Target tracking method for vehicle-mounted radar, vehicle-mounted radar and storage medium

Abstract

The present invention provides a target tracking method for a vehicle-mounted radar, a vehicle-mounted radar, and a storage medium. The method includes: obtaining a measurement of a target detected by the vehicle radar in the vehicle coordinate system at the current moment; if the vehicle is in a turning state at the current moment, calculating a state estimate of the target in the world coordinate system at the current moment based on the measurement of the target in the vehicle coordinate system at the current moment and the state estimate of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the vehicle enters the current turning state; finally, converting the state estimate of the target in the world coordinate system at the current moment to the vehicle coordinate system at the current moment. Through the above process, the present application can avoid tracking failure caused by the relative motion between the radar and the target no longer conforming to a linear relationship when the vehicle turns, thereby improving the target tracking accuracy of the vehicle-mounted radar.

Description

Technical Field

[0001] The present invention relates to the field of radar technology, and in particular to a target tracking method for a vehicle-mounted radar, a vehicle-mounted radar, and a storage medium. Background Art

[0002] Compared to traditional sensors, high-resolution millimeter-wave radar offers advantages such as high measurement accuracy, rich detection point clouds, and all-day, all-weather coverage. It has been widely used in environmental perception for Level 3 and higher assisted driving. During assisted driving, stable tracking of detected targets and accurate velocity estimation are crucial for subsequent planning and decision-making.

[0003] Currently, millimeter-wave radar target tracking is performed in the vehicle coordinate system. However, when the vehicle turns or even makes a U-turn, tracking fails because the relative motion between the radar and the target no longer conforms to a linear relationship. Summary of the Invention

[0004] In view of this, the present invention provides a target tracking method for a vehicle-mounted radar, a vehicle-mounted radar, and a storage medium, which can solve the problem of radar failure in tracking a target during a vehicle turning process.

[0005] In a first aspect, an embodiment of the present invention provides a target tracking method for a vehicle-mounted radar, comprising:

[0006] Obtain the target's measurement in the vehicle coordinate system at the current moment detected by the vehicle's radar;

[0007] If the ego vehicle is in a turning state at the current moment, then calculating the estimated state of the target in the world coordinate system at the current moment based on the measured quantity of the target in the vehicle coordinate system at the current moment and the estimated state of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the ego vehicle enters the current turning state;

[0008] The state estimation of the target at the current moment in the world coordinate system is converted to the vehicle coordinate system at the current moment.

[0009] In a second aspect, an embodiment of the present invention provides a terminal comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the steps of the target tracking method of the vehicle-mounted radar as described in any possible implementation of the first aspect above are implemented.

[0010] In a third aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, it implements the steps of the target tracking method of the vehicle-mounted radar as described in the first aspect or any possible implementation method of the first aspect.

[0011] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0012] The embodiment of the present invention first obtains the quantity measurement of the target detected by the vehicle radar in the vehicle coordinate system at the current moment; if the vehicle is in a turning state at the current moment, the state estimation of the target in the world coordinate system at the current moment is calculated based on the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the vehicle enters the current turning state; the state estimation of the target in the world coordinate system at the current moment is converted to the vehicle coordinate system at the current moment. Through the above process, this embodiment can avoid tracking failure caused by the relative motion between the radar and the target no longer conforming to the linear relationship when the vehicle turns, and track the target in the world coordinate system when the vehicle turns, thereby improving the target tracking accuracy of the vehicle-mounted radar. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0014] Figure 1 1 is a flow chart of a target tracking method for a vehicle-mounted radar provided by an embodiment of the present invention;

[0015] Figure 2 Schematic diagram of the coordinates of the vehicle coordinate system and the world coordinate system provided by an embodiment of the present invention;

[0016] Figure 3 1 is a schematic structural diagram of a target tracking device for a vehicle-mounted radar provided by an embodiment of the present invention;

[0017] Figure 4 is a schematic diagram of a vehicle-mounted radar provided by an embodiment of the present invention;

[0018] Figure 5 It is a schematic diagram comparing the quantity measurement of a target detected by radar and the estimated quantity calculated by the method provided by the embodiment of the present invention. DETAILED DESCRIPTION

[0019] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0020] In order to explain this solution more clearly, this embodiment first explains the formula symbols mentioned below, which are detailed as follows;

[0021] V t represents the vehicle speed at time t;

[0022] V k+1 represents the vehicle speed at time k+1;

[0023] F k Represents the state transfer matrix at time k;

[0024] v k represents the process noise at time k in the world coordinate system;

[0025] Q k,W Represents the process noise matrix in the world coordinate system;

[0026] Q k,ego represents the process noise matrix in the vehicle coordinate system;

[0027] ω k+1 represents the measurement noise at time k+1;

[0028] R k+1,W represents the measurement noise matrix in the world coordinate system at time k+1;

[0029] R k+1,ego represents the measurement noise matrix at time k+1 in the vehicle coordinate system;

[0030] H k+1 represents the measurement transfer matrix at time k+1;

[0031] ε k+1 represents the cumulative change in yaw angle from the time of entering the turning state to time k+1;

[0032] represents the yaw rate of the vehicle at time k+1;

[0033] θ i represents the change in the yaw angle of the vehicle at time i;

[0034] T represents the frame period;

[0035] Z k+1,W represents the measurement of the target in the world coordinate system at time k+1;

[0036] Z k+1,ego represents the measurement of the target in the vehicle coordinate system at time k+1;

[0037] Z k+1|k,ego represents the predicted quantity of the target at time k+1 in the vehicle coordinate system;

[0038] represents the predicted mean value of the quantity measured for the target at time k+1 in the vehicle coordinate system;

[0039] M k+1 Represents the rotation matrix at time k+1;

[0040] N k+1 represents the translation vector at time k+1;

[0041] X k+1,W Represents the real state of the target in the world coordinate system at time k+1;

[0042] X k,W Represents the true state of the target in the world coordinate system at time k;

[0043] represents the state estimate of the target in the world coordinate system at time k+1;

[0044] represents the mean value of the predicted state of the target at time k+1 in the world coordinate system;

[0045] X k+1|k,W represents the predicted state of the target at time k+1 in the world coordinate system;

[0046] represents the state estimate of the target in the vehicle coordinate system at time k+1;

[0047] Represents the actual state of the vehicle in the world coordinate system at time k+1;

[0048] represents the error between the predicted state of the target at time k+1 and the actual state in the world coordinate system;

[0049] represents the error of the target's state estimate at time k+1 relative to its true state in the world coordinate system;

[0050] Pk+1|k,W represents the predicted value of the state covariance of the target at time k+1 in the world coordinate system;

[0051] P k+1|k+1,W represents the state covariance of the target at time k+1 in the world coordinate system;

[0052] P k+1|k+1,ego represents the state covariance of the target at time k+1 in the vehicle coordinate system;

[0053] P k|k,W represents the state covariance of the target at time k in the world coordinate system;

[0054] K k+1 represents the gain matrix at time k+1;

[0055] S k+1 represents the innovation covariance matrix of the target at time k+1;

[0056] I represents the identity matrix;

[0057] (·) T Represents the transpose of a vector or matrix;

[0058] (•) -1 Represents the inverse of a vector or matrix.

[0059] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0060] Figure 1 A schematic diagram of the implementation flow of a target tracking method for a vehicle-mounted radar provided in an embodiment of the present invention.

[0061] Details are as follows:

[0062] S101: Obtaining the target measurement detected by the vehicle radar in the vehicle coordinate system at the current moment.

[0063] In this embodiment, the quantity measurement represents the data of the target measured by the radar, and the state quantity represents the real data of the target. There is usually a certain deviation between the quantity measurement and the state quantity.

[0064] S102: If the vehicle is in a turning state at the current moment, the state estimate of the target in the world coordinate system at the current moment is calculated based on the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimate of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the vehicle enters this turning state.

[0065] Specifically, when the vehicle is in a straight-moving state, the relative motion between the vehicle and the target conforms to a linear relationship, so it is sufficient to directly create a linear state update equation for the target in the vehicle coordinate system. However, when the vehicle is in a turning state, the relative motion between the vehicle and the target no longer conforms to a linear relationship, and the linear state update equation created in the vehicle coordinate system cannot be used to accurately track the target. Therefore, when the vehicle is in a turning state, the present application tracks the target in the world coordinate system. Since the motion relationship between the vehicle and the target vehicle in the world coordinate system is still linear, the target can be tracked well in the world coordinate system.

[0066] In one embodiment, before S102, the target tracking method of the vehicle-mounted radar further includes:

[0067] If the ego vehicle is currently in a turning state and the cumulative change in the yaw angle of the ego vehicle within M consecutive frames is less than a first preset threshold, it is determined that the ego vehicle has entered a straight-ahead state from a turning state;

[0068] If the vehicle is in a straight-ahead state at the current moment and the accumulated change in the yaw angle of the vehicle within N consecutive frames is detected to be greater than a first preset threshold, it is determined that the vehicle has entered a turning state from the straight-ahead state.

[0069] Specifically, the turning state includes a turn maintaining state and a turn entering state. The yaw angle of the ego vehicle is monitored in real time. If the ego vehicle is currently in the turn maintaining state or the turn entering state, and the cumulative change in the yaw angle of the ego vehicle over M consecutive frames is less than or equal to a first preset threshold, the ego vehicle is determined to have entered the straight ahead state from the turn state. Otherwise, the ego vehicle maintains the current state. The first preset threshold may be 0.003 rad.

[0070] The straight-ahead state includes straight-ahead and standby states. The yaw angle of the ego vehicle is monitored in real time. If the ego vehicle is currently in the straight-ahead state or standby state, and the cumulative change in the yaw angle over N consecutive frames is greater than a first preset threshold, the ego vehicle is determined to have entered a turning state from the straight-ahead state. Otherwise, the ego vehicle maintains its current state. The standby state refers to the state when the vehicle is not moving.

[0071] Specifically, M>N, M can be 5, and N can be 3.

[0072] In one embodiment, the specific implementation process of S102 includes:

[0073] Inputting the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target in the world coordinate system at the previous moment into the state update equation to obtain the state estimation and state covariance of the target in the world coordinate system at the current moment;

[0074] The state update equation is an equation obtained by performing Kalman filtering calculation on the state space model of the target; the state space model includes a state equation and a measurement equation, and the measurement equation is used to express the relationship between the quantity measurement of the target in the vehicle coordinate system corresponding to the same moment and the state quantity in the world coordinate system.

[0075] In one embodiment, when the vehicle detects that it has entered a turning state from a straight state, the vehicle coordinate system corresponding to the turning state is used as the world coordinate system, and the target is tracked in this world coordinate system throughout the turning state. The state space model in this coordinate system is as follows:

[0076] The state equation is:

[0077] X k+1,W =F k X k,W +v k ;

[0078] Among them, if the vehicle enters the turning state from the straight state at time t, that is, the vehicle coordinate system at time t is used as the world coordinate system, then when t = k, the real state quantity at time k in the world coordinate system is x(t) represents the x-axis coordinate of the target in the vehicle coordinate system at time t; y(t) represents the y-axis coordinate of the target in the vehicle coordinate system at time t; v x (t) represents the x-axis velocity of the target in the vehicle coordinate system at time t; v y (t) represents the y-axis velocity of the target in the vehicle coordinate system at time t; F k represents the state transition matrix at time k, v k represents the process noise at time k in the world coordinate system, which obeys the Gaussian distribution N(0,Q k,W ).

[0079] The measurement equation is:

[0080] Among them, Z k+1,ego represents the target measurement in the vehicle coordinate system at time k+1, H k+1 represents the measurement transfer matrix at time k+1, ω k+1 represents the measurement noise at time k+1, which obeys the Gaussian distribution N(0, R k+1,ego ), Represents the actual state of the vehicle in the world coordinate system at time k+1.

[0081] Specifically, the rotation matrix M k+1 The derivation process is as follows:

[0082] The vehicle coordinate system is a coordinate system with the center of mass of the vehicle as the origin, the forward direction of the vehicle as the y-axis, and the direction perpendicular to the y-axis on the horizontal plane as the x-axis. Figure 2 A schematic diagram showing the relationship between the vehicle coordinate systems at two moments is shown, as Figure 2 As shown, the vehicle coordinate system at time k is Coordinate system, the state vector of the target in this coordinate system is Among them, x k Indicates that the target at time k is The x-axis coordinate of the coordinate system, y k Indicates that the target at time k is The y-axis coordinate of the coordinate system, Indicates that the target at time k is The x-axis velocity of the coordinate system, Indicates that the target at time k is The y-axis speed of the coordinate system. At the origin The vehicle only has a linear velocity V along the positive half of the y-axis. k , the yaw angle is δ k ; At time k+1, the vehicle coordinate system is Coordinate system, the state vector of the target in this coordinate system is Among them, x k+1 Indicates that the target at time k+1 is The x-axis coordinate of the coordinate system, y k+1 Indicates that the target at time k+1 is The y-axis coordinate of the coordinate system, Indicates that the target at time k+1 is The x-axis velocity of the coordinate system, Indicates that the target at time k+1 is The y-axis speed of the coordinate system. The vehicle is located at the origin of the coordinate system. The vehicle only has a linear velocity V along the positive half of the y-axis. k+1 , the yaw angle is δ k+1 .

[0083] Based on the above state vector and coordinate relationship, the coordinate system With vehicle coordinate system The derivation process of the transformation matrix is ​​as follows:

[0084] Assume that the position vector coordinates in the original coordinate system are [xy] T ; Rotate the vector counterclockwise around the origin (Unit: radians) or the original coordinate system rotates clockwise around the origin Then the new coordinates of the vector in the world coordinate system are:

[0085]

[0086] By taking the derivative of both sides of the above equation with respect to t, we can get the relationship between the speed changes before and after the conversion:

[0087]

[0088] Combining the above two equations, we can get the transformed equation as follows:

[0089]

[0090] According to the above conversion process, assuming that the vehicle enters the turning state at time k, the vehicle coordinate system corresponding to time k is used as the world coordinate system, and the cumulative change of the vehicle's yaw angle from time k to time k+1 is ε k+1 , the rotation matrix between the vehicle coordinate system and the world coordinate system corresponding to time k+1 is:

[0091]

[0092] In this embodiment, the measurement equation established in this embodiment is established in a hybrid coordinate system, which is used to express the relationship between the state quantity in the world coordinate system and the quantity measurement in the vehicle coordinate system. This process does not require the quantity measurement to be converted from the vehicle coordinate system to the world coordinate system, but only requires the process noise to be converted, thereby simplifying the calculation process and improving calculation efficiency.

[0093] Based on the Kalman filter algorithm, the state update equation established in the hybrid coordinate system is:

[0094]

[0095]

[0096] Specifically, at time k, the world coordinate system In the example, the real state of the target is The process noise in the vehicle coordinate system is Q k,ego ; At time k+1, the world coordinate system In the equation, the predicted state of the target at time k+1 is We can get:

[0097]

[0098] The process noise conversion formula between the vehicle coordinate system and the world coordinate system is:

[0099] Specifically, Z k+1|k,ego Represents the predicted amount of the target at time k+1 in the vehicle coordinate system, which satisfies And the predicted value of the quantity measurement is:

[0100] The covariance matrix is:

[0101] Therefore, based on the Kalman algorithm, the state update equation in the hybrid coordinate system is:

[0102]

[0103]

[0104] Among them, the error of the target state prediction at time k+1 relative to the actual state in the world coordinate system is It can be obtained by the following formula:

[0105]

[0106] The error of the target's state estimate at time k+1 relative to the true state in the world coordinate system It can be obtained by the following formula:

[0107]

[0108] S103: Convert the state estimation of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment.

[0109] Specifically, the state estimation and state covariance of the target at the current moment in the world coordinate system are converted to the vehicle coordinate system at the current moment.

[0110] In one embodiment, the specific implementation process of S103 includes:

[0111] Converting the state estimation of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state estimation transformation formula;

[0112] Converting the state covariance of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state covariance transformation formula;

[0113] The state estimation transformation formula is:

[0114] The state covariance transformation formula is:

[0115] in,

[0116] In one embodiment, the target tracking method of the vehicle-mounted radar further includes:

[0117] If the vehicle enters a turning state from a straight state or a straight state from a turning state at the current moment, then ε k+1 Reset to zero.

[0118] Specifically,

[0119] In one embodiment, the target tracking method of the vehicle-mounted radar further includes:

[0120] If the vehicle is in a straight-ahead state at the current moment, the state estimation of the target at the current moment is calculated based on the quantity measurement of the target at the current moment and the state estimation of the target at the previous moment in the vehicle coordinate system.

[0121] In this embodiment, if the vehicle is in a straight-moving state at the current moment, the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target at the previous moment are input into the state update equation in the vehicle coordinate system to obtain the state estimation of the target in the vehicle coordinate system at the current moment.

[0122] The above method is used to estimate the state data of the actual measurement data. It is found that when the vehicle turns around, even if there is a measurement loss, the target speed and position can still be accurately estimated, such as Figure 5 As shown in the black box, it is impossible to accurately estimate the target speed if only the vehicle coordinate system is used for tracking.

[0123] It can be seen from the above embodiments that this embodiment can adopt vehicle coordinate system tracking when the vehicle is not turning or maneuvering, and adopt world coordinate system tracking when the vehicle is in a turning state through the derivation of the conversion formula between the world coordinate system and the vehicle coordinate system, the derivation of the Kalman formula under the world coordinate system, and the solution and derivation of the conversion matrix, thereby improving the target tracking accuracy of the radar and avoiding the problem of tracking failure caused by the relative motion between the radar and the target not conforming to a linear relationship.

[0124] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0125] The following are device embodiments of the present invention. For details not fully described therein, reference may be made to the corresponding method embodiments described above.

[0126] Figure 3 The following is a schematic diagram showing the structure of a target tracking device for a vehicle-mounted radar according to an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are described in detail as follows:

[0127] like Figure 3As shown, the target tracking device 100 of the vehicle-mounted radar includes:

[0128] The measurement acquisition module 110 is used to obtain the measurement of the target detected by the vehicle radar in the vehicle coordinate system at the current moment;

[0129] a state estimation calculation module 120 for calculating, if the ego vehicle is currently in a turning state, a state estimation of the target in the world coordinate system at the current moment based on a measurement of the target in the vehicle coordinate system at the current moment and a state estimation of the target in the world coordinate system at a previous moment; wherein the world coordinate system is the vehicle coordinate system at a first moment, and the first moment is the moment when the ego vehicle enters the current turning state;

[0130] The coordinate conversion module 130 is used to convert the state estimation of the target at the current moment in the world coordinate system into the vehicle coordinate system at the current moment.

[0131] As can be seen from the above embodiment, this embodiment obtains the quantity measurement of the target detected by the ego vehicle radar in the vehicle coordinate system at the current moment; if the ego vehicle is in a turning state at the current moment, the state estimation of the target in the world coordinate system at the current moment is calculated based on the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the ego vehicle enters this turning state; finally, the state estimation of the target in the world coordinate system at the current moment is converted to the vehicle coordinate system at the current moment. Through the above process, the present application can avoid tracking failure caused by the relative motion between the radar and the target no longer conforming to the linear relationship when the vehicle turns, thereby improving the target tracking accuracy of the on-board radar.

[0132] In one embodiment, the state estimation calculation module 120 includes:

[0133] Inputting the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target in the world coordinate system at the previous moment into the state update equation to obtain the state estimation and state covariance of the target in the world coordinate system at the current moment;

[0134] The state update equation is an equation obtained by performing a Kalman filter calculation on the state space model of the target; the state space model includes a state equation and a measurement equation, and the measurement equation is used to express the relationship between the quantity measurement of the target in the vehicle coordinate system and the state quantity in the world coordinate system at the same time;

[0135] Accordingly, the coordinate conversion module 130 includes:

[0136] The state estimation and state covariance of the target at the current moment in the world coordinate system are converted to the vehicle coordinate system at the current moment.

[0137] In one embodiment, the state equation is:

[0138] X k+1,W =F k X k,W +v k ;

[0139] Among them, X k+1,W represents the real state of the target at time k+1 in the world coordinate system; X k,W represents the true state of the target at time k in the world coordinate system, and x(t) represents the x-axis coordinate of the target in the world coordinate system at time t, y(t) represents the y-axis coordinate of the target in the world coordinate system at time t, and v x (t) represents the x-axis velocity of the target in the world coordinate system at time t, v y (t) represents the y-axis velocity of the target in the world coordinate system at time t, V t represents the vehicle speed at time t; F k represents the state transition matrix at time k, and v k represents the process noise at time k, and v k Obey Gaussian distribution N(0,Q k,W );

[0140] The measurement equation is:

[0141] Among them, Z k+1,ego represents the measurement of the target in the vehicle coordinate system at time k+1, represents the actual state of the vehicle in the world coordinate system at time k+1; H k+1 represents the measurement transfer matrix at time k+1, and ω k+1 represents the measurement noise at time k+1, and ω k+1 Obey Gaussian distribution N(0, R k+1,ego );M k+1 represents the rotation matrix at time k+1, and ε k+1 Indicates the cumulative change in the yaw angle from the time the vehicle enters the turn to time k+1.

[0142] In one embodiment, the state update equation is:

[0143]

[0144] in, represents the state estimate of the target in the world coordinate system at time k+1, represents the predicted mean value of the state quantity of the target at time k+1 in the world coordinate system, Z represents the error between the predicted state of the target at time k+1 and the true state in the world coordinate system; k+1,ego represents the measurement of the target in the vehicle coordinate system at time k+1, represents the predicted mean value of the target's measurement at time k+1 in the vehicle coordinate system, K k+1 represents the gain matrix at time k+1, S k+1 represents the new information covariance matrix of the target at time k+1, H k+1 represents the measurement transfer matrix at time k+1, ω k+1 represents the measurement noise at time k+1, P k+1|k,W represents the predicted value of the state covariance of the target at time k+1 in the world coordinate system, P k|k,W represents the state covariance of the target at time k in the world coordinate system, Q k,W represents the process noise in the world coordinate system;

[0145]

[0146] Among them, P k+1|k+1,W represents the state covariance of the target at time k+1 in the world coordinate system, R k+1,W represents the measurement noise matrix at time k+1 in the world coordinate system, R k+1,ego represents the measurement noise matrix at time k+1 in the vehicle coordinate system, and I represents the identity matrix.

[0147] In one embodiment, the coordinate conversion module 130 specifically includes:

[0148] Converting the state estimation of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state estimation transformation formula;

[0149] Converting the state covariance of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state covariance transformation formula;

[0150] The state estimation transformation formula is:

[0151] The state covariance transformation formula is:

[0152] Among them, P k+1|k+1,egorepresents the state covariance of the target at time k+1 in the vehicle coordinate system, P k+1|k+1,W represents the state covariance of the target at time k+1 in the world coordinate system; represents the state estimate of the target in the vehicle coordinate system at time k+1; represents the state estimate of the target in the world coordinate system at time k+1; M k+1 represents the rotation matrix at time k+1, and N k+1 represents the translation vector at time k+1, and

[0153] Among them, ε k+1 V represents the cumulative change in the yaw angle of the vehicle from the time it enters the turning state to time k+1; k+1 represents the vehicle speed at time k+1; represents the yaw rate of the vehicle at time k+1; T represents the frame period; x k represents the x-axis coordinate of the target in the vehicle coordinate system at time k, y k represents the y-axis coordinate of the target in the vehicle coordinate system at time k.

[0154] In one embodiment, the target tracking device 100 of the vehicle-mounted radar further includes:

[0155] The yaw angle reset module is used to reset ε if the vehicle enters a turning state from a straight state or a straight state from a turning state at the current moment. k+1 Reset to zero.

[0156] In one embodiment, the target tracking device 100 of the vehicle-mounted radar further includes:

[0157] a first turning state determination module configured to determine that the vehicle is entering a straight-ahead state from a turning state if the vehicle is currently in a turning state and a cumulative change in the yaw angle of the vehicle within M consecutive frames is less than a first preset threshold;

[0158] The second turning state judgment module is used to determine that the vehicle has entered a turning state from the straight state if the vehicle is currently in a straight state and the cumulative change in the yaw angle of the vehicle within N consecutive frames is greater than a first preset threshold.

[0159] Figure 4 FIG is a schematic diagram of a terminal provided by an embodiment of the present invention. Figure 4As shown, the vehicle-mounted radar 4 of this embodiment includes: a processor 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processor 40. When the processor 40 executes the computer program 42, the steps in the target tracking method embodiments of each vehicle-mounted radar described above are implemented, such as Figure 1 Alternatively, when the processor 40 executes the computer program 42, the functions of the modules / units in the above-mentioned device embodiments are realized, for example, Figure 3 The functions of the units 110 to 130 are shown.

[0160] For example, the computer program 42 may be divided into one or more modules / units, which are stored in the memory 41 and executed by the processor 40 to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing specific functions, and the instruction segments are used to describe the execution process of the computer program 42 in the vehicle-mounted radar.

[0161] The vehicle-mounted radar may include, but is not limited to, a processor 40 and a memory 41. Those skilled in the art will appreciate that Figure 4 This is only an example of a vehicle-mounted radar and does not constitute a limitation on the vehicle-mounted radar. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the terminal may also include input and output devices, network access devices, buses, etc.

[0162] The processor 40 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor.

[0163] The memory 41 can be an internal storage unit of the vehicle-mounted radar, such as a hard disk or memory of the vehicle-mounted radar. The memory 41 can also be an external storage device of the vehicle-mounted radar, such as a plug-in hard disk equipped on the vehicle-mounted radar, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. Furthermore, the memory 41 can also include both the internal storage unit of the vehicle-mounted radar and an external storage device. The memory 41 is used to store the computer program and other programs and data required by the terminal. The memory 41 can also be used to temporarily store data that has been output or is to be output.

[0164] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0165] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0166] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0167] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0168] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0169] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0170] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention can implement all or part of the processes in the above-mentioned embodiment method by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of the above-mentioned vehicle-mounted radar target tracking method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0171] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A target tracking method for a vehicle-mounted radar, characterized in that: include: Obtain the target's measurement in the vehicle coordinate system at the current moment detected by the vehicle's radar; If the ego vehicle is in a turning state at the current moment, then calculating the estimated state of the target in the world coordinate system at the current moment based on the measured quantity of the target in the vehicle coordinate system at the current moment and the estimated state of the target in the world coordinate system at the previous moment; wherein the world coordinate system is the vehicle coordinate system at the first moment, and the first moment is the moment when the ego vehicle enters the current turning state; The state estimation of the target at the current moment in the world coordinate system is converted to the vehicle coordinate system at the current moment.

2. The target tracking method of the vehicle-mounted radar according to claim 1, characterized in that: The calculating the estimated state of the target in the world coordinate system at the current moment based on the quantity measurement of the target in the vehicle coordinate system at the current moment and the estimated state of the target in the world coordinate system at the previous moment includes: Inputting the quantity measurement of the target in the vehicle coordinate system at the current moment and the state estimation of the target in the world coordinate system at the previous moment into the state update equation to obtain the state estimation and state covariance of the target in the world coordinate system at the current moment; The state update equation is an equation obtained by performing a Kalman filter calculation on the state space model of the target; the state space model includes a state equation and a measurement equation, and the measurement equation is used to express the relationship between the quantity measurement of the target in the vehicle coordinate system and the state quantity in the world coordinate system at the same time; Accordingly, converting the state estimate of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment includes: The state estimation and state covariance of the target at the current moment in the world coordinate system are converted to the vehicle coordinate system at the current moment.

3. The target tracking method of the vehicle-mounted radar according to claim 2, characterized in that: The state equation is: X k+1,W =F k X k,W +v k ; Among them, X k+1,W represents the real state of the target at time k+1 in the world coordinate system; X k,W represents the true state of the target at time k in the world coordinate system, and x(t) represents the x-axis coordinate of the target in the world coordinate system at time t, y(t) represents the y-axis coordinate of the target in the world coordinate system at time t, and v x (t) represents the x-axis velocity of the target in the world coordinate system at time t, v y (t) represents the y-axis velocity of the target in the world coordinate system at time t, V t represents the vehicle speed at time t; F k represents the state transition matrix at time k, and v k represents the process noise at time k, and v k Obey Gaussian distribution N(0,Q k,W ); T represents the frame period; Q k,W Represents the process noise matrix in the world coordinate system; The measurement equation is: Among them, Z k+1,ego represents the target's measurement in the vehicle coordinate system at time k+1, represents the actual state of the vehicle in the world coordinate system at time k+1; H k+1 represents the measurement transfer matrix at time k+1, and ω k+1 represents the measurement noise at time k+1, and ω k+1 Obey Gaussian distribution N(0, R k+1,ego );M k+1 represents the rotation matrix at time k+1, and ε k+1 represents the cumulative change in the yaw angle of the vehicle from the time it enters the turning state to time k+1; represents the yaw rate of the vehicle at time k+1; R k+1,ego represents the measurement noise matrix at time k+1 in the vehicle coordinate system.

4. The target tracking method of the vehicle-mounted radar according to claim 3, characterized in that: The state update equation is: in, represents the state estimate of the target in the world coordinate system at time k+1, represents the predicted mean value of the state quantity of the target at time k+1 in the world coordinate system, Z represents the error between the predicted state of the target at time k+1 and the true state in the world coordinate system; k+1,ego represents the target's measurement in the vehicle coordinate system at time k+1, represents the predicted mean value of the target's measurement at time k+1 in the vehicle coordinate system, K k+1 represents the gain matrix at time k+1, S k+1 represents the new information covariance matrix of the target at time k+1, H k+1 represents the measurement transfer matrix at time k+1, ω k+1 represents the measurement noise at time k+1, P k+1|k,W represents the predicted value of the state covariance of the target at time k+1 in the world coordinate system, P k|k,W represents the state covariance of the target at time k in the world coordinate system, Q k,W represents the process noise in the world coordinate system; Among them, P k+1|k+1,W represents the state covariance of the target at time k+1 in the world coordinate system, R k+1,W represents the measurement noise matrix at time k+1 in the world coordinate system, R k+1,ego represents the measurement noise matrix at time k+1 in the vehicle coordinate system, and I represents the identity matrix.

5. The target tracking method of the vehicle-mounted radar according to claim 2, characterized in that: The converting the state estimation and state covariance of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment includes: Converting the state estimation of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state estimation transformation formula; Converting the state covariance of the target at the current moment in the world coordinate system to the vehicle coordinate system at the current moment according to a state covariance transformation formula; The state estimation transformation formula is: The state covariance transformation formula is: Among them, P k+1|k+1,ego represents the state covariance of the target at time k+1 in the vehicle coordinate system, P k+1|k+1,W represents the state covariance of the target at time k+1 in the world coordinate system; represents the state estimate of the target in the vehicle coordinate system at time k+1; represents the state estimate of the target in the world coordinate system at time k+1; M k+1 represents the rotation matrix at time k+1, and N k+1 represents the translation vector at time k+1, and Among them, ε k+1 V represents the cumulative change in the yaw angle of the vehicle from the time it enters the turning state to time k+1; k+1 represents the vehicle speed at time k+1; represents the yaw rate of the vehicle at time k+1; T represents the frame period; x k represents the x-axis coordinate of the target in the vehicle coordinate system at time k, y k represents the y-axis coordinate of the target in the vehicle coordinate system at time k.

6. The target tracking method of a vehicle-mounted radar according to any one of claims 3 to 5, characterized in that: The method further comprises: If the vehicle enters a turning state from a straight state or a straight state from a turning state at the current moment, then ε k+1 Reset to zero.

7. The target tracking method of a vehicle-mounted radar according to any one of claims 1 to 5, characterized in that: Before the vehicle is in a turning state at the current moment, the method further includes: If the ego vehicle is currently in a turning state and the cumulative change in the yaw angle of the ego vehicle within M consecutive frames is less than a first preset threshold, it is determined that the ego vehicle has entered a straight-ahead state from a turning state; If the vehicle is in a straight-ahead state at the current moment and the accumulated change in the yaw angle of the vehicle within N consecutive frames is detected to be greater than a first preset threshold, it is determined that the vehicle has entered a turning state from the straight-ahead state.

8. The target tracking method of a vehicle-mounted radar according to any one of claims 1 to 5, characterized in that: The method further comprises: If the vehicle is in a straight-ahead state at the current moment, the state estimation of the target at the current moment is calculated based on the quantity measurement of the target at the current moment and the state estimation of the target at the previous moment in the vehicle coordinate system.

9. A vehicle-mounted radar, characterized in that: The method comprises a processor and a memory, wherein the memory is used to store a computer program, and the processor is used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images