Traffic flow monitoring method and system for traffic control point

Abstract

The invention discloses a traffic flow monitoring method and system for a traffic control point, and relates to the technical field of intelligent traffic, and the method comprises the steps: configuring monitoring equipment at the traffic control point, and the monitoring equipment comprises an image collection device and a radar device; video images of the traffic control points are acquired through an image acquisition device, and radar data of the traffic control points are acquired through a radar device; and performing feature extraction based on video images and radar data, performing multi-dimensional flow change analysis according to the obtained fusion traffic flow related feature set, and dynamically adjusting signal lamp timing according to a predicted traffic flow change trend to generate a dynamic traffic scheduling scheme. According to the invention, the technical problems of low traffic efficiency and safety caused by single source of existing traffic flow monitoring data and insufficient dynamic response capability are solved, and the technical effects of realizing multi-dimensional flow monitoring and signal lamp timing adjustment and improving the traffic efficiency and safety by fusing the image and the radar data are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent transportation, and particularly to a traffic flow monitoring method and system for traffic control points. Background Art

[0002] With the increase in urban traffic flow, the problem of traffic congestion has become increasingly serious. Existing traffic flow monitoring technologies mainly rely on a single data source, such as video monitoring or radar monitoring. Although these methods can provide certain traffic flow information, there are problems such as incomplete data and insufficient accuracy. For example, video-based traffic flow monitoring may be affected by lighting conditions and occlusion, while radar monitoring is difficult to distinguish vehicle types. In addition, existing technologies also have deficiencies in dynamic traffic scheduling, mostly based on fixed schedules or simple traffic flow data. Summary of the Invention

[0003] This application provides a traffic flow monitoring method and system for traffic control points, which are used to solve the technical problems of low traffic efficiency and safety caused by the single data source and insufficient dynamic response ability of existing traffic flow monitoring.

[0004] In the first aspect of this application, a traffic flow monitoring method for traffic control points is provided. The method includes: configuring monitoring devices at traffic control points, where the monitoring devices include an image acquisition device and a radar device; collecting video images of the traffic control points through the image acquisition device, and collecting radar data of the traffic control points through the radar device; extracting features based on the video images and radar data to obtain a feature set related to the fused traffic flow; performing multi-dimensional traffic flow change analysis based on the feature set related to the fused traffic flow to generate a predicted traffic flow change trend; and dynamically adjusting the signal light timing according to the predicted traffic flow change trend to generate a dynamic traffic scheduling plan.

[0005] In a second aspect of the present application, a traffic flow monitoring system for a traffic control point is provided. The system includes: a monitoring device configuration module for configuring monitoring devices at the traffic control point, where the monitoring devices include an image acquisition device and a radar device; a traffic data acquisition module for acquiring video images of the traffic control point through the image acquisition device and radar data of the traffic control point through the radar device; a feature extraction module for performing feature extraction based on the video images and radar data to obtain a set of features related to the integrated traffic flow; a multi-dimensional traffic flow change analysis module for performing multi-dimensional traffic flow change analysis according to the set of features related to the integrated traffic flow to generate a predicted traffic flow change trend; and a signal light timing adjustment module for dynamically adjusting the signal light timing according to the predicted traffic flow change trend to generate a dynamic traffic scheduling plan.

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

[0007] The traffic flow monitoring method and system for a traffic control point provided in the present application relate to the field of intelligent transportation technology. By configuring an image acquisition device and a radar device at the traffic control point to respectively acquire video images and radar data, and through feature extraction and fusion to generate a set of features related to the traffic flow, multi-dimensional traffic flow change analysis is performed to predict the traffic flow trend, and based on this, the signal light timing is dynamically adjusted to generate an intelligent traffic scheduling plan, improving traffic management efficiency and traffic capacity, solving the technical problems of single source of traffic flow monitoring data and insufficient dynamic response ability in the prior art, which lead to low traffic efficiency and safety, and achieving the technical effect of realizing multi-dimensional traffic flow monitoring and signal light timing adjustment by fusing image and radar data, and improving traffic efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0009] Figure 1 It is a schematic flowchart of the traffic flow monitoring method for a traffic control point provided in an embodiment of the present application;

[0010] Figure 2 It is a schematic structural diagram of the traffic flow monitoring system for a traffic control point provided in an embodiment of the present application.

[0011] Description of the attached drawing reference numerals: Monitoring device configuration module 11, traffic data acquisition module 12, feature extraction module 13, multi-dimensional traffic flow change analysis module 14, signal timing adjustment module 15. Detailed implementation manners

[0012] This application provides a traffic flow monitoring method and system for traffic control points, which is used to solve the technical problems of single data source and insufficient dynamic response ability in existing traffic flow monitoring, resulting in low traffic efficiency and safety.

[0013] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without creative efforts shall fall within the protection scope of the present application.

[0014] It should be noted that the terms "first", "second", etc. in the description and the above-mentioned drawings of the present application are used to distinguish similar objects, and do not necessarily need to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server including a series of steps or units does not necessarily have to be limited to those clearly listed steps or units, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices.

[0015] Embodiment 1, as Figure 1 shown, this application provides a traffic flow monitoring method for traffic control points, and the method includes:

[0016] P10: Configure a monitoring device at the traffic control point, and the monitoring device includes an image acquisition device and a radar device.

[0017] Specifically, configuring a monitoring device at the traffic control point is the basis for traffic flow monitoring. Specifically, it is necessary to install a monitoring device including an image acquisition device and a radar device at the traffic control point. The image acquisition device is mainly used to capture real-time video images of the traffic control point, and through a high-resolution camera and optical technology, record the appearance of vehicles, license plate information, and the dynamic changes of traffic flow. The radar device detects information such as the speed, distance, and direction of vehicles by emitting and receiving electromagnetic waves, and has the advantages of being unaffected by light conditions and being able to work all-weather.

[0018] To ensure the effective operation of the monitoring equipment, the image acquisition device needs to have the characteristics of high frame rate and high resolution in order to capture clear and continuous image data in a complex traffic environment. At the same time, the radar device can adopt Doppler radar technology, which can accurately measure the speed and distance of vehicles and achieve coverage of multiple lanes through a multi-beam design. The combination of these two devices provides a rich data source for subsequent feature extraction and traffic flow analysis.

[0019] During the installation process, the image acquisition device is usually installed at a high position of the traffic control point, such as on a street lamp pole or a special bracket, to ensure that its field of view can cover the entire traffic control area. The radar device selects a suitable angle and position according to its working principle to avoid signal interference and ensure accurate detection of vehicles. By reasonably arranging these two monitoring devices, comprehensive monitoring of the traffic control point can be achieved, providing reliable data support for subsequent traffic flow analysis and dynamic scheduling.

[0020] In addition, the monitoring equipment also needs to have data transmission and storage functions, and be able to transmit the captured image and radar data to the background processing system in real time and store them efficiently. The real-time and integrity of this data are the keys to achieving accurate traffic flow prediction and dynamic scheduling.

[0021] P20: Collect the video image of the traffic control point through the image acquisition device, and collect the radar data of the traffic control point through the radar device.

[0022] Optionally, in the traffic flow monitoring system, data acquisition is a key step in achieving precise traffic management. Specifically, the image acquisition device and the radar device are respectively responsible for collecting the video image and radar data of the traffic control point, and these two types of data are the basis for subsequent feature extraction and traffic flow analysis.

[0023] First, the image acquisition device captures the video image of the traffic control point in real time through a high-resolution camera. These cameras are usually installed at a high position of the traffic control point, such as on a signal lamp pole or a special monitoring bracket, to ensure that they can cover multiple lanes and traffic flows. The resolution and frame rate of the camera are important factors affecting the image quality. A high-resolution camera can capture clearer images, including details such as the appearance of vehicles, license plate numbers, and traffic signs. At the same time, a high-frame-rate camera can record the dynamic changes of vehicles, providing richer data for subsequent traffic flow analysis.

[0024] To ensure the stability and reliability of image acquisition, image acquisition devices are usually equipped with autofocus, low-light enhancement, and anti-shake technologies. These technologies can effectively cope with complex environmental conditions, such as insufficient lighting at night or vibrations when the vehicle is moving at high speed. In addition, the image acquisition device also preprocesses the acquired video images, such as removing noise, enhancing contrast, and compressing the images, for subsequent transmission and storage.

[0025] Next, the radar device detects radar data at the traffic control point by transmitting and receiving electromagnetic waves. The working principle of the radar device is based on the Doppler effect, that is, the speed and distance of the vehicle are determined by measuring the frequency change of the reflected wave. The radar device can monitor the driving speed of the vehicle, the vehicle spacing, and the moving direction of the vehicle in real time.

[0026] The radar device usually adopts a multi-beam design and can cover multiple lanes simultaneously, so as to achieve comprehensive monitoring of the traffic flow. In addition, the radar device also has the ability to work all-weather and can operate stably even under adverse weather conditions (such as rain, fog, snow, etc.). To improve the accuracy of radar data, the radar device will perform data calibration and filtering processing to remove possible interference signals.

[0027] The data collected by the image acquisition device and the radar device complement each other, forming a complete traffic flow monitoring data set. The image data provides the appearance information of the vehicle and the visual details of the traffic scene, while the radar data provides dynamic information such as the speed and distance of the vehicle. By combining these two types of data, the traffic conditions at the traffic control point can be more comprehensively reflected, providing richer information for subsequent feature extraction and traffic flow analysis. In the process of data acquisition, the synchronization of the image acquisition device and the radar device is also very important. Through precise time synchronization, the consistency of the image data and the radar data in time can be ensured, providing a reliable data basis for subsequent data fusion and analysis.

[0028] P30: Based on the video image and radar data, perform feature extraction to obtain a feature set related to the integrated traffic flow.

[0029] Furthermore, step P30 of the embodiment of the present application further includes:

[0030] P31: Construct a feature extraction unit, where the feature extraction unit includes an image feature extraction channel and a radar feature extraction channel; P32: Based on the feature extraction unit, perform dual-channel feature extraction on the video image and radar data, and fuse the extracted image features and radar data features to generate a feature set related to the integrated traffic flow.

[0031] It should be understood that feature extraction is a key step in converting the collected video images and radar data into traffic flow features that can be used for analysis. The present invention constructs a dual-channel feature extraction unit to process the video images and radar data separately, and fuse the extracted features to generate a fused traffic flow-related feature set. This process not only involves the independent processing of images and radar data, but also includes the collaborative analysis of the two types of data to ensure that the finally generated feature set can comprehensively reflect the real-time traffic conditions at the traffic control point.

[0032] First, in order to effectively process the video images and radar data, the present invention designs a feature extraction unit comprising two independent channels. The image feature extraction channel focuses on extracting visual information related to traffic flow from video images, such as the appearance of vehicles, license plate numbers, vehicle types, and traffic signs. This process utilizes advanced image processing techniques, such as convolutional neural networks (CNNs), to extract hierarchical features of the images through multi-layer convolutional operations, thereby providing rich visual details for subsequent analysis. The radar feature extraction channel focuses on extracting dynamic information such as the speed, distance, and movement direction of vehicles from radar data. The radar device measures the frequency change of the reflected wave through the Doppler effect to obtain the real-time dynamic data of the vehicle. The design of these two channels fully considers the different characteristics of video images and radar data, providing a solid foundation for subsequent feature fusion.

[0033] Next, after the independent extraction of image features and radar features, the two types of features are further fused to generate a fused traffic flow-related feature set. The fusion process first matches the types of the extracted image features and radar features to ensure their consistency in time and space. For example, through timestamp synchronization and spatial position calibration, the image features and radar features at the same moment and the same position are aligned. Subsequently, through feature comparison and fusion algorithms, the feature values with too high dispersion are screened out to reduce the influence of noise and abnormal data. This process can adopt methods such as weighted summation, feature splicing, or fusion networks in deep learning, and finally generate a fused feature set that combines visual information and dynamic information. This fusion strategy not only retains the rich details of the image data but also combines the dynamic advantages of radar data, thus providing more comprehensive and accurate data support for the multi-dimensional analysis and prediction of traffic flow.

[0034] Through the above steps, the present invention achieves the goal of extracting and fusing traffic flow-related features from video images and radar data, providing a high-quality data basis for subsequent traffic flow analysis and dynamic scheduling.

[0035] Furthermore, step P32 of the embodiment of the present application further includes:

[0036] P32-1: Based on the image feature extraction channel of the feature extraction unit, perform semantic segmentation on the video image to generate a pure image set; P32-2: Perform key frame extraction and image downsampling on the pure image set respectively to generate a detailed image set and a dynamic feature set; P32-3: Identify traffic flow characteristics according to the detailed image set and the dynamic feature set to obtain a first traffic flow feature set; P32-4: Based on the radar feature extraction channel of the feature extraction unit, extract features from the radar data to obtain a second traffic flow feature set.

[0037] In a possible embodiment of the present application, the process of dual-channel feature extraction can be further refined. The video image and radar data are processed through the image feature extraction channel and the radar feature extraction channel respectively, and finally a feature set related to the integrated traffic flow is generated.

[0038] In the image feature extraction channel, first perform semantic segmentation on the collected video image. Semantic segmentation is an advanced image processing technology. By classifying each pixel in the image into different semantic categories (such as vehicles, roads, pedestrians, traffic signs, etc.), background noise and other irrelevant information can be effectively removed, thereby generating a pure image set. This process can not only highlight the core objects of traffic control points (such as vehicles and lanes), but also provide a clearer and more accurate image basis for subsequent feature extraction. Through semantic segmentation, the system can focus on the image content directly related to traffic flow, improving the efficiency and accuracy of feature extraction.

[0039] After generating the pure image set, further process the image data to extract more representative and efficient data. First, through the key frame extraction technology, select the frames containing important information from the continuous video frames. Key frame extraction can reduce redundant data while retaining the movement trajectories of vehicles and the dynamic changes of traffic flow. Subsequently, perform image downsampling on the pure image set to reduce the image resolution, reduce the data volume, and at the same time retain the core features of the image. Through this process, a detailed image set and a dynamic feature set are generated, which are used to capture the appearance details of vehicles and the dynamic changes of traffic flow respectively.

[0040] Furthermore, based on the generated detailed image set and dynamic feature set, traffic flow feature recognition is performed. Detect, classify, and count the vehicles in the image through deep learning algorithms (such as convolutional neural network, CNN), and at the same time extract features such as the speed, type, and color of the vehicles. These features are integrated into a first traffic flow feature set, providing rich visual information for subsequent traffic flow analysis and prediction. This process can not only identify the features of individual vehicles, but also analyze the overall state of traffic flow, such as congestion level and vehicle distribution.

[0041] Next, in the radar feature extraction channel, the collected radar data is processed to obtain dynamic information related to traffic flow. The radar device measures the speed, distance, and direction of movement of vehicles by emitting and receiving electromagnetic waves and using the Doppler effect. After filtering and calibration processing, these data generate a second traffic flow feature set, which contains key information such as vehicle speed, acceleration, and spacing. The extraction process of radar data particularly emphasizes the capture of dynamic changes and can provide real-time movement information for traffic flow analysis, making up for the deficiencies of image data in dynamic perception.

[0042] Through the above steps, the image feature extraction channel and the radar feature extraction channel respectively generate the first and second traffic flow feature sets. These two feature sets will be further fused to generate a comprehensive traffic flow-related feature set, providing comprehensive data support for subsequent multi-dimensional traffic flow change analysis and dynamic scheduling.

[0043] Furthermore, step P32 of the embodiment of the present application further includes:

[0044] P32-5: Match the feature types of the first traffic flow feature set and the second traffic flow feature set to generate multiple feature control groups; P32-6: Based on the multiple feature control groups, perform feature comparison and fusion, and filter out feature values with a dispersion greater than the threshold to generate a fused traffic flow-related feature set.

[0045] Optionally, after the feature extraction of the image feature extraction channel and the radar feature extraction channel is completed, the present invention further performs a fusion process on the first traffic flow feature set and the second traffic flow feature set generated by the two channels.

[0046] In order to effectively fuse image features and radar features, it is first necessary to match the feature types of the two feature sets. Specifically, according to the physical meaning and timestamp information of the features, image features (such as vehicle type, license plate number, vehicle color, etc.) are aligned with radar features (such as vehicle speed, distance, direction of movement, etc.) to generate multiple feature control groups. For example, for vehicles at the same moment and in the same lane, their image features and radar features will be combined into a control group. This process ensures the correspondence between the two types of features in time and space, providing a basis for subsequent fusion analysis.

[0047] After generating the feature control group, the feature comparison and fusion of these feature groups are further carried out. During the fusion process, the correlation between the image features and radar features within each feature group is calculated, and the fused features are evaluated. To ensure the reliability and accuracy of the fused features, the system will screen out the feature values with a dispersion greater than the preset threshold. Dispersion refers to the degree of deviation of the feature values in the statistical distribution. Feature values with too high dispersion usually represent noise or abnormal data. By using empirical data to set a reasonable threshold, these unreliable feature values can be eliminated, and more representative and consistent features can be retained. Finally, after comparison fusion and dispersion screening, a fused traffic flow related feature set is generated, providing high-quality data support for subsequent traffic flow analysis and dynamic scheduling.

[0048] P40: According to the fused traffic flow related feature set, perform multi-dimensional traffic flow change analysis to generate the predicted traffic flow change trend.

[0049] Furthermore, step P40 of the embodiment of the present application further includes:

[0050] P41: The fused traffic flow related feature set includes the number of vehicles passing through during the pre-trial period, vehicle types, vehicle speeds, and vehicle driving directions; P42: Based on the number of vehicles passing through, vehicle types, vehicle speeds, and vehicle driving directions during the pre-trial period, perform multi-dimensional traffic flow change analysis to generate traffic flow change trends in multiple dimensions; P43: Fuse the traffic flow change trends in the multiple dimensions to generate the predicted traffic flow change trend.

[0051] It should be understood that it is a key link to perform multi-dimensional traffic flow change analysis based on the fused traffic flow related feature set and generate the predicted traffic flow change trend.

[0052] First of all, the fused traffic flow related feature set is the basis of traffic flow analysis, including multi-dimensional information such as the number of vehicles passing through the traffic control point, vehicle types, vehicle speeds, and vehicle driving directions during the pre-trial period. This information is obtained through feature extraction and fusion of image and radar data, and can comprehensively reflect the traffic conditions at the traffic control point during the pre-trial period. The number of vehicles reflects the scale of traffic flow; vehicle types reveal the proportion of different types of vehicles; vehicle speeds and driving directions provide the dynamic characteristics of traffic flow. These features provide rich data support for subsequent multi-dimensional traffic flow change analysis.

[0053] Next, based on the vehicle quantity, type, speed, and driving direction in the integrated traffic flow - related feature set, multi - dimensional traffic flow change analysis is carried out. This process generates traffic flow change trends for multiple dimensions by analyzing the change trends of each dimension separately. Specifically, the system first counts the vehicle quantity in different time periods within the pre - review cycle, analyzes the increasing and decreasing trends of traffic flow, and thus determines the peak and trough traffic periods. At the same time, the system analyzes the traffic flow changes of different types of vehicles to understand their proportion changes in the traffic flow, providing a basis for traffic planning. In addition, by monitoring the changes in vehicle speed, the system can judge the smoothness and congestion of the traffic flow, while the changes in vehicle driving direction help analyze the distribution and flow direction of the traffic flow. These multi - dimensional traffic flow change trends provide detailed and comprehensive information for subsequent comprehensive prediction.

[0054] After completing the multi - dimensional traffic flow change analysis, the traffic flow change trends of multiple dimensions are integrated to generate the predicted traffic flow change trend. This process comprehensively analyzes the change trends of vehicle quantity, type, speed, and driving direction, combines the actual needs of traffic management, evaluates the importance of the traffic flow change trends of different dimensions, and assigns weights. For example, the change in vehicle speed may be more critical for judging traffic congestion, so a higher weight is assigned. Through weighted summation or other integration algorithms, the multi - dimensional trends are integrated into a comprehensive trend, and combined with historical data and machine - learning models, the predicted traffic flow change trend is generated. This trend not only reflects the dynamic changes of the current traffic flow but also can predict the traffic flow changes in a future period, providing forward - looking guidance for traffic scheduling, thus effectively alleviating traffic congestion and improving road traffic efficiency.

[0055] Furthermore, step P43 of the embodiment of the present application further includes:

[0056] P43 - 1: Based on the traffic - related features of multiple dimensions, conduct importance evaluation respectively, and generate the traffic impact weights of each feature according to the evaluation results; P43 - 2: According to the traffic impact weights, integrate the traffic flow change trends of the multiple dimensions to generate the predicted traffic flow change trend.

[0057] Specifically, after completing the multi - dimensional traffic flow change analysis, it is possible to further refine how to integrate the traffic flow change trends of multiple dimensions to generate an accurate predicted traffic flow change trend.

[0058] First, in order to more scientifically integrate the traffic flow change trends in different dimensions, the importance of traffic-related characteristics in each dimension is evaluated. These characteristics include the number of vehicles, vehicle types, vehicle speeds, and vehicle driving directions, etc. The purpose of the importance evaluation is to determine the influence of each characteristic on the traffic flow change, so as to assign a traffic flow influence weight to each characteristic. For example, the change in vehicle speed may be more critical for judging traffic congestion, so it will be given a higher weight; while the change in vehicle type may have an important impact on traffic planning, but has a relatively small impact on the immediate traffic flow change, so the weight is relatively low. Through this evaluation, the system can dynamically adjust the weights of each characteristic according to the actual traffic management needs to ensure that the integration process is more scientific and reasonable.

[0059] After determining the traffic flow influence weights of each characteristic, the traffic flow change trends in multiple dimensions are integrated according to these weights. Specifically, the change trend of each dimension is multiplied by the corresponding weight, and then these trends are integrated into a comprehensive predicted traffic flow change trend through weighted summation. This process not only considers the independent changes of each dimension, but also adjusts the contribution degree of different dimensions to the overall trend through weights. The finally generated predicted traffic flow change trend can more accurately reflect the real-time traffic conditions at traffic control points and provide forward-looking guidance for future traffic flow changes. This weight-based trend integration method enables the system to dynamically adapt to different traffic scenarios, improving the accuracy and reliability of predictions. This process provides a scientific basis for dynamic traffic scheduling and signal light optimization, effectively enhancing the intelligent level of traffic management.

[0060] P50: Dynamically adjust the signal light timing according to the predicted traffic flow change trend to generate a dynamic traffic scheduling plan.

[0061] Furthermore, step P50 of the embodiment of this application further includes:

[0062] P51: Receive the predicted traffic flow change trends of multiple traffic control points; P52: Obtain the signal light timing information of the target urban road network, a pre-trained traffic scheduling model; P53: Optimize the signal light timing in combination with the predicted traffic flow change trends according to the traffic scheduling model to generate the dynamic traffic scheduling plan.

[0063] Optionally, by dynamically adjusting the signal light timing, a dynamic traffic scheduling plan applicable to multiple traffic control points is generated, converting the predicted traffic flow change trend into actual traffic management measures, thereby realizing the intelligent management of the urban traffic network.

[0064] In order to achieve effective management of the entire urban traffic network, the predicted traffic flow change trends from multiple traffic control points are first received. These trends are obtained based on the analysis of the integrated traffic flow-related feature sets of each control point, which can reflect the changes in traffic flow at each control point in the future. By integrating data from multiple control points, the system can fully understand the dynamic status of the urban traffic network and provide a global perspective for subsequent signal timing optimization and traffic scheduling. This process ensures that traffic management decisions are not only based on the local situation of a single intersection, but also take into account the dynamic changes of the entire traffic network.

[0065] Furthermore, before generating a dynamic traffic scheduling plan, the system needs to obtain the current signal light timing information of the target city's road network and the pre-trained traffic scheduling model. The signal light timing information includes parameters such as the signal cycle, phase setting, and current green light duration of each intersection. These are the basis for dynamic adjustment and reflect the current operating status of traffic management. At the same time, the pre-trained traffic scheduling model is an intelligent model built based on historical data and machine learning algorithms. It can quickly generate optimized signal light timing plans based on the input traffic flow change trend. By learning the patterns and rules in historical traffic data, the model can effectively cope with complex traffic scenarios and ensure the scientificity and practicality of the scheduling plan.

[0066] Furthermore, based on the pre-trained traffic scheduling model, combined with the predicted traffic flow change trends of multiple traffic control points, the signal light timing is optimized. Specifically, the predicted traffic flow change trends are input into the traffic scheduling model. The model analyzes the distribution and changes of future traffic flow based on these trends, and calculates the optimal signal light timing plan based on the current signal light timing information. The goal of the optimization is to reduce traffic congestion, improve road traffic efficiency, and ensure the smoothness of traffic flow. A dynamic traffic scheduling plan is generated based on the optimized signal light timing plan. The plan not only includes the adjustment of signal light timing, but may also involve measures such as traffic flow guidance and priority traffic strategies. By dynamically adjusting the signal light timing, it can respond to changes in traffic flow in real time, effectively alleviate traffic congestion, and improve the overall operating efficiency of urban traffic. This process not only improves the flexibility and adaptability of traffic management, but also provides strong support for the efficient operation of urban traffic.

[0067] In summary, the embodiments of the present application have at least the following technical effects:

[0068] This application configures image acquisition devices and radar devices at traffic control points to collect video images and radar data respectively, generates traffic flow-related feature sets through feature extraction and fusion, conducts multi-dimensional traffic change analysis to predict traffic flow trends, and dynamically adjusts traffic light timing accordingly, generates intelligent traffic scheduling plans, and improves traffic management efficiency and traffic capacity.

[0069] It achieves the technical effect of realizing multi-dimensional traffic flow monitoring and signal light timing adjustment by fusing image and radar data, and improving traffic passing efficiency and safety.

[0070] Embodiment 2, based on the same inventive concept as the traffic flow monitoring method for traffic control points in the foregoing embodiment, as Figure 2 shown, the present application provides a traffic flow monitoring system for traffic control points. The system in the embodiments of the present application and the method embodiments are based on the same inventive concept. Among them, the system includes:

[0071] A monitoring device configuration module 11, which is used to configure monitoring devices at traffic control points. The monitoring devices include an image acquisition device and a radar device.

[0072] A traffic data acquisition module 12, which is used to acquire video images of the traffic control points through the image acquisition device and acquire radar data of the traffic control points through the radar device.

[0073] A feature extraction module 13, which is used to extract features based on the video images and radar data to obtain a set of features related to the fused traffic flow.

[0074] A multi-dimensional traffic flow change analysis module 14, which is used to perform multi-dimensional traffic flow change analysis according to the set of features related to the fused traffic flow and generate a predicted traffic flow change trend.

[0075] A signal light timing adjustment module 15, which is used to dynamically adjust the signal light timing according to the predicted traffic flow change trend and generate a dynamic traffic scheduling plan.

[0076] Furthermore, the feature extraction module 13 is further used to perform the following steps:

[0077] Construct a feature extraction unit, which includes an image feature extraction channel and a radar feature extraction channel; based on the feature extraction unit, perform two-channel feature extraction on the video images and radar data, and fuse the extracted image features and radar data features to generate a set of features related to the fused traffic flow.

[0078] Furthermore, the feature extraction module 13 is further used to perform the following steps:

[0079] Based on the image feature extraction channels of the feature extraction unit, semantic segmentation is performed on the video image to generate a pure image set; the pure image set is respectively subjected to key frame extraction and image downsampling to generate a detailed image set and a dynamic feature set; traffic flow feature recognition is performed according to the detailed image set and the dynamic feature set to obtain a first traffic flow feature set; based on the radar feature extraction channels of the feature extraction unit, feature extraction is performed on the radar data to obtain a second traffic flow feature set.

[0080] Further, the feature extraction module 13 is further configured to perform the following steps:

[0081] Match the feature types of the first traffic flow feature set and the second traffic flow feature set to generate multiple feature comparison groups; based on the multiple feature comparison groups, perform feature comparison and fusion, and screen out feature values with a dispersion greater than the threshold to generate a fused traffic flow related feature set.

[0082] Further, the multi-dimensional traffic flow change analysis module 14 is further configured to perform the following steps:

[0083] The fused traffic flow related feature set includes the number of vehicles passing through during the pre-trial period, vehicle types, vehicle speeds, and vehicle driving directions; based on the number of vehicles passing through, vehicle types, vehicle speeds, and vehicle driving directions during the pre-trial period, multi-dimensional traffic flow change analysis is performed to generate traffic flow change trends in multiple dimensions; the traffic flow change trends in multiple dimensions are fused to generate a predicted traffic flow change trend.

[0084] Further, the multi-dimensional traffic flow change analysis module 14 is further configured to perform the following steps:

[0085] Based on traffic flow related features in multiple dimensions, importance assessments are respectively performed, and traffic flow impact weights for each feature are generated according to the assessment results; according to the traffic flow impact weights, the traffic flow change trends in multiple dimensions are fused to generate a predicted traffic flow change trend.

[0086] Further, the signal light timing adjustment module 15 is further configured to perform the following steps:

[0087] Receive the predicted traffic flow change trends of multiple traffic control points; obtain the signal light timing information of the target urban road network, a pre-trained traffic scheduling model; according to the traffic scheduling model, combine the multiple predicted traffic flow change trends to optimize the signal light timing and generate the dynamic traffic scheduling plan.

[0088] It should be noted that the above order of the embodiments of the present application is only for description and does not represent the superiority or inferiority of the embodiments. In addition, the above description of specific embodiments of this specification has been made. Further, the processes depicted in the drawings do not necessarily require the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0089] The above are only the preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present application shall be included within the protection scope of the present application.

[0090] This specification and the drawings are only exemplary descriptions of the present application and are considered to have covered any and all modifications, variations, combinations, or equivalents within the scope of the present application. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalent technologies, the present application is intended to include these changes and modifications.

Claims

1. A method for monitoring traffic flow at a traffic control point, characterized in that: The method comprises: Configuring monitoring equipment at traffic control points, wherein the monitoring equipment includes an image acquisition device and a radar device; Collecting the video image of the traffic control point by the image acquisition device, and collecting the radar data of the traffic control point by the radar device; Extract features based on the video image and radar data to obtain a fused traffic flow related feature set; Perform multi-dimensional traffic flow change analysis based on the fused traffic flow related feature set to generate a predicted traffic flow change trend; According to the predicted traffic flow change trend, the signal light timing is dynamically adjusted to generate a dynamic traffic scheduling plan.

2. The method for monitoring traffic flow at a traffic control point according to claim 1, characterized in that: Feature extraction is performed based on the video image and radar data to obtain a fused traffic flow related feature set, including: Constructing a feature extraction unit, wherein the feature extraction unit includes an image feature extraction channel and a radar feature extraction channel; Based on the feature extraction unit, dual-channel feature extraction is performed on the video image and radar data, and the extracted image features and radar data features are fused to generate a fused traffic flow related feature set.

3. The method for monitoring traffic flow at a traffic control point according to claim 2, characterized in that: Based on the feature extraction unit, dual-channel feature extraction is performed on the video image and radar data, including: Based on the image feature extraction channel of the feature extraction unit, semantically segment the video image to generate a clean image set; The clean image set is subjected to key frame extraction and image downsampling respectively to generate a detail image set and a dynamic feature set; Performing traffic flow feature recognition according to the detail image set and the dynamic feature set to obtain a first traffic flow feature set; Based on the radar feature extraction channel of the feature extraction unit, feature extraction is performed on the radar data to obtain a second traffic flow feature set.

4. The method for monitoring traffic flow at a traffic control point according to claim 3, characterized in that: The extracted image features and radar data features are fused, including: Performing feature type matching on the first traffic flow feature set and the second traffic flow feature set to generate a plurality of feature control groups; Based on the multiple feature control groups, feature comparison and fusion are performed to screen out feature values ​​whose discreteness is greater than a threshold value, and generate a fused traffic flow related feature set.

5. The method for monitoring traffic flow at a traffic control point according to claim 1, characterized in that: Based on the fused traffic flow related feature set, a multi-dimensional traffic flow change analysis is performed to generate a predicted traffic flow change trend, including: The fused traffic flow related feature set includes the number of vehicles passing through the pre-screening period, the vehicle type, the vehicle speed and the vehicle driving direction; Based on the number of vehicles, vehicle types, vehicle speeds and vehicle travel directions passing through the pre-examination period, a multi-dimensional traffic flow change analysis is performed to generate traffic flow change trends in multiple dimensions; The traffic flow change trends in the multiple dimensions are integrated to generate a predicted traffic flow change trend.

6. The method for monitoring traffic flow at a traffic control point according to claim 5, characterized in that: The traffic flow change trends in the multiple dimensions are integrated to generate a predicted traffic flow change trend, including: Based on the traffic-related features of multiple dimensions, the importance is evaluated respectively, and the traffic impact weight of each feature is generated according to the evaluation results; According to the traffic impact weights, the traffic change trends in the multiple dimensions are integrated to generate a predicted traffic flow change trend.

7. The method for monitoring traffic flow at a traffic control point according to claim 1, characterized in that: According to the predicted traffic flow change trend, the signal light timing is dynamically adjusted to generate a dynamic traffic scheduling plan, including: Receive multiple predicted traffic flow change trends at multiple traffic control points; Obtain the traffic light timing information of the target city’s road network and pre-train the traffic scheduling model; According to the traffic scheduling model, the signal light timing is optimized in combination with the multiple predicted traffic flow change trends to generate the dynamic traffic scheduling plan.

8. A traffic flow monitoring system for a traffic control point, characterized in that: The system comprises: A monitoring device configuration module, the monitoring device configuration module is used to configure monitoring equipment at a traffic control point, the monitoring equipment including an image acquisition device and a radar device; A traffic data acquisition module, the traffic data acquisition module is used to acquire the video image of the traffic control point through the image acquisition device, and to acquire the radar data of the traffic control point through the radar device; A feature extraction module, the feature extraction module is used to extract features based on the video image and radar data to obtain a fused traffic flow related feature set; A multi-dimensional traffic flow change analysis module, which is used to perform multi-dimensional traffic flow change analysis based on the fused traffic flow related feature set to generate a predicted traffic flow change trend; The signal light timing adjustment module is used to dynamically adjust the signal light timing according to the predicted traffic flow change trend and generate a dynamic traffic scheduling plan.

Images