Intelligent traffic control system based on vehicle-road cooperation

Abstract

The invention discloses an intelligent traffic control system based on vehicle-road cooperation, which comprises a data acquisition module, a monitoring module, a danger prediction module and an output module, and is characterized in that the monitoring module is used for monitoring drivers of motor vehicles and non-motor vehicles driving to an intersection; the motor vehicle monitoring module is used for judging whether the motor vehicle can normally pass the intersection at the intersection or not, and the danger prediction module is used for obtaining the possibility of dangerous accidents of the motor vehicle and the non-motor vehicle through the monitoring module. The non-motor vehicle monitoring module analyzes non-motor vehicles which may pass in advance and obtains whether a non-motor vehicle driver observes vehicles on two sides of a road when passing in advance, so that the possibility of collision between the motor vehicles and the non-motor vehicles is reduced to the greatest extent, the safety of a traffic crossroad is improved, traffic safety management is enhanced, and the traffic safety is improved. The method has the characteristics of comprehensive risk monitoring range and high behavior prediction capability.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic safety management, and specifically to an intelligent traffic control system based on vehicle-road collaboration. Background Art

[0002] As a new direction for the development of future transportation systems, new information-based smart transportation integrates computer technology, data communication technology, wireless sensor technology, automatic control technology, etc. into each node of the transportation system to form a system that integrates comprehensive perception, communication, decision-making and control, effectively promoting the transformation of transportation management methods and the improvement of governance capabilities, and further providing diversified services for transportation participants. New information-based smart 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 the existing technology, the traffic safety warning system uses a variety of detection technologies to clearly restore the road conditions. After analyzing the road danger coefficient, the intelligent road-side equipment in the system sends out warning signals to remind the majority of traffic managers and traffic participants to grasp various information that affect traffic safety in a timely manner. However, when the straight-through traffic light enters the countdown, the subsequent motor vehicle drives to the intersection. If the motor vehicle driver subjectively judges that it can pass the intersection within the remaining countdown time, it will not slow down or even speed up; and non-motor vehicle drivers generally lack road safety knowledge and have weak road safety awareness. Many non-motor vehicle drivers will cross the road in advance before the green light comes on, and even do not observe the driving conditions of vehicles on both sides of the road. This leads to the possibility of collision between cars that quickly pass the stop line and non-motor vehicles that travel sideways, resulting in serious traffic accidents. The information between the intersection sensing devices is not interoperable, and the sensing methods are not complementary. The detection method for the safety of the intersection environment is too single and cannot be organically combined with human actions. Therefore, it is necessary to design an intelligent traffic control system based on vehicle-road collaboration with a comprehensive risk monitoring range and strong behavior prediction capabilities. Summary of the invention

[0004] The purpose of the present invention is to provide an intelligent traffic control system based on vehicle-road collaboration to solve the problems raised in the above-mentioned background technology.

[0005] In order to solve the above technical problems, the present invention provides the following technical solutions: an intelligent traffic control system based on vehicle-road collaboration, comprising a data acquisition module, a monitoring module, a danger prediction module and an output module, wherein the data acquisition module is used to collect relevant information of traffic intersections; the monitoring module is used to monitor the drivers of motor vehicles and non-motor vehicles traveling to the intersection; the danger prediction module is used to obtain the possibility of dangerous accidents between motor vehicles and non-motor vehicles through the monitoring module; and the output module is used to remind motor vehicles predicted by the danger prediction module to have collision risks.

[0006] According to the above technical solution, the data acquisition module includes an intersection data acquisition module and a historical road condition collection module. The intersection data acquisition module is used to obtain relevant data of traffic lights and warning lines at intersections; the historical road condition collection module is used to screen intersections with large traffic volume and high accident risk rate.

[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 when a motor vehicle is about to drive to an intersection; the non-motor vehicle monitoring module is used to determine whether a non-motor vehicle driver has the possibility of crossing the road in advance while waiting for a traffic light, and to determine whether the non-motor vehicle driver can observe the intersection information; the camera module is used to photograph vehicles at the intersection and obtain image information of the vehicle and the driver; the timing unit is used to time during monitoring.

[0008] According to the above technical solution, 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 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 ends. The non-motor vehicle monitoring module includes an advance crossing prediction submodule and an observation degree analysis submodule. The advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; the observation degree 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 prompt module. The safety warning module is used to transmit alarm information to the warning indicator on the nearby traffic police; the prompt module is used to prompt the motor vehicle driver to slow down in time through the motor vehicle's on-board warning device.

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

[0011] Step S1: When a motor vehicle passes through a speed monitoring line set below the rear of 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 turns off. 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-motor vehicle monitoring module determines whether the non-motor vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule, and if so, activates the observation degree analysis submodule to detect the attention of the non-motor vehicle driver;

[0014] Step S4: the observation degree analysis submodule analyzes the observation frequency of the non-motor vehicle driver during the waiting time;

[0015] Step S5: the observation degree analysis submodule determines whether the non-motor vehicle driver fully observes the road conditions on both sides of the road through the camera module;

[0016] Step S6: If the danger prediction module detects that a non-motor vehicle driver may cross the road in advance and does not fully observe the conditions of the motor vehicle lanes on both sides, it is judged that there is a risk of collision. The safety warning module transmits the alarm information to the warning indicator on the nearby traffic police and controls the on-board warning indicator of the motor vehicle through the prompt 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 through the first speed monitoring line set 50 meters behind the intersection, the speed detection submodule obtains the vehicle's speed V1 (km / h). If V1>40, the output module immediately prompts the owner to slow down; if V1<40, the prediction submodule obtains the time it takes for the traffic light to turn from green to red, F seconds, 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 of the intersection, H is the distance from the stop line of the intersection to the opposite intersection, and the units of T1 and T2 are seconds;

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

[0020] 0.9<η<1;

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

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

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

[0024] Step S31: The camera module captures the image of the non-motor vehicle driver waiting for the traffic light through a camera set just above the non-motor vehicle parking area, extracts the image features of the helmet through the database, and focuses on the non-motor vehicle driver according to the helmet features of the driver; the advance crossing prediction submodule takes the center of the driver's helmet as the origin, makes a straight line passing through the center of the driver's helmet and parallel to the bottom edge of the picture as the X-axis, makes a straight line passing through the center of the driver's helmet and parallel to the left edge of the picture as the Y-axis, and establishes a plane rectangular coordinate system, the unit side length of the coordinate system is 1, and the coordinate of the center of the driver's helmet is (0, 0);

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

[0026] Step S33: The camera module obtains the real-time positions (X1, Y1), (X2, Y2) ... (X1, Y1) of the center points of the helmet foreheads of different drivers at n time points during the current non-motor vehicle driver's waiting time for the traffic light through the timing unit. n , Y n ), where the intervals between the n time points are all t, and the formula Calculate the offset radian value between the center point of the helmet forehead and the positive half axis of the Y axis at each time point and arrange the absolute values ​​of the radian angle values ​​from small to large |θ1|, |θ2|...|θ n |, calculate the total deflection arc value 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 the non-motor vehicle driver has the possibility of crossing the road in advance, where λ is the error index of the non-motor vehicle driver slightly turning his head to the other direction without observing the oncoming vehicle in one direction, and 0.8<λ<1.

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

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

[0029] Step S51: The camera module continuously captures the image of the non-motor vehicle driver waiting for the traffic light through a camera arranged in the green belt on the opposite side of the non-motor vehicle parking area, focuses on the driver's left eye according to the driver's eye features, and obtains an enlarged eye image; after the non-motor vehicle monitoring module obtains the enlarged eye image, the positions of the current left eyeball, inner eye corner and outer eye corner are calibrated with the first image information, and a plane rectangular coordinate system is established with the left eyeball convergence center point as the origin, the line segment from the inner eye corner to the outer eye corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis, the coordinate system unit side length is 1, and the current left eyeball convergence center point position is (0, 0);

[0030] Step S52: the camera module continuously obtains the position of the left eye's eyeball convergence center point, and obtains the eyeball convergence center point position (x, y) after real-time scaling and comparison with the first picture information;

[0031] Step S53: The observation degree analysis submodule obtains the offset arc value between the center point of the helmet forehead and the positive half axis of the Y axis greater than The real-time position of the left eye of the non-motor vehicle driver (x 11 ,y 11 )、(x 21 ,y 21 )……(x i1 ,y i1 ), and by the formula Calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 11 , γ 21 …γ i1 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the vehicle situation on the right side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the left through the output module;

[0032] Step S54: The observation degree analysis submodule obtains the real-time position (x) of the left eye of the non-motor vehicle driver when the offset angle between the center point of the helmet forehead and the positive semi-axis of the Y axis is greater than 30°. 21 ,y 21 )、(x22 ,y 22 )……(x i2 ,y i2 ), where i1+i2<n, and respectively calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 21 , γ 22 …γ i2 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the situation on the left side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the right through the output module.

[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. In the case where a motor vehicle rushes through an intersection before a red light, a non-motor vehicle monitoring module analyzes non-motor vehicles that may pass through in advance, obtains whether the driver of the non-motor vehicle observes the vehicles on both sides of the road when passing in advance, and predicts the possibility of a traffic accident through a hazard prediction module. By making real-time predictions of the scenarios with the greatest possibility of accidents, the possibility of collision between motor vehicles and non-motor vehicles is reduced to the greatest extent, the safety of traffic intersections is improved, and traffic safety management is strengthened. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0035] Figure 1 It is a schematic diagram of the system module composition of the present invention. DETAILED DESCRIPTION

[0036] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

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

[0038] The data acquisition module, monitoring module, danger prediction module and output module are used to collect relevant information of traffic intersections; the monitoring module is used to monitor the drivers of motor vehicles and non-motor vehicles driving to the intersection; the danger prediction module is used to obtain the possibility of dangerous accidents between motor vehicles and non-motor vehicles through the monitoring module; and the output module is used to remind motor vehicles predicted by the danger prediction module to have collision risks.

[0039] The present invention determines whether a motor vehicle can pass through an intersection normally through a motor vehicle monitoring module. In the case that a motor vehicle rushes through an intersection before a red light, a non-motor vehicle monitoring module analyzes non-motor vehicles that may pass through in advance, and obtains whether the driver of the non-motor vehicle observes the vehicles on both sides of the road when passing in advance, and predicts the possibility of a traffic accident through a hazard prediction module. By making real-time predictions of the scenarios with the highest probability of an accident, the possibility of a collision between a motor vehicle and a non-motor vehicle is reduced to the greatest extent, the safety of traffic intersections is improved, and traffic safety management is strengthened.

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

[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 a motor vehicle is about to drive to an intersection; the non-motor vehicle monitoring module is used to determine whether a non-motor vehicle driver has the possibility of crossing the road in advance while waiting for a traffic light, and to judge whether the non-motor vehicle driver can observe the intersection information; the camera module is used to take pictures of vehicles at the intersection and obtain image information of the vehicle and the driver; the timing unit is used to 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 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 ends. The non-motor vehicle monitoring module includes an advance crossing prediction submodule and an observation degree analysis submodule. The advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; the observation degree 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 the alarm information to the warning indicator on the nearby traffic police; the prompt module is used to prompt the motor vehicle driver to slow down in time through the motor vehicle's on-board warning device.

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

[0045] Step S1: When a motor vehicle passes through a speed monitoring line set below the rear of 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 turns off. 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-motor vehicle monitoring module determines whether the non-motor vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule, and if so, activates the observation degree analysis submodule to detect the attention of the non-motor vehicle driver;

[0048] Step S4: the observation degree analysis submodule analyzes the observation frequency of the non-motor vehicle driver during the waiting time;

[0049] Step S5: the observation degree analysis submodule determines whether the non-motor vehicle driver fully observes the road conditions on both sides of the road through the camera module;

[0050] Step S6: If the danger prediction module detects that a non-motor vehicle driver may cross the road in advance and does not fully observe the conditions of the motor vehicle lanes on both sides, it is judged that there is a risk of collision. The safety warning module transmits the alarm information to the warning indicator on the nearby traffic police and controls the on-board warning indicator of the motor vehicle through the prompt 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 through the first speed monitoring line set 50 meters behind the intersection, the speed detection submodule obtains the vehicle's speed V1 (km / h). If V1>40, the output module immediately prompts the owner to slow down; if V1<40, the prediction submodule obtains the time it takes for the traffic light to turn from green to red, F seconds, 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 of the intersection, H is the distance from the stop line of the intersection to the opposite intersection, and the units of T1 and T2 are seconds;

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

[0054] 0.9<η<1;

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

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

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

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

[0059] Step S31: The camera module captures the image of the non-motor vehicle driver waiting for the traffic light through a camera set just above the non-motor vehicle parking area, extracts the image features of the helmet through the database, and focuses on the non-motor vehicle driver according to the helmet features of the driver; the advance crossing prediction submodule takes the center of the driver's helmet as the origin, makes a straight line passing through the center of the driver's helmet and parallel to the bottom edge of the picture as the X-axis, makes a straight line passing through the center of the driver's helmet and parallel to the left edge of the picture as the Y-axis, and establishes a plane rectangular coordinate system, the unit side length of the coordinate system is 1, and the coordinate of the center of the driver's helmet is (0, 0);

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

[0061] Step S33: The camera module obtains the real-time positions (X1, Y1), (X2, Y2) ... (X1, Y1) of the center points of the helmet foreheads of different drivers at n time points during the current non-motor vehicle driver's waiting time for the traffic light through the timing unit. n , Y n ), where the intervals between the n time points are all t, and the formula Calculate the offset radian value between the center point of the helmet forehead and the positive half axis of the Y axis at each time point and arrange the absolute values ​​of the radian angle values ​​from small to large |θ1|, |θ2|...|θ n |, calculate the total deflection arc value 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 the non-motor vehicle driver has observed the left and right sides within the time and has the possibility of crossing the road in advance, where λ is the error index of the non-motor vehicle driver observing the oncoming vehicle in one direction and turning his head slightly to the other direction without observing, 0.8<λ<1.

[0062] is the maximum deflection arc of the non-motor vehicle driver in the time period, excluding the non-motor vehicle driver's small head swing, and actually has no intention of crossing the road; |θ1|+|θ2|......|θ n | refers to the deflection arc value of the non-motor vehicle driver's head in the (n-1)t time period. Since the arc value of θ can be positive or negative, the total deflection arc value of the non-motor vehicle driver's head in the (n-1)t time period is less than the deflection arc value in the direction of one side, which indicates that the non-motor vehicle driver has turned his head left and right to observe.

[0063] Obtain information on whether non-motor vehicle drivers turn their heads significantly to the left and right to observe road conditions while waiting for traffic lights.

[0064] In step S4 of this embodiment, the standard deviation of the offset arc between the center point of the helmet forehead and the positive half axis of the Y axis is like The observation degree analysis submodule determines that the non-motor vehicle driver's head is offset and cannot directly observe the vehicle. The camera module detects the non-motor vehicle driver's eye observation to further determine whether the non-motor vehicle driver fully observes the passing vehicles. If The observation degree analysis submodule determines whether the non-motor vehicle driver fully observes the oncoming vehicles.

[0065] The calculation of the standard deviation of the driver's offset arc can obtain the time the driver spends observing the driving conditions of vehicles on both sides of the road within (n-1)t, eliminating the possibility that the driver only spends a short time observing the intersection.

[0066] The observation degree analysis submodule calculates the standard deviation of the non-motor vehicle driver's head deviation arc to obtain the frequency of the non-motor vehicle driver observing the road conditions left and right while waiting for the traffic light.

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

[0068] Step S51: The camera module continuously captures the image of the non-motor vehicle driver waiting for the traffic light through a camera arranged in the green belt on the opposite side of the non-motor vehicle parking area, focuses on the driver's left eye according to the driver's eye features, and obtains an enlarged eye image; after the non-motor vehicle monitoring module obtains the enlarged eye image, the positions of the current left eyeball, inner eye corner and outer eye corner are calibrated with the first image information, and a plane rectangular coordinate system is established with the left eyeball convergence center point as the origin, the line segment from the inner eye corner to the outer eye corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis, the coordinate system unit side length is 1, and the current left eyeball convergence center point position is (0, 0);

[0069] Step S52: the camera module continuously obtains the position of the left eye's eyeball convergence center point, and obtains the eyeball convergence center point position (x, y) after real-time scaling and comparison with the first picture information;

[0070] Step S53: The observation degree analysis submodule obtains the offset arc value between the center point of the helmet forehead and the positive half axis of the Y axis greater than The real-time position of the left eye of the non-motor vehicle driver (x 11 ,y 11 )、(x 21 ,y 21 )……(x i1 ,y i1 ), and by the formula Calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 11 , γ 21 …γ i1 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the vehicle situation on the right side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the left through the output module;

[0071] Step S54: The observation degree analysis submodule obtains the real-time position (x) of the left eye of the non-motor vehicle driver when the offset angle between the center point of the helmet forehead and the positive semi-axis of the Y axis is greater than 30°. 21 ,y 21 )、(x 22 ,y 22 )……(x i2 ,y i2 ), where i1+i2<n, and respectively calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 21 , γ 22 …γ i2 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the situation on the left side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the right through the output module.

[0072] The observation degree analysis submodule obtains the eye deviation when the driver's face deviation is within 30 degrees, and accurately obtains whether the non-motor vehicle driver fully observes the driving conditions of the left and right motor vehicles through the eye deviation after a small deviation of the head.

[0073] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions recorded in the aforementioned embodiments, or to replace some of the technical features therein by equivalents. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent traffic control system based on vehicle-road collaboration, characterized by: It includes a data acquisition module, a monitoring module, a danger prediction module and an output module. The data acquisition module is used to collect relevant information of the traffic intersection; the monitoring module is used to monitor the drivers of motor vehicles and non-motor vehicles traveling to the intersection; the danger prediction module is used to obtain the possibility of dangerous accidents between motor vehicles and non-motor vehicles through the monitoring module; the output module is used to remind the motor vehicles predicted by the danger prediction module to have collision risks; The data acquisition module includes an intersection data acquisition module and a historical road condition collection module. The intersection data acquisition module is used to obtain relevant data of traffic lights and warning lines at intersections; the historical road condition collection module is used to screen intersections with large traffic volume and high accident risk rate; 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 the motor vehicle is about to drive to the intersection; the non-motor vehicle monitoring module is used to determine whether the non-motor vehicle driver has the possibility of crossing the road in advance while waiting for the traffic light, and whether the non-motor vehicle driver can observe the intersection information; the camera module is used to take pictures of the vehicles at the intersection and obtain the image information of the vehicles and the drivers; the timing unit is used to count the time during monitoring; The motor vehicle monitoring module further includes a speed detection submodule, a distance detection submodule and a driving analysis submodule, wherein the 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 indicator light ends; the non-motor vehicle monitoring module includes an advance crossing prediction submodule and an observation degree analysis submodule, wherein the advance crossing prediction submodule is used to determine whether it is possible to cross the road in advance; the observation degree analysis submodule is used to determine whether the non-motor vehicle driver has fully observed the road conditions on both sides of the road; The output module includes a safety warning module and a prompt module. The safety warning module is used to transmit the alarm information to the warning prompter on the nearby traffic police; the prompt module is used to prompt the motor vehicle driver to slow down in time through the vehicle-mounted warning device of the motor vehicle; The operation method of the intelligent traffic control system mainly includes the following steps: Step S1: When a motor vehicle passes through a speed monitoring line set below the rear of 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 turns off. 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-motor vehicle monitoring module determines whether the non-motor vehicle driver is likely to cross the road in advance through the advance crossing prediction submodule, and if so, activates the observation degree analysis submodule to detect the attention of the non-motor vehicle driver; Step S4: the observation degree analysis submodule analyzes the observation frequency of the non-motor vehicle driver during the waiting time; Step S5: the observation degree analysis submodule determines whether the non-motor vehicle driver fully observes the road conditions on both sides of the road through the camera module; Step S6: If the danger prediction module detects that a non-motor vehicle driver may cross the road in advance and does not fully observe the conditions of the motor vehicle lanes on both sides, it is determined that there is a risk of collision, and the safety warning module transmits the alarm information to the warning reminder on the nearby traffic police, and the reminder module controls the vehicle-mounted warning reminder of the motor vehicle to prompt the motor vehicle driver to slow down in time; The step S5 further comprises: Step S51: The camera module continuously captures the image of the non-motor vehicle driver waiting for the traffic light through a camera arranged in the green belt on the opposite side of the non-motor vehicle parking area, focuses on the driver's left eye according to the driver's eye features, and obtains an enlarged eye image; after the non-motor vehicle monitoring module obtains the enlarged eye image, the positions of the current left eyeball, inner eye corner and outer eye corner are calibrated with the first image information, and a plane rectangular coordinate system is established with the left eyeball convergence center point as the origin, the line segment from the inner eye corner to the outer eye corner as the x-axis, and the x-axis rotated 90 degrees as the y-axis, the coordinate system unit side length is 1, and the current left eyeball convergence center point position is (0, 0); Step S52: the camera module continuously obtains the position of the left eye's eyeball convergence center point, and obtains the eyeball convergence center point position (x, y) after real-time scaling and comparison with the first picture information; Step S53: The observation degree analysis submodule obtains the offset arc value between the center point of the helmet forehead and the positive half axis of the Y axis greater than The real-time position of the left eye of the non-motor vehicle driver (x 11 ,y 11 )、(x 21 ,y 21 )……(x i1 ,y i1 ), and by the formula Calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 11 , γ 21 …γ i1 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the vehicle situation on the right side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the left through the output module; Step S54: The observation degree analysis submodule obtains the real-time position (x) of the left eye of the non-motor vehicle driver when the offset angle between the center point of the helmet forehead and the positive semi-axis of the Y axis is greater than 30°. 21 ,y 21 )、(x 22 ,y 22 )……(x i2 ,y i2 ), where i1+i2<n, and respectively calculate the offset distance value γ between the eyeball position in each time period and the left eyeball position calibrated by the first picture information 21 , γ 22 …γ i2 , calculate the total eye deviation angle of the driver like It is judged that the non-motor vehicle driver observes the situation on the left side of the road through his eyes, otherwise the speed reduction information is transmitted to the motor vehicle driver traveling to the right through the output module.

Images