Method and device for automatic tracking of maneuvering targets

Abstract

The present application relates to a method and device for automatic tracking of maneuvering targets, wherein the method for automatic tracking of maneuvering targets includes: obtaining the track state of the target at the current moment, and obtaining the probability of existence of the track of the target; judging whether the target is maneuvering according to the probability of existence of the track of the target at the current moment and the probability of existence of the track of the target at the historical moment; if so, correcting the track state of the target at the current moment; and determining the track of the target at the current moment according to the corrected track state of the target at the current moment. Through the present application, when the calculation result of the IPDA automatic tracking algorithm is corrected using the method for automatic tracking of maneuvering targets, the problem of the sharp deterioration of the tracking performance of the IPDA automatic tracking algorithm in the target maneuvering area can be solved.

Description

Technical Field

[0001] The present application relates to the field of automatic target tracking, and in particular to a method and device for automatic tracking of a maneuvering target. Background Art

[0002] In the field of automatic target tracking, there are often challenges such as clutter interference and missed target detection. The existing IPDA (Integrated Probabilistic Data Association) method achieves automatic target tracking by modeling the target state and introducing the probability of target existence (PTE) for track management. However, in areas where the target is maneuvering, IPDA has problems such as a large number of target losses and a decrease in the track share.

[0003] When the existing IPDA makes observation selection based on the predicted value of the track, the predicted value is obtained based on the target's motion model. When modeling, the target's motion model is often uniform linear motion. However, when the target maneuvers, there is a high probability that the target measurement will not fall into the wave gate, which ultimately leads to a sharp deterioration in the tracking performance in the target maneuvering area. How to improve the tracking performance of maneuvering targets based on the IPDA automatic tracking algorithm is an important problem that needs to be overcome.

[0004] With regard to the problem that the tracking performance of the IPDA automatic tracking algorithm in the target maneuvering area in the related art deteriorates sharply, no effective solution has been proposed yet. Summary of the invention

[0005] In this embodiment, a method, device, electronic device and storage medium for automatic tracking of a maneuvering target are provided to solve the problem in the related art that the tracking performance of the IPDA automatic tracking algorithm in the target maneuvering area deteriorates sharply.

[0006] In a first aspect, a method for automatically tracking a maneuvering target is provided in this embodiment, and the method includes:

[0007] Obtaining the track state of the target at the current moment, and obtaining the track existence probability of the target;

[0008] Determining whether the target is maneuvering according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment;

[0009] If yes, the track state of the target at the current moment is corrected;

[0010] The track of the target at the current moment is determined according to the corrected track state of the target at the current moment.

[0011] In some embodiments, judging whether the target maneuvers according to the track existence probability of the target at the current moment and the track existence probability of the target at the historical moment includes:

[0012] Obtaining a preset maneuver discrimination value;

[0013] Determine whether the probability of the existence of the track of the target at any historical moment within the first time backtracking range is greater than the track confirmation threshold;

[0014] If so, determining whether the probability of the existence of the track of the target at any historical moment within the second time backtracking range is greater than or equal to the preset maneuvering discrimination value;

[0015] If yes, determining whether the target's track existence probability at the current moment is less than or equal to the preset maneuvering discrimination value;

[0016] If so, it is determined that the target is maneuvering.

[0017] In some embodiments, the historical moment includes a first historical moment and a second historical moment, the first historical moment is a moment before the current moment, and the second historical moment is a moment before the first historical moment;

[0018] The step of judging whether the probability of existence of the track of the target at any historical moment within the first time backtracking range is greater than the track confirmation threshold comprises:

[0019] Determining whether the probability of existence of the track of the target at the first historical moment and / or the second historical moment is greater than a confirmed track threshold;

[0020] The step of determining whether the probability of existence of the track of the target at any historical moment within the second time backtracking range is greater than or equal to the preset maneuvering discrimination value comprises:

[0021] Determine whether the track existence probability of the target at the first historical moment is greater than or equal to the preset maneuver discrimination value.

[0022] In some embodiments, the method further comprises:

[0023] Obtaining a measurement set about the target at a current moment;

[0024] The correcting of the track state of the target at the current moment includes:

[0025] Taking the maximum speed of the target as a constraint, selecting a target measurement from the measurement set;

[0026] generating a maneuvering state of the target at a current moment based on the target measurement;

[0027] According to the maneuvering state of the target at the current moment, the track state of the target at the current moment is corrected.

[0028] In some embodiments, the correcting the track state of the target at the current moment according to the maneuvering state of the target at the current moment includes:

[0029] Determining whether there is a measurement in the measurement set that is in a track gate;

[0030] If yes, then the track state of the target at the current moment is updated to the maneuvering state of the target at the current moment;

[0031] If not, performing a weighted sum correction on the track state of the target at the current moment according to the maneuvering state of the target at the current moment;

[0032] The weight coefficient of the track state of the target at the current moment is the probability of the track of the target at the current moment.

[0033] In some of the embodiments, the maximum speed of the target is used as a constraint to select the target measurement from the measurement set;

[0034] Calculate the change rate of each measurement in the measurement set compared to the measurement of the target at the previous moment;

[0035] The measurement whose changing speed is less than or equal to the maximum speed of the target is taken as the target measurement.

[0036] In some embodiments, the obtaining of the track state of the target at the current moment and the obtaining of the track existence probability of the target include:

[0037] Obtaining the track state and track existence probability of the target at the previous moment;

[0038] Based on the track state and track existence probability of the target at the previous moment, the track state and track existence probability of the target at the current moment are determined by a comprehensive probability data association algorithm.

[0039] In some embodiments, the determining the track state and track existence probability of the target at the current moment by a comprehensive probability data association algorithm based on the track state and track existence probability of the target at the previous moment includes:

[0040] Determining a predicted track state according to the track state of the target at a previous moment, and determining a predicted track existence probability according to the track existence probability of the target at a previous moment;

[0041] determining a subset of measurements from the set of measurements according to the track gate, wherein the measurements in the subset of measurements are within the track gate;

[0042] Determining the track state of the target at the current moment according to the measurement subset and the predicted track state;

[0043] The probability of existence of the track of the target at the current moment is determined according to the predicted track existence probability.

[0044] In some embodiments, determining the track of the target at the current moment according to the corrected track state of the target at the current moment includes:

[0045] Determine whether the probability of the target's track existing at the current moment is greater than or equal to a track confirmation threshold;

[0046] If yes, determining the track of the target at the current moment based on the corrected track state of the target at the current moment;

[0047] Determine whether the probability of the target's track existing at the current moment is less than or equal to a clipping threshold;

[0048] If so, the corrected track state of the target at the current moment is deleted.

[0049] In a second aspect, a mobile target automatic tracking device is provided in this embodiment, and the device includes:

[0050] An information acquisition module, used to acquire the track state of the target at the current moment, and acquire the track existence probability of the target;

[0051] A maneuver determination module, used to determine whether the target has maneuvered according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment;

[0052] A track correction module, used for correcting the track state of the target at the current moment when the target is maneuvering;

[0053] The track confirmation module is used to determine the track of the target at the current moment according to the corrected track state of the target at the current moment.

[0054] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the method for automatic tracking of maneuvering targets described in the first aspect above is implemented.

[0055] In a fourth aspect, in this embodiment, a storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method for automatically tracking a maneuvering target described in the first aspect above is implemented.

[0056] Compared with the related art, the method for automatic tracking of maneuvering targets provided in this embodiment can correct the track state of the target at the current moment, and use the probability of the target's track existence at the current moment and the probability of the target's track existence at the historical moment as the basis for whether the target is maneuvering. When it is determined that the target is maneuvering, the track state of the target at the current moment is corrected, thereby obtaining a more accurate track state and improving the target automatic tracking capability. When the method in this embodiment is used to correct the calculation results of the IPDA automatic tracking algorithm, the problem of the sharp deterioration of the tracking performance of the IPDA automatic tracking algorithm in the target maneuvering area can be solved.

[0057] Details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0059] Figure 1 It is a hardware structure block diagram of the terminal of the method for automatic tracking of a maneuvering target of this embodiment.

[0060] Figure 2 4 is a flow chart of the method for automatic tracking of a maneuvering target of this embodiment.

[0061] Figure 3 It is a schematic diagram of the initial position, motion state, sensor position and clutter distribution of the target in the preferred embodiment.

[0062] Figure 4 It is a flow chart of the method for automatic tracking of a maneuvering target of the preferred embodiment.

[0063] Figure 5 It is a comparison chart of the average number of CTTs of the existing IPDA and the IPDA improved by the present invention.

[0064] Figure 6 It is a comparison chart of the track share of the existing IPDA and the improved IPDA using the present invention.

[0065] Figure 7 It is a structural block diagram of the automatic tracking device for maneuvering targets of this embodiment. DETAILED DESCRIPTION

[0066] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0067] Unless otherwise defined, the technical terms or scientific terms involved in this application shall have the general meaning understood by people with ordinary skills in the technical field to which this application belongs. The words "one", "a", "a", "the", "these" and the like in this application do not represent quantitative restrictions, and they can be singular or plural. The terms "include", "comprise", "have" and any variants thereof involved in this application are intended to cover non-exclusive inclusions; for example, a process, method and system, product or device comprising a series of steps or modules (units) is not limited to the listed steps or modules (units), but may include unlisted steps or modules (units), or may include other steps or modules (units) inherent to these processes, methods, products or devices. The words "connect", "connected", "coupled" and the like involved in this application are not limited to physical or mechanical connections, but may include electrical connections, whether directly or indirectly. The "multiple" involved in this application refers to two or more. "And / or" describes the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: A exists alone, A and B exist at the same time, and B exists alone. Usually, the character " / " indicates that the objects associated with each other are in an "or" relationship. The terms "first", "second", "third", etc. involved in this application are only used to distinguish similar objects and do not represent a specific ordering of the objects.

[0068] The method embodiment provided in this embodiment can be executed in a terminal, a computer or a similar computing device. For example, running on a terminal, Figure 1 : is a hardware structure block diagram of a terminal of the method for automatically tracking a maneuvering target in this embodiment. Figure 1 As shown, the terminal may include one or more ( Figure 1 Only one is shown in the figure) processor 102 and memory 104 for storing data, wherein processor 102 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA. The above terminal may also include a transmission device 106 and an input and output device 108 for communication functions. It can be understood by those skilled in the art that Figure 1 The structure shown is for illustration only and does not limit the structure of the above terminal. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.

[0069] The memory 104 can be used to store computer programs, for example, software programs and modules of application software, such as the computer program corresponding to the method for automatic tracking of mobile targets in this embodiment. The processor 102 executes various functional applications and data processing by running the computer program stored in the memory 104, that is, to implement the above method. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor 102, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0070] The transmission device 106 is used to receive or send data via a network. The above network includes a wireless network provided by the communication provider of the terminal. In one example, the transmission device 106 includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.

[0071] In this embodiment, a method for automatically tracking a maneuvering target is provided. Figure 2 : is a flow chart of the method for automatically tracking a maneuvering target of this embodiment. Figure 2 As shown, the process includes the following steps:

[0072] Step S210, obtaining the track state of the target at the current moment, and obtaining the track existence probability of the target.

[0073] Specifically, the target automatic tracking device first needs to obtain the target's track state at the current moment and the probability of track existence at different moments, which specifically includes the target's track existence probability at the current moment and the track existence probability at historical moments. It should be noted that the method in this embodiment is mainly to correct the target's track state at the current moment, so as to obtain a more accurate track state of the target at the current moment. For example, the existing IPDA target automatic tracking algorithm, when the target is in a maneuvering state, the calculated track state of the target at the current moment is inaccurate, so it is necessary to correct its track state when the target is maneuvering. The track state mainly includes the track state mean and the track state covariance.

[0074] Step S220, judging whether the target has maneuvered according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment; if so, executing step S230.

[0075] Specifically, before the target automatic tracking device corrects the track state of the target at the current moment, it needs to determine whether the target is maneuvering. If it is maneuvering, correction is required, and if it is not maneuvering, no correction is required. Further, it is necessary to comprehensively judge whether the target is going to maneuver based on the probability of the target's track existence at the current moment and the probability of the target's track existence at the historical moment. If so, execute step S230, if not, terminate the correction process, and directly determine the target track based on the target's track state at the current moment.

[0076] Step S230, correcting the track state of the target at the current moment.

[0077] Specifically, when the target maneuvers, the target automatic tracking device corrects the track state of the target at the current moment. Further, the track state mean and track state covariance are adjusted and corrected to obtain a more accurate track state mean and track state covariance.

[0078] Step S240, determining the track of the target at the current moment according to the corrected track state of the target at the current moment.

[0079] Specifically, after the calibration is completed, the target automatic tracking device determines the track of the target at the current moment according to the calibrated track state mean and track state covariance of the target at the current moment.

[0080] Through the above steps, the track state of the target at the current moment can be corrected, and the probability of the target's track at the current moment and the probability of the target's track at the historical moment are used as the basis for whether the target has maneuvered. When it is determined that the target has maneuvered, the track state of the target at the current moment is corrected, thereby obtaining a more accurate track state and improving the target automatic tracking capability. When the method in this embodiment is used to correct the calculation results of the IPDA automatic tracking algorithm, the problem of the sharp deterioration of the tracking performance of the IPDA automatic tracking algorithm in the target maneuvering area can be solved.

[0081] In some embodiments, step S220, judging whether the target has maneuvered according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment, specifically includes:

[0082] Step S221, obtaining a preset maneuver discrimination value.

[0083] Specifically, the preset maneuvering discrimination value is pre-set as one of the criteria for judging whether the target maneuvers. Preferably, the preset maneuvering discrimination value can be 0.8, in which case it is possible to better judge whether the target maneuvers. If the preset maneuvering discrimination value is too large, the tracking accuracy will be reduced, and if the preset maneuvering discrimination value is too small, the best time for the target to maneuver will be missed.

[0084] Step S222, determine whether the probability of the existence of the target's track at any historical moment within the first time backtracking range is greater than the track confirmation threshold; if so, execute step S223.

[0085] Specifically, based on the existing target automatic tracking algorithm, the track confirmation threshold is generally 0.98. The first time backtracking range refers to the time range from the current moment to the past, such as 0.5 seconds before the current moment. There is at least one historical moment in the first time backtracking range. When the probability of the target's track at any of the historical moments is greater than the track confirmation threshold, step S223 is executed; if it is not satisfied, it means that the target does not maneuver.

[0086] In step S223, it is determined whether the probability of the existence of the target's track at any historical moment within the second time backtracking range is greater than or equal to the preset maneuvering judgment value; if so, step 224 is executed.

[0087] Specifically, the second time backtracking range also refers to the time range from the current moment to the past, such as 0.3 seconds before the current moment. There is at least one historical moment in the second time backtracking range. When the probability of the target's track existence at any of the historical moments is greater than or equal to the preset maneuvering discrimination value, step S224 is executed; if not, it means that the target does not maneuver.

[0088] In step S224, it is determined whether the target's track existence probability at the current moment is less than or equal to a preset maneuvering discrimination value.

[0089] Specifically, in addition to determining whether the target's track existence probability at the historical moment meets the predetermined condition, it is also necessary to determine whether the target's track existence probability at the current moment is less than or equal to the preset maneuvering discrimination value. When the target's track existence probability at the current moment is less than or equal to the preset maneuvering discrimination value, step S225 is executed; if not, it means that the target does not maneuver.

[0090] In step S225, it is determined that the target is maneuvering.

[0091] Specifically, after the above three judgment steps, it can be determined whether the target has maneuvered. It should be noted that the condition for the target to maneuver is: the probability of the target's track existing at any historical moment within the first retrospective time range is greater than the track confirmation threshold, and the probability of the target's track existing at any historical moment within the second time retrospective range is greater than or equal to the preset maneuvering judgment value, and the probability of the target's track existing at the current moment is less than or equal to the preset maneuvering judgment value. As long as the three conditions are met, it can be determined that the target has maneuvered. Therefore, the order of the above judgment steps can be interchanged, and other judgment orders can be used in other embodiments.

[0092] To be more specific, the historical moment includes a first historical moment and a second historical moment, the first historical moment is the moment before the current moment, and the second historical moment is the moment before the first historical moment.

[0093] Step S222, determining whether the probability of the existence of the target's track at any historical moment within the first time backtracking range is greater than the track confirmation threshold, specifically includes:

[0094] Determine whether the probability of the target's track existence at the first historical moment and / or the second historical moment is greater than a confirmed track threshold.

[0095] Specifically, the first time backtracking range includes the first historical moment and the second historical moment. If the probability of the target's track existence at any of the two moments is greater than the confirmed track threshold, the requirement for judging whether the target has maneuvered is met.

[0096] Step S223 determines whether the probability of the target's track existence at any historical moment within the second time backtracking range is greater than or equal to a preset maneuvering discrimination value, specifically including:

[0097] Determine whether the target's track existence probability at the first historical moment is greater than or equal to a preset maneuver discrimination value.

[0098] Specifically, the first time backtracking range includes the first historical moment. If the probability of the target's track existence at the first historical moment is greater than or equal to a preset maneuvering judgment value, the requirement for judging whether the target has maneuvered is met.

[0099] It should be further explained that the time interval between two adjacent moments in this embodiment is determined by the sensor acquisition interval. In a general target automatic tracking algorithm, it is necessary to collect target information through a corresponding sensor, and the sensor collects target information at intervals. Exemplarily, the sensor acquisition interval can be used as the moment interval in this embodiment.

[0100] In some of the embodiments, the method for automatic tracking of a maneuvering target further includes: acquiring a measurement set about the target at a current moment.

[0101] Specifically, the measurement set includes all measurements of the target, and the measurement is the target information collected by the sensor and is used to generate the target's track state.

[0102] Step S230, correcting the track state of the target at the current moment, specifically includes:

[0103] Step S231 , taking the maximum speed of the target as a constraint condition, selecting the target measurement from the measurement set.

[0104] Specifically, in this step, the maximum speed of the target is used as a constraint condition, and measurements that meet the conditions are selected from the measurement set, and these measurements are recorded as target measurements. It should be noted that in the existing IPDA target automatic tracking algorithm, the wave gate is used as a constraint condition, and the target measurement is selected from the measurement set to generate the target's track state at the current moment. However, when the target maneuvers, the target measurement may not fall into the wave gate, which will cause the problem of inaccurate track state. This step increases the means of selecting target measurements, thereby reducing the probability of target measurements being missed.

[0105] Step S232, generating the maneuvering state of the target at the current moment based on the target measurement.

[0106] Specifically, after obtaining the target measurement, the maneuvering state of the target at the current moment is generated through the target measurement. The maneuvering state is the same as the track state, and has a maneuvering state mean and a maneuvering state covariance.

[0107] Step S233, correcting the track state of the target at the current moment according to the maneuvering state of the target at the current moment.

[0108] Specifically, after obtaining the maneuvering state of the target at the current moment, the track state of the target at the current moment is corrected according to the maneuvering state, thereby obtaining a more accurate track state, thereby improving the accuracy of automatic target tracking.

[0109] Further, in a specific embodiment, step S233, according to the maneuvering state of the target at the current moment, correcting the track state of the target at the current moment, specifically includes:

[0110] Determine whether there is a measurement in the measurement set that is in the track gate. If so, update the target's track state at the current moment to the target's maneuvering state at the current moment; if not, perform a weighted sum correction on the target's track state at the current moment by the target's maneuvering state at the current moment. The weight coefficient of the target's track state at the current moment is the probability of the target's track existing at the current moment.

[0111] Specifically, there are two situations for track state correction. When no target measurement in the measurement set falls into the wave gate, it means that the target's track state at the current moment is very inaccurate, so it is necessary to use the target's maneuvering state at the current moment as the track state, or to correct the target's track state at the current moment to the maneuvering state. When there are target measurements in the measurement set that fall into the wave gate, it means that the target's track state at the current moment is still relatively accurate, so only a small correction is required. Specifically, the maneuvering state and the track state are weighted and summed to obtain the corrected track state of the target at the current moment. Among them, the weight coefficient of the track state is the probability of the target's track existing at the current moment, and the corresponding weight coefficient of the maneuvering state is: 1-the probability of the target's track existing at the current moment.

[0112] In one specific embodiment, step S231, taking the maximum speed of the target as a constraint condition, selecting the target measurement from the measurement set, specifically includes:

[0113] Calculate the change speed of each measurement in the measurement set compared to the target measurement at the previous moment, and take the measurement whose change speed is less than or equal to the maximum speed of the target as the target measurement.

[0114] Specifically, first calculate the difference between the measurement in the measurement set and the measurement of the target at the previous moment, and then divide the difference by the time interval between two adjacent moments, so as to obtain the change speed of each measurement in the measurement set, and then select the measurement with a change speed less than or equal to the target maximum speed as the target measurement.

[0115] In some embodiments, step S210, obtaining the track state of the target at the current moment, and obtaining the track existence probability of the target, specifically includes:

[0116] Step S211, obtaining the track state and track existence probability of the target at the previous moment;

[0117] Step S212, based on the track state and track existence probability of the target at the previous moment, the track state and track existence probability of the target at the current moment are determined by a comprehensive probability data association algorithm.

[0118] Specifically in this embodiment, the track state of the target at the current moment and the probability of the track state existence are directly obtained mainly through the integrated probability data association algorithm (IPDA). However, when the target is maneuvering, the result calculated by the IPDA algorithm is not accurate enough, so it needs to be corrected in subsequent steps. Therefore, the automatic tracking method of the maneuvering target in this embodiment is a method based on the IPDA algorithm, but correcting its calculation results to obtain a more accurate target track state at the current moment.

[0119] In one embodiment, step S212, based on the track state and track existence probability of the target at the previous moment, determines the track state and track existence probability of the target at the current moment by using a comprehensive probability data association algorithm, specifically including:

[0120] The predicted track state is determined according to the track state of the target at the previous moment, and the predicted track existence probability is determined according to the track existence probability of the target at the previous moment.

[0121] A measurement subset is determined from the measurement set according to the track gate, wherein the measurements in the measurement subset are within the track gate.

[0122] According to the measurement subset and the predicted track state, the track state of the target at the current moment is determined.

[0123] According to the predicted track existence probability, the target track existence probability at the current moment is determined.

[0124] In this specific embodiment, the process of calculating the target's track state and track existence probability at the current moment based on the IPDA algorithm is specifically described. It is mainly to calculate the predicted track state and predicted track existence probability of the target respectively through the target's track state and track existence probability at the previous moment; then select the target measurement from the measurement set with the track gate as the constraint condition to form a measurement subset; finally, determine the target's track state at the current moment based on the selected measurement subset and the predicted track state. Through the above process, it can be seen that the accuracy of the target's track state at the current moment depends on the measurement subset. If there is a target measurement in the measurement subset, the track state is relatively accurate; however, when the target maneuvers, it may happen that the target measurement does not fall into the track gate. At this time, the measurement subset is an empty set, which makes the calculated track state inaccurate, and ultimately leads to the loss of the target.

[0125] In some embodiments, step S240, determining the track of the target at the current moment according to the corrected track state of the target at the current moment, specifically includes:

[0126] Step S241, determine whether the probability of the target's track existence at the current moment is greater than or equal to the track confirmation threshold; if so, execute step S242.

[0127] Step S242, determining the target's track at the current moment based on the corrected target's track state at the current moment.

[0128] Step S243, determine whether the probability of the target's track existence at the current moment is less than or equal to the clipping threshold; if so, execute step S244.

[0129] Step S244, deleting the corrected track state of the target at the current moment.

[0130] Specifically, after obtaining the corrected track state of the target at the current moment, the target's track is not determined directly based on the track state, but track management is required. Specifically, determine whether the probability of the target's track existing at the current moment is greater than or equal to the track confirmation threshold. If so, retain the corrected track state. And determine whether the probability of the target's track existing at the current moment is less than or equal to the clipping threshold. If so, delete the corrected track state. Among them, the track confirmation threshold is generally taken as 0.98, and the clipping threshold is half of the probability of the initial track existing.

[0131] The technical solution in this application is described below through a specific preferred embodiment.

[0132] Before introducing the method flow in this preferred embodiment, it is necessary to briefly explain the target automatic tracking algorithm.

[0133] In a better understood situation, three assumptions are first established:

[0134] 1. Assume that the resolution of the sensor is infinite and the target is a point target, that is, each measurement has only one source (clutter or target).

[0135] 2. In the monitoring area, the state of clutter obeys uniform distribution in space, and the number of clutter obeys Poisson distribution in time.

[0136] 3. The target's initial position, motion state, sensor position, and clutter distribution are as follows: Figure 3 As shown; the black solid line represents the motion trajectory of the target, which reflects the motion state of the target, and the starting point of the motion trajectory is the initial position of the target; the five-pointed star symbol indicates the sensor position, and other star-shaped measurements reflect the distribution of clutter.

[0137] Based on the above assumptions, some concepts in this preferred embodiment are explained:

[0138] The time domain evolution model expression of the dynamic state in the two-dimensional plane is:

[0139] X k =FX k-1 +v k

[0140] Among them, X k represents the target dynamic state at time k, and x kk They represent the position and velocity state information of the target in the x and y directions in the two-dimensional Cartesian coordinate system respectively; F represents the target state transfer matrix at time k; v kis a Gaussian white noise with zero mean and covariance Q, where Q is the noise error covariance matrix of the target motion process.

[0141] At each moment, the sensor has a certain detection probability P D Detection obtains the target measurement value y k , the expression is:

[0142] y k =HX k +w k

[0143] Where H is the measurement linear transfer matrix, and the measurement noise w k is a Gaussian white noise with zero mean and covariance R; when the target does not exist, the sensor cannot detect the target measurement y k .

[0144] Based on the above basic concept description, the automatic tracking method of a maneuvering target in the preferred embodiment is described below. In the preferred embodiment, the current moment is recorded as moment k, moment k-1 is the moment before moment k, and moment k-2 is the moment before moment k-1. Figure 4 FIG. 1 is a flow chart of the method for automatically tracking a maneuvering target according to the preferred embodiment of the present invention. Figure 4 As shown, the preferred method for automatically tracking a maneuvering target comprises the following steps:

[0145] Step S410, obtaining input at time k.

[0146] Specifically, the input at time k includes: the measurement set Y generated by the sensor k ; Track existence probability P(χ k-1 |Y k-1 ); track state mean With covariance P k-1|k-1 . Where χ k-1 Indicates that the target exists at time k-1.

[0147] Step S420, predicting the track status at time k.

[0148] The specific prediction process includes two aspects:

[0149] 1. Track existence probability prediction:

[0150]

[0151]

[0152] Where M is the target state transfer matrix; Indicates that the target does not exist at time κ. Preferably,

[0153] 2. Mean and covariance prediction of track state:

[0154]

[0155] Among them, KF P Represents a standard Kalman filter prediction:

[0156]

[0157] P k|k-1 =FP k-1|k-1 F T +Q

[0158] Step S430, observation selection.

[0159] Specifically, the observed predicted mean of the track at time k is and the innovation covariance S k :

[0160]

[0161]

[0162] S k =H*P k|k-1 *H T +R

[0163] Kalman gain K:

[0164]

[0165] The track is used to select the observation time. The specific selection criteria are as follows:

[0166]

[0167] in, is the gate size, which depends on the gate probability P G The size of the wave gate is sorted to obtain the pre-selected observation set

[0168]

[0169] Step S440, calculating the likelihood value of the pre-selected observation i through the likelihood function.

[0170] Specifically, the likelihood value p k (i)

[0171]

[0172] Step S450: target track status is updated.

[0173] Specifically, the likelihood ratio is:

[0174]

[0175] Among them, ρ k is the clutter density, P D represents the sensor detection probability, m k To measure the number of values ​​falling into the threshold, let δ k =P D P G , when m k = 0, that is, no measurement falls within the threshold, then Λ k =1-δ k .

[0176] Association probability:

[0177]

[0178] Update of target track dynamics state:

[0179]

[0180] i=0, the track status is not updated:

[0181]

[0182]

[0183] i>0, the track state is updated by standard Kalman filtering:

[0184]

[0185]

[0186] Step S460: output the target dynamic state.

[0187] The probability of the existence of a track at time k is P(χ k |Y k )renew:

[0188]

[0189] The target dynamic state output at time k:

[0190]

[0191]

[0192]

[0193] It should be further explained that the above steps S410 to S460 are specific preferred implementation steps of step S212, that is, a specific preferred implementation method of determining the track state and track existence probability of the target at the current moment through a comprehensive probabilistic data association algorithm.

[0194] Among them, the target's track state at the current moment includes the track state mean and track state covariance P k|k , and the probability of the target’s track existing at the current moment is P(χ k |Y k ). The target's track state at the previous moment includes the track state mean and track state covariance P k-1|k-1 , and the probability of the target’s track existing at the previous moment is P(χ k-1 |Y k -1 ). Further, in this preferred embodiment, P(x k |Y k-1 ) is the predicted track existence probability and the track state mean and track state covariance P k|k-1 The predicted track state is formed. This is equivalent to the measurement subset in the above embodiment.

[0195] Step S470, performing maneuvering correction, mainly includes the following sub-steps:

[0196] Step S471: When the probability of existence of a track at any time (k-1 and k-2) within the first two frames is greater than the track confirmation threshold, and P(χ k-1 |Y k-1 )≥κ,P(χ k |Y k )≤κ, where κ represents the maneuver discrimination value. If the target dynamic state at the current moment needs to be corrected, then step S462 is executed; if one of the above conditions is not satisfied, then the target dynamic state at the current moment does not need to be corrected.

[0197] Among them, the maneuver discrimination value κ is 0.8, and the value range of κ is (τ c ,1),τ c If κ is too large, the tracking accuracy will decrease, and if κ is too small, the best time for the target to maneuver will be missed.

[0198] Step S472, using the maximum speed information of the target, select the measurement y that satisfies the maximum speed constraint from the measurement k (j) The mean of the maneuvering state is obtained by two-point difference method and covariance

[0199]

[0200]

[0201] Where T is the sensor sampling interval and the maximum speed constraint is:

[0202]

[0203] Among them, Vx_max and Vy_max are the maximum speeds of the target in the x and y directions respectively. is the coefficient of maximum speed. Preferably, Take 1.2.

[0204] Through the above constraints, from the measurement set Y k Select the measurement y that meets the conditions k (j).

[0205] Step S473, using the maneuvering state to correct the target dynamic state at the current moment.

[0206] If i = 0 (no measurement falls into the gate), then the mean of the maneuvering state closest to the posterior state at time k-1 is selected and covariance Replace the target dynamic state at the current moment:

[0207]

[0208]

[0209] If i>0 (there is a measurement falling into the wave gate), the target dynamic state at time k is maneuvered and weighted correction is performed:

[0210]

[0211]

[0212] Where J represents the J maneuvering states of the track.

[0213] If all measurements at the current moment cannot meet the maximum speed constraint, no processing is performed.

[0214] It should be further explained that steps S471 to S473 are preferred implementations of steps S220 and S230. The target dynamic state in this preferred embodiment is equivalent to the target track state.

[0215] Step S480: track management.

[0216] Specifically, when the track has probability P(x k |Y k )≥τ t When the track status is confirmed, the track exists with probability P(χ k |Y k )≤τ c When , the track is deleted. t Confirmation track threshold, τ c is the clipping threshold. t The value is 0.98, τ c is half of the initial track probability.

[0217] Repeat steps S410 to S480 to perform iterative calculations in the time domain, and finally obtain the target dynamic state estimation at each moment.

[0218] Compared with the prior art, the present invention has the following effects: the present invention uses the historical information of the probability of track existence and combines it with the information at the current moment as the basis for whether the target has maneuvered, uses the posterior state of the previous frame and all the measurements of the current frame to screen the maximum speed constraint conditions, generates a temporary track by the two-point difference method for the measurements that meet the conditions, and uses the probability of track existence to correct and weight the maneuvering state and the track obtained by Gaussian mixture at the current moment to obtain the corrected target dynamic state. In a complex environment with missed target detection and clutter interference, the tracking performance of strong maneuvering targets is improved, and compared with the existing IPDA, the performance in track maintenance, true track confirmation rate, etc. is improved.

[0219] Figure 5 It is a comparison chart of the average number of CTTs of the existing IPDA and the IPDA improved by the present invention. Figure 6 It is a comparison chart of the track share of the existing IPDA and the improved IPDA using the present invention. Figure 6 The vertical axis in represents the track ratio. Figure 5 and 6 It can be seen that the performance of the improved IPDA target automatic tracking algorithm is significantly improved.

[0220] In this embodiment, a mobile target automatic tracking device is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and the descriptions that have been made will not be repeated. The terms "module", "unit", "subunit" and the like used below can implement a combination of software and / or hardware of a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0221] Figure 7 : is a block diagram of the automatic tracking device for mobile targets of this embodiment. Figure 7As shown, the device comprises:

[0222] The information acquisition module 710 is used to obtain the track state of the target at the current moment and the probability of the target's track existence;

[0223] A maneuver determination module 720, for determining whether the target is maneuvering according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment;

[0224] The track correction module 730 is used to correct the track state of the target at the current moment when the target is maneuvering;

[0225] The track confirmation module 740 is used to determine the track of the target at the current moment according to the corrected track state of the target at the current moment.

[0226] It should be noted that the above modules can be functional modules or program modules, and can be implemented by software or hardware. For modules implemented by hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0227] In this embodiment, an electronic device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0228] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0229] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0230] In addition, in combination with the automatic tracking method for a maneuvering target provided in the above embodiment, a storage medium may be provided in this embodiment to implement the automatic tracking method for a maneuvering target. The storage medium stores a computer program; when the computer program is executed by a processor, any automatic tracking method for a maneuvering target in the above embodiment is implemented.

[0231] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0232] It should be understood that the specific embodiments described herein are only used to explain the application, rather than to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the protection scope of this application.

[0233] Obviously, the drawings are only some examples or embodiments of the present application. For ordinary technicians in the field, the present application can also be applied to other similar situations based on these drawings without creative work. In addition, it is understandable that although the work done in this development process may be complicated and lengthy, for ordinary technicians in the field, certain changes in design, manufacturing or production based on the technical content disclosed in this application are only conventional technical means and should not be regarded as insufficient content disclosed in this application.

[0234] The term "embodiment" in this application refers to a specific feature, structure or characteristic described in conjunction with the embodiment that can be included in at least one embodiment of the present application. The appearance of this phrase in various locations in the specification does not necessarily mean the same embodiment, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is clearly or implicitly understood by those of ordinary skill in the art that the embodiments described in this application can be combined with other embodiments without conflict.

[0235] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of patent protection. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the scope of protection of the present application. Therefore, the scope of protection of the present application shall be subject to the attached claims.

Claims

1. A method for automatically tracking a maneuvering target, characterized in that: The method comprises: Obtaining the track state of the target at the current moment, and obtaining the track existence probability of the target; Determining whether the target is maneuvering according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment; If yes, then the track state of the target at the current moment is corrected; wherein the following steps are included: Obtaining a measurement set about the target at a current moment; The correcting of the track state of the target at the current moment includes: Taking the maximum speed of the target as a constraint, selecting a target measurement from the measurement set; generating a maneuvering state of the target at a current moment based on the target measurement; According to the maneuvering state of the target at the current moment, the track state of the target at the current moment is corrected; this includes: determining whether there is a measurement in the measurement set that is in a track gate; If yes, then the track state of the target at the current moment is updated to the maneuvering state of the target at the current moment; If not, a weighted sum correction is performed on the track state of the target at the current moment by the maneuvering state of the target at the current moment; wherein the weight coefficient of the track state of the target at the current moment is the probability of existence of the track of the target at the current moment; The track of the target at the current moment is determined according to the corrected track state of the target at the current moment.

2. The method for automatic tracking of a mobile target according to claim 1, characterized in that: The determining whether the target is maneuvering according to the track existence probability of the target at the current moment and the track existence probability of the target at the historical moment comprises: Obtaining a preset maneuver discrimination value; Determine whether the probability of the existence of the track of the target at any historical moment within the first time backtracking range is greater than the track confirmation threshold; If so, determining whether the probability of the existence of the track of the target at any historical moment within the second time backtracking range is greater than or equal to the preset maneuvering discrimination value; If yes, determining whether the target's track existence probability at the current moment is less than or equal to the preset maneuvering discrimination value; If so, it is determined that the target is maneuvering.

3. The method for automatic tracking of a mobile target according to claim 2, characterized in that: The historical moment includes a first historical moment and a second historical moment, the first historical moment is the moment before the current moment, and the second historical moment is the moment before the first historical moment; The step of judging whether the probability of existence of the track of the target at any historical moment within the first time backtracking range is greater than the track confirmation threshold comprises: Determining whether the probability of existence of the track of the target at the first historical moment and / or the second historical moment is greater than a confirmed track threshold; The step of determining whether the probability of existence of the track of the target at any historical moment within the second time backtracking range is greater than or equal to the preset maneuvering discrimination value comprises: Determine whether the track existence probability of the target at the first historical moment is greater than or equal to the preset maneuver discrimination value.

4. The method for automatic tracking of a mobile target according to claim 1, characterized in that: The maximum speed of the target is used as a constraint condition to select the target measurement from the measurement set; Calculate the change rate of each measurement in the measurement set compared to the measurement of the target at the previous moment; The measurement whose changing speed is less than or equal to the maximum speed of the target is taken as the target measurement.

5. The method for automatically tracking a maneuvering target according to any one of claims 1 to 4, characterized in that: The obtaining of the track state of the target at the current moment and the obtaining of the track existence probability of the target include: Obtaining the track state and track existence probability of the target at the previous moment; Based on the track state and track existence probability of the target at the previous moment, the track state and track existence probability of the target at the current moment are determined by a comprehensive probability data association algorithm.

6. The method for automatic tracking of a mobile target according to claim 5, characterized in that: The step of determining the track state and track existence probability of the target at the current moment by using a comprehensive probability data association algorithm based on the track state and track existence probability of the target at the previous moment includes: Determining a predicted track state according to the track state of the target at a previous moment, and determining a predicted track existence probability according to the track existence probability of the target at a previous moment; determining a subset of measurements from the set of measurements according to the track gate, wherein the measurements in the subset of measurements are within the track gate; Determining the track state of the target at the current moment according to the measurement subset and the predicted track state; The probability of existence of the track of the target at the current moment is determined according to the predicted track existence probability.

7. The method for automatically tracking a maneuvering target according to claim 2, characterized in that: Determining the track of the target at the current moment according to the corrected track state of the target at the current moment includes: Determine whether the probability of the target's track existing at the current moment is greater than or equal to a track confirmation threshold; If yes, determining the track of the target at the current moment based on the corrected track state of the target at the current moment; Determine whether the probability of the target's track existing at the current moment is less than or equal to a clipping threshold; If so, the corrected track state of the target at the current moment is deleted.

8. A mobile target automatic tracking device, characterized in that: The device comprises: An information acquisition module, used to acquire the track state of the target at the current moment, and acquire the track existence probability of the target; A maneuver determination module, used to determine whether the target has maneuvered according to the probability of the target's track existing at the current moment and the probability of the target's track existing at the historical moment; The track correction module is used to correct the track state of the target at the current moment when the target is maneuvering; wherein the following steps are included: Obtaining a measurement set about the target at a current moment; The correcting of the track state of the target at the current moment includes: Taking the maximum speed of the target as a constraint, selecting a target measurement from the measurement set; generating a maneuvering state of the target at a current moment based on the target measurement; According to the maneuvering state of the target at the current moment, the track state of the target at the current moment is corrected; this includes: determining whether there is a measurement in the measurement set that is in a track gate; If yes, then the track state of the target at the current moment is updated to the maneuvering state of the target at the current moment; If not, a weighted sum correction is performed on the track state of the target at the current moment by the maneuvering state of the target at the current moment; wherein the weight coefficient of the track state of the target at the current moment is the probability of existence of the track of the target at the current moment; The track confirmation module is used to determine the track of the target at the current moment according to the corrected track state of the target at the current moment.

Images