A target object relative speed determination method, system, device, medium

Abstract

The application provides a target object relative speed determination method, system, device and medium. The method comprises the following steps: obtaining the azimuth angle of a plurality of radar points of a target object, determining the azimuth angle sine value and the azimuth angle cosine value of each radar point; generating a first matrix and a second matrix based on the azimuth angle sine value and the azimuth angle cosine value of each radar point, determining a third matrix, determining the matrix determinant value and the eigenvalue of the third matrix according to the third matrix; if the matrix determinant value is greater than a first preset threshold value and the eigenvalue quotient is greater than a second preset threshold value, performing regularization processing on the third matrix; determining the target object relative speed of the target object relative to the vehicle based on the ground radial velocity of the radar point, the third matrix after regularization processing and the second matrix, wherein the ground radial velocity of the radar point is determined by the longitudinal speed, the lateral speed of the vehicle and the azimuth angle, and the azimuth angle is collected by the front millimeter wave radar of the vehicle.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle radar speed measurement, in particular to a target object relative speed determination method, system, device and medium. BACKGROUND

[0002] In the automatic driving technology, the accurate measurement of vehicle speed is extremely important. In the prior art, the signals obtained by the front millimeter wave radar through its channels are all the radial speeds of the points on the target object measured by the front radar in the polar coordinate system, which represent the speed of the front millimeter wave radar hitting the target at a certain position relative to the vehicle. The number of points on the same target hit by the front millimeter wave radar depends on the size of the target, the distance of the target, and the material of the target. Generally, the more points, the more accurate the estimated speed of the target will be. However, there are some specific cases, such as the points on the tire hit by the radar due to the linear speed of the wheel, which will affect the estimation of the speed of the target in the vehicle coordinate system. In addition, if the points on the target object are all near the AB straight line, that is, they are collinear, it will also have a great influence on the solution of the linear equation set and the estimation of the speed of the target in the vehicle coordinate system. Therefore, the prior art generally has too many factors affecting the measurement, low test accuracy and other problems that cause errors in the measurement of the speed of the target. SUMMARY

[0003] In view of the above-mentioned shortcomings of the prior art, the present application provides a scheme, system, device and medium for estimating the speed of a target based on a detection radar to solve the above-mentioned technical problems.

[0004] The present application provides:

[0005] A target object relative speed determination method, the estimated speed determination method of the target object comprises:

[0006] Obtaining the azimuth angle of a plurality of radar points of the target object, determining the sine value and the cosine value of the azimuth angle of each radar point;

[0007] Generating a first matrix and a second matrix based on the sine value and the cosine value of the azimuth angle of each radar point, determining a third matrix, the second matrix being the inverse matrix of the first matrix, and the third matrix being the product of the first matrix and the second matrix;

[0008] Determining the matrix determinant value and the eigenvalue of the third matrix according to the third matrix;

[0009] If the matrix determinant value is greater than a first preset threshold value, and a characteristic quotient is greater than a second preset threshold value, the third matrix is subjected to regularization processing, the characteristic quotient being a quotient of a maximum eigenvalue and a minimum eigenvalue of the third matrix;

[0010] A target object relative speed of the target object relative to the vehicle is determined based on the ground radial speed of the radar point, the third matrix subjected to the regularization processing, and the second matrix, the ground radial speed of the radar point being determined by a longitudinal speed, a lateral speed of the vehicle, and the azimuth angle, the azimuth angle being collected by the front millimeter wave radar of the vehicle.

[0011] In an embodiment of the present application, the first matrix is an n*2 matrix, n being a radar point acquisition number of the target object, a first column of the first matrix being a cosine value of the azimuth angle of each radar point, and a second column of the first matrix being a sine value of the azimuth angle of each radar point.

[0012] The second matrix is a transpose matrix of the first matrix, and the second matrix is a 2*n matrix.

[0013] The third matrix is the second matrix multiplied by the first matrix, and the third matrix is a 2*2 matrix.

[0014] In an embodiment of the present application, the ground radial speed of the radar point comprises:

[0015] A vehicle CAN signal is collected based on a vehicle body CAN, and a longitudinal speed and a lateral speed of the vehicle are obtained based on the vehicle body CAN signal.

[0016] The longitudinal speed and the lateral speed of the vehicle are projected onto a direction of a line connecting the vehicle and the radar point respectively, and the ground radial speed of the radar point is a projection value of the longitudinal speed of the vehicle in the direction of the line connecting the vehicle and the radar point plus a projection value of the lateral speed of the vehicle in the direction of the line connecting the vehicle and the radar point.

[0017] In an embodiment of the present application, if the matrix determinant value is greater than the first preset threshold value, and the characteristic quotient is greater than the second preset threshold value, the third matrix is subjected to regularization processing, comprising the steps of:

[0018] The third matrix is subjected to regularization processing, and an optimized third matrix solution set is obtained;

[0019] The third matrix is subjected to regularization iteration optimization for a preset number of times, and a characteristic quotient is calculated based on the third matrix after each iteration; whether the characteristic quotient after each iteration is greater than the second preset threshold value is determined; if not, it is determined that the calculated ground radial speed of the radar point is accurate and is retained; if yes, the calculated ground radial speed of the radar point is abandoned.

[0020] In an embodiment of the present application, the preset number of times is five, and if the characteristic quotient calculated according to the third matrix is still greater than the second preset threshold value after the third matrix is introduced into the regularization iterative processing for five times, the target object relative speed of the target object relative to the vehicle is abandoned for this time.

[0021] In an embodiment of the present application, the regularization iterative processing of the third matrix includes the following steps:

[0022] After each regularization processing of the third matrix, the characteristic quotient of the third matrix after the regularization processing is calculated, and if the calculated characteristic quotient of the third matrix is not greater than the second preset threshold value, the L2 regularization processing of the third matrix is stopped, and the ground radial velocity of the radar point calculated according to the third matrix after the regularization processing is retained.

[0023] In an embodiment of the present application, the regularization iterative processing of the third matrix further includes the following steps:

[0024] After each regularization processing of the third matrix, the matrix determinant value of the third matrix after the regularization processing is calculated, and if the matrix determinant value of the third matrix after the regularization processing is greater than the first preset threshold value, the target object relative speed of the target object relative to the vehicle calculated by the third matrix for this time is abandoned.

[0025] In an embodiment of the present application, the regularization processing of the third matrix includes:

[0026] L1 regularization processing or L2 regularization processing.

[0027] A system for estimating target speed based on detected radar, comprising:

[0028] A collection module acquires the azimuth angle of a plurality of radar points of a target object, and determines the sine value and the cosine value of the azimuth angle of the acquired radar points.

[0029] A calculation module generates a first matrix and a second matrix based on the sine value and the cosine value of the azimuth angle of each radar point, determines a third matrix, the second matrix is the inverse matrix of the first matrix, the third matrix is the product of the first matrix and the second matrix, and determines the target object relative speed of the target object relative to the vehicle based on the ground radial velocity of the radar point, the third matrix after the regularization processing, and the second matrix.

[0030] An optimization module determines the matrix determinant value and the characteristic value of the third matrix according to the third matrix, and if the matrix determinant value is greater than the first preset threshold value and the characteristic quotient is greater than the second preset threshold value, the regularization processing of the third matrix is performed, and the characteristic quotient is the quotient of the maximum characteristic value and the minimum characteristic value of the third matrix.

[0031] An electronic device, comprising:

[0032] one or more processors;

[0033] a memory device for storing one or more programs, which when executed by the one or more processors, cause the electronic device to implement the target object relative speed determination method as claimed in any one of claims 1 to 9.

[0034] A computer readable storage medium, having stored thereon a computer program, which when executed by a processor of a computer, causes the computer to perform the target object relative speed determination method as claimed in any one of claims 1 to 9.

[0035] Advantages of the present application:

[0036] The present application converts the radial speed of a vehicle in a polar coordinate system into absolute radial speed relative to the ground, establishes an absolute radial speed matrix equation of the millimeter wave radar point cloud data relative to the ground, calculates the speed of the target point from the solution set of the absolute radial speed matrix equation, and judges whether there is a method for eliminating ill-conditioned matrix, introducing L1 or L2 regularization to adjust and optimize the solution set of the ill-conditioned matrix, more accurately eliminating errors and calculating the speed of the target.

[0037] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the present application. BRIEF DESCRIPTION OF DRAWINGS

[0038] The drawings herein are incorporated into the specification and form part of the specification, show embodiments consistent with the present application, and together with the specification serve to explain the principles of the present application. It is obvious that the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings from these drawings without creative labor. In the drawings:

[0039] Figure 1 is a schematic diagram of the position relationship between the radar and the target shown by an exemplary embodiment of the present application;

[0040] Figure 2 is a schematic diagram of the position relationship between the radar and the target shown by an exemplary embodiment of the present application;

[0041] Figure 3 is a schematic diagram of the system structure shown by an exemplary embodiment of the present application;

[0042] Figure 4 is a schematic diagram of the ill-conditioned matrix judgment step shown by an exemplary embodiment of the present application;

[0043] Figure 5 This is a schematic diagram illustrating the ill-conditioned matrix optimization steps in an exemplary embodiment of this application;

[0044] Figure 6 A schematic diagram of the structure of a computer system suitable for implementing the electronic device of the present application is shown. Detailed Implementation

[0045] The embodiments of the present invention will be described below with reference to the accompanying drawings and preferred embodiments. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be understood that the preferred embodiments are only for illustrating the present invention and not for limiting the scope of protection of the present invention.

[0046] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. Therefore, the drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0047] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0048] First, it's important to understand that radar speed measurement primarily utilizes the Doppler effect: when a target approaches the radar antenna, the frequency of the reflected signal will be higher than the transmitter frequency; conversely, when the target moves away from the antenna, the frequency of the reflected signal will be lower than the transmitter frequency. Thus, the relative speed between the target and the radar can be calculated by observing the change in frequency (a positive Doppler frequency when the target is facing the radar, and a negative Doppler frequency when the target is flying away from the radar). Figure 1 As shown, the embodiments of this application relate to millimeter-wave radar speed measurement. Millimeter-wave radar is a radar that operates in the millimeter-wave band for detection. Typically, millimeter waves refer to the 30–300 GHz frequency domain (wavelength 1–10 mm). The wavelength of millimeter waves lies between that of centimeter waves and light waves; therefore, millimeter waves combine the advantages of microwave guidance and photoelectric guidance.

[0049] likeFigure 2 As shown in the figure, a target object relative speed determination method, the method comprises:

[0050] S210, the azimuth angle of the plurality of radar points of the target object is obtained, and the azimuth angle sine value and the azimuth angle cosine value of each radar point are determined;

[0051] S220, a first matrix and a second matrix are generated based on the azimuth angle sine value and the azimuth angle cosine value of each radar point, the second matrix is the inverse matrix of the first matrix, and a third matrix is determined, the third matrix is the product of the first matrix and the second matrix;

[0052] S230, the matrix determinant value and the eigenvalue of the third matrix are determined according to the third matrix;

[0053] S240, if the matrix determinant value is greater than a first preset threshold, and the characteristic quotient is greater than a second preset threshold, the third matrix is regularized, and the characteristic quotient is the quotient of the maximum eigenvalue and the minimum eigenvalue of the third matrix;

[0054] S250, the target object relative speed of the target object relative to the vehicle is determined based on the ground radial velocity of the radar point, the third matrix after the regularization processing and the second matrix, the ground radial velocity of the radar point is determined by the longitudinal velocity, the transverse velocity of the vehicle and the azimuth angle, and the azimuth angle is collected by the front millimeter wave radar of the vehicle.

[0055] As shown in the figure, Figure 1 The vehicle moving speed is decomposed, and the radial speed along the vehicle-target point straight line direction is calculated, and the point cloud speed measured by the millimeter wave radar projected on the target point is converted to the absolute radial speed relative to the ground. Through the obtained data set, the absolute radial matrix equation of the millimeter wave radar point cloud data relative to the ground is combined to calculate the solution set of the absolute radial speed matrix equation, so as to obtain the speed of the target point.

[0056] Regularization is a general term for a class of methods in machine learning that introduce additional information to the original loss function to prevent overfitting and improve the generalization performance of the model. That is, the objective function becomes the original loss function + additional term. The commonly used additional terms are generally two kinds, English called l1-norm and l2-norm, Chinese called L1 regularization and L2 regularization, or L1 norm and L2 norm (actually the square of L2 norm). L2 regularization can prevent model overfitting.

[0057] The ground radial velocity of the radar point comprises:

[0058] Collect vehicle CAN signals based on a vehicle body CAN, and obtain longitudinal speed Vx and lateral speed Vy of the vehicle according to the vehicle body CAN signals;

[0059] Project the longitudinal speed Vx and the lateral speed Vy of the vehicle onto a radial speed direction of the millimeter wave radar in polar coordinates, and obtain an absolute radial speed of the millimeter wave radar point cloud relative to the ground according to a first preset formula.

[0060] The first preset formula is:

[0061] RRotg=Vx*cosα+Vy*sinα;

[0062] Wherein, RRotg is an absolute radial speed relative to the ground in a polar coordinate system, and a is an azimuth angle of a millimeter wave radar point.

[0063] Some vehicle information is obtained from some vehicle CAN signals received on the vehicle body CAN, some ego vehicle information is estimated by a vehicle state estimation module, Vx and Vy information of the ego vehicle is obtained, Vx and Vy of the ego vehicle are projected onto a radial speed direction of the millimeter wave radar in polar coordinates, an absolute radial speed of the millimeter wave radar point cloud relative to the ground is obtained, as shown in the first preset formula, and all point cloud data is converted into an absolute radial speed according to the first preset formula.

[0064] The absolute radial speed matrix equation solution set is calculated to obtain the speed of the target point, including the steps of:

[0065] A second preset formula for calculating the absolute radial speed of the millimeter wave radar point cloud relative to the ground is established based on a least square method, the second preset formula is simplified into a third preset formula, and the absolute radial speed of the millimeter wave radar point cloud data relative to the ground is solved by transposing a matrix.

[0066] In an embodiment of the present application, the second preset formula is:

[0067]

[0068] Wherein, RRotg is the absolute radial speed of the millimeter wave radar point cloud relative to the ground, a is the azimuth angle of the millimeter wave radar point on the target vehicle, 1 to n represent the number of points on the target vehicle, Vx_obj is the longitudinal speed of the target vehicle in the vehicle coordinate system, and Vy_obj is the lateral speed of the target vehicle in the vehicle coordinate system.

[0069] Theoretically, the precision of estimating the speed of a target point by using the millimeter wave radar point cloud data depends on the number of points, the points on the same target are calculated by the least square method to estimate the speed of the target, and a second preset formula is combined for calculation.

[0070] In an embodiment of the present application, the third preset formula is Y = Ax, wherein Y is A is that is, the first matrix, x is

[0071] wherein the second preset formula can be simplified as Y = Ax,

[0072] The third preset formula is multiplied by the transpose matrix A T of A on both sides to obtain A T Y = A T Ax; wherein A T is the second matrix, A T A is the third matrix.

[0073] wherein A T A is the matrix solution set and is an invertible matrix; x is the radial velocity of the millimeter wave radar point cloud relative to the ground.

[0074] Since the number of points on the target is large, the A matrix is a matrix with multiple rows and two columns, that is, an n*2 matrix, which is not a square matrix and cannot be operated inversely, so the equation is multiplied by A T (the transpose matrix of the A matrix) on both sides to make it a 2*2 square matrix, and the equation is transformed into A T A = A T Ax, A T A is now a 2*2 matrix, and assuming that ATA is an invertible matrix, the vector x is successfully solved at this time.

[0075] In an embodiment of the present application, as Figure 4As shown, the more the number of point clouds, the more accurate the estimated target point speed is, but there are some specific cases, such as the radar hitting the wheels of the target vehicle, due to the linear speed of the moving wheels, the points hitting the moving tires are often larger than the points hitting the tires, and the relative radial speed is larger than the general points. Some radar detects a bunch of noise, and in addition, even if there are many points hitting the target vehicle, but these points are near the AB straight line, that is, they are collinear, which has a great influence on the solution of the linear equation set. This may cause the emergence of an ill-conditioned matrix, that is, the third matrix may be an ill-conditioned matrix, which affects the ground radial velocity of the radar point calculated by the third matrix, and further affects the accuracy of the target object relative speed of the target object relative to the vehicle. Therefore, it is necessary to judge whether the third matrix is an ill-conditioned matrix, including the following steps:

[0076] S410, calculating the matrix A T The value of the determinant, judging whether the value of the determinant is greater than a preset threshold value, if yes, continuing to solve the radial velocity of the millimeter wave radar point cloud relative to the ground, if not, directly abandoning the radial velocity of the millimeter wave radar point cloud relative to the ground calculated by the absolute radial velocity matrix;

[0077] S420, solving the matrix A T The eigenvalue of A, dividing the maximum eigenvalue obtained by solving by the minimum eigenvalue to obtain the matrix A T The condition number of A, judging whether the matrix A T Whether the condition number of A is greater than a preset threshold value, if not, the matrix A T A is not an ill-conditioned matrix; if yes, the matrix A T A is an ill-conditioned matrix.

[0078] In an embodiment of the present application, as shown in Figure 5 The step of introducing regularization to optimize the ill-conditioned matrix solution set includes:

[0079] S510, introducing regularization into the solution of the absolute radial velocity of the millimeter wave radar point cloud relative to the ground to obtain an optimized ill-conditioned matrix solution set;

[0080] S520, introducing regularization into the ill-conditioned matrix according to a preset number of iterations to optimize the ill-conditioned matrix, and calculating the condition number of the ill-conditioned matrix after each iteration; judging whether the condition number of each iteration is greater than a preset threshold value; if not, it is determined that the calculated radial velocity of the millimeter wave radar point cloud relative to the ground is accurate and is retained; if yes, the calculated speed is abandoned.

[0081] After each iteration of regularization, the condition number is calculated, and it is judged whether the condition number is greater than the preset threshold value, if yes, the iteration is continued, and a total of 5 iterations are performed, and if it is still greater than the preset threshold value after 5 iterations, the estimated speed of the target point is abandoned.

[0082] In an embodiment of the present application, the formula for solving the radial velocity of the millimeter wave radar point cloud relative to the ground is: x=(A T A) -1 *A T Y;

[0083] The formula for the regularization optimization solution set is: x=(A T A+λI) -1 *A T Y.

[0084] As Figure 3 shown, a system for estimating target speed based on detection radar includes:

[0085] An acquisition module acquires azimuth angles of a plurality of radar points of a target object, and determines a sine value and a cosine value of the acquired azimuth angle;

[0086] A calculation module generates a first matrix and a second matrix based on the sine value and the cosine value of the azimuth angle of each radar point, determines a third matrix, the second matrix is an inverse matrix of the first matrix, the third matrix is a product of the first matrix and the second matrix, and determines a target object relative speed of the target object relative to a vehicle based on a ground radial velocity of the radar point, the third matrix after regularization processing, and the second matrix;

[0087] An optimization module determines a matrix determinant value and an eigenvalue of the third matrix according to the third matrix, performs regularization processing on the third matrix if the matrix determinant value is greater than a first preset threshold value and a characteristic quotient is greater than a second preset threshold value, and the characteristic quotient is a quotient of a maximum eigenvalue and a minimum eigenvalue of the third matrix.

[0088] Embodiments of the present application also provide an electronic device, including: one or more processors; a storage device for storing one or more programs, when the one or more programs are executed by the one or more processors, the electronic device implements the target object relative speed determination method provided in each of the above embodiments.

[0089] Figure 6 The structure of the computer system of the electronic device suitable for implementing the embodiments of the present application is shown. It should be noted that, Figure 6 The computer system 600 of the electronic device shown is only an example, and should not limit the functions and use range of the embodiments of the present application.

[0090] like Figure 6 As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 602 or programs loaded from Storage Unit 608 into Random Access Memory (RAM) 603, such as performing the methods described in the above embodiments. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0091] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0092] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including a computer program for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of this application.

[0093] It should be noted that the computer-readable medium in the embodiments of the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may, for example, be an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any combination thereof. More specific examples of the computer-readable storage medium can include, but are not limited to, an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this application, the computer-readable signal medium can include a data signal propagated in a baseband or as a carrier wave in a propagated data signal, in which the computer-readable computer program is carried. Such a propagated data signal can take on many forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit the program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted in any suitable medium, including but not limited to wireless, wired, or the like, or any suitable combination thereof.

[0094] The flowcharts and block diagrams in the drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present application. Each block in the flowcharts or block diagrams can represent a module, a program segment, or a portion of code, which contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur in a different order than that shown in the figures. For example, two blocks noted in succession can actually be executed substantially concurrently, or they can sometimes be executed in reverse order, depending on the functionality involved. It should also be noted that each block in the flowcharts or block diagrams, and combinations of blocks in the flowcharts or block diagrams, can be implemented by special-purpose hardware-based systems, which perform the specified functions or operations, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0095] The units described in the embodiments of the present application can be implemented in the form of software, or can be implemented in the form of hardware, and the described units can also be arranged in a processor. In some cases, the names of the units do not constitute a limitation on the units themselves.

[0096] Another aspect of the present application also provides a computer readable storage medium, which stores a computer program. When the computer program is executed by a processor of a computer, the computer executes the target object relative speed determination method as described above. The computer readable storage medium can be included in the electronic device described in the above embodiments, or can exist separately and not be assembled into the electronic device.

[0097] Another aspect of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device executes the target object relative speed determination method provided in each of the above embodiments.

[0098] The above embodiments only exemplarily illustrate the principles and effects of the present application, and are not used to limit the present application. Any person skilled in the art can modify or change the above embodiments without departing from the spirit and scope of the present application. Therefore, all equivalent modifications or changes completed by those skilled in the art without departing from the spirit and technical thought of the present application should be covered by the claims of the present application.

Claims

1. A method for determining the relative velocity of a target object, characterized in that, The method for determining the estimated velocity of the target object includes: Acquire the azimuth angles of multiple radar points of the target object, and determine the azimuth sine and azimuth cosine values ​​of each radar point; A first matrix is ​​generated based on the azimuth sine and azimuth cosine values ​​of each radar point, and a third matrix is ​​determined. The second matrix is ​​the transpose of the first matrix, and the third matrix is ​​the product of the first matrix and the second matrix. Determine the matrix determinant value and the eigenvalues ​​of the third matrix based on the third matrix; If the determinant of the matrix is ​​greater than a first preset threshold and the feature quotient is greater than a second preset threshold, the third matrix is ​​subjected to regularization iterative optimization for a preset number of times, and the feature quotient is the quotient of the maximum and minimum eigenvalues ​​of the third matrix; The relative velocity of the target object with respect to the vehicle is determined based on the ground radial velocity of the radar point, the regularized third matrix, and the second matrix. The ground radial velocity of the radar point is determined by the longitudinal velocity, lateral velocity, and azimuth angle of the vehicle. The azimuth angle is acquired by the front millimeter-wave radar of the vehicle. Furthermore, the preset number of iterations is five. After the third matrix is ​​introduced into regularization iterations five times, if the feature quotient calculated based on the third matrix is ​​still greater than the second preset threshold, then the relative speed of the target object with respect to the target object of the vehicle in that iteration is abandoned.

2. The method for determining the relative velocity of a target object according to claim 1, characterized in that, The first matrix is ​​an n*2 matrix, where n is the number of radar points acquired for the target object. The first column of the first matrix is ​​the cosine value of the azimuth angle of each radar point, and the second column of the first matrix is ​​the sine value of the azimuth angle of each radar point. The second matrix is ​​the transpose of the first matrix, and the second matrix is ​​a 2*n matrix; The third matrix is ​​the second matrix multiplied by the first matrix on the left, and the third matrix is ​​a 2*2 matrix.

3. The method for determining the relative velocity of a target object according to claim 1, characterized in that, The ground radial velocity of the radar point includes: The vehicle's longitudinal and lateral speeds are obtained by collecting vehicle CAN signals based on the body CAN signals. The vehicle's longitudinal and lateral velocities are projected onto the line connecting the vehicle and the radar point, respectively. The radial velocity of the radar point on the ground is the sum of the projection of the vehicle's longitudinal velocity onto the line connecting the vehicle and the radar point and the projection of the vehicle's lateral velocity onto the line connecting the vehicle and the radar point.

4. The method for determining the relative velocity of a target object according to claim 1, characterized in that, If the determinant of the matrix is ​​greater than a first preset threshold and the feature quotient is greater than a second preset threshold, the third matrix is ​​regularized, including the following steps: By introducing regularization to the third matrix, an optimized solution set for the third matrix is ​​obtained; Calculate the feature quotient using the third matrix after each iteration; Determine whether the feature quotient in each iteration is greater than the second preset threshold; if not, then the calculated ground radial velocity of the radar point is considered accurate and retained. If so, then discard the ground radial velocity of the radar point calculated in this instance.

5. The method for determining the relative velocity of a target object according to claim 4, characterized in that, The regularization iterative process introduced into the third matrix includes the following steps: Each time the third matrix is ​​regularized, the feature quotient of the regularized third matrix is ​​calculated. If the calculated feature quotient of the third matrix is ​​not greater than the second preset threshold, the L2 regularization of the third matrix is ​​stopped, and the ground radial velocity of the radar point calculated based on the regularized third matrix is ​​retained.

6. The method for determining the relative velocity of a target object according to claim 5, characterized in that, The regularization iterative processing introduced by the third matrix also includes the following steps: Each time the third matrix is ​​regularized, the determinant of the regularized third matrix is ​​calculated. If the determinant of the regularized third matrix is ​​greater than a first preset threshold, the calculation of the relative speed of the target object with respect to the vehicle using the third matrix is ​​abandoned.

7. The method for determining the relative velocity of a target object according to claim 5, characterized in that, Regularization of the third matrix includes: L1 regularization or L2 regularization.

8. A system for estimating target velocity based on detection radar, characterized in that, include: The acquisition module obtains the azimuth angles of multiple radar points of the target object and determines the sine and cosine values ​​of the azimuth angles of the acquired radar points. The calculation module generates a first matrix based on the azimuth sine and azimuth cosine values ​​of each radar point, determines a third matrix, the second matrix is ​​the transpose of the first matrix, and the third matrix is ​​the product of the first matrix and the second matrix. Based on the ground radial velocity of the radar point, the regularized third matrix, and the second matrix, the relative velocity of the target object with respect to the vehicle is determined. The optimization module determines the determinant value and eigenvalues ​​of the third matrix based on the third matrix. If the determinant value is greater than a first preset threshold and the eigenvalue quotient is greater than a second preset threshold, the module introduces regularization iterative optimization of the third matrix for a preset number of iterations. The eigenvalue quotient is the quotient of the largest and smallest eigenvalues ​​of the third matrix. The preset number of iterations is five. If, after five iterations of regularization, the eigenvalue quotient calculated based on the third matrix is ​​still greater than the second preset threshold, the module abandons the relative speed of the target object with respect to the target object of the vehicle in that iteration.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the target object relative velocity determination method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the target object relative velocity determination method according to any one of claims 1 to 7.

Images