Evaluation Method, Device and Electronic Device for Track Confidence

Abstract

The present invention provides a method, apparatus and electronic device for evaluating the track confidence. The method includes: obtaining the measurement information of each of a preset number of radar frames of a target track; calculating the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability and longitudinal velocity correction likelihood probability of the target track according to the measurement information of each of the preset number of radar frames; calculating the track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability and longitudinal velocity correction likelihood probability of the target track; and evaluating the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and target recognition probability confidence feature of the target track obtained in advance. The present invention can improve the evaluation accuracy of the track confidence.

Description

Technical Field

[0001] The present invention relates to the technical field of radar measurement and control, and particularly to a method, device and electronic device for evaluating track confidence. Background Art

[0002] In the field of radar detection, a track generally refers to the movement trajectory of moving targets such as vehicles, ships, and aircraft. Currently, the target detection and tracking ability of a radar can be evaluated by an index of track quality.

[0003] Track confidence is an important factor in evaluating track quality. The higher the track confidence, the better the track quality. Due to various factors such as the movement speed, smoothness, continuity, and recognizability of the target, the evaluation of track confidence will be affected. Therefore, how to evaluate track quality faces great challenges. Thus, there is an urgent need for a method that can accurately evaluate track confidence. Summary of the Invention

[0004] Embodiments of the present invention provide a method, device and electronic device for evaluating track confidence to solve the problem that the evaluation of track confidence in the prior art is not accurate enough.

[0005] In a first aspect, embodiments of the present invention provide a method for evaluating track confidence, including:

[0006] Obtaining measurement information of each of a preset number of radar frames of a target track; wherein the measurement information includes a lateral position measurement value, a longitudinal position measurement value, a lateral speed measurement value, and a longitudinal speed measurement value;

[0007] Calculating a lateral position correction likelihood probability, a longitudinal position correction likelihood probability, a lateral speed correction likelihood probability, and a longitudinal speed correction likelihood probability of the target track according to the measurement information of each of the preset number of radar frames;

[0008] Calculating a track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track;

[0009] Evaluating the track confidence of the target track according to the track accuracy confidence feature of the target track, and a track continuous tracking rate confidence feature and a target recognition probability confidence feature of the target track obtained in advance.

[0010] In a second aspect, embodiments of the present invention provide an apparatus for evaluating track confidence, including:

[0011] A measurement acquisition module, configured to acquire measurement information of each of a preset number of radar frames of a target track; wherein, the measurement information includes a lateral position measurement value, a longitudinal position measurement value, a lateral speed measurement value, and a longitudinal speed measurement value;

[0012] A first calculation module, configured to calculate a lateral position correction likelihood probability, a longitudinal position correction likelihood probability, a lateral speed correction likelihood probability, and a longitudinal speed correction likelihood probability of the target track according to the measurement information of each of the preset number of radar frames;

[0013] A second calculation module, configured to calculate a track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track;

[0014] A confidence evaluation module, configured to evaluate the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and the target recognition probability confidence feature of the target track obtained in advance.

[0015] In a third aspect, an embodiment of the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described in the first aspect or any possible implementation manner of the first aspect above are implemented.

[0016] An embodiment of the present invention provides a method, device, and electronic device for evaluating track confidence, provides a feature that can more comprehensively and accurately evaluate track confidence, that is, a track accuracy confidence feature, and provides a specific calculation method for the track accuracy confidence feature. On this basis, the track accuracy confidence feature is fused with the track continuous tracking rate confidence feature and the target recognition probability confidence feature, which are two evaluation features of track confidence, to provide a method for evaluating track confidence. Through the foregoing processing, the evaluation accuracy of track confidence can be improved. In addition, it also has the advantages of fast convergence speed and timely response to target changes. Description of the Drawings

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is a flowchart of the implementation of the method for evaluating track confidence provided by an embodiment of the present invention;

[0019] Figure 2 It is a schematic structural diagram of an evaluation device for track confidence provided by an embodiment of the present invention;

[0020] Figure 3 It is a schematic diagram of an electronic device provided by an embodiment of the present invention. Specific Embodiments

[0021] In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0022] To make the objectives, technical solutions, and advantages of the present invention clearer, the following will be described through specific embodiments in conjunction with the accompanying drawings.

[0023] As described in the related art, track confidence is an important factor in evaluating track quality. The higher the track confidence, the better the track quality. The existing evaluation of track confidence generally has the problem of insufficient accuracy. Therefore, there is an urgent need for a method that can accurately evaluate track confidence.

[0024] To solve the problems of the prior art, embodiments of the present invention provide a method, device, and electronic device for evaluating track confidence. First, the method for evaluating track confidence provided by the embodiments of the present invention will be introduced below.

[0025] The execution subject of the method for evaluating track confidence can be an evaluation device for track confidence. This device can be an electronic device with data processing capabilities, such as a microwave radar, vehicle-mounted radar, traffic radar, security radar, etc. The embodiments of the present invention do not make specific limitations.

[0026] See Figure 1 , which shows a flowchart of the implementation of a method for evaluating track confidence provided by an embodiment of the present invention, and is described in detail as follows:

[0027] Step 110, obtain the measurement information of each of a preset number of radar frames of the target track.

[0028] In some embodiments, a track refers to a possible motion trajectory of a target extracted from a series of echoes detected by a radar. Therefore, during the tracking of a target, multiple tracks may exist for a single target, and as the tracking continues, the tracks are continuously updated. Tracks with high track quality are retained, while those with low track quality are deleted. Track confidence can be used to evaluate the track quality of a certain track. The higher the track confidence, the higher the track quality. For ease of description, hereinafter, a target track is used to refer to any one of the multiple tracks of a target.

[0029] In some embodiments, data processing may be performed on a radar frame to obtain measurement information of a target. Specifically, the measurement information may include a lateral position measurement value, a longitudinal position measurement value, a lateral velocity measurement value, and a longitudinal velocity measurement value of the target.

[0030] Optionally, measurement information may be obtained through the Doppler information of a radar frame. Correspondingly, the specific processing of step 110 may be as follows: obtain the lateral position measurement value and the longitudinal position measurement value of a target radar frame according to the Doppler information of the target radar frame, where the target radar frame is any one of a preset number of radar frames of a target track; obtain the lateral velocity measurement value and the longitudinal velocity measurement value of the target radar frame according to the lateral position measurement value and the longitudinal position measurement value of at least one radar frame located before the target radar frame that are obtained in advance.

[0031] In some embodiments, the position measurement values of a target, that is, the lateral position measurement value and the longitudinal position measurement value, can be directly obtained by using Doppler information, and the corresponding obtaining method may be a general method in the radar field. However, there is currently no unified method for obtaining the velocity measurement values of a target, that is, the lateral velocity measurement value and the longitudinal velocity measurement value, and the accuracies of different obtaining methods are also different. Here, a method for obtaining the lateral velocity measurement value and the longitudinal velocity measurement value with relatively high accuracy is provided.

[0032] Specifically, various data processing may be performed on the position measurement values of at least one radar frame located before the target radar frame to obtain multiple sets of velocity measurement values, and then different weights may be used to perform weighted calculation on these multiple sets of velocity measurement values, so as to obtain the final velocity measurement value.

[0033] First, perform a least-squares fitting process with respect to time on the lateral position measurement values of the above at least one radar frame to obtain the first lateral velocity measurement value of the target radar frame, and perform a least-squares fitting process with respect to time on the longitudinal position measurement values of at least one radar frame to obtain the first longitudinal velocity measurement value. Taking five radar frames as an example, the time information corresponding to these five radar frames is T = [t1, t2, t3, t4, t5], the respective lateral position measurement values are X = [x1, x2, x3, x4, x5], and the longitudinal position measurement values are Y = [y1, y2, y3, y4, y5]. Then, performing a least-squares fitting on X with respect to time T can obtain the first lateral velocity measurement value Performing a least-squares fitting on Y with respect to time T can obtain the first longitudinal velocity measurement value

[0034] Next, perform a difference process with respect to time on the lateral position measurement value of the radar frame immediately preceding the target radar frame and the lateral position measurement value of the target radar frame to obtain the second lateral velocity measurement value of the target radar frame, and perform a difference process with respect to time on the longitudinal position measurement value of the radar frame immediately preceding the target radar frame and the longitudinal position measurement value of the target radar frame to obtain the second longitudinal velocity measurement value of the target radar frame. For example, the calculation formula for the second lateral velocity measurement value of the target radar frame is The second longitudinal velocity measurement value The calculation formula for it is where, x 目标帧 is the lateral position measurement value of the target radar frame, x 前一帧 is the lateral position measurement value of the radar frame immediately preceding the target radar frame, y 目标帧 is the longitudinal position measurement value of the target radar frame, y 前一帧 is the longitudinal position measurement value of the radar frame immediately preceding the target radar frame, t 目标帧 is the time of the target radar frame, t 前一帧 is the time of the radar frame immediately preceding the target radar frame.

[0035] Then, perform a Kalman estimation process on the lateral position measurement value of the radar frame immediately preceding the target radar frame to obtain the third lateral velocity measurement value of the target radar frame Perform a Kalman estimation process on the longitudinal position measurement value of the radar frame immediately preceding the target radar frame to obtain the third longitudinal velocity measurement value of the target radar frame

[0036] Finally, according to the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value, perform weighted calculations on the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value to obtain the lateral velocity measurement value of the target radar frame; according to the respective weight values of the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value, perform weighted calculations on the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value to obtain the longitudinal velocity measurement value of the target radar frame.

[0037] In some embodiments, the following acquisition method can be used, that is, decompose the above three groups of transverse and longitudinal velocities into the direction of the line connecting the target and the radar, and then compare and normalize them with the Doppler information of the target frame to obtain the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, the third lateral velocity measurement value, the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value, as follows:

[0038]

[0039]

[0040]

[0041] Among them, α is the azimuth angle at which the radar is installed. is the i-th lateral velocity measurement value. is the i-th longitudinal velocity measurement value, doppler is the measured Doppler information of the target radar frame, and η i ′ is the reference weight value of the i-th lateral velocity measurement value and the i-th longitudinal velocity measurement value, and η i is the weight value of the i-th lateral velocity measurement value and the i-th longitudinal velocity measurement value.

[0042] It should be noted that doppler i is the decomposition value of the i-th lateral velocity measurement value and the i-th longitudinal velocity measurement value in the direction of the line connecting the target and the radar. For example, doppler1 is the decomposition value of the first lateral velocity measurement value and the first longitudinal velocity measurement value in the direction of the line connecting the target and the radar, doppler2 is the decomposition value of the second lateral velocity measurement value and the second longitudinal velocity measurement value in the direction of the line connecting the target and the radar, and doppler3 is the decomposition value of the third lateral velocity measurement value and the third longitudinal velocity measurement value in the direction of the line connecting the target and the radar. For η i ′, here |doppler - doppler i | is used to evaluate doppler and doppler iThe similarity of these two variables, and in order to prevent the numerical values from being too large or too small, |doppler - doppler i | can be divided by the sum of the absolute values of the two variables, that is It is easy to understand that the closer the two variables doppler and doppler i are, the smaller it is, and the greater the corresponding weight should be. In this regard, the reciprocal can be taken to make the reciprocal of, that is as the reference weight value of the corresponding variable.

[0043] In this way, based on the above weight values, the measured value of the lateral velocity of the target radar frame finally obtained by weighted calculation is The measured value of the longitudinal velocity is

[0044] Step 120: Calculate the likelihood probability of lateral position correction, the likelihood probability of longitudinal position correction, the likelihood probability of lateral velocity correction, and the likelihood probability of longitudinal velocity correction for the target track according to the measurement information of each of the preset number of radar frames.

[0045] In some embodiments, the likelihood probability can reflect the degree of closeness between the estimated quantity and the average value or the true value. The closer the estimated quantity is to the average value or the true value, the greater the likelihood probability. Considering that the likelihood probability is not a value between 0 and 1, normalization is used for correction this time to obtain the corrected likelihood probability.

[0046] Specifically, in Kalman filtering, it is generally assumed that the random variable x to be estimated follows a normal distribution with a mean of and a variance of , that is According to formula derivation, it can be obtained that follows the standard normal distribution N(0, 1), that is:

[0047]

[0048] Obviously, In order to make the likelihood probability value between 0 and 1, both sides of the above formula can be multiplied by for normalization, and thus the corrected likelihood probability function is obtained as:

[0049]

[0050] It should be noted that if the corrected likelihood probability value is larger, it means the higher the confidence level.

[0051] In this way, the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability of the target track can be obtained, which are respectively:

[0052]

[0053]

[0054]

[0055]

[0056] Among them, the capital P is the state covariance matrix of the Kalman filter, P 11 is the element in the first row and first column of the P matrix, and so on, P 44 is the element in the fourth row and fourth column of the P matrix. p1 is the lateral position correction likelihood probability, p2 is the longitudinal position correction likelihood probability, p3 is the lateral velocity correction likelihood probability, p4 is the longitudinal velocity correction likelihood probability, x is the lateral position variable, and σ x is the standard deviation of the lateral position measurement values of a preset number of radar frames, is the average value of the lateral position measurement values of a preset number of radar frames, y is the longitudinal position variable, and σ y is the standard deviation of the longitudinal position measurement values of a preset number of radar frames, is the average value of the longitudinal position measurement values of a preset number of radar frames, V x is the lateral velocity variable, and σ Vx is the standard deviation of the lateral velocity measurement values of a preset number of radar frames, is the average value of the lateral velocity measurement values of a preset number of radar frames, V y is the longitudinal velocity variable, and σ Vy is the standard deviation of the longitudinal velocity measurement values of a preset number of radar frames, is the average value of the longitudinal velocity measurement values of a preset number of radar frames.

[0057] Step 130: Calculate the track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability of the target track.

[0058] In some embodiments, after obtaining the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability of the target track, the track accuracy confidence feature can be further obtained. Track accuracy is an important dimension for evaluating track confidence, and the present invention summarizes it as the track accuracy confidence feature.

[0059] In some embodiments, the weight values of the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability of the target track can be utilized to perform weighted calculation on the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability of the target track, so as to obtain the track accuracy confidence feature of the target track.

[0060] Specifically, for the track accuracy confidence feature confidence1, its calculation method is as follows:

[0061]

[0062] where ω1 - ω4 are respectively the weight values of the lateral position correction likelihood probability, longitudinal position correction likelihood probability, lateral velocity correction likelihood probability, and longitudinal velocity correction likelihood probability.

[0063] It should be noted that for the track accuracy, the impacts of four variables including the lateral and longitudinal positions and the lateral and longitudinal velocities on the track accuracy are comprehensively considered. Since the lateral position and lateral velocity determine the smoothness of the track to a certain extent, relatively higher weights can be assigned to the lateral position and lateral velocity. Specifically, the weight values can be assigned in the following manner: the weight values of the lateral position correction likelihood probability and the lateral velocity correction likelihood probability are the same, the weight values of the longitudinal position correction likelihood probability and the longitudinal velocity correction likelihood probability are the same, and the weight value of the lateral position correction likelihood probability is greater than the weight value of the longitudinal position correction likelihood probability. For example, ω1 = 0.5 and ω3 = 0.3.

[0064] Step 140: Evaluate the track confidence of the target track according to the track accuracy confidence feature of the target track, as well as the track continuous tracking rate confidence feature and target recognition probability confidence feature of the target track obtained in advance.

[0065] In some embodiments, the track continuous tracking rate confidence feature can be used to evaluate the probability that the target is continuously detected, and it can be obtained through variables such as the number of target lost frames, the number of target detections, the target life cycle, and the target detection number threshold.

[0066] Specifically, for the number of target lost frames lostNum, if the track is not associated currently, the number of lost frames increases, and if the association is successful, the number of lost frames is set to 0. For the number of target detections detectNum, it represents the number of times the track successfully associates with measurements. For the target life cycle lifeTime, it represents the frame count from the start of establishing the track to the final end of the track. The target detection number threshold is represented by thr. Thus, for the track continuous tracking rate confidence feature confidence2, its calculation method is as follows:

[0067]

[0068] For the target recognition probability confidence feature, it can be obtained through the target recognition module. Specifically, the target recognition module can output the recognition probability P that the target belongs to the current category through a neural network model. If the recognition probability is closer to 1, the target confidence is greater. Thus, for the target recognition probability confidence feature confidence3, its calculation method can be as follows:

[0069] where P1 is the recognition probability threshold. For example, P1 can be taken as 0.98.

[0070] Optionally, the track confidence of the target track can be evaluated by the Analytic Hierarchy Process (AHP). Accordingly, the specific processing of step S140 can be as follows: Using the AHP, obtain the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature; According to the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature, perform weighted calculation on the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature to obtain the track confidence of the target track.

[0071] The Analytic Hierarchy Process (AHP) is an analysis method that combines qualitative and quantitative methods and has the characteristics of systematic hierarchy. The AHP can decompose a problem into different constituent factors according to the nature of the problem and the overall goal to be achieved, and cluster and combine the factors into different levels according to the mutual correlation and influence and subordination relationship between the factors, forming a multi-level analysis structure model, so that the problem is finally reduced to the determination of the relative importance weights or the ranking of the relative advantages and disadvantages of the lowest level (the options, measures, etc. for decision-making) relative to the highest level (the overall goal).

[0072] The following gives a specific implementation method for obtaining the track confidence of the target track by using the AHP.

[0073] First, construct the judgment matrix of the AHP. In this embodiment, A1 - A3 are respectively used to represent the track continuous tracking rate confidence feature, the target recognition probability confidence feature, and the track accuracy confidence feature. It is specified that the track accuracy confidence feature A3 is strongly more important than the track continuous tracking rate confidence feature A1, the track accuracy confidence feature A3 is slightly more important than the target recognition probability confidence feature A2, and the target recognition probability confidence feature A2 is significantly more important than the track continuous tracking rate confidence feature A1. Then, according to the 1 - 9 scaling method shown in Table 1, the judgment matrix A is obtained.

[0074] Table 1

[0075] Scale Factor i is more important than Factor j 1 Equally important 3 Slightly more important 5 Obviously more important 7 Strongly more important 9 Extremely more important 2,4,6,8 The median value of adjacent judgments Reciprocal <![CDATA[Comparison a of feature i and j ij , comparison a of feature j and i ji = 1 / a ij >

[0076] Thus, the judgment matrix A can be:

[0077]

[0078] After that, consistency check is carried out. Considering that the processing of solving the eigenvalues of the judgment matrix is very complex and complex numbers may occur, for the sake of simplification, the following simplified calculation idea can be adopted: Any column vector of the judgment matrix is an eigenvector, and the column vectors of a positive reciprocal matrix with good consistency should all be approximate eigenvectors, and the average in a certain sense can be taken.

[0079] Thus, through the normalization processing of the column vectors, the following can be obtained:

[0080]

[0081] After calculating the row sum and normalizing, the following can be obtained:

[0082]

[0083] Finally, let the eigenvector be After weighted summation processing, the following confidence level solving formula can be obtained:

[0084] confidence = λ1·confidence2 + λ2·confidence3 + λ3·confidence1

[0085] In this way, substituting the obtained confidence level features into the above formula, the track confidence level of the target track can be obtained.

[0086] It is worth mentioning that the above track confidence level evaluation method provided by the present invention not only has higher accuracy compared with the existing evaluation methods, but also has the advantages of fast convergence speed and timely response to target changes.

[0087] In the embodiment of the present invention, first, a feature capable of more comprehensively and accurately evaluating the track confidence level is provided, that is, the track accuracy confidence level feature, and the specific calculation method of the track accuracy confidence level feature is given. On this basis, the track accuracy confidence level feature is fused with the two track confidence level evaluation features of the track continuous tracking rate confidence level feature and the target recognition probability confidence level feature, and an evaluation method of the track confidence level is given. Through the above processing, the evaluation accuracy of the track confidence level can be improved. In addition, it also has the advantages of fast convergence speed and timely response to target changes.

[0088] It should be understood that the sequence numbers of the steps in the above embodiments do not indicate the order of execution. The order of execution of each process should be determined according to its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0089] The following is an apparatus embodiment of the present invention. For details not described in detail, reference may be made to the corresponding method embodiments above.

[0090] Figure 2 The structural schematic diagram of the apparatus for evaluating the track confidence provided by the embodiments of the present invention is shown. For the sake of convenience of description, only the parts related to the embodiments of the present invention are shown and are described in detail as follows:

[0091] As Figure 2 shown, the apparatus for evaluating the track confidence includes:

[0092] A measurement acquisition module 210, configured to acquire measurement information of each of a preset number of radar frames of a target track; wherein, the measurement information includes a lateral position measurement value, a longitudinal position measurement value, a lateral speed measurement value, and a longitudinal speed measurement value;

[0093] A first calculation module 220, configured to calculate a lateral position correction likelihood probability, a longitudinal position correction likelihood probability, a lateral speed correction likelihood probability, and a longitudinal speed correction likelihood probability of the target track according to the measurement information of each of the preset number of radar frames;

[0094] A second calculation module 230, configured to calculate a track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track;

[0095] A confidence evaluation module 240, configured to evaluate the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and the target recognition probability confidence feature of the target track obtained in advance.

[0096] In a possible implementation manner, the measurement acquisition module is further configured to:

[0097] acquire a lateral position measurement value and a longitudinal position measurement value of the target radar frame according to the Doppler information of the target radar frame; wherein, the target radar frame is any one of the preset number of radar frames of the target track;

[0098] acquire a lateral speed measurement value and a longitudinal speed measurement value of the target radar frame according to the lateral position measurement values and longitudinal position measurement values of at least one radar frame before the target radar frame acquired in advance.

[0099] In a possible implementation manner, the measurement acquisition module is further configured to:

[0100] Perform a least-squares fitting process with respect to time on the lateral position measurement values of at least one radar frame to obtain the first lateral velocity measurement value of the target radar frame; perform a least-squares fitting process with respect to time on the longitudinal position measurement values of at least one radar frame to obtain the first longitudinal velocity measurement value;

[0101] Perform a difference process with respect to time on the lateral position measurement value of the previous radar frame of the target radar frame and the lateral position measurement value of the target radar frame to obtain the second lateral velocity measurement value of the target radar frame; perform a difference process with respect to time on the longitudinal position measurement value of the previous radar frame of the target radar frame and the longitudinal position measurement value of the target radar frame to obtain the second longitudinal velocity measurement value of the target radar frame;

[0102] Perform a Kalman estimation process on the lateral position measurement value of the previous radar frame of the target radar frame to obtain the third lateral velocity measurement value of the target radar frame; perform a Kalman estimation process on the longitudinal position measurement value of the previous radar frame of the target radar frame to obtain the third longitudinal velocity measurement value of the target radar frame;

[0103] According to the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value, perform a weighted calculation on the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value to obtain the lateral velocity measurement value of the target radar frame; according to the respective weight values of the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value, perform a weighted calculation on the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value to obtain the longitudinal velocity measurement value of the target radar frame.

[0104] In a possible implementation manner, the obtaining methods of the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, the third lateral velocity measurement value, the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value include:

[0105]

[0106]

[0107]

[0108] where α is the azimuth angle at which the radar is installed, is the i-th lateral velocity measurement value, is the i-th longitudinal velocity measurement value, doppler is the measured Doppler information of the target radar frame, η i is the weight value of the i-th lateral velocity measurement value and the i-th longitudinal velocity measurement value.

[0109] In a possible implementation, the first calculation module is further configured to:

[0110]

[0111]

[0112]

[0113]

[0114] where p1 is the likelihood probability of lateral position correction, p2 is the likelihood probability of longitudinal position correction, p3 is the likelihood probability of lateral speed correction, p4 is the likelihood probability of longitudinal speed correction, x is the lateral position variable, and σ x is the standard deviation of the lateral position measurements of a preset number of radar frames, is the average value of the lateral position measurements of a preset number of radar frames, P is the state covariance matrix of the Kalman filter, and P 11 P 22 P 33 and P 44 are the element values in the state covariance matrix, y is the longitudinal position variable, and σ y is the standard deviation of the longitudinal position measurements of a preset number of radar frames, is the average value of the longitudinal position measurements of a preset number of radar frames, V x is the lateral speed variable, and σ Vx is the standard deviation of the lateral speed measurements of a preset number of radar frames, is the average value of the lateral speed measurements of a preset number of radar frames, V y is the longitudinal speed variable, and σ Vx is the standard deviation of the longitudinal speed measurements of a preset number of radar frames, is the average value of the longitudinal speed measurements of a preset number of radar frames.

[0115] In a possible implementation, the second calculation module is further configured to:

[0116] According to the respective weight values of the likelihood probability of lateral position correction, the likelihood probability of longitudinal position correction, the likelihood probability of lateral speed correction, and the likelihood probability of longitudinal speed correction of the target track, perform a weighted calculation on the likelihood probability of lateral position correction, the likelihood probability of longitudinal position correction, the likelihood probability of lateral speed correction, and the likelihood probability of longitudinal speed correction of the target track to obtain the track accuracy confidence feature of the target track.

[0117] In a possible implementation, the weight values of the lateral position correction likelihood probability and the lateral velocity correction likelihood probability are the same, the weight values of the longitudinal position correction likelihood probability and the longitudinal velocity correction likelihood probability are the same, and the weight value of the lateral position correction likelihood probability is greater than the weight value of the longitudinal position correction likelihood probability.

[0118] In a possible implementation, the confidence evaluation module is further configured to:

[0119] Use the analytic hierarchy process to obtain the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature;

[0120] According to the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature, perform weighted calculations on the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature to obtain the track confidence of the target track.

[0121] In the embodiments of the present invention, first, a feature capable of more comprehensively and accurately evaluating the track confidence is provided, that is, the track accuracy confidence feature, and the specific calculation method of the track accuracy confidence feature is given. On this basis, the track accuracy confidence feature is fused with the two track confidence evaluation features of the track continuous tracking rate confidence feature and the target recognition probability confidence feature, and an evaluation method of the track confidence is given. Through the foregoing processing, the evaluation accuracy of the track confidence can be improved. In addition, it also has the advantages of fast convergence speed and timely response to target changes.

[0122] Figure 3 is a schematic diagram of the electronic device provided by the embodiments of the present invention. As Figure 3 shown, the electronic device 3 of this embodiment includes: a processor 30, a memory 31, and a computer program 32 stored in the memory 31 and executable on the processor 30. When the processor 30 executes the computer program 32, the steps in the above-mentioned embodiments of the evaluation method of each track confidence are implemented, such as Figure 1 the steps 110 to 140 shown. Alternatively, when the processor 30 executes the computer program 32, the functions of each module in the above-mentioned device embodiments are implemented, such as Figure 2 the functions of the modules 210 to 240 shown.

[0123] Exemplarily, the computer program 32 can be divided into one or more modules. One or more modules are stored in the memory 31 and executed by the processor 30 to complete the present invention. The one or more modules can be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 32 in the electronic device 3. For example, the computer program 32 can be divided intoFigure 2 The modules 210 to 240 shown

[0124] The electronic device 3 may include, but is not limited to, a processor 30 and a memory 31. Those skilled in the art can understand that Figure 3 These are merely examples of the electronic device 3 and do not constitute a limitation on the electronic device 3. It may include more or fewer components than shown, or combine certain components, or have different components. For example, the electronic device may also include input / output devices, network access devices, a bus, etc.

[0125] The so-called processor 30 may be a central processing unit (CPU), or may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0126] The memory 31 may be an internal storage unit of the electronic device 3, such as the hard disk or memory of the electronic device 3. The memory 31 may also be an external storage device of the electronic device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc., equipped on the electronic device 3. Further, the memory 31 may also include both the internal storage unit and the external storage device of the electronic device 3. The memory 31 is used to store the computer program and other programs and data required by the electronic device 3. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0127] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of this application. The specific working processes of the units and modules in the above system can refer to the corresponding processes in the foregoing method embodiments and will not be elaborated here.

[0128] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0129] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or by a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present invention.

[0130] In the embodiments provided by the present invention, it should be understood that the disclosed device / electronic device and method can be implemented in other ways. For example, the device / electronic device embodiments described above are only illustrative. For example, the division of the modules or units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of the device or unit can be in an electrical, mechanical or other form.

[0131] The unit described as a separated component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it can be located in one place, or can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0132] In addition, in each embodiment of the present invention, each functional unit may be integrated into one processing unit, or each unit may exist physically alone, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of a software functional unit.

[0133] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above-mentioned embodiment methods of the present invention, it may also be completed by instructing relevant hardware through a computer program. The computer program may be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-mentioned embodiments of the method for evaluating the confidence of each track can be implemented. Among them, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium, etc. It should be noted that the content included in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable medium does not include electrical carrier signals and telecommunication signals.

[0134] The above-mentioned embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for evaluating track confidence, characterized in that Including: Obtaining the measurement information of each of a preset number of radar frames of a target track; wherein, the measurement information includes a lateral position measurement value, a longitudinal position measurement value, a lateral speed measurement value, and a longitudinal speed measurement value; Calculating a lateral position correction likelihood probability, a longitudinal position correction likelihood probability, a lateral speed correction likelihood probability, and a longitudinal speed correction likelihood probability of the target track according to the measurement information of each of the preset number of radar frames; Calculating a track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track; Evaluating the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and the target recognition probability confidence feature of the target track obtained in advance; The calculation methods of the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track include: Among them, p1 is the likelihood probability of lateral position correction, p2 is the likelihood probability of longitudinal position correction, p3 is the likelihood probability of lateral velocity correction, p4 is the likelihood probability of longitudinal velocity correction, x is the lateral position variable, and σ x is the standard deviation of the lateral position measurement values of the preset number of radar frames, is the average value of the lateral position measurement values of the preset number of radar frames, P is the state covariance matrix of the Kalman filter, P 11 、P 22 、P 33 and P 44 are the element values in the state covariance matrix, y is the longitudinal position variable, and σ y is the standard deviation of the longitudinal position measurement values of the preset number of radar frames, is the average value of the longitudinal position measurement values of the preset number of radar frames, V x is the lateral velocity variable, and σ Vx is the standard deviation of the lateral velocity measurement values of the preset number of radar frames, is the average value of the lateral velocity measurement values of the preset number of radar frames, V y is the longitudinal velocity variable, and σ Vy is the standard deviation of the longitudinal velocity measurement values of the preset number of radar frames, is the average value of the longitudinal velocity measurement values of the preset number of radar frames; The calculating the track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track includes: Performing weighted calculation on the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track according to the respective weight values of the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral speed correction likelihood probability, and the longitudinal speed correction likelihood probability of the target track, to obtain the track accuracy confidence feature of the target track.

2. The method for evaluating the track confidence according to claim 1, characterized in that, The obtaining the measurement information of each of a preset number of radar frames of a target track includes: Obtaining the lateral position measurement value and the longitudinal position measurement value of the target radar frame according to the Doppler information of the target radar frame; wherein, the target radar frame is any one of the preset number of radar frames of the target track; Obtaining the lateral speed measurement value and the longitudinal speed measurement value of the target radar frame according to the lateral position measurement values and the longitudinal position measurement values of at least one radar frame before the target radar frame obtained in advance.

3. The method for evaluating the track confidence according to claim 2, wherein The obtaining the lateral speed measurement value and the longitudinal speed measurement value of the target radar frame according to the lateral position measurement values and the longitudinal position measurement values of at least one radar frame before the target radar frame obtained in advance includes: Performing least squares fitting processing on the lateral position measurement values of the at least one radar frame with respect to time to obtain a first lateral speed measurement value of the target radar frame; performing least squares fitting processing on the longitudinal position measurement values of the at least one radar frame with respect to time to obtain a first longitudinal speed measurement value; Perform differential processing with respect to time on the lateral position measurement value of the previous radar frame of the target radar frame and the lateral position measurement value of the target radar frame to obtain the second lateral velocity measurement value of the target radar frame; perform differential processing with respect to time on the longitudinal position measurement value of the previous radar frame of the target radar frame and the longitudinal position measurement value of the target radar frame to obtain the second longitudinal velocity measurement value of the target radar frame. Perform Kalman estimation processing on the lateral position measurement value of the previous radar frame of the target radar frame to obtain the third lateral velocity measurement value of the target radar frame; perform Kalman estimation processing on the longitudinal position measurement value of the previous radar frame of the target radar frame to obtain the third longitudinal velocity measurement value of the target radar frame. According to the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value, perform weighted calculation on the first lateral velocity measurement value, the second lateral velocity measurement value, and the third lateral velocity measurement value to obtain the lateral velocity measurement value of the target radar frame; according to the respective weight values of the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value, perform weighted calculation on the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value to obtain the longitudinal velocity measurement value of the target radar frame.

4. The method for evaluating the track confidence according to claim 3, wherein The acquisition methods of the respective weight values of the first lateral velocity measurement value, the second lateral velocity measurement value, the third lateral velocity measurement value, the first longitudinal velocity measurement value, the second longitudinal velocity measurement value, and the third longitudinal velocity measurement value include: where α is the azimuth angle at which the radar is installed, is the i-th lateral velocity measurement value, is the i-th longitudinal velocity measurement value, doppler is the measured Doppler information of the target radar frame, and η i is the weight value of the i-th lateral velocity measurement value and the i-th longitudinal velocity measurement value.

5. The method for evaluating the track confidence according to claim 1, wherein The weight values of the lateral position correction likelihood probability and the lateral velocity correction likelihood probability are the same, the weight values of the longitudinal position correction likelihood probability and the longitudinal velocity correction likelihood probability are the same, and the weight value of the lateral position correction likelihood probability is greater than the weight value of the longitudinal position correction likelihood probability.

6. The method for evaluating the track confidence according to claim 1, wherein The evaluation of the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and the target recognition probability confidence feature of the target track obtained in advance includes: Use the analytic hierarchy process to obtain the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature; According to the respective weight values of the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature, perform weighted calculation on the track accuracy confidence feature, the track continuous tracking rate confidence feature, and the target recognition probability confidence feature to obtain the track confidence of the target track.

7. An evaluation device for track confidence, characterized in that, Include: A measurement acquisition module, configured to acquire the measurement information of each of a preset number of radar frames of the target track; wherein, the measurement information includes a lateral position measurement value, a longitudinal position measurement value, a lateral velocity measurement value, and a longitudinal velocity measurement value. A first calculation module, configured to calculate a lateral position correction likelihood probability, a longitudinal position correction likelihood probability, a lateral velocity correction likelihood probability, and a longitudinal velocity correction likelihood probability of the target track according to measurement information of each of the preset number of radar frames; A second calculation module, configured to calculate a track accuracy confidence feature of the target track according to the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral velocity correction likelihood probability, and the longitudinal velocity correction likelihood probability of the target track; A confidence evaluation module, configured to evaluate the track confidence of the target track according to the track accuracy confidence feature of the target track, and the track continuous tracking rate confidence feature and the target recognition probability confidence feature of the target track obtained in advance; The first calculation module is further configured to: Among them, p1 is the likelihood probability of lateral position correction, p2 is the likelihood probability of longitudinal position correction, p3 is the likelihood probability of lateral velocity correction, p4 is the likelihood probability of longitudinal velocity correction, x is the lateral position variable, and σ x is the standard deviation of the lateral position measurement values of the preset number of radar frames, is the average value of the lateral position measurement values of the preset number of radar frames, P is the state covariance matrix of the Kalman filter, P 11 、P 22 、P 33 and P 44 are the element values in the state covariance matrix, y is the longitudinal position variable, and σ y is the standard deviation of the longitudinal position measurement values of the preset number of radar frames, is the average value of the longitudinal position measurement values of the preset number of radar frames, V x is the lateral velocity variable, and σ Vx is the standard deviation of the lateral velocity measurement values of the preset number of radar frames, is the average value of the lateral velocity measurement values of the preset number of radar frames, V y is the longitudinal velocity variable, and σ Vy is the standard deviation of the longitudinal velocity measurement values of the preset number of radar frames, is the average value of the longitudinal velocity measurement values of the preset number of radar frames; The second calculation module is further configured to: Perform weighted calculation on the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral velocity correction likelihood probability, and the longitudinal velocity correction likelihood probability of the target track according to respective weight values of the lateral position correction likelihood probability, the longitudinal position correction likelihood probability, the lateral velocity correction likelihood probability, and the longitudinal velocity correction likelihood probability of the target track, to obtain a track accuracy confidence feature of the target track.

8. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, the steps of the method for evaluating the track confidence according to any one of claims 1 to 6 above are implemented.

Images