Automobile collision warning method, device, equipment and storage medium

Abstract

The application belongs to the field of intelligent driving, and proposes a vehicle collision detection method, device, equipment and storage medium. The method comprises the following steps: collecting the position of a vehicle in a predetermined area range, and the time when the vehicle is in the position; acquiring a determined motion trajectory of the vehicle at a current time, the motion trajectory comprising a first motion trajectory and a second motion trajectory; determining the driving state of the vehicle based on the second motion trajectory, and determining the linear equation of the motion of the vehicle based on the first motion trajectory; and determining whether there is a collision risk of the vehicle in the area range within a preset prediction period according to the driving state and the linear equation. Through the method, the collision calculation can be simplified, and the collision warning can be quickly and accurately generated.

Description

Technical Field

[0001] This application belongs to the field of intelligent driving, and in particular relates to methods, devices, equipment and storage media for automobile collision warning. Background Technology

[0002] With the increasing prevalence of automobiles, the number of traffic accidents has also increased. Driving safety has become a primary concern for both manufacturers and consumers. To reduce collisions, it is common practice to predict vehicle movement and routes based on historical trajectories, thereby determining the time of collision and identifying potential targets for early warning.

[0003] However, during vehicle operation, road conditions are complex and vehicle posture changes. Predicting vehicle motion status and route through historical trajectory to predict collision risk requires obtaining relatively complex vehicle information, including vehicle size, braking information, steering wheel movements, etc. The data acquisition and calculation are complex and the accuracy is not high, which can easily generate false alarms and is not conducive to improving the driver's driving experience. Summary of the Invention

[0004] In view of this, embodiments of this application provide a vehicle collision detection method, apparatus, device, and storage medium to solve the problems that in the prior art, when conducting collision detection, the data to be acquired and the calculations are relatively complex, the detection accuracy is not high, false alarms are easily generated, and it is not conducive to improving the driver's driving experience.

[0005] A first aspect of this application provides a vehicle collision warning method, the method comprising:

[0006] Collect the location of vehicles within a predetermined area, as well as the time when the vehicles were in the designated location;

[0007] Based on the multiple locations of the vehicle and the time when the vehicle was in the location, the motion trajectory of the vehicle at the current moment is obtained. The motion trajectory includes a first motion trajectory and a second motion trajectory, and the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory.

[0008] The driving state of the vehicle is determined based on the second motion trajectory, and the linear equation of the vehicle's motion is determined based on the first motion trajectory.

[0009] Based on the driving status and the linear equation, determine whether there is a collision risk for vehicles within the area during a preset prediction period.

[0010] In conjunction with the first aspect, in a first possible implementation of the first aspect, determining the driving state of the vehicle based on the second motion trajectory includes:

[0011] The acceleration and speed of the vehicle are determined based on the second motion trajectory;

[0012] When the acceleration and the velocity are in different directions, the deceleration completion time when the vehicle speed decelerates to 0 is determined based on the acceleration and the velocity. The driving state of the vehicle is determined based on the relationship between the deceleration completion time and the predicted time period.

[0013] In conjunction with the first possible implementation of the first aspect, in the second possible implementation of the first aspect, determining the driving state of the vehicle based on the relationship between the time when the vehicle completes deceleration and the predicted time period includes:

[0014] When the deceleration completion time falls within a preset prediction period, the vehicle is marked as being in a deceleration state.

[0015] If the deceleration completion time is earlier than the start time of the predicted time period, the vehicle is marked as a stationary vehicle.

[0016] If the deceleration completion time is later than the end time of the predicted time period, the vehicle is marked as being in motion.

[0017] In conjunction with the first aspect, in a third possible implementation of the first aspect, determining the linear equation of the vehicle's motion based on the first motion trajectory includes:

[0018] The first system of linear equations is determined based on the relationship between the x-coordinates of the trajectory points in the first motion trajectory and time.

[0019] The second set of linear equations is determined based on the relationship between the ordinate of the trajectory points in the first motion trajectory and time.

[0020] The linear equations of vehicle motion are determined based on the first and second sets of linear equations.

[0021] In conjunction with the first aspect, in a fourth possible implementation of the first aspect, determining whether there is a collision risk for vehicles within the area during a preset prediction period based on the driving state and the linear equation includes:

[0022] The intersection point of the two vehicles is determined based on the linear equation.

[0023] Based on the driving status, determine the first and second times when the two vehicles arrive at the intersection point respectively;

[0024] When the first moment and the second moment belong to a preset prediction period, and both the first moment and the second moment are earlier than the deceleration completion moment when the vehicle speed decelerates to 0, the collision duration is calculated based on the first moment and the second moment.

[0025] A collision warning is generated when the collision duration is less than a predetermined collision duration threshold.

[0026] In conjunction with the fourth possible implementation of the first aspect, in the fifth possible implementation of the first aspect, before generating a collision warning when the collision duration is less than a predetermined collision duration threshold, the method further includes:

[0027] Obtain the first position P1, the second position P2, the third position P3, and the intermediate position P3 of the second motion trajectory, which are the closest time points to the current time.

[0028] Calculate the distance L between the middle line segment formed by the third position P3 and the first position P1. p3p1 The distance L between the middle line segment formed by the third position P3 and the second position P2 p2p3 And the trajectory segment L formed by the first position P1 and the second position P2. p1p2 ;

[0029] The curvature of the vehicle's trajectory is determined by the ratio of the middle line segment to the beginning and end line segments of the trajectory.

[0030] The collision duration threshold is determined based on the curvature of the vehicle's trajectory.

[0031] In conjunction with the fourth possible implementation of the first aspect, in the sixth possible implementation of the first aspect, determining the first and second moments when the two vehicles arrive at the intersection point respectively, based on the driving state, includes:

[0032] Based on the position of the intersection point relative to the vehicle, determine the main coordinate axis movement direction of the vehicle;

[0033] Based on the vehicle's main coordinate axis direction of motion, a linear equation corresponding to that coordinate axis is selected to calculate the first and second moments when the vehicle arrives at the intersection point.

[0034] In conjunction with the first aspect, in the seventh possible implementation of the first aspect, collecting the location of vehicles within a predetermined area and the time when the vehicles are at said locations includes:

[0035] When the vehicle is in a C-V2X scenario without a roadside, the vehicle's position within a predetermined area and the time when the vehicle is in the predetermined position are collected by the vehicle's onboard unit.

[0036] When the vehicle is in a C-V2X scenario with a roadside unit, the location of the vehicle within a predetermined area and the time when the vehicle is in the location are collected through the roadside unit.

[0037] A second aspect of this application provides a vehicle collision warning device, the device comprising:

[0038] The data acquisition unit is used to acquire the location of vehicles within a predetermined area, as well as the time when the vehicles are at the specified locations.

[0039] A motion trajectory determination unit is used to obtain the motion trajectory of the vehicle at the current moment based on multiple positions of the vehicle and the time when the vehicle is in the position. The motion trajectory includes a first motion trajectory and a second motion trajectory, wherein the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory.

[0040] A driving state determination unit is used to determine the driving state of the vehicle based on the second motion trajectory and to determine the linear equation of the vehicle's motion based on the first motion trajectory.

[0041] The warning unit is used to determine whether there is a collision risk for vehicles within the area within a preset prediction period, based on the driving status and the linear equation.

[0042] A third aspect of this application provides a vehicle collision warning device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method as described in any of the first aspects.

[0043] A fourth aspect of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the method as described in any of the first aspects.

[0044] The beneficial effects of this application embodiment compared with the prior art are as follows: In this application, by using the position of the vehicle within a predetermined area and the time when the vehicle is in the position, the data obtained by this application is simpler than that obtained by acquiring vehicle body data; based on the position and the time, the first trajectory and the second trajectory of the vehicle are obtained, and the driving state of the car is determined based on the second trajectory with a longer movement duration, which can improve the accuracy of the acquired driving state of the car compared with the roadside intelligent perception system; the linear equation of the car's motion is determined based on the first trajectory with a shorter movement duration, thereby simplifying the calculation, so that it is possible to quickly and accurately determine whether to generate a collision warning through the driving state and the linear equation. Attached Figure Description

[0045] To more clearly illustrate the technical solutions in the embodiments of this application, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0046] Figure 1 This is a schematic diagram illustrating an implementation scenario of a vehicle collision warning system provided in an embodiment of this application;

[0047] Figure 2 This is a schematic diagram of another vehicle collision warning implementation scenario provided in the embodiments of this application;

[0048] Figure 3 This is a schematic diagram illustrating the implementation process of a vehicle collision warning method provided in an embodiment of this application;

[0049] Figure 4 This is a schematic diagram illustrating a method for calculating trajectory curvature provided in an embodiment of this application;

[0050] Figure 5 This is a schematic diagram illustrating the implementation process for determining the acceleration and deceleration state of a vehicle, provided in an embodiment of this application.

[0051] Figure 6 This is a schematic diagram illustrating the implementation process of collision detection based on linear equations and driving states, provided in an embodiment of this application.

[0052] Figure 7 This is a schematic diagram of a car collision warning device provided in an embodiment of this application;

[0053] Figure 8 This is a schematic diagram of the vehicle collision warning device provided in the embodiments of this application. Detailed Implementation

[0054] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of this application. However, those skilled in the art will understand that this application may also be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods have been omitted so as not to obscure the description of this application with unnecessary detail.

[0055] To illustrate the technical solution described in this application, specific embodiments are provided below.

[0056] Figure 1 This is a schematic diagram illustrating an implementation scenario of a vehicle collision warning method provided in an embodiment of this application. Figure 1 As shown, in a car-driving scenario, roadside sensing devices, roadside units (RSUs), and traffic guidance screens are installed on the roadside. MEC (Mobile Edge Computing) servers are connected to the roadside units. Cars driving on the road can include both regular cars and connected vehicles.

[0057] Roadside sensing devices can include cameras, millimeter-wave radar, and lidar. These devices can acquire images of vehicles traveling on the road and send them to an MEC server. The MEC server determines the vehicle's position and the time at each position, and based on the collision warning method described in this application, determines whether to generate a collision warning. When a connected vehicle (or intelligent connected vehicle) is detected requiring a collision warning, the MEC server can send the warning to the vehicle via the RSU (Roadside Unit) or display a notification on a traffic guidance screen. When a regular vehicle is detected requiring a collision warning, a notification can be displayed on the traffic guidance screen.

[0058] Figure 2 This is a schematic diagram illustrating an implementation scenario of another vehicle collision warning method provided in this application embodiment. For example... Figure 2 As shown, in this scenario, no roadside units or roadside sensing devices are deployed alongside the road. The vehicles traveling on the road are connected vehicles. Within a certain range, the onboard units of connected vehicles can obtain information such as the vehicle's number, location, and the corresponding time of that location. Based on the vehicle collision warning method described in this application, the onboard unit can determine whether a collision warning will be issued for the vehicle within a predetermined prediction period. If so, it can directly remind the driver of the collision risk or automatically collect information on avoidance measures such as braking.

[0059] Figure 3 This is a flowchart illustrating the implementation of a vehicle collision warning method provided in an embodiment of this application. Figure 3 As shown, the method includes:

[0060] In S301, the location of vehicles within a predetermined area and the time when the vehicles are at the designated locations are collected.

[0061] Depending on the implementation scenario of this application, the entity executing the vehicle collision warning method described in this application will also differ. For example, in Figure 1 In the implementation scenario shown, the execution entity can be an MEC server. Figure 2 In the implementation scenario shown, the executing entity can be the vehicle's on-board unit (OBU).

[0062] When collecting data on vehicle location and the time the vehicle is in that location, different data collection methods can be used depending on the implementation scenario. For example, in... Figure 1 In the implementation scenario shown, specifically in a roadside C-V2X intelligent system environment, the MEC server can obtain the ID, location, and corresponding time of connected vehicles equipped with OBUs via the RSU. The ID, location, and corresponding time of ordinary vehicles (i.e., vehicles without OBUs) can be obtained via roadside sensing devices.

[0063] exist Figure 2 In the implementation scenarios shown, in scenarios without roadside units, such as in a C-V2X intelligent system environment without roadside units, connected vehicles equipped with onboard units obtain the numbers, locations, and corresponding times of other connected vehicles through network communication.

[0064] In S302, the motion trajectory of the vehicle at the current moment is obtained based on the multiple positions of the vehicle and the time when the vehicle was in the position.

[0065] The motion trajectory includes a first motion trajectory and a second motion trajectory, wherein the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory.

[0066] During each vehicle collision warning calculation, a first trajectory and a second trajectory can be determined based on the acquired location and the corresponding time. Both the first and second trajectories are relevant to the current moment. For example, the first and second trajectories may include the current moment.

[0067] Alternatively, the first or second trajectory can be a trajectory updated according to a predetermined update cycle. In this case, the first or second trajectory can be the trajectory that is closest to the current time among the multiple updated trajectories.

[0068] In one possible implementation, the calculation cycle of the vehicle collision warning is the same as the update cycle of the second trajectory, or an integer multiple of the update cycle of the first trajectory. In this case, the first and second trajectories, including the current moment, can be directly determined based on the current moment when the vehicle collision warning is issued.

[0069] In this embodiment, the first trajectory is shorter than the second trajectory. For example, the first trajectory can be an instantaneous motion trajectory lasting less than 1 second. The second trajectory can be a medium-distance motion trajectory lasting more than 2 seconds. The trajectory generated based on the position can be cyclically stored in the trajectory record according to a preset time interval.

[0070] In the implementation, the coordinate systems of the positions obtained in the same scene may be different. For example, the coordinates obtained by the vehicle-road cooperative method are based on the WGS-84 coordinate system. The coordinate positions perceived by the OBU can be unified into the same coordinate system through coordinate transformation, such as the position in Euclidean coordinates on the xy-axis plane, which facilitates the unified calculation of the vehicle's position.

[0071] In S303, the driving state of the vehicle is determined based on the second motion trajectory, and the linear equation of the vehicle's motion is determined based on the first motion trajectory.

[0072] In this embodiment of the application, the driving state may include a moving state, a stationary state, a deceleration state, etc.

[0073] When determining the driving state of the vehicle, the vehicle's acceleration and deceleration states may also be included. For example... Figure 5 As shown, the process of determining the driving status may include:

[0074] In S501, the acceleration and speed of the vehicle are determined based on the second motion trajectory.

[0075] The vehicle's velocity between two trajectory points can be calculated based on the distance between them and the time difference between them. The vehicle's acceleration during travel can be calculated based on the change in its velocity along the second trajectory.

[0076] In S502, when the acceleration and velocity have different directions, the deceleration completion time when the vehicle speed decelerates to 0 is determined based on the acceleration and the velocity.

[0077] When the vehicle's acceleration is in the same direction as its velocity, it indicates that the vehicle is accelerating. When the vehicle's acceleration and velocity are in the same direction, the vehicle is accelerating and will not stop within a preset predicted time period.

[0078] When the vehicle's acceleration is in a different direction from its velocity, i.e., the acceleration is negative, it indicates that the vehicle is decelerating. The deceleration completion time when the vehicle's speed reaches 0 can then be calculated. Based on the relationship between the deceleration completion time and a preset prediction time period, the vehicle's driving state is determined.

[0079] Specifically, based on the velocity formula v = v0 + at, we can calculate the time t required for the vehicle to decelerate to 0 when the current acceleration a is negative and the vehicle is in a deceleration state. s = -v0 / a. The vehicle's current speed is v0.

[0080] In S503, when the deceleration completion time is within a preset prediction period, the vehicle is marked as being in a deceleration state.

[0081] The prediction period can be set to [t]. p-min , t p-max If the deceleration is completed within the set prediction period, it means that the vehicle may stop within the prediction period, and the vehicle can be marked as decelerating.

[0082] In S504, if the deceleration completion time is earlier than the start time of the predicted time period, the vehicle is marked as a stationary vehicle.

[0083] If the deceleration is completed before the start of the prediction period, but not during the prediction period, it means that the vehicle may have already stopped moving at the start of the prediction, and the vehicle can be marked as stationary during the prediction period. Alternatively, if the acceleration is negative and the vehicle's current speed V is less than the preset minimum speed, the vehicle can also be marked as stationary during the prediction period.

[0084] In S505, if the deceleration completion time is later than the end time of the predicted time period, the vehicle is marked as being in motion.

[0085] If the vehicle completes its deceleration later than the end of the predicted time period, meaning the vehicle continues to travel at a certain speed after the predicted time period ends, then the vehicle can be marked as being in motion.

[0086] When determining the linear equation of the vehicle's motion, it can be calculated based on the first motion trajectory, i.e., the instantaneous motion trajectory.

[0087] Assuming the current instantaneous motion is linear, subsequent motion will continue in this trend. Its matrix relationship is Ax = b, where...

[0088]

[0089] Substituting the instantaneous trajectory's time T and x-axis position X into A and b respectively, we obtain the linear equation system X = Kx*T + Cx relating T and X. Here, K and C are the constants of the linear equations.

[0090] Substituting the instantaneous trajectory's time T and y-axis position Y into A and b respectively, we obtain the linear equation system Y = Ky*T + Cy relating T and Y.

[0091] Substituting the x-axis position X and the y-axis position Y into A and b respectively, we obtain the linear equation system Y = Kp*X + Cp relating X and Y.

[0092] In S304, based on the driving state and the linear equation, it is determined whether there is a collision risk for vehicles within the area during a preset prediction period.

[0093] Before performing collision calculations, a preliminary assessment of the vehicles can be made based on their driving status. For example, a vehicle A can be selected as the main vehicle, and it can be determined whether the main vehicle A is stationary. If the vehicle is stationary, it will not participate in the collision assessment.

[0094] By selecting another vehicle as vehicle B, the heading angles of both vehicle A and vehicle B can be obtained. If the heading angles of the two vehicles are similar, for example, if the difference in heading angles is less than a predetermined angle threshold, then the two vehicles are traveling in the same direction, and forward collision detection can be performed. If the difference in heading angles between the two vehicles is greater than or equal to the predetermined angle threshold, then cross-collision detection can be performed.

[0095] When performing cross-collision detection, it can be done as follows: Figure 6 As shown, it includes:

[0096] In S601, the intersection point of the two vehicles is determined according to the linear equation.

[0097] Specifically, when determining the intersection point of two vehicles, the linear equations of the two vehicles at the current moment can be obtained. The solutions to the two linear equations can be calculated based on the position equations of the two vehicles Y=Kp*X+Cp, and the intersection point position (Xp, Yp) can be obtained.

[0098] In S602, based on the driving state, the first and second times when the two vehicles arrive at the intersection point are determined respectively.

[0099] You can compare the vehicle's Ky and Kx values ​​with the distance to the intersection point. Based on the distance, you can select either the x-axis or y-axis as the vehicle's primary direction of motion. For example, select the direction with the larger distance as the primary direction of motion.

[0100] If the main vehicle A's primary direction of motion is along the x-axis, substitute the Xp at the intersection point into the linear equation X = Kx * T + Cx to calculate the time Ta to reach the collision point. If the primary direction of motion is along the y-axis, substitute the Yp at the intersection point into Y = Kp * X + Cp to calculate the time Ta to reach the collision point. Using the same method, the time Tb for vehicle B to reach the collision point can be calculated.

[0101] In S603, when the first moment and the second moment belong to a preset prediction period, and both the first moment and the second moment are earlier than the deceleration completion moment when the vehicle speed decelerates to 0, the collision duration is calculated based on the first moment and the second moment.

[0102] The validity of the collision time can be determined based on the predicted time period. When Ta or Tb is later than the latest value t in the predicted time period... p-max This indicates that the collision occurred very early, and the status of subsequent vehicles is unknown. This can filter out the current situation, reduce false alarms, and improve the accuracy of the warning.

[0103] Alternatively, if either vehicle A (the primary vehicle) or vehicle B (the secondary vehicle) is marked as decelerating, the calculated deceleration time is t. s If the deceleration time t s If the value is less than Ta or Tb, it means that the vehicle has stopped running before reaching the collision point, and therefore no collision calculation is required.

[0104] If the deceleration time is t s Less than Ta, and deceleration time t s If the value is less than Tb, it indicates that the vehicle is still moving after reaching the intersection collision point, and a collision may occur. In this case, the collision duration can be calculated. The collision duration can be calculated by taking the absolute value of the difference between the arrival times of the primary vehicle A and the secondary vehicle B at the collision point, |Ta – Tb|, as the collision duration of the primary vehicle A and the secondary vehicle B.

[0105] In S604, a collision warning is generated when the collision duration is less than a predetermined collision duration threshold.

[0106] The collision duration is compared with a predetermined collision duration threshold. If it is less than or equal to the threshold, it indicates that a collision is likely to occur within the predicted time period, and a collision risk warning can be generated. This warning can be sent to the vehicle owner via the OBU, broadcast to the owner via the RSU, or displayed on a traffic information screen. Alternatively, collision risks within the area can be statistically analyzed to guide traffic management departments in improving and optimizing traffic conditions, thereby enhancing traffic safety in the area.

[0107] If the collision duration exceeds the predetermined collision duration threshold, it means that the vehicle will not be involved in a collision within the predicted time period.

[0108] In this embodiment, the collision duration threshold can be determined based on the curvature of the calculated path. When the curvature is large, a smaller collision duration threshold can be used. When the curvature is small, i.e., closer to linear motion, a larger collision duration threshold can be used.

[0109] When obtaining the curvature of the vehicle's motion trajectory, it can be calculated and determined based on a second motion trajectory with a longer duration.

[0110] The first position P1, which is the closest time point to the current time (which may be the current time or a time point before the current time), the second position P2, which is the farthest time point from the current time, and the third position P3, which is the intermediate time point, can be obtained from the second motion trajectory.

[0111] After determining the first position P1, the second position P2, and the third position P3, the intermediate line segment L determined by the third position P3 and the first position P1 can be used. p3p1 The distance L between the middle line segment formed by the third position P3 and the second position P2 p2p3 And the trajectory segment L formed by the first position P1 and the second position P2. p1p2 .

[0112] The lengths of the intermediate line segment and the beginning and end line segments of the trajectory can be calculated separately, and the curvature of the vehicle's trajectory can be determined based on the ratio of the lengths of the intermediate line segment to the beginning and end line segments of the trajectory.

[0113] In one possible calculation method, the curvature of the vehicle's trajectory can be determined by the ratio of the sum of the lengths of the two intermediate line segments to the lengths of the beginning and end line segments of the trajectory. For example... Figure 4 As shown, it can be calculated using the formula Q = (L p3p1 +L p2p3 ) / L p1p2 This allows us to obtain the line segment ratio Q. The closer the ratio Q (curvature) is to 1, the closer the vehicle is to traveling in a straight line. The larger the ratio, the higher the curvature of the vehicle's travel, such as when the vehicle is traveling on a curve.

[0114] It is understandable that the calculation method is not limited to the ratio of the lengths of two intermediate line segments to the lengths of the beginning and end line segments of the trajectory; the ratio can also be calculated for the lengths of a single intermediate line segment to the lengths of the beginning and end line segments of the trajectory.

[0115] The vehicle collision warning method described in this application performs cyclic calculations at a set frequency during vehicle operation. Furthermore, in a vehicle-to-infrastructure (V2I) environment, the vehicle's trajectory is updated according to a predetermined period, such as every 200ms. This application allows setting the collision warning calculation frequency to be consistent with the trajectory update frequency, for example, setting it to a 200ms calculation period. Additionally, the collision detection frequency can be adjusted according to changes in vehicle speed. For example, as the operating speed increases, the warning calculation frequency is increased to achieve a real-time warning effect.

[0116] The vehicle collision warning detection method described in this application has the following advantages:

[0117] 1. The data source is simple.

[0118] The data obtained in this application only requires the vehicle's serial number, location, and the corresponding time; complex vehicle information such as steering wheel angle, braking information, and vehicle size is not required. This simplifies data acquisition and improves the ease of implementation.

[0119] 2. The calculation is simple.

[0120] This application uses linear equations, which greatly reduces the computational complexity for scenarios involving curved collisions.

[0121] 3. High compatibility.

[0122] This application divides historical trajectories into instantaneous motion trajectories and mid-range motion trajectories. The mid-range motion trajectory is used to calculate the vehicle's heading, speed, acceleration, and deceleration stopping time, while the instantaneous motion trajectory is used to obtain the linear equation of the vehicle's instantaneous motion. In a roadside C-V2X intelligent system environment, the vehicle's heading, speed, and acceleration data calculated from the mid-range motion trajectory can effectively mitigate data errors introduced by roadside intelligent sensing systems and improve compatibility with different roadside intelligent sensing systems.

[0123] 4. High accuracy of early warning

[0124] 4.1 The vehicle motion state defined in this application differs from the definition of vehicle motion state in general methods. In this application, a stationary state is defined as a vehicle speed less than a predefined speed, or a vehicle speed that may become 0 before the prediction period; a running state is defined as a state where the vehicle speed may still be greater than 0 after the latest time of the prediction period; and a decelerating state is defined as a state where the vehicle speed may decrease to 0 within the prediction time. This definition reduces false triggering of the method during operation and improves the accuracy of the warning.

[0125] 4.2 This application assesses collision risk by calculating the time difference between the arrival times of the two vehicles at the predicted collision point. This method can improve the accuracy of early warnings and reduce the occurrence of missed warnings.

[0126] 5. It has a wide range of applications.

[0127] The vehicle collision warning method described in this application can be used for safety reminders on the vehicle side of a connected vehicle, and also for risk calculation and safety reminder services within a region on the roadside computing terminal.

[0128] It should be understood that the sequence number of each step in the above embodiments does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0129] Figure 7 This is a schematic diagram of a car collision warning device provided in an embodiment of this application, as shown below. Figure 6 As shown, the device includes:

[0130] The acquisition unit 701 is used to acquire the location of vehicles within a predetermined area, as well as the time when the vehicles are at the location;

[0131] The motion trajectory determination unit 702 is used to obtain the motion trajectory of the vehicle at the current moment based on multiple positions of the vehicle and the time when the vehicle is in the position. The motion trajectory includes a first motion trajectory and a second motion trajectory, wherein the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory.

[0132] The driving state determination unit 703 is used to determine the driving state of the vehicle based on the second motion trajectory and to determine the linear equation of the vehicle's motion based on the first motion trajectory.

[0133] The warning unit 704 is used to determine whether there is a collision risk for vehicles within the area within a preset prediction period, based on the driving status and the linear equation.

[0134] Figure 7 The car collision warning device shown is, with Figure 3 The corresponding car collision warning method is shown.

[0135] Figure 8 This is a schematic diagram of a car collision warning device provided in one embodiment of this application. Figure 8As shown, the vehicle collision warning device 8 of this embodiment includes: a processor 80, a memory 81, and a computer program 82 stored in the memory 81 and executable on the processor 80, such as a vehicle collision warning program. When the processor 80 executes the computer program 82, it implements the steps in the various vehicle collision warning method embodiments described above. Alternatively, when the processor 80 executes the computer program 82, it implements the functions of each module / unit in the various device embodiments described above.

[0136] For example, the computer program 82 may be divided into one or more modules / units, which are stored in the memory 81 and executed by the processor 80 to complete this application. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, which describe the execution process of the computer program 82 in the vehicle collision warning device 8.

[0137] The vehicle collision warning device may include, but is not limited to, a processor 80 and a memory 81. Those skilled in the art will understand that... Figure 8 This is merely an example of the car collision warning device 8 and does not constitute a limitation on the car collision warning device 8. It may include more or fewer components than shown, or combine certain components, or different components. For example, the car collision warning device may also include input / output devices, network access devices, buses, etc.

[0138] The processor 80 may be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor.

[0139] The memory 81 can be an internal storage unit of the vehicle collision warning device 8, such as a hard drive or memory of the vehicle collision warning device 8. The memory 81 can also be an external storage device of the vehicle collision warning device 8, such as a plug-in hard drive, Smart Media Card (SMC), Secure Digital (SD) card, or Flash Card equipped on the vehicle collision warning device 8. Furthermore, the memory 81 can include both internal and external storage units of the vehicle collision warning device 8. The memory 81 is used to store the computer program and other programs and data required by the vehicle collision warning device. The memory 81 can also be used to temporarily store data that has been output or will be output.

[0140] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the above-described division of functional units and modules is merely an example. In practical applications, the above functions can be assigned to different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiments can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit. Furthermore, the specific names of the functional units and modules are only for easy differentiation and are not intended to limit the scope of protection of this application. The specific working process of the units and modules in the above system can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0141] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0142] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0143] In the embodiments provided in this application, it should be understood that the disclosed devices / terminal equipment and methods can be implemented in other ways. For example, the device / terminal equipment embodiments described above are merely illustrative. For instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling or direct coupling or communication connection may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0144] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0145] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0146] If the integrated module / unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, all or part of the processes in the methods of the above embodiments can also be implemented by hardware related to computer program instructions. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the various method embodiments described above. The computer program includes computer program code, which can be in the form of source code, object code, executable files, or certain intermediate forms. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording media, USB flash drives, portable hard drives, magnetic disks, optical disks, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signals, telecommunication signals, and software distribution media, etc. It should be noted that the content included in the computer-readable medium can be appropriately added or removed according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0147] The above-described embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application, and should all be included within the protection scope of this application.

Claims

1. A method for vehicle collision warning, characterized in that, The method includes: Collect the location of vehicles within a predetermined area, as well as the time when the vehicles were in the designated location; Based on the multiple locations of the vehicle and the time when the vehicle was in the location, the motion trajectory of the vehicle at the current moment is obtained. The motion trajectory includes a first motion trajectory and a second motion trajectory, and the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory. The driving state of the vehicle is determined based on the second motion trajectory, and the linear equation of the vehicle's motion is determined based on the first motion trajectory. The intersection point of the two vehicles is determined based on the linear equation. Based on the driving status, determine the first and second times when the two vehicles arrive at the intersection point respectively; When the first moment and the second moment belong to a preset prediction period, and both the first moment and the second moment are earlier than the deceleration completion moment when the vehicle speed decelerates to 0, the collision duration is calculated based on the first moment and the second moment. A collision warning is generated when the collision duration is less than a predetermined collision duration threshold. Before generating a collision warning when the collision duration is less than a predetermined collision duration threshold, the first position P1, the second position P2, and the third position P3, which are the closest time points to the current time points and the farthest time points from the current time points, are obtained in the second motion trajectory. Calculate the distance L between the middle line segment formed by the third position P3 and the first position P1. p3p1 The distance L between the middle line segment formed by the third position P3 and the second position P2 p2p3 And the trajectory segment L formed by the first position P1 and the second position P2. p1p2 ; The curvature of the vehicle's trajectory is determined by the ratio of the middle line segment to the beginning and end line segments of the trajectory. The collision duration threshold is determined based on the curvature of the vehicle's trajectory.

2. The method according to claim 1, characterized in that, Determining the vehicle's driving state based on the second motion trajectory includes: The acceleration and speed of the vehicle are determined based on the second motion trajectory; When the acceleration and the velocity are in different directions, the deceleration completion time when the vehicle speed decelerates to 0 is determined based on the acceleration and the velocity. The driving state of the vehicle is determined based on the relationship between the deceleration completion time and the predicted time period.

3. The method according to claim 2, characterized in that, Based on the relationship between the vehicle's deceleration completion time and the predicted time period, the driving state of the vehicle is determined, including: When the deceleration completion time falls within a preset prediction period, the vehicle is marked as being in a deceleration state. If the deceleration completion time is earlier than the start time of the predicted time period, the vehicle is marked as a stationary vehicle. If the deceleration completion time is later than the end time of the predicted time period, the vehicle is marked as being in motion.

4. The method according to claim 1, characterized in that, Determining the linear equation of the vehicle's motion based on the first motion trajectory includes: The first system of linear equations is determined based on the relationship between the x-coordinates of the trajectory points in the first motion trajectory and time. The second set of linear equations is determined based on the relationship between the ordinate of the trajectory points in the first motion trajectory and time. The linear equations of vehicle motion are determined based on the first and second sets of linear equations.

5. The method according to claim 1, characterized in that, Based on the driving status, the first and second moments when the two vehicles arrive at the intersection point are determined, including: Based on the position of the intersection point relative to the vehicle, determine the main coordinate axis movement direction of the vehicle; Based on the vehicle's main coordinate axis direction of motion, a linear equation corresponding to that coordinate axis is selected to calculate the first and second moments when the vehicle arrives at the intersection point.

6. The method according to claim 1, characterized in that, Collect the location of vehicles within a predetermined area, and the time when the vehicles are at said locations, including: When the vehicle is in a scenario without a roadside unit, the vehicle's position within a predetermined area and the time when the vehicle is in that position are collected by the vehicle's onboard unit. When the vehicle is in a scenario with a roadside unit, the location of the vehicle within a predetermined area and the time when the vehicle is in the location are collected through the roadside unit.

7. A vehicle collision warning device, characterized in that, The device includes: The data acquisition unit is used to acquire the location of vehicles within a predetermined area, as well as the time when the vehicles are at the specified locations. A motion trajectory determination unit is used to obtain the motion trajectory of the vehicle at the current moment based on multiple positions of the vehicle and the time when the vehicle is in the position. The motion trajectory includes a first motion trajectory and a second motion trajectory, wherein the motion duration of the first motion trajectory is less than the motion duration of the second motion trajectory. A driving state determination unit is used to determine the driving state of the vehicle based on the second motion trajectory and to determine the linear equation of the vehicle's motion based on the first motion trajectory. The warning unit is used to determine whether there is a collision risk among vehicles within the area within a preset prediction period based on the driving state and the linear equation. Specifically, it includes: determining the intersection point of two vehicles based on the linear equation; determining the first and second times when the two vehicles arrive at the intersection point respectively based on the driving state; when the first and second times belong to the preset prediction period and both the first and second times are earlier than the deceleration completion time when the vehicle speed decelerates to 0, calculating the collision duration based on the first and second times; and generating a collision warning when the collision duration is less than a predetermined collision duration threshold. Before generating a collision warning when the collision duration is less than a predetermined collision duration threshold, the first position P1, the second position P2, and the third position P3, which are the closest time points to the current time points and the farthest time points from the current time points, are obtained in the second motion trajectory. Calculate the distance L between the middle line segment formed by the third position P3 and the first position P1. p3p1 The distance L between the middle line segment formed by the third position P3 and the second position P2 p2p3 And the trajectory segment L formed by the first position P1 and the second position P2. p1p2 ; The curvature of the vehicle's trajectory is determined by the ratio of the middle line segment to the beginning and end line segments of the trajectory. The collision duration threshold is determined based on the curvature of the vehicle's trajectory.

8. A vehicle collision warning device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method as described in any one of claims 1 to 6.

Images