Behavior prediction method and device, computer equipment, storage medium and program product

Abstract

The invention relates to a behavior prediction method and device, computer equipment, a storage medium and a program product, and the method comprises the steps: determining a target driving region according to the position information of a target subject and the information of a pedestrian crossing corresponding to the target subject; determining relative position information of the target main body and the target driving area; and predicting the behavior of the target subject according to the relative position information and the motion information of the target subject. By using the behavior prediction method provided by the invention, the future behavior of the target subject can be predicted more accurately.

Description

Technical Field

[0001] The present application relates to the technical field of vehicle driving, and particularly to a behavior prediction method, device, computer device, storage medium, and program product. Background Art

[0002] With the rapid development of vehicle intelligence, the use of autonomous driving systems in the automotive field is becoming increasingly widespread. The autonomous driving system can automatically obtain the environmental information around the vehicle to predict the autonomous driving intention and trajectory. For example, it can predict the future behavior of road traffic participants based on the environmental information around the vehicle, so as to predict the autonomous driving intention and trajectory.

[0003] In traditional technologies, during the process of predicting the behavior of traffic participants, relevant characteristics of traffic participants are usually obtained, such as: the speed and acceleration of traffic participants, the distance between traffic participants and the autonomous driving vehicle, and the speed of the autonomous driving vehicle, etc. The future behavior of traffic participants is predicted using the obtained relevant characteristics. However, the characteristics obtained using traditional technologies cannot accurately predict the future behavior of traffic participants. Summary of the Invention

[0004] Based on this, it is necessary to provide a behavior prediction method, device, computer device, storage medium, and program product that can accurately predict the future behavior of traffic participants for the above technical problems.

[0005] In a first aspect, the present application provides a behavior prediction method, which includes:

[0006] Determine a target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity;

[0007] Determine the relative position information between the target entity and the target driving area;

[0008] Predict the behavior of the target entity according to the relative position information and the motion information of the target entity.

[0009] In a second aspect, the present application further provides a behavior prediction device, which includes:

[0010] An area determination module, configured to determine a target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity;

[0011] An information determination module, configured to determine the relative position information between the target entity and the target driving area;

[0012] A prediction module, configured to predict the behavior of the target entity according to the relative position information and the motion information of the target entity.

[0013] In a third aspect, the present application further provides a computer device, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps of the method provided in the first aspect are implemented.

[0014] In a fourth aspect, the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0015] In a fifth aspect, the present application further provides a computer program product, including a computer program. When the computer program is executed by a processor, the steps of the method provided in the first aspect are implemented.

[0016] For the above behavior prediction method, device, computer device, storage medium, and program product, the method determines a target driving area according to the position information of the target subject and the information of the crosswalk corresponding to the target subject; determines the relative position information between the target subject and the target driving area; and predicts the behavior of the target subject according to the relative position information and the motion information of the target subject. In this embodiment, by determining the relative position information between the target subject and the target driving area, the geometric relationship between the target subject and the surrounding environmental information, that is, the target driving area, can be better expressed. Therefore, according to the relative position information and the motion information of the target subject, the behavior of the target subject in a future period of time can be accurately predicted. Moreover, according to the prediction result of the behavior of the target subject, the intention and trajectory of the driving vehicle can be predicted more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a schematic diagram of the application environment of the behavior prediction method in an embodiment;

[0018] Figure 2 It is a schematic diagram of the step flow of the behavior prediction method in an embodiment;

[0019] Figure 3 It is a schematic diagram of a crosswalk in an embodiment;

[0020] Figure 4 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0021] Figure 5 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0022] Figure 6 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0023] Figure 7 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0024] Figure 8 It is a schematic diagram of the driving area at an intersection in an embodiment;

[0025] Figure 9 It is a schematic diagram of the driving area in an embodiment;

[0026] Figure 10 It is a schematic diagram of the driving area outside an intersection in an embodiment;

[0027] Figure 11 It is a schematic diagram of the relative position information between the target entity and the target driving area in an embodiment;

[0028] Figure 12 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0029] Figure 13 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0030] Figure 14 It is a schematic diagram of the step flow of the behavior prediction method in another embodiment;

[0031] Figure 15 It is a schematic diagram of the relative information between the target entity and the crosswalk in an embodiment;

[0032] Figure 16 It is a schematic diagram of the relative information between the target entity and the crosswalk in another embodiment;

[0033] Figure 17 It is a schematic diagram of the structure of the behavior prediction device in an embodiment;

[0034] Figure 18 It is the internal structure diagram of a computer device in an embodiment. Detailed implementation manners

[0035] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0036] The serial numbers assigned to the components herein, such as "first", "second", etc., are only used to distinguish the described objects and do not have any sequential or technical meanings.

[0037] First, before specifically introducing the technical solutions of the disclosed embodiments of the present application, the background technology or the technical evolution context based on which the embodiments of the present application are described will be introduced. With the rapid development of vehicle intelligence, the use of autonomous driving systems in the automotive field is becoming increasingly widespread. The autonomous driving system can automatically obtain the environmental information around the driving vehicle to predict the autonomous driving intention and trajectory. For example, the autonomous driving system predicts the future behavior of traffic participants based on the environmental information of the driving vehicle, so as to predict the autonomous driving intention and trajectory. Traffic participants include pedestrians, motor vehicles or non-motor vehicles (bicycles). In order to accurately predict the future behavior of traffic participants, it is necessary to obtain not only the historical behavior and current behavior of the traffic participants themselves, but also the information of the traffic participants and the surrounding environment. For example, when a traffic participant passes through the crosswalk at an intersection, it is necessary to obtain the geometric relationship between the traffic participant and the crosswalk. In the traditional technology, in the process of predicting the behavior of traffic participants, relevant characteristics of the traffic participants are usually obtained, such as: the speed and acceleration of the traffic participant, the distance between the traffic participant and the driving vehicle, the moving speed of the traffic participant perpendicular to the driving lane, the Euclidean distance between the traffic participant and the crosswalk, the distance between the traffic participant and the nearby lanes, etc. The future behavior of the traffic participant is predicted using the obtained relevant characteristics. However, the relevant characteristics of the traffic participant obtained by the traditional technology cannot accurately express the geometric relationship between the predicted traffic participant and the crosswalk, as well as the future behavior (characterizing behavior) of the traffic participant. For example, whether the traffic participant has just arrived at the crosswalk, or is about to leave the crosswalk, whether the traffic participant has left the crosswalk, or there is still a certain distance before entering the crosswalk, etc., so that the future behavior of the traffic participant cannot be accurately predicted, and thus the driving intention and trajectory of the driving vehicle cannot be accurately predicted. In response to this, the present application provides a behavior prediction method.

[0038] The following will specifically describe the technical solutions of the present application and how the technical solutions of the present application solve the technical problems with specific embodiments.

[0039] The behavior prediction method provided by the present application can be applied to, for example Figure 1In the system architecture shown, the system architecture includes an in-vehicle terminal 101 and an external terminal 102. The in-vehicle terminal 101 can be an autonomous driving system for driving a vehicle or an electronic device installed on the driving vehicle, etc. The external terminal 102 can be a computer device, a tablet computer, a server, etc. The in-vehicle terminal 101 is provided with a communication component, which can communicate with the external terminal 102 wirelessly. The behavior prediction method provided by the present application can be executed using the in-vehicle terminal 101, or can be executed using the external terminal 102, or can also be executed through the interaction between the in-vehicle terminal 101 and the external terminal 102.

[0040] In one embodiment, as Figure 2 shown, a behavior prediction method is provided. In this embodiment, an example is given where this method is applied to an in-vehicle terminal. In this embodiment, the method includes the following steps:

[0041] Step 200: Determine a target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity.

[0042] The target entity refers to a traffic participant of the driving vehicle corresponding to the in-vehicle terminal, that is, during the driving process of the driving vehicle, pedestrians, other motor vehicles, non-motor vehicles, etc. that have an interaction with the driving vehicle. The crosswalk corresponding to the target entity can refer to the crosswalk that the target entity is about to enter, or the crosswalk where the target entity is located, or the crosswalk that the target entity has left. The information of the crosswalk can include the shape of the crosswalk, the center line of the crosswalk, etc. The target driving area refers to the area where the driving vehicle can drive, and can include the crosswalk area and the lane area where the driving vehicle is driving. The position information of the target entity can refer to the coordinate value of the target entity in the world coordinate system.

[0043] Various sensors are installed in the driving vehicle, such as cameras, lidars, millimeter-wave radars, etc. Each sensor can collect data of the target entity and transmit the collected data to the in-vehicle terminal. After the in-vehicle terminal receives the data of the target entity collected by each sensor, it determines the position information of the target entity according to the data.

[0044] After the in-vehicle terminal determines the position information of the target entity, it can determine the crosswalk corresponding to the target entity according to the position information of the target entity.

[0045] In an optional embodiment, a map system is integrated in the vehicle terminal, and the vehicle terminal can determine the crosswalk corresponding to the target subject in the map system according to the location information of the target subject. Alternatively, a map system is included in the external terminal, and the vehicle terminal sends the location information of the target subject to the external terminal through a communication component, and the external terminal determines the crosswalk corresponding to the target subject according to the received location information of the target subject, and transmits the information of the crosswalk corresponding to the target subject to the vehicle terminal.

[0046] In an optional embodiment, the method for determining the information of a crosswalk by a vehicle-mounted terminal or an external terminal may include: obtaining an image of a crosswalk corresponding to the target subject from a map system according to the location information of the target subject; outlining the border of the crosswalk according to the image of the crosswalk, that is, outlining along the boundary of the crosswalk in the image of the crosswalk to obtain the border of the crosswalk; determining the shape of the crosswalk according to the shape of the border of the crosswalk; if the shape of the crosswalk is a rectangle, obtaining two midpoints corresponding to two short sides of the rectangle, and determining the line connecting the two midpoints as the center line of the crosswalk; if the shape of the crosswalk is an irregular polygon, estimating the center line of the crosswalk according to the border of the crosswalk. The vehicle-mounted terminal may estimate the center line of the crosswalk according to a relevant algorithm, such as principal component analysis, or may determine the center line of the crosswalk according to a pre-trained estimation model.

[0047] When the pedestrian crossing is rectangular, the pedestrian crossing obtained by the vehicle terminal is as follows Figure 3 As shown, the outermost rectangular frame of the crosswalk is the border of the crosswalk, and the center line of the rectangular frame is the center line of the crosswalk.

[0048] After determining the location information of the target subject and the information of the crosswalk corresponding to the target subject, the vehicle-mounted terminal determines the area where the driving vehicle interacting with the target subject can travel, i.e., the target driving area, based on the location information of the target location and the information of the crosswalk. In other words, the area of ​​the crosswalk where the driving vehicle may travel (the entire area of ​​the crosswalk or a part of the crosswalk) and the area where the lane where the driving vehicle is traveling (a part of the lane where the driving vehicle is traveling) are determined during the interaction between the target subject and the driving vehicle.

[0049] Step 210: Determine the relative position information between the target subject and the target driving area.

[0050] After determining the target driving area and the position information of the target entity, the in-vehicle terminal can determine the relative position information of the target entity and the target driving area based on the position information of the target entity and the target driving area. That is to say, it can determine at least one of the following: whether the target entity is within the target driving area or outside the target driving area, whether the target entity is about to enter the target driving area or has left the target driving area, and when the target entity is within the target driving area, the position of the target entity within the target driving area.

[0051] Step 220: Predict the behavior of the target entity based on the relative position information and the motion information of the target entity.

[0052] The motion information of the target entity may include the driving speed of the target entity, the driving direction of the target entity, and the driving acceleration of the target entity, etc. The motion information of the target entity can be calculated from the data collected by various sensors installed on the driving vehicle. This embodiment does not limit the specific method for obtaining the motion information of the target entity, as long as its function can be realized.

[0053] After determining the relative position information of the target entity and the target driving area, the in-vehicle terminal predicts the behavior of the target entity based on the relative position information and the motion information of the target entity, that is, predicts the behavior of the target entity in the next time period. For example, predict whether the target entity will continue to drive or stop in the next time period; when the target entity continues to drive, predict whether the target entity will continue to drive at the speed of the current time period, or accelerate or decelerate. This embodiment does not limit the specific method for predicting the behavior of the target entity based on the relative position information and the motion information of the target entity, as long as its function can be realized.

[0054] In an alternative embodiment, the in-vehicle terminal includes a pre-trained first neural network model for predicting the behavior of traffic participants. By inputting the relative position information and the motion information of the target entity into the first neural network model, and performing prediction through the first neural network model, the behavior of the target entity in the next time period is obtained.

[0055] In an alternative embodiment, the in-vehicle terminal includes a pre-trained second neural network model for predicting the intention and trajectory of the driving vehicle. After obtaining the prediction result of the behavior of the target entity, the in-vehicle terminal inputs the prediction result into the second neural network model to predict the intention and trajectory of the driving vehicle, that is, predict whether the driving vehicle needs to stop or continue to drive; if the driving vehicle continues to drive, whether it accelerates or decelerates, and the driving trajectory, etc.

[0056] The behavior prediction method provided by this application determines the target driving area based on the position information of the target entity and the information of the crosswalk corresponding to the target entity; determines the relative position information between the target entity and the target driving area; and predicts the behavior of the target entity based on the relative position information and the motion information of the target entity. In this embodiment, by determining the relative position information between the target entity and the target driving area, the geometric relationship between the target entity and the surrounding environmental information, that is, the target driving area, can be better expressed. Therefore, based on this relative position information and the motion information of the target entity, the behavior of the target entity in a future period of time can be accurately predicted. Moreover, based on the prediction result of the behavior of the target entity, the intention and trajectory of the driving vehicle can be predicted more accurately.

[0057] In one embodiment, as Figure 4 shown, it relates to an implementation manner for determining the relative position information between the target entity and the target driving area. The steps of this implementation manner include:

[0058] Step 400: Determine the intersection points between the movement trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity.

[0059] The target driving area may be an irregularly formed closed area, so the target driving area has a boundary. The driving direction of the target entity can be determined by the in-vehicle terminal based on the data collected by each sensor in the driving vehicle.

[0060] Based on the driving direction of the target entity, the in-vehicle terminal can determine the movement trajectory of the target entity when driving along the driving direction. According to this movement trajectory and the target driving area, the intersection points between the movement trajectory and the boundary of the target driving area can be determined.

[0061] In this embodiment, the driving direction of the target entity obtained by the in-vehicle terminal is the driving direction at the current moment determined according to the data of the target entity collected by the sensor at the current moment. Then, the intersection points between the movement trajectory of the target entity and the boundary of the target driving area are the intersection points between the movement trajectory of the target entity when driving along the driving direction at the current moment and the boundary of the target driving area.

[0062] Step 410: Determine the relative position information according to the position information of the target entity and the position information of the intersection points.

[0063] After the in-vehicle terminal determines the intersection points between the movement trajectory of the target entity and the boundary of the target driving area, it obtains the position information of the intersection points, that is, the coordinate values of the intersection points in the world coordinate system; and determines the relative position information between the target entity and the target driving area according to the position information of the target entity and the position information of the intersection points. That is to say, by calculating the distance between the target entity and the intersection points, the relative position information can be determined.

[0064] In this embodiment, the intersection point between the moving trajectory of the target entity and the boundary of the target driving area is determined based on the driving direction of the target entity. According to the position information of the intersection point and the position information of the target entity, the relative position information between the target entity and the target driving area can be determined. This method of determining the relative position information is fast and easy to implement.

[0065] In one embodiment, the relative position information between the target entity and the target driving area includes a first distance and a second distance, and both the first distance and the second distance are the distances between the target entity and the boundary of the target driving area. In this case, as Figure 5 shown, an implementation manner for determining the intersection point between the moving trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity is involved. The steps of this implementation manner include:

[0066] Step 500: Determine a first intersection point between the target entity and the boundary of the target driving area when the target entity enters the target driving area according to the moving trajectory of the target entity, and determine a second intersection point between the target entity and the boundary of the target driving area when the target entity leaves the target driving area.

[0067] The vehicle-mounted terminal determines a first intersection point among the intersection points between the moving trajectory and the boundary of the target driving area according to the moving trajectory of the target entity, that is, the intersection point between the moving trajectory and the boundary of the target driving area when the target entity enters the target driving area, and a second intersection point among the intersection points between the target entity and the boundary of the target driving area, that is, the intersection point between the moving trajectory and the boundary of the target driving area when the target entity leaves the target driving area.

[0068] In other words, the moving trajectory of the target entity is related to the driving direction of the target entity, that is, the moving trajectory has a directionality. According to the moving trajectory, it can be determined whether the target entity enters or leaves the target driving area. The intersection point between the target entity and the boundary of the target driving area when the target entity enters the target driving area is used as the first intersection point, and the intersection point between the target entity and the boundary of the target driving area when the target entity leaves the target driving area is used as the second intersection point.

[0069] In the case where the vehicle-mounted terminal determines the first intersection point and the second intersection point between the moving trajectory of the target entity and the target driving area, an implementation manner for determining the relative position information according to the position information of the target entity and the position information of the intersection point is involved. This implementation manner includes:

[0070] Step 510: Determine the distance between the target entity and the first intersection point to obtain the first distance, and determine the distance between the target entity and the second intersection point to obtain the second distance.

[0071] The vehicle-mounted terminal obtains the position information of the first intersection point, that is, the coordinate value of the first intersection point in the world coordinate system. According to the coordinate value of the target object in the world coordinate system and the coordinate value of the first intersection point in the world coordinate system, the distance between the target object and the first intersection point is calculated to obtain the first distance.

[0072] The vehicle-mounted terminal obtains the position information of the second intersection point, that is, the coordinate value of the second intersection point in the world coordinate system. According to the coordinate value of the target object in the world coordinate system and the coordinate value of the second intersection point in the world coordinate system, the distance between the target object and the second intersection point is calculated to obtain the second distance.

[0073] In this embodiment, by determining the distance between the target object and the first intersection point of the boundary of the target driving area, and the distance between the target object and the second intersection point of the boundary of the target driving area, the relative position information between the target object and the target driving area is obtained. The method of determining the relative position information in this way is fast and simple, and easy to implement, and can more accurately represent the position relationship between the target object and the target driving area, so as to improve the accuracy of predicting the behavior of the target object.

[0074] In one embodiment, the relative position information between the target object and the target driving area further includes a first relative distance, and the first relative distance is used to characterize the degree of intrusion into the target driving area when the target object is inside the target driving area. In this case, the implementation manner of determining the relative position information between the target object and the target driving area further includes:

[0075] Obtain the sum of the first distance and the second distance, and determine the ratio of the first distance to the sum of the distances to obtain the first relative distance.

[0076] After the vehicle-mounted terminal determines the first distance and the second distance between the target object and the boundary of the target driving area, it calculates the sum of the first distance and the second distance to obtain the sum of the distances, and calculates the ratio of the first distance to the sum of the distances, that is, divides the first distance by the sum of the distances, to obtain the first relative distance.

[0077] In this embodiment, by calculating the ratio of the first distance to the sum of the distances to determine the first relative distance, the first relative distance can better depict the degree of intrusion of the target object into the target driving area, so as to more accurately predict the behavior of the target object. For example, if the first relative distance characterizes that the target object intrudes deeply into the target driving area, that is, the first distance is greater than the second distance, the greater the first relative distance, it can be predicted that the target object will tend to leave the target driving area as soon as possible, so it can be predicted that the vehicle does not need to brake emergently.

[0078] In one embodiment, as Figure 6 shown, the steps of the behavior prediction method further include:

[0079] Step 600: Determine the duration for the target entity to leave the target driving area based on the second distance and the driving speed of the target entity.

[0080] The driving speed of the target entity can be determined by the vehicle-mounted terminal based on the data collected by each sensor in the driving vehicle. After the vehicle-mounted terminal determines the second distance between the target entity and the boundary of the target driving area, it obtains the duration for the target entity to leave the target driving area based on this second distance and the driving speed of the target entity. In other words, calculate the ratio between the second distance and the absolute value of the driving speed of the target entity to obtain the time required for the target entity to continue driving at this driving speed and leave the target driving area.

[0081] In the case where the vehicle-mounted terminal obtains the duration for the target entity to leave the target driving area, another implementation manner related to predicting the behavior of the target entity based on the relative position information and the motion information of the target entity includes:

[0082] Step 610: Predict the behavior of the target entity based on the relative position information, the duration for the target entity to leave the target driving area, and the motion information of the target entity.

[0083] The vehicle-mounted terminal predicts the behavior of the target entity based on the relative position information between the target entity and the target driving area, the duration for the target entity to leave the target driving area, and the motion information of the target entity.

[0084] In an optional embodiment, the vehicle-mounted terminal inputs the relative position information, the duration for the target entity to leave the target driving area, and the motion information of the target entity into the first neural network model to predict the behavior of the target entity.

[0085] In this embodiment, when predicting the behavior of the target entity, not only the relative position information between the target entity and the target driving area and the motion information of the target entity are obtained, but also the duration for the target entity to leave the target driving area is obtained. These features can more fully and accurately represent the geometric relationship between the target entity and the target driving area, and can improve the accuracy of predicting the behavior of the target entity.

[0086] In one embodiment, as Figure 7 shown, an implementation manner related to determining the target driving area based on the position information of the target entity and the information of the crosswalk corresponding to the target entity includes the following steps:

[0087] Step 700: Determine multiple candidate driving areas based on the position information of the target entity and the information of the crosswalk.

[0088] The in-vehicle terminal can determine multiple candidate driving areas based on the position information of the target entity and the information of the crosswalk corresponding to the target entity. That is to say, there are multiple candidate driving areas related to the crosswalk, and the target entity may be in the area where multiple candidate driving areas intersect.

[0089] In an alternative embodiment, a schematic diagram of the driving area at a certain intersection is as Figure 8 shown. Figure 8 It shows the area included in a driving area for a horizontal crosswalk. This driving area includes a partial area on the right side of the crosswalk, a partial area of the actual road where the vehicle is driving, a partial area of the virtual straight lane, a partial area of the virtual left-turn lane, and a partial area of the virtual right-turn lane. Among them, the partial area of the actual road where the vehicle is driving refers to the area with a distance of a1 from one of the longer borders of the crosswalk; the partial area of the virtual straight lane refers to the area with a distance of a2 (not shown in the figure) from the other longer border of the crosswalk; similarly, the partial area of the virtual left-turn lane refers to the area with a distance of a3 (not shown in the figure) from the other longer border of the crosswalk; the partial area of the virtual right-turn vehicle refers to the area with a distance of b from one of the shorter borders of the crosswalk, and a1, a2, and a3 can be the same. Figure 8 The driving area at the intersection in Figure 9 is the area enclosed by the dashed line in Figure 8 There may be multiple driving areas at the intersection shown in

[0090] In another alternative embodiment, for the driving area at a non-intersection as Figure 10 shown, the driving area at the non-intersection is composed of a partial area of the straight lane and a partial area of the crosswalk. Figure 10 The area enclosed by the thick dashed line in

[0091] In an alternative embodiment, the relative position information between the target entity and the target driving area can be as Figure 11 shown. The dashed line along the driving direction of the target entity is the movement trajectory of the target entity. The intersection points between this movement trajectory and the boundary of the target driving area are the first intersection point and the second intersection point. The distance between the target entity and the first intersection point is the first distance, and the distance between the target entity and the second intersection point is the second distance.

[0092] Step 710: Obtain the center point of each candidate driving area, and determine the distance between the target entity and each center point according to the position information of the target entity.

[0093] After the vehicle-mounted terminal determines multiple candidate driving areas, it calculates the center point of each candidate driving area and obtains the coordinate values of the center points of each candidate driving area. This embodiment does not limit the specific method for determining the center point of each candidate driving area as long as its function can be realized.

[0094] The vehicle-mounted terminal determines the distance between the target entity and each center point according to the coordinate values of the center points of each candidate driving area and the position information of the target entity.

[0095] Step 720: Determine the candidate driving area corresponding to the center point with the smallest distance as the target driving area.

[0096] After the vehicle-mounted terminal determines the distance between the target entity and each center point, it compares the multiple distances to obtain the center point with the smallest distance, and determines the candidate driving area corresponding to the center point with the smallest distance as the target driving area.

[0097] In this embodiment, multiple candidate driving areas are determined according to the information of the target entity and the crosswalk, and the target driving area is determined from the multiple candidate driving areas through the distance between the target entity and the center point of each candidate driving area. The method for determining the target driving area in this way is fast and easy to implement, and can improve the efficiency of the behavior prediction method.

[0098] In one embodiment, as Figure 12 shown, it relates to an implementation manner for predicting the behavior of a target entity according to relative position information and motion information of the target entity, including:

[0099] Step 120: Obtain the relative information between the target entity and the crosswalk.

[0100] The vehicle-mounted terminal obtains the position information of the target entity and the information of the crosswalk corresponding to the target entity, and determines the relative information between the target entity and the crosswalk according to the position information of the target entity and the information of the crosswalk. The relative information between the target entity and the crosswalk may include any one of that the target entity is about to enter the crosswalk, the target entity has left the crosswalk, and the position of the target entity in the crosswalk. The description of the vehicle-mounted terminal obtaining the position information of the target entity and the information of the crosswalk corresponding to the target entity can refer to the specific description in the above embodiment and will not be elaborated here.

[0101] In one embodiment, the relative information includes at least one of the target speed of the target entity, the distance between the target entity and the crosswalk, and the second relative distance.

[0102] The target speed of the target entity is used to characterize the speed of the target entity during its travel in the crosswalk. The distance between the target entity and the crosswalk is used to characterize whether the target entity is about to enter the crosswalk, has left the crosswalk, or is in the crosswalk. The second relative distance is used to characterize the degree to which the target entity intrudes into the crosswalk.

[0103] Step 121: Predict the behavior of the target entity based on the relative information, relative position information, and motion information of the target entity.

[0104] After obtaining the relative information between the target entity and the crosswalk, the in-vehicle terminal predicts the behavior of the target entity based on this relative information, as well as the relative position information between the target entity and the target driving area and the motion information of the target entity.

[0105] In an optional embodiment, the in-vehicle terminal inputs the relative information between the target entity and the crosswalk, the relative position information between the target entity and the target driving area, and the motion information of the target entity into the first neural network model to predict the behavior of the target entity.

[0106] In this embodiment, when predicting the behavior of the target entity, not only the relative position information between the target entity and the target driving area and the motion information of the target entity are obtained, but also the relative information between the target entity and the crosswalk is obtained. These obtained features can more fully and accurately characterize the geometric relationship between the target entity and the target driving area, and the geometric relationship between the target entity and the crosswalk, which can improve the accuracy of predicting the behavior of the target entity.

[0107] In an embodiment, when the relative information between the target entity and the crosswalk includes the target speed of the target entity, the method for obtaining the target speed includes:

[0108] Determine the speed of the target entity along the center line of the crosswalk to obtain the target speed.

[0109] After the in-vehicle terminal obtains the driving speed of the target entity and determines the center line of the crosswalk where the target entity is located, it decomposes the driving speed of the target entity along the center line of the crosswalk, and determines the decomposed speed along the center line of the crosswalk as the target speed. The specific methods for obtaining the driving speed of the target entity and determining the center line of the crosswalk where the target entity is located can refer to the specific descriptions of the above embodiments and will not be elaborated here.

[0110] In this embodiment, the target speed is obtained by determining the speed of the target object along the center line of the crosswalk. The target speed of the target object determined in this way can more fully and accurately represent the geometric relationship between the target object and the crosswalk, that is, the urgency of the target object passing through the crosswalk. Therefore, the behavior of the target object can be predicted more accurately based on the target speed.

[0111] In one embodiment, when the relative information between the target object and the crosswalk includes the distance between the target object and the crosswalk. During the process of the target object passing through the crosswalk, it will usually pass through the border of the crosswalk twice. Then the distance between the target object and the crosswalk includes a third distance and a fourth distance, that is, the two distances between the target object and the border of the crosswalk. As Figure 13 shown, the method for obtaining the distance between the target object and the crosswalk includes:

[0112] Step 130: Determine the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point according to the driving direction of the target object, and determine the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the ending point.

[0113] There are two intersection points between the center line of the crosswalk and the border of the crosswalk. The vehicle-mounted terminal can determine the third intersection point among the two intersection points between the center line of the crosswalk and the border of the crosswalk as the starting point and the fourth intersection point as the ending point according to the driving direction of the target object. The starting point refers to the intersection point between the border passed by the target object when entering the crosswalk according to the driving direction and the center line of the crosswalk, and the ending point refers to the intersection point between the boundary passed by the target object when leaving the crosswalk according to the driving direction and the center line of the crosswalk. The direction from the starting point to the ending point is the same as the driving direction of the target object.

[0114] Step 131: Determine the distance between the target object and the starting point to obtain the third distance, and determine the distance between the target object and the ending point to obtain the fourth distance.

[0115] After the vehicle-mounted terminal determines the starting point and the ending point between the center line of the crosswalk and the border of the crosswalk, it obtains the coordinate value of the starting point in the world coordinate system, determines the distance between the target object and the starting point, that is, calculates the distance between the coordinate value of the target object and the coordinate value of the starting point to obtain the third distance. Obtain the coordinate value of the ending point in the world coordinate system, determine the distance between the target object and the ending point, that is, calculate the distance between the coordinate value of the target object and the coordinate value of the ending point to obtain the fourth distance.

[0116] In this embodiment, starting from the third intersection point between the center line of the crosswalk and the border of the crosswalk and ending at the fourth intersection point are determined according to the driving direction of the target entity; the distance between the target entity and the starting point is determined to obtain a third distance, and the distance between the target entity and the ending point is determined to obtain a fourth distance. The method for determining the third distance and the fourth distance in this way is fast and easy to implement.

[0117] In one embodiment, as Figure 14 shown, an implementation manner for determining the distance between the target entity and the starting point to obtain a third distance, and determining the distance between the target entity and the ending point to obtain a fourth distance is involved. The steps of this implementation manner include:

[0118] Step 140: Project the target entity onto the center line of the crosswalk to obtain a projected entity.

[0119] After the vehicle-mounted terminal obtains the position information of the target entity, it projects the target entity onto the center line of the crosswalk to obtain a projected entity. If the target entity has not entered the crosswalk or has left the crosswalk, the projected entity is on the extension line of the center line of the crosswalk; if the target entity is within the crosswalk, the projected entity is on the center line of the crosswalk.

[0120] Step 141: Determine the distance between the projected entity and the starting point to obtain a third distance, and determine the distance between the projected entity and the ending point to obtain a fourth distance.

[0121] After the vehicle-mounted terminal obtains the projected entity, it obtains the coordinate value of the projected entity in the world coordinate system, calculates the distance between the coordinate value of the projected entity and the coordinate value of the starting point to obtain a third distance, and calculates the distance between the coordinate value of the projected entity and the coordinate value of the ending point to obtain a fourth distance.

[0122] In this embodiment, after projecting the target entity onto the center line of the crosswalk to obtain a projected entity, the distance between the projected entity and the starting point is determined to obtain a third distance, and the distance between the projected entity and the starting point is determined to obtain a fourth distance. The third distance and the fourth distance obtained in this way can more fully and accurately represent the geometric relationship between the target entity and the crosswalk, thereby improving the accuracy of predicting the behavior of the target entity.

[0123] In one embodiment, when the relevant information between the target entity and the crosswalk includes a second relative distance, the method for obtaining the second relative distance includes:

[0124] Determine the ratio between the fourth distance and the total length of the center line of the crosswalk to obtain the second relative distance.

[0125] After the in-vehicle terminal determines the distances (the third distance and the fourth distance) between the target entity and the crosswalk, it obtains the total length of the center line of the crosswalk, calculates the ratio between the fourth distance and the total length of the center line of the crosswalk, that is, the fourth distance divided by the total length of the center line of the crosswalk, and determines this ratio as the second relative distance.

[0126] In this embodiment, by determining the ratio between the fourth distance and the total length of the center line of the crosswalk, the second relative distance is obtained. Through the second relative distance, the degree to which the target entity invades the crosswalk can be more vividly depicted, so that the behavior of the target entity can be predicted more accurately. For example, if the second relative distance indicates that the degree to which the target entity invades the crosswalk is very deep, that is, the second relative distance is small, it can be predicted that the target entity will tend to leave the crosswalk as soon as possible, so that it can be predicted that the driving vehicle does not need to brake emergently.

[0127] In an alternative embodiment, when the relative information between the target entity and the crosswalk includes the target speed, as Figure 15 shown, Figure 15 the speed along the crosswalk in is the target speed of the target entity. When the relative information between the target entity and the crosswalk includes the distance between the target entity and the crosswalk, as Figure 16 shown. If the target entity 1 is about to enter the crosswalk, the third distance between the target entity 1 and the crosswalk is C, and the fourth distance between the target entity 1 and the crosswalk is D. If the target entity 2 is in the crosswalk, the third distance between the target entity 2 and the crosswalk is E, and the fourth distance between the target entity 2 and the crosswalk is F. If the target entity 3 has left the crosswalk, the third distance between the target entity 3 and the crosswalk is H, and the fourth distance between the target entity 3 and the crosswalk is K.

[0128] An embodiment of the present application provides a behavior prediction method, and the steps of this method include:

[0129] Step S1: Determine a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk corresponding to the target entity;

[0130] Step S2: Obtain the center point of each candidate driving area, and determine the distance between the target entity and each center point according to the position information of the entity;

[0131] Step S3: Determine the candidate driving area corresponding to the center point with the smallest distance as the target driving area;

[0132] Step S4: According to the driving direction of the target entity, determine the first intersection point between the target entity and the boundary of the target driving area when entering the target driving area, and determine the second intersection point between the target entity and the boundary of the target driving area when leaving the target driving area;

[0133] Step S5: Determine the distance between the target object and the first intersection point to obtain a first distance, and determine the distance between the target object and the second intersection point to obtain a second distance;

[0134] Step S6: Obtain the sum of the first distance and the second distance, and determine the ratio of the first distance to the sum of the distances to obtain a first relative distance;

[0135] Step S7: Determine the duration for which the target object leaves the target driving area based on the second distance and the driving speed of the target object;

[0136] Step S8: Determine the speed of the target object along the center line of the crosswalk to obtain a target speed;

[0137] Step S9: Based on the driving direction of the target object, determine the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point, and determine the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the ending point;

[0138] Step S10: Project the target object onto the center line of the crosswalk to obtain a projected object;

[0139] Step S11: Determine the distance between the projected object and the starting point to obtain a third distance, and determine the distance between the projected object and the ending point to obtain a fourth distance;

[0140] Step S12: Determine the ratio between the fourth distance and the total length of the center line of the crosswalk to obtain a second relative distance;

[0141] Step S13: Predict the behavior of the target object based on the first distance, the second distance, the first relative distance, the duration for which the target object leaves the target driving area, the target speed, the third distance, the fourth distance, and the second relative distance.

[0142] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown as indicated by the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0143] Based on the same inventive concept, an embodiment of the present application further provides a behavior prediction device for implementing the behavior prediction method involved above. The solution provided by this device for solving problems is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the behavior prediction device provided below can refer to the limitations on the behavior prediction method in the above text and will not be elaborated here.

[0144] In one embodiment, as Figure 17 shown, a behavior prediction device 10 is provided, including: a region determination module 11, an information determination module 12, and a prediction module 13, where:

[0145] The region determination module 11 is configured to determine a target driving region according to the position information of the target entity and the information of the crosswalk corresponding to the target entity.

[0146] The information determination module 12 is configured to determine the relative position information between the target entity and the target driving region.

[0147] The prediction module 13 is configured to predict the behavior of the target entity according to the relative position information and the motion information of the target entity.

[0148] In one embodiment, the information determination module 12 includes an intersection determination unit and an information determination unit. The intersection determination unit is configured to determine the intersection between the moving trajectory of the target entity and the boundary of the target driving region according to the driving direction of the target entity; the information determination unit is configured to determine the relative position information according to the position information of the target entity and the position information of the intersection.

[0149] In one embodiment, the intersection determination unit is specifically configured to determine the first intersection between the target entity and the boundary of the target driving region when the target entity enters the target driving region according to the moving trajectory of the target entity, and determine the second intersection between the target entity and the boundary of the target driving region when the target entity leaves the target driving region; the information determination unit is specifically configured to determine the distance between the target entity and the first intersection to obtain the first distance, and determine the distance between the target entity and the second intersection to obtain the second distance.

[0150] In one embodiment, the information determination module 12 is further configured to obtain the sum of the first distance and the second distance, and determine the ratio of the first distance to the sum of the distances to obtain the first relative distance.

[0151] In one embodiment, the behavior prediction device 10 further includes a duration determination module. The duration determination module is configured to determine the duration for the target entity to leave the target driving region according to the second distance and the driving speed of the target entity; the prediction module is specifically configured to predict the behavior of the target entity according to the relative position information, the duration for the target entity to leave the target driving region, and the motion information of the target entity.

[0152] In one embodiment, the area determination module is specifically configured to determine a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk; obtain the center point of each candidate driving area, and determine the distance between the target entity and each center point according to the position information of the target entity; and determine the candidate driving area corresponding to the center point with the minimum distance as the target driving area.

[0153] In one embodiment, the prediction module 13 includes an information acquisition unit and a prediction unit. The information acquisition unit is configured to acquire the relative information between the target entity and the crosswalk; the prediction unit is configured to predict the behavior of the target entity according to the relative information, the relative position information, and the motion information of the target entity.

[0154] In one embodiment, the relative information includes at least one of the target speed of the target entity, the distance between the target entity and the crosswalk, and the second relative distance.

[0155] In one embodiment, the behavior prediction device 10 further includes a speed acquisition module, and the speed acquisition module is configured to determine the speed of the target entity along the center line of the crosswalk to obtain the target speed.

[0156] In one embodiment, the behavior prediction device 10 further includes a distance acquisition module. The distance acquisition module is configured to determine the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point according to the driving direction of the target entity, and determine the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the end point; determine the distance between the target entity and the starting point to obtain the third distance, and determine the distance between the target entity and the end point to obtain the fourth distance.

[0157] In one embodiment, the distance acquisition module is specifically configured to project the target entity onto the center line of the crosswalk to obtain a projected entity; determine the distance between the projected entity and the starting point to obtain the third distance, and determine the distance between the projected entity and the end point to obtain the fourth distance.

[0158] In one embodiment, the distance acquisition module is further configured to determine the ratio between the fourth distance and the total length of the center line of the crosswalk to obtain the second relative distance.

[0159] Each module in the above behavior prediction device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0160] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 18As shown in the figure. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a behavior prediction method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0161] Those skilled in the art can understand that Figure 18 the structure shown in the figure is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0162] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory. When the processor executes the computer program, the following steps are implemented:

[0163] Determine the target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity;

[0164] Determine the relative position information between the target entity and the target driving area;

[0165] Predict the behavior of the target entity according to the relative position information and the motion information of the target entity.

[0166] In one embodiment, when the processor executes the computer program, the following steps are also implemented: Determine the intersection point between the moving trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity; Determine the relative position information according to the position information of the target entity and the position information of the intersection point.

[0167] In one embodiment, when the processor executes the computer program, the following steps are further implemented: according to the moving trajectory of the target entity, determine the first intersection point of the target entity with the boundary of the target driving area when the target entity enters the target driving area, and determine the second intersection point of the target entity with the boundary of the target driving area when the target entity leaves the target driving area; determine the distance between the target entity and the first intersection point to obtain the first distance, and determine the distance between the target entity and the second intersection point to obtain the second distance.

[0168] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtain the sum of the first distance and the second distance, and determine the ratio of the first distance to the sum of the distances to obtain the first relative distance.

[0169] In one embodiment, when the processor executes the computer program, the following steps are further implemented: according to the second distance and the driving speed of the target entity, determine the duration for which the target entity leaves the target driving area; according to the relative position information, the duration for which the target entity leaves the target driving area, and the motion information of the target entity, predict the behavior of the target entity.

[0170] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determine a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk; obtain the center point of each candidate driving area, and determine the distance between the target entity and each center point according to the position information of the target entity; determine the candidate driving area corresponding to the center point with the smallest distance as the target driving area.

[0171] In one embodiment, when the processor executes the computer program, the following steps are further implemented: obtain the relative information between the target entity and the crosswalk; according to the relative information, the relative position information, and the motion information of the target entity, predict the behavior of the target entity.

[0172] In one embodiment, the relative information includes at least one of the target speed of the target entity, the distance between the target entity and the crosswalk, and the second relative distance.

[0173] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determine the speed of the target entity along the center line of the crosswalk to obtain the target speed.

[0174] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determine the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point according to the driving direction of the target entity, and determine the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the end point; determine the distance between the target entity and the starting point to obtain the third distance, and determine the distance between the target entity and the end point to obtain the fourth distance.

[0175] In one embodiment, when the processor executes the computer program, the following steps are further implemented: project the target object onto the center line of the crosswalk to obtain a projected object; determine the distance between the projected object and the starting point to obtain a third distance, and determine the distance between the projected object and the end point to obtain a fourth distance.

[0176] In one embodiment, when the processor executes the computer program, the following steps are further implemented: determine the ratio between the fourth distance and the total length of the center line of the crosswalk to obtain a second relative distance.

[0177] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented:

[0178] Determine a target driving area according to the position information of the target object and the information of the crosswalk corresponding to the target object;

[0179] Determine the relative position information between the target object and the target driving area;

[0180] Predict the behavior of the target object according to the relative position information and the motion information of the target object.

[0181] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determine the intersection point between the moving trajectory of the target object and the boundary of the target driving area according to the driving direction of the target object; determine the relative position information according to the position information of the target object and the position information of the intersection point.

[0182] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determine the first intersection point between the target object and the boundary of the target driving area when the target object enters the target driving area according to the moving trajectory of the target object, and determine the second intersection point between the target object and the boundary of the target driving area when the target object leaves the target driving area; determine the distance between the target object and the first intersection point to obtain a first distance, and determine the distance between the target object and the second intersection point to obtain a second distance.

[0183] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: obtain the sum of the first distance and the second distance, and determine the ratio between the first distance and the sum of the distances to obtain a first relative distance.

[0184] In one embodiment, when the computer program is executed by the processor, the following steps are further implemented: determine the duration for the target object to leave the target driving area according to the second distance and the driving speed of the target object; predict the behavior of the target object according to the relative position information, the duration for the target object to leave the target driving area, and the motion information of the target object.

[0185] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk; obtaining the center point of each candidate driving area, and determining the distance between the target entity and each center point according to the position information of the target entity; and determining the candidate driving area corresponding to the center point with the minimum distance as the target driving area.

[0186] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtaining the relative information between the target entity and the crosswalk; and predicting the behavior of the target entity according to the relative information, the relative position information, and the motion information of the target entity.

[0187] In one embodiment, the relative information includes at least one of the target speed of the target entity, the distance between the target entity and the crosswalk, and the second relative distance.

[0188] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining the speed of the target entity along the center line of the crosswalk to obtain the target speed.

[0189] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point according to the driving direction of the target entity, and determining the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the ending point; determining the distance between the target entity and the starting point to obtain the third distance, and determining the distance between the target entity and the ending point to obtain the fourth distance.

[0190] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: projecting the target entity onto the center line of the crosswalk to obtain the projected entity; determining the distance between the projected entity and the starting point to obtain the third distance, and determining the distance between the projected entity and the ending point to obtain the fourth distance.

[0191] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining the ratio of the fourth distance to the total length of the center line of the crosswalk to obtain the second relative distance.

[0192] In one embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0193] Determining a target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity;

[0194] Determining the relative position information between the target entity and the target driving area;

[0195] Predict the behavior of the target entity based on the relative position information and the motion information of the target entity. In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the intersection point between the moving trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity; determine the relative position information according to the position information of the target entity and the position information of the intersection point.

[0196] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the first intersection point between the target entity and the boundary of the target driving area when the target entity enters the target driving area according to the moving trajectory of the target entity, and determine the second intersection point between the target entity and the boundary of the target driving area when the target entity leaves the target driving area; determine the distance between the target entity and the first intersection point to obtain the first distance, and determine the distance between the target entity and the second intersection point to obtain the second distance.

[0197] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtain the sum of the first distance and the second distance, and determine the ratio of the first distance to the sum of the distances to obtain the first relative distance.

[0198] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the duration for which the target entity leaves the target driving area according to the second distance and the driving speed of the target entity; predict the behavior of the target entity according to the relative position information, the duration for which the target entity leaves the target driving area, and the motion information of the target entity.

[0199] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk; obtain the center point of each candidate driving area, and determine the distance between the target entity and each center point according to the position information of the target entity; determine the candidate driving area corresponding to the center point with the smallest distance as the target driving area.

[0200] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: obtain the relative information between the target entity and the crosswalk; predict the behavior of the target entity according to the relative information, the relative position information, and the motion information of the target entity.

[0201] In one embodiment, the relative information includes at least one of the target speed of the target entity, the distance between the target entity and the crosswalk, and the second relative distance.

[0202] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determine the speed of the target entity along the center line of the crosswalk to obtain the target speed.

[0203] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining, based on the driving direction of the target entity, the third intersection point of the center line of the crosswalk and the border of the crosswalk as the starting point, and determining the fourth intersection point of the center line of the crosswalk and the border of the crosswalk as the ending point; determining the distance between the target entity and the starting point to obtain a third distance, and determining the distance between the target entity and the ending point to obtain a fourth distance.

[0204] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: projecting the target entity onto the center line of the crosswalk to obtain a projected entity; determining the distance between the projected entity and the starting point to obtain a third distance, and determining the distance between the projected entity and the ending point to obtain a fourth distance.

[0205] In one embodiment, when the computer program is executed by a processor, the following steps are further implemented: determining the ratio between the fourth distance and the total length of the center line of the crosswalk to obtain a second relative distance.

[0206] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in the present application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in the present application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0207] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0208] The above-described embodiments only represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A behavior prediction method, characterized in that, The method includes: Determining a target driving area according to the position information of a target entity and the information of the crosswalk corresponding to the target entity; Determining the relative position information between the target entity and the target driving area; Predicting the behavior of the target entity according to the relative position information and the motion information of the target entity.

2. The method according to claim 1, wherein The determining the relative position information between the target entity and the target driving area includes: Determining the intersection points between the moving trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity; Determining the relative position information according to the position information of the target entity and the position information of the intersection points.

3. The method according to claim 2, characterized in that The relative position information includes a first distance and a second distance. The determining the intersection points between the moving trajectory of the target entity and the boundary of the target driving area according to the driving direction of the target entity includes: Determining a first intersection point between the moving trajectory of the target entity and the boundary of the target driving area when the target entity enters the target driving area, and determining a second intersection point between the moving trajectory of the target entity and the boundary of the target driving area when the target entity leaves the target driving area according to the moving trajectory of the target entity; The determining the relative position information according to the position information of the target entity and the position information of the intersection points includes: Determining the distance between the target entity and the first intersection point to obtain the first distance, and determining the distance between the target entity and the second intersection point to obtain the second distance.

4. The method according to claim 3, characterized in that, The relative position information further includes a first relative distance. The determining the relative position information between the target entity and the target driving area further includes: Obtaining the sum of the first distance and the second distance, and determining the ratio of the first distance to the sum of the distances to obtain the first relative distance.

5. The method according to claim 3, wherein The method further includes: Determining the duration for the target entity to leave the target driving area according to the second distance and the driving speed of the target entity; The predicting the behavior of the target entity according to the relative position information and the motion information of the target entity includes: Predicting the behavior of the target entity according to the relative position information, the duration for the target entity to leave the target driving area, and the motion information of the target entity.

6. The method according to any one of claims 1-5, characterized in that The determining the target driving area according to the position information of the target entity and the information of the crosswalk corresponding to the target entity includes: Determining a plurality of candidate driving areas according to the position information of the target entity and the information of the crosswalk; Obtaining the center point of each candidate driving area, and determining the distance between the target entity and each center point according to the position information of the target entity; Determining the candidate driving area corresponding to the center point with the minimum distance as the target driving area.

7. The method according to any one of claims 1-5, characterized in that, The predicting the behavior of the target entity according to the relative position information and the motion information of the target entity includes: Obtaining the relative information between the target entity and the crosswalk; Predicting the behavior of the target entity according to the relative information, the relative position information, and the motion information of the target entity.

8. The method according to claim 7, wherein The relative information includes at least one of a target speed of a target entity, a distance between the target entity and the crosswalk, and a second relative distance.

9. The method according to claim 8, wherein The method for obtaining the target speed includes: Determining a speed of the target entity along a center line of the crosswalk to obtain the target speed.

10. The method according to claim 8, wherein The distance between the target entity and the crosswalk includes a third distance and a fourth distance. The method for obtaining the distance between the target entity and the crosswalk includes: According to a traveling direction of the target entity, determining a third intersection point of the center line of the crosswalk and a border of the crosswalk as a starting point, and determining a fourth intersection point of the center line of the crosswalk and the border of the crosswalk as an end point; Determining a distance between the target entity and the starting point to obtain the third distance, and determining a distance between the target entity and the end point to obtain the fourth distance.

11. The method according to claim 10, wherein The determining the distance between the target entity and the starting point to obtain the third distance, and the determining the distance between the target entity and the end point to obtain the fourth distance includes: Projecting the target entity onto the center line of the crosswalk to obtain a projected entity; Determining a distance between the projected entity and the starting point to obtain the third distance, and determining a distance between the projected entity and the end point to obtain the fourth distance.

12. The method according to claim 10, characterized in that The method for obtaining the second relative distance includes: Determining a ratio between the fourth distance and a total length of the center line of the crosswalk to obtain the second relative distance.

13. A behavior prediction device, characterized in that, The apparatus includes: A region determination module, configured to determine a target traveling region according to position information of a target entity and information of a crosswalk corresponding to the target entity; An information determination module, configured to determine relative position information between the target entity and the target traveling region; A prediction module, configured to predict an action of the target entity according to the relative position information and motion information of the target entity.

14. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 12 are implemented.

15. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

16. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 12 are implemented.

Images