Vehicle-road coordination system and vehicle passing management method

Abstract

The embodiment of the invention relates to the technical field of traffic management, and discloses a vehicle-road coordination system and a vehicle passing management method. The vehicle-road coordination system accurately monitors the number of turning vehicles on a first passing road and reasonably regulates and controls traffic lights; under the condition that data of the vehicle to be steered is increased and abnormal road occupation exists, the green light passing duration of the steering indication traffic signal lamp is controlled to be prolonged, so that the waiting time of the steering vehicle on the road is effectively shortened, the passing efficiency of the vehicle is improved, and meanwhile traffic jam aggravation caused by the abnormal road occupation vehicle is avoided. Under the condition that the passing time of the steering traffic signal lamp is prolonged, the prompt information sending interval is reasonably arranged for the second passing road according to the traffic flow condition of the target passing direction, so that downstream vehicles can make preparation in advance, smooth fusion of the confluence traffic flow and the main road traffic flow is guaranteed, and the traffic safety is improved. And the problem that the traffic capacity of the whole road network is reduced due to unsmooth confluence is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic management, and particularly to a vehicle-road coordination system and a vehicle passing management method. Background Art

[0002] With the acceleration of the urbanization process, the traffic flow on roads has increased sharply, and the problem of traffic congestion has become increasingly serious, bringing great inconvenience to people's travel, and at the same time causing many negative effects such as energy waste and environmental pollution. In an urban road network, it is very common for vehicles to enter the second passing road from the first passing road via a connecting road, and such intersections or connecting sections are often high-incidence areas of traffic congestion.

[0003] Traditional traffic management methods mainly rely on traffic signal settings with fixed durations and simple traffic flow monitoring devices, and are difficult to adapt to complex and changeable traffic conditions. For example, in the turning area of the first passing road, only based on the fixed signal timing, it is impossible to make timely adjustments according to the dynamic changes in the number of vehicles waiting to turn. Especially when the backlog of normal waiting vehicles is too large or there are abnormal occupation situations, it is easy to cause long waiting times and queue extensions for turning vehicles, thereby affecting the traffic efficiency of the entire road and even causing congestion on the first passing road. Summary of the Invention

[0004] The main object of the present invention is to provide a vehicle-road coordination system and a vehicle passing management method, aiming to solve the technical problem of low traffic efficiency of the entire road caused by easy congestion at intersections in the prior art.

[0005] To achieve the above object, in a first aspect, an embodiment of the present application provides a vehicle-road coordination system. The vehicle-road coordination system is provided in a target passing road network. The target passing road network includes a first passing road, a second passing road, and a connecting road connecting the first passing road and the second passing road. The vehicle-road coordination system includes: A camera device, which is provided at the turning position of the first passing road facing the connecting road, and is used to detect the number of target vehicles waiting to turn on the first passing road, where the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; A passing traffic flow monitor, which is provided on the second passing road and is used to monitor the traffic flow in the target passing direction of the second passing road, and the target passing direction is the same as the direction in which the connecting road merges into the second passing road; A traffic signal, which is used to indicate the passage of vehicles turning from the first passing road to the connecting road; The first roadside information interaction device is arranged on the first passing road and is at a first preset distance from the camera device. It is used to send a first prompt message to the passing vehicles on the first passing road when the number of target vehicles waiting to turn on the first passing road is greater than or equal to a preset number. The first prompt message is used to prompt the downstream vehicles on the first passing road to pay attention to the large turning traffic flow ahead. The second roadside information interaction device is arranged on the second passing road and is at a second preset distance from the passing traffic flow monitor. It is used to send a second prompt message to the passing vehicles in the target passing direction of the second passing road when the traffic signal extends the passing duration of the vehicles turning from the first passing road to the connected road. The second prompt message is used to prompt the downstream vehicles on the second passing road to pay attention to the large confluence traffic flow ahead.

[0006] In a possible implementation manner, the passing traffic flow monitor includes a loop detector arranged on the ground of the second passing road and / or a laser sensor arranged on the roadside of the second passing road. The first roadside information interaction device and the second roadside information interaction device include short-range wireless communication devices arranged on the roadside. The short-range wireless communication devices are used to send prompt messages to in-vehicle units.

[0007] In a second aspect, an embodiment of the present application further provides a vehicle passing management method. This method is applied to the vehicle-road coordination system as described in the first aspect. The method includes: Obtain the number of target vehicles waiting to turn on the first passing road according to the captured image of the camera device, where the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally. When the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the road abnormally is greater than or equal to a second preset value, adjust the green light duration ratio of the traffic signal and trigger a vehicle-road coordination instruction. Obtain the historical average traffic flow in the target passing direction of the second passing road through the passing traffic flow monitor according to the vehicle-road coordination instruction. Correct the historical average traffic flow according to the current day's traffic flow data in the target passing direction of the second passing road to obtain the current target traffic flow in the target passing direction of the second passing road. When the current target traffic flow in the target traffic direction of the second traffic lane is greater than the preset traffic flow, the second roadside information interaction device repeatedly sends a second prompt message to the passing vehicles on the second traffic lane at a first preset time interval. When the current target traffic flow in the target traffic direction of the second traffic lane is less than or equal to the preset traffic flow, the second roadside information interaction device repeatedly sends a second prompt message to the passing vehicles on the second traffic lane at a second preset time interval, where the first preset time interval is less than the second preset time interval, and the second prompt message is used to prompt the downstream vehicles on the second traffic lane to pay attention to the large merging traffic flow ahead.

[0008] In a possible implementation manner, when the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the road abnormally is greater than or equal to a second preset value, adjusting the green light duration ratio of the traffic signal lamp and triggering a vehicle-road coordination instruction includes: Determining an increase value of the green light duration ratio of the traffic signal lamp according to the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; Adjusting the original green light duration ratio according to the increase value of the green light duration ratio of the traffic signal lamp to extend the passing duration of the vehicles turning from the first traffic lane to the connected road.

[0009] In a possible implementation manner, the determining an increase value of the green light duration ratio of the traffic signal lamp according to the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally includes: Obtaining the queuing length of the vehicles waiting normally according to the number of target vehicles waiting normally and the preset average vehicle length; Obtaining the queuing length of the vehicles occupying the road abnormally according to the number of target vehicles occupying the road abnormally and the average vehicle length; Inputting the queuing length of the vehicles waiting normally and the queuing length of the vehicles occupying the road abnormally into a pre-trained green light ratio increment prediction model to obtain an increase value of the green light duration ratio; The green light ratio increment prediction model satisfies the following expression: ΔP = (W 1 *L 1 +W 2 *L 2 )*P 0 , where, W 2 >W 1 , ΔP is the increase value of the green light duration ratio, L 1 is the queuing length of the vehicles waiting normally, L 2 is the queuing length of the vehicles occupying the road abnormally, W 1 is the influence weight of the queuing length of the vehicles waiting normally on the increment of the green light ratio, W 2The influence weight of the queue length of abnormally occupying vehicles on the increment of the green light ratio, P 0 The reference value of the increment of the green light ratio.

[0010] In a possible implementation, after adjusting the proportion of the green light duration of the traffic signal lamp and triggering the vehicle-road coordination instruction, it further includes: Sending a first prompt message to the passing vehicles on the first passing road through the first roadside information interaction device, where the first prompt message is used to prompt the downstream vehicles on the first passing road to pay attention to the large turning traffic flow ahead.

[0011] In a possible implementation, the sending a first prompt message to the passing vehicles on the first passing road through the first roadside information interaction device includes: Determining the expected congestion duration according to the number of target vehicles waiting normally and the number of target vehicles abnormally occupying the road; When the expected congestion duration is greater than or equal to the preset congestion duration, sending a first prompt message for detouring to the passing vehicles on the first passing road through the first roadside information interaction device.

[0012] In a possible implementation, the historical average traffic flow is the average of the historical traffic flows within a preset time period corresponding to the moment when the traffic signal lamp starts to be adjusted, and the correcting the historical average traffic flow according to the traffic flow data of the second passing road in the target passing direction on the current day to obtain the current target traffic flow of the second passing road in the target passing direction includes: Obtaining the average traffic flow data of the second passing road in the target passing direction on the current day; Determining that the average traffic flow of the second passing road in the target passing direction on the current day is greater than or equal to the historical average traffic flow, and performing a positive correction on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction; Determining that the average traffic flow of the second passing road in the target passing direction on the current day is less than the historical average traffic flow, and performing a negative correction on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction.

[0013] In a possible implementation, the performing a positive correction on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction includes: Calculating the difference between the average traffic flow data on the current day and the historical average traffic flow data to obtain a positive correction increment.

[0014] Adding the product of the positive correction increment and the first preset correction coefficient to the historical average traffic flow to obtain the current target traffic flow; The performing a negative correction on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction includes: Calculate the difference between the historical average traffic flow data and the average traffic flow data of the current day to obtain a negative correction reduction amount; Subtract the product of the negative correction reduction amount and the second preset correction coefficient from the historical average traffic flow to obtain the current target traffic flow, where the first preset correction coefficient is not equal to the second preset correction coefficient.

[0015] In a possible implementation manner, the imaging device includes a first imaging device and a second imaging device, and the shooting perspectives of the first imaging device and the second imaging device are different. The method for obtaining the number of target vehicles waiting to turn on the first passing road according to the captured image of the imaging device includes: Obtain the captured images of the first imaging device and the second imaging device respectively; Use image fusion technology to fuse the captured images from different perspectives, and analyze the fused image through a pre-trained target detection model to obtain the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally.

[0016] Different from the prior art, the vehicle-road coordination system and vehicle passing management method provided by the embodiments of the present application accurately monitor the number of turning vehicles on the first passing road and reasonably control the traffic lights. That is, when the data of the vehicles waiting to turn increases and there are abnormal road occupancies, the green light passing duration of the turning indication traffic light is controlled to be extended, so as to effectively reduce the waiting time of the turning vehicles on this road, improve its passing efficiency, and at the same time avoid the aggravation of traffic jams caused by abnormally occupying vehicles. And when the passing duration of the turning traffic light is extended, for the second passing road, the sending interval of the prompt information is reasonably arranged according to the traffic flow situation in the target passing direction, so that the downstream vehicles can make preparations in advance, ensuring the smooth integration of the merging traffic flow and the main road traffic flow, reducing the problem of the overall road network passing capacity decline caused by unsmooth merging, and realizing the optimal distribution of the traffic flow of the target passing road network. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on the structures shown in these drawings.

[0018] Figure 1 It is a schematic diagram of the equipment layout of the vehicle-road coordination system in some embodiments of the present application; Figure 2 It is a schematic flowchart of the vehicle passing management method in some embodiments of the present application; Figure 3 It is a schematic flowchart of a vehicle traffic management method in some other embodiments of this application; Figure 4 It is a schematic diagram of the module structure of a vehicle-road coordination system in some embodiments of this application.

[0019] The realization, functional features and advantages of the object of the present invention will be further described in conjunction with the embodiments with reference to the accompanying drawings. Specific embodiments

[0020] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative work fall within the protection scope of the present invention.

[0021] It should be noted that all directional indications (such as up, down, left, right, front, back...) in the embodiments of the present invention are only used to explain the relative positional relationship and movement conditions between components in a specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indications will also change accordingly.

[0022] In addition, the descriptions involving "first", "second", etc. in the present invention are only for descriptive purposes, and cannot be understood as indicating or implying their relative importance or implicitly indicating the quantity of the indicated technical features. Thus, the features defined with "first" and "second" may explicitly or implicitly include at least one of the features. In addition, "and / or" throughout the text includes three scenarios. Taking A and / or B as an example, it includes the technical solution of A, the technical solution of B, and the technical solution that A and B are satisfied at the same time. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of those of ordinary skill in the art to implement. When the combination of technical solutions results in contradictions or cannot be implemented, it should be considered that such a combination of technical solutions does not exist and is not within the protection scope required by the present invention.

[0023] With the acceleration of the urbanization process, the traffic flow on the road has increased sharply, and the problem of traffic congestion has become increasingly serious, bringing great inconvenience to people's travel, and at the same time causing many negative effects such as energy waste and environmental pollution. In the urban road network, it is very common for vehicles to enter the second traffic road from the first traffic road via the connecting road, and such intersections or connecting sections are often high-incidence areas of traffic congestion.

[0024] Traditional traffic management methods mainly rely on traffic signal settings with fixed durations and simple traffic flow monitoring devices, making it difficult to adapt to complex and changing traffic conditions. For example, in the turning area of the first through road, simply based on the fixed signal timing, it is impossible to make timely adjustments according to the dynamic changes in the number of vehicles waiting to turn. Especially when there is an excessive backlog of normal waiting vehicles or abnormal lane occupation, it is easy to cause long waiting times for turning vehicles and queue extension, thereby affecting the traffic efficiency of the entire road and even causing congestion on the first through road.

[0025] As Figure 1 shown, in the embodiment of the present application, the vehicle-road coordination system is deployed in the target through road network. The target through road network includes the first through road D100, the second through road D200, and the connecting road D300 connecting the first through road D100 and the second through road D200. The vehicle-road coordination system includes: A camera device 100, which is arranged at the turning position of the first through road D100 facing the connecting road D300, and is used to detect the number of target vehicles waiting to turn on the first through road D100. Among them, the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the lane abnormally; A passing traffic flow monitor 200, which is arranged on the second through road D200 and is used to monitor the traffic flow in the target passing direction of the second through road D200. The target passing direction is the same as the direction in which the connecting road D300 merges into the second through road D200; the passing traffic flow monitor 200 can be a loop detector arranged on the ground of the second through road or a laser sensor arranged on the roadside of the second through road; A traffic signal 300, which is used to indicate the passage of vehicles turning from the first through road D100 to the connecting road D300; A first roadside information interaction device 400, which is arranged on the first through road D100 and is spaced a first preset distance (such as at a position 800M away) from the camera device 100. It is used to send a first prompt message to the passing vehicles on the first through road D100 when the number of target vehicles waiting to turn on the first through road D100 is greater than or equal to a preset number. The first prompt message is used to prompt the downstream vehicles on the first through road to pay attention to the large turning traffic flow ahead; The second roadside information interaction device 500 is disposed on the second traffic lane D200 and is spaced from the traffic flow monitor 200 by a second preset distance (for example, at a position 1 km away). When the traffic signal 300 extends the passing time of the vehicles turning from the first traffic lane D100 to the connecting road D300, the second roadside information interaction device 500 is configured to send a second prompt message to the passing vehicles in the target passing direction of the second traffic lane D200. The second prompt message is used to prompt the downstream vehicles in the second traffic lane D200 to pay attention to the large confluence traffic flow ahead.

[0026] It should be noted that the first roadside information interaction device and the second roadside information interaction device include short-range wireless communication devices (such as local area network communication or Bluetooth communication, etc.) disposed on the roadside. The short-range wireless communication device is used to send prompt messages to the in-vehicle unit.

[0027] As Figures 1 - 3 shown, the following takes the vehicle road coordination system executing the vehicle passing management method as an example for description. It should be noted that although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order than here. Please refer to the appendix Figure 2 , the method includes the following steps S100-step S500: Step S100: Obtain the number of target vehicles waiting to turn on the first traffic lane according to the captured images of the imaging device. Among them, the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; In one embodiment, first, the imaging device can shoot the turning position of the first traffic lane towards the connecting road at a fixed frame rate (for example, 25 frames per second) to obtain an image sequence with high resolution (such as 1080p). The collected images are grayscale processed to reduce the data volume and highlight the contour features of the vehicles, and then Gaussian filtering is performed to remove the noise interference in the images, making the edges of the vehicles clearer and facilitating subsequent vehicle detection and recognition. Then, a deep learning-based object detection algorithm (such as the YOLOv5 model) is used to analyze the preprocessed images. The algorithm is trained in advance on a large number of traffic scene images containing different types of vehicles, and can accurately identify the vehicles in the images, and locate and classify them (distinguish between normally waiting vehicles and abnormally occupying road vehicles). For each detected vehicle, the corresponding counter is incremented by 1, so as to count the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally.

[0028] To improve the accuracy of counting, in other embodiments, multi-frame image data can be used for fusion analysis to avoid missed detection or misdetection caused by factors such as vehicle occlusion.

[0029] In another embodiment, the imaging device includes a first imaging device and a second imaging device, and the shooting perspectives of the first imaging device and the second imaging device are different. The step S100: obtaining the number of target vehicles waiting to turn on the first passing road according to the captured image of the imaging device includes: Obtain the captured images of the first imaging device and the second imaging device respectively; Use image fusion technology to fuse the captured images from different perspectives, and analyze the fused image through a pre-trained target detection model to obtain the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally.

[0030] Specifically, the first camera device and the second camera device are installed near the turning position of the first traffic road towards the connecting road, but there are differences in their shooting angles. For example, the first camera device is installed at a higher position and shoots from a top-down perspective, which can cover a larger waiting area and obtain the overall distribution of vehicles; the second camera device is installed at a slightly lower position and shoots from an oblique side perspective, focusing on capturing the detailed features of vehicles, such as license plate information and the specific postures of vehicles, which helps to more accurately identify abnormal occupancy situations. The two camera devices collect high-definition images simultaneously in a synchronous manner (for example, by connecting to the same clock signal source to ensure that the acquisition time of each frame of image is basically the same), at a predetermined frame rate (such as 25 frames per second), and transmit the collected image data to the back-end image processing server in real time through wired (such as Ethernet) or wireless (such as a Wi-Fi 6 standard wireless network) transmission methods. On the image processing server, first, preprocessing operations are performed on the images from the first camera device and the second camera device respectively. This includes grayscale processing of the images, converting the color images into grayscale images to reduce the data volume and highlight the contour features of the vehicles, facilitating subsequent processing; then Gaussian filtering is performed to remove noise interference in the images, making the edges of the vehicles clearer and smoother and avoiding false detections caused by noise. Then, histogram equalization operation is performed on the images to enhance the contrast of the images, making the difference between the vehicles and the background more obvious and further improving the accuracy of vehicle detection. Since the shooting perspectives of the first camera device and the second camera device are different, the images collected have differences in spatial position and scale, so image registration operation is required. A method based on feature point matching is adopted, such as using the SIFT (Scale-Invariant Feature Transform) or SURF (Speeded-Up Robust Features) algorithm, to extract representative feature points from the two images and match them through feature descriptors. Then, according to the matched feature points, using the affine transformation or perspective transformation model, the transformation relationship between the images is calculated, and the image of the second camera device is mapped into the image coordinate system of the first camera device to achieve image registration. Based on the registered images, image fusion operation is performed. A fusion method based on pixel weighted average can be adopted. According to factors such as the clarity and contrast of the images, different weights are assigned to the pixels at different positions, and the pixel values of the two images are weighted and summed to obtain the fused image. Such a fused image can integrate the advantages of the two camera devices and provide more comprehensive and accurate vehicle information. Then, the fused image is analyzed using a pre-trained object detection model. This object detection model can be constructed based on a deep learning framework (such as TensorFlow or PyTorch), adopt a convolutional neural network (CNN) structure, and be trained on a large image dataset containing vehicles in different traffic scenarios, and can accurately identify the vehicles in the image and distinguish between normal waiting vehicles and abnormal occupancy vehicles.During the detection process, the model outputs a bounding box for each vehicle target in the image, identifying the position of the vehicle and giving the class probability of the vehicle (normal vehicle or abnormal lane occupation vehicle). By counting these bounding boxes, the number of target vehicles waiting normally and the number of target vehicles occupying the lane abnormally are calculated.

[0031] Step S200, when the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the lane abnormally is greater than or equal to a second preset value, adjust the green light duration ratio of the traffic signal lamp and trigger a vehicle-road coordination instruction; In an embodiment of the present invention, when it is detected that the number of normal waiting target vehicles waiting to turn on the first traffic lane is greater than or equal to a first preset value, and the number of target vehicles occupying the lane abnormally is greater than or equal to a second preset value, it is necessary to adjust the green light duration ratio of the traffic signal lamp and trigger a vehicle-road coordination instruction. The specific steps are as follows: S210, determine the increase value of the green light duration ratio of the traffic signal lamp according to the number of target vehicles waiting normally and the number of target vehicles occupying the lane abnormally; In the embodiment of the present application, first, based on the number of normal waiting target vehicles obtained by the camera device, combined with the preset average vehicle length, the queuing length of the normal waiting vehicles is obtained through multiplication operation. This average vehicle length value can be determined based on the long-term statistical analysis of the vehicles passing through this section of the road. Similarly, according to the number of target vehicles occupying the lane abnormally and the average vehicle length, the queuing length of the vehicles occupying the lane abnormally is calculated. Then, the queuing length of the normal waiting vehicles and the queuing length of the vehicles occupying the lane abnormally are input into a pre-trained green light ratio increment prediction model to obtain the increase value of the green light duration ratio.

[0032] The embodiment of the present application adopts a pre-trained green light ratio increment prediction model, which is optimized and trained according to the actual situation and historical data of traffic flow to achieve accurate prediction of the increase value of the green light duration ratio. The model satisfies the expression: ΔP = (W 1 *L 1 +W 2 *L 2 )*P 0 , where, W 2 >W 1 (for example, W 2 is 0.6, W 1 is 0.4, indicating that the influence of the queuing length of the vehicles occupying the lane abnormally on the increase value of the green light duration ratio is more significant), ΔP is the increase value of the green light duration ratio, L 1 is the queuing length of the normal waiting vehicles, L 2 is the queuing length of the vehicles occupying the lane abnormally, W 1 is the influence weight of the queuing length of the normal waiting vehicles on the green light ratio increment, W 2is the influence weight of the queue length of abnormal lane - occupying vehicles on the increment of the green - light ratio, P 0 is the benchmark value of the increment of the green - light ratio. This benchmark value is determined based on a large amount of actual traffic data and simulation experiments and is used to calibrate the calculation of the increment value of the green - light duration ratio.

[0033] S220. Adjust the original green - light duration ratio according to the increment value of the green - light duration ratio of the traffic signal to extend the passing duration of the vehicles turning from the first passing road to the connected road.

[0034] In the embodiment of the present application, first, the original green - light duration ratio is obtained. The traffic signal control system pre - stores the original green - light duration ratio data for each passing direction, and these data are comprehensively set according to factors such as traffic flow characteristics and road passing capacity in different time periods. Then, the increment value of the green - light duration ratio calculated by the green - light ratio increment prediction model in step S210 is combined with the original green - light duration ratio in the direction of the first passing road turning to the connected road, so as to extend the passing duration of the vehicles in this direction. Specifically, by adding the increment value of the green - light duration ratio to the original green - light duration ratio, the adjusted green - light duration ratio is obtained, and then the signal timing of the traffic signal is adjusted accordingly to extend the passing duration of the vehicles turning from the first passing road to the connected road, so as to preferentially ensure the smooth passing of the vehicles turning from the first passing road to the connected road. At the same time, after the traffic signal control system completes the adjustment of the green - light duration ratio, since the number of vehicles merging into the second passing road increases (especially when the connected road is short), it is necessary to trigger a vehicle - road coordination instruction to transmit the signal state change information to other relevant devices in the vehicle - road coordination system, such as passing traffic flow monitors and roadside information interaction devices, so that the entire system works together to jointly respond to traffic flow changes and improve road passing efficiency and safety.

[0035] Step S300. Obtain the historical average traffic flow of the target passing direction of the second passing road according to the vehicle - road coordination instruction through the passing traffic flow monitor; After the system triggers the vehicle - road coordination instruction, it indicates that it is necessary to conduct overall coordination of other roads to jointly respond to traffic flow changes and improve road passing efficiency and safety.

[0036] In the embodiment of the present application, after the system triggers the vehicle - road coordination instruction, the passing traffic flow monitor will obtain the historical average traffic flow of the target passing direction of the second passing road, providing accurate data support for subsequent vehicle - road coordination. Specifically, the historical average traffic flow can be the average value of the traffic flow at the same time of each day (such as 10 minutes before and after the regulation time) within the previous month corresponding to the moment when the traffic signal starts regulation. For example, if the traffic signal starts regulation at 10 o'clock, the historical average traffic flow is the average value of the traffic flow from 9:50 to 10:10 every day in the previous month.

[0037] Step S400: Calibrate the historical average traffic flow based on the traffic flow data of the second passing road in the target passing direction on the same day to obtain the current target traffic flow of the second passing road in the target passing direction; In an embodiment, the step S400: Calibrate the historical average traffic flow based on the traffic flow data of the second passing road in the target passing direction on the same day to obtain the current target traffic flow of the second passing road in the target passing direction, includes: Obtain the average traffic flow data of the second passing road in the target passing direction on the same day; Determine that the average traffic flow of the second passing road in the target passing direction on the same day is greater than or equal to the historical average traffic flow, and perform a positive calibration on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction; Determine that the average traffic flow of the second passing road in the target passing direction on the same day is less than the historical average traffic flow, and perform a negative calibration on the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction.

[0038] Specifically, first obtain the average traffic flow data of the second passing road in the target passing direction through a passing traffic monitor. This data is a comprehensive statistical value of the traffic flow on this road section on the same day, reflecting the actual traffic flow situation during this period on the same day. Then compare the obtained average traffic flow data on the same day with the historical average traffic flow data: If it is determined that the average traffic flow of the second passing road in the target passing direction on the same day is greater than or equal to the historical average traffic flow, it indicates that the traffic flow on this road section on the same day has increased or remained the same compared to the historical situation. At this time, a positive calibration needs to be performed on the historical average traffic flow to more accurately reflect the current traffic flow situation, and obtain the current target traffic flow of the second passing road in the target passing direction. If it is determined that the average traffic flow of the second passing road in the target passing direction on the same day is less than the historical average traffic flow, it indicates that the traffic flow on this road section on the same day has decreased compared to the historical situation. At this time, a negative calibration needs to be performed on the historical average traffic flow to obtain the current target traffic flow that conforms to the actual situation.

[0039] In other embodiments, to improve the accuracy of calibrating the historical average traffic flow, the positive calibration of the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction includes: Calculate the difference between the average traffic flow data on the same day and the historical average traffic flow data to obtain a positive calibration increment. Add the product of the positive calibration increment and the first preset calibration coefficient to the historical average traffic flow to obtain the current target traffic flow; The negative calibration of the historical average traffic flow to obtain the current target traffic flow of the second passing road in the target passing direction includes: Calculate the difference between the historical average traffic flow data and the average traffic flow data on the same day to obtain a negative calibration decrement; Subtract the product of the negative calibration decrement and the second preset calibration coefficient from the historical average traffic flow to obtain the current target traffic flow, where the first preset calibration coefficient is not equal to the second preset calibration coefficient.

[0040] Specifically, the specific steps of the forward correction are as follows: First, calculate the difference between the average traffic flow data of the current day and the historical average traffic flow data. This difference is the forward correction increment. Let the average traffic flow data of the current day be Davg and the historical average traffic flow data be Havg. Then the forward correction increment △1 = Davg - Havg. Then add the product of the forward correction increment and the first preset correction coefficient K1 to the historical average traffic flow to obtain the current target traffic flow C+. That is, C+ = Hag + Δ1 x K1. The first preset correction coefficient K1 is a value preset in advance according to the actual traffic conditions and experience, and is used to adjust the correction amplitude to ensure that the corrected traffic flow is more in line with the actual traffic conditions. Similarly, the specific steps of the negative correction are as follows: First, calculate the difference between the historical average traffic flow data and the average traffic flow data of the current day. This difference is the negative correction decrement. That is, the negative correction decrement △2 = Havg - Davg.

[0041] Then subtract the product of the negative correction decrement and the second preset correction coefficient K2 from the historical average traffic flow to obtain the current target traffic flow C-. That is, C- = Havg - △2 x K2. Among them, the second preset correction coefficient K2 is also a value preset in advance according to the actual traffic conditions and experience. Generally speaking, the first preset correction coefficient K1 and the second preset correction coefficient K2 are affected by different factors. Therefore, the forward correction and the negative correction require different adjustment amplitudes to more accurately reflect the changes in traffic flow under different conditions. Therefore, K1 ≠ K2 (for example, K1 = 0.8, K2 = 0.7). In this way, when the traffic flow of the current day is less than the historical average traffic flow, a more accurate current target traffic flow can also be obtained.

[0042] Through the above correction scheme, the historical average traffic flow can be reasonably corrected according to the actual traffic flow data of the current day in the target traffic direction of the second traffic lane, so as to obtain a current target traffic flow that is more in line with the actual situation, providing accurate data support for subsequent traffic decisions and information prompts.

[0043] Step S500: When the current target traffic flow in the target traffic direction of the second traffic lane is greater than the preset traffic flow, the second roadside information interaction device repeatedly sends the second prompt message to the passing vehicles on the second traffic lane at the first preset time interval. When the current target traffic flow in the target traffic direction of the second traffic lane is less than or equal to the preset traffic flow, the second roadside information interaction device repeatedly sends the second prompt message to the passing vehicles on the second traffic lane at the second preset time interval. Among them, the first preset time interval is less than the second preset time interval, and the second prompt message is used to prompt the downstream vehicles on the second traffic lane to pay attention to the relatively large confluence traffic flow ahead.

[0044] In an embodiment of the present application, after obtaining the current target traffic flow of the corrected second passing road in the target passing direction, it is necessary to compare it with the preset traffic flow, and based on the comparison result, accurately control the time interval for the second roadside information interaction device to send the second prompt message to the passing vehicles on the second passing road.

[0045] If the current target traffic flow is greater than the preset traffic flow, this indicates that the second passing road in the target passing direction is about to face a relatively large confluence traffic flow pressure. To enable the downstream vehicle drivers to timely and fully understand the road conditions ahead and ensure driving safety and traffic smoothness, the second roadside information interaction device will repeatedly send the second prompt message to the passing vehicles on the second passing road at relatively short first preset time intervals. This prompt message is designed to clearly remind the downstream vehicles to pay attention to the relatively large confluence traffic flow ahead, prompting the drivers to make preparations in advance, such as adjusting the vehicle speed and maintaining a safe vehicle distance.

[0046] On the contrary, if the current target traffic flow is less than or equal to the preset traffic flow, it means that the confluence traffic flow pressure on this section of the road is relatively small. In this case, to avoid interfering with the drivers due to excessive prompts while ensuring the effective transmission of information, the second roadside information interaction device will repeatedly send the second prompt message to the passing vehicles at relatively long second preset time intervals. By dynamically adjusting the prompt frequency according to the traffic flow in this way, the accuracy and rationality of information prompts are achieved, which not only ensures road traffic safety but also improves the driving experience of the drivers. It should be noted that the first preset time interval is less than the second preset time interval to meet the different requirements for the information prompt frequency in different traffic flow situations.

[0047] In other embodiments, after completing the regulation of the green light duration ratio of the traffic signal and triggering the vehicle-road coordination instruction, the system will further use the first roadside information interaction device to send targeted first prompt messages to the passing vehicles on the first passing road to remind the downstream vehicles on this road to pay attention to the relatively large turning traffic flow ahead.

[0048] Specifically, first, based on the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally, a specific algorithm is used to determine the expected congestion duration. This algorithm comprehensively considers various factors such as the average vehicle speed, road capacity, and traffic signal cycle, and can more accurately estimate the congestion duration that vehicles may face due to turning traffic flow. Subsequently, the expected congestion duration is compared with the preset congestion duration. If the expected congestion duration is greater than or equal to the preset congestion duration, it indicates that the congestion situation is relatively serious. At this time, the first roadside information interaction device will send a first prompt message for detouring to the passing vehicles on the first passing road, guiding the vehicles to choose other routes to relieve the traffic pressure on the current road. On the contrary, if the expected congestion duration is less than the preset congestion duration, it indicates that the congestion degree is relatively light, and the vehicle can still pass within an acceptable time. In this case, the first roadside information interaction device will send a first prompt message for decelerating to the passing vehicles on the first passing road, reminding the driver to drive carefully, maintain a safe vehicle distance, and pass through the section in an orderly manner, avoiding traffic accidents caused by excessive vehicle speed, and ensuring the safety and smoothness of road traffic.

[0049] Based on this, the vehicle-road coordination system and vehicle passing management method provided by the embodiments of the present application accurately monitor the number of turning vehicles on the first passing road and reasonably control the traffic signal lights. That is, when the data of the vehicles to be turned increases and there are abnormal road occupancies, the green light passing duration of the turning indication traffic signal light is controlled to be extended, so as to effectively reduce the waiting time of the turning vehicles on this road, improve their passing efficiency, and at the same time avoid the aggravation of traffic jams caused by abnormally occupying vehicles. And when the passing duration of the turning traffic signal light is extended, for the second passing road, the interval for sending prompt messages is reasonably arranged according to the traffic flow situation in the target passing direction, so that the downstream vehicles can make preparations in advance, ensuring the smooth integration of the merging traffic flow and the main road traffic flow, reducing the problem of the overall road network passing capacity decline caused by unsmooth merging, and realizing the optimal distribution of the traffic flow of the target passing road network.

[0050] The vehicle-road coordination system provided by the embodiments of the present application further includes a memory 110 and a processor 120. Among them, the memory 110 is used to store computer-readable instructions, and the processor 120 is used to call the computer-readable instructions to execute the vehicle passing management method as described above.

[0051] Among them, the processor 120 is used to provide computing and control capabilities to control the vehicle-road coordination system to perform corresponding tasks. For example, it controls the vehicle-road coordination system to execute the vehicle passing management method in any of the above method embodiments. The method includes: obtaining the number of target vehicles waiting to turn on the first passing road according to the captured image of the imaging device, where the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; when the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the road abnormally is greater than or equal to a second preset value, adjusting the green light duration ratio of the traffic signal lamp and triggering a vehicle-road coordination instruction; obtaining the historical average traffic flow of the target passing direction of the second passing road through the passing traffic flow monitor according to the vehicle-road coordination instruction; correcting the historical average traffic flow according to the current traffic flow data of the target passing direction of the second passing road to obtain the current target traffic flow of the target passing direction of the second passing road; when the current target traffic flow of the target passing direction of the second passing road is greater than the preset traffic flow, the second roadside information interaction device repeatedly sends a second prompt message to the passing vehicles on the second passing road at a first preset time interval; when the current target traffic flow of the target passing direction of the second passing road is less than or equal to the preset traffic flow, the second roadside information interaction device repeatedly sends a second prompt message to the passing vehicles on the second passing road at a second preset time interval, where the first preset time interval is less than the second preset time interval, and the second prompt message is used to prompt the downstream vehicles on the second passing road to pay attention to the relatively large confluence traffic flow ahead.

[0052] The processor 120 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), a hardware chip, or any combination thereof; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The above PLD may be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL), or any combination thereof.

[0053] The memory 110 serves as a non-transitory computer-readable storage medium and can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the vehicle passing management method in the embodiments of the present application. By running the non-transitory software programs, instructions, and modules stored in the memory 110, the processor 120 can implement the vehicle passing management method in any of the above method embodiments.

[0054] Specifically, the memory 110 may include volatile memory (VM), such as random access memory (RAM); the memory 110 may also include non-volatile memory (NVM), such as read-only memory (ROM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), or other non-transitory solid-state storage devices; the memory 110 may further include a combination of the above types of memories.

[0055] In summary, the vehicle-road coordination system of the present application adopts the technical solution of any one of the above vehicle passing management method embodiments. Therefore, it at least has the beneficial effects brought by the technical solutions of the above embodiments, which will not be elaborated here one by one.

[0056] The embodiments of the present application also provide a computer-readable storage medium, such as a memory including program codes, and the above program codes can be executed by a processor to complete the vehicle passing management method in the above embodiments. For example, the computer-readable storage medium may be a read-only memory (ROM), random access memory (RAM), compact disc read-only memory (CDROM), magnetic tape, floppy disk, and optical data storage device, etc.

[0057] The embodiments of the present application also provide a computer program product, which includes one or more program codes, and the program codes are stored in a computer-readable storage medium. The processor of the vehicle-road coordination system reads the program codes from the computer-readable storage medium, and the processor executes the program codes to complete the steps of the vehicle passing management method provided in the above embodiments.

[0058] Those of ordinary skill in the art can understand that all or part of the steps to implement the above embodiments can be completed by hardware, or can be completed by hardware related to program code. The program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, or the like.

[0059] It should be noted that the device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0060] Through the description of the above embodiments, those of ordinary skill in the art can clearly understand that each embodiment can be implemented by means of software plus a general hardware platform, and of course, it can also be implemented by hardware. Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the above method embodiments. Among them, the storage medium can be a magnetic disk, an optical disc, a read-only memory (ROM), or a random access memory (RAM), etc.

[0061] The above are only the preferred embodiments of the present invention, and do not limit the patent scope of the present invention accordingly. Any equivalent structural transformation made by using the description and drawings of the present invention under the inventive concept of the present invention, or direct / indirect application in other related technical fields, is included in the patent protection scope of the present invention.

Claims

1. A vehicle-road coordination system, characterized in that: The vehicle-road coordination system is arranged in a target passable road network, the target passable road network includes a first passable road, a second passable road, and a connecting road connecting the first passable road and the second passable road, and the vehicle-road coordination system includes: A camera device, the camera device is arranged at a turning position of the first passage road toward the connecting road, and is used to detect the number of target vehicles waiting to turn on the first passage road, wherein the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; a traffic flow monitor, the traffic flow monitor being arranged on the second traffic road and used for monitoring the traffic flow in a target traffic direction of the second traffic road, the target traffic direction being the same as the direction in which the connecting road merges into the second traffic road; a traffic light, the traffic light being used to indicate the passage of vehicles turning from the first traffic road to the connecting road; a first roadside information interaction device, which is disposed on the first passable road and is separated from the camera device by a first preset distance, and is used to send a first prompt message to vehicles passing through the first passable road when the number of target vehicles waiting to turn on the first passable road is greater than or equal to a preset number, wherein the first prompt message is used to prompt downstream vehicles on the first passable road to pay attention to the large turning traffic ahead; A second roadside information interaction device is provided on the second passage and is a second preset distance away from the traffic flow monitor, and is used for sending a second prompt message to vehicles traveling in the target travel direction of the second passage when the traffic light prolongs the travel time of vehicles turning from the first passage to the connecting road. The second prompt message is used to remind downstream vehicles on the second passage to pay attention to the large merging traffic ahead.

2. The vehicle-road coordination system according to claim 1, characterized in that: The traffic flow monitor includes a ring coil detector arranged on the ground of the second traffic road and / or a laser sensor arranged on the side of the second traffic road; The first roadside information interaction device and the second roadside information interaction device include a short-range wireless communication device arranged on the roadside, and the short-range wireless communication device is used to send prompt information to the vehicle-mounted unit.

3. A vehicle traffic management method, characterized in that: Applied to the vehicle-road coordination system according to any one of claims 1-2, the method comprising: Acquire the number of target vehicles waiting to turn on the first traffic road according to the images captured by the camera device, wherein the number of target vehicles includes the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; When the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the road abnormally is greater than or equal to a second preset value, adjusting the green light duration ratio of the traffic light and triggering a vehicle-road coordination instruction; According to the vehicle-road coordination instruction, the historical average vehicle flow in the target travel direction of the second travel road is obtained through the travel flow monitor; Correcting the historical average traffic flow according to the current day traffic flow data of the target traffic direction of the second traffic road to obtain the current target traffic flow in the target traffic direction of the second traffic road; When the current target traffic flow in the target traffic direction of the second passable road is greater than the preset traffic flow, the second roadside information interaction device repeatedly sends the second prompt message to the vehicles passing through the second passable road at a first preset time interval; when the current target traffic flow in the target traffic direction of the second passable road is less than or equal to the preset traffic flow, the second roadside information interaction device repeatedly sends the second prompt message to the vehicles passing through the second passable road at a second preset time interval, wherein the first preset time interval is less than the second preset time interval, and the second prompt message is used to remind downstream vehicles of the second passable road to pay attention to the large merging traffic flow ahead.

4. The vehicle traffic management method according to claim 3, characterized in that: When the number of target vehicles waiting normally is greater than or equal to a first preset value and the number of target vehicles occupying the road abnormally is greater than or equal to a second preset value, adjusting the green light duration ratio of the traffic light and triggering the vehicle-road coordination instruction includes: Determine the increase in the green light duration ratio of the traffic light according to the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; The original green light duration ratio is adjusted according to the increased value of the green light duration ratio of the traffic light to extend the travel time of vehicles turning from the first traffic road to the connecting road.

5. The vehicle traffic management method according to claim 4, characterized in that: The determining of the increase in the green light duration ratio of the traffic light according to the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally includes: Obtaining the queue length of normally waiting vehicles according to the target number of normally waiting vehicles and a preset average vehicle length; The queue length of vehicles occupying the road abnormally is obtained according to the number of target vehicles occupying the road abnormally and the average vehicle length; Input the queue length of the normal waiting vehicles and the queue length of the abnormally occupying vehicles into the pre-trained green light proportion increment estimation model to obtain the green light duration proportion increase value; The green light proportion increment estimation model satisfies the following expression: ΔP=(W1*L1+W2*L2)*P0, wherein W2>W1, ΔP is the increase in the green light duration ratio, L1 is the queue length of normal waiting vehicles, L2 is the queue length of abnormal vehicles occupying the road, W1 is the influence weight of the queue length of normal waiting vehicles on the increment of green light proportion, W2 is the influence weight of the queue length of abnormal vehicles occupying the road on the increment of green light proportion, and P0 is the baseline value of the green light proportion increment.

6. The vehicle traffic management method according to claim 3, characterized in that: After adjusting the green light duration ratio of the traffic light and triggering the vehicle-road coordination instruction, the method further includes: A first prompt message is sent to vehicles passing through the first road through a first roadside information interaction device, and the first prompt message is used to remind downstream vehicles of the first road to pay attention to the heavy turning traffic ahead.

7. The vehicle traffic management method according to claim 6, characterized in that: The sending of the first prompt information to the vehicles passing through the first pass road by the first roadside information interaction device includes: Determine the estimated congestion duration according to the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally; When the predicted congestion duration is greater than or equal to the preset congestion duration, a first prompt message for detour is sent to vehicles passing through the first road through the first roadside information interaction device.

8. The vehicle traffic management method according to claim 3, characterized in that: The historical average traffic flow is the average value of the historical traffic flow in a preset time period corresponding to the traffic light start-up control moment, and the current target traffic flow in the target traffic direction of the second traffic road is obtained by correcting the historical average traffic flow according to the traffic flow data of the day on the target traffic direction of the second traffic road, including: Obtain the average traffic flow data of the day in the target traffic direction of the second traffic road; Determine that the average traffic flow of the second passable road in the target traffic direction on the day is greater than or equal to the historical average traffic flow, and perform a positive correction on the historical average traffic flow to obtain the current target traffic flow of the second passable road in the target traffic direction; It is determined that the average traffic flow of the day in the target traffic direction of the second passable road is less than the historical average traffic flow, and a negative correction is performed on the historical average traffic flow to obtain the current target traffic flow in the target traffic direction of the second passable road.

9. The vehicle traffic management method according to claim 7, characterized in that: The forward correction of the historical average traffic flow to obtain the current target traffic flow in the target traffic direction of the second traffic road includes: Calculate the difference between the average traffic flow data of the day and the historical average traffic flow data to obtain the positive correction increment; The historical average vehicle flow is added to the product of the positive correction increment and the first preset correction coefficient to obtain the current target vehicle flow; The negative correction of the historical average traffic flow to obtain the current target traffic flow in the target traffic direction of the second traffic road includes: Calculate the difference between the historical average traffic flow data and the average traffic flow data of the day to obtain the negative correction reduction; The current target vehicle flow rate is obtained by subtracting the product of the negative correction decrement and the second preset correction coefficient from the historical average vehicle flow rate, wherein the first preset correction coefficient is not equal to the second preset correction coefficient.

10. The vehicle traffic management method according to claim 3, characterized in that: The camera device includes a first camera device and a second camera device, the first camera device and the second camera device have different shooting angles, and obtaining the number of target vehicles waiting to turn on the first pass road according to the images captured by the camera devices includes: Respectively acquiring images captured by the first camera device and the second camera device; Image fusion technology is used to fuse images taken from different perspectives. The fused images are analyzed by a pre-trained target detection model to obtain the number of target vehicles waiting normally and the number of target vehicles occupying the road abnormally.

Images