] A traffic control system based on road condition information, comprising a road condition information acquisition module, a traffic flow simulation module and a dynamic adjustment module;
[0006] The road condition information collection module is arranged on the roads in each direction of the intersection, and is used to collect and transmit road condition information;
[0007] The traffic flow simulation module is used to predict the traffic flow information of the intersection in real time according to the received road condition information;
[0008] The dynamic adjustment module is used to adjust the traffic in the preset direction to a red light state when determining that the traffic flow information in the preset direction of the intersection meets the preset rules.
[0009] Preferably, the preset rule is that no vehicles pass within a preset time period or the number of vehicles passing within the preset time period is less than a preset value.
[0010] Preferably, the dynamic adjustment module further includes an adaptive adjustment unit;
[0011] The adaptive adjustment unit is used to generate a traffic indication strategy for the intersection according to the traffic flow information and the preset rules.
[0012] Preferably, the traffic flow simulation module includes a dynamic traffic flow model;
[0013] The dynamic traffic flow model is used to predict the traffic flow information at the intersection in real time according to the road condition information.
[0014] Preferably, the traffic control system further includes a road segment division module;
[0015] The road segment division module is used to divide the road in each direction of the intersection into a first driving segment and a second driving segment.
[0016] Preferably, the first driving section specifically includes a preset section before the vehicle enters the intersection;
[0017] The second driving section specifically includes a road section before the vehicle enters the first driving section.
[0018] Preferably, it also includes a control module;
[0019] The control module is used to identify abnormal vehicle information in the received road condition information and issue an early warning based on the abnormal vehicle information.
[0020] Preferably, the regulation module includes an abnormality marking unit and an analysis unit;
[0021] The abnormal marking unit is used to identify and mark abnormal vehicles in the road condition information;
[0022] The analysis unit is used to analyze the abnormal vehicle, obtain abnormal information of the abnormal vehicle, and issue an early warning according to the abnormal information.
[0023] Preferably, the road condition information collection module includes a monitoring device installed on the road.
[0024] Preferably, the road condition information includes traffic flow, vehicle speed, vehicle density, vehicle position, vehicle driving trajectory and road information.
[0025] Beneficial effects: The traffic control system of the present invention can perceive and analyze road conditions in real time, quickly make traffic signal light control decisions, adaptively adjust signal light time parameters, improve road traffic efficiency, alleviate traffic congestion problems, and reduce traffic jams, shorten vehicle commuting time, and improve the quality of life of urban residents by optimizing signal light duration and vehicle traffic order.
[0026] In the traffic control system of the present invention, the dynamic adjustment unit can flexibly adjust the signal light duration and traffic flow distribution according to the traffic demands of different time periods and different roads, better adapt to the diversified needs of urban traffic, and can realize accurate monitoring and effective regulation of traffic flow, thereby improving the efficiency and level of traffic management and reducing the workload of traffic management personnel. BRIEF DESCRIPTION OF THE DRAWINGS
[0027] Figure 1 Schematic diagram of a traffic control system in an embodiment of the present invention. DETAILED DESCRIPTION
[0028] In order to make the purpose, technical solution and advantages of the present invention more clear, the present invention is further described in detail below in conjunction with specific implementation methods. It should be understood that the specific implementation methods described here are only used to explain the present invention and do not limit the scope of protection of the present invention.
[0029] like Figure 1 As shown, a traffic control system based on road condition information includes a road condition information collection module, a traffic flow simulation module and a dynamic adjustment module; the road condition information collection module is arranged on the roads in each direction of the intersection, and is used to collect and transmit road condition information; the traffic flow simulation module is used to predict the traffic flow information of the intersection in real time according to the received road condition information; the dynamic adjustment module is used to adjust the traffic in the preset direction to a red light state when determining that the traffic flow information in the preset direction of the intersection meets the preset rules.
[0030] The traffic control system also includes a road segment division module; the road segment division module is used to divide the road in each direction of the intersection into a first driving segment and a second driving segment. The first driving segment specifically includes a preset road segment before the vehicle enters the intersection; the second driving segment specifically includes a road segment before the vehicle enters the first driving segment.
[0031] The road condition information collection module includes monitoring equipment installed on the road. The road condition information includes traffic flow, vehicle speed, vehicle density, vehicle location, vehicle driving trajectory and road information.
[0032] Specifically, in an embodiment of the invention, the traffic control system includes a road condition information collection module, a traffic flow simulation module and a dynamic adjustment module, wherein the road condition information collection module is arranged on the roads in each direction of the intersection, and the road condition information collection module specifically includes monitoring equipment arranged on the road, and the monitoring equipment can select video monitoring cameras, radars and infrared probes, etc.
[0033] In practical applications, in order to carry out sustainable traffic regulation, timely predict the future period of time, and obtain road condition information more precisely and effectively. Therefore, according to the geometric structure of the traffic intersection, the road in each direction of the intersection is divided into a first driving section and a second driving section, wherein the first driving section is located at the preset section about to enter the intersection, and the second driving section is specifically the section before entering the first driving section. In this embodiment, the road section 0 to 150 meters away from the intersection is named the first driving section, and the road section 150 meters away from the intersection to the previous intersection is named the second driving section.
[0034] In this embodiment, monitoring equipment is installed in the first driving section and the second driving section respectively to monitor the traffic flow, speed, vehicle position, vehicle driving trajectory and other information in real time, and also includes obtaining special road information such as road closures or narrowing of passable roads caused by traffic accidents, construction, and other reasons on the road section.
[0035] Specifically, the traffic flow simulation module of the present invention is connected to the road condition information collection module, and is used to receive the road condition information collected by the road condition information collection module, and predict the traffic flow information of the intersection in real time according to the received road condition information.
[0036] Specifically, the traffic flow simulation module includes a dynamic traffic flow model generated according to road condition information. The acquisition of the dynamic traffic flow model specifically includes:
[0037] Data collection and preprocessing: Collect a large amount of historical vehicle data, including traffic flow information at different time periods and intersections, and clean, deduplicate and normalize the data to make it consistent and available.
[0038] Model selection: Select a deep learning model suitable for time series prediction, such as a recurrent neural network. Divide the preprocessed historical data into training set, validation set, and test set. Use the training set to train the model and continuously adjust the model parameters through the back propagation algorithm. During the training process, use the validation set to monitor the model performance to determine the optimal training parameters.
[0039] Parameter optimization: Use appropriate optimization algorithms, such as stochastic gradient descent, to adjust model parameters such as weights and biases. Try different hyperparameters, such as learning rate, number of layers, number of nodes, etc., and find the optimal combination through experimentation and evaluation.
[0040] Real-time prediction: After the model training is completed, relevant feature data of the current intersection and road section, such as time, weather, etc., are obtained in real time, and these features are input into the model to obtain the predicted traffic information.
[0041] The dynamic adjustment module is connected to the traffic flow simulation module and is used to adjust the traffic in the preset direction to a red light state when the traffic flow information in the preset direction of the intersection meets the preset rules. The preset rules are that there are no vehicles passing within the preset time period or the number of vehicles passing within the preset time period is less than the preset value.
[0042] Specifically, the dynamic adjustment module is used to set preset rules. If no vehicles pass through a road in one direction at a traffic intersection within a preset time period, the corresponding traffic light of the road in that direction is adjusted to red. If no vehicles pass through roads in multiple directions, the corresponding traffic lights of roads in multiple directions are adjusted to yellow so that the traffic light status can be quickly adjusted when needed. At this time, the vehicle data information of the second driving section of the traffic intersection is obtained, and the traffic light corresponding to the road in the direction in which the vehicle first enters the first driving section is adjusted to green.
[0043] In practical applications, on rural roads, since there are fewer vehicles at night, in order to improve the driving efficiency of traffic vehicles and reduce the waiting time of traffic lights, the dynamic adjustment module includes a threshold setting unit and a recognition unit;
[0044] The threshold setting unit is used to define a time threshold during which no vehicle passes, i.e., a preset time period;
[0045] The recognition unit is used to obtain the information of vehicles passing through the traffic intersection section in the road condition information collection module. Based on this information, it intelligently adapts to different traffic conditions and realizes the optimization control of the following three states:
[0046] Specifically, road section no-vehicle detection: real-time monitoring of vehicle traffic on each road section, recording the time when no vehicles pass through, if no vehicles pass through a road in a certain direction within a set time threshold, the traffic light corresponding to the road in that direction is set to red;
[0047] No-vehicle detection at all intersections: Continuously monitor the roads in all directions of the intersection. If no vehicles pass through the roads in all directions within a certain time threshold, all traffic lights will be adjusted to yellow and enter a special yellow light control state, indicating that no vehicles have passed through the intersection recently;
[0048] Vehicle detection and control in the yellow light control state: In the yellow light control state, focus on the vehicle data information of the second driving section, identify the vehicle that will enter the first driving section first, and quickly adjust the traffic light corresponding to the section to green. By detecting and switching the green light in advance, ensure that the vehicles about to enter the intersection can pass smoothly. When the vehicle enters the second driving section, this signal light control strategy that combines time threshold detection and vehicle prediction in the yellow light control state can effectively reduce energy consumption in the absence of vehicles, while improving the traffic efficiency of vehicles approaching the intersection, thereby optimizing the overall traffic flow.
[0049] The dynamic adjustment module also includes an adaptive adjustment unit; the adaptive adjustment unit is used to generate a traffic indication strategy for the intersection according to the traffic flow information and preset rules.
[0050] Specifically, in actual applications, the adaptive adjustment unit simulates the traffic flow information of the intersection section in different time periods according to the dynamic traffic flow model, and adaptively adjusts the traffic lights; the adaptive adjustment unit generates a traffic indication strategy based on the judgment result of the traffic flow information, and the system automatically adjusts the duration and phase of the traffic lights according to the traffic indication strategy. If there is traffic congestion in a certain direction, the traffic light may extend the green light time in that direction to increase the number of vehicles passing; conversely, if there are fewer vehicles in a certain direction, the green light time may be shortened accordingly, so as to more reasonably allocate road resources and improve the traffic efficiency of traffic intersections.
[0051] The real-time prediction of traffic flow information at traffic intersections through dynamic traffic flow models helps to rationally plan road networks, adjust traffic signal timing, etc., and improve the operating efficiency of the entire transportation system. It can determine in advance which intersections are prone to congestion, so as to take targeted measures to alleviate traffic pressure.
[0052] The algorithm formula for predicting traffic flow information using the dynamic traffic flow model is as follows:
[0053]
[0054] in:
[0055] Indicates the current time The predicted traffic volume;
[0056] Indicates the last moment The predicted traffic volume;
[0057] Indicates the current time The actual traffic volume collected on the road section;
[0058] is the smoothing coefficient, ranging from 0 to 1; It is to control the weight of historical data (i.e. the predicted traffic flow at the previous moment) in the current prediction. The closer it is to 1, The smaller the value of , the greater the impact of the predicted traffic flow at the previous moment on the current prediction. The dynamic traffic flow model pays more attention to the continuity and stability of historical data. On the contrary, when The closer it is to 0, The larger the value is, the smaller the impact of the predicted traffic flow at the previous moment on the current prediction is. The dynamic traffic flow model is more inclined to rely on the actual traffic flow collected on the road section at the current moment for prediction and adjustment.
[0059] The system dynamically adjusts the time parameters of traffic lights, such as green light duration and turn green light duration, based on the real-time traffic information of the two sections to be driven, to ensure smooth passage of vehicles at the intersection. The system monitors the first and second sections in real time. For example, when a vehicle enters the second section, the distance to the traffic intersection according to the speed limit is 2 minutes, and when the vehicle enters the first section, the distance to the traffic intersection according to the speed limit is 1 minute. The system obtains real-time traffic conditions and reduces the risk of traffic congestion.
[0060] In each control cycle, the system will update its internal state equation parameters based on the real-time collected data such as traffic flow and speed, and re-solve the optimal traffic indication strategy and implement control in a rolling manner. Such a dynamic traffic flow model incorporates the characteristics of vehicle queuing and passage at intersections. The global optimal signal light control strategy can be obtained through dynamic planning solution. The system's dynamic traffic flow model operation framework and solution process have strong real-time and adaptive capabilities, and can effectively cope with complex and changeable road conditions.
[0061] Furthermore, it also includes a control module; the control module is used to identify abnormal vehicle information in the received road condition information and issue an early warning based on the abnormal vehicle information.
[0062] Furthermore, the control module includes an abnormal marking unit and an analysis unit; the abnormal marking unit is used to identify and mark abnormal vehicles in road condition information; the analysis unit is used to analyze abnormal vehicles, obtain abnormal information of abnormal vehicles, and issue early warnings based on the abnormal information.
[0063] Specifically, the abnormal marking unit is used to identify abnormal vehicle data in the road condition information collected by the road condition information collection module and mark abnormal vehicle behavior.
[0064] The analysis unit is used to use computer vision and machine learning technology to analyze abnormal vehicle data and identify behaviors that may pose safety hazards. Once an abnormal situation is detected, it immediately sends an early warning message to traffic management personnel, makes manual intervention, and adjusts the traffic lights at the corresponding intersection through the control system.
[0065] The specific steps for constructing the control module are as follows:
[0066] Data collection: Collect a large amount of video data including normal vehicle driving and various abnormal behaviors.
[0067] Data labeling: Manually label the collected data to mark normal behaviors and behaviors that pose safety hazards, such as speeding and brake failure.
[0068] Feature extraction: Use computer vision technology to extract vehicle features in the video, such as vehicle location, speed, driving trajectory, etc.
[0069] Model selection and training: Computer vision and machine learning technologies are used to input labeled data into the model for training, so that the model can learn how to distinguish between normal and abnormal behaviors.
[0070] Real-time monitoring: Use cameras installed at intersections or other locations to obtain vehicle video data in real time, use trained models to analyze real-time video, extract features and make judgments.
[0071] Anomaly detection: When the model detects a behavior that may pose a safety hazard, it is considered an abnormal situation and an early warning message is immediately sent to traffic management personnel through specific communication channels such as text messages and system notifications, including detailed information such as the type of abnormal behavior and the location where it occurred.
[0072] Manual intervention: After receiving the warning, traffic management personnel will take corresponding manual intervention measures according to the situation, such as dispatching police to deal with the situation, so as to promptly discover and deal with abnormal situations, effectively reduce the risk of accidents caused by abnormal driving behavior, and protect the lives and property of pedestrians and vehicles. By flexibly adjusting traffic lights, congestion that may be caused by abnormal situations can be quickly diverted to keep the roads unobstructed.
[0073] The traffic control system of the present invention can sense and analyze road conditions in real time, quickly make traffic signal light control decisions, adaptively adjust signal light time parameters, improve road traffic efficiency, alleviate traffic congestion problems, and reduce traffic jams, shorten vehicle commuting time, and improve the quality of life of urban residents by optimizing signal light duration and vehicle traffic order.
[0074] In the traffic control system of the present invention, the dynamic adjustment module can flexibly adjust the signal light duration and traffic flow distribution according to the traffic demands of different time periods and different roads, better adapt to the diversified needs of urban traffic, and can realize accurate monitoring and effective regulation of traffic flow, thereby improving the efficiency and level of traffic management and reducing the workload of traffic management personnel.
[0075] The above are only several embodiments of the present invention and are not intended to limit the present invention in any form. Although the present invention is disclosed as above in the form of a preferred embodiment, it is not intended to limit the present invention. Any technician familiar with the art, without departing from the scope of the technical solution of the present invention, using the above disclosed technical content to make slight changes or modifications are equivalent to equivalent implementation cases and fall within the scope of the technical solution.
Claims
1. A traffic control system based on road condition information, characterized in that: It includes road condition information collection module, traffic flow simulation module and dynamic adjustment module; The road condition information collection module is arranged on the roads in each direction of the intersection, and is used to collect and transmit road condition information; The traffic flow simulation module is used to predict the traffic flow information of the intersection in real time according to the received road condition information; The dynamic adjustment module is used to adjust the traffic in the preset direction to a red light state when determining that the traffic flow information in the preset direction of the intersection meets the preset rules.
2. The traffic control system according to claim 1, characterized in that: The preset rule is that there is no vehicle passing within a preset time period or the number of vehicles passing within the preset time period is less than a preset value.
3. The traffic control system according to claim 2, characterized in that: The dynamic adjustment module also includes an adaptive adjustment unit; The adaptive adjustment unit is used to generate a traffic indication strategy for the intersection according to the traffic flow information and the preset rules.
4. The traffic control system according to claim 1, characterized in that: The traffic flow simulation module includes a dynamic traffic flow model; The dynamic traffic flow model is used to predict the traffic flow information at the intersection in real time according to the road condition information.
5. The traffic control system according to claim 1, characterized in that: The traffic control system also includes a road segment division module; The road segment division module is used to divide the road in each direction of the intersection into a first driving segment and a second driving segment.
6. The traffic control system according to claim 5, characterized in that: The first driving section specifically includes a preset section before the vehicle enters the intersection; The second driving section specifically includes a road section before the vehicle enters the first driving section.
7. The traffic control system according to claim 1, characterized in that: Also includes a control module; The control module is used to identify abnormal vehicle information in the received road condition information and issue an early warning based on the abnormal vehicle information.
8. The traffic control system according to claim 7, characterized in that: The regulation module includes an abnormality marking unit and an analysis unit; The abnormal marking unit is used to identify and mark abnormal vehicles in the road condition information; The analysis unit is used to analyze the abnormal vehicle, obtain abnormal information of the abnormal vehicle, and issue an early warning according to the abnormal information.
9. The traffic control system according to claim 1, characterized in that: The road condition information collection module includes monitoring equipment installed on the road.
10. The traffic control system according to claim 1, characterized in that: The road condition information includes traffic flow, vehicle speed, vehicle density, vehicle position, vehicle driving trajectory and road information.
Citation Information
Cited By
Intelligent traffic light scheduling method and system combined with edge calculation
CN120356352A
