Target object positioning method and device and vehicle key positioning method

Abstract

The invention relates to a target object positioning method and device and a vehicle key positioning method. The target object positioning comprises the following steps: acquiring detection parameters of multiple parameter types obtained by detecting the target object by at least two detection anchor points; inputting each detection parameter into a pre-constructed space coordinate prediction model to obtain an initial space coordinate of the target object; the space coordinate prediction model comprises space coordinate constraint equations corresponding to the detection anchor points and the parameter types; inputting the initial space coordinates into a pre-constructed motion state model to obtain target space coordinates; wherein the motion state model is used for modeling the motion state change of the target object; and outputting a positioning result of the target object according to the target space coordinates. By adopting the method, low-cost and high-precision target positioning can be realized.

Description

Technical Field

[0001] This application relates to the field of target positioning technology, and in particular to a target object positioning method, device, vehicle key positioning method, computer equipment, and computer storage medium. Background Technology

[0002] With the widespread application of smart devices, the requirements for the accuracy of target object positioning are constantly increasing. For example, in the scenario of vehicle key positioning, the need for accurate positioning of vehicle owners and occupants is becoming increasingly prominent, such as functions like smart key sensing, automatic door opening, and welcome light control.

[0003] In related technologies, multiple detection anchor points are required to locate the target object, which leads to complex hardware costs and in-vehicle wiring, increasing the overall vehicle manufacturing cost and system complexity. Summary of the Invention

[0004] Therefore, it is necessary to provide a target object positioning method, device, vehicle key positioning method, computer equipment, and computer storage medium that can achieve high-precision and low-cost positioning to address the above-mentioned technical problems.

[0005] Firstly, this application provides a method for locating a target object, including:

[0006] Acquire detection parameters of various parameter types obtained from detecting the target object using at least two detection anchor points;

[0007] Each of the aforementioned detection parameters is input into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the aforementioned detection anchor points and corresponding to each of the aforementioned parameter types;

[0008] The initial spatial coordinates are input into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object;

[0009] Based on the target spatial coordinates, output the positioning result of the target object.

[0010] In one embodiment, the step of inputting each of the detection parameters into a pre-built spatial coordinate prediction model to obtain the initial spatial coordinates of the target object includes:

[0011] Each of the aforementioned detection parameters is injected into the corresponding spatial coordinate constraint equation to obtain the updated spatial coordinate constraint equations.

[0012] The updated spatial coordinate constraint equations are combined into an overdetermined system of equations. The objective solution of the overdetermined system of equations is determined to obtain the initial spatial coordinates.

[0013] In one embodiment, the parameter types include orientation angle, pitch angle, and straight-line distance, and each of the spatial coordinate constraint equations has a corresponding weighting coefficient. The step of injecting each of the detection parameters into the corresponding spatial coordinate constraint equation to obtain updated spatial coordinate constraint equations includes:

[0014] Obtain the real-time angle of arrival confidence parameter for each of the aforementioned detection anchor points; wherein, the angle of arrival confidence parameter is used to characterize the confidence of the detection parameters of the heading angle or the pitch angle;

[0015] Based on the real-time arrival angle confidence parameters of each of the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to each of the aforementioned detection anchor points and corresponding to the azimuth angle or the pitch angle;

[0016] Based on the real-time arrival angle confidence parameters of all the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to the straight-line distance;

[0017] The values ​​of each of the weight coefficients are injected into the corresponding weight coefficients, and the values ​​of each of the detection parameters are injected into the corresponding spatial coordinate constraint equations to obtain the updated spatial coordinate constraint equations.

[0018] In one embodiment, determining the value of the weighting coefficient corresponding to the straight-line distance based on the real-time arrival angle confidence parameters of all the probe anchor points includes:

[0019] If the real-time arrival angle confidence parameter of all the aforementioned detection anchor points is less than or equal to the first threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the first value.

[0020] If the real-time arrival angle confidence parameter of any of the aforementioned detection anchor points is less than or equal to the second threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the second value.

[0021] Wherein, the first threshold is greater than the second threshold, and the first value is less than the second value.

[0022] In one embodiment, the motion state model includes a state transition matrix, which characterizes the motion state changes of the target object. The step of inputting the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates includes:

[0023] Obtain the historical spatial coordinates of the target object, and determine the predicted spatial coordinates of the target object based on the historical spatial coordinates and the state transition matrix;

[0024] Determine the initial residual between the initial spatial coordinates and the predicted spatial coordinates;

[0025] Obtain the arrival angle confidence parameters of each of the aforementioned probe anchor points in history, and perform weighted processing on the initial residuals based on the arrival angle confidence parameters of each of the aforementioned probe anchor points in history to obtain weighted residuals;

[0026] The predicted spatial coordinates are updated based on the weighted residuals to obtain the target spatial coordinates.

[0027] In one embodiment, the target object is a vehicle key, the detection anchor point is set on the vehicle, and the method further includes:

[0028] Based on the target spatial coordinates, the target vehicle area where the vehicle key is located is determined in several pre-divided vehicle areas; wherein, different vehicle areas are divided according to different distances between the vehicle key and the vehicle, and the vehicle is pre-configured with in-vehicle functions associated with each vehicle area.

[0029] Control the vehicle to perform the target vehicle functions associated with the target vehicle region.

[0030] Secondly, this application also provides a method for locating a vehicle key, the method comprising:

[0031] Acquire detection parameters of various parameter types obtained from vehicle key detection at at least two detection anchor points;

[0032] Each of the aforementioned detection parameters is input into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the vehicle key; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the aforementioned detection anchor points and corresponding to each of the aforementioned parameter types;

[0033] The initial spatial coordinates are input into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the vehicle key;

[0034] Based on the target spatial coordinates, the location result of the vehicle key is output.

[0035] Thirdly, this application also provides a target object positioning device, comprising:

[0036] The detection parameter acquisition module is used to acquire detection parameters of various parameter types obtained from the detection of the target object by at least two detection anchor points;

[0037] An initial spatial coordinate determination module is used to input each of the detection parameters into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the detection anchor points and corresponding to each of the parameter types;

[0038] The target spatial coordinate determination module is used to input the initial spatial coordinates into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object;

[0039] The positioning result output module is used to output the positioning result of the target object based on the target spatial coordinates.

[0040] Fourthly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the method described above.

[0041] Fifthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the method described above.

[0042] The aforementioned target object positioning method, device, vehicle key positioning method, computer equipment, and computer storage medium input detection parameters of various parameter types into a spatial coordinate prediction model. Using spatial coordinate constraint equations corresponding to each detection anchor point and each parameter type, they establish associated constraints on the spatial coordinates to obtain the initial spatial coordinates of the target object, achieving a preliminary estimation of the target object's location. Then, the initial spatial coordinates are input into a pre-constructed motion state model to model the changes in the target object's motion state, removing dynamic noise and obtaining higher-precision target spatial coordinates. This achieves high-precision, low-cost target object positioning, requiring only at least two detection anchor points, meeting the cost control requirements of scenarios such as vehicle key positioning. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0044] Figure 1 A flowchart illustrating the steps of a target localization method provided in an embodiment of this application;

[0045] Figure 2A schematic diagram of a preset area of ​​a vehicle provided in an embodiment of this application;

[0046] Figure 3 This is a schematic diagram of the installation of a detection anchor point according to an embodiment of this application;

[0047] Figure 4 A schematic diagram of a positioning system provided in an embodiment of this application;

[0048] Figure 5 A flowchart illustrating the vehicle-side process for locating the vehicle key according to an embodiment of this application;

[0049] Figure 6 A flowchart illustrating the steps of a vehicle key location method provided in an embodiment of this application;

[0050] Figure 7 This is a structural block diagram of a vehicle key locating device provided in an embodiment of this application;

[0051] Figure 8 This is a schematic diagram of the structure of a computer device provided in an embodiment of this application. Detailed Implementation

[0052] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0053] It should be noted that the terms "first," "second," etc., used in this application can be used to describe various elements, but these elements are not limited by these terms. These terms are only used to distinguish the first element from the second element. The terms "comprising" and "having," and any variations thereof, used in this application, are intended to cover non-exclusive inclusion. The term "multiple" used in this application refers to two or more. The term "and / or" used in this application refers to one of the embodiments, or any combination of multiple embodiments.

[0054] In one embodiment, such as Figure 1 As shown, a method for locating a target object is provided. This embodiment illustrates the application of this method to a terminal, which may include in-vehicle systems, smart home systems, and other smart terminals. It is understood that this method can also be applied to a server, and further to a system including both a terminal and a server, and is implemented through interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0055] Step 101: Obtain detection parameters of various parameter types obtained from the detection of the target object by at least two detection anchor points;

[0056] In practical implementation, the detection anchor point can be a device with a relatively fixed and known position in the positioning system. It can use its own position as a reference to detect various parameter types of the target object. The target object is the object to be located, such as Bluetooth car keys, smartphones, smartwatches, and other electronic devices. Parameter types can include AOA (Angle of Arrival) based direction angle, TOF (Time of Flight) based distance measurement, TDOA (Time Difference of Arrival) based distance measurement, and ChannelSounding based distance measurement, etc.

[0057] Step 102: Input each of the detection parameters into the pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the detection anchor points and corresponding to each of the parameter types;

[0058] Spatial coordinate prediction models are used to make preliminary predictions of the location of target objects, obtaining their initial spatial coordinates. Spatial coordinate constraint equations are equations that constrain the spatial coordinates of the target object for different parameter types and different probe anchor points. Each spatial coordinate constraint equation uses the spatial coordinates of the target object as the unknown to be determined. For example, if a probe anchor point detects a target object with a direction angle as its parameter type, the corresponding spatial coordinate constraint equation represents constraints on the target object's spatial coordinates in two dimensions: parameter type (direction angle) and data source (the probe anchor point).

[0059] The number of spatial coordinate constraint equations corresponds to the number of probe anchor points and the number of probe parameters of different parameter types detected by each anchor point. For example, if there are 2 probe anchor points, and each probe anchor point detects probe data of 3 parameter types of the target object, then the spatial coordinate prediction model includes 6 spatial coordinate constraint equations, and each spatial coordinate constraint equation corresponds to 1 probe anchor point and 1 parameter type.

[0060] In practical implementation, the structure of spatial coordinate constraint equations corresponding to different parameter types can be predefined in the spatial coordinate prediction model. After receiving each detection parameter, the spatial coordinate constraint equations corresponding to different detection parameters can be determined through the predefined structure.

[0061] Furthermore, the initial spatial coordinates of the target object are determined based on the spatial coordinate constraint equations. For example, the spatial coordinate constraint equations can be transformed into a multi-objective optimization model, and the loss function of the multi-objective optimization model can be determined. By minimizing the loss function, the optimal solution of the multi-objective optimization model can be determined, thus obtaining the initial spatial coordinates. Alternatively, the spatial coordinate constraint equations can be combined into an overdetermined system of equations (a system of equations with more equations than unknowns). The optimal solution of the overdetermined system of equations can be obtained by solving a preset algorithm, thus obtaining the initial spatial coordinates.

[0062] In some embodiments, the detection parameters are input into a pre-built spatial coordinate prediction model to obtain the initial spatial coordinates of the vehicle key, including:

[0063] Each detection parameter is injected into the corresponding spatial coordinate constraint equation to obtain the updated spatial coordinate constraint equation;

[0064] The updated spatial coordinate constraint equations are combined into an overdetermined system of equations. The objective solution of the overdetermined system of equations is determined, and the initial spatial coordinates are obtained.

[0065] In practical implementation, specific detection parameters are injected into the corresponding spatial coordinate constraint equations, resulting in updated spatial coordinate constraint equations. For example, if the parameter type is direction angle, the predefined spatial coordinate constraint equation for the direction angle is:

[0066] cos(az)*(x-x0) - sin(az)*(y-y0)=0(1)

[0067] In equation (1), az represents the direction angle parameter, the spatial coordinates of the detection anchor point are represented as (x0, y0, z0), and the spatial coordinates of the target object are represented as (x, y, z).

[0068] Then, the specific detection parameters of the direction angle detected by a certain detection anchor point, as well as the spatial coordinates of the detection anchor point, are injected into equation (1) to obtain the updated spatial coordinate constraint equation corresponding to the detection anchor point and parameter type.

[0069] Furthermore, the spatial coordinate constraint equations are combined into an overdetermined system of equations. For example, if there are two detection anchor points, and each detection anchor point detects detection data of three parameter types of the target object, then an overdetermined system of equations including six spatial coordinate constraint equations can be formed.

[0070] Based on a preset algorithm, such as the least squares method or the maximum likelihood estimation algorithm, the target solution of the overdetermined system of equations is determined, and the target solution is the initial spatial coordinates of the target object.

[0071] In some examples, the overdetermined system of equations consisting of the spatial coordinate constraint equations is A*X = b, where A is a 6*3 coefficient matrix, X is a position vector, and b is a constant vector. The process of determining the objective solution of the overdetermined system of equations is as follows:

[0072] Construct a weighted covariance matrix: Based on the weight coefficients, weight each row of the 6*3 coefficient matrix A; then calculate the weighted A*A (A*A is a 3×3 square matrix, which can be achieved through double loop accumulation) and A*b (3*1 vector), transforming the overdetermined system of equations into a weighted regularized system of equations A*A*X = A*b, so that high-confidence data accounts for a higher proportion in the solution;

[0073] Matrix inversion solution: The LU decomposition method is used to invert A*A to avoid the numerical instability of direct inversion; X = (A*A)*A*b is calculated to obtain the target solution of X, which is the initial spatial coordinates of the target object.

[0074] In this embodiment, by forming an overdetermined set of equations from the spatial coordinate constraint equations, determining the objective solution of the overdetermined set of equations, and obtaining the initial spatial coordinates, the rigid constraints are transformed into an optimization problem. By introducing redundant information, noise is suppressed and the robustness and numerical stability of the initial spatial coordinates are improved.

[0075] In some embodiments, the parameter types include orientation angle, pitch angle, and straight-line distance. Each spatial coordinate constraint equation has a corresponding weighting coefficient. Each detection parameter is injected into the corresponding spatial coordinate constraint equation to obtain updated spatial coordinate constraint equations, including:

[0076] Obtain the real-time angle of arrival confidence parameters for each detection anchor point; whereby the angle of arrival confidence parameters are used to characterize the confidence of the detection parameters of the heading angle or pitch angle;

[0077] Based on the real-time arrival angle confidence parameters of each detection anchor point, determine the value of the weighting coefficient corresponding to each detection anchor point and corresponding to the heading angle or pitch angle;

[0078] Based on the real-time arrival angle confidence parameters of all probe anchor points, determine the value of the weighting coefficient corresponding to the straight-line distance;

[0079] The values ​​of each weight coefficient and each detection parameter are injected into the corresponding spatial coordinate constraint equations to obtain the updated spatial coordinate constraint equations.

[0080] In this embodiment, the detection data with the parameter type of direction angle is used to represent the angle (range -180°~180°) between the projection of the target object on the xy plane of the detection anchor point and the positive x-axis direction of the anchor point, reflecting the orientation information of the target object in the horizontal direction.

[0081] The parameter type is the detection data of pitch angle, which is used to represent the angle (range -90°~90°) between the line connecting the target object and the detection anchor point and the xy plane, reflecting the height information of the target object.

[0082] The parameter type is detection data of straight-line distance, which is used to represent the straight-line distance between the target object and the detection anchor point, reflecting the absolute spatial distance of the target object.

[0083] The azimuth and pitch angles are obtained by using the angle of arrival technology at each anchor point. Since the detection accuracy of the anchor points may vary and they may be affected by interference signals in different ways, the reliability parameter of the angle of arrival of each anchor point can characterize the reliability of the detection parameters of the azimuth or pitch angles detected by different anchor points, so as to indicate the reliability of the data source.

[0084] Each spatial coordinate constraint equation has a corresponding weight coefficient, and different weight coefficients are used to characterize the degree of influence of different spatial coordinate constraint equations in the overdetermined equation set. Therefore, based on the real-time arrival angle confidence parameters of each probe anchor point, the values ​​of the weight coefficients corresponding to each probe anchor point and corresponding to the heading angle or pitch angle are determined.

[0085] For example, if the confidence parameter FOM of the angle of arrival of a certain probe anchor point is 80 (the value range is 0-100), then the value of the weight coefficient corresponding to that probe anchor point and corresponding to the azimuth angle or pitch angle can be determined as 0.8 by w=FOM / 100.

[0086] Furthermore, based on the real-time arrival angle confidence parameters of all detection anchor points, the value of the weighting coefficient corresponding to the straight-line distance is determined.

[0087] For example, the average value of the real-time arrival angle confidence parameter of all probe anchor points can be calculated. If the average value is too small (e.g., less than the threshold), the value of the weight coefficient corresponding to the straight-line distance can be increased from the initial 1 to 1.2. Alternatively, after averaging the real-time arrival angle confidence parameters of all probe anchor points, normalization can be performed. The difference between 1 and the normalized average value is the value of the weight coefficient corresponding to the straight-line distance.

[0088] Finally, the values ​​of each weight coefficient and each detection parameter are injected into the corresponding spatial coordinate constraint equations. For example, the values ​​of each weight coefficient are injected into the corresponding weight coefficients, and the detection parameters are injected into the corresponding spatial coordinate constraint equation parameters to obtain the updated spatial coordinate constraint equations.

[0089] In some examples, the spatial coordinates of a probe anchor point are represented as (x0, y0, z0), the spatial coordinates of the target object are represented as (x, y, z), the azimuth is az, the elevation is el, and the straight-line distance is d;

[0090] The orientation angle of the target object can be expressed as:

[0091] tan(az)=(y-y0) / (x-x0)(2)

[0092] After linearizing equation (2), we obtain equation (1). Adding weight coefficient w to equation (1) yields the spatial coordinate constraint equation corresponding to the direction angle:

[0093] w*sin(az)*y = w*[cos(az)*x0- sin(az)*y0](3)

[0094] The pitch angle of the target object is expressed as:

[0095] tan(el)=(z-z0) / √[(x-x0)²+(y-y0)²] (4)

[0096] After applying linearization constraints to equation (4), we get:

[0097] sin(el)*(x-x0) - cos(el)*(z-z0) = 0(5)

[0098] Adding a weighting coefficient w to equation (5) yields the spatial coordinate constraint equation corresponding to the pitch angle:

[0099] w*sin(el)*x - w*cos(el)*z = w*[sin(el)*x0 - cos(el)*z0] (6)

[0100] The straight-line distance to the target object can be expressed as:

[0101] (x-x0)²+(y-y0)²+(z-z0)²=d² (7)

[0102] Let the spatial coordinates of the target object in the previous frame be (x_prev, y_prev, z_prev). Then, after applying linear constraints to equation (7) based on the spatial coordinates of the previous frame, we get:

[0103] 2*dx*x + 2*dy*y + 2*dz*z = d² - (dx²+dy²+dz²) + 2*(dx*x0+dy*y0+dz*z0) (8)

[0104] Adding a weighting coefficient w to equation (8) yields the spatial coordinate constraint equation corresponding to the straight-line distance:

[0105] w*2*dx*x + w*2*dy*y + w*2*dz*z = w*d² - w*(dx²+dy²+dz²) + w*2*(dx*x0+dy*y0+dz*z0) (9)

[0106] There are two detection anchor points. Each detection anchor point obtains the direction angle and pitch angle detection parameters of the target object based on AOA detection, and the straight distance detection parameters based on TOF detection. Then each detection anchor point has a spatial constraint equation corresponding to equations (3), (6), and (9).

[0107] Furthermore, the arrival angle confidence parameters of each detection anchor point are obtained. After determining the weight coefficients of each spatial constraint equation through the arrival angle confidence parameters, the values ​​of each weight coefficient and each detection parameter are injected into the corresponding spatial constraint equations to obtain the updated spatial constraint equations.

[0108] In this embodiment, by injecting the values ​​of each weight coefficient and each detection parameter into the corresponding spatial coordinate constraint equation, the influence of the detection accuracy of each detection anchor point can be reduced, thereby improving the accuracy and reliability of the initial spatial coordinates.

[0109] In some embodiments, the value of the weighting coefficient corresponding to the straight-line distance is determined based on the real-time arrival angle confidence parameters of all probe anchor points, including:

[0110] If the real-time arrival angle confidence parameter of all detection anchor points is less than or equal to the first threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the first value.

[0111] If the real-time arrival angle confidence parameter of any detection anchor point is less than or equal to the second threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the second value.

[0112] Among them, the first threshold is greater than the second threshold, and the first value is less than the second value.

[0113] In the specific implementation, if the real-time angle of arrival (AOA) reliability parameter of all probe anchor points is less than or equal to the first threshold, it indicates that the reliability of the probe parameters for each azimuth and pitch angle obtained by the current probe anchor points through AOA is low. In this case, the value of the weighting coefficient corresponding to the straight-line distance is increased from the initial value to the first value, for example, from 1 to 1.2. If the real-time AOA reliability parameter of any probe anchor point is less than or equal to the second threshold, it indicates that the reliability of the data obtained through AOA is even lower. In this case, the value of the weighting coefficient corresponding to the straight-line distance is increased from the initial value to the second value, for example, from 1 to 1.4.

[0114] In some examples, the angle-of-arrival confidence parameter ranges from 0 to 100%, so the first threshold can be 70% and the second threshold can be 40%. When the angle-of-arrival confidence parameter of each probe anchor point is less than or equal to 70%, the weighting coefficient corresponding to the straight-line distance is increased from 1 to 1.2; when the angle-of-arrival confidence parameter of any probe anchor point is less than or equal to 40%, the weighting coefficient corresponding to the straight-line distance is increased from 1 to 1.4.

[0115] In this embodiment, by judging the first threshold and the second threshold, the weight corresponding to the straight-line distance is adaptively increased, thereby reducing the impact on the accuracy of the positioning result when the confidence parameter of the arrival angle of each anchor point is low.

[0116] Step 103: Input the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object;

[0117] In the specific implementation, after obtaining the initial predicted spatial coordinates, since the target object may have changes in motion state (e.g., the user runs or moves while carrying the Bluetooth vehicle key to be located), the initial spatial coordinates are input into the pre-built motion state model. The motion state changes of the target object are modeled using the initial spatial coordinates, and the changes in spatial coordinates are predicted to obtain target spatial coordinates with higher accuracy after removing dynamic noise.

[0118] In some examples, motion state models can be built based on observers such as Extended Kalman Filter (EKF), robust observers, and adaptive observers to model the motion state of the target object and remove dynamic noise.

[0119] In some embodiments, the motion state model includes a state transition matrix, which is used to characterize the changes in the motion state of the target object. Initial spatial coordinates are input into the pre-constructed motion state model to obtain the target spatial coordinates, including:

[0120] Obtain the historical spatial coordinates of the target object, and determine the predicted spatial coordinates of the target object based on the historical spatial coordinates and the state transition matrix;

[0121] Determine the initial residuals between the initial spatial coordinates and the predicted spatial coordinates;

[0122] Obtain the historical angle of arrival confidence parameters of each probe anchor point, and perform weighted processing on the initial residuals based on the historical angle of arrival confidence parameters of each probe anchor point to obtain the weighted residuals;

[0123] The predicted spatial coordinates are updated based on the weighted residuals to obtain the target spatial coordinates.

[0124] In the specific implementation, the historical spatial coordinates can be the spatial coordinates of the target object in the previous frame, and the state transition matrix can be an identity matrix determined based on a preset motion state, such as the identity matrix corresponding to uniform motion. The predicted spatial coordinates are determined by performing operations on the historical spatial coordinates using the state transition matrix (e.g., multiplying the state transition matrix with the historical spatial coordinates represented as vectors).

[0125] Furthermore, the initial residual between the initial spatial coordinates and the predicted spatial coordinates is determined. This initial residual can reflect the degree of deviation of the predicted spatial coordinates from the initial spatial coordinates.

[0126] Furthermore, to reduce the impact of the historical data accuracy of each detection anchor point on the predicted spatial coordinates, the arrival angle confidence parameters of each detection anchor point in history are obtained. The initial residuals are then weighted based on the arrival angle confidence parameters of each detection anchor point in history to obtain the weighted residuals.

[0127] Furthermore, the predicted spatial coordinates are updated and corrected by weighted residuals. For example, the weighted residuals are added to the predicted spatial coordinates to obtain the final target spatial coordinates.

[0128] In some examples, the motion state model may also include a state vector X (x, y, z positions), a covariance matrix P (for positioning uncertainty), process noise Q (for characterizing motion noise), observation noise R (for characterizing sensor error), and an angle-of-arrival confidence weight matrix W, with W initially set to 1.0. The process of outputting the target spatial coordinates based on this motion state model is as follows:

[0129] Get the historical spatial coordinates of the target object in the previous frame. The historical spatial coordinates can be set to {0,0,0} when the system starts.

[0130] Based on historical spatial coordinates, the predicted spatial coordinates X_pred of the target object are predicted through the state transition matrix F, and the prediction covariance is updated: P_pred = F*P*F + Q; at the same time, the weight matrix W is updated according to the historical arrival angle confidence parameters of each detection anchor point; the initial spatial coordinates are used as the observation value Z, and the weighted residual Y = W*(Z - X_pred) is calculated in combination with the weight matrix W.

[0131] Finally, the predicted spatial coordinates are corrected by the Kalman gain coefficient K (which can be combined with the weight matrix to weigh the reliability of prediction and observation), and the target spatial coordinates X_new = X_pred + K*Y are obtained; at the same time, the prediction covariance P_new is updated.

[0132] In this embodiment, the initial residual between the initial spatial coordinates and the predicted spatial coordinates is determined to quantify the deviation between the observed data (initial spatial coordinates) and the predicted state (predicted spatial coordinates). Then, by introducing the arrival angle confidence parameter of each probe anchor point in history, the initial residual is weighted to obtain the weighted residual. This effectively reduces the impact of low confidence probe parameters on the accuracy of the target spatial coordinates, improves the accuracy and robustness of the target spatial coordinates, and enables effective noise suppression and error correction in complex observation environments.

[0133] Step 104: Output the positioning result of the target object based on the target spatial coordinates.

[0134] In practical implementation, the target spatial coordinates can be directly output as the positioning result, or the target spatial coordinates and the associated information can be encapsulated as the positioning result for output, thereby realizing the positioning of the target object.

[0135] In some embodiments, the target object is a vehicle key, the detection anchor point is set on the vehicle, and the method further includes:

[0136] Based on the target spatial coordinates, the target vehicle area where the vehicle key is located is determined in multiple pre-divided vehicle areas; different vehicle areas are divided according to different distances between the vehicle key and the vehicle, and the vehicle has preset in-vehicle functions associated with each vehicle area.

[0137] Control the vehicle to perform the target vehicle functions associated with the target vehicle area.

[0138] In practice, different preset areas are defined based on the distance between the vehicle key and the vehicle. The preset area where the vehicle is located can be determined using the target spatial coordinates. The vehicle can then execute different in-vehicle functions depending on the preset area where the vehicle key is located. For example, when the user is carrying the vehicle key in a preset area at a greater distance, the vehicle can perform corresponding welcome functions, activating welcome voice prompts and lighting effects; when the user is carrying the vehicle key in a preset area at a closer distance, the vehicle can perform corresponding unlocking functions, such as unlocking the car doors.

[0139] In some examples, such as Figure 2 As shown, with the vehicle as the center point, the interior area P4, the circular areas P2 and P3, and the area P1 outside P3 are divided according to the distance from near to far. Among them, P4 is the PS (Passive Start) area, where the vehicle is pre-set with corresponding start functions; P2 is the PE (Passive Entry) area, where the vehicle is pre-set with corresponding door unlock functions; and P3 is the welcome area, where the vehicle is pre-set with corresponding welcome functions.

[0140] In practical applications, the detection anchor points can be set on the vehicle as follows: Figure 3 As shown. The detection anchor points can be UWB chip-based devices. Two detection anchor points are installed on the left and right sides of the front of the vehicle (which can be adjusted according to actual needs), and a coordinate system is established with the center position of the vehicle body axis.

[0141] In some embodiments, such as Figure 4 As shown, a positioning system structure diagram for vehicle key positioning scenarios is also provided. The positioning system includes a device end, as well as a vehicle end and a cloud end that communicate with the device end.

[0142] The device side may include the vehicle owner's or authorized device, which communicates via UWB / Bluetooth, and the communication uses SE encryption;

[0143] The vehicle-side system includes dual detection anchor points (such as UWB anchor points), a main control unit (such as an ECU), and an execution module. The detection anchor points collect detection parameters such as AOA and TOF, and obtain FOM (Angle of Arrival) reliability parameters. The main control unit is responsible for receiving the detection parameters and outputting the target space coordinates of the vehicle key. The execution module executes the vehicle functions in the corresponding preset area according to the target space coordinates.

[0144] The cloud is responsible for secure synchronization and manages and controls access to Bluetooth keys.

[0145] Specifically, the workflow for vehicle-side target object localization is as follows: Figure 5 As shown, it includes:

[0146] The main control unit performs system initialization, such as initializing various parameters; the main control unit collects detection parameters such as AOA and TOF through the detection anchor points, and obtains the FOM (Angle of Arrival) confidence parameters of each detection anchor point.

[0147] The main control unit verifies the detection parameters. If the verification fails, it performs anomaly handling, for example, using the historical spatial coordinates of the target object from the previous frame as the initial spatial coordinates.

[0148] If the verification is successful, the main control unit injects each detection parameter and the weight value determined based on FOM into the spatial coordinate equation and forms an overdetermined equation set. If the overdetermined equation set can be solved, the main control unit uses the least squares method to find the target solution and obtain the initial spatial coordinates. If the overdetermined equation set cannot be solved, the main control unit performs a separate calculation on the TOF to obtain the initial spatial coordinates.

[0149] The main control unit inputs the initial spatial coordinates into the motion state model, performs state prediction through EKF, and outputs the target spatial coordinates.

[0150] The execution module performs the corresponding vehicle functions based on the target space coordinates.

[0151] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0152] Based on the same inventive concept, this application also provides a vehicle key positioning method for implementing the target object positioning method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more vehicle key positioning method embodiments provided below can be found in the limitations of the target object positioning method described above, and will not be repeated here.

[0153] In one exemplary embodiment, such as Figure 6 As shown, a vehicle key location method is provided, including:

[0154] Step 601: Obtain detection parameters of various parameter types obtained from the detection of the vehicle key at at least two detection anchor points;

[0155] Step 602: Input each of the detection parameters into the pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the vehicle key; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the detection anchor points and corresponding to each of the parameter types;

[0156] Step 603: Input the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the vehicle key;

[0157] Step 604: Output the location result of the vehicle key based on the target spatial coordinates.

[0158] In one embodiment, the step of inputting each of the detection parameters into a pre-built spatial coordinate prediction model to obtain the initial spatial coordinates of the vehicle key includes:

[0159] Each of the aforementioned detection parameters is injected into the corresponding spatial coordinate constraint equation to obtain the updated spatial coordinate constraint equations.

[0160] The updated spatial coordinate constraint equations are combined into an overdetermined system of equations. The objective solution of the overdetermined system of equations is determined to obtain the initial spatial coordinates.

[0161] In one embodiment, the parameter types include orientation angle, pitch angle, and straight-line distance, and each of the spatial coordinate constraint equations has a corresponding weighting coefficient. The step of injecting each of the detection parameters into the corresponding spatial coordinate constraint equation to obtain updated spatial coordinate constraint equations includes:

[0162] Obtain the real-time angle of arrival confidence parameter for each of the aforementioned detection anchor points; wherein, the angle of arrival confidence parameter is used to characterize the confidence of the detection parameters of the heading angle or the pitch angle;

[0163] Based on the real-time arrival angle confidence parameters of each of the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to each of the aforementioned detection anchor points and corresponding to the azimuth angle or the pitch angle;

[0164] Based on the real-time arrival angle confidence parameters of all the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to the straight-line distance;

[0165] The values ​​of each of the weight coefficients are injected into the corresponding weight coefficients, and the values ​​of each of the detection parameters are injected into the corresponding spatial coordinate constraint equations to obtain the updated spatial coordinate constraint equations.

[0166] In one embodiment, determining the value of the weighting coefficient corresponding to the straight-line distance based on the real-time arrival angle confidence parameters of all the probe anchor points includes:

[0167] If the real-time arrival angle confidence parameter of all the aforementioned detection anchor points is less than or equal to the first threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the first value.

[0168] If the real-time arrival angle confidence parameter of any of the aforementioned detection anchor points is less than or equal to the second threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the second value.

[0169] Wherein, the first threshold is greater than the second threshold, and the first value is less than the second value.

[0170] In one embodiment, the motion state model includes a state transition matrix, which characterizes the motion state changes of the vehicle key. The step of inputting the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates includes:

[0171] Obtain the historical spatial coordinates of the vehicle key, and determine the predicted spatial coordinates of the vehicle key based on the historical spatial coordinates and the state transition matrix;

[0172] Determine the initial residual between the initial spatial coordinates and the predicted spatial coordinates;

[0173] Obtain the arrival angle confidence parameters of each of the aforementioned probe anchor points in history, and perform weighted processing on the initial residuals based on the arrival angle confidence parameters of each of the aforementioned probe anchor points in history to obtain weighted residuals;

[0174] The predicted spatial coordinates are updated based on the weighted residuals to obtain the target spatial coordinates.

[0175] In one embodiment, the detection anchor point is located on the vehicle, and the method further includes:

[0176] Based on the target spatial coordinates, the target vehicle area where the vehicle key is located is determined in several pre-divided vehicle areas; wherein, different vehicle areas are divided according to different distances between the vehicle key and the vehicle, and the vehicle is pre-configured with in-vehicle functions associated with each vehicle area.

[0177] Control the vehicle to perform the target vehicle functions associated with the target vehicle region.

[0178] Based on the same inventive concept, this application also provides a vehicle key locating device for implementing the vehicle key locating method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more vehicle key locating device embodiments provided below can be found in the limitations of the vehicle key locating method described above, and will not be repeated here.

[0179] In one exemplary embodiment, such as Figure 7 As shown, a target object positioning device is provided, comprising:

[0180] The detection parameter acquisition module 701 is used to acquire detection parameters of various parameter types obtained from the detection of the target object by at least two detection anchor points;

[0181] The initial spatial coordinate determination module 702 is used to input each of the detection parameters into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the detection anchor points and corresponding to each of the parameter types;

[0182] The target spatial coordinate determination module 703 is used to input the initial spatial coordinates into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object;

[0183] The positioning result output module 704 is used to output the positioning result of the target object based on the target spatial coordinates.

[0184] In one embodiment, the step of inputting each of the detection parameters into a pre-built spatial coordinate prediction model to obtain the initial spatial coordinates of the target object includes:

[0185] Each of the aforementioned detection parameters is injected into the corresponding spatial coordinate constraint equation to obtain the updated spatial coordinate constraint equations.

[0186] The updated spatial coordinate constraint equations are combined into an overdetermined system of equations. The objective solution of the overdetermined system of equations is determined to obtain the initial spatial coordinates.

[0187] In one embodiment, the parameter types include orientation angle, pitch angle, and straight-line distance, and each of the spatial coordinate constraint equations has a corresponding weighting coefficient. The step of injecting each of the detection parameters into the corresponding spatial coordinate constraint equation to obtain updated spatial coordinate constraint equations includes:

[0188] Obtain the real-time angle of arrival confidence parameter for each of the aforementioned detection anchor points; wherein, the angle of arrival confidence parameter is used to characterize the confidence of the detection parameters of the heading angle or the pitch angle;

[0189] Based on the real-time arrival angle confidence parameters of each of the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to each of the aforementioned detection anchor points and corresponding to the azimuth angle or the pitch angle;

[0190] Based on the real-time arrival angle confidence parameters of all the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to the straight-line distance;

[0191] The values ​​of each of the weight coefficients are injected into the corresponding weight coefficients, and the values ​​of each of the detection parameters are injected into the corresponding spatial coordinate constraint equations to obtain the updated spatial coordinate constraint equations.

[0192] In one embodiment, determining the value of the weighting coefficient corresponding to the straight-line distance based on the real-time arrival angle confidence parameters of all the probe anchor points includes:

[0193] If the real-time arrival angle confidence parameter of all the aforementioned detection anchor points is less than or equal to the first threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the first value.

[0194] If the real-time arrival angle confidence parameter of any of the aforementioned detection anchor points is less than or equal to the second threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the second value.

[0195] Wherein, the first threshold is greater than the second threshold, and the first value is less than the second value.

[0196] In one embodiment, the motion state model includes a state transition matrix, which characterizes the motion state changes of the target object. The step of inputting the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates includes:

[0197] Obtain the historical spatial coordinates of the target object, and determine the predicted spatial coordinates of the target object based on the historical spatial coordinates and the state transition matrix;

[0198] Determine the initial residual between the initial spatial coordinates and the predicted spatial coordinates;

[0199] Obtain the arrival angle confidence parameters of each of the aforementioned probe anchor points in history, and perform weighted processing on the initial residuals based on the arrival angle confidence parameters of each of the aforementioned probe anchor points in history to obtain weighted residuals;

[0200] The predicted spatial coordinates are updated based on the weighted residuals to obtain the target spatial coordinates.

[0201] In one embodiment, the target object is a vehicle key, the detection anchor point is set on the vehicle, and the device is further used for:

[0202] Based on the target spatial coordinates, the target vehicle area where the vehicle key is located is determined in several pre-divided vehicle areas; wherein, different vehicle areas are divided according to different distances between the vehicle key and the vehicle, and the vehicle is pre-configured with in-vehicle functions associated with each vehicle area.

[0203] Control the vehicle to perform the target vehicle functions associated with the target vehicle region.

[0204] Each module in the aforementioned target object positioning device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0205] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 8 As shown, this computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data including, but not limited to, probe parameters. The I / O interfaces are used for exchanging information between the processor and external devices. The communication interface is used for communicating with external terminals via a network connection. When executed by the processor, the computer program implements a target object localization method.

[0206] Those skilled in the art will understand that Figure 8 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0207] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method described above.

[0208] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the method described above.

[0209] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the method described above.

[0210] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, data stored, data displayed, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data must comply with relevant regulations.

[0211] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0212] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0213] The above embodiments are merely illustrative of several implementation methods of this application, and their descriptions are relatively specific and detailed. However, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for locating a target object, characterized in that, The method includes: Acquire detection parameters of various parameter types obtained from detecting the target object using at least two detection anchor points; Each of the aforementioned detection parameters is input into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the aforementioned detection anchor points and corresponding to each of the aforementioned parameter types; The initial spatial coordinates are input into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object; Based on the target spatial coordinates, output the positioning result of the target object.

2. The target object localization method according to claim 1, characterized in that, The step of inputting each of the detection parameters into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object includes: Each of the aforementioned detection parameters is injected into the corresponding spatial coordinate constraint equation to obtain the updated spatial coordinate constraint equations. The updated spatial coordinate constraint equations are combined into an overdetermined system of equations. The objective solution of the overdetermined system of equations is determined to obtain the initial spatial coordinates.

3. The target object positioning method according to claim 2, characterized in that, The parameter types include orientation angle, pitch angle, and straight-line distance. Each of the spatial coordinate constraint equations has a corresponding weighting coefficient. The step of injecting each of the detection parameters into the corresponding spatial coordinate constraint equations to obtain updated spatial coordinate constraint equations includes: Obtain the real-time angle of arrival confidence parameter for each of the aforementioned detection anchor points; wherein, the angle of arrival confidence parameter is used to characterize the confidence of the detection parameters of the heading angle or the pitch angle; Based on the real-time arrival angle confidence parameters of each of the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to each of the aforementioned detection anchor points and corresponding to the azimuth angle or the pitch angle; Based on the real-time arrival angle confidence parameters of all the aforementioned detection anchor points, determine the value of the weighting coefficient corresponding to the straight-line distance; The values ​​of each of the weight coefficients are injected into the corresponding weight coefficients, and the values ​​of each of the detection parameters are injected into the corresponding spatial coordinate constraint equations to obtain the updated spatial coordinate constraint equations.

4. The target object positioning method according to claim 3, characterized in that, The step of determining the value of the weight coefficient corresponding to the straight-line distance based on the real-time arrival angle confidence parameters of all the probe anchor points includes: If the real-time arrival angle confidence parameter of all the aforementioned detection anchor points is less than or equal to the first threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the first value. If the real-time arrival angle confidence parameter of any of the aforementioned detection anchor points is less than or equal to the second threshold, the value of the weight coefficient corresponding to the straight-line distance will be increased from the initial value to the second value. Wherein, the first threshold is greater than the second threshold, and the first value is less than the second value.

5. The target object positioning method according to claim 3, characterized in that, The motion state model includes a state transition matrix, which is used to characterize the motion state changes of the target object. The step of inputting the initial spatial coordinates into the pre-constructed motion state model to obtain the target spatial coordinates includes: Obtain the historical spatial coordinates of the target object, and determine the predicted spatial coordinates of the target object based on the historical spatial coordinates and the state transition matrix; Determine the initial residual between the initial spatial coordinates and the predicted spatial coordinates; Obtain the arrival angle confidence parameters of each of the aforementioned probe anchor points in history, and perform weighted processing on the initial residuals based on the arrival angle confidence parameters of each of the aforementioned probe anchor points in history to obtain weighted residuals; The predicted spatial coordinates are updated based on the weighted residuals to obtain the target spatial coordinates.

6. The target object localization method according to any one of claims 1 to 5, characterized in that, The target object is a vehicle key, the detection anchor point is set on the vehicle, and the target object positioning method further includes: Based on the target spatial coordinates, the target vehicle area where the vehicle key is located is determined in several pre-divided vehicle areas; wherein, different vehicle areas are divided according to different distances between the vehicle key and the vehicle, and the vehicle is pre-configured with in-vehicle functions associated with each vehicle area. Control the vehicle to perform the target vehicle functions associated with the target vehicle region.

7. A method for locating a vehicle key, characterized in that, The vehicle key location method includes: Acquire detection parameters of various parameter types obtained from vehicle key detection at at least two detection anchor points; Each of the aforementioned detection parameters is input into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the vehicle key; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the aforementioned detection anchor points and corresponding to each of the aforementioned parameter types; The initial spatial coordinates are input into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the vehicle key; Based on the target spatial coordinates, the location result of the vehicle key is output.

8. A target object positioning device, characterized in that, The device includes: The detection parameter acquisition module is used to acquire detection parameters of various parameter types obtained from the detection of the target object by at least two detection anchor points; An initial spatial coordinate determination module is used to input each of the detection parameters into a pre-constructed spatial coordinate prediction model to obtain the initial spatial coordinates of the target object; the spatial coordinate prediction model includes spatial coordinate constraint equations corresponding to each of the detection anchor points and corresponding to each of the parameter types; The target spatial coordinate determination module is used to input the initial spatial coordinates into a pre-constructed motion state model to obtain the target spatial coordinates; wherein, the motion state model is used to model the motion state changes of the target object; The positioning result output module is used to output the positioning result of the target object based on the target spatial coordinates.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images