Method, device and equipment for suppressing false alarm point cloud of vehicle hanging body and medium

Abstract

The invention provides a method, a device, equipment and a medium for suppressing false alarm point cloud of a vehicle hanging body, and the method comprises the steps: determining the yaw velocity of a vehicle head based on the longitudinal velocity of the vehicle head and the wheelbase of the vehicle head; when a vehicle runs, an included angle possibly exists between a vehicle head and the hanging body, a speed balance equation at the hanging point is established based on the included angle, and the lateral speed of the hanging body is determined. And determining the yaw velocity of the hanging body based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point. And determining an included angle based on a difference value between the vehicle head yaw velocity and the hanging body yaw velocity. And converting the point cloud acquired by the radar by using the included angle, and determining the converted point cloud. In the converted point clouds, target false alarm point clouds located in a filtering area are determined and filtered out, and the filtering area is determined by fitting the edge of a hanging body through the point clouds collected by a radar in the straight moving process of the vehicle.

Description

Technical Field

[0001] This application relates to the field of point cloud data processing technology, specifically to a method, apparatus, equipment, and medium for suppressing false alarm point clouds on vehicle attachments. Background Technology

[0002] In Advanced Driving Assistance Systems (ADAS) of large commercial vehicles, millimeter-wave radar is typically installed near the rear axle at the front of the vehicle. During radar detection, strong reflections and multiple scattering effects from the metal structures of the vehicle's front and suspension components create a type of false alarm point cloud with relatively fixed positions. This causes the ADAS system to misinterpret the false alarm point cloud as real obstacle targets, thus interfering with the ADAS function.

[0003] Current methods for suppressing false alarm signals mainly involve fitting the outline of the vehicle body to historical multi-frame point clouds, and then filtering the false alarm point clouds based on this outline. However, this method is highly dependent on the spatial distribution of the point cloud. If the vehicle is turning or pitching, the relative displacement and attitude changes between the front of the vehicle and the vehicle body will cause the point cloud collected by the radar to be asymmetrical, making it difficult to fit an accurate outline of the vehicle body, and thus difficult to accurately suppress the false alarm point cloud. Summary of the Invention

[0004] In view of this, this application aims to provide a method, apparatus, device and medium for suppressing false alarm point clouds on vehicle attachments, so as to improve the accuracy of suppressing false alarm point clouds.

[0005] In a first aspect, this application provides a method for suppressing false alarm point clouds of vehicle attachments, the method comprising: The yaw rate of the vehicle front is determined based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front. Based on the angle between the vehicle head and the hanging body, a velocity balance equation is established at the hanging point to determine the lateral velocity of the hanging body; The lateral velocity of the hanging body is determined based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point; The included angle is determined based on the difference between the yaw rate of the vehicle front and the yaw rate of the hanging body. The point cloud acquired by the radar is transformed using the included angle to determine the transformed point cloud; In the converted point cloud, false alarm point clouds of targets located within the filtering area are identified and filtered out. The filtering area is determined by fitting the edge of the hanging body with the point cloud collected by radar during the straight-moving process of the vehicle.

[0006] In one possible implementation, the process of determining the filtering region includes: When the vehicle is traveling in a straight line, acquire multiple frames of raw point cloud data collected by a single-sided radar. False alarm point clouds are obtained by filtering based on the velocity of the original point clouds in multiple frames. The straight line at the edge of the hanging object is obtained by fitting the false alarm point cloud. In the false alarm point cloud, determine the target point cloud that is farthest from the single-sided radar; The length of the hanging object is determined based on the projection point of the target point cloud onto the straight line; The filtering area is determined based on the length.

[0007] In one possible implementation, the step of filtering based on the velocity of multiple frames of the original point cloud to obtain a false alarm point cloud includes: The original point cloud from multiple frames is transformed into the vehicle coordinate system to obtain the transformed point cloud; The converted point cloud is filtered based on a preset acquisition area to determine the set of point clouds located within the preset acquisition area; Point clouds with speeds less than a preset value are selected from the point cloud set and designated as false alarm point clouds.

[0008] In one possible implementation, determining the lateral velocity of the suspension body by establishing a velocity balance equation at the attachment point based on the angle between the vehicle front and the suspension body includes: The lateral velocity of the vehicle front is determined based on the yaw rate of the vehicle front and the distance between the rear axle of the vehicle front and the attachment point. Based on the included angle, the longitudinal velocity of the vehicle head and the lateral velocity of the vehicle head are determined as two lateral components in the direction of the lateral velocity of the hanging body; A velocity balance equation is established based on the two lateral components and the lateral velocity of the hanging body to determine the lateral velocity of the hanging body.

[0009] In one possible implementation, the step of transforming the radar-acquired point cloud using the included angle and determining the transformed point cloud includes: Determine the rotation matrix based on the included angle and the coordinates of the hanging point; Based on the point cloud acquired by the radar and the rotation matrix, the transformed point cloud is determined.

[0010] In one possible implementation, determining the transformed point cloud based on the point cloud acquired by the radar and the rotation matrix includes: Determine the target radial velocity of the point cloud located at the hanging point; In the point cloud acquired by the radar, point clouds with velocities less than or equal to the radial velocity of the target are selected as candidate point clouds; The candidate point cloud is transformed using the rotation matrix to obtain the transformed point cloud.

[0011] In one possible implementation, determining the target radial velocity of the point cloud located at the hanging point includes: Based on the included angle, the longitudinal velocity of the vehicle head and the lateral velocity of the vehicle head are determined as two longitudinal components in the longitudinal velocity direction of the hanging body, respectively. A velocity balance equation is established based on the two longitudinal components and the longitudinal velocity of the hanging body to determine the longitudinal velocity of the hanging body; The components of the longitudinal velocity of the vehicle head, the longitudinal velocity of the attachment body, and the lateral velocity of the attachment body in the direction of the line connecting the attachment point and the radar are determined as the radial velocity of the target.

[0012] Secondly, this application provides a device for suppressing false alarm point clouds of vehicle attachments, the device comprising: The first angular velocity determination unit is used to determine the yaw rate of the vehicle front based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front. The lateral velocity determination unit is used to establish a velocity balance equation at the attachment point based on the angle between the vehicle head and the hanging body, and to determine the lateral velocity of the hanging body. The second angular velocity determination unit is used to determine the yaw rate of the hanging body based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point; Angle determination unit is used to determine the included angle based on the difference between the yaw rate of the vehicle front and the yaw rate of the hanging body; A conversion unit is used to convert the point cloud acquired by the radar using the included angle, and to determine the converted point cloud; A suppression unit is used to identify and filter out false alarm point clouds of targets located within a filtering area in the converted point cloud, wherein the filtering area is determined by fitting the edge of the hanging body with a point cloud collected by radar during the straight-moving process of the vehicle.

[0013] Thirdly, this application provides an electronic device, the device comprising: a memory and a processor; The memory is used to store the relevant program code; The processor is used to call the program code to execute the method for suppressing false alarm point clouds of vehicle attachments as described in any of the implementations of the first aspect above.

[0014] Fourthly, this application provides a computer-readable storage medium for storing a computer program for executing the method for suppressing false alarm point clouds of vehicle attachments as described in any implementation of the first aspect above.

[0015] Fifthly, this application provides a computer program product, which includes a computer program / instruction, and when the computer program / instruction is executed by a processor, it implements the method for suppressing false alarm point clouds of vehicle attachments as described in any of the implementations of the first aspect.

[0016] In the above implementation of this application, a filtering region for suppressing false alarm point clouds can be determined in advance during the straight-moving process of the vehicle, i.e., the area where false alarm point clouds may exist. During straight-moving, the angle between the front of the vehicle and the suspension is 0°. This filtering region is determined by fitting the edge of the suspension using point clouds collected by radar. Then, during subsequent vehicle movement, the pre-determined filtering region is used to suppress false alarm point clouds generated by the suspension. Specifically, the Ackerman steering model can be referenced, and the yaw rate of the front of the vehicle can be determined based on the longitudinal velocity of the front of the vehicle and the wheelbase. When the vehicle is moving, there may be an angle between the front of the vehicle and the suspension. Based on this angle, a velocity balance equation can be established at the suspension point to determine the lateral velocity of the suspension. The yaw rate of the suspension is determined based on the lateral velocity of the suspension and the distance between the rear axle of the suspension and the suspension point. Since the angle between the vehicle's front end and the suspension can be understood as the difference between the vehicle's yaw angle and the suspension's yaw angle, the angle can be determined based on this difference. The radar-acquired point cloud is then transformed using this angle, converting it to a coordinate system where there is no angle between the vehicle's front end and the suspension. This allows for the suppression of false alarms within a filtering region. Specifically, within the false alarm point cloud, target false alarm points located within the filtering region are identified and filtered out. The method provided in this application is applicable to situations where there is an angle between the vehicle's front end and the suspension when the vehicle is turning. By determining the angle between the vehicle's front end and the suspension, the radar-acquired point cloud can be transformed. Combined with the filtering region determined during the vehicle's straight-line movement, false alarm points can be identified, thus suppressing them and improving the accuracy of false alarm suppression. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments provided in this application. For those skilled in the art, other drawings can be obtained based on these drawings.

[0018] Figure 1 This is a schematic diagram of a vehicle provided in an embodiment of this application.

[0019] Figure 2 This is a flowchart for determining a filtering region, provided as an embodiment of this application.

[0020] Figure 3 A flowchart illustrating a method for suppressing false alarm point clouds associated with vehicle attachments, provided in this application embodiment.

[0021] Figure 4 This is a schematic diagram of another vehicle provided in an embodiment of this application.

[0022] Figure 5 This is a schematic diagram illustrating a point cloud conversion method provided in an embodiment of this application.

[0023] Figure 6 This is a schematic diagram illustrating the relative positions of the vehicle front and the trailer as provided in an embodiment of this application.

[0024] Figure 7 This is a schematic diagram of a device for suppressing false alarm point clouds on vehicle attachments, provided in an embodiment of this application.

[0025] Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0026] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. The described embodiments are merely exemplary implementations of this application and not all implementation methods. Those skilled in the art can obtain other embodiments in conjunction with the embodiments of this application without creative effort, and these embodiments are also within the protection scope of this application.

[0027] In ADAS systems for large commercial vehicles, millimeter-wave radar is typically installed near the rear axle at the front of the vehicle. During radar detection, strong reflections and multiple scattering effects from the metal structures of the vehicle's front and suspension components create a type of false alarm point cloud with relatively fixed positions. This causes the ADAS system to misinterpret the false alarm point cloud as real obstacle targets, thus interfering with ADAS functionality.

[0028] Current methods for suppressing false alarms mainly involve fitting the outline of the vehicle to historical multi-frame point clouds, and then filtering the false alarm point clouds based on this outline. Alternatively, static point clouds can be separated through vehicle motion compensation, then the accumulated static point clouds can be clustered, and a prior geometric model (such as a rectangular box) can be used for fitting to estimate the outline of the vehicle. Finally, a dynamically updated shielding region is generated based on the fitting results, and point clouds within this shielding region are filtered out during real-time sensing, thereby achieving false alarm suppression.

[0029] However, this method is highly dependent on the spatial distribution of the point cloud. When the vehicle is turning or pitching, the relative displacement and attitude changes between the front of the vehicle and the mounting body cause the point cloud collected by the radar to be asymmetrical. One side of the radar can capture sufficient and stable point cloud signals, while the other side has fewer point cloud and sparser distribution due to geometric obstruction, deviation of the reflective surface angle, and other factors. It is difficult to fit an accurate mounting body contour based on the collected point cloud, and the accuracy of suppressing false alarm point clouds is also reduced.

[0030] Based on this, this application provides a method for suppressing false alarm point clouds from vehicle attachments to improve the accuracy of false alarm point cloud suppression. A filtering region for suppressing false alarm point clouds can be pre-determined during the vehicle's straight-line movement, i.e., the area where false alarm point clouds may exist. During straight-line movement, the angle between the vehicle's front and the attachment is 0°. This filtering region is determined by fitting the edge of the attachment using point clouds acquired by radar. Then, during subsequent vehicle movement, the pre-determined filtering region is used to suppress false alarm point clouds generated by the attachment. Specifically, the Ackermann steering model can be referenced, and the yaw rate of the vehicle's front can be determined based on the longitudinal velocity of the vehicle's front and the wheelbase. When the vehicle is moving, there may be an angle between the vehicle's front and the attachment. Based on this angle, a velocity balance equation can be established at the attachment point to determine the lateral velocity of the attachment. The yaw rate of the attachment is determined based on the lateral velocity of the attachment and the distance between the rear axle of the attachment and the attachment point. Since the angle between the vehicle's front end and the suspension can be understood as the difference between the vehicle's yaw angle and the suspension's yaw angle, the angle can be determined based on this difference. The radar-acquired point cloud is then transformed using this angle, converting it to a coordinate system where there is no angle between the vehicle's front end and the suspension. This allows for the suppression of false alarms within a filtering region. Specifically, within the false alarm point cloud, target false alarm points located within the filtering region are identified and filtered out. The method provided in this application is applicable to situations where there is an angle between the vehicle's front end and the suspension when the vehicle is turning. By determining the angle between the vehicle's front end and the suspension, the radar-acquired point cloud can be transformed. Combined with the filtering region determined during the vehicle's straight-line movement, false alarm points can be identified, thus suppressing them and improving the accuracy of false alarm suppression.

[0031] To facilitate understanding of the technical solutions provided in the embodiments of this application, a detailed description will be given below in conjunction with the accompanying drawings.

[0032] Optionally, after the radar is installed on the vehicle, the installation angle usually needs to be calibrated initially. After radar calibration, a filtering area for suppressing false alarm point clouds can be determined. The filtering area represents the region where false alarm point clouds generated by the attachment may exist, thereby suppressing the point clouds within the filtering area.

[0033] See Figure 1 As shown, Figure 1 This is a schematic diagram of a vehicle provided in an embodiment of this application.

[0034] The vehicle consists of a front end and a mounting frame. Two radars can be installed on both sides of the front end to detect obstacles around the vehicle and assist in performing ADAS functions.

[0035] In one possible implementation, the process of determining the filtering area can be initiated when the vehicle is in a stable straight-line driving state. The stable straight-line driving state can be determined by the following condition: during vehicle operation, the vehicle's yaw rate remains consistently below a preset value to ensure that there is no significant relative angular movement between the vehicle's front and the suspension. Since the radars mounted on both sides are usually symmetrical, the processing of the radar point clouds on both sides is similar; in subsequent embodiments, only a single-sided radar will be used as an example for explanation.

[0036] See Figure 2 As shown, Figure 2 This is a flowchart for determining a filtering region, provided as an embodiment of this application.

[0037] Optionally, this method can be executed by a radar system. This radar system includes a preprocessing module and a real-time processing module, and the preprocessing module can execute the following method.

[0038] The method may include the following steps: S201: When the vehicle is traveling straight, acquire multiple frames of raw point cloud data collected by a single-side radar.

[0039] Multiple frames of raw point cloud data are continuously acquired to cover the effective reflective area of ​​the object. The data for each point cloud can include coordinates, velocity, angle, etc.

[0040] S202: Filter based on the speed of multiple frames of original point clouds to obtain false alarm point clouds.

[0041] Since the vehicle is traveling in a straight line, the relative speed between the mounting device and the radar is theoretically zero. Therefore, the radial speed of the false alarm point cloud generated by the mounting device relative to the radar on one side is also theoretically zero. Thus, the false alarm point cloud generated by the mounting device can be obtained by filtering based on the speed of multiple frames of original point clouds. For example, point clouds with speeds less than a preset value can be selected as false alarm point clouds based on the speed of the original point clouds.

[0042] In one possible implementation, when other vehicles located on both sides of the vehicle are detected by a single-sided radar, the speed of the other vehicles and the relative speed of the vehicle (single-sided radar) are also less than a preset value. Therefore, in order to exclude the point clouds generated by other vehicles, a preset collection area can be pre-determined based on the edge of the attachment to ensure that most of the false alarm point clouds generated by the attachment are located in the preset collection area, while the point clouds of other vehicles are as far away from the preset collection area as possible.

[0043] A preset data collection area can be determined based on the position of the hanging device's edge. The length of this preset area should be greater than the length of the hanging device, and its width should cover the reflective width of the hanging device, but should be as small as possible compared to the width distance between the vehicle and other vehicles. Figure 1 It can be seen that the preset collection area can be set as a rectangular area represented by a dashed line. Figure 1 The vehicle's coordinate system is represented as XOY, the coordinate system of a single-sided radar (left radar) is represented as xOy, and the preset acquisition area marked with a dashed line is represented as D. Then, D can be represented in the vehicle coordinate system as: The unit is meters.

[0044] To facilitate calculations, the original point cloud from the radar coordinate system can be transformed to the vehicle coordinate system based on the transformation relationship between the radar coordinate system and the vehicle coordinate system, resulting in a transformed point cloud in the vehicle coordinate system. Then, the transformed point cloud is filtered using a preset acquisition area to determine the set of point clouds located within that area, thus excluding interference from other vehicles. Finally, point clouds with speeds lower than a preset value are selected from this set, yielding the false alarm point cloud generated by the vehicle attachment.

[0045] S203: Based on the false alarm point cloud, a straight line is obtained from the edge of the hanging object.

[0046] Since the false alarm point cloud generated by the device is the point cloud detected by a single-sided radar at the edge of the device, a straight line can be fitted using the false alarm point cloud to obtain a straight line representing the edge of the device. For example, the least squares method can be used to fit the false alarm point cloud to obtain a straight line passing through the origin, representing the edge of the device. Because the false alarm point cloud is obtained using a single-sided radar, the fitted line represents the straight line of the single-sided edge of the device.

[0047] S204: In the false alarm point cloud, identify the target point cloud that is farthest from a single radar.

[0048] Based on the coordinates of multiple false alarm point clouds, the target point cloud furthest from a single radar can be determined. This target point cloud can represent the point cloud generated at the furthest position of the mounting.

[0049] S205: Determine the length of the hanging object based on the projection points of the target point cloud onto the straight line.

[0050] After determining the target point cloud furthest from the single-sided radar, this target point cloud is projected onto a straight line. The distance between the projected point on the line and the single-sided radar (i.e., the origin) is determined as the length of the mounting. For example, if the equation of the straight line is y=kx, the coordinates of the target point cloud are represented as ( , The target point cloud is projected onto a straight line to obtain the projected point. The distance between the projected point and the origin is expressed as... .

[0051] In one possible implementation, the distance between the projection point determined by the point cloud acquired by the radar on the other side and the origin can be obtained based on the above process. Then calculate and The average value is used as the length of the hanging object.

[0052] S206: Determine the filtering area based on the length of the hanging body.

[0053] Optionally, the filtering area can be defined as a rectangular region. For example, a preset distance can be added to the length of the hanging device to form the length of the filtering area. For instance, the preset distance can be within the range of 1 to 2 meters. The width of the filtering area can be determined based on the actual application scenario; for example, the width of the filtering area can be set to be within the range of 0.5 to 1 meter. For example, denoted by I, the filtering area can be represented as... L represents the length of the hanging part. Values ​​can be taken within the range of 0.5 meters to 1 meter. Values ​​can be taken within a range of 1 to 2 meters.

[0054] It should be noted that the embodiments of this application do not limit the specific shape of the filtering area. The above embodiments are only illustrative examples and are not limited to rectangular areas.

[0055] The process of determining the filtering region provided in the above embodiments can be a preprocessing process, which can store the parameters of the filtering region. Subsequently, during vehicle operation, the pre-stored filtering region can be directly invoked to suppress the point cloud collected by the radar in real time.

[0056] See Figure 3 As shown, Figure 3 A flowchart illustrating a method for suppressing false alarm point clouds associated with vehicle attachments, provided in this application embodiment.

[0057] Optionally, this method can be executed by a radar system, for example, by the real-time processing module of the radar system. In subsequent embodiments, "radar" also refers to a single-side radar at the front of the vehicle, i.e., a left-side radar or a right-side radar.

[0058] The method may include the following steps: S301: Determine the yaw rate of the vehicle front based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front.

[0059] By combining the Ackermann steering model, the yaw rate of the vehicle's front end can be determined based on the longitudinal velocity of the front end and the corresponding turning radius. The turning radius can be determined based on the wheelbase of the vehicle's front end.

[0060] See Figure 4 As shown, Figure 4 This is a schematic diagram of another vehicle provided in an embodiment of this application.

[0061] Where G represents the center of the front axle of the vehicle, and D represents the center of the rear axle of the vehicle. The velocity of the vehicle at point G can be decomposed into the longitudinal velocity of the vehicle. (Longitudinal velocity of the front of the vehicle at the front wheels) and lateral velocity of the front of the vehicle (The lateral velocity of the vehicle's front end at the front wheels). The steering angle of the front wheels is... This represents the angle between the vehicle's front speed and its longitudinal axis. The longitudinal speed and front wheel steering angle can be measured by vehicle sensors. The wheelbase of the vehicle's front is... ,and The parameters are known.

[0062] according to Figure 4 It can be seen that the longitudinal velocity of the car front The corresponding turning radius is QD, which can be represented as L2 / Therefore, the yaw rate of the front of the car It can be represented as .

[0063] S302: Based on the angle between the front of the vehicle and the attached body, establish the speed balance equation at the attachment point to determine the lateral speed of the attached body.

[0064] The cab and the trailer are connected via a coupling point. To ensure relative stability between the cab and the trailer, the resultant velocity of the cab and the trailer at the coupling point should be zero. This resultant velocity at the coupling point includes: the lateral velocity of the trailer (lateral velocity of the trailer at the coupling point) and the longitudinal velocity of the trailer (longitudinal velocity of the trailer at the coupling point), as well as the longitudinal velocity of the cab (longitudinal velocity of the cab at the coupling point) and the lateral velocity of the cab (lateral velocity of the cab at the coupling point). Since both the midpoint of the front wheels and the coupling point are located on the vehicle's longitudinal axis, the longitudinal velocity of the cab at the coupling point is the same as the longitudinal velocity of the cab at the front wheels.

[0065] To determine the lateral velocity of the trailer, the lateral and longitudinal velocities of the truck front can be decomposed into two lateral components in the direction of the trailer's lateral velocity, based on the angle between the truck front and the trailer. A velocity balance equation is then established based on these two lateral components and the trailer's lateral velocity to determine the trailer's lateral velocity. Similarly, the lateral and longitudinal velocities of the truck front can also be decomposed into components in the direction of the trailer's longitudinal velocity, based on the angle between the truck front and the trailer, and a velocity balance equation is established to determine the trailer's longitudinal velocity.

[0066] according to Figure 4 It can be seen that the angle between the front of the vehicle and the hanging body is expressed as At this time, the included angle As an unknown, Indicates the lateral speed of the hanging body, Indicates the longitudinal speed of the hanging body. Indicates the lateral speed of the vehicle's front end. This indicates the longitudinal velocity of the vehicle's front end. It also indicates the lateral velocity of the vehicle's front end. and longitudinal speed of the front of the car Decomposed into lateral velocity of the hanging body By establishing the velocity balance equations for the directional components, we can obtain: Similarly, the speed of the car's front side... and longitudinal speed of the front of the car Decomposed into longitudinal velocity of the hanging body By establishing the velocity balance equations for the directional components, we can obtain: .

[0067] in, Figure 4 The lateral velocity of the hanging body marked in the figure Longitudinal speed of the hanging body lateral speed of the vehicle front longitudinal speed of the car front The direction is only an illustrative example; other forms may exist in actual application scenarios, and the velocity balance equation can be established based on the same principle.

[0068] In one possible implementation, the lateral velocity of the vehicle's front end may not be measurable by vehicle sensors. In this case, the Ackerman steering model can be used to determine the yaw rate based on the ratio between the lateral velocity and the corresponding turning radius. Since the yaw rate has already been calculated using the aforementioned embodiments, the lateral velocity of the front end can be determined based on the yaw rate and the corresponding turning radius. The turning radius corresponding to the lateral velocity is the distance between the coupling point and the rear axle of the front end. Therefore, the lateral velocity of the front end can be determined based on the yaw rate and the distance between the rear axle and the coupling point.

[0069] according to Figure 4It can be seen that the distance between the rear axle of the front of the vehicle and the attachment point P is PD, denoted as d, and the yaw rate of the front of the vehicle is... Represented as Therefore, the lateral speed of the car's front end It can be represented as Then the lateral velocity of the hanging body. It can be represented as Among them, the angle between the front of the vehicle and the hanging body. The unknown variable is the lateral velocity of the suspended body. It can be represented as the included angle. The relational expression.

[0070] S303: Determine the yaw rate of the hanger based on the lateral velocity of the hanger and the distance between the rear axle of the hanger and the hanging point.

[0071] By combining the Ackermann steering model, the yaw rate of the suspension can be determined based on the lateral velocity of the suspension at the attachment point and the corresponding steering radius. The steering radius corresponding to the lateral velocity can be expressed as the distance between the rear axle of the suspension and the attachment point. Therefore, the yaw rate of the suspension can be determined based on the lateral velocity and the distance between the rear axle and the attachment point.

[0072] according to Figure 4 It can be seen that the center of the rear axle of the hanging device is H, and the distance between the rear axle of the hanging device and the hanging point P is PH, which is represented as ,and These are known parameters. Let represent the yaw rate of the hanging body. It can be represented as .

[0073] S304: Determine the included angle based on the difference between the yaw rate of the vehicle's front end and the yaw rate of the attached body.

[0074] The angle between the front of the vehicle and the attached body can be understood as the yaw angle of the front of the vehicle. The horizontal angle of the hanging body The difference between them, therefore, the difference between the yaw rate of the vehicle front and the yaw rate of the suspension body can be expressed as the rate of change of the included angle. rate of change of included angle Indicates the included angle The first derivative with respect to time t, the angle This can represent the angle between the initial moment of vehicle turning and the current moment. The yaw rate of the suspension body can be expressed as an angle. Therefore, the relationship can be established, and the included angle can be established. The differential equation can be used to determine the included angle. .

[0075] Among them, the rate of change of the included angle Yaw rate of the front of the car angular velocity of the hanging body Then the rate of change of the included angle It can be represented as Solving the differential equation allows us to determine the included angle. .

[0076] S305: Use the included angle to transform the point cloud acquired by the radar and determine the transformed point cloud.

[0077] Since the filtering area is determined when the vehicle is traveling straight, that is, the angle between the attachment and the front of the vehicle is theoretically 0°, in order to determine the false alarm point cloud generated by the attachment, when there is an angle between the front of the vehicle and the attachment, the point cloud collected by the radar can be converted using the angle, that is, converted to the position where the angle between the attachment and the front of the vehicle is 0°, so as to determine the converted point cloud.

[0078] See Figure 5 As shown, Figure 5 This is a schematic diagram illustrating a point cloud conversion method provided in an embodiment of this application.

[0079] according to Figure 5 It can be seen that the angle between the front of the vehicle and the hanging body is By using the included angle, any point cloud R1 of the hanging body can be rotated to the position of point cloud R2 with the hanging point P as the rotation center. After rotation, the hanging body corresponds to the area indicated by the dashed line. At this time, the included angle between the hanging body and the front of the vehicle is 0°.

[0080] In one possible implementation, a rotation matrix can be determined based on the angle between the vehicle front and the mounting body and the coordinates of the mounting point. Then, the point cloud acquired by the radar can be transformed based on the rotation matrix to determine the transformed point cloud.

[0081] In practice, for ease of calculation, the coordinates of the attachment point are represented using coordinates in the vehicle coordinate system, and the coordinates of the attachment point are assumed to be known values, which can be represented as P( Then, the rotation matrix A can be expressed as: For point clouds acquired by radar, the coordinates of the point cloud in the radar coordinate system can first be converted to coordinates in the vehicle coordinate system. Then, a rotation matrix is ​​used to multiply the coordinates of the point cloud in the vehicle coordinate system, and the product is the coordinates of the converted point cloud. Finally, a filtering region is used to suppress the converted point cloud.

[0082] When there is an angle between the vehicle's front end and the suspension mount, for the multiple point clouds generated by the radar collecting data from the suspension mount, the radial velocity of any point cloud relative to the radar is correlated with the distance between that point cloud and the rear axle of the suspension mount. Therefore, in order to more accurately suppress false alarm point clouds, the velocity information of the point clouds can be used to achieve preliminary screening of false alarm point clouds.

[0083] See Figure 6 As shown, Figure 6 This is a schematic diagram illustrating the relative positions of the vehicle front and the trailer as provided in an embodiment of this application.

[0084] For any point cloud R generated by the attachment, the speed of point cloud R This means that the point cloud R is relative to the radar ( Figure 6 The radial velocity of the left-hand radar (in the center). Since the radar is mounted at the front of the vehicle, the velocity of the point cloud R... It can also be expressed as the radial relative velocity between the vehicle's front and the point cloud of the attached structure, that is, the lateral velocity through the vehicle's front. longitudinal speed of the car front and the lateral speed of the hanging body Longitudinal speed of the hanging body The projection component in the radar radial direction is used to represent this. Based on this, the velocity can be obtained. in, Indicates the yaw angle of the front of the vehicle. This represents the yaw angle of the suspension. As can be seen from the above embodiment, the yaw rate of the vehicle front and the yaw rate of the suspension can be calculated, and the yaw angle of the vehicle front is... The first derivative with respect to time t is the yaw rate of the vehicle. The yaw angle represents the yaw angle generated between the initial moment of the vehicle's turn and the current moment. Therefore, the yaw angle can be obtained by integrating the yaw rate. Similarly, the horizontal swing angle of the hanging object can also be calculated. .

[0085] Let point O represent the radar's position, and let x represent the distance between the point cloud R and the center H of the rear axle of the mount. Let OP represent the distance between the radar and the mounting point. In triangle POR, the side length OR is calculated using the law of cosines. Similarly, in triangle POR, the side length OR can be calculated using the sine theorem to obtain... ,in, Let represent the angle between the line connecting point cloud R and the radar and the horizontal direction. Based on this, we can derive: Therefore, it can be concluded that as the distance x between the point cloud R and the center H of the rear axle of the mount increases, Increase, speed It also increases. Therefore, when x is at its maximum, the velocity... It is also the largest. Since x represents the distance between the point cloud R and the center H of the rear axis of the hanging object, it can be seen that x is the largest when the point cloud R is located at the hanging point P, at which time x = , You can get Therefore, the maximum velocity of the point cloud generated by the attachment can be determined.

[0086] Based on this, the target radial velocity of the point cloud located at the hanging point can be determined (i.e., Then, the radar-acquired point cloud is filtered using the target's radial velocity to obtain candidate point clouds. That is, only point clouds with a velocity less than or equal to the target's radial velocity can be considered as point clouds generated by the mounting. Next, a rotation matrix is ​​used to transform the candidate point clouds, resulting in the transformed point clouds. Specifically, the product of the rotation matrix and the coordinates of the candidate point clouds in the vehicle coordinate system is the coordinates of the transformed point clouds.

[0087] The target radial velocity can be determined as follows: based on the angle between the vehicle front and the trailer, the longitudinal velocity of the vehicle front and the lateral velocity of the vehicle front can be determined as two longitudinal components in the longitudinal velocity direction of the trailer, respectively. and A velocity balance equation is established based on the two longitudinal components and the longitudinal velocity of the hanging body to determine the longitudinal velocity of the hanging body. The radial velocity of the target is determined by the components of the longitudinal velocity of the vehicle's front, the longitudinal velocity of the attachment body, and the lateral velocity of the attachment body along the line connecting the attachment point and the radar.

[0088] S306: In the converted point cloud, identify and filter out false alarm point clouds of targets located within the filtering area.

[0089] The converted point cloud represents the point cloud generated when there is no angle between the attachment and the front of the vehicle. The filtering area is a pre-determined area used to suppress false alarm point clouds. Therefore, the target false alarm point cloud located within the filtering area can be identified in the converted point cloud and filtered out to suppress the false alarm point cloud.

[0090] The method provided in this application is applicable to situations where there is an angle between the front of the vehicle and the suspension when the vehicle is turning. By determining the angle between the front of the vehicle and the suspension, the point cloud collected by the radar can be transformed. Then, by combining the filtering area determined during the straight-moving process of the vehicle, the false alarm point cloud can be determined, thereby suppressing the false alarm point cloud and improving the accuracy of suppressing the false alarm point cloud.

[0091] Based on the above method embodiments, this application also provides a device for suppressing false alarm point clouds on vehicle attachments.

[0092] See Figure 7 As shown, Figure 7This is a schematic diagram of a device for suppressing false alarm point clouds on vehicle attachments, provided in an embodiment of this application.

[0093] The device 700 includes: The first angular velocity determination unit 701 is used to determine the yaw rate of the vehicle front based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front. The lateral velocity determination unit 702 is used to establish a velocity balance equation at the attachment point based on the angle between the vehicle head and the hanging body, and to determine the lateral velocity of the hanging body. The second angular velocity determination unit 703 is used to determine the yaw rate of the hanging body based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point; Angle determination unit 704 is used to determine the included angle based on the difference between the yaw rate of the vehicle front and the yaw rate of the hanging body; The conversion unit 705 is used to convert the point cloud acquired by the radar using the included angle, and to determine the converted point cloud; The suppression unit 706 is used to identify and filter out false alarm point clouds of targets located within the filtering area in the converted point cloud, wherein the filtering area is determined by fitting the edge of the hanging body with the point cloud collected by radar during the straight-moving process of the vehicle.

[0094] In one possible implementation, the device further includes: a filtering region determination unit, configured to acquire multiple frames of raw point cloud data collected by a single-side radar when the vehicle is traveling straight; filter the raw point cloud data based on the speed of the multiple frames to obtain a false alarm point cloud; fit the false alarm point cloud data to obtain a straight line along the edge of the hanger; determine the target point cloud data that is farthest from the single-side radar in the false alarm point cloud data; determine the length of the hanger data based on the projection point of the target point cloud data onto the straight line; and determine the filtering region based on the length.

[0095] In one possible implementation, the filtering region determination unit is used to convert multiple frames of the original point cloud into a vehicle coordinate system to obtain a converted point cloud; filter the converted point cloud based on a preset acquisition region to determine a set of point clouds located within the preset acquisition region; and select point clouds with speeds less than a preset value from the point cloud set as the false alarm point clouds.

[0096] In one possible implementation, the lateral velocity determination unit 702 is used to determine the lateral velocity of the vehicle front based on the yaw rate of the vehicle front and the distance between the rear axle of the vehicle front and the attachment point; to determine the longitudinal velocity of the vehicle front and the two lateral components of the lateral velocity of the vehicle front in the direction of the lateral velocity of the attachment body based on the included angle; and to establish a velocity balance equation based on the two lateral components and the lateral velocity of the attachment body to determine the lateral velocity of the attachment body.

[0097] In one possible implementation, the conversion unit 705 is used to determine a rotation matrix based on the included angle and the coordinates of the hanging point; and to determine the converted point cloud based on the point cloud acquired by the radar and the rotation matrix.

[0098] In one possible implementation, the conversion unit 705 is used to determine the target radial velocity of the point cloud located at the attachment point; in the point cloud acquired by the radar, point clouds with velocities less than or equal to the target radial velocity are selected as candidate point clouds; and the candidate point clouds are converted using the rotation matrix to obtain the converted point cloud.

[0099] In one possible implementation, the conversion unit 705 is used to determine, based on the included angle, two longitudinal components of the longitudinal velocity of the vehicle front and the lateral velocity of the vehicle front in the longitudinal velocity direction of the mounting body; establish a velocity balance equation based on the two longitudinal components and the longitudinal velocity of the mounting body to determine the longitudinal velocity of the mounting body; and determine the components of the longitudinal velocity of the vehicle front, the longitudinal velocity of the mounting body, and the lateral velocity of the mounting body in the direction of the line connecting the mounting point and the radar as the radial velocity of the target. Based on the above method and device embodiments, this application also provides an electronic device. The following will describe it in conjunction with the accompanying drawings.

[0100] See Figure 8 , Figure 8 This is a schematic diagram of an electronic device provided in an embodiment of this application.

[0101] The device 800 includes: a memory 801 and a processor 802; The memory 801 is used to store relevant program code; The processor 802 is used to call the program code to execute the method for suppressing false alarm point clouds of vehicle attachments as described in the above method embodiment.

[0102] Furthermore, this application embodiment also provides a computer-readable storage medium for storing a computer program for executing the method for suppressing false alarm point clouds of vehicle attachments as described in the above method embodiment.

[0103] This application also provides a computer program product, which includes a computer program / instruction. When the computer program / instruction is executed by a processor, it implements the method for suppressing false alarm point clouds of vehicle attachments as described in the above method embodiments.

[0104] It should be noted that the computer-readable medium described above in this application may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0105] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0106] It should be noted that the various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. In particular, for system or device embodiments, since they are basically similar to method embodiments, the description is relatively simple, and relevant parts can be referred to the descriptions in the method embodiments. The device embodiments described above are merely illustrative. The units or modules described as separate components may or may not be physically separate. The components shown as units or modules may or may not be physical modules; that is, they may be located in one place or distributed across multiple network units. Some or all of the units or modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without creative effort.

[0107] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functions, and operations that may be implemented by methods, apparatuses, and devices according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0108] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0109] It should also be noted that, in this application, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0110] The steps of the methods or algorithms described in conjunction with the embodiments disclosed in this application can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0111] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method for suppressing false alarm point clouds of vehicle attachments, characterized in that, The method includes: The yaw rate of the vehicle front is determined based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front. Based on the angle between the vehicle head and the hanging body, a velocity balance equation is established at the hanging point to determine the lateral velocity of the hanging body; The lateral velocity of the hanging body is determined based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point; The included angle is determined based on the difference between the yaw rate of the vehicle front and the yaw rate of the hanging body. The point cloud acquired by the radar is transformed using the included angle to determine the transformed point cloud; In the converted point cloud, false alarm point clouds of targets located within the filtering area are identified and filtered out. The filtering area is determined by fitting the edge of the hanging body with the point cloud collected by radar during the straight-moving process of the vehicle.

2. The method according to claim 1, characterized in that, The process of determining the filtering region includes: When the vehicle is traveling in a straight line, acquire multiple frames of raw point cloud data collected by a single-sided radar. False alarm point clouds are obtained by filtering based on the velocity of the original point clouds in multiple frames. The straight line at the edge of the hanging object is obtained by fitting the false alarm point cloud. In the false alarm point cloud, determine the target point cloud that is farthest from the single-sided radar; The length of the hanging object is determined based on the projection point of the target point cloud onto the straight line; The filtering area is determined based on the length.

3. The method according to claim 2, characterized in that, The process of filtering based on the velocity of the original point cloud across multiple frames to obtain a false alarm point cloud includes: The original point cloud from multiple frames is transformed into the vehicle coordinate system to obtain the transformed point cloud; The converted point cloud is filtered based on a preset acquisition area to determine the set of point clouds located within the preset acquisition area; Point clouds with speeds less than a preset value are selected from the point cloud set and designated as false alarm point clouds.

4. The method according to claim 1, characterized in that, The process of establishing a velocity balance equation at the attachment point based on the angle between the vehicle front and the hanging body, and determining the lateral velocity of the hanging body, includes: The lateral velocity of the vehicle front is determined based on the yaw rate of the vehicle front and the distance between the rear axle of the vehicle front and the attachment point. Based on the included angle, the longitudinal velocity of the vehicle head and the lateral velocity of the vehicle head are determined as two lateral components in the direction of the lateral velocity of the hanging body; A velocity balance equation is established based on the two lateral components and the lateral velocity of the hanging body to determine the lateral velocity of the hanging body.

5. The method according to claim 1, characterized in that, The process of converting the point cloud acquired by the radar using the included angle and determining the converted point cloud includes: Determine the rotation matrix based on the included angle and the coordinates of the hanging point; Based on the point cloud acquired by the radar and the rotation matrix, the transformed point cloud is determined.

6. The method according to claim 5, characterized in that, The process of determining the transformed point cloud based on the point cloud acquired by the radar and the rotation matrix includes: Determine the target radial velocity of the point cloud located at the hanging point; In the point cloud acquired by the radar, point clouds with velocities less than or equal to the radial velocity of the target are selected as candidate point clouds; The candidate point cloud is transformed using the rotation matrix to obtain the transformed point cloud.

7. The method according to claim 6, characterized in that, Determining the target radial velocity of the point cloud located at the hanging point includes: Based on the included angle, the longitudinal velocity of the vehicle head and the lateral velocity of the vehicle head are determined as two longitudinal components in the longitudinal velocity direction of the hanging body, respectively. A velocity balance equation is established based on the two longitudinal components and the longitudinal velocity of the hanging body to determine the longitudinal velocity of the hanging body; The components of the longitudinal velocity of the vehicle head, the longitudinal velocity of the attachment body, and the lateral velocity of the attachment body in the direction of the line connecting the attachment point and the radar are determined as the radial velocity of the target.

8. A device for suppressing false alarm point clouds on vehicle attachments, characterized in that, The device includes: The first angular velocity determination unit is used to determine the yaw rate of the vehicle front based on the longitudinal velocity of the vehicle front and the wheelbase of the vehicle front. The lateral velocity determination unit is used to establish a velocity balance equation at the attachment point based on the angle between the vehicle head and the hanging body, and to determine the lateral velocity of the hanging body. The second angular velocity determination unit is used to determine the yaw rate of the hanging body based on the lateral velocity of the hanging body and the distance between the rear axle of the hanging body and the hanging point; Angle determination unit is used to determine the included angle based on the difference between the yaw rate of the vehicle front and the yaw rate of the hanging body; A conversion unit is used to convert the point cloud acquired by the radar using the included angle, and to determine the converted point cloud; A suppression unit is used to identify and filter out false alarm point clouds of targets located within a filtering area in the converted point cloud, wherein the filtering area is determined by fitting the edge of the hanging body with a point cloud collected by radar during the straight-moving process of the vehicle.

9. An electronic device, characterized in that, The device includes: a memory and a processor; The memory is used to store the relevant program code; The processor is used to call the program code to execute the method for suppressing false alarm point clouds of vehicle attachments as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store a computer program for executing the method for suppressing false alarm point clouds of vehicle attachments as described in any one of claims 1 to 7.

Images