Vehicle collision early warning method

Abstract

The invention belongs to the field of vehicle collision early warning, and particularly discloses a vehicle collision early warning method, which specifically comprises the following steps: step 1, collecting real-time point cloud data of roads around a current vehicle and other vehicles; 2, resolving the collected high-precision differential point cloud data at the frequency of 50 times per second to generate high-precision vehicle positioning data; 3, according to the collected road information and the high-frequency position information of other vehicles, the running speed and steering speed of the other vehicles are calculated, and the motion trail is fitted; a vehicle-mounted point cloud data acquisition instrument is used for acquiring vehicle surrounding environment data, fitting running paths of other vehicles and predicting positions of a target vehicle at different moments, and according to an AEB algorithm, the time required for two vehicles to run at the current speed until collision occurs from the current moment is calculated, so that the collision speed of the two vehicles is calculated. And when the speed of the rear vehicle is greater than that of the front vehicle, performing a TTC algorithm, determining an AEB trigger type according to a TTC value, and determining an early warning level.

Description

Technical Field

[0001] The invention belongs to the field of vehicle collision warning, and in particular relates to a vehicle collision warning method. Background Art

[0002] A vehicle is a mechanical device used to transport people or goods, usually consisting of one or more wheels, a power system and a cockpit. A vehicle collision can not only cause damage to the vehicle and property, but may even result in casualties. Therefore, it is very important to avoid a vehicle collision in time before it occurs.

[0003] Since the driver's field of vision is limited and he cannot pay attention to the situation in front, behind, left and right of the vehicle at the same time, he needs others or equipment to warn the driver;

[0004] However, the existing warning system usually uses cameras or ranging sensors to detect the distance between the vehicle and other vehicles. The warning range is small, and it is impossible to detect and predict the trajectory of other vehicles. It is easy to have false warnings, and the warning time cannot be adjusted according to the vehicle specifications and the driver's reaction time. The warning effect is not ideal. Summary of the invention

[0005] The purpose of the present invention is to provide a vehicle collision warning method to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A vehicle collision warning method, the specific steps are as follows:

[0008] Step 1: Collect real-time point cloud data of the roads and other vehicles around the current vehicle;

[0009] Step 2: Solve the collected high-precision differential point cloud data at a frequency of 50 times per second to generate high-precision vehicle positioning data;

[0010] Step 3: Based on the collected road information and high-frequency position information of other vehicles, calculate the driving speed and turning speed of other vehicles and fit the motion trajectory;

[0011] Step 4: Fit the vehicle's driving path through the position, speed, and steering angle of the vehicle itself, other vehicles, and the outer contours of obstacles, and predict the time when a collision may occur, so as to issue an early warning.

[0012] Step 5: Considering the driver's reaction delay, in order to avoid collision avoidance failure, the longitudinal and lateral redundancy values ​​are set according to different vehicle models, and the actual outer contour vertex coordinates of the vehicle are converted into the calculated outer contour vertex coordinates;

[0013] Step 6: Check whether the vertex coordinates of the other vehicle's outer contour are within or above the quadrilateral of the vehicle at that moment. If so, it is determined that the two vehicles will collide at the target moment.

[0014] Step 7: Trigger the corresponding warning level according to the target time of the warning.

[0015] Preferably, the point cloud data in step 1 is centered on the vehicle, collects environmental information with a radius of 15 meters, and uses differential GPS to ensure that the position accuracy is at the centimeter level.

[0016] Preferably, in step 1, a point cloud data collector is used to collect point cloud data, the point cloud data collector is located at the center of the top of the vehicle, and the relative distance between the device and the outer contour of the vehicle is determined.

[0017] Preferably, the vehicle trajectory in step 3 is divided into two categories, namely, a straight line and a circular curve. The straight line trajectory is that the vehicle travels in a straight line at a constant speed; the circular curve trajectory is that the vehicle travels along a circular curve at a constant speed, and the turning radius and angular velocity are calculated.

[0018] Preferably, in step 4, the positions of the vehicle itself and other vehicles and the outer contours of obstacles are relative positions; the speed is a constant moving speed calculated through continuous position data, and the steering angle is a steering angle calculated through changes in the vehicle's forward direction.

[0019] Preferably, the calculation steps of whether the vertex coordinates of other vehicle outer contours are within or above the vehicle quadrilateral in step 6 are as follows:

[0020] Step 6.1: Calculate each side of the ego vehicle quadrilateral using the coordinates of the four vertices of the ego vehicle's outer contour;

[0021] Step 6.2: Send a ray from the vertex coordinates of the outer contour of other vehicles in any direction;

[0022] Step 6.3: Calculate the intersection point of the ray with each edge of the ego-car quadrilateral;

[0023] Step 6.4: Count the total number of intersections between the ray and the ego-vehicle quadrilateral;

[0024] Step 6.5: When the number of intersection points is an even number, it means that the vertex coordinates of the other vehicle's outer contour are not within the self-vehicle quadrilateral; when the number of intersection points is an odd number, it means that the vertex coordinates of the other vehicle's outer contour are within the self-vehicle quadrilateral.

[0025] Preferably, in step 6.5, when the vertex coordinates of the outer contours of other vehicles are within the range of each side of the self-set quadrilateral, it means that the vertex coordinates of the outer contours of other vehicles are on the boundary of the self-set quadrilateral.

[0026] Preferably, the warning level of step 7 is set to three levels, namely, attention warning and emergency warning. When the speed of the rear vehicle is greater than that of the own vehicle, the relative speed is calculated, and the collision time is calculated by the relative speed and the distance between the two vehicles. The corresponding warning level is selected according to the collision time, that is, when the vertex coordinates of the outer contour of the other vehicle are located inside or on the quadrilateral of the own vehicle, the attention warning is triggered, and when the collision time is consistent with the safety braking time, the emergency warning is triggered.

[0027] Preferably, in step 5, the driver's reaction delay is 1-2 seconds, and the longitudinal redundancy value is calculated by the driver's reaction delay and the length of the vehicle; the lateral redundancy value is calculated by the width of the vehicle and the steering angle.

[0028] Preferably, automatic emergency braking is triggered when the collision time between the vertex coordinates of the outer contour of the other vehicle and the actual outer contour of the own vehicle is consistent with the safety braking time.

[0029] Compared with the prior art, the present invention has the following beneficial effects:

[0030] The present invention uses a vehicle-mounted point cloud data collector to collect data on the vehicle's surrounding environment, fits the driving paths of other vehicles, predicts the position of the target vehicle at different times, and calculates the time required for the two vehicles to maintain the current speed until a collision occurs from the current moment based on the AEB algorithm. When the speed of the rear vehicle is greater than that of the front vehicle, the TTC algorithm is performed, and the AEB trigger type is determined based on the TTC value, and finally the warning level is determined.

[0031] The present invention takes into account the difference in driver reaction delay and vehicle model specifications, calculates the longitudinal redundancy value according to the driver's reaction delay and the length of the vehicle, calculates the lateral redundancy value according to the width and steering angle of the vehicle, and then adds the calculated longitudinal redundancy value and lateral redundancy value to the horizontal and vertical axes of the actual outer contour vertex coordinates of the vehicle, so as to obtain the calculated outer contour vertex coordinates, thereby adjusting the warning time to avoid the occurrence of collision avoidance failure due to the slow reaction of the driver or the different vehicle model specifications. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0033] Figure 1 A block diagram of the specific steps of the vehicle collision warning method of the present invention;

[0034] Figure 2The flowchart of the calculation steps of determining whether the vertex coordinates of other vehicle outer contours are within or above the vehicle quadrilateral is provided. DETAILED DESCRIPTION

[0035] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0036] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0037] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0038] As attached Figure 1 To Attachment Figure 2 As shown:

[0039] Embodiment 1: This embodiment provides a vehicle collision warning method, and the specific steps are as follows:

[0040] Step 1: Collect real-time point cloud data of the roads and other vehicles around the current vehicle;

[0041] Step 2: Solve the collected high-precision differential point cloud data at a frequency of 50 times per second to generate high-precision vehicle positioning data;

[0042] Step 3: Based on the collected road information and high-frequency position information of other vehicles, calculate the driving speed and turning speed of other vehicles and fit the motion trajectory;

[0043] Step 4: Fit the vehicle's driving path through the position, speed, and steering angle of the vehicle itself, other vehicles, and the outer contours of obstacles, and predict the time when a collision may occur, so as to issue an early warning.

[0044] Step 5: Considering the driver's reaction delay, in order to avoid collision avoidance failure, the longitudinal and lateral redundancy values ​​are set according to different vehicle models, and the actual outer contour vertex coordinates of the vehicle are converted into the calculated outer contour vertex coordinates;

[0045] Step 6: Check whether the vertex coordinates of the other vehicle's outer contour are within or above the quadrilateral of the vehicle at that moment. If so, it is determined that the two vehicles will collide at the target moment.

[0046] Step 7: Trigger the corresponding warning level according to the target time of the warning.

[0047] Specifically, in step 1, the point cloud data is centered on the vehicle, collects environmental information with a radius of 15 meters, and uses differential GPS to ensure that the position accuracy is at the centimeter level.

[0048] Specifically, in step 1, a point cloud data collector is used to collect point cloud data. The point cloud data collector is located at the center of the top of the vehicle, and the relative distance between the device and the outer contour of the vehicle is determined.

[0049] Specifically, in step 3, the vehicle trajectory is divided into two categories, namely, a straight line and a circular curve. The straight line trajectory is that the vehicle travels in a straight line at a constant speed; the circular curve trajectory is that the vehicle travels along a circular curve at a constant speed, and the turning radius and angular velocity are calculated.

[0050] Specifically, the positions of the vehicle itself and other vehicles and the outer contours of obstacles in step 4 are relative positions; the speed is a constant moving speed calculated through continuous position data, and the steering angle is a steering angle calculated through the change in the vehicle's forward direction.

[0051] From the above, it can be seen that the vehicle-mounted point cloud data collector is used to collect data on the vehicle's surrounding environment. The collection frequency is 50 Hz and the accuracy is at the centimeter level. It can collect real-time point cloud data of roads and other vehicles with a radius of 15 meters around the vehicle-mounted point cloud data collector as the center, fit the driving path of other vehicles, predict the position of the target vehicle at different times, and calculate the time required for the two vehicles to maintain the current speed until a collision occurs based on the AEB algorithm. When the speed of the rear vehicle is greater than that of the front vehicle, the TTC algorithm is performed, and the AEB trigger type is determined based on the TTC value, and finally the warning level is determined.

[0052] Embodiment 2: This embodiment provides a vehicle collision warning method, and the specific steps are as follows:

[0053] Step 1: Collect real-time point cloud data of the roads and other vehicles around the current vehicle;

[0054] Step 2: Solve the collected high-precision differential point cloud data at a frequency of 50 times per second to generate high-precision vehicle positioning data;

[0055] Step 3: Based on the collected road information and high-frequency position information of other vehicles, calculate the driving speed and turning speed of other vehicles and fit the motion trajectory;

[0056] Step 4: Fit the vehicle's driving path through the position, speed, and steering angle of the vehicle itself, other vehicles, and the outer contours of obstacles, and predict the time when a collision may occur, so as to issue an early warning.

[0057] Step 5: Considering the driver's reaction delay, in order to avoid collision avoidance failure, the longitudinal and lateral redundancy values ​​are set according to different vehicle models, and the actual outer contour vertex coordinates of the vehicle are converted into the calculated outer contour vertex coordinates;

[0058] Step 6: Check whether the vertex coordinates of the other vehicle's outer contour are within or above the quadrilateral of the vehicle at that moment. If so, it is determined that the two vehicles will collide at the target moment.

[0059] Step 7: Trigger the corresponding warning level according to the target time of the warning.

[0060] Specifically, in step 1, the point cloud data is centered on the vehicle, collects environmental information with a radius of 15 meters, and uses differential GPS to ensure that the position accuracy is at the centimeter level.

[0061] Specifically, in step 1, a point cloud data collector is used to collect point cloud data. The point cloud data collector is located at the center of the top of the vehicle, and the relative distance between the device and the outer contour of the vehicle is determined.

[0062] Specifically, in step 3, the vehicle trajectory is divided into two categories, namely, a straight line and a circular curve. The straight line trajectory is that the vehicle travels in a straight line at a constant speed; the circular curve trajectory is that the vehicle travels along a circular curve at a constant speed, and the turning radius and angular velocity are calculated.

[0063] Specifically, the positions of the vehicle itself and other vehicles and the outer contours of obstacles in step 4 are relative positions; the speed is a constant moving speed calculated through continuous position data, and the steering angle is a steering angle calculated through the change in the vehicle's forward direction.

[0064] Specifically, the calculation steps for determining whether the vertex coordinates of the other vehicle outer contours are within or above the vehicle quadrilateral in step 6 are as follows:

[0065] Step 6.1: Calculate each side of the ego vehicle quadrilateral using the coordinates of the four vertices of the ego vehicle's outer contour;

[0066] Step 6.2: Send a ray from the vertex coordinates of the outer contour of other vehicles in any direction;

[0067] Step 6.3: Calculate the intersection point of the ray with each edge of the ego-car quadrilateral;

[0068] Step 6.4: Count the total number of intersections between the ray and the ego-vehicle quadrilateral;

[0069] Step 6.5: When the number of intersection points is an even number, it means that the vertex coordinates of the other vehicle's outer contour are not within the self-vehicle quadrilateral; when the number of intersection points is an odd number, it means that the vertex coordinates of the other vehicle's outer contour are within the self-vehicle quadrilateral.

[0070] Specifically, in step 6.5, when the vertex coordinates of the outer contours of other vehicles are within the range of each side of the self-set quadrilateral, it means that the vertex coordinates of the outer contours of other vehicles are on the boundary of the self-set quadrilateral.

[0071] Specifically, the warning level of step 7 is set to three levels, namely, attention warning and emergency warning. When the speed of the rear vehicle is greater than that of the own vehicle, the relative speed is calculated, and the collision time is calculated by the relative speed and the distance between the two vehicles. The corresponding warning level is selected according to the collision time, that is, when the vertex coordinates of the outer contour of the other vehicle are located inside or on the quadrilateral of the own vehicle, the attention warning is triggered, and when the collision time is consistent with the safety braking time, the emergency warning is triggered.

[0072] From the above, we can see that by setting the warning level to level three, the ray method is used to calculate whether the vertex coordinates of the outer contours of other vehicles at that moment are within or above the quadrilateral of the own vehicle. If they are within or before the quadrilateral of the own vehicle, it is judged that the two vehicles will collide at the target moment, and then the attention alarm is triggered to remind the driver to slow down, brake or avoid. When the collision time is consistent with the safe braking time, an emergency warning is triggered to brake immediately to avoid a collision conflict.

[0073] Embodiment 3: This embodiment provides a vehicle collision warning method, and the specific steps are as follows:

[0074] Step 1: Collect real-time point cloud data of the roads and other vehicles around the current vehicle;

[0075] Step 2: Solve the collected high-precision differential point cloud data at a frequency of 50 times per second to generate high-precision vehicle positioning data;

[0076] Step 3: Based on the collected road information and high-frequency position information of other vehicles, calculate the driving speed and turning speed of other vehicles and fit the motion trajectory;

[0077] Step 4: Fit the vehicle's driving path through the position, speed, and steering angle of the vehicle itself, other vehicles, and the outer contours of obstacles, and predict the time when a collision may occur, so as to issue an early warning.

[0078] Step 5: Considering the driver's reaction delay, in order to avoid collision avoidance failure, the longitudinal and lateral redundancy values ​​are set according to different vehicle models, and the actual outer contour vertex coordinates of the vehicle are converted into the calculated outer contour vertex coordinates;

[0079] Step 6: Check whether the vertex coordinates of the other vehicle's outer contour are within or above the quadrilateral of the vehicle at that moment. If so, it is determined that the two vehicles will collide at the target moment.

[0080] Step 7: Trigger the corresponding warning level according to the target time of the warning.

[0081] Specifically, in step 1, the point cloud data is centered on the vehicle, collects environmental information with a radius of 15 meters, and uses differential GPS to ensure that the position accuracy is at the centimeter level.

[0082] Specifically, in step 1, a point cloud data collector is used to collect point cloud data. The point cloud data collector is located at the center of the top of the vehicle, and the relative distance between the device and the outer contour of the vehicle is determined.

[0083] Specifically, in step 3, the vehicle trajectory is divided into two categories, namely, a straight line and a circular curve. The straight line trajectory is that the vehicle travels in a straight line at a constant speed; the circular curve trajectory is that the vehicle travels along a circular curve at a constant speed, and the turning radius and angular velocity are calculated.

[0084] Specifically, the positions of the vehicle itself and other vehicles and the outer contours of obstacles in step 4 are relative positions; the speed is a constant moving speed calculated through continuous position data, and the steering angle is a steering angle calculated through the change in the vehicle's forward direction.

[0085] Specifically, the calculation steps for determining whether the vertex coordinates of the other vehicle outer contours are within or above the vehicle quadrilateral in step 6 are as follows:

[0086] Step 6.1: Calculate each side of the ego vehicle quadrilateral using the coordinates of the four vertices of the ego vehicle's outer contour;

[0087] Step 6.2: Send a ray from the vertex coordinates of the outer contour of other vehicles in any direction;

[0088] Step 6.3: Calculate the intersection point of the ray with each edge of the ego-car quadrilateral;

[0089] Step 6.4: Count the total number of intersections between the ray and the ego-vehicle quadrilateral;

[0090] Step 6.5: When the number of intersection points is an even number, it means that the vertex coordinates of the other vehicle's outer contour are not within the self-vehicle quadrilateral; when the number of intersection points is an odd number, it means that the vertex coordinates of the other vehicle's outer contour are within the self-vehicle quadrilateral.

[0091] Specifically, in step 6.5, when the vertex coordinates of the outer contours of other vehicles are within the range of each side of the self-set quadrilateral, it means that the vertex coordinates of the outer contours of other vehicles are on the boundary of the self-set quadrilateral.

[0092] Specifically, the warning level of step 7 is set to three levels, namely, attention warning and emergency warning. When the speed of the rear vehicle is greater than that of the own vehicle, the relative speed is calculated, and the collision time is calculated by the relative speed and the distance between the two vehicles. The corresponding warning level is selected according to the collision time, that is, when the vertex coordinates of the outer contour of the other vehicle are located inside or on the quadrilateral of the own vehicle, the attention warning is triggered, and when the collision time is consistent with the safety braking time, the emergency warning is triggered.

[0093] Specifically, in step 5, the driver's reaction delay is 1-2 seconds, and the longitudinal redundancy value is calculated by the driver's reaction delay and the length of the vehicle; the lateral redundancy value is calculated by the width of the vehicle and the steering angle.

[0094] Specifically, automatic emergency braking is triggered when the collision time between the vertex coordinates of the outer contour of the other vehicle and the actual outer contour of the own vehicle is consistent with the safety braking time.

[0095] From the above, it can be seen that by considering the driver's reaction delay and the difference in vehicle specifications, in order to avoid collision avoidance failure, the longitudinal redundancy value is calculated according to the driver's reaction delay and the length of the vehicle, and the lateral redundancy value is calculated according to the width and steering angle of the vehicle. Then, the calculated outer contour vertex coordinates can be obtained by adding the horizontal and vertical axes of the actual outer contour vertex coordinates of the vehicle to the calculated outer contour vertex coordinates, and then the actual outer contour vertex coordinates of the vehicle are converted into calculated outer contour vertex coordinates. The calculated outer contour vertex coordinates are used to calculate the vehicle quadrilateral, so that when the system issues an emergency warning when the collision detection time is consistent with the safe braking time, there is still a part of redundant time for the driver to react, thereby avoiding collision avoidance failure due to slow driver reaction or different vehicle specifications.

[0096] This design application is applied to vehicle driving scenarios, and uses a vehicle-mounted point cloud data collector to collect data on the vehicle's surrounding environment. It has a wide range and high accuracy. It can also detect the movement trajectories of other vehicles to predict their movement routes, and judge the collision time based on the route and its relative speed to improve the warning effect. By considering the driver's reaction delay and the difference in vehicle specifications, the warning time is adjusted synchronously to improve the warning sensitivity and accuracy, thereby increasing the driver's trust.

[0097] Importantly, it should be noted that the construction and arrangement of the present application shown in a plurality of different exemplary embodiments are only exemplary. Although only a few embodiments are described in detail in this disclosure, it should be readily understood by those who refer to this disclosure that many modifications are possible (e.g., the size, scale, structure, shape and proportion of various elements, and parameter values ​​(e.g., temperature, pressure, etc.), installation arrangement, use of materials, color, directional changes, etc.) without substantially departing from the novel teachings and advantages of the subject matter described in the application. For example, the element shown as integrally formed can be composed of multiple parts or elements, the position of the element can be inverted or otherwise changed, and the nature or number or position of the discrete element can be changed or changed. Therefore, all such modifications are intended to be included in the scope of the present invention. The order or sequence of any process or method steps can be changed or reordered according to alternative embodiments. In the claims, any "device plus function" clause is intended to cover the structure of performing the function described herein, and is not only structurally equivalent but also equivalent structure. Without departing from the scope of the present invention, other replacements, modifications, changes and omissions can be made in the design, operating conditions and arrangement of the exemplary embodiments. Therefore, the invention is not limited to a specific embodiment, but extends to numerous modifications still falling within the scope of the appended claims.

[0098] Additionally, in order to provide a concise description of exemplary embodiments, all features of an actual embodiment (ie, those features that are not relevant to the best mode presently contemplated for carrying out the invention or those that are not relevant to implementing the invention) may not be described.

[0099] It will be appreciated that in the development of any actual implementation, as in any engineering or design project, numerous implementation-specific decisions may be made. Such a development effort may be complex and time-consuming, but will be a routine task of design, fabrication, and production for those of ordinary skill having the benefit of this disclosure without undue experimentation.

[0100] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A vehicle collision warning method, characterized in that: The specific steps are as follows: Step 1: Collect real-time point cloud data of the roads and other vehicles around the current vehicle; Step 2: Solve the collected high-precision differential point cloud data at a frequency of 50 times per second to generate high-precision vehicle positioning data; Step 3: Based on the collected road information and high-frequency position information of other vehicles, calculate the driving speed and turning speed of other vehicles and fit the motion trajectory; Step 4: Fit the vehicle's driving path through the position, speed, and steering angle of the vehicle itself, other vehicles, and the outer contours of obstacles, and predict the time when a collision may occur, so as to issue an early warning. Step 5: Considering the driver's reaction delay, in order to avoid collision avoidance failure, the longitudinal and lateral redundancy values ​​are set according to different vehicle models, and the actual outer contour vertex coordinates of the vehicle are converted into the calculated outer contour vertex coordinates; Step 6: Check whether the vertex coordinates of the other vehicle's outer contour are within or above the quadrilateral of the vehicle at that moment. If so, it is determined that the two vehicles will collide at the target moment. Step 7: Trigger the corresponding warning level according to the target time of the warning.

2. A vehicle collision warning method according to claim 1, characterized in that: In step 1, the point cloud data is centered on the vehicle, collects environmental information with a radius of 15 meters, and uses differential GPS to ensure that the position accuracy is at the centimeter level.

3. A vehicle collision warning method according to claim 1, characterized in that: In the step 1, a point cloud data collector is used to collect point cloud data. The point cloud data collector is located at the center of the top of the vehicle, and the relative distance between the device and the outer contour of the vehicle is determined.

4. A vehicle collision warning method according to claim 1, characterized in that: In step 3, the vehicle trajectory is divided into two categories, namely, a straight line and a circular curve. The straight line trajectory is that the vehicle travels in a straight line at a constant speed; the circular curve trajectory is that the vehicle travels along a circular curve at a constant speed, and the turning radius and angular velocity are calculated.

5. A vehicle collision warning method according to claim 4, characterized in that: In step 4, the positions of the vehicle itself and other vehicles and the outer contours of obstacles are relative positions; the speed is a constant moving speed calculated through continuous position data, and the steering angle is a steering angle calculated through the change in the vehicle's forward direction.

6. A vehicle collision warning method according to claim 5, characterized in that: The calculation steps for determining whether the vertex coordinates of other vehicle outer contours in step 6 are within or above the vehicle quadrilateral are as follows: Step 6.1: Calculate each side of the ego vehicle quadrilateral using the coordinates of the four vertices of the ego vehicle's outer contour; Step 6.2: Send a ray from the vertex coordinates of the outer contour of other vehicles in any direction; Step 6.3: Calculate the intersection point of the ray with each edge of the ego-car quadrilateral; Step 6.4: Count the total number of intersections between the ray and the ego-vehicle quadrilateral; Step 6.5: When the number of intersection points is an even number, it means that the vertex coordinates of the other vehicle's outer contour are not within the self-vehicle quadrilateral; when the number of intersection points is an odd number, it means that the vertex coordinates of the other vehicle's outer contour are within the self-vehicle quadrilateral.

7. A vehicle collision warning method according to claim 6, characterized in that: In step 6.5, when the vertex coordinates of the outer contour of the other vehicle are within the range of each side of the self-set quadrilateral, it means that the vertex coordinates of the outer contour of the other vehicle are on the boundary of the self-set quadrilateral.

8. A vehicle collision warning method according to claim 7, characterized in that: The warning level of step 7 is set to three levels, namely, attention warning and emergency warning. When the speed of the rear vehicle is greater than that of the own vehicle, the relative speed is calculated, and the collision time is calculated by the relative speed and the distance between the two vehicles. The corresponding warning level is selected according to the collision time, that is, when the vertex coordinates of the outer contour of the other vehicle are located inside or on the quadrilateral of the own vehicle, the attention warning is triggered, and when the collision time is consistent with the safety braking time, the emergency warning is triggered.

9. A vehicle collision warning method according to claim 8, characterized in that: In step 5, the driver's reaction delay is 1-2 seconds, and the longitudinal redundancy value is calculated by the driver's reaction delay and the length of the vehicle; the lateral redundancy value is calculated by the width of the vehicle and the steering angle.

10. A vehicle collision warning method according to claim 9, characterized in that: Automatic emergency braking is triggered when the collision time between the vertex coordinates of the outer contour of the other vehicle and the actual outer contour of the own vehicle is consistent with the safety braking time.

Images