Intelligent traffic control system based on vehicle-road cooperation

Abstract

This invention discloses a vehicle-road cooperative intelligent traffic control system, including a data acquisition module, a monitoring module, a hazard prediction module, and an output module. The monitoring module is used to monitor drivers of motor vehicles and non-motor vehicles approaching intersections. The hazard prediction module is used to obtain the probability of dangerous accidents between motor vehicles and non-motor vehicles through the monitoring module. This invention uses the motor vehicle monitoring module to determine whether a motor vehicle can pass through the intersection normally. When a motor vehicle rushes through the intersection before the red light, the non-motor vehicle monitoring module analyzes non-motor vehicles that may cross the intersection early, and obtains whether the non-motor vehicle driver observes vehicles on both sides of the road when crossing early. This minimizes the possibility of collisions between motor vehicles and non-motor vehicles, improves the safety of traffic intersections, and strengthens traffic safety management. This invention has the characteristics of comprehensive risk monitoring and strong behavior prediction capabilities.

Description

Technical Field

[0001] This invention relates to the field of traffic safety management technology, specifically to a smart traffic control system based on vehicle-road cooperation. Background Technology

[0002] As a new direction for the development of future transportation systems, the new type of information-based intelligent transportation integrates computer technology, data communication technology, wireless sensing technology, and automatic control technology into various nodes of the transportation system, forming a comprehensive system integrating perception, communication, decision-making, and control. This effectively promotes the transformation of traffic management methods and the improvement of governance capabilities, further providing diverse services for traffic participants. The new type of information-based intelligent transportation is committed to the application of technologies such as the Internet of Things, cloud computing, artificial intelligence, and big data in the transportation industry.

[0003] In existing technologies, traffic safety early warning systems clearly reconstruct road conditions through various detection technologies. After analyzing road hazard coefficients, intelligent roadside devices within the system issue warning signals to remind traffic managers and participants to promptly grasp various information affecting traffic safety. However, when the straight-ahead traffic light enters its countdown, subsequent vehicles approaching the intersection may not slow down or even accelerate if the driver subjectively judges that they can cross the intersection within the remaining countdown time. Non-motorized vehicle drivers, on the other hand, generally lack road safety knowledge and have weak road safety awareness. Many non-motorized vehicle drivers cross the road before the green light turns on, even without observing the traffic conditions on both sides of the road. This can lead to collisions between cars speeding across the stop line and non-motorized vehicles traveling laterally, resulting in serious traffic accidents. Furthermore, the lack of information sharing and complementary sensing methods among intersection sensing devices results in overly simplistic detection methods for intersection environmental safety, failing to organically integrate with human actions. Therefore, it is essential to design a vehicle-road cooperative intelligent traffic control system with comprehensive risk monitoring and strong behavioral prediction capabilities. Summary of the Invention

[0004] The purpose of this invention is to provide a smart transportation control system based on vehicle-road cooperation to solve the problems mentioned in the background art.

[0005] To address the aforementioned technical problems, this invention provides the following technical solution: a vehicle-road cooperative intelligent traffic control system, comprising a data acquisition module, a monitoring module, a hazard prediction module, and an output module. The data acquisition module is used to collect relevant information about traffic intersections; the monitoring module is used to monitor drivers of motor vehicles and non-motor vehicles approaching the intersection; the hazard prediction module is used to obtain the probability of dangerous accidents between motor vehicles and non-motor vehicles through the monitoring module; and the output module is used to provide alerts to motor vehicles predicted by the hazard prediction module to have a collision risk.

[0006] According to the above technical solution, the data acquisition module includes an intersection data acquisition module and a historical traffic condition recording module. The intersection data acquisition module is used to acquire relevant data on traffic lights and warning lines at intersections. The historical traffic condition recording module is used to filter intersections with high traffic volume and high accident risk.

[0007] According to the above technical solution, the monitoring module includes a motor vehicle monitoring module, a non-motor vehicle monitoring module, a camera module, and a timing unit. The motor vehicle monitoring module is used to monitor the time period during which motor vehicles are about to arrive at the intersection; the non-motor vehicle monitoring module is used to determine whether non-motor vehicle drivers are likely to cross the road prematurely while waiting for the traffic light, and to determine whether non-motor vehicle drivers can observe the intersection information; the camera module is used to photograph vehicles at the intersection and obtain image information of vehicles and drivers; the timing unit is used to keep track of time during monitoring.

[0008] According to the above technical solution, the motor vehicle monitoring module further includes a vehicle speed detection submodule, a distance detection submodule, and a driving analysis submodule. The vehicle speed detection submodule is used to detect the real-time driving speed of the vehicle behind the intersection; the distance detection submodule is used to detect the real-time distance between the vehicle and the intersection; the driving analysis submodule is used to determine whether the vehicle can pass through the intersection before the traffic light indicator ends. The non-motor vehicle monitoring module includes an advance crossing prediction submodule and an observation level analysis submodule. The advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; the observation level analysis submodule is used to determine whether the non-motor vehicle driver has fully observed the road conditions on both sides of the road.

[0009] According to the above technical solution, the output module includes a safety warning module and a prompting module. The safety warning module is used to transmit alarm information to the warning prompting device on the nearby traffic police officer; the prompting module is used to prompt the driver of the motor vehicle to slow down in time through the vehicle's onboard warning device.

[0010] According to the above technical solution, the operation method of the intelligent transportation control system mainly includes the following steps:

[0011] Step S1: When a motor vehicle passes the speed monitoring line set up below the intersection, the motor vehicle monitoring module is activated;

[0012] Step S2: The driving analysis submodule determines whether the vehicle can pass through the intersection before the traffic light ends. If it is determined that the motor vehicle can pass through the intersection normally but there is a risk of collision, the non-motor vehicle monitoring module monitors the non-motor vehicle driver.

[0013] Step S3: The non-motorized vehicle monitoring module determines whether the non-motorized vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule. If so, the observation level analysis submodule is activated to detect the non-motorized vehicle driver's attention.

[0014] Step S4: The observation frequency analysis submodule analyzes the observation frequency of non-motorized vehicle drivers during their waiting time;

[0015] Step S5: The observation level analysis submodule uses the camera module to determine whether the non-motorized vehicle driver has fully observed the road conditions on both sides of the road;

[0016] Step S6: If the hazard prediction module detects that a non-motorized vehicle driver may cross the road in advance without fully observing the conditions of the motor vehicle lanes on both sides, it determines that there is a risk of collision. The safety warning module transmits the alarm information to the warning device on the nearby traffic police officer and controls the vehicle's onboard warning device through the warning module to prompt the motor vehicle driver to slow down in time.

[0017] According to the above technical solution, step S2 further includes:

[0018] Step S21: When the car passes the first speed monitoring line set 50 meters behind the intersection, the speed detection submodule obtains the vehicle's speed as V1 (km / h). If V1 > 40, the output module immediately prompts the driver to slow down; if V1 < 40, the prediction submodule obtains the time F seconds it takes for the traffic light to turn from green to red, and the time it takes for the car to reach the intersection at this speed. Time to reach the opposite intersection Where L is the distance from the monitoring line to the stop line at the intersection, H is the distance from the stop line at the intersection to the opposite intersection, and T1 and T2 are in seconds;

[0019] Step S22: If T1≥F, the speed detection submodule acquires the vehicle's speed V2 when the car passes the second speed monitoring line set 30 meters behind the intersection. If V2≥ηV1, the output module immediately prompts the driver to slow down, where η is the minimum threshold parameter for normal vehicle deceleration.

[0020] 0.9 < η < 1;

[0021] Step S23: If The vehicle monitoring module determines that the vehicle can drive through the intersection normally.

[0022] Step S24: If The motor vehicle monitoring module determines that a motor vehicle can pass through the intersection normally but there is a risk of collision. The hazard prediction module is activated and obtains the monitoring results of non-motor vehicle drivers on both sides of the road from the non-motor vehicle monitoring module. If there is a risk of collision, the output module will immediately prompt the motor vehicle driver to slow down.

[0023] According to the above technical solution, step S3 further includes:

[0024] Step S31: The camera module captures images of non-motorized vehicle drivers waiting at traffic lights using a camera positioned directly above the non-motorized vehicle parking area. It extracts image features of the helmet from the database and focuses on the non-motorized vehicle driver based on the helmet features. The advance travel prediction submodule establishes a Cartesian coordinate system with the center of the driver's helmet as the origin, drawing a straight line through the center of the driver's helmet and parallel to the bottom edge of the image as the X-axis, and another straight line through the center of the driver's helmet and parallel to the left edge of the image as the Y-axis. The unit side length of the coordinate system is 1, and the coordinates of the center of the driver's helmet are (0, 0).

[0025] Step S32: The camera module obtains the position (X, Y) of the center point of the helmet forehead using a Cartesian coordinate system with the center of the driver's helmet as a reference;

[0026] Step S33: The camera module acquires the real-time position (X1, Y1), (X2, Y2)...(X...) of the center point of the helmet at different times (X1, Y1), (X2, Y2)...(X...) of the non-motorized vehicle driver's helmet at n different time points during the current waiting time at the traffic light using the timing unit. n Y n ), where the interval between n time points is t, and is expressed by the formula Calculate the offset in radians between the center point of the helmet forehead and the positive Y-axis at each time point, and arrange the absolute values ​​of the radian angles in ascending order: |θ1|, |θ2|, ..., |θ n | Calculate the total radian offset of the driver's head M = θ1 + θ2 + ... + θ n , if M<λ(|θ1|+|θ2|......|θ n |)and The advance crossing prediction submodule determines whether a non-motorized vehicle driver is likely to cross the road ahead of time. λ is the error index of a non-motorized vehicle driver who observes oncoming traffic in one direction and then slightly turns their head in another direction without actually observing the traffic, where 0.8 < λ < 1.

[0027] According to the above technical solution, in step S4, the standard deviation of the radian offset between the center point of the helmet forehead and the positive half-axis of the Y-axis is... like The observation level analysis submodule determines that the non-motorized vehicle driver's head is deflected and cannot directly observe the vehicles. The camera module then detects the driver's eye observation to further determine whether the driver has adequately observed oncoming vehicles. The observation level analysis submodule determines whether the non-motorized vehicle driver has fully observed the oncoming vehicles.

[0028] According to the above technical solution, step S5 further includes:

[0029] Step S51: The camera module continuously captures images of non-motorized vehicle drivers waiting at traffic lights using a camera set in the green belt opposite the non-motorized vehicle parking area. Based on the driver's eye characteristics, it focuses on the driver's left eye and acquires a magnified image of the eye. After acquiring the magnified image of the eye, the non-motorized vehicle monitoring module uses the information from the first image to mark the current position of the left eyeball, inner corner, and outer corner. It establishes a Cartesian coordinate system with the center point of the left eyeball as the origin, the line segment from the inner corner to the outer corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis. The unit side length of the coordinate system is 1, and the current position of the center point of the left eyeball is (0, 0).

[0030] Step S52: The camera module continuously acquires the position of the center point of the left eyeball convergence and compares it with the information in the first image in real time to obtain the position (x, y) of the center point of the eyeball convergence.

[0031] Step S53: The observation degree analysis submodule obtains the offset radian value of the helmet forehead center point position from the positive Y-axis. Real-time focus position of the left eye of the non-motorized vehicle driver (x) 11 y 11 ), (x 21 y 21 )……(x i1 y i1 ), and through the formula Calculate the offset distance γ between the eye position and the left eye position as indicated by the information in the first image for each time period. 11 γ 21 ...γ i1 Calculate the total eye offset angle of the driver. like If the non-motorized vehicle driver observes the vehicles on the right side of the road with their eyes, then the deceleration information will be transmitted to the driver of the motorized vehicle traveling to the left through the output module.

[0032] Step S54: The observation degree analysis submodule obtains the real-time focus position (x) of the non-motorized vehicle driver's left eye when the offset angle between the center point of the helmet forehead and the positive half-axis of the Y-axis is higher than 30°. 21 y 21 ), (x22 y 22 )……(x i2 y i2 ), where i1+i2<n, and calculate the offset distance γ between the eye position and the left eye position marked by the first image information for each time period. 21 γ 22 ...γ i2 Calculate the total eye offset angle of the driver. like If the system determines that the non-motorized vehicle driver has observed the situation on the left side of the road, it will output the speed reduction information to the driver of the motorized vehicle traveling to the right.

[0033] Compared with the prior art, the beneficial effects achieved by the present invention are as follows: The present invention uses a motor vehicle monitoring module to determine whether a motor vehicle can pass through an intersection normally. When a motor vehicle rushes through an intersection before the red light, the non-motor vehicle monitoring module analyzes non-motor vehicles that may cross the intersection in advance, and obtains information on whether the non-motor vehicle driver observes vehicles on both sides of the road when crossing in advance. The invention also uses a hazard prediction module to predict the possibility of traffic accidents. By making real-time predictions of the scenarios with the highest probability of accidents, the possibility of collisions between motor vehicles and non-motor vehicles is reduced to the greatest extent, thereby improving the safety of traffic intersections and strengthening traffic safety management. Attached Figure Description

[0034] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0035] Figure 1 This is a schematic diagram of the system module composition of the present invention. Detailed Implementation

[0036] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0037] Please see Figure 1 The present invention provides a technical solution: a smart traffic control system based on vehicle-road cooperation, comprising:

[0038] The system comprises a data acquisition module, a monitoring module, a hazard prediction module, and an output module. The data acquisition module collects relevant information about traffic intersections; the monitoring module monitors drivers of motor vehicles and non-motor vehicles approaching the intersection; the hazard prediction module uses the monitoring module to determine the likelihood of dangerous accidents between motor vehicles and non-motor vehicles; and the output module provides alerts for motor vehicles predicted by the hazard prediction module to be at risk of collision.

[0039] This invention uses a motor vehicle monitoring module to determine whether a motor vehicle can pass through an intersection normally. When a motor vehicle rushes through an intersection before the red light, a non-motor vehicle monitoring module analyzes non-motor vehicles that may cross the intersection early, and obtains information on whether the non-motor vehicle driver observes vehicles on both sides of the road when crossing early. The invention also uses a hazard prediction module to predict the probability of a traffic accident. By making real-time predictions of the scenarios with the highest probability of accidents, the invention minimizes the possibility of collisions between motor vehicles and non-motor vehicles, improves the safety of traffic intersections, and strengthens traffic safety management.

[0040] The data acquisition module includes an intersection data acquisition module and a historical traffic condition collection module. The intersection data acquisition module is used to obtain relevant data on traffic lights and warning lines at intersections; the historical traffic condition collection module is used to filter intersections with high traffic volume and high accident risk.

[0041] The monitoring module includes a motor vehicle monitoring module, a non-motor vehicle monitoring module, a camera module, and a timing unit. The motor vehicle monitoring module is used to monitor the time period when motor vehicles are about to arrive at the intersection; the non-motor vehicle monitoring module is used to detect whether non-motor vehicle drivers are likely to cross the road in advance while waiting for the traffic light, and to determine whether non-motor vehicle drivers can observe the intersection information; the camera module is used to photograph vehicles at the intersection and obtain image information of vehicles and drivers; the timing unit is used to keep track of time during monitoring.

[0042] The motor vehicle monitoring module further includes a speed detection submodule, a distance detection submodule, and a driving analysis submodule. The speed detection submodule is used to detect the real-time speed of the vehicle behind the intersection; the distance detection submodule is used to detect the real-time distance between the vehicle and the intersection; and the driving analysis submodule is used to determine whether the vehicle can pass through the intersection before the traffic light turns off. The non-motor vehicle monitoring module includes an advance crossing prediction submodule and an observation level analysis submodule. The advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; and the observation level analysis submodule is used to determine whether the non-motor vehicle driver has fully observed the road conditions on both sides of the road.

[0043] The output module includes a safety warning module and a prompt module. The safety warning module is used to transmit alarm information to the warning prompt device on the nearby traffic police officer; the prompt module is used to prompt the driver of the motor vehicle to slow down in time through the vehicle's onboard warning device.

[0044] In a preferred embodiment, the operation method of the intelligent transportation control system mainly includes the following steps:

[0045] Step S1: When a motor vehicle passes the speed monitoring line set up below the intersection, the motor vehicle monitoring module is activated;

[0046] Step S2: The driving analysis submodule determines whether the vehicle can pass through the intersection before the traffic light ends. If it is determined that the motor vehicle can pass through the intersection normally but there is a risk of collision, the non-motor vehicle monitoring module monitors the non-motor vehicle driver.

[0047] Step S3: The non-motorized vehicle monitoring module determines whether the non-motorized vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule. If so, the observation level analysis submodule is activated to detect the non-motorized vehicle driver's attention.

[0048] Step S4: The observation frequency analysis submodule analyzes the observation frequency of non-motorized vehicle drivers during their waiting time;

[0049] Step S5: The observation level analysis submodule uses the camera module to determine whether the non-motorized vehicle driver has fully observed the road conditions on both sides of the road;

[0050] Step S6: If the hazard prediction module detects that a non-motorized vehicle driver may cross the road in advance without fully observing the conditions of the motor vehicle lanes on both sides, it determines that there is a risk of collision. The safety warning module transmits the alarm information to the warning device on the nearby traffic police officer and controls the vehicle's onboard warning device through the warning module to prompt the motor vehicle driver to slow down in time.

[0051] In this embodiment, step S2 further includes:

[0052] Step S21: When the car passes the first speed monitoring line set 50 meters behind the intersection, the speed detection submodule obtains the vehicle's speed as V1 (km / h). If V1 > 40, the output module immediately prompts the driver to slow down; if V1 < 40, the prediction submodule obtains the time F seconds it takes for the traffic light to turn from green to red, and the time it takes for the car to reach the intersection at this speed. Time to reach the opposite intersection Where L is the distance from the monitoring line to the stop line at the intersection, H is the distance from the stop line at the intersection to the opposite intersection, and T1 and T2 are in seconds;

[0053] Step S22: If T1≥F, the speed detection submodule acquires the vehicle's speed V2 when the car passes the second speed monitoring line set 30 meters behind the intersection. If V2≥ηV1, the output module immediately prompts the driver to slow down, where η is the minimum threshold parameter for normal vehicle deceleration.

[0054] 0.9 < η < 1;

[0055] Step S23: If The vehicle monitoring module determines that the vehicle can drive through the intersection normally.

[0056] Step S24: If The motor vehicle monitoring module determines that a motor vehicle can pass through the intersection normally but there is a risk of collision. The hazard prediction module is activated and obtains the monitoring results of non-motor vehicle drivers on both sides of the road from the non-motor vehicle monitoring module. If there is a risk of collision, the output module will immediately prompt the motor vehicle driver to slow down.

[0057] The driving analysis submodule classifies motor vehicle speeds, provides alerts to drivers of vehicles that cannot pass through intersections at normal speeds, and filters out motor vehicles that may pose a collision risk at the current speed.

[0058] In this embodiment, step S3 further includes:

[0059] Step S31: The camera module captures images of non-motorized vehicle drivers waiting at traffic lights using a camera positioned directly above the non-motorized vehicle parking area. It extracts image features of the helmet from the database and focuses on the non-motorized vehicle driver based on the helmet features. The advance travel prediction submodule establishes a Cartesian coordinate system with the center of the driver's helmet as the origin, drawing a straight line through the center of the driver's helmet and parallel to the bottom edge of the image as the X-axis, and another straight line through the center of the driver's helmet and parallel to the left edge of the image as the Y-axis. The unit side length of the coordinate system is 1, and the coordinates of the center of the driver's helmet are (0, 0).

[0060] Step S32: The camera module obtains the position (X, Y) of the center point of the helmet forehead using a Cartesian coordinate system with the center of the driver's helmet as a reference;

[0061] Step S33: The camera module acquires the real-time position (X1, Y1), (X2, Y2)...(X...) of the center point of the helmet at different times (X1, Y1), (X2, Y2)...(X...) of the non-motorized vehicle driver's helmet at n different time points during the current waiting time at the traffic light using the timing unit. n Y n ), where the interval between n time points is t, and is expressed by the formula Calculate the offset in radians between the center point of the helmet forehead and the positive Y-axis at each time point, and arrange the absolute values ​​of the radian angles in ascending order: |θ1|, |θ2|, ..., |θ n | Calculate the total radian offset of the driver's head M = θ1 + θ2 + ... + θ n , if M<λ(|θ1|+|θ2|......|θ n |)and The advance crossing prediction submodule determines whether a non-motorized vehicle driver has made left and right observations within a certain time and is likely to cross the road ahead of time. Here, λ is the error index of the non-motorized vehicle driver who observes oncoming traffic in one direction and then slightly turns their head to the other direction without actually observing the other direction. 0.8 < λ < 1.

[0062] This represents the maximum deviation arc of the non-motorized vehicle driver within a given time period, excluding minor head movements by the driver who did not actually intend to cross the road; |θ1|+|θ2|......|θ n | refers to the radian value of the non-motorized vehicle driver's head deviation to one side within a time period of (n-1)t. Since the radian value of θ can be positive or negative, the fact that the total radian value of the non-motorized vehicle driver's head deviation to one side within a time period of (n-1)t is less than the radian value of deviation to one side indicates that the non-motorized vehicle driver is turning his head left and right to observe.

[0063] To determine whether non-motorized vehicle drivers significantly turn their heads left and right to observe road conditions while waiting at traffic lights.

[0064] In step S4 of this embodiment, the standard deviation of the offset arc of the helmet forehead center point position from the positive Y-axis is... like The observation level analysis submodule determines that the non-motorized vehicle driver's head is deflected and cannot directly observe the vehicles. The camera module then detects the driver's eye observation to further determine whether the driver has adequately observed oncoming vehicles. The observation level analysis submodule determines whether the non-motorized vehicle driver has fully observed the oncoming vehicles.

[0065] The standard deviation of the driver's offset arc can be calculated to obtain the time the driver spends observing the vehicle's movement on both sides of the road within (n-1)t, thus eliminating the possibility that the driver only spends a short time observing the intersection.

[0066] The observation frequency analysis submodule calculates the standard deviation of the head offset arc of non-motorized vehicle drivers to obtain the frequency of non-motorized vehicle drivers looking left and right at the road conditions while waiting for traffic lights.

[0067] In this embodiment, step S5 further includes:

[0068] Step S51: The camera module continuously captures images of non-motorized vehicle drivers waiting at traffic lights using a camera set in the green belt opposite the non-motorized vehicle parking area. Based on the driver's eye characteristics, it focuses on the driver's left eye and acquires a magnified image of the eye. After acquiring the magnified image of the eye, the non-motorized vehicle monitoring module uses the information from the first image to mark the current position of the left eyeball, inner corner, and outer corner. It establishes a Cartesian coordinate system with the center point of the left eyeball as the origin, the line segment from the inner corner to the outer corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis. The unit side length of the coordinate system is 1, and the current position of the center point of the left eyeball is (0, 0).

[0069] Step S52: The camera module continuously acquires the position of the center point of the left eyeball convergence and compares it with the information in the first image in real time to obtain the position (x, y) of the center point of the eyeball convergence.

[0070] Step S53: The observation degree analysis submodule obtains the offset radian value of the helmet forehead center point position from the positive Y-axis. Real-time focus position of the left eye of the non-motorized vehicle driver (x) 11 y 11 ), (x 21 y 21 )……(x i1 y i1 ), and through the formula Calculate the offset distance γ between the eye position and the left eye position as indicated by the information in the first image for each time period. 11 γ 21 ...γ i1 Calculate the total eye offset angle of the driver. like If the non-motorized vehicle driver observes the vehicles on the right side of the road with their eyes, then the deceleration information will be transmitted to the driver of the motorized vehicle traveling to the left through the output module.

[0071] Step S54: The observation degree analysis submodule obtains the real-time focus position (x) of the non-motorized vehicle driver's left eye when the offset angle between the center point of the helmet forehead and the positive half-axis of the Y-axis is higher than 30°. 21 y 21 ), (x 22 y 22 )……(x i2 y i2 ), where i1+i2<n, and calculate the offset distance γ between the eye position and the left eye position marked by the first image information for each time period. 21 γ 22 ...γ i2 Calculate the total eye offset angle of the driver. like If the system determines that the non-motorized vehicle driver has observed the situation on the left side of the road, it will output the speed reduction information to the driver of the motorized vehicle traveling to the right.

[0072] The observation degree analysis submodule obtains the eye deviation when the driver's face deviates within 30 degrees, accurately determining whether the non-motorized vehicle driver has fully observed the driving situation of the left and right motor vehicles through the eye deviation after a slight head deviation.

[0073] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Finally, it should be noted that the above descriptions are merely preferred embodiments of the present invention and are not intended to limit the invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A smart transportation control system based on vehicle-road cooperation, characterized in that: The system includes a data acquisition module, a monitoring module, a hazard prediction module, and an output module. The data acquisition module collects relevant information about traffic intersections. The monitoring module monitors drivers of motor vehicles and non-motor vehicles approaching the intersection. The hazard prediction module uses the monitoring module to determine the likelihood of a dangerous accident between a motor vehicle and a non-motor vehicle. The output module provides alerts to motor vehicles predicted by the hazard prediction module to have a collision risk. The data acquisition module includes an intersection data acquisition module and a historical traffic condition recording module. The intersection data acquisition module is used to acquire relevant data on traffic lights and warning lines at intersections. The historical traffic condition recording module is used to filter intersections with high traffic volume and high accident risk. The monitoring module includes a motor vehicle monitoring module, a non-motor vehicle monitoring module, a camera module, and a timing unit. The motor vehicle monitoring module monitors the time period during which motor vehicles are about to arrive at the intersection. The non-motor vehicle monitoring module monitors whether non-motor vehicle drivers are likely to cross the road prematurely while waiting for the traffic light and determines whether they can observe the intersection information. The camera module captures images of vehicles at the intersection, obtaining visual information about the vehicles and drivers. The timing unit keeps track of the time during monitoring. The motor vehicle monitoring module further includes a vehicle speed detection submodule, a distance detection submodule, and a driving analysis submodule. The vehicle speed detection submodule is used to detect the real-time speed of the vehicle behind the intersection; the distance detection submodule is used to detect the real-time distance between the vehicle and the intersection; and the driving analysis submodule is used to determine whether the vehicle can pass through the intersection before the traffic light indicator ends. The non-motorized vehicle monitoring module includes an advance crossing prediction submodule and an observation level analysis submodule. The advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; and the observation level analysis submodule is used to determine whether the non-motorized vehicle driver has fully observed the road conditions on both sides of the road. The output module includes a safety warning module and a prompting module. The safety warning module is used to transmit alarm information to the warning prompting device on the nearby traffic police officer. The prompting module is used to prompt the driver of the motor vehicle to slow down in time through the vehicle's onboard warning device. The operation method of the intelligent transportation control system mainly includes the following steps: Step S1: When a motor vehicle passes the speed monitoring line set up below the intersection, the motor vehicle monitoring module is activated; Step S2: The driving analysis submodule determines whether the vehicle can pass through the intersection before the traffic light ends. If it is determined that the motor vehicle can pass through the intersection normally but there is a risk of collision, the non-motor vehicle monitoring module monitors the non-motor vehicle driver. Step S3: The non-motorized vehicle monitoring module determines whether the non-motorized vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule. If so, the observation level analysis submodule is activated to detect the non-motorized vehicle driver's attention. Step S4: The observation frequency analysis submodule analyzes the observation frequency of non-motorized vehicle drivers during their waiting time; Step S5: The observation level analysis submodule uses the camera module to determine whether the non-motorized vehicle driver has fully observed the road conditions on both sides of the road; Step S6: If the hazard prediction module detects that a non-motorized vehicle driver may cross the road in advance without fully observing the conditions of the motor vehicle lanes on both sides, it determines that there is a risk of collision. The safety warning module transmits the alarm information to the warning device on the nearby traffic police officer and controls the vehicle's onboard warning device through the warning module to prompt the motor vehicle driver to slow down in time. Step S5 further includes: Step S51: The camera module continuously captures images of non-motorized vehicle drivers waiting at traffic lights using a camera set in the green belt opposite the non-motorized vehicle parking area. Based on the driver's eye characteristics, it focuses on the driver's left eye and acquires a magnified image of the eye. After acquiring the magnified image of the eye, the non-motorized vehicle monitoring module uses the information from the first image to mark the current position of the left eyeball, inner corner, and outer corner. It establishes a Cartesian coordinate system with the center point of the left eyeball as the origin, the line segment from the inner corner to the outer corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis. The unit side length of the coordinate system is 1, and the current position of the center point of the left eyeball is (0, 0). Step S52: The camera module continuously acquires the position of the center point of the left eyeball convergence and compares it with the information in the first image in real time to obtain the position (x, y) of the center point of the eyeball convergence. Step S53: The observation degree analysis submodule obtains the offset radian value of the helmet forehead center point position from the positive Y-axis. Real-time focus position of the left eye of the non-motorized vehicle driver (x) 11 y 11 ), (x 21 y 21 )……(x i1 y i1 ), and through the formula Calculate the offset distance γ between the eye position and the left eye position as indicated by the information in the first image for each time period. 11 γ 21 ...γ i1 Calculate the total eye offset angle of the driver. like If the non-motorized vehicle driver observes the vehicles on the right side of the road with their eyes, then the deceleration information will be transmitted to the driver of the motorized vehicle traveling to the left through the output module. Step S54: The observation degree analysis submodule obtains the real-time focus position (x) of the non-motorized vehicle driver's left eye when the offset angle between the center point of the helmet forehead and the positive half-axis of the Y-axis is higher than 30°. 21 y 21 ), (x 22 y 22 )……(x i2 y i2 ), where i1+i2<n, and calculate the offset distance γ between the eye position and the left eye position marked by the first image information for each time period. 21 γ 22 ...γ i2 Calculate the total eye offset angle of the driver. like If the system determines that the non-motorized vehicle driver has observed the situation on the left side of the road, it will output the speed reduction information to the driver of the motorized vehicle traveling to the right.

Images