Target vehicle fusion method and device, electronic equipment and storage medium

Abstract

The invention provides a target vehicle fusion method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a first driving state parameter of a three-dimensional target of a first vehicle-mounted sensor and a second driving state parameter of a point target of a second vehicle-mounted sensor of a target vehicle of any frame of a preset area around an automatic driving vehicle; determining a preset number of first reference points of the target vehicle based on a geometrical relationship between the first driving state parameter and the autonomous vehicle; determining a second reference point of the target vehicle based on the second driving state parameter and each first reference point; if the second reference point and each first reference point meet a preset condition, determining one first reference point as a third reference point of the target vehicle; and based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form the fused driving state parameter, so that the difference of the detection data of each sensor is greatly reduced, and the accuracy of the fused data of the target vehicle is improved.

Description

Technical Field

[0001] The present application belongs to the field of autonomous driving technology, and in particular, relates to a target vehicle fusion method, device, electronic device and storage medium. Background Art

[0002] At present, target fusion mainly processes target information sent by multiple on-board sensors, fuses the data of the same attributes of the detected target, and obtains detection performance that is better than that of a single sensor. In the prior art, when multiple sensors detect the same target, the detection data of each sensor differs, resulting in errors in the fusion data of the target, causing the autonomous driving vehicle to misoperate.

[0003] The existing technology has the problem that the detection data of multiple sensors detecting the same target are different, resulting in errors in the fused data. Summary of the invention

[0004] The embodiments of the present application provide a method, device, electronic device and storage medium for fusing a target vehicle, which can solve the problem that detection data of the same target detected by multiple sensors are different, resulting in errors in fused data.

[0005] In a first aspect, an embodiment of the present application provides a method for fusing a target vehicle, comprising:

[0006] Acquire a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor;

[0007] Determining a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle;

[0008] Determining a second reference point of the target vehicle based on the second driving state parameter and each of the first reference points;

[0009] If the second reference point and each of the first reference points meet a preset condition, determining one of the first reference points as a third reference point of the target vehicle;

[0010] Based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form a fused driving state parameter.

[0011] In one embodiment, the first driving state parameter includes a vehicle head orientation angle and a three-dimensional coordinate of the target vehicle, wherein the vehicle head orientation angle is an angle formed by the vehicle head direction of the autonomous driving vehicle and the vehicle head direction of the target vehicle;

[0012] The step of determining a preset number of first reference points of the target vehicle based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle comprises:

[0013] Determine the two-dimensional plane coordinates of the target vehicle in a preset coordinate system based on the three-dimensional coordinates of the target vehicle, wherein the preset coordinate system is a two-dimensional plane coordinate system with the first on-board sensor of the autonomous driving vehicle as the coordinate origin;

[0014] Determining a plane geometric center point of the target vehicle based on the two-dimensional plane coordinates of the target vehicle;

[0015] Based on the vehicle head orientation angle, the two-dimensional plane coordinates and the plane geometric center point, determine the four corner points of the target vehicle and the four sides formed by the corner points;

[0016] A preset number of first reference points of the target vehicle are determined based on each of the corner points, the plane geometric center point and the coordinate origin of the preset coordinate system.

[0017] In one embodiment, the longitudinal axis of the two-dimensional plane coordinate system is along the driving direction from the rear end to the front end of the autonomous driving vehicle, and the transverse axis of the two-dimensional plane coordinate system is perpendicular to the longitudinal axis;

[0018] The step of determining a preset number of first reference points of the target vehicle based on each of the corner points, the plane geometric center point and the coordinate origin of the preset coordinate system comprises:

[0019] Based on the plane geometric center point and the coordinate origin of the preset coordinate system, determining the angle between the center point of the plane geometric center point and the coordinate origin;

[0020] Based on each of the corner points and the coordinate origin of the preset coordinate system, determining a corresponding corner point angle formed by each of the corner points and the coordinate origin;

[0021] Based on the difference calculation between the center point angle and each of the corner point angles, determine the corner point angle difference corresponding to each of the corner point angles;

[0022] Determine the minimum corner point angle difference based on the angle differences of each corner point;

[0023] Determine the corner point corresponding to the minimum corner point angle difference and the corner point farthest from the autonomous driving vehicle as the farthest corner point;

[0024] Determine two sides away from the farthest corner point and three corner points corresponding to the two sides based on the two-dimensional plane coordinates of the target vehicle and the farthest corner point;

[0025] Five first reference points are formed based on midpoints corresponding to two sides far away from the farthest corner point and the three corner points.

[0026] In one embodiment, the second driving state parameter includes a radar target point of the target vehicle in a preset coordinate system, wherein the preset coordinate system is a two-dimensional plane coordinate system with a first on-board sensor of the autonomous driving vehicle as a coordinate origin, the longitudinal axis of the two-dimensional plane coordinate system is in a direction from the front to the rear of the autonomous driving vehicle, and the transverse axis of the two-dimensional plane coordinate system is perpendicular to the longitudinal axis;

[0027] The step of determining the second reference point of the target vehicle based on the second driving state parameter and each of the first reference points includes:

[0028] Determine the angle between the target point and the longitudinal axis based on the radar target point and the coordinate origin;

[0029] Determine the first reference point angle with the longitudinal axis based on each of the first reference points and the coordinate origin respectively;

[0030] If the angle between the target point and each of the first reference points meets a preset requirement, the radar target point is determined to be a second reference point of the target vehicle.

[0031] In one of the embodiments, the preset requirement is that the target point angle is greater than or equal to the minimum value of the first reference point angles, and less than or equal to the maximum value of the first reference point angles.

[0032] In one embodiment, the preset condition includes a first preset condition, a second preset condition and a third preset condition, the first driving state parameter includes a first longitudinal speed and a first lateral speed, and the second driving state parameter includes a second longitudinal speed and a second lateral speed;

[0033] The step of determining one of the first reference points as the third reference point of the target vehicle if the second reference point and each of the first reference points meet a preset condition comprises:

[0034] If the difference between the first longitudinal velocity of the second reference point and the second longitudinal velocity of each of the first reference points satisfies a first preset condition, the difference between the first lateral velocity of the second reference point and the second lateral velocity of each of the first reference points satisfies a second preset condition, and the straight-line distance between the coordinate position of the second reference point and the coordinate position of each of the first reference points satisfies a third preset condition, the first reference point is determined to be the third reference point of the target vehicle.

[0035] In one of the embodiments, the preset conditions further include a fourth preset condition;

[0036] If the straight-line distances between the coordinate positions of the second reference point in the next frame and the coordinate positions of each of the first reference points respectively meet a fourth preset condition, one of the first reference points is updated to be the third reference point of the target vehicle.

[0037] In a second aspect, an embodiment of the present application provides a fusion device for a target vehicle, comprising:

[0038] An acquisition module, used to acquire a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor;

[0039] A first determination module, configured to determine a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle;

[0040] A second determination module, configured to determine a second reference point of the target vehicle based on the second driving state parameter and each of the first reference points;

[0041] A third determination module, configured to determine one of the first reference points as a third reference point of the target vehicle if the second reference point and each of the first reference points meet a preset condition;

[0042] A fusion module is used to fuse the first driving state parameter and the second driving state parameter to form a fused driving state parameter based on the second reference point and the third reference point.

[0043] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a method as described in any one of the contents of the first aspect above.

[0044] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the contents of the first aspect above is implemented.

[0045] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described in the first aspect above.

[0046] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0047] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0048] The present application obtains the first driving state parameter and the second driving state parameter of the target vehicle in any frame of the preset area around the autonomous driving vehicle, wherein the first driving state parameter is the driving state parameter of the three-dimensional target formed by the first vehicle-mounted sensor, and the second driving state parameter is the driving state parameter of the point target formed by the second vehicle-mounted sensor; based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle, a preset number of first reference points of the target vehicle are determined; based on the second driving state parameter and each of the first reference points, a second reference point of the target vehicle is determined; if the second reference point and each of the first reference points meet the preset conditions, one of the first reference points is determined as the third reference point of the target vehicle; based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form a fused driving state parameter. Since the third reference point and the second reference point with the closest properties to the first vehicle-mounted sensor and the second vehicle-mounted sensor are determined respectively, and then the fused driving state parameter is obtained by fusion, the detection data of multiple sensors greatly reduces the difference in the detection data of each sensor when detecting the same target vehicle, improves the accuracy of the fused data of the target vehicle, avoids the misoperation of the autonomous driving vehicle, and improves the safety of the autonomous driving vehicle. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0050] Figure 1 It is a flowchart of a target vehicle fusion method provided by an embodiment of the present application;

[0051] Figure 2 It is a schematic diagram of a process for determining a preset number of first reference points of a target vehicle based on a geometric relationship between a first driving state parameter and an autonomous driving vehicle provided by an embodiment of the present application;

[0052] Figure 3 is a schematic diagram of determining a first reference point provided by an embodiment of the present application;

[0053] Figure 4 It is a schematic diagram of a process for determining a preset number of first reference points of a target vehicle based on each corner point, a plane geometric center point and a coordinate origin of a preset coordinate system provided by an embodiment of the present application;

[0054] Figure 5 is a schematic diagram of a process for determining a second reference point of a target vehicle based on a second driving state parameter and each first reference point provided by an embodiment of the present application;

[0055] Figure 6 is a schematic diagram of determining a third reference point provided by an embodiment of the present application;

[0056] Figure 7 It is a structural schematic diagram of a fusion device of a target vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0058] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0059] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0060] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0061] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0062] The current target fusion mainly processes the target information sent by multiple vehicle-mounted sensors, and fuses the data with the same attributes of the detected targets to obtain detection performance that is better than that of a single sensor.

[0063] In the prior art, when detection data from multiple sensors detect the same target, the target is described in inconsistent forms by each sensor: the first vehicle-mounted sensor describes the target as a three-dimensional target with length, width, and height, while the second vehicle-mounted sensor describes the target as a scanning point without length, width, and height; or, for the same target, due to different installation positions, the field of view angles of the sensors are different, and therefore the position references of the detected targets are inconsistent, resulting in differences in the detection data of each sensor, causing large errors in the association of each sensor with the same target, resulting in errors in the target's fusion data, which in turn causes misoperation of the autonomous driving vehicle, reducing the experience or safety of autonomous driving.

[0064] The existing technology has the problem that the detection data of multiple sensors detecting the same target are different, resulting in errors in the fused data.

[0065] The present application obtains the first driving state parameter and the second driving state parameter of the target vehicle in any frame of the preset area around the autonomous driving vehicle, wherein the first driving state parameter is the driving state parameter of the three-dimensional target formed by the first vehicle-mounted sensor, and the second driving state parameter is the driving state parameter of the point target formed by the second vehicle-mounted sensor; based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle, a preset number of first reference points of the target vehicle are determined; based on the second driving state parameter and each of the first reference points, a second reference point of the target vehicle is determined; if the second reference point and each of the first reference points meet the preset conditions, one of the first reference points is determined as the third reference point of the target vehicle; based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form a fused driving state parameter. Since the third reference point and the second reference point with the closest properties to the first vehicle-mounted sensor and the second vehicle-mounted sensor are determined respectively, and then the fused driving state parameter is obtained by fusion, the detection data of multiple sensors greatly reduces the difference in the detection data of each sensor when detecting the same target vehicle, improves the accuracy of the fused data of the target vehicle, avoids the misoperation of the autonomous driving vehicle, and improves the safety of the autonomous driving vehicle.

[0066] The technical solution of the present application is described below through specific embodiments.

[0067] First, as Figure 1 As shown, this embodiment provides a target vehicle fusion method, including:

[0068] S100, obtaining first driving state parameters and second driving state parameters of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameters are driving state parameters of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameters are driving state parameters of a point target formed by a second vehicle-mounted sensor.

[0069] In the prior art, when the distance between the autonomous driving vehicle and the target vehicle is relatively far (for example, the distance from the autonomous driving vehicle is greater than 20m), the stereoscopic target formed by the target vehicle detected by the first on-board sensor of the stereoscopic target (for example, a camera-type sensor) can be approximately regarded as a point target, and the point target formed by the target vehicle detected by the second on-board sensor of the point target (for example, a millimeter-wave radar-type sensor) is the center of the rear bumper of the target vehicle. The reference points of data fusion are consistent, so no other data processing is required in farther areas, the reference points can be matched and associated normally, and the data fusion of the driving status parameters can be performed.

[0070] However, in a relatively close preset area (for example, the preset area is an area where the distance to the autonomous driving vehicle is less than or equal to 20m), due to the different fields of view of each on-board sensor, the position points of the target vehicle detected by different on-board sensors are inconsistent, and the reference points for associated fusion are inconsistent, resulting in large differences in the driving state parameters of the reference points for associated matching, which in turn causes errors in the fusion data.

[0071] For example, the target vehicle is a large truck that overtakes the autonomous vehicle. The front radar detects the front of the vehicle, and the corner radar detects the rear of the vehicle. Or, when the camera identifies the front orientation angle of the large truck (the front orientation angle is the angle formed by the front direction of the autonomous vehicle and the front direction of the target vehicle), there is a large difference in the position description of the target vehicle large truck (for example, the position point is misplaced by one vehicle body, or the position point is offset). All of the above situations cause the reference points of the associated fusion of different on-board sensors to be inconsistent, resulting in large differences in the driving state parameters of the reference points for associated matching, which in turn causes errors in the fusion data.

[0072] In one embodiment, a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle are obtained, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor. This is beneficial for determining a suitable reference point based on the driving state parameters of the target vehicle that have been obtained in order to perform data fusion.

[0073] S200, determining a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle.

[0074] In one embodiment, the first driving state parameter includes the vehicle head orientation angle and the three-dimensional coordinates of the target vehicle. The image data of the stereoscopic target acquired by the first vehicle-mounted sensor is converted into the three-dimensional coordinates of the target vehicle, and the vehicle head orientation angle of the target vehicle is acquired, which is conducive to selecting the reference point of the target vehicle.

[0075] In one embodiment, Figure 2 As shown, based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle, the step of determining a preset number of first reference points of the target vehicle includes:

[0076] S210, determining the two-dimensional plane coordinates of the target vehicle in a preset coordinate system based on the three-dimensional coordinates of the target vehicle, where the preset coordinate system is a two-dimensional plane coordinate system with the first on-board sensor of the autonomous driving vehicle as the coordinate origin.

[0077] In one embodiment, the two-dimensional plane coordinates of the target vehicle in a preset coordinate system are determined based on the three-dimensional coordinates of the target vehicle. Converting the three-dimensional coordinates into two-dimensional plane coordinates is beneficial to reducing the workload of the autonomous driving vehicle, facilitating the rapid determination of reference points, and improving the response speed of the autonomous driving vehicle.

[0078] S220, determining a plane geometric center point of the target vehicle based on the two-dimensional plane coordinates of the target vehicle.

[0079] In one embodiment, the plane geometric center point of the target vehicle is determined based on the two-dimensional plane coordinates of the target vehicle and the geometric relationship between the center point, so as to facilitate the determination of the reference point through the geometric center point.

[0080] S230, based on the vehicle head orientation angle, the two-dimensional plane coordinates and the plane geometric center point, determine four corner points of the target vehicle and four edges formed by the corner points.

[0081] In one embodiment, the two-dimensional plane coordinates of the target vehicle, the two-dimensional plane coordinates of the plane geometric center point and the front heading angle are combined to determine the two-dimensional plane coordinates of the four corner points of the target vehicle, and at the same time, the four edges of the target vehicle formed by the two corner points are determined, so as to facilitate the determination of reference points through corner points and edges.

[0082] It should be noted that if the target vehicle is not a quadrilateral, based on the vehicle head orientation angle, the two-dimensional plane coordinates and the plane geometric center point, the actual situation determines different numbers of corner points and the corresponding edges formed by each corner point.

[0083] S240, determining a preset number of first reference points of the target vehicle based on each corner point, the plane geometric center point and the coordinate origin of the preset coordinate system.

[0084] In one embodiment, based on each corner point, plane geometric center point and the coordinate origin of a preset coordinate system, a preset number of first reference points of the target vehicle are determined in a two-dimensional plane coordinate system according to each corner point and plane geometric center point of the target vehicle, thereby facilitating data fusion of the target vehicle.

[0085] In one embodiment, Figure 3 As shown, the vertical axis of the two-dimensional plane coordinate system is the driving direction from the rear to the front of the autonomous driving vehicle. The direction from the rear to the front of the vertical axis is set to be positive, and the direction from the front to the rear of the vertical axis is set to be negative. The horizontal axis of the two-dimensional plane coordinate system is perpendicular to the vertical axis. When looking down at the target vehicle, the horizontal axis is set to be positive from the left to the right direction of the target vehicle and negative from the right to the left direction of the target vehicle, so as to facilitate the judgment of the direction information and posture information of the target vehicle. Among them, the vertical axis is set to the X-axis and the horizontal axis is set to the Y-axis.

[0086] In one embodiment, Figure 4As shown, the step of determining a preset number of first reference points of the target vehicle based on each corner point, the plane geometric center point and the coordinate origin of the preset coordinate system includes:

[0087] S241, based on the plane geometric center point and the coordinate origin of the preset coordinate system, determine the angle between the center point of the plane geometric center point and the coordinate origin.

[0088] In one embodiment, the plane geometric center point and the coordinate origin O of the preset coordinate system are connected to form a first side, and the X-axis of the two-dimensional plane coordinate system is the second side. The first side and the second side form an angle A between the center point of the plane geometric center point and the coordinate origin.

[0089] S242, based on each corner point and the coordinate origin of the preset coordinate system, determining a corresponding corner point angle formed by each corner point and the coordinate origin.

[0090] In one embodiment, each corner point is connected to the coordinate origin O of the preset coordinate system to form a first side, and the X-axis of the two-dimensional plane coordinate system is taken as the second side. The first side and the second side form a corresponding corner point angle B between each corner point and the coordinate origin. In this embodiment, since there are four corner points, the corner point angles include a first corner point angle B1, a second corner point angle B2, a third corner point angle B3 and a fourth corner point angle B4.

[0091] S243, performing difference calculations based on the center point angle and the angles of each corner point to determine the corner point angle differences corresponding to the angles of each corner point.

[0092] In one embodiment, the degree of the center point angle A is sequentially subtracted from the angles B of each corner point to determine the corner point angle difference corresponding to each corner point angle B, so as to facilitate determination of the direction and position of the geometric center point and each corner point relative to the autonomous driving vehicle, so as to determine the reference point; in this embodiment, since there are four corner points, the corner point angle differences include a first corner point angle difference C1, a second corner point angle difference C2, a third corner point angle difference C3 and a fourth corner point angle difference C4.

[0093] S244: Determine the minimum corner point angle difference based on the corner point angle differences.

[0094] In one embodiment, the minimum corner point angle difference is determined from the first corner point angle difference C1, the second corner point angle difference C2, the third corner point angle difference C3 and the fourth corner point angle difference C4, indicating that the corner point corresponding to the minimum corner point angle difference is more consistent with the geometric center point relative to the direction of the autonomous driving vehicle.

[0095] S245: Determine the corner point corresponding to the minimum corner point angle difference and the corner point farthest from the autonomous driving vehicle as the farthest corner point.

[0096] In one embodiment, the corner point corresponding to the minimum corner point angle difference and the corner point farthest from the autonomous driving vehicle is determined as the farthest corner point, so as to avoid misjudging the corner point close to the autonomous driving vehicle as the farthest corner point when the corner point close to the autonomous driving vehicle, the corner point far from the autonomous driving vehicle and the geometric center point are in a straight line relative to the autonomous driving vehicle, thereby improving the accuracy of the farthest corner point.

[0097] S246, based on the two-dimensional plane coordinates of the target vehicle and the farthest corner point, determine two sides far away from the farthest corner point and three corner points corresponding to the two sides.

[0098] In one embodiment, based on the two-dimensional plane coordinates and the farthest corner point of the target vehicle, two edges connected to the farthest corner point are excluded, and two edges far away from the farthest corner point and three corner points corresponding to the two edges are selected, so as to facilitate the selection of a point closer to the autonomous driving vehicle as a reference point to reduce the fusion error.

[0099] S247, forming five first reference points based on the midpoints corresponding to the two sides farthest from the farthest corner point and the three corner points.

[0100] In one embodiment, the midpoints corresponding to the two sides farthest from the farthest corner point and three corner points are selected to form five first reference points, such as Figure 3 As shown, the limited selection of 5 points instead of more points can reduce the amount of calculation during data fusion and reduce the load of the autonomous driving vehicle, thereby improving the response speed of the autonomous driving vehicle and improving the safety and experience of the autonomous driving vehicle.

[0101] In another embodiment, the step of determining a preset number of first reference points of the target vehicle based on the corner points, the plane geometric center point and the coordinate origin of the preset coordinate system includes:

[0102] Based on the geometric center point of the plane, the angle of the vehicle head and the coordinate origin of the preset coordinate system, two sides close to the autonomous driving vehicle are determined; five first reference points are formed based on the midpoints and three corner points corresponding to the two sides close to the autonomous driving vehicle.

[0103] S300: Determine a second reference point of the target vehicle based on the second driving state parameter and each first reference point.

[0104] In one embodiment, the second reference point of the target vehicle is determined based on the second driving state parameter and each first reference point, so as to facilitate selecting the second reference point of the target vehicle that is more relevant to each first reference point.

[0105] In one embodiment, the second driving state parameter includes a radar target point of the target vehicle in a preset coordinate system.

[0106] In one embodiment, Figure 5As shown, the step of determining the second reference point of the target vehicle based on the second driving state parameter and each first reference point includes:

[0107] S310, determining an angle between the target point and the longitudinal axis based on the radar target point and the coordinate origin.

[0108] In one embodiment, a line connecting the radar target point and the coordinate origin forms a first side, an X-axis of the two-dimensional plane coordinate is a second side, and the first side and the second side form a target point angle.

[0109] S320: Determine the angle between the first reference point and the vertical axis based on the first reference points and the coordinate origin.

[0110] In one embodiment, each first reference point is connected with the coordinate origin to form a first side, the X-axis of the two-dimensional plane coordinate is the second side, and the first side and the second side form a first reference point angle corresponding to each first reference point; in this embodiment, since the number of first reference points is 5, the first reference point angle formed corresponding to the first reference points is also 5.

[0111] S330: If the angle between the target point and the angles between the first reference points meet a preset requirement, determine the radar target point as a second reference point of the target vehicle.

[0112] In one embodiment, if the included angle of the target point and the included angle of each first reference point meet the preset requirements, it is convenient to screen the radar target point that meets the preset requirements as the second reference point of the target vehicle.

[0113] In one embodiment, the preset requirement is that the target point angle is greater than or equal to the minimum value of the angles of the first reference points, and less than or equal to the maximum value of the angles of the first reference points, indicating that the radar point target that meets the preset requirement is between the lines connecting the first reference points and the coordinate origin, and the radar point target has a relatively large correlation with each reference point, which is conducive to data fusion and reduces the error of the driving state parameters after fusion.

[0114] S400: If the second reference point and each first reference point satisfy a preset condition, determine a first reference point as a third reference point of the target vehicle.

[0115] In one embodiment, the first reference points that meet the preset conditions are screened through the preset conditions of the second reference point and each first reference point, so as to determine that a certain first reference point among the first reference points is the third reference point of the target vehicle, so as to increase the correlation between the first reference point and the second reference point that meet the preset conditions, facilitate data fusion, further reduce the error of the driving state parameters after fusion, and improve the accuracy of the fused driving state parameters.

[0116] In one embodiment, the preset conditions include a first preset condition, a second preset condition and a third preset condition, the first driving state parameter includes a first longitudinal speed and a first lateral speed, and the second driving state parameter includes a second longitudinal speed and a second lateral speed.

[0117] In one embodiment, if the second reference point and each first reference point meet a preset condition, the step of determining a first reference point as a third reference point of the target vehicle includes:

[0118] If the difference between the first longitudinal speed of the second reference point and the second longitudinal speed of each first reference point meets the first preset condition, the difference between the first lateral speed of the second reference point and the second lateral speed of each first reference point meets the second preset condition, and the straight-line distance between the coordinate position of the second reference point and the coordinate position of each first reference point meets the third preset condition, a first reference point is determined as the third reference point of the target vehicle. The screened first reference point has a greater correlation with the second reference point in terms of longitudinal speed, lateral speed and straight-line distance, which is further conducive to data fusion, further reduces the error of the fused driving state parameters, and improves the accuracy of the fused driving state parameters. Among them, the straight-line distance is the radial distance squared of the square of the lateral distance between the coordinate position of the second reference point and the coordinate position of a first reference point plus the square of the longitudinal distance, such as Figure 6 shown.

[0119] In one embodiment, the first preset condition is that the difference between the first longitudinal velocity of the second reference point and the second longitudinal velocity of each first reference point is less than or equal to the first preset threshold; the second preset condition is that the difference between the first lateral velocity of the second reference point and the second lateral velocity of each first reference point is less than or equal to the second preset threshold; the third preset condition is that the straight-line distance between the coordinate position of the second reference point and the coordinate position of each first reference point is less than or equal to the third preset threshold, and the first reference point corresponding to the minimum straight-line distance. In one embodiment, the first preset threshold is less than or equal to 3m / s, the second preset threshold is less than or equal to 2m / s, and the third preset threshold is less than or equal to 6m.

[0120] In one embodiment, the preset conditions also include a fourth preset condition; as the autonomous driving vehicle and the target vehicle move, a first reference point that is more suitable for matching the second reference point will appear after the current frame. Therefore, if the straight-line distances between the coordinate positions of the second reference point of the next frame and the coordinate positions of the first reference points respectively meet the fourth preset condition, the first reference point is updated to be the third reference point of the target vehicle.

[0121] In one embodiment, the fourth preset condition is that the difference between the straight-line distance between the coordinate position of the second reference point of the current frame and the coordinate position of the first reference point and the straight-line distance between the coordinate position of the second reference point of the next frame and the coordinate position of the first reference point is less than or equal to the fourth preset threshold value and the difference is greater than 0, indicating that the straight-line distance between the first reference point and the second reference point of the next frame has become smaller, and the correlation with the second reference point is greater, and it is more suitable as a fused reference point, further reducing the error of the fused driving state parameters, further improving the accuracy of the fused driving state parameters, and also improving the matching stability of the first reference point and the second reference point. In one embodiment, the fourth preset threshold value is less than or equal to 0.3m.

[0122] S500: Based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are integrated to form an integrated driving state parameter.

[0123] In one embodiment, the second reference point is associated with the third reference point, and then the first driving state parameter of the second reference point and the second driving state parameter of the third reference point are combined to form a fused driving state parameter according to a fusion rule.

[0124] Compared with the prior art, the present embodiment has the following beneficial effects:

[0125] By acquiring the first driving state parameter and the second driving state parameter of the target vehicle in any frame of the preset area around the autonomous driving vehicle, the first driving state parameter is the driving state parameter of the three-dimensional target formed by the first vehicle-mounted sensor, and the second driving state parameter is the driving state parameter of the point target formed by the second vehicle-mounted sensor; based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle, a preset number of first reference points of the target vehicle are determined; based on the second driving state parameter and each first reference point, a second reference point of the target vehicle is determined; if the second reference point and each first reference point meet the preset conditions, a first reference point is determined as the third reference point of the target vehicle; based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form a fused driving state parameter. Since the third reference point and the second reference point with the closest properties to the first vehicle-mounted sensor and the second vehicle-mounted sensor are determined respectively, and then the fused driving state parameter is obtained by fusion, the detection data of multiple sensors greatly reduces the difference in the detection data of each sensor when detecting the same target vehicle, improves the accuracy of the fused data of the target vehicle, avoids the misoperation of the autonomous driving vehicle, and improves the safety of the autonomous driving vehicle.

[0126] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0127] Second, as Figure 7 As shown, this embodiment provides a fusion device for a target vehicle, including:

[0128] An acquisition module 100 is used to acquire a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor;

[0129] A first determination module 200, configured to determine a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle;

[0130] A second determination module 300, configured to determine a second reference point of the target vehicle based on the second driving state parameter and each of the first reference points;

[0131] A third determination module 400, configured to determine one of the first reference points as a third reference point of the target vehicle if the second reference point and each of the first reference points meet a preset condition;

[0132] The fusion module 500 is used to fuse the first driving state parameter and the second driving state parameter to form a fused driving state parameter based on the second reference point and the third reference point.

[0133] It should be noted that the information interaction, execution process, etc. between the above-mentioned devices / modules are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0134] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0135] In a third aspect, an embodiment of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements a method as described in any one of the contents of the first aspect above.

[0136] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the method as described in any one of the contents of the first aspect above is implemented.

[0137] In a fifth aspect, an embodiment of the present application provides a computer program product, which, when executed on a terminal device, enables the terminal device to execute any of the methods described in the first aspect above.

[0138] It can be understood that the beneficial effects of the second to fifth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here.

[0139] A target vehicle fusion method provided in an embodiment of the present application can be applied to terminal devices such as mobile phones, tablet computers, wearable devices, vehicle-mounted devices, augmented reality (AR) / virtual reality (VR) devices, laptop computers, ultra-mobile personal computers (UMPC), netbooks, personal digital assistants (PDA), etc. The embodiment of the present application does not impose any restrictions on the specific type of the terminal device.

[0140] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by a processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0141] The computer-readable medium may include at least: any entity or device capable of carrying computer program codes to a camera / terminal device, a recording medium, a computer memory, a read-only memory (ROM), a random access memory (RAM), an electric carrier signal, a telecommunication signal, and a software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk, or an optical disk. In some jurisdictions, according to legislation and patent practice, a computer-readable medium cannot be an electric carrier signal or a telecommunication signal.

[0142] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0143] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0144] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment and methods can be implemented in other ways. For example, the device / network equipment embodiments described above are merely schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0145] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0146] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A target vehicle fusion method, characterized in that: include: Acquire a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor; Determining a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle; Determining a second reference point of the target vehicle based on the second driving state parameter and each of the first reference points; If the second reference point and each of the first reference points meet a preset condition, determining one of the first reference points as a third reference point of the target vehicle; Based on the second reference point and the third reference point, the first driving state parameter and the second driving state parameter are fused to form a fused driving state parameter.

2. The method according to claim 1, characterized in that The first driving state parameter includes a vehicle head orientation angle and the three-dimensional coordinates of the target vehicle, wherein the vehicle head orientation angle is an angle formed by the vehicle head direction of the autonomous driving vehicle and the vehicle head direction of the target vehicle; The step of determining a preset number of first reference points of the target vehicle based on the geometric relationship between the first driving state parameter and the autonomous driving vehicle comprises: Determine the two-dimensional plane coordinates of the target vehicle in a preset coordinate system based on the three-dimensional coordinates of the target vehicle, wherein the preset coordinate system is a two-dimensional plane coordinate system with the first on-board sensor of the autonomous driving vehicle as the coordinate origin; Determining a plane geometric center point of the target vehicle based on the two-dimensional plane coordinates of the target vehicle; Based on the vehicle head orientation angle, the two-dimensional plane coordinates and the plane geometric center point, determine the four corner points of the target vehicle and the four sides formed by the corner points; A preset number of first reference points of the target vehicle are determined based on each of the corner points, the plane geometric center point and the coordinate origin of the preset coordinate system.

3. The method according to claim 2, characterized in that The longitudinal axis of the two-dimensional plane coordinate system is along the driving direction from the rear end to the front end of the autonomous driving vehicle, and the transverse axis of the two-dimensional plane coordinate system is perpendicular to the longitudinal axis; The step of determining a preset number of first reference points of the target vehicle based on each of the corner points, the plane geometric center point and the coordinate origin of the preset coordinate system comprises: Based on the plane geometric center point and the coordinate origin of the preset coordinate system, determining the angle between the center point of the plane geometric center point and the coordinate origin; Based on each of the corner points and the coordinate origin of the preset coordinate system, determining a corresponding corner point angle formed by each of the corner points and the coordinate origin; Based on the difference calculation between the center point angle and each of the corner point angles, determine the corner point angle difference corresponding to each of the corner point angles; Determine the minimum corner point angle difference based on the angle differences of each corner point; Determine the corner point corresponding to the minimum corner point angle difference and the corner point farthest from the autonomous driving vehicle as the farthest corner point; Determine two sides away from the farthest corner point and three corner points corresponding to the two sides based on the two-dimensional plane coordinates of the target vehicle and the farthest corner point; Five first reference points are formed based on midpoints corresponding to two sides far away from the farthest corner point and the three corner points.

4. The method according to claim 1, characterized in that The second driving state parameter includes a radar target point of the target vehicle in a preset coordinate system, wherein the preset coordinate system is a two-dimensional plane coordinate system with a first on-board sensor of the autonomous driving vehicle as a coordinate origin, the longitudinal axis of the two-dimensional plane coordinate system is in a direction from the front to the rear of the autonomous driving vehicle, and the transverse axis of the two-dimensional plane coordinate system is perpendicular to the longitudinal axis; The step of determining the second reference point of the target vehicle based on the second driving state parameter and each of the first reference points includes: Determine the angle between the target point and the longitudinal axis based on the radar target point and the coordinate origin; Determine the first reference point angle with the longitudinal axis based on each of the first reference points and the coordinate origin respectively; If the angle between the target point and each of the first reference points meets a preset requirement, the radar target point is determined to be a second reference point of the target vehicle.

5. The method according to claim 4, characterized in that The preset requirement is that the target point angle is greater than or equal to the minimum value of the first reference point angles, and less than or equal to the maximum value of the first reference point angles.

6. The method according to claim 1, characterized in that The preset conditions include a first preset condition, a second preset condition and a third preset condition, the first driving state parameter includes a first longitudinal speed and a first lateral speed, and the second driving state parameter includes a second longitudinal speed and a second lateral speed; The step of determining one of the first reference points as the third reference point of the target vehicle if the second reference point and each of the first reference points meet a preset condition comprises: If the difference between the first longitudinal velocity of the second reference point and the second longitudinal velocity of each of the first reference points satisfies a first preset condition, the difference between the first lateral velocity of the second reference point and the second lateral velocity of each of the first reference points satisfies a second preset condition, and the straight-line distance between the coordinate position of the second reference point and the coordinate position of each of the first reference points satisfies a third preset condition, the first reference point is determined to be the third reference point of the target vehicle.

7. The method according to claim 6, characterized in that The preset conditions also include a fourth preset condition; If the straight-line distances between the coordinate positions of the second reference point in the next frame and the coordinate positions of each of the first reference points respectively meet a fourth preset condition, one of the first reference points is updated to be the third reference point of the target vehicle.

8. A target vehicle fusion device, characterized in that: include: An acquisition module, used to acquire a first driving state parameter and a second driving state parameter of a target vehicle in any frame of a preset area around the autonomous driving vehicle, wherein the first driving state parameter is a driving state parameter of a three-dimensional target formed by a first vehicle-mounted sensor, and the second driving state parameter is a driving state parameter of a point target formed by a second vehicle-mounted sensor; A first determination module, configured to determine a preset number of first reference points of the target vehicle based on a geometric relationship between the first driving state parameter and the autonomous driving vehicle; A second determination module, configured to determine a second reference point of the target vehicle based on the second driving state parameter and each of the first reference points; A third determination module, configured to determine one of the first reference points as a third reference point of the target vehicle if the second reference point and each of the first reference points meet a preset condition; A fusion module is used to fuse the first driving state parameter and the second driving state parameter to form a fused driving state parameter based on the second reference point and the third reference point.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images