High-speed maneuvering target tracking method based on continuous space-time track function random process
Through the random process model based on continuous space-time track function and the adaptive hierarchical Gaussian process, the mean function of the target track is fitted, and the problem of insufficient prior knowledge dependence and data time-varying trend representation ability in high-speed maneuvering target tracking is solved. Achieve higher precision and stable target tracking effects.
Patent Information
- Application Number
- CN202411016528.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-28
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-07-28
AI Technical Summary
The existing target tracking methods rely on precise prior knowledge in high-speed maneuvering and the data time-varying trend representation ability of the Gaussian process tracking method leads to large tracking errors and loss of follow-up problems.
The random process model based on continuous space-time track function is adopted, and the mean function of the target track is fitted through a polynomial function, and state estimation is performed in combination with an adaptive stratified Gaussian process, and the target state is learned by using time sequence measurement data.
Real-time tracking of targets with higher accuracy is achieved in complex maneuvering scenarios, breaking through the insufficient covariance kernel characterization of constant mean function dependence, and improving tracking accuracy and stability.
Smart Images

Figure CN118963381A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of target tracking, and in particular to a high-speed maneuvering target tracking method based on a continuous space-time track function random process, which is suitable for a series of high-speed moving targets such as unmanned aerial vehicles. Background Art
[0002] In recent years, with the continuous development of modern computer and communication technology, high-precision data acquisition and real-time information transmission capabilities have become more convenient. Target tracking technology has indispensable application value and clear technical requirements. Researchers from all walks of life at home and abroad have been conducting extensive and in-depth research on it, and have proposed a large number of tracking theories and methods. However, the existing mainstream target tracking method models the dynamic state system as a hidden Markov model: when the target is maneuvering, the system needs to identify the changes in the dynamic system model in real time, otherwise the filter / tracker will diverge or even fail completely. In actual tracking tasks, high-value threat targets often take advantage of this and make it difficult for the early warning and surveillance system to form effective and accurate track estimates through high-speed, frequent and large maneuvers, greatly increasing the difficulty of positioning and tracking. The classic filter model-driven tracking method may deteriorate rapidly due to inaccurate prior knowledge and complex real system models. Therefore, model-driven filter tracking algorithms face more and more challenges in meeting practical applications and needs, and data-driven methods with learning as the main feature are gradually showing more and more advantages.
[0003] The paper "A Gaussian Process Regression Approach for Point Target Tracking" proposes a data-driven Gaussian Process Motion Tracker (GPMT), which proves that it can effectively achieve target tracking. This method models the target state as a function of time based on the Gaussian process (GP) prior, and continuously updates and learns the relevant parameters of the Gaussian process through time series measurement data, thereby achieving real-time estimation and prediction of the target state. However, the above work and its subsequent development are all based on the solution of the zero mean function of the Gaussian process, and only learn the unknown target dynamic model through the covariance kernel function. Although this is interpreted as "no prior information about the average behavior of the modeled function" (obviously, this does not mean that the mean function is constant or zero, but its form should be determined by learning from the data), this method does not have the ability to characterize the time-varying trend of data that should be learned through the mean function. Moreover, the parameters of the covariance kernel function used are often time-invariant, which actually assumes that the target motion trajectory is a stationary process, which does not conform to the vast majority of actual target tracking scenarios. In actual target tracking scenarios, the target track has a non-zero mean, and its fluctuations are often non-stationary, corresponding to a non-stationary random process. And if the mean function is fixed as a constant, the covariance learning and characterization capabilities are limited. When the target undergoes high-speed and large maneuvers, and the track shows a large change in mean trend, the adjustment of the covariance is difficult to fully characterize the randomness of the track, resulting in large tracking errors or even loss of tracking. In view of the above-mentioned Gaussian process modeling problem for high-speed maneuvering targets, how to model the mean function of the Gaussian process, and reasonably integrate possible additional system constraint information, and give full play to the Gaussian process's ability to characterize dynamic systems is the main starting point of the present invention. Summary of the invention
[0004] The technical problems to be solved by the present invention are:
[0005] In view of the problems that existing classical methods heavily rely on accurate prior knowledge of target motion and that Gaussian process tracking methods are insufficient in characterizing the time-varying trend of data, the present invention proposes a data-driven maneuvering target tracking method based on a continuous space-time trajectory function random process to solve the maneuvering target tracking problem in complex maneuvering scenarios.
[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:
[0007] A high-speed maneuvering target tracking method based on a continuous space-time track function random process, characterized by comprising:
[0008] The continuous space-time trajectory of a high-speed maneuvering target with an unknown motion model is modeled as a random process based on a continuous-time trajectory function.
[0009] The mean function of the target track random process is modeled as a continuous space-time track function;
[0010] Fit and estimate the continuous space-time trajectory function and output the target state.
[0011] A further technical solution of the present invention is to model the continuous space-time trajectory of a high-speed maneuvering target of an unknown motion model as a random process based on a continuous time trajectory function, specifically:
[0012] Based on the continuous-time trajectory function T-FoT, the continuous space-time trajectory f(t) of a high-speed maneuvering target with an unknown motion model is modeled as a random process specified by the parameter Θ Then any target track is a sample of the random process, that is, the continuous time-space domain track function f(t) satisfies:
[0013]
[0014] In the formula, Indicates time, x t represents the target state at time t, and m(t) is the mean function of the random process;
[0015] The target track random process is modeled by GP as:
[0016]
[0017] in, represents the GP random process, k(t, t′) represents the covariance kernel function with parameters.
[0018] A further technical solution of the present invention is as follows: the continuous space-time trajectory is to construct two motion model trajectory libraries of uniform linear motion CV and uniform circular motion CT by using a two-dimensional trajectory generation method based on a state space model and combine them to simulate the trajectory of a real maneuvering target.
[0019] A further technical solution of the present invention is to model the mean function of the target track random process as a continuous space-time track function, specifically:
[0020] The target track mean function m(t) is parameterized as F(t; C), which is determined by the parameter C:
[0021] F(t;C)=m(t)
[0022] By estimating the parameter C in real time, the target track mean function m(t) can be obtained; assuming that the estimated track mean function parameter at time k is C k ,but
[0023] F(t;C k )=c0+c1t+…+c γ t γ
[0024] Among them, C k ={c i} i=0,1,…,γ represents the polynomial track coefficient, γ represents the polynomial order, c0 corresponds to the initial position of the target, c1 corresponds to the velocity, and c2 corresponds to the acceleration.
[0025] A further technical solution of the present invention is to optimize and estimate the continuous space-time track function and output the target state, specifically:
[0026] Estimate the target mean function parameters and states
[0027] Establish sensor measurement model:
[0028] z t =h t (f(t))+v t In the formula, z t represents the measurement value of the target at time t, which is used to calculate and update the system state value; h(·) represents the measurement function; v t represents the observation noise at time t, which is assumed to be Gaussian noise;
[0029] Select the polynomial order to fit the target mean function of the corresponding time window, and estimate the coefficient parameter C based on the least squares method. k :
[0030]
[0031] In the formula, ||ab|| represents a certain distance between a and b, z t represents the observed data at time t. When t = k, z k =h(x k , v k ), h(x k , v k ) represents the measurement function, v k Represents the observation error; obtains the target mean function state estimate at the corresponding sampling moment by determining the mean function order and coefficient;
[0032] Use GP to compensate for the residual function of the mean function fitting and obtain the target state estimate at the current moment:
[0033]
[0034] in, It is the state estimate of the fitted residual function e(t) at the current moment.
[0035] A further technical solution of the present invention is to use the root mean square error RMSE as a comparison index and define the target position RMSE at time t as:
[0036]
[0037] In the formula, x t and t is the true state of the target, and is the state estimate of the output.
[0038] A computer system, characterized in that it comprises: one or more processors, and a computer-readable storage medium for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the above-mentioned method.
[0039] A computer-readable storage medium, characterized in that it stores computer-executable instructions, which are used to implement the above method when executed.
[0040] A computer program product, characterized by comprising computer executable instructions, wherein the instructions are used to implement the above method when executed.
[0041] The beneficial effects of the present invention are:
[0042] The present invention provides a high-speed maneuvering target tracking method based on a continuous space-time track function random process. Focusing on the high speed, large maneuver and other problems faced by high-speed maneuvering targets, the method analyzes the dynamic motion mechanism and the space-time change law of the track, and constructs a continuous space-time function track random process model based on a long-range time series angle rather than a single point state at each moment, that is, the mean function of the target track random process is modeled as a continuous space-time track function, which is learned and acquired through time series measurement data, and the accurate estimation of the maneuvering target state is further obtained with the help of an adaptive hierarchical Gaussian process.
[0043] The method of the present invention can achieve higher-precision real-time tracking of targets in complex maneuvering scenarios, and overcomes the shortcomings of existing random process target tracking methods that often add a constant mean function and rely solely on the covariance kernel function characterization for track estimation. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The drawings are only for the purpose of illustrating particular embodiments and are not to be considered limiting of the present invention. Like reference symbols denote like components throughout the drawings.
[0045] Figure 1 It is a flow chart of the method of the present invention.
[0046] Figure 2 It is the target simulation scenario of the method of the present invention.
[0047] Figure 3 It is the target tracking simulation result of the method of the present invention.
[0048] Figure 4 It is the simulation accuracy result of the method of the present invention. DETAILED DESCRIPTION
[0049] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.
[0050] The present invention provides a high-speed maneuvering target tracking method based on a continuous space-time track function random process. The polynomial T-FoT is used to construct a target track mean function, and a fitting residual function of the mean function is compensated by GP to obtain an accurate state estimation of the maneuvering target at the current moment by using pure measurement information.
[0051] like Figure 1 As shown, the present invention comprises the following steps:
[0052] Step 1: Establish the target continuous space-time trajectory function.
[0053] Based on the continuous time trajectory function (T-FoT), the continuous spatiotemporal trajectory f(t) of a high-speed maneuvering target with an unknown motion model is modeled as a random process specified by the parameter Θ. Then any target track is a sample of the random process, that is, the continuous time-space domain track function f(t) satisfies:
[0054]
[0055] In the formula, Indicates time, x t represents the target state at time t, and m(t) is the mean function of the random process.
[0056] The target track random process is modeled by GP as:
[0057]
[0058] in, represents a GP random process, k(t, t′) represents a process with parameters (variance ∑m and length scale ζ).
[0059] Step 2: Establish the objective function random process mean function.
[0060] A track model (i.e., polynomial T-FoT) which can approximate any continuous track curve in time and space domain with arbitrary accuracy is used to parameterize the target track mean function m(t) into F(t; C), which is determined by the parameter C.
[0061] F(t;C)=m(t) (3)
[0062] By estimating the parameter C in real time, the target track mean function m(t) can be obtained. Assume that the parameter of the track mean function estimated at time k is C k ,
[0063]
[0064] Among them, C k ={c i} i=0,1,…,γ represents the polynomial track coefficient, γ represents the polynomial order, c0 corresponds to the initial position of the target, c1 corresponds to the velocity, and c2 corresponds to the acceleration.
[0065] Step 3: Continuous space-time trajectory function parameter estimation and target state estimation.
[0066] In order to avoid the track function being too complicated due to a large time span, the estimation of track parameters is generally based on a time window of appropriate length, which is denoted as follows: k =[kd, k-d+1, ..., k-1] T , where d is the sliding window length. For formula (2), it is necessary to jointly identify the hyperparameters online in and k is the sliding window t corresponding to time k k The GP covariance kernel parameters in will be given in detail in equation (8). However, due to the difficulty of non-convex solution and the easy fall into local minimum, the above GP online fitting is transformed into hierarchical GP modeling of the residual function e(t) fitted by the mean function, and the joint learning of hyperparameters is decomposed into two stages to seek suboptimal solutions:
[0067]
[0068] where O represents a zero vector / matrix of appropriate dimension.
[0069] Step 3-1: Target mean function parameter estimation and state estimation.
[0070] The sensor measurement model is modeled as:
[0071] z t =h t (f(t))+v t (6)
[0072] In the formula, z t represents the measurement value of the target at time t, which is used to calculate and update the system state value; h(·) represents the measurement function; v t represents the observation noise at time t, which is assumed to be Gaussian noise.
[0073] Select the appropriate polynomial order to fit the target mean function of the corresponding time window, and estimate the coefficient parameter C based on the least squares fitting residual k :
[0074]
[0075] In the formula, ||ab|| represents a certain distance between a and b (when it is agreed to be the 2-norm or Mahalanobis distance, that is, least squares (LS) or weighted least squares), z t represents the observed data at time t. When t = k, z k =h(x k , v k ), h(x k , v k ) represents the measurement function, v k Represents the observation error. The target mean function state estimate at the corresponding sampling moment is obtained by determining the mean function order and coefficient.
[0076] Step 3-2: Use GP to compensate for the residual function of the mean function fitting, obtain the target state estimate at the current moment, and obtain the fitting uncertainty, thereby obtaining the GP closed solution of the random process of the target track function.
[0077] The present invention uses the squared exponential kernel (SE) for GP analysis, and the calculation formula is as follows:
[0078]
[0079] In the formula, the hyperparameter ∑ m and ζ denote the variance and length scale of the covariance kernel, respectively.
[0080] On the one hand, considering that the optimization model of hyperparameters is often non-convex, it is easy to fall into local minima. On the other hand, under the condition of lack of prior information, it is extremely difficult to identify unknown parameters or even time-varying synchronous parameters. Therefore, the present invention assumes that the hyperparameters are unknown and conducts online learning in the state space framework to reduce delay and improve identification accuracy.
[0081]
[0082] y k =A k x k-1 +v k (10)
[0083]
[0084] Among them, x k-1 represents the state vector; y k is an enhancement vector consisting of the state vector and the function prediction at the measurement position; θ k =[η k ,∑] T represents the hyperparameter vector, ∑ represents the observation noise v t The covariance of k represents the hyperparameter vector of the GP modeling covariance function; e k and They represent the sliding window corresponding to the k moment [kd, k-d+1,…, k+1] respectively. T And the function evaluation value at the current moment; A k is the state update matrix, is the mean gain matrix, K tt′ is the covariance matrix between the data at time t and t′, which is calculated by k(t, t′); v k is an additive Gaussian noise vector with independent and identically distributed (iid) elements, with the following parameters:
[0085]
[0086] in, represents the mean state estimate of the modeling residual function e(t) at time k, Represents the joint GP mean estimate of the modeling residual function e(t) in the sliding window corresponding to time k; represents the covariance gain.
[0087] Model the mean state of GP at time t = k As the mean function fitting error compensation, the target track function at time t = k is expressed as follows:
[0088]
[0089] in, represents the gain matrix; and They represent the predicted covariance and mean of e(t) at time k, respectively. It represents the joint GP estimated covariance of the modeling residual function e(t) in the sliding window corresponding to the k-1 moment; and Denote prediction and estimate, respectively.
[0090] The estimated covariance of the GP model at time k is taken as the covariance of the fitting error of the time series track random process, which is expressed as follows:
[0091]
[0092] In order to enable those skilled in the art to better understand the present invention, the present invention is described in detail below in conjunction with specific embodiments.
[0093] 1. Set up the simulation scene.
[0094] The simulation scenario uses a two-dimensional trajectory generation method based on the state space model to construct two motion model trajectory libraries of constant velocity (CV) and constant circular motion (CT) and combine them to simulate the trajectory of a real maneuvering target. The state of the target at time step k is included in the two-dimensional Cartesian coordinate system x k and k The position in the coordinate system, and the speed towards these coordinate axes and Therefore, the state vector can be expressed as:
[0095]
[0096] Among them, the dynamic modeling of CV is:
[0097]
[0098] Among them, q k-1 is a Gaussian process noise with zero mean
[0099]
[0100] Wherein, q is the spectral density of noise, which is set to q=0.1 in the simulation.
[0101] In the dynamic modeling of CT, the turning rate parameter ω is used to enhance the state vector, so the joint system vector is expressed as:
[0102]
[0103] in, is the univariate Gaussian white process noise of the turning rate parameter, and set ∑ ω =0.1.
[0104] The observation equations of CV and CT are:
[0105]
[0106] in, To observe the noise, set ∑ = 0.1.
[0107] The system is simulated for 200 time steps with a step size of Δt = 0.1. The motion process of the target is as follows:
[0108] Target speed Start from the origin.
[0109] After 4 seconds, the target starts to turn left at a rate of ω = 1.
[0110] After 9 seconds, the target stops turning and moves straight ahead at a constant speed for 2 seconds.
[0111] After 11 seconds, the target starts to turn right at a rate of ω = -1.
[0112] After 16 seconds, the target stops turning and moves straight at the same speed for 4 seconds.
[0113] The sensor generating the position measurement value is located at (s x ,s y )=(-0.5, 3.5). The specific target trajectory and the measurement data obtained by the sensor are as follows Figure 2 shown.
[0114] 2. Fit the target mean function based on the polynomial T-FoT method.
[0115] The sliding window size d=5 is set, and the polynomial T-FoT method (fitting order is second order) is applied to estimate the target mean function parameters, and the estimated value of the mean function at the current moment is obtained.
[0116] 3. Use GP to compensate for the fitting residual function of the mean function, obtain the target state estimate at the current moment, and obtain the fitting uncertainty.
[0117] 3-1: GP modeling initialization.
[0118] Use the measured data in the initial sliding window to initialize the GP model. Use the first d measurement samples to establish the initial sliding window, and use GP regression to fit the target track function in the initial sliding window, that is, to obtain the mean and covariance of the joint Gaussian to which the target track belongs in the first sliding window, which is in the form of:
[0119]
[0120] Where p(·) is the probability density function; The mean is μ and the covariance is Gaussian distribution of and They represent the GP mean and covariance of the measurement data set in the initial sliding window, respectively, and are specifically expressed as follows:
[0121]
[0122] Determine the initial distribution of the hyperparameter vector, which is of the form:
[0123]
[0124] in, and denote the GP mean and covariance of the initial hyperparameter vector respectively.
[0125] 3-2: Target state estimation.
[0126] First, according to formula (5), the GP modeling mean estimate and covariance estimate of the mean function fitting residual function e(t) at time t = k are obtained. The GP mean estimate is used as the state estimate of the fitting residual function e(t) at the current time. Then, the target state estimate at the current moment is obtained according to formula (13).
[0127]
[0128] 3-3: Calculate tracking uncertainty and measure tracking accuracy.
[0129] The GP covariance estimate is used as the covariance estimate of the fitted residual function e(t) at the current moment. Since the covariance term is not included in the mean function fitting process, the target tracking uncertainty can be obtained according to formula (14), thereby obtaining the GP closed solution of the target track function random process.
[0130] 4. Comparison of performance indicators.
[0131] In order to demonstrate the superiority of the method proposed in the present invention, the comparison methods are selected as the existing target tracking methods, including polynomial time trajectory function fitting (fitting order is second order) and target tracking method based on zero mean Gaussian process modeling (GPMT). The root mean square error (RMSE) is used as the comparison index, and the RMSE of the target position at time t is defined as:
[0132]
[0133] In the formula, x t and t is the true state of the target, and is the state estimate of the output.
[0134] Table 1 Average performance of different tracking methods
[0135]
[0136] like Figure 4 As shown in the figure, the simulation of the position error of maneuvering target tracking of this method and other methods shows that this method has achieved significantly better results when tracking large maneuvering targets with high turning rates, and the error at the point where the target has large maneuvers is significantly smaller than that of other methods. Especially after considering the mean function, compared with the existing GPMT method based on zero-mean GP, in addition to higher tracking accuracy, the tracking stability has also been significantly improved. The experimental results prove the effectiveness of the present invention in maneuvering target tracking.
[0137] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should be included in the protection scope of the present invention.
Claims
1. A high-speed maneuvering target tracking method based on a continuous space-time track function random process, characterized in that: include: The continuous space-time trajectory of a high-speed maneuvering target with an unknown motion model is modeled as a random process based on a continuous-time trajectory function. The mean function of the target track random process is modeled as a continuous space-time track function; Fit and estimate the continuous space-time trajectory function and output the target state.
2. According to claim 1, a high-speed maneuvering target tracking method based on a continuous space-time track function random process is characterized in that: Based on the continuous time trajectory function, the continuous space-time trajectory of a high-speed maneuvering target with an unknown motion model is modeled as a random process, specifically: Based on the continuous-time trajectory function T-FoT, the continuous space-time trajectory f(t) of a high-speed maneuvering target with an unknown motion model is modeled as a random process specified by the parameter Θ Then any target track is a sample of the random process, that is, the continuous time-space domain track function f(t) satisfies: In the formula, Indicates time, x t represents the target state at time t, and m(t) is the mean function of the random process; The target track random process is modeled by GP as: in, represents the GP random process, κ(t, t′) represents the covariance kernel function with parameters.
3. According to claim 2, a high-speed maneuvering target tracking method based on a continuous space-time track function random process is characterized in that: The continuous space-time trajectory adopts a two-dimensional trajectory generation method based on a state space model to construct two motion model trajectory libraries of uniform linear motion CV and uniform circular motion CT and combine them to simulate the real maneuvering target trajectory.
4. According to claim 2, a high-speed maneuvering target tracking method based on a continuous space-time track function random process is characterized in that: The mean function of the target track random process is modeled as a continuous space-time track function, specifically: The target track mean function m(t) is parameterized as F(t; C), which is determined by the parameter C: F(t;C)=m(t) By estimating the parameter C in real time, the target track mean function m(t) can be obtained; assuming that the estimated track mean function parameter at time k is C k ,but F(t;C k )=c0+c1t+…+c γ t γ Among them, C k ={c i } i=0,1,…,γ represents the polynomial track coefficient, γ represents the polynomial order, c0 corresponds to the initial position of the target, c1 corresponds to the velocity, and c2 corresponds to the acceleration.
5. According to claim 4, a high-speed maneuvering target tracking method based on a continuous space-time track function random process is characterized in that: The continuous space-time trajectory function is optimized and estimated, and the target state is output, specifically: Estimate the target mean function parameters and states Establish sensor measurement model: z t =h t (f(t))+v t In the formula, z t represents the measurement value of the target at time t, which is used to calculate and update the system state value; h(·) represents the measurement function; v t represents the observation noise at time t, which is assumed to be Gaussian noise; Select the polynomial order to fit the target mean function of the corresponding time window, and estimate the coefficient parameter C based on the least squares method. k : In the formula, ||ab|| represents a certain distance between a and b, z t represents the observed data at time t. When t = k, z k =h(x k , v k ), h(x k , v k ) represents the measurement function, v k Represents the observation error; obtains the target mean function state estimate at the corresponding sampling moment by determining the mean function order and coefficient; Use GP to compensate for the residual function of the mean function fitting and obtain the target state estimate at the current moment: in, It is the state estimate of the fitted residual function e(t) at the current moment.
6. A performance comparison method for high-speed maneuvering target tracking methods based on a continuous space-time track function random process, characterized in that: Taking the root mean square error RMSE as the comparison index, the target position RMSE at time t is defined as: In the formula, x t and t is the true state of the target, and is the state estimate of the output.
7. A computer system, characterized in that include: One or more processors, a computer-readable storage medium, for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method described in any one of claims 1 or 6.
8. A computer-readable storage medium, characterized in that Computer executable instructions are stored, and when the instructions are executed, they are used to implement the method according to any one of claims 1 or 6.
9. A computer program product, characterized in that The method comprises computer executable instructions, which are used to implement the method according to any one of claims 1 or 6 when being executed.
Citation Information
Patent Citations
Heterogeneous sensor information fusion and multi-target tracking method based on random finite set
CN114089363A
High-speed maneuvering target tracking error compensation method based on time sequence intelligent smoothing
CN116993778A
Probability hypothesis density filtering multi-maneuvering target tracking method based on Gaussian process
CN117197491A
Tracking method for a radar system
US6243037B1
Method for performing tracking-before-detecting on multiple weak targets by high-resolution sensor
WO2022116375A1
