Intelligent Adaptive Control Method for Traffic Lights that Integrates Sensing, Computation, and Control

Abstract

This application provides an intelligent traffic light adaptive control method integrating sensing, computing, and control, belonging to the field of intelligent traffic control technology. The method includes: deploying multiple sensing devices to construct a sensing and monitoring device group, obtaining a regional traffic dataset, calculating the timing of the target traffic light, generating a timing control scheme, dynamically adjusting the timing control scheme based on real-time sensing feedback, generating an optimized timing control scheme, and intelligently controlling the target traffic light. This application solves the technical problem in existing technologies where the lack of flexibility in dynamic adjustment of signal timing leads to poor traffic system operating efficiency. By integrating multiple sensors, generating a timing control scheme based on traffic characteristics, and dynamically adjusting the signal timing based on real-time traffic conditions, the method achieves intelligent control of the target traffic light, thus improving traffic operating efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent traffic control technology, and in particular to an intelligent traffic light adaptive control method that integrates sensing, computing and control. Background Technology

[0002] With the acceleration of urbanization, traffic congestion has become increasingly serious, causing great inconvenience to people's travel. In order to alleviate traffic congestion and improve road traffic efficiency, intelligent traffic light adaptive control technology has emerged. At present, the existing intelligent traffic light control system has poor flexibility in dynamically adjusting signal timing under complex and changing traffic conditions, resulting in traffic congestion, increased vehicle waiting time, and even affecting traffic safety.

[0003] In summary, existing technologies suffer from poor operational efficiency of traffic systems due to insufficient flexibility in the dynamic adjustment of signal timing. Summary of the Invention

[0004] The purpose of this application is to provide an intelligent traffic light adaptive control method that integrates sensing, computing, and control, in order to solve the technical problem in the prior art where the dynamic adjustment of signal timing is not flexible enough, resulting in poor operating efficiency of the traffic system.

[0005] In view of the above problems, this application provides an intelligent traffic light adaptive control method integrating sensing, computing, and control. The method includes: deploying multiple sensing devices in a target monitoring area to construct a sensing monitoring device group; sensing the target monitoring area based on the sensing monitoring device group to obtain a regional traffic dataset; extracting features from the regional traffic dataset to obtain multiple regional traffic features; calculating the timing of the target traffic light according to the multiple regional traffic features to generate a timing control scheme; executing the timing control scheme, providing real-time sensing feedback to the target monitoring area, and dynamically adjusting the timing control scheme based on the feedback information to generate an optimized timing control scheme; and intelligently controlling the target traffic light according to the optimized timing control scheme.

[0006] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0007] By deploying multiple sensing devices in the target monitoring area, a sensor monitoring device group is constructed. Based on this group, the target monitoring area is sensed to obtain a regional traffic dataset. Feature extraction is performed on the regional traffic dataset to obtain multiple regional traffic features. The timing of the target traffic lights is calculated according to these features to generate a timing control scheme. This timing control scheme is executed, with real-time sensing feedback provided to the target monitoring area. The timing control scheme is then dynamically adjusted based on the feedback information to generate an optimized timing control scheme. Finally, the target traffic lights are intelligently controlled according to this optimized scheme. In other words, by integrating multiple sensors, generating a timing control scheme based on traffic features, dynamically adjusting signal timing based on real-time traffic conditions, and intelligently controlling the target traffic lights, the technical effect of improving traffic efficiency is achieved.

[0008] The above description is merely an overview of the technical solution of this application. To better understand the technical means of this application and to facilitate its implementation according to the description, and to make the above and other objects, features, and advantages of this application more apparent, specific embodiments of this application are described below. It should be understood that the content described in this section is not intended to identify key or important features of the embodiments of this application, nor is it intended to limit the scope of this application. Other features of this application will become readily apparent through the following description. Attached Figure Description

[0009] To more clearly illustrate the technical solutions in this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely exemplary. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0010] Figure 1 This is a flowchart illustrating the intelligent traffic light adaptive control method integrating sensing, computing, and control as described in this application.

[0011] Figure 2 This is a flowchart illustrating the process of generating a timing control optimization scheme in the intelligent traffic light adaptive control method integrating sensing, computing, and control in this application. Detailed Implementation

[0012] This application provides an intelligent traffic light adaptive control method that integrates sensing, computing, and control, solving the technical problem of poor traffic system operating efficiency caused by insufficient dynamic adjustment of signal timing in existing technologies. By integrating multiple sensors, generating timing control schemes based on traffic characteristics, and dynamically adjusting signal timing in conjunction with real-time traffic conditions, the method intelligently controls target traffic lights, achieving the technical effect of improving traffic operating efficiency.

[0013] The technical solutions of this application will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. It should be understood that this application is not limited to the exemplary embodiments described herein. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application. It should also be noted that, for ease of description, only the parts related to this application are shown in the accompanying drawings, not all of them.

[0014] Please see the appendix Figure 1 This application provides an intelligent traffic light adaptive control method integrating sensing, computing, and control, wherein the method specifically includes the following steps:

[0015] Step 1: Deploy multiple sensing devices in the target monitoring area to construct a sensing monitoring device group.

[0016] Specifically, a comprehensive survey of the target monitoring area is conducted to determine the key locations for sensor deployment, including busy intersections and accident-prone areas. The deployed sensing devices include, but are not limited to, cameras, radar, geomagnetic sensors, and infrared sensors. Each device has its own function; for example, cameras identify vehicle type and direction of travel, radar measures vehicle speed and distance, and geomagnetic sensors detect vehicle presence. These different types of sensing devices are combined to construct a comprehensive sensing and monitoring system, providing multi-dimensional and multi-angle traffic data to more accurately reflect traffic conditions. The integration of multiple sensing devices allows for data verification and supplementation, thereby improving data accuracy.

[0017] Step 2: Based on the sensor monitoring equipment group, perceive the target monitoring area and obtain the regional traffic dataset.

[0018] Specifically, a group of sensors is used to monitor the target area, collecting information such as vehicle speed at specific points, vehicle length and height (for vehicle type identification), and queue length. The collected data is preprocessed to remove invalid or erroneous data. Traffic data analysis and processing software is then used for in-depth analysis, including traffic flow statistics, speed distribution, vehicle classification, and traffic pattern recognition. The analyzed traffic data is then integrated into a regional traffic dataset, a dynamically updated database containing historical and real-time traffic information. This integration of multi-source data allows for more accurate analysis and prediction of traffic conditions.

[0019] Step 3: Extract features from the regional traffic dataset to obtain multiple regional traffic features, and calculate the timing of the target traffic lights according to the multiple regional traffic features to generate a timing control scheme.

[0020] Specifically, utilizing regional traffic datasets collected through a group of sensor monitoring devices, key features reflecting traffic conditions are extracted by analyzing multi-dimensional characteristics such as traffic flow, vehicle speed, and vehicle type, resulting in road frequency domain and time domain features. Feature extraction includes statistical description, time series analysis, and frequency analysis to capture the dynamic characteristics and periodicity of traffic flow. These road frequency and time domain features are then added to multiple regional traffic features. Traffic light timing is calculated based on these regional traffic features. Using the extracted regional traffic features, an optimal signal cycle length, green light time, and red light time are calculated through a traffic flow analysis model, generating a timing control scheme. The timing scheme for each time period is calculated and optimized separately based on the traffic characteristics of that time period to adapt to different traffic demands and reduce congestion. By optimizing signal timing, vehicle waiting time is reduced, thereby improving traffic efficiency.

[0021] Step 4: Execute the timing control scheme, perform real-time sensing feedback on the target monitoring area, and dynamically adjust the timing control scheme based on the feedback information to generate an optimized timing control scheme.

[0022] Specifically, the timing control scheme is implemented by collecting feedback information from the target detection area through real-time sensing devices (such as cameras and radar), including data on vehicle speed, type, and traffic flow. This real-time traffic feedback information is compared with a preset matching threshold. If the matching coefficient is lower than the threshold, the timing control scheme needs adjustment. Based on the feedback information, the timing control scheme is dynamically adjusted, including changing signal cycle length, adjusting phase sequence, and optimizing green light time allocation. After verification, the adjusted timing control scheme generates an optimized timing control scheme, which will be used for subsequent traffic signal control to adapt to constantly changing traffic conditions. Through real-time sensing feedback and dynamic adjustment, the system can respond to traffic changes in real time, achieving more precise traffic management.

[0023] Step 5: Perform intelligent control of the target traffic lights according to the timing control optimization scheme.

[0024] Specifically, the optimized timing control scheme is applied to the target traffic lights, including adjusting parameters such as green light duration, red light duration, yellow light duration, and phase switching sequence. Based on updated green light duration, red light duration, yellow light duration, and phase switching sequence data, it is determined whether the real-time traffic information meets the preset traffic efficiency indicators. If not, an anomaly backtracking command is generated to perform anomaly analysis on the timing control optimization scheme. Anomaly analysis identifies the source of the abnormal data, including sensor malfunctions, data processing errors, and traffic flow anomalies. The source of the abnormal data is sent to the remote control terminal, where the timing control optimization scheme is intelligently processed. Through intelligent control, the control scheme is always kept in its optimal state, improving traffic efficiency and reducing congestion.

[0025] Furthermore, step one of this application includes:

[0026] Traverse the control requirement information of the target traffic lights within the target monitoring area and identify multiple sensing points; deploy the multiple sensing devices according to the multiple sensing points to construct a sensing communication network; add the sensing communication network to the sensing monitoring device group.

[0027] Specifically, a comprehensive survey of the target monitoring area is conducted, collecting information such as current traffic light timing schemes, traffic flow data, historical traffic patterns, and accident-prone areas to determine which traffic lights require intelligent control. Based on the survey results, the control requirements for traffic lights are analyzed, including the spatiotemporal distribution of traffic flow, traffic congestion patterns, and vehicle type distribution, to determine the key locations for sensor deployment. Based on the control requirements analysis, multiple sensing points are identified. The selection of these points should be based on locations that can provide necessary traffic data, such as key intersections, traffic bottlenecks, and accident-prone areas. For example, if traffic light control in a certain area requires based on traffic flow, sensors need to be deployed at locations capable of detecting vehicle flow; these locations are the sensing points.

[0028] Based on the identified sensing points, factors such as equipment type, coverage area, and environmental adaptability are considered to ensure that each point can effectively collect the required traffic data. Appropriate sensing equipment, such as geomagnetic sensors, cameras, and radar, is installed. These sensing devices are then interconnected to form a communication network. This network can have various topologies, such as star, ring, or mesh, chosen based on specific needs, cost, and reliability. For example, a star topology is simple and easy to manage, but a failure of the central node can paralyze the entire network; a mesh topology is more complex but offers higher reliability and fault tolerance. The sensing communication network is applied to the sensor monitoring equipment group, connecting and coordinating the sensing devices in the communication network with other devices (such as cameras and radar) within the group. The traffic management center can then receive and analyze real-time traffic data through this equipment group and adjust traffic light control strategies accordingly. By constructing a sensor monitoring equipment group, the intelligent transportation system can achieve real-time monitoring and adaptive control of traffic lights.

[0029] Furthermore, step two of this application includes:

[0030] The sensor monitoring equipment group collects multiple sensor data from the target monitoring area, including vehicle speed sensor data and vehicle type sensor data. Based on the vehicle speed sensor data, traffic flow analysis is performed on the target monitoring area to obtain first traffic data for the target monitoring area. Based on the vehicle type sensor data, traffic road analysis is performed on the target monitoring area to obtain second traffic data for the target monitoring area. The first traffic data and the second traffic data are then added to the regional traffic dataset.

[0031] Specifically, a pre-deployed array of sensor monitoring equipment is used to collect real-time data from the target monitoring area, including vehicle speed and vehicle type data. By collecting vehicle speed information from the sensors deployed in the monitoring area, the speed distribution of traffic flow can be understood, congestion points can be identified, and traffic light timing can be optimized. Similarly, vehicle type information, such as small cars, large vehicles, and buses, is collected through the sensors. Different types of vehicles have different impacts on traffic flow, allowing for analysis of the impact of different vehicle types on road use. Based on the vehicle speed data, traffic flow analysis is performed on the target detection area. By analyzing information such as the number of vehicles and speed distribution in the monitoring area, the traffic flow characteristics of the monitoring area can be understood, such as peak hours and flow fluctuations. This initial traffic data is used to assess the traffic conditions in the monitoring area and identify congestion points.

[0032] Using vehicle type sensor data, traffic road analysis is performed on the target monitoring area to analyze the impact of different vehicle types (such as small cars, large vehicles, and buses) on road capacity and traffic flow. The distribution characteristics of different vehicle types within the monitoring area are understood, such as high-frequency areas for specific vehicle types and changes in vehicle type flow, to obtain secondary traffic data. This data is then used to assess road use in the monitoring area and identify congestion points for specific vehicle types. For example, low speed limits for large vehicles or the use of non-motorized vehicles in motorized vehicle lanes can lead to road obstruction and slow traffic. The acquired data is processed, including format standardization, data cleaning, and fusion. The processed primary and secondary traffic data are then added to the regional traffic dataset. The integrated dataset contains comprehensive traffic information, such as traffic flow and vehicle type data. By integrating traffic data from different sources, traffic conditions are comprehensively monitored, resulting in more comprehensive and accurate traffic information.

[0033] Furthermore, step three of this application includes:

[0034] Based on the first traffic data, determine the road density information of the target monitoring area; based on the second traffic data, determine the road traffic status of the target monitoring area; perform feature extraction based on the road density information and the road traffic status to obtain road frequency domain features and road time domain features; add the road frequency domain features and the road time domain features to the multiple regional traffic features.

[0035] Specifically, the first traffic data, obtained from vehicle speed sensing data, includes information such as the number of vehicles passing through the monitoring area and their speed distribution. This data is statistically analyzed to understand traffic flow characteristics within the monitoring area, such as peak hours and flow fluctuations. A reference length or area is defined for each road segment or intersection, which will be used to calculate road density. The total number of vehicles is divided by the length of the corresponding road segment or the area of ​​the intersection to obtain the road density value. The road density of the target monitoring area is calculated as the ratio of the number of vehicles passing through a certain road segment or intersection per unit time to the length of that road segment or the area of ​​that intersection. The second traffic data, obtained from vehicle type sensing data, is statistically analyzed to understand the distribution characteristics of different vehicle types within the monitoring area, such as high-frequency areas for specific vehicle types and changes in vehicle type flow. Road traffic conditions are analyzed, including indicators such as traffic speed, lane occupancy, and queue length, to determine whether the road is clear, congested, or in another state.

[0036] Feature extraction is performed on road density information and road traffic status to obtain the frequency domain and time domain features of the road. Frequency domain features mainly focus on the periodicity and frequency distribution of the signal, while time domain features focus on the trend and statistical characteristics of the signal over time. Road frequency domain features refer to the characteristics of road traffic status or road density information in the frequency domain. This typically involves converting time-domain data (such as changes in road traffic status over time) into a frequency domain representation to reveal its periodicity and frequency distribution characteristics, such as using Fast Fourier Transform (FFT) to identify periodic patterns in traffic flow. Road time domain features refer to the characteristics of road traffic status or road density information in the time domain. This typically involves directly analyzing the raw data to extract time-related information. For example, by analyzing the vehicle traffic situation at a certain intersection, a series of time-series data representing vehicle traffic status (such as congestion, smooth traffic, etc.) can be obtained. Through Fourier transform, this data is converted into a frequency domain representation, and the main frequency components of vehicle traffic at the intersection (such as the frequency of morning and evening rush hours) and the intensity of these frequency components are extracted. The extracted road frequency domain features and road time domain features are added to the regional traffic feature set. The extraction of road frequency domain features and time domain features helps to understand the periodicity and trends of traffic flow, providing a basis for traffic signal timing.

[0037] Furthermore, this application also includes the following steps:

[0038] Based on the traffic characteristics of the multiple regions, the loss of the target traffic lights is calculated to generate the total signal loss time; according to the total signal loss time, multiple signal cycle durations are calculated in combination with the first traffic data; the multiple signal cycle durations are matched with multiple traffic time periods to obtain multiple timing control information; the multiple timing control information is added to the timing control scheme.

[0039] Specifically, based on multiple regional traffic characteristics, such as traffic flow, vehicle speed, and lane occupancy, the impact of traffic light signal changes on traffic flow is calculated, i.e., signal loss time. Loss time refers to the time lost when vehicles must stop or slow down due to changes in traffic lights. Calculating this loss time requires statistics on vehicle waiting time at traffic lights, comparison of signal cycle time and actual passage time, and balancing of traffic flow in different directions. Based on the loss calculation results, the total signal loss time is generated, including vehicle start-up loss time, pedestrian crossing time, and signal transition time, reflecting the impact of signal control on the overall traffic efficiency of the monitored area. Combining the total signal loss time and primary traffic data, a reasonable signal cycle length is calculated. The signal cycle length refers to the duration of a complete signal cycle.

[0040] The system matches signal cycle lengths with multiple traffic periods, such as dividing a day into peak and off-peak periods. The calculated signal cycle lengths are then matched with these different traffic periods to generate signal timing control information for each period. Each period's timing scheme is calculated and optimized separately based on its traffic characteristics. For example, during peak hours, when traffic volume is high, a longer calculated signal cycle length is used to reduce vehicle waiting time. Timing control information, such as extending green light time and shortening red light time, is generated based on the peak-hour signal cycle length. Conversely, during off-peak hours, when traffic volume is low, a shorter calculated signal cycle length is used to improve intersection throughput. Timing control information, such as adjusting green and red light times, is generated based on the off-peak signal cycle length to improve intersection efficiency. These multiple timing control information sets are integrated into a single timing control scheme, forming a comprehensive signal control strategy to guide signal timing at different traffic periods. By optimizing signal timing, the intelligent traffic signal control system can automatically adjust traffic light timings based on real-time traffic conditions, thereby improving intersection efficiency.

[0041] Furthermore, step four of this application includes:

[0042] The target traffic lights are controlled according to the timing control scheme to obtain timing control results; the timing control results are evaluated to generate a timing traffic score; multiple abnormal control data are extracted based on the timing traffic score, and feedback instructions are generated based on the multiple abnormal control data; the multiple abnormal control data are added to the feedback information according to the feedback instructions.

[0043] Specifically, the generated timing control scheme is applied to actual traffic light control. This scheme includes parameters such as the optimal signal cycle length, green light time, and red light time. Real-time control of the target traffic lights, adjusting the green, yellow, and red light times, can be achieved automatically through the traffic signal control system or manually by traffic management personnel. Traffic data after the implementation of timing control, such as vehicle transit time, queue length, and number of stops, is collected to evaluate traffic flow, generating a timing-based traffic score to determine the effectiveness of the timing control.

[0044] Anomalies in traffic timing scores are analyzed to identify data points that deviate from normal control performance—those with scores below a certain threshold—indicating problems or areas for improvement in signal control. Anomalies include high delays, frequent stop-and-go traffic, and excessively long queues. Based on this data, targeted feedback instructions are generated, indicating the necessary adjustments to timing parameters or signal control strategies. For example, excessively long or short green light times during certain periods can lead to traffic congestion or low efficiency; based on the identified anomalies, feedback instructions are generated to adjust green light times or cycle lengths. The identified anomalies and feedback instructions are combined to form a feedback information set. Through analysis and feedback of the timing control scheme, the scheme is optimized and adjusted to improve signal timing and overall traffic efficiency.

[0045] Further details are attached. Figure 2 As shown, this application also includes the following steps:

[0046] Using the multiple abnormal control data as index information, the timing control scheme is traversed and matched to generate multiple timing control data, which correspond to the multiple abnormal control data. The multiple timing control data are analyzed in conjunction with real-time traffic and road information to generate multiple control matching coefficients. Control matching coefficients less than a preset matching threshold are extracted from the multiple control matching coefficients to determine N control matching coefficients, where N is an integer greater than or equal to 0. Based on the N control matching coefficients, N timing control data are extracted. The timing control scheme is dynamically adjusted according to the N timing control data, and the timing control scheme is updated based on the adjustment results to generate the timing control optimization scheme.

[0047] Specifically, the identified abnormal control data is used as an index to find corresponding data points in the timing control scheme, thereby generating a series of timing control data. These data and the abnormal control data come from the same intersection or signal cycle and have a corresponding relationship. The timing control data is calculated and analyzed with the real-time traffic and road information of the current intersection or area (such as current traffic flow, lane occupancy, etc.) to determine the degree of matching between the timing control data and the actual traffic conditions. The matching degree between the current traffic conditions and the defined abnormal timing control data is analyzed. If the system only detects an anomaly, but it matches the real-time traffic conditions, the scheme is retained and propagated. If the matching degree is low, the scheme is adjusted. Since road traffic conditions change in real time, it is necessary to continuously and dynamically adjust the timing control scheme to ensure that it is always most adapted to the real-time traffic conditions. A series of control matching coefficients obtained by calculating the matching degree between the timing control data and the real-time traffic and road information are used to guide the adjustment and optimization of signal control.

[0048] Based on different traffic conditions and objectives, a pre-set matching threshold is used to evaluate the degree of matching between timing control data and real-time traffic conditions. The matching threshold can differ between peak and off-peak hours; a lower threshold is set during peak hours to respond more quickly to changes in traffic flow, while a higher threshold is set during off-peak hours to reduce unnecessary adjustments. When the control matching coefficient falls below the preset matching threshold, it indicates that the timing control scheme is not optimal and needs adjustment to improve traffic flow. These control matching coefficients below the preset matching threshold are extracted, identifying N control matching coefficients that require further attention. The selected N control matching coefficients are used to extract corresponding timing control data, and then the existing timing control scheme is dynamically adjusted based on this data. The adjusted results are used to update the timing control scheme, generating a new optimized timing control scheme. The optimized scheme will be used for the next round of signal timing to adapt to real-time traffic demand and improve traffic flow. By dynamically adjusting the timing control scheme, continuous optimization of signal timing is achieved to improve traffic efficiency and reduce congestion.

[0049] Furthermore, step five of this application includes:

[0050] The traffic light status is updated according to the timing control optimization scheme to obtain an update instruction; the update instruction is parsed to obtain green light duration update data, red light duration update data, yellow light duration update data, and phase switching sequence update data; based on the green light duration update data, red light duration update data, yellow light duration update data, and phase switching sequence update data, it is determined whether the real-time traffic road information has reached the preset traffic efficiency index; if the real-time traffic road information has not reached the preset traffic efficiency index, an anomaly backtracking instruction is generated, and the timing control optimization scheme is analyzed for anomalies according to the anomaly backtracking instruction to determine the source of the abnormal data; the source of the abnormal data is sent to the remote control terminal, and the timing control optimization scheme is intelligently processed through the remote control terminal.

[0051] Specifically, the optimized timing control scheme is applied to actual traffic light control to update traffic lights, obtaining update commands, including adjusting the duration of red, green, and yellow lights, and changing the phase switching sequence. The update commands are parsed to extract green light duration update data, red light duration update data, yellow light duration update data, and phase switching sequence update data. The green light duration update data updates the duration of the green light; the red light duration update data updates the duration of the red light; the yellow light duration update data updates the duration of the yellow light; and the phase switching sequence update data updates the sequence of traffic flow switching for different directions of traffic at different time periods, including the start and end times of each phase.

[0052] In a traffic signal control system, each traffic light controls traffic flow in one direction, and these directions are divided into different phases. For example, a typical intersection may have traffic flow in four directions, thus requiring four phases, each controlling traffic flow in one direction. The phase switching sequence refers to how these phases alternate control within a signal cycle; different phase switching sequences affect the continuity of traffic flow and the capacity of the intersection.

[0053] A traffic efficiency metric is pre-set to measure the effectiveness of traffic signal control. Updated traffic light control parameters are combined with real-time traffic information, and this data is analyzed to determine whether the current traffic conditions meet the pre-set efficiency metric, such as vehicle throughput or waiting time. If the real-time traffic information does not meet the pre-set efficiency metric, an anomaly backtracking instruction is generated. This instruction guides the anomaly analysis of the timing control optimization scheme and typically includes specific analysis suggestions and data source guidance. Based on the anomaly backtracking instruction, anomaly analysis is performed on the timing control optimization scheme to determine the source of the abnormal data that caused the efficiency metric not to be met—whether it's a problem with the traffic light control parameters or a sudden change in real-time traffic conditions.

[0054] The abnormal data source is sent to a remote control terminal, which could be a traffic management center or a cloud service platform responsible for monitoring and managing the traffic signal control system. The remote control terminal utilizes advanced data analytics and machine learning technologies to intelligently process the timing control optimization scheme to resolve problems in signal control. When an anomaly has a minor impact on overall traffic flow, is unavoidable, and the current scheme is already optimal, a remote human assessment determines whether the scheme needs adjustment. If no adjustment is decided, the system-generated scheme is executed. Through intelligent control of the target traffic lights using the timing control optimization scheme, continuous anomaly analysis and adjustments are made to continuously improve signal control strategies and enhance the overall performance of traffic management.

[0055] In summary, the intelligent traffic light adaptive control method integrating sensing, computing, and control provided in this application has the following technical effects:

[0056] By deploying multiple sensing devices in the target monitoring area, a sensor monitoring device group is constructed. Based on this group, the target monitoring area is sensed to obtain a regional traffic dataset. Feature extraction is performed on the regional traffic dataset to obtain multiple regional traffic features. The timing of the target traffic lights is calculated according to these features to generate a timing control scheme. This timing control scheme is executed, with real-time sensing feedback provided to the target monitoring area. The timing control scheme is then dynamically adjusted based on the feedback information to generate an optimized timing control scheme. Finally, the target traffic lights are intelligently controlled according to this optimized scheme. In other words, by integrating multiple sensors, generating a timing control scheme based on traffic features, dynamically adjusting signal timing based on real-time traffic conditions, and intelligently controlling the target traffic lights, the technical effect of improving traffic efficiency is achieved.

[0057] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0058] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application also intends to include such modifications and variations.

Claims

1. A smart traffic light adaptive control method integrating sensing, computing, and control, characterized in that, The method includes: Multiple sensing devices are deployed in the target monitoring area to construct a sensing monitoring device group; Based on the aforementioned sensor monitoring equipment group, the target monitoring area is perceived, and a regional traffic dataset is obtained; Based on the regional traffic dataset, feature extraction is performed to obtain multiple regional traffic features. The timing of the target traffic lights is then calculated according to the multiple regional traffic features to generate a timing control scheme. The timing control scheme is executed, and the target monitoring area is perceived and fed back in real time. The timing control scheme is dynamically adjusted based on the feedback information to generate an optimized timing control scheme. The target traffic lights are intelligently controlled according to the timing control optimization scheme. The method for executing the timing control scheme and providing real-time sensing feedback on the target monitoring area includes: The target traffic lights are controlled according to the timing control scheme to obtain the timing control results. The timing control results are evaluated to generate a timing-based traffic score. Multiple abnormal control data are extracted based on the timing passage score, and feedback instructions are generated based on the multiple abnormal control data. According to the feedback instruction, the multiple abnormal control data are added to the feedback information; The timing control scheme is dynamically adjusted based on feedback information to generate an optimized timing control scheme. The method includes: Using the multiple abnormal control data as index information, the timing control scheme is traversed and matched to generate multiple timing control data, and the multiple timing control data have a corresponding relationship with the multiple abnormal control data. The multiple timing control data and real-time traffic road information are analyzed to calculate and generate multiple control matching coefficients; Extract the control matching coefficients that are less than a preset matching threshold from among the multiple control matching coefficients, and determine N control matching coefficients, where N is an integer greater than or equal to 0; Based on the N control matching coefficients, N timing control data are extracted. The timing control scheme is dynamically adjusted according to the N timing control data. The timing control scheme is updated according to the adjustment results to generate the timing control optimization scheme.

2. The intelligent traffic light adaptive control method integrating sensing, computing, and control as described in claim 1, characterized in that, The method involves deploying multiple sensing devices in the target monitoring area to construct a sensing monitoring device group, the method comprising: Traverse the control requirement information of the target traffic lights within the target monitoring area and identify multiple sensing points; Based on the multiple sensing points, the multiple sensing devices are deployed to construct a sensing communication network; Add the sensing communication network to the sensing and monitoring device group.

3. The intelligent traffic light adaptive control method integrating sensing, computing, and control as described in claim 1, characterized in that, The method involves sensing the target monitoring area based on the aforementioned sensor monitoring device group to obtain a regional traffic dataset, wherein the method includes: The sensor monitoring equipment group collects data from the target monitoring area to obtain multiple sensor data, including vehicle speed sensor data and vehicle type sensor data. Based on the vehicle speed sensor data, traffic flow analysis is performed on the target monitoring area to obtain the first traffic data of the target monitoring area. Based on the vehicle type sensor data, traffic road analysis is performed on the target monitoring area to obtain the second traffic data of the target monitoring area. Add the first traffic data and the second traffic data to the regional traffic dataset.

4. The intelligent traffic light adaptive control method integrating sensing, computing, and control as described in claim 3, characterized in that, The method involves extracting features from the regional traffic dataset to obtain multiple regional traffic features, including: Based on the first traffic data, determine the road density information of the target monitoring area; The road traffic status of the target monitoring area is determined based on the second traffic data; Based on the road density information and the road traffic status, feature extraction is performed to obtain road frequency domain features and road time domain features; The road frequency domain features and the road time domain features are added to the multiple regional traffic features.

5. The intelligent traffic light adaptive control method integrating sensing, computing, and control as described in claim 3, characterized in that, Based on the traffic characteristics of the multiple regions, the timing of the target traffic lights is calculated to generate a timing control scheme. The method includes: Based on the traffic characteristics of the multiple regions, the loss of the target traffic lights is calculated to generate the total signal loss time. Based on the total signal loss time, multiple signal cycle durations are calculated using the first traffic data. Multiple timing control information is obtained by matching the duration of the multiple signal cycles with multiple traffic periods; The multiple timing control information is added to the timing control scheme.

6. The intelligent traffic light adaptive control method integrating sensing, computing, and control as described in claim 1, characterized in that, The method for intelligently controlling the target traffic lights according to the timing control optimization scheme includes: The traffic light status is updated according to the timing control optimization scheme to obtain an update command; Parse the update instruction to obtain green light duration update data, red light duration update data, yellow light duration update data, and phase switching sequence update data; Based on the green light duration update data, the red light duration update data, the yellow light duration update data, and the phase switching sequence update data, it is determined whether the real-time traffic road information has reached the preset traffic efficiency index. If the real-time traffic road information does not reach the preset traffic efficiency index, an anomaly backtracking instruction is generated, and anomaly analysis is performed on the timing control optimization scheme according to the anomaly backtracking instruction to determine the source of the abnormal data. The abnormal data source is sent to the remote control terminal, which then performs intelligent processing on the timing control optimization scheme.

Images