CN115331482B

CN115331482B - Vehicle early warning prompting method, device, base station and storage medium

Info

Publication number: CN115331482B
Application number: CN202110508438.0A
Authority: CN
Inventors: 张诗晨; 马冰; 王邓江; 邓永强
Original assignee: Beijing Wanji Technology Co Ltd
Current assignee: Beijing Wanji Technology Co Ltd
Priority date: 2021-05-10
Filing date: 2021-05-10
Publication date: 2024-05-28
Anticipated expiration: 2041-05-10
Also published as: CN115331482A

Abstract

The application discloses a vehicle early warning prompting method, a vehicle early warning prompting device, a base station and a storage medium, and belongs to the technical field of intelligent traffic. The method comprises the following steps: the method comprises the steps of obtaining perception data of a road side base station at a curve, wherein the perception data comprise first position information of a first vehicle and second position information of a second vehicle on the curve, and the second vehicle is positioned in front of the running direction of the first vehicle. And determining an arc angle between the first vehicle and the second vehicle according to the curve center coordinate information, the first position information and the second position information of the curve. And if the second vehicle is determined to be the vehicle vision blind area target of the first vehicle according to the radian angle, sending a first early warning prompt message to the first vehicle so as to prompt the first vehicle of the state of the second vehicle. Therefore, the state of the front vehicle can be informed to the rear vehicle in advance, namely, the situation of the blind area of the visual field of the vehicle is informed in advance, so that the driver obtains beyond visual range sensing capability, the driver can drive carefully, and the driving safety at the curve is improved.

Description

Vehicle early warning prompting method, device, base station and storage medium

Technical Field

The application relates to the technical field of intelligent transportation, in particular to a vehicle early warning prompting method, a device, a base station and a storage medium.

Background

The curve is a dangerous road end on the road, and the driver is difficult to find the front vehicle in advance due to the shielding of the view at the curve, so that the vehicle is easy to accident at the curve. For this reason, it is often necessary to give a vehicle warning prompt for a curve. A method generally adopted in the related art is to set up a warning sign at a curve, for example, to set up a warning sign for prompting a driver to run at a reduced speed. However, this approach has poor warning prompt effect on the vehicle, resulting in lower driving safety at the curve.

Disclosure of Invention

The embodiment of the application provides a vehicle early warning prompting method, a device, a base station and a storage medium, which can solve the problem of lower driving safety at a curve in the prior art. The technical scheme is as follows:

in a first aspect, a vehicle early warning prompting method is provided, the method includes:

Acquiring perception data of a road side base station at a curve, wherein the perception data comprises first position information of a first vehicle on the curve and second position information of a second vehicle on the curve, and the second vehicle is positioned in front of the running direction of the first vehicle;

Determining an arc angle between the first vehicle and the second vehicle according to curve center coordinate information of the curve, the first position information and the second position information;

And if the second vehicle is determined to be the vehicle vision blind area target of the first vehicle according to the radian angle, sending a first early warning prompt message to the first vehicle, wherein the first early warning prompt message is used for prompting the state of the second vehicle to the first vehicle.

Therefore, the state of the front vehicle is informed to the rear vehicle in advance, namely, the condition of the blind area of the vehicle vision is informed in advance, so that the driver obtains beyond-vision perception capability, the driver can drive carefully, and the driving safety at the curve is improved.

As an example of the present application, the determining an arc angle between the first vehicle and the second vehicle according to curve center coordinate information of the curve, the first position information, and the second position information includes:

determining a distance between a location at which the first vehicle is located and a location at which the second vehicle is located based on the first location information and the second location information;

Determining a curve circle radius of the curve based on the curve circle center coordinate information and target position information, wherein the target position information is the first position information or the second position information;

an arc angle between the first vehicle and the second vehicle is determined based on the distance and the curve circle radius.

Determining a vector taking the circle center of the curve as a starting point and the position of the first vehicle as an ending point based on the first position information and the curve circle center coordinate information to obtain a first vector;

Determining a vector taking the circle center of the curve as a starting point and the position of the second vehicle as an ending point based on the second position information and the curve circle center coordinate information to obtain a second vector;

An arc angle between the first vehicle and the second vehicle is determined based on the first vector and the second vector.

The above-described determination of the arc angle between the first vehicle and the second vehicle by different methods increases the implementation of determining the arc angle.

As an example of the present application, the perception data includes lidar point cloud data and image data, the method further comprising:

establishing a point cloud image at the curve based on the laser radar point cloud data and the image data to obtain a first point cloud image;

Respectively determining predicted running tracks of each vehicle perceived by the road side base station in the first point cloud image to obtain a plurality of predicted running tracks, wherein any one of the predicted running tracks comprises predicted frames of the corresponding vehicle at different future time points;

And when the vehicles perceived by the road side base station include the vehicles with collision risks according to the predicted running tracks, carrying out early warning prompt on the vehicles with collision risks.

In this way, under the condition that the vehicles with collision risk exist in the plurality of vehicles, early warning prompt is carried out on the vehicles with collision risk, for example, a third early warning prompt message is sent to the vehicles with collision risk so as to remind the vehicles possibly suffering from collision, and the vehicles with collision risk enter the warning state in advance, so that the accident occurrence rate is reduced, and the occurrence rate of safety accidents can be reduced.

As an example of the present application, the determining, separately, a predicted travel track of each vehicle perceived by the road side base station in the first cloud image includes:

For any vehicle perceived by the road base station, determining a running track of the any vehicle in a future time period through a target nonlinear motion prediction model based on the position information and the speed of the any vehicle;

and generating a prediction frame of any vehicle at different time points on the determined running track based on the size information of any vehicle to obtain the predicted running track of any vehicle.

In this way, the running track of the vehicle is determined by the target nonlinear motion prediction model, and a prediction frame is generated in the running track according to the size information, so that whether the vehicle has collision risk can be accurately judged according to the predicted running track.

As an example of the present application, the method further comprises:

And determining that a vehicle with collision risk is included in the plurality of vehicles perceived by the road side base station when a first predicted running track intersected with a target line exists in the plurality of predicted running tracks, wherein the target line comprises a second predicted running track of other vehicles perceived by the road side base station and/or a curve boundary of the curve.

In this way, when judging whether there is a vehicle having a collision risk, it is judged whether there is a vehicle that collides with each other and whether there is a vehicle that collides with the curve boundary, so that the effectiveness of collision judgment can be improved in consideration of a plurality of possible collision situations.

As one example of the present application, the determining that the road side base station perceived vehicle includes a vehicle having a collision risk when there is a first predicted travel locus intersecting a target line among the plurality of predicted travel loci includes:

When a first predicted running track intersected with the second predicted running track exists in the plurality of predicted running tracks, determining the continuous collision times and the continuous collision duration of the two corresponding vehicles according to the first predicted running track and the second predicted running track;

determining vehicle collision risk values of the corresponding two vehicles based on the continuous collision times and the collision duration;

And if the vehicle collision risk value is greater than or equal to a first risk value threshold, determining the vehicle corresponding to the first predicted running track and the vehicle corresponding to the second predicted running track as the vehicle with collision risk in the plurality of vehicles.

In this way, under the condition that a first predicted running track intersected with a second predicted running track exists in the plurality of predicted running tracks, a vehicle collision risk value is determined, and whether a vehicle with collision risk exists or not is judged according to the collision risk value, so that erroneous judgment can be reduced, the accuracy of judgment is improved, and the accuracy of early warning prompt is improved.

As an example of the present application, the warning prompt for a vehicle having a collision risk includes:

Determining collision grades according to the vehicle collision risk values, wherein different collision grades correspond to different early warning prompt intensities;

And based on the determined collision grade, carrying out early warning prompt on the vehicle with collision risk through the corresponding early warning prompt strength.

Therefore, the driver can be timely reminded of paying attention to safe driving, and safety accidents can be reduced.

Acquiring a high-precision map of the curve;

Drawing a curved path boundary in the first point cloud image according to the high-precision map to obtain a second point cloud image;

When the plurality of predicted driving tracks in the second point cloud chart comprise a first predicted driving track intersected with the curve boundary, and at least two intersection points exist between the first predicted driving track and the curve boundary, determining a boundary crossing area and a boundary crossing duration, wherein the boundary crossing area is the area of an area formed after the first predicted driving track is intersected with the curve boundary;

Determining a boundary collision risk value based on the out-of-range area, the out-of-range duration, and the speed of the vehicle corresponding to the first predicted travel track;

and if the boundary collision risk value is greater than or equal to a second risk value threshold, determining the vehicle corresponding to the first predicted running track as the vehicle with collision risk in the plurality of vehicles.

Under the condition that a first predicted running track intersected with the curve boundary exists in the plurality of predicted running tracks, determining a curve collision risk value, and judging whether a vehicle with collision risk exists or not according to the curve collision risk value, so that erroneous judgment can be reduced, the accuracy of judgment is improved, and the accuracy of early warning prompt is improved.

As an example of the present application, the first warning message includes second location information and speed of the second vehicle.

Therefore, when the second vehicle is in the blind area of the vehicle vision of the first vehicle, the second position information and the speed of the second vehicle are sent to the first vehicle, so that a driver of the rear vehicle can judge the position and the running speed of the front vehicle in time, a reasonable driving decision is made, and potential safety hazards are avoided.

In a second aspect, a vehicle warning prompt device is provided, the device comprising:

The system comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring perception data of a road side base station at a curve, the perception data comprise first position information of a first vehicle on the curve and second position information of a second vehicle on the curve, and the second vehicle is positioned in front of the running direction of the first vehicle;

the determining module is used for determining an arc angle between the first vehicle and the second vehicle according to curve center coordinate information of the curve, the first position information and the second position information;

And the sending module is used for sending a first early warning prompt message to the first vehicle if the second vehicle is determined to be a vehicle vision blind area target of the first vehicle according to the radian angle, wherein the first early warning prompt message is used for prompting the state of the second vehicle to the first vehicle.

As an example of the present application, the determining module is configured to:

As an example of the present application, the perception data includes lidar point cloud data and image data, and the sending module is further configured to:

As an example of the present application, the transmitting module is configured to:

Acquiring a high-precision map of the curve;

In a third aspect, there is provided a roadside base station comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of any one of the first aspects when executing the computer program.

In a fourth aspect, there is provided a computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the method of any of the first aspects above.

In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform the method of any of the first aspects above.

It will be appreciated that the advantages of the second to fifth aspects may be found in the relevant description of the first aspect, and are not described here again.

The technical scheme provided by the embodiment of the application has the beneficial effects that:

The method comprises the steps of obtaining perception data of a road side base station at a curve, wherein the perception data comprise first position information of a first vehicle at the curve and second position information of a second vehicle at the curve, and the second vehicle is positioned in front of the running direction of the first vehicle. And determining an arc angle between the first vehicle and the second vehicle according to the curve center coordinate information, the first position information and the second position information of the curve. If the second vehicle is determined to be a vehicle vision blind area target of the first vehicle according to the radian angle, the fact that the second vehicle cannot be seen in the vehicle vision range of the first vehicle is indicated, and at the moment, in order to avoid collision, a first early warning prompt message is sent to the first vehicle so as to inform the state of the second vehicle to the first vehicle in advance. Therefore, the state of the front vehicle is informed to the rear vehicle in advance, namely, the condition of the blind area of the vehicle vision is informed in advance, so that the driver obtains beyond-vision perception capability, the driver can drive carefully, and the driving safety at the curve is improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic diagram illustrating a set-up of a roadside base station at a curve, according to an example embodiment;

FIG. 2 is a flow chart illustrating a vehicle warning prompting method according to an exemplary embodiment;

FIG. 3 is a schematic diagram illustrating a positional relationship between a first vehicle and a second vehicle, according to an example embodiment;

fig. 4 is a schematic diagram showing a positional relationship between a first vehicle and a second vehicle according to another exemplary embodiment;

Fig. 5 is a schematic diagram showing a positional relationship between a first vehicle and a second vehicle according to another exemplary embodiment;

FIG. 6 is a flow chart illustrating a vehicle warning prompting method according to another exemplary embodiment;

FIG. 7 is a schematic diagram illustrating a predicted travel path according to an exemplary embodiment;

FIG. 8 is a flow chart illustrating a vehicle warning prompting method according to another exemplary embodiment;

FIG. 9 is a schematic diagram of a vehicle warning presentation device according to an exemplary embodiment;

fig. 10 is a schematic diagram illustrating a structure of a roadside base station according to an exemplary embodiment.

Detailed Description

For the purpose of making the objects, technical solutions and advantages of the present application more apparent, the embodiments of the present application will be described in further detail with reference to the accompanying drawings.

It should be understood that references to "a plurality" in this disclosure refer to two or more. In the description of the present application, "/" means or, unless otherwise indicated, for example, A/B may represent A or B; "and/or" herein is merely an association relationship describing an association object, and means that three relationships may exist, for example, a and/or B may mean: a exists alone, A and B exist together, and B exists alone. In addition, in order to facilitate the clear description of the technical solution of the present application, the words "first", "second", etc. are used to distinguish the same item or similar items having substantially the same function and function. It will be appreciated by those of skill in the art that the words "first," "second," and the like do not limit the amount and order of execution, and that the words "first," "second," and the like do not necessarily differ.

Before describing the vehicle early warning prompting method provided by the embodiment of the application in detail, the application scene and the execution subject related to the embodiment of the application are briefly described.

The method provided by the embodiment of the application is applied to vehicle early warning prompt at the curve. In general, safety accidents are likely to occur at curves (particularly, sharp turns and curves on highways) due to a view obstruction or the like. For this reason, in the embodiment of the present application, the road-side base station is set up at the curve, for example, as shown in fig. 1, the road-side base station may be set up at the outer side of the curve, the number of the road-side base stations may be one or more, and the specific setting positions and the number may be selected according to the actual requirements. And sensing the vehicles running on the curve through the road side base station to obtain sensing data. The state of the vehicle on the curve can be determined based on the perception data, so that whether the potential safety hazard exists or not is judged according to the determined state, and vehicle early warning prompt is carried out under the condition that the potential safety hazard exists is determined.

The road side base station is an important infrastructure for intelligent traffic road cooperation and is a service station integrating sensing, calculating and communication capabilities. In one embodiment, the roadside base station may also be referred to as a smart base station or a roadside fusion awareness system. A sensing device is generally configured in the roadside base station, for example, the sensing device includes an image capturing device, a 3D high-precision laser radar sensor, and the like, the laser radar sensor is used for acquiring laser radar point cloud data, and the image capturing device is used for acquiring image data. The road side base station can accurately sense the road traffic participation object in real time through the sensing equipment so as to accurately sense the sensing data of the traffic participation object in real time. Traffic participant objects may include, but are not limited to, vehicles, pedestrians, non-motor vehicles, trees, among others.

In one embodiment, the method provided by the embodiment of the present application may be performed by a router-side base station. The road side base station and each perceived vehicle can perform data communication so as to perform early warning prompt on a certain vehicle under the condition that the potential safety hazard exists in the certain vehicle.

In another embodiment, the method provided by the embodiment of the application can be further executed by a server. In this case, the server establishes a communication connection with the roadside base station to acquire the perception data from the roadside base station through the communication connection. In addition, the server and each vehicle perceived by the road side base station can perform data communication so as to perform early warning prompt on a certain vehicle under the condition that the potential safety hazard exists in the certain vehicle.

In one embodiment, the server may be one server, or may also be a server cluster composed of a plurality of servers. In one embodiment, the server may be an information service providing end disposed at the roadside (for example, the server may be a unit integrated into the roadside base station), or an information service end disposed at the edge node, or an information service end disposed at the cloud, which is not limited in the embodiment of the present application.

After the application scenario and the execution subject related to the embodiment of the present application are introduced, the vehicle early warning prompting method provided by the embodiment of the present application is described in detail below with reference to the accompanying drawings.

Referring to fig. 2, fig. 2 is a flowchart illustrating a vehicle early warning prompting method according to an exemplary embodiment, and the embodiment is described by using the method performed by the server as an example. The method comprises the following implementation steps:

step 201: the method comprises the steps of acquiring sensing data of a road side base station at a curve, wherein the sensing data comprises first position information of a first vehicle at the curve and second position information of a second vehicle at the curve, and the second vehicle is positioned in front of the first vehicle in the running direction.

The road side base station perceives the vehicles in the perception range to acquire perception data of the vehicles. In one embodiment, the sensing data may include information such as a heading angle of the vehicle, a traveling direction of the vehicle, and the like, in addition to the position information of the vehicle.

As an example of the present application, the first vehicle and the second vehicle are any two vehicles among a plurality of vehicles perceived by the road side base station, and the first vehicle and the second vehicle may travel in opposite directions or may travel in the same direction. In implementation, for each two vehicles in the plurality of vehicles perceived by the road side base station, the determination may be performed according to the method provided by the embodiment of the present application, where the first vehicle and the second vehicle are described as examples.

In one embodiment, the first location information includes coordinate information of the first vehicle and the second location information includes coordinate information of the second vehicle. For example, the first position information is denoted by (x ₁,y₁), and the second position information is denoted by (x ₂,y₂), where the coordinate system may be established according to practical requirements, for example, the position of the road base station may be established as the origin of coordinates, or the center of a curve may be established as the origin of coordinates, which is not limited in the embodiment of the present application.

Step 202: and determining an arc angle between the first vehicle and the second vehicle according to the curve center coordinate information, the first position information and the second position information of the curve.

In one embodiment, the curve center coordinate information may be stored in the road side base station in advance, or may be obtained by sensing by the road side base station. In an implementation, if the curve center coordinate information, the first position information and the second position information are not in the same coordinate system, the curve center coordinate information, the first position information and the second position information are subjected to coordinate conversion so that the curve center coordinate information, the first position information and the second position information are in the same coordinate system. And then, determining an arc angle between the first vehicle and the second vehicle according to the curve center coordinate information, the first position information and the second position information of the curve. As an example of the present application, its specific implementation may include two possible implementations:

The first implementation mode: a distance between a location at which the first vehicle is located and a location at which the second vehicle is located is determined based on the first location information and the second location information. And determining the curve circle radius of the curve based on the curve circle center coordinate information and the target position information, wherein the target position information is the first position information or the second position information. An arc angle between the first vehicle and the second vehicle is determined based on the distance and the curve circle radius.

For example, referring to fig. 3, assuming that the position of the first vehicle is point a, the position of the second vehicle is point B, the first position information corresponding to point a is (x ₁,y₁), and the second position information corresponding to point B is (x ₂,y₂), the distance between point a and point B is determined by the following formula (1):

Where d represents the distance between points A and B.

Taking the target position information as the first position information as an example, determining the radius of the curve circle according to the following formula (2) based on the curve circle center coordinate information and the target position information:

Where r represents the radius of the curve circle and (x ₀,y₀) represents the curve center coordinate information.

Then, based on the distance and the curve circle radius, the radian angle between the first vehicle and the second vehicle is determined by the following formula (3):

where θ represents the arc angle between the first vehicle and the second vehicle.

It should be noted that, when the first vehicle and the second vehicle are not on the same concentric circle, the curve radius determined based on the first position information and the target position information is made not to completely coincide with the curve radius determined based on the second position information and the target position information, but since the error is small in the calculation process, the embodiment of the present application can ignore the error.

The second implementation mode: and determining a vector which takes the circle center of the curve as a starting point and the position of the first vehicle as an ending point on the basis of the first position information and the circle center coordinate information of the curve to obtain a first vector. And determining a vector taking the circle center of the curve as a starting point and the position of the second vehicle as an ending point based on the second position information and the circle center coordinate information of the curve to obtain a second vector. An arc angle between the first vehicle and the second vehicle is determined based on the first vector and the second vector.

For example, referring to fig. 4, assume that the position of the first vehicle is point a, the position of the second vehicle is point B, and the center of the curve is point P. Determining a first vector by the following formula (4) based on the first position information and the curve center coordinate information, and determining a second vector by the following formula (5) based on the second position information and the curve center coordinate information:

Wherein, Representing the first vector,/>Representing a second vector.

Then, based on the first vector and the second vector, an arc angle between the first vehicle and the second vehicle is determined by the following formula (6):

Step 203: and if the second vehicle is determined to be the vehicle vision blind area target of the first vehicle according to the radian angle, sending a first early warning prompt message to the first vehicle, wherein the first early warning prompt message is used for prompting the state of the second vehicle to the first vehicle.

The vehicle vision blind area target refers to a target that is not within the vehicle vision range. For example, if the second vehicle is a blind spot target of the vehicle vision of the first vehicle, it is indicated that the second vehicle is not in the vehicle vision of the first vehicle, that is, the second vehicle is not visible in the vehicle vision of the first vehicle.

As an example of the present application, the specific implementation of determining whether the second vehicle is the vehicle vision blind area target of the first vehicle according to the radian angle may include: and if the radian angle is greater than or equal to the radian angle threshold, determining that the second vehicle is a vehicle vision blind area target of the first vehicle.

The radian angle threshold value can be set according to actual requirements. For example, the arc angle threshold is 45 degrees.

When the radian angle between the first vehicle and the second vehicle is greater than or equal to the radian angle threshold, it is indicated that the second vehicle is difficult to see in the vehicle vision range of the first vehicle, as shown in fig. 5, so that it can be determined that the second vehicle is the vehicle vision blind area target of the first vehicle.

In one embodiment, if the radian angle between the first vehicle and the second vehicle is less than the radian angle threshold, the second vehicle may be considered to be visible in the vehicle horizon of the first vehicle, and thus it may be determined that the second vehicle is not the vehicle horizon blind spot target of the first vehicle.

Of course, the implementation of determining whether the second vehicle is the blind spot target of the first vehicle according to the radian angle is merely exemplary, and in another embodiment, it may also be determined whether the second vehicle is the blind spot target of the first vehicle according to the radian angle in other manners, for example, determining according to the range of the radian angle, etc.

And when the second vehicle is determined to be the vehicle vision blind area target of the first vehicle, sending a first early warning prompt message to the first vehicle to carry out early warning prompt on the first vehicle. Therefore, when the front vehicle is not in the vehicle vision range of the rear vehicle, the state of the front vehicle is informed to the rear vehicle in advance, namely, the situation of the vision blind area of the vehicle is informed in advance, so that the driver obtains the beyond-vision perception capability, and the driver can drive carefully and safely.

In one embodiment, the first warning message includes second location information and a speed of the second vehicle. Therefore, when the second vehicle is in the blind area of the vehicle vision of the first vehicle, the second position information and the speed of the second vehicle are sent to the first vehicle, so that a driver of the rear vehicle can judge the position and the running speed of the front vehicle in time, a reasonable driving decision is made, and potential safety hazards are avoided.

The foregoing description is given by taking the first warning message including the second position information and the speed of the second vehicle as an example. In another embodiment, the first warning message may further include other status information of the second vehicle, such as a heading angle of the second vehicle, which is not limited in the embodiment of the present application.

In one possible implementation, after the first vehicle receives the first early warning prompt message, early warning prompt is performed based on the first early warning prompt message, so as to remind the driver. The early warning prompt method can include but is not limited to text prompt, ringing prompt and vibration prompt. For example, the text may be displayed by the terminal device or the car device, for example, the text may be "a car with a speed xx of 200 meters in front", or may be displayed by the terminal device or the car device.

It will be understood that if the second vehicle is not the blind area target of the vehicle vision of the first vehicle according to the radian angle, the first vehicle is not warned.

In one embodiment, the first vehicle and the second vehicle may be two vehicles traveling in the same direction, or may be two vehicles traveling in opposite directions. When the first vehicle and the second vehicle run in opposite directions, and the second vehicle is determined to be the blind zone target of the vehicle vision of the first vehicle according to the radian angle between the first vehicle and the second vehicle, the first vehicle is also the blind zone target of the vehicle vision of the second vehicle, and at the moment, a second early warning prompt message can be sent to the second vehicle in addition to the first early warning prompt message, and the second early warning prompt message is used for prompting the state of the first vehicle to the second vehicle. The second warning message includes status information of the first vehicle, such as the first vehicle includes first position information and speed of the first vehicle. In this way, both the driver of the first vehicle and the driver of the second vehicle can be brought into the armed state in advance, thereby minimizing the occurrence of a safety accident as much as possible.

In the embodiment of the application, the sensing data of the road side base station at the curve is acquired, wherein the sensing data comprises the first position information of the first vehicle at the curve and the second position information of the second vehicle at the curve, and the second vehicle is positioned in front of the running direction of the first vehicle. And determining an arc angle between the first vehicle and the second vehicle according to the curve center coordinate information, the first position information and the second position information of the curve. If the second vehicle is determined to be a vehicle vision blind area target of the first vehicle according to the radian angle, the fact that the second vehicle cannot be seen in the vehicle vision range of the first vehicle is indicated, and at the moment, in order to avoid collision, a first early warning prompt message is sent to the first vehicle so as to inform the state of the second vehicle to the first vehicle in advance. Therefore, the state of the front vehicle is informed to the rear vehicle in advance, namely, the condition of the blind area of the vehicle vision is informed in advance, so that the driver obtains beyond-vision perception capability, the driver can drive carefully, and the driving safety at the curve is improved.

Referring to fig. 6, fig. 6 is a flowchart illustrating a vehicle early warning prompting method according to another exemplary embodiment, which is described by taking the method performed by a road side base station as an example, the method may include some or all of the following:

specific implementations of steps 601 to 603 may refer to steps 201 to 203, and the detailed description thereof will not be repeated here.

Step 604: and establishing a point cloud image at the curve based on the laser radar point cloud data and the image data to obtain a first point cloud image.

In the embodiment of the application, the laser radar point cloud data is detected by a laser radar sensor in the road side base station, and the image data is shot by an imaging device in the road side base station. That is, the perception data of the road side base station may further include laser radar point cloud data and image data, and a first point cloud image is established based on the laser radar point cloud data and the image data, wherein the first point cloud image includes each vehicle perceived by the road side base station.

As an example of the present application, in order to ensure the richness and accuracy of the relevant information of the vehicle perceived by the road side base station, and in order to facilitate the subsequent tracking and prediction of the vehicle, fusion processing may be performed based on the lidar point cloud data and the image data. For this purpose, the lidar point cloud data and the image data may be preprocessed separately.

For example, the laser radar point cloud data is preprocessed by a deep learning method to determine information such as position information, course angle, speed, size information and the like of traffic participation objects perceived by a road side base station. The deep learning method can be performed by adopting LaserNet: AN EFFICIENT Probabilitic 3D Object Detector for Autonomous Driving.

By way of example, the image data is preprocessed by the deep learning method, and characteristic information of the vehicle perceived by the road side base station, for example, the characteristic information including information of the color, the type, and the like of the vehicle, can be determined.

And then, fusion processing is carried out on the basis of the data obtained after preprocessing so as to be convenient for correcting and supplementing the information of the vehicle, for example, the laser radar point cloud data can be corrected through fusion on the basis of the image data.

Illustratively, the fusion may be performed by the following equation (7):

Wherein s represents scale factors, alpha and beta represent pixel values, f _x、f_y、c_x、c_y are internal parameters of the image pickup device, For three-dimensional conversion relation, can be determined in advance through camera calibration,/>Is the actual physical coordinates of the target.

Step 605: and respectively determining the predicted running tracks of each vehicle perceived by the road side base station in the first point cloud image to obtain a plurality of predicted running tracks, wherein any one of the predicted running tracks comprises a predicted frame of the corresponding vehicle at different future time points.

As an example, a specific implementation of determining predicted travel tracks of respective vehicles perceived by the road side base station in the first point cloud image may include: for any vehicle perceived by the road side base station, determining the running track of the any vehicle in a future time period through the target nonlinear motion prediction model based on the position information and the speed of the any vehicle. And generating a prediction frame of any vehicle at different time points on the determined running track based on the size information of any vehicle to obtain the predicted running track of any vehicle.

The specific duration of the future time period may be set according to actual requirements, for example, the future time period may be within 5 seconds of the future, and for example, may also be within 10 seconds of the future. If the image capturing rate of the image capturing apparatus is 10 frames/second, the predicted travel locus in the future period is referred to as a predicted travel locus of 50 frames in the future, assuming that the future period is within 5 seconds in the future.

Since the vehicle makes a curved motion on a curve, tracking and nonlinear motion prediction can be performed using a target nonlinear motion prediction model to determine the travel track of the vehicle in a future period of time. In one embodiment, the target nonlinear motion prediction model may employ an extended kalman CTRV (Constant Turn Rate And Velocity Magnitude, fixed speed and velocity size) model. Illustratively, the state transfer function of the extended kalman CTRV model is shown in equations (8) and (9):

/>

Wherein, Is a state quantity, t represents time, Δt represents time interval of the previous and subsequent frames, ω is angular velocity,/>For the heading angle of the vehicle, v denotes the speed of the vehicle, x (t) denotes the abscissa in the position information, and y (t) denotes the ordinate in the position information.

In addition, the prediction function and update equation of the extended kalman CTRV model are shown in formulas (10) and (11), respectively:

x_k+1＝g(x_k,μ) (10)

where x _k represents a kth state quantity, x _k+1 represents a k+1th state quantity, a time difference between the k+1th state quantity and the kth state quantity is Δt, and μ is an external input quantity. P _k+1 represents the (k+1) th output, P _k represents the (k) th output, J _A is a state transition matrix, Transpose of the state transition matrix, Q is uncertainty. The prediction function is used to iterate the state quantity and the update equation is used to update the output result.

After the running track of any vehicle in a future time period is determined through the target nonlinear motion prediction model, the size of a prediction frame of any vehicle is determined according to the size information of any vehicle, so that the prediction frames of any vehicle with the corresponding size are generated at different time points on the running track, and the predicted running track of any vehicle is obtained. For example, the predicted travel locus of any one of the vehicles is shown in fig. 7.

According to the method, the predicted running tracks of the vehicles perceived by the road side base station can be determined, and a plurality of predicted running tracks can be obtained.

The above description is given taking, as an example, a prediction frame of any one vehicle generated based on size information of any one vehicle. In another embodiment, the type of any vehicle may also be determined, after which a prediction box for any vehicle is generated based on the size information and type of any vehicle.

Step 606: and when the vehicles perceived by the road side base station comprise the vehicles with collision risks according to the plurality of predicted running tracks, carrying out early warning prompt on the vehicles with collision risks.

As an example, determining whether a vehicle perceived by the roadside base station includes a vehicle having a collision risk according to a plurality of predicted travel tracks may include: when a first predicted travel track intersecting a target line is present in the plurality of predicted travel tracks, a vehicle having a collision risk is included in the plurality of vehicles perceived by the road side base station, wherein the target line includes a second predicted travel track of other vehicles perceived by the road side base station and/or a curve boundary of a curve.

That is, when it is determined that there is a vehicle that may collide with another vehicle among the plurality of vehicles perceived by the road side base station based on the plurality of predicted travel tracks, it is determined that the vehicle having a risk of collision is included among the plurality of vehicles. Or when it is determined that there is a vehicle that may collide with the curve boundary among the plurality of vehicles perceived by the road side base station from the plurality of predicted travel tracks, it is determined that the plurality of vehicles include a vehicle having a collision risk. And further or when it is determined that there is a vehicle that may collide with another vehicle among the plurality of vehicles perceived by the road side base station according to the plurality of predicted travel tracks and there is a vehicle that may collide with the curve boundary, it is determined that the plurality of vehicles include vehicles having a collision risk, and it is easy to understand that the number of vehicles having a collision risk is greater than or equal to 2 at this time.

In one embodiment, determining whether a collision with another vehicle may include: when a first predicted running track intersected with a second predicted running track exists in the plurality of predicted running tracks, the continuous collision times and the continuous collision duration of the two corresponding vehicles are determined according to the first predicted running track and the second predicted running track. Based on the number of consecutive collisions and the duration of the collision, a vehicle collision risk value for the corresponding two vehicles is determined. And if the vehicle collision risk value is greater than or equal to the first risk value threshold, determining the vehicle corresponding to the first predicted running track and the vehicle corresponding to the second predicted running track as the vehicle with collision risk in the plurality of vehicles perceived by the road side base station.

The first risk value threshold may be set by the user according to the actual requirement, or may be set by default by the router side base station, which is not limited in the embodiment of the present application.

Since the first predicted travel track includes the predicted frame of the corresponding vehicle and the second predicted travel track includes the predicted frame of the corresponding vehicle, the number of consecutive collisions can be determined based on the number of overlaps of the predicted frames in the two predicted travel tracks. In addition, for a plurality of prediction frames that overlap consecutively, the number of prediction frames between the first and last prediction frames may be determined from the first and last prediction frames, so that the collision duration may be determined from the determined number, for example, if the number of prediction frames between the two is 7, the collision duration may be determined to be 7 seconds.

Then, different weights may be set for the number of consecutive collisions and the collision duration, respectively, and the vehicle collision risk values for the two vehicles may be determined by a weighted sum operation. If the vehicle collision risk value is greater than or equal to the first risk value threshold value, which indicates that there is a high possibility that two vehicles collide, the two vehicles can be determined as vehicles having collision risk among the vehicles perceived by the road side base station. As an example, if the vehicle collision risk value is less than the first risk value threshold, it is indicated that the probability of collision of two vehicles is small, and the two vehicles may not be determined to be vehicles having collision risk among the vehicles perceived by the road side base station.

It is worth mentioning that, above-mentioned in a plurality of prediction travel track have with the first prediction travel track of crossing of second prediction travel track under the condition, confirm the vehicle collision risk value to judge whether there is the vehicle that has the collision risk according to the vehicle collision risk value, so can reduce the erroneous judgement, improved the accuracy of judgement, thereby improved the accuracy of early warning suggestion.

The above description is made taking as an example whether or not the corresponding vehicle is a vehicle having a collision risk, by determining a vehicle collision risk value and determining the vehicle collision risk value. In another embodiment, when there is a first predicted travel track intersecting with a second predicted travel track among the plurality of predicted travel tracks, it may be determined that the vehicle corresponding to the first predicted travel track and the vehicle corresponding to the second predicted travel track are vehicles having a risk of collision, that is, as long as there is an intersecting predicted travel track among the plurality of predicted travel tracks, it may be determined that there is a vehicle having a risk of collision.

In another embodiment, the specific implementation of determining whether a collision with a curve boundary may include: and obtaining a high-precision map of the curve. And drawing a curved path boundary in the first point cloud image according to the high-precision map to obtain a second point cloud image. When the plurality of predicted running tracks in the second point cloud image comprise first predicted running tracks intersected with the curve boundary, and at least two intersection points exist between the first predicted running tracks and the curve boundary, determining the area of the out-of-range area and the out-of-range duration, wherein the out-of-range area refers to the area of an area formed after the first predicted running tracks are intersected with the curve boundary. And determining a boundary collision risk value based on the area of the out-of-range region, the out-of-range duration and the speed of the vehicle corresponding to the first predicted driving track. And if the boundary collision risk value is greater than or equal to the second risk value threshold, determining the vehicle corresponding to the first predicted running track as a vehicle with collision risk in the plurality of vehicles.

The second risk value threshold may be set by the user according to actual requirements, or may be set by default by the router base station. The second risk value threshold may be the same as or different from the first risk value threshold, which is not limited in the embodiment of the present application.

The high-definition map of a curve includes detailed information of the curve, such as boundary line information of the curve, lane line information of the curve, and the like. Therefore, the high-precision map of the curve is fused with the first point cloud image, so that the curve boundary of the curve is drawn in the first point cloud image, and the second point cloud image is obtained. And judging whether vehicles with collision risk with the curve boundary exist in the vehicles perceived by the road side base station or not based on the second point cloud image. In implementation, whether a first predicted running track intersecting the curve boundary exists in the second point cloud chart is judged (for convenience of description and understanding, the predicted running track intersecting the curve boundary is called a first predicted running track in this embodiment), if the first predicted running track exists, the number of intersection points of the first predicted running track and the curve boundary is judged, when the number of intersection points is multiple, as shown in fig. 8, the number of intersection points is two, and then the area of the area formed after the first predicted running track intersects the curve boundary is determined, so as to obtain the out-of-range area. In addition, the duration between the two intersection points is judged, and the out-of-range duration is obtained. Then, different weights can be set for the area of the out-of-range area, the out-of-range duration and the speed of the vehicle corresponding to the first predicted driving track respectively, and the boundary collision risk value can be determined in a weighted summation mode.

When the boundary collision risk value is greater than or equal to the second risk value threshold, it is indicated that the collision probability between the vehicle corresponding to the first predicted running track and the curve boundary is greater, or that the vehicle corresponding to the first predicted running track is most likely to have a boundary crossing behavior with the curve boundary during running, in which case the vehicle corresponding to the first predicted running track may be determined to be a vehicle having a collision risk.

As one example of the present application, when the collision risk value is smaller than the second risk value threshold value, it may be determined that the collision probability between the vehicle corresponding to the first predicted travel locus and the curve boundary is small, at which time the vehicle corresponding to the first predicted travel locus may not be determined as the vehicle having the collision risk.

As an example of the present application, for any one of a plurality of predicted travel tracks, if there is only one intersection point of any one predicted travel track with a curve boundary, it may be determined that the vehicle corresponding to the any one predicted travel track is not a vehicle having a collision risk.

The above description is given by taking the example of determining the boundary collision risk value and judging whether there is a collision risk with the boundary according to the boundary collision risk value. In another embodiment, it may also be determined whether there is a collision risk between the vehicle and the curve boundary in other manners, for example, when the first predicted driving track has an intersection with the curve boundary and a continuous period of time (for example, 5 frames) of out-of-range behavior occurs, the boundary collision risk value is determined, and whether out-of-range behavior occurs with the curve boundary is determined according to the boundary collision risk value, so as to determine whether there is a vehicle with a collision risk in the plurality of vehicles. For another example, when an intersection exists between a predicted driving track of a certain vehicle and a curve boundary, it may be determined that the vehicle is a vehicle having a collision risk among a plurality of vehicles, and the embodiment of the present application is not limited thereto.

Under the condition that the vehicles with collision risk exist in the plurality of vehicles, early warning prompt is carried out on the vehicles with collision risk, for example, a third early warning prompt message is sent to the vehicles with collision risk so as to remind the vehicles possibly suffering from collision, and the vehicles with collision risk enter a warning state in advance, so that the accident rate is reduced, and the occurrence of safety accidents can be reduced.

As an example, the third early warning message may include a collision risk type, for example, the collision risk type may include a vehicle collision type, which is determined to be likely to collide with other vehicles through the above process, and a curve boundary collision type, which is determined to be likely to collide with a curve boundary through the above process.

In one embodiment, when the vehicle with collision risk is likely to collide with other vehicles, the third warning prompt message may further include state information of other vehicles with collision risk, such as one or more of position information, speed and course angle of the other vehicles.

As an example of the present application, taking a collision between vehicles as an example, when there is a collision between vehicles among a plurality of vehicles, a specific implementation of an early warning prompt for a vehicle having a collision risk may include: and determining collision grades according to the collision risk values of the vehicles, wherein different collision grades correspond to different early warning prompt intensities. And based on the determined collision grade, carrying out early warning prompt on the vehicle with collision risk through the corresponding early warning prompt strength.

As one example, the higher the collision level, the stronger the warning intensity. In some cases, when the collision risk value of the vehicle is larger, the probability of the collision is larger or the collision occurs faster, and then high-intensity early warning prompt such as continuous ringing and the like can be performed. Therefore, the driver can be timely reminded of paying attention to safe driving, and the occurrence of safety accidents can be reduced.

It should be noted that, the steps 604 to 606 and the steps 601 to 603 are not sequentially performed, that is, the steps 604 to 606 may be performed before the steps 601 to 603, or may be performed after the steps 601 to 603, or may be performed in parallel with the steps 601 to 603. For ease of understanding, the implementation flow is described below by taking fig. 8 as an example:

The road side base station detects the vehicle through the laser radar sensor to obtain laser radar point cloud data, and shoots the vehicle through the camera equipment to obtain image data. Preprocessing laser radar point cloud data to obtain position information, speed, size information and course angle of the vehicle, and preprocessing image data to obtain category, color and vehicle type information of the vehicle. And fusing the information obtained after the two pretreatment. On the one hand, based on the position information in the fused information, the radian angle between every two vehicles is determined, and when the vehicle in front is determined to be a vehicle vision blind area target of the vehicle in back according to the radian angle, early warning prompt is carried out. On the other hand, based on the position information and the speed in the fused information, the predicted travel locus of each vehicle is determined, and whether or not the vehicle has a collision risk is determined based on the predicted travel locus of each vehicle. When the vehicle with collision risk is determined to exist, judging the collision grade, and carrying out early warning prompt of corresponding intensity according to the collision grade.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of the processes should be determined by the functions and internal logic, and should not be construed as limiting the implementation process of the embodiments of the present application.

Fig. 9 is a schematic structural diagram of a vehicle early warning prompting device according to an exemplary embodiment, and the device may be implemented as the above-mentioned roadside base station by software, hardware or a combination of both. The apparatus may include:

an acquisition module 910, configured to acquire perception data of a road-side base station at a curve, where the perception data includes first location information of a first vehicle on the curve and second location information of a second vehicle on the curve, and the second vehicle is located in front of a traveling direction of the first vehicle;

A determining module 920, configured to determine an arc angle between the first vehicle and the second vehicle according to curve center coordinate information of the curve, the first position information, and the second position information;

And the sending module 930 is configured to send a first early warning prompt message to the first vehicle if the second vehicle is determined to be the blind area target of the vehicle vision of the first vehicle according to the radian angle, where the first early warning prompt message is used to prompt the first vehicle of the state of the second vehicle.

As an example of the present application, the determining module 920 is configured to:

As an example of the present application, the sending module 930 is configured to:

Acquiring a high-precision map of the curve;

Fig. 10 is a schematic structural diagram of an electronic device according to an embodiment of the present application. As shown in fig. 10, the roadside base station 100 of this embodiment includes: at least one processor 1010 (only one shown in fig. 10), a memory 1020, and a computer program 1030 stored in the memory 1020 and executable on the at least one processor 1010, the processor 1010 implementing the steps in any of the various method embodiments described above when executing the computer program 1030.

The road base station 100 may be a desktop computer, a notebook computer, a palm computer, a cloud server, or other computing devices. The electronic device may include, but is not limited to, a processor 1010, a memory 1020. It will be appreciated by those skilled in the art that fig. 10 is merely an example of a roadside base station 100 and is not meant to be limiting as to the roadside base station 100, and may include more or fewer components than shown, or may combine certain components, or different components, such as may also include input-output devices, network access devices, etc.

The Processor 1010 may be a CPU (Central Processing Unit ), the Processor 1010 may also be other general purpose processors, DSPs (DIGITAL SIGNAL processors), ASICs (Application SPECIFIC INTEGRATED circuits), FPGAs (Field-Programmable GATE ARRAY), or other Programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

The memory 1020 may be an internal storage unit of the roadside base station 100 in some embodiments, such as a hard disk or a memory of the roadside base station 100. The memory 1020 may also be an external storage device of the roadside base station 100 in other embodiments, for example, a plug-in hard disk, SMC (SMART MEDIA CARD, smart memory card), SD (Secure Digital) card, flash memory card (FLASH CARD) or the like, which are equipped on the roadside base station 100. Further, the memory 1020 may also include both an internal storage unit and an external storage device of the roadside base station 100. The memory 1020 is used to store an operating system, application programs, boot loader (BootLoader), data, and other programs, such as program code for the computer program. The memory 1020 may also be used to temporarily store data that has been output or is to be output.

It should be noted that, because the content of information interaction and execution process between the above devices/units is based on the same concept as the method embodiment of the present application, specific functions and technical effects thereof may be referred to in the method embodiment section, and will not be described herein.

It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions. The functional units and modules in the embodiment may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of a software functional unit. In addition, the specific names of the functional units and modules are only for distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working process of the units and modules in the above system may refer to the corresponding process in the foregoing method embodiment, which is not described herein again.

The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; although the application has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present application, and are intended to be included in the scope of the present application.

Claims

1. A vehicle warning prompting method, characterized in that the method comprises:

determining an arc angle between the first vehicle and the second vehicle according to curve center coordinate information, the first position information and the second position information of the curve, wherein the arc angle is a center angle of an arc pair between a position point where the first vehicle is located and a position point where the second vehicle is located;

if the radian angle is greater than or equal to a radian angle threshold, determining that the second vehicle is a vehicle vision blind area target of the first vehicle;

A first early warning prompt message is sent to the first vehicle, and the first early warning prompt message is used for prompting the state of the second vehicle to the first vehicle;

The determining the radian angle between the first vehicle and the second vehicle according to the curve center coordinate information of the curve, the first position information and the second position information comprises the following steps:

2. The method of claim 1, wherein the determining an arc angle between the first vehicle and the second vehicle based on the curve center coordinate information, the first position information, and the second position information of the curve further comprises:

3. The method of claim 1, wherein the perception data comprises lidar point cloud data and image data, the method further comprising:

4. The method of claim 3, wherein said separately determining predicted travel trajectories in said first cloud pattern for each vehicle perceived by said road side base station comprises:

5. The method of claim 3 or 4, wherein the method further comprises:

6. The method of claim 5, wherein determining that the road side base station perceived vehicle comprises a vehicle having a collision risk when there is a first predicted travel trajectory intersecting a target line among the plurality of predicted travel trajectories comprises:

7. The method of claim 6, wherein the warning of the vehicle at risk of collision comprises:

8. The method of claim 5, wherein determining that the road side base station perceived vehicle comprises a vehicle having a collision risk when there is a first predicted travel trajectory intersecting a target line among the plurality of predicted travel trajectories comprises:

Acquiring a high-precision map of the curve;

9. The method of any of claims 1-8, wherein the first warning message includes second location information and speed of the second vehicle.

10. A vehicle warning cue device, the device comprising:

The determining module is used for determining an radian angle between the first vehicle and the second vehicle according to curve circle center coordinate information, the first position information and the second position information of the curve, wherein the radian angle is a circle center angle of an arc pair between a position point where the first vehicle is located and a position point where the second vehicle is located;

The sending module is used for determining that the second vehicle is a vehicle vision blind area target of the first vehicle if the radian angle is greater than or equal to a radian angle threshold value; a first early warning prompt message is sent to the first vehicle, and the first early warning prompt message is used for prompting the state of the second vehicle to the first vehicle;

The determining module is configured to determine an arc angle between the first vehicle and the second vehicle according to curve center coordinate information of the curve, the first position information, and the second position information, and includes:

11. A roadside base station comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any one of claims 1 to 9 when executing the computer program.

12. A computer readable storage medium having instructions stored thereon, which when executed by a processor, implement the steps of the method of any of claims 1 to 9.