Methods and apparatus for tracking mobile targets, storage media and electronic equipment

Abstract

This application discloses a method, apparatus, storage medium, and electronic device for tracking maneuvering targets. The method includes: determining a first noise matrix and a second noise matrix; calculating a first probability and a second probability corresponding to each data frame based on a set of measurement data from multiple consecutive data frames, the first noise matrix, and the second noise matrix, wherein the first probability indicates the probability that the target motion model and target motion trajectory match in the current data frame, and the second probability indicates the probability that the target motion model and target motion trajectory do not match in the current data frame; if the first probability and second probability of multiple consecutive frames meet preset conditions, determining that the target motion trajectory does not match the target motion model, and updating the parameters of the target motion model. This application solves the technical problem of low resource utilization in target tracking algorithms provided by related technologies.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology, and more specifically, to a method and apparatus for tracking mobile targets, a storage medium, and an electronic device. Background Technology

[0002] In intelligent driving systems, vehicle-mounted radar can identify the motion of target vehicles on the road. When a target vehicle suddenly changes speed, turns, or makes a U-turn, the vehicle-mounted radar needs to identify the mismatch between the current motion model and the actual motion model in order to change the tracking parameters to better track the target vehicle.

[0003] In the process of target tracking, related technologies typically employ multi-model-based maneuvering target tracking methods. These methods use multiple motion models to track the target and calculate the tracking results for the target vehicle using these models, selecting the model with the highest probability as the final tracking result. However, because this method uses multiple motion models, it requires significant storage and computational complexity. In other words, the target tracking algorithms provided by these technologies suffer from low resource utilization.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This application provides a method and apparatus for tracking mobile targets, a storage medium, and an electronic device, to at least solve the technical problem of low resource utilization in target tracking algorithms provided by related technologies.

[0006] According to one aspect of the embodiments of this application, a method for tracking a maneuvering target is provided, comprising: determining a first noise matrix and a second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match; calculating a first probability and a second probability corresponding to each data frame based on a set of measurement data of multiple consecutive data frames, the first noise matrix, and the second noise matrix, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory do not match in the current data frame; and determining that the target motion trajectory does not match the target motion model and updating the parameters of the target motion model when the first probability and the second probability of multiple consecutive frames meet preset conditions.

[0007] According to another aspect of the embodiments of this application, a maneuvering target tracking device is also provided, comprising: a noise matrix determination unit, configured to determine a first noise matrix and a second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match; a probability calculation unit, configured to calculate a first probability and a second probability corresponding to each data frame based on a set of measurement data of multiple consecutive data frames, the first noise matrix, and the second noise matrix, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory do not match in the current data frame; and a maneuver judgment unit, configured to determine that the target motion trajectory does not match the target motion model and update the parameters of the target motion model when the first probability and the second probability of multiple consecutive frames meet preset conditions.

[0008] Optionally, the probability calculation unit includes: a first probability calculation module, used to calculate a first probability and a second probability corresponding to the first data frame based on the measurement data set, a first noise matrix, and a second noise matrix of the first data frame, including: calculating the likelihood probability pair corresponding to each measurement data of the first data frame according to the measurement data set, the first noise matrix, and the second noise matrix of the first data frame; calculating the first probability and the second probability corresponding to the first data frame using the initial prior probability pair and the likelihood probability pair corresponding to each measurement data of the first data frame, wherein the initial prior probability pair is used to indicate the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when no measurement data is received; and a second probability calculation module, used to calculate the first probability and the second probability corresponding to the k-th data frame based on the measurement data set, the first noise matrix, and the second noise matrix of the first data frame. The calculation of the first probability and the second probability corresponding to the k-th data frame, based on the set of data, the first noise matrix, and the second noise matrix, where k is an integer greater than 1, includes: calculating the prior probability pair corresponding to the k-th data frame based on the first probability and the second probability corresponding to the (k-1)-th data frame, where the prior probability pair indicates the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when the measurement data of the k-th data frame is not received; calculating the likelihood probability pair corresponding to each measurement data of the k-th data frame based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix; and calculating the first probability and the second probability corresponding to the k-th data frame using the prior probability pair corresponding to the k-th data frame and the likelihood probability pair corresponding to each measurement data of the k-th data frame.

[0009] Optionally, the probability calculation unit includes: a first parameter calculation module, used to obtain a first parameter using the first prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, and to obtain a second parameter using the second prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, wherein the first parameter and the first prior probability correspond to the case where the target motion model and the target motion trajectory match, and the second parameter and the second prior probability correspond to the case where the target motion model and the target motion trajectory do not match; and a second parameter calculation module, used to calculate the sum of the first likelihood probabilities in the likelihood probability pairs corresponding to each measurement data of the k-th data frame and the first prior probability of the k-th data frame. The third parameter is obtained by multiplying the probabilities by the first probability. The fourth parameter is obtained by multiplying the sum of the second likelihood probabilities of each likelihood probability pair corresponding to the measurement data of the k-th data frame with the second prior probability corresponding to the k-th data frame. The third parameter and the first likelihood probability correspond to the case where the target motion model and the target motion trajectory match, while the fourth parameter and the second likelihood probability correspond to the case where the target motion model and the target motion trajectory do not match. The probability determination module is used to determine the first probability by the ratio of the sum of the first parameter and the third parameter to the sum of the first parameter, the second parameter, and the third parameter and the fourth parameter; and to determine the second probability by the ratio of the sum of the second parameter and the fourth parameter to the sum of the first parameter, the second parameter, the third parameter and the fourth parameter.

[0010] Optionally, the above probability calculation unit includes: a mean calculation module, used to input the predicted state of the maneuvering target in the k-th data frame into the radar's measurement model to obtain the measurement mean, wherein the predicted state of the maneuvering target is determined according to the target motion model; a covariance matrix calculation module, used to obtain a first covariance matrix and a second covariance matrix using a first noise matrix, a second noise matrix, and the predicted state of the maneuvering target corresponding to the k-th data frame; a Gaussian distribution function calculation module, used to obtain a first Gaussian distribution function based on the measurement mean and the first covariance matrix, and to obtain a second Gaussian distribution function based on the measurement mean and the second covariance matrix; and a likelihood probability calculation module, used to input the measurement data of the k-th data frame into the first Gaussian distribution function and the second Gaussian distribution function respectively to obtain likelihood probability pairs.

[0011] Optionally, the above probability calculation unit includes: a prior probability calculation module, used to multiply the first probability and the second probability corresponding to the (k-1)th data frame with the transition probability matrix to obtain the prior probability pair corresponding to the kth data frame, wherein the transition probability matrix is ​​used to indicate the probability of changes in the matching relationship between the target motion model and the target motion trajectory in the (k-1)th data frame and the kth data frame.

[0012] Optionally, the aforementioned mobile target tracking device further includes: an initialization unit, configured to: set initial values ​​for the radar clutter density, detection probability, and gate probability, and determine the initial values ​​of the radar clutter density, detection probability, and gate probability as an initial radar parameter set; set the value of the transition matrix, wherein the transition matrix includes the probability that the target motion model and target motion trajectory are in a matched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a matched state to a mismatched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a mismatched state to a matched state for two consecutive data frames, and the probability that the target motion model and target motion trajectory are in a mismatched state for two consecutive data frames.

[0013] Optionally, the aforementioned motion judgment unit further includes: a counting module, used to increment the counting parameter by one when the first probability and the second probability in a data frame meet the preset conditions; and to clear the counting parameter to zero when the first probability and the second probability in a data frame do not meet the preset conditions; and a judgment module, used to determine that the target motion trajectory does not match the target motion model when the counting parameter is greater than the counting threshold.

[0014] Optionally, the above-mentioned counting module is further configured to: determine that a preset condition is met when the ratio of the first probability to the second probability is less than a preset ratio.

[0015] According to another aspect of the embodiments of this application, a computer-readable storage medium is also provided, wherein a computer program is stored in the computer program, and the computer program is configured to execute the above-described maneuvering target tracking method when it is run.

[0016] According to another aspect of the embodiments of this application, a computer program product is provided, the computer program product including a computer program / instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer program / instructions from the computer-readable storage medium, and executes the computer program / instructions, causing the computer device to perform the maneuvering target tracking method as described above.

[0017] According to another aspect of the embodiments of this application, an electronic device is also provided, including a memory and a processor, wherein the memory stores a computer program and the processor is configured to execute the above-described maneuvering target tracking method through the computer program.

[0018] In this embodiment, a first noise matrix and a second noise matrix are determined. The first noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match. Based on a set of measurement data from multiple consecutive data frames, the first noise matrix, and the second noise matrix, a first probability and a second probability are calculated for each data frame. The first probability indicates the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability indicates the probability that the target motion model and the target motion trajectory do not match in the current data frame. If the first probability and the second probability in multiple consecutive frames meet preset conditions, it is determined that the target motion trajectory does not match the target motion model, and the parameters of the target motion model are updated. Different noise matrices are used as process noise covariance to characterize whether the target motion model and the target motion trajectory match. The first probability of a matching state and the second probability of a mismatch state are determined by combining the target position and Doppler information provided by multiple measurement data within the gate. By comparing the first probability and the second probability, it is determined whether the target has maneuvered, and tracking is performed after the target has maneuvered. The above method solves the technical problem of low resource utilization in target tracking algorithms provided by related technologies. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 This is a schematic diagram of the hardware environment of an optional maneuvering target tracking method according to an embodiment of this application;

[0021] Figure 2 This is a flowchart of an optional maneuvering target tracking method according to an embodiment of this application;

[0022] Figure 3 This is a schematic diagram of an optional maneuvering target tracking method according to an embodiment of this application;

[0023] Figure 4 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application;

[0024] Figure 5 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application;

[0025] Figure 6 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application;

[0026] Figure 7 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application;

[0027] Figure 8 This is a schematic diagram of an optional mobile target tracking device according to an embodiment of this application;

[0028] Figure 9 This is a schematic diagram of an optional electronic device according to an embodiment of this application. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] According to one aspect of the embodiments of this application, a maneuvering target tracking method is provided. As an optional implementation, the above-described maneuvering target tracking method can be applied to, but is not limited to, [examples of other methods]. Figure 1 The illustrated hardware environment shows a mobile target tracking system. Optionally, the above-described mobile target tracking method can be applied to a vehicle terminal. Figure 1A side view of a vehicle terminal 101 is shown, which is mounted on and capable of traversing a travel surface 113. The vehicle terminal 101 includes an onboard navigation system 103, a computer-readable storage device or medium (memory) 102 including a digital road map 104, a spatial monitoring system 117, a vehicle controller 109, a GPS (Global Positioning System) sensor 110, an HMI (Human / Machine Interface) device 111, and also includes an autonomous controller 112 and a telematics controller 114. The vehicle terminal 101 may include, but is not limited to, commercial vehicles, industrial vehicles, agricultural vehicles, passenger vehicles, all-terrain vehicles, personal mobile devices, robots, and similar mobile platforms to achieve the purposes of this application.

[0032] In one embodiment, the spatial monitoring system 117 includes: one or more spatial sensors and systems arranged to monitor a visible area 105 in front of a vehicle terminal 101; and a spatial monitoring controller 118. Spatial sensors for monitoring the visible area 105 include, for example, a lidar sensor 106, a radar sensor 107, a camera 108, and so on. The placement of the spatial sensors allows the spatial monitoring controller 118 to monitor traffic flow, including approaching vehicles, intersections, lane markings, and other objects surrounding the vehicle terminal 101. The spatial sensors of the spatial monitoring system 117 may include object location sensing devices. The lidar sensor 106 uses pulsed and reflected laser beams to measure the range or distance to objects. The radar sensor 107 uses radio waves to determine the range, angle, and / or speed of objects. The camera 108 includes an image sensor, a lens, and a camera controller. The lidar sensor 106 and the radar sensor 107 can acquire sets of measurement data of targets on the road, generating individual data frames.

[0033] Camera 108 is advantageously mounted and positioned on vehicle terminal 101 in a location that allows for the capture of images of a visible area 105, wherein at least a portion of the visible area 105 includes the area in front of vehicle terminal 101 and a portion of the travel surface 113 of the trajectory of vehicle terminal 101. The visible area 105 may also include the surrounding environment. Other cameras (not shown) may also be employed, for example, including a second camera positioned on the rear or side portion of vehicle terminal 101 to monitor the rear of vehicle terminal 101 and one of the right or left sides of vehicle terminal 101. Camera 108 can acquire road information while vehicle terminal 101 is in motion.

[0034] The autonomous controller 112 is configured to implement autonomous driving or advanced driver assistance system (ADAS) vehicle functionality. Such functionality may include an onboard vehicle control system capable of providing a certain level of driving automation. Driving automation may include a series of dynamic driving and vehicle operations. Driving automation may include simultaneous automatic control of vehicle driving functions (including steering, acceleration, and braking), wherein the driver relinquishes control of the vehicle for a period of time during the journey. Driving automation may include simultaneous automatic control of vehicle driving functions (including steering, acceleration, and braking), wherein the driver relinquishes control of the vehicle terminal 101 for the entire journey. Driving automation includes hardware and controllers configured to monitor the spatial environment in various driving modes to perform various driving tasks during dynamic vehicle operations. By way of non-limiting example, autonomous vehicle functionality includes adaptive cruise control (ACC) operation, lane guidance and lane keeping operation, lane changing operation, steering assist operation, object avoidance operation, parking assist operation, vehicle braking operation, vehicle speed and acceleration operation, vehicle lateral movement operation, for example, as part of lane guidance, lane keeping, and lane changing operations, etc.

[0035] The aforementioned autonomous controller can be equipped with an operating system and an autonomous driving system. The operating system manages the hardware resources (including sensors, system bus, network, etc.) of the vehicle terminal 101 and schedules computing resources. The autonomous driving system implements various algorithms required for autonomous driving, including localization, environmental perception, path planning, and control, and can make decisions in situations such as cornering, straight driving, driving in complex road conditions, and lane changing. The aforementioned autonomous controller can determine maneuvering targets and acquire measurement data sets while the vehicle is in motion.

[0036] The vehicle terminal 101 may include a telematics controller 114, which includes a wireless telematics communication system capable of performing external communication (including communication with a communication network 115 having wireless and wired communication capabilities). Optionally or additionally, the telematics controller 114 directly performs external communication by communicating with a non-airborne server 116 via the communication network 115. The server may execute steps S1-S3: determining a first noise matrix and a second noise matrix; calculating a first probability and a second probability corresponding to each data frame based on a set of measurement data from multiple consecutive data frames, the first noise matrix, and the second noise matrix; and determining that the target motion trajectory does not match the target motion model if the first probability and the second probability of multiple consecutive frames meet preset conditions, and updating the parameters of the target motion model.

[0037] In an optional implementation, the vehicle terminal 101 can use the space monitoring system 117 to collect measurement data sets of targets on the road using the lidar sensor 106 and the radar sensor 107, generating various data frames, and can track the targets. Mobile targets include surrounding vehicles, pedestrians, and other traffic participants. The collected measurement data sets can be stored in the memory 102.

[0038] In an optional implementation, the maneuvering target tracking method of this application can be applied to a vehicle. During vehicle operation, the radar system can acquire measurement data of surrounding targets and track them to determine their trajectories. The target can be observed first to determine its motion characteristics, and then a suitable motion model can be determined based on these characteristics for target tracking. After the motion model is determined, the target may maneuver (e.g., sudden turn, acceleration, deceleration, etc.), and the vehicle can adjust the model parameters to adapt to the target's new motion state. When determining whether the target has maneuvered, the probability of the target maneuvering can be calculated.

[0039] In this embodiment, a first noise matrix and a second noise matrix are determined. The first noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match. Based on a set of measurement data from multiple consecutive data frames, the first noise matrix, and the second noise matrix, a first probability and a second probability are calculated for each data frame. The first probability indicates the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability indicates the probability that the target motion model and the target motion trajectory do not match in the current data frame. If the first probability and the second probability in multiple consecutive frames meet preset conditions, it is determined that the target motion trajectory does not match the target motion model, and the parameters of the target motion model are updated. Different noise matrices are used as process noise covariance to characterize whether the target motion model and the target motion trajectory match. The first probability of a matching state and the second probability of a mismatch state are determined by combining the target position and Doppler information provided by multiple measurement data within the gate. By comparing the first probability and the second probability, it is determined whether the target has maneuvered, and tracking is performed after the target has maneuvered. The above method solves the technical problem of low resource utilization in target tracking algorithms provided by related technologies.

[0040] In alternative implementations, such as Figure 2 As shown, the above-mentioned maneuvering target tracking method includes the following steps:

[0041] S202, determine the first noise matrix and the second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match;

[0042] It should be noted that the first and second noise matrices can be the process noise covariance matrix Q, used to quantify the covariance matrix of the prediction error of the target motion model. It describes the uncertainty caused by imperfect or unmodeled dynamic factors during state transitions. Each element of the Q matrix is ​​the covariance between the element errors of state X.

[0043] It should be noted that the target motion model can be a motion model established by the radar system during target tracking based on the actual movement of the target. The target motion model is a mathematical model of the target's position, velocity, acceleration, and other states as they change over time. The target motion model can be a uniform motion model, assuming the target moves along a straight line at a constant speed; it can be a uniformly accelerated motion model, assuming the target moves with a constant acceleration, suitable for situations where acceleration changes are small; it can be a uniform turning model, where the target's speed and rate of rotation remain constant during turning. The target motion model can also be a first-order time-dependent model, etc., and there are no restrictions on the specific form of the target motion model.

[0044] It should be noted that the target's trajectory can be the target's actual motion model or trajectory. It can indicate the target's actual speed and position at the current moment.

[0045] In optional implementations, different events can be set, such as θ. k =1 can represent the event at time k where the target motion model and the target trajectory of the maneuvering target match. The corresponding process noise covariance matrix Q1 can be set as the first noise matrix to indicate the level of uncertainty during model matching; such as θ k =2 can represent the event at time k where the target motion model and the target trajectory of the maneuvering target do not match. The corresponding process noise covariance matrix Q2 can be set as the second noise matrix to indicate the level of uncertainty when the model does not match.

[0046] In an optional implementation, the probability of maneuvering during the target's movement is low, and the target remains in a stable state for most of the time. Therefore, the first noise matrix can be set smaller, and the second noise matrix can be set larger to indicate that the uncertainty of matching the target motion model and the target motion trajectory is small, while the uncertainty of mismatch between the target motion model and the target motion trajectory is large.

[0047] In an optional implementation, a reference process covariance matrix Q can be set. b Then the first noise matrix and the second noise matrix can be set as follows:

[0048]

[0049] Where a is a positive integer greater than 1, and c1 and c2 can both be natural numbers.

[0050] S204, calculate the first probability and the second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix and the second noise matrix, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame match, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame do not match.

[0051] It should be noted that radar systems can collect measurement data from the surrounding environment; some of this data originates from the target, while some does not. Therefore, χ² can be used to... k,i Indicates the measurement of z at time k. k,i "Originating from the goal". χ k,0 This indicates that "no measurement originates from the target at time k". Measurement data typically refers to raw observations obtained directly from sensors. These data can be continuous or discrete values, used to describe certain specific attributes or states of the observed target. In radar systems, measurement data may include: Range: The straight-line distance between the target and the radar. Velocity: The target's velocity relative to the radar, possibly measured via the Doppler effect. Azimuth and elevation angles: The target's orientation relative to the radar antenna. Reflection intensity: The intensity of the signal reflected by the target, which can be used to infer the target's size or material. Timestamp: The specific time the measurement data was acquired.

[0052] χ k,i This can represent the i-th measurement data z at time k. k,i It is directly caused by the target. This measurement data is considered to be the target's true reflection, not from background clutter or other interference sources. In a radar system, each z... k,i This could be the echo signal generated by the target at the radar receiver, including information such as distance, speed, and angle. χ k,0 This can be interpreted as meaning that at time k, no measurement data is caused by the target. In other words, at that moment, the radar does not receive any valid signal from the target; all received signals are likely clutter, interference, or noise. χ k,0 The occurrence of this event may mean that the target was not detected at that moment, or that the target's signal was masked by environmental factors (such as obstacles, multipath effects, etc.).

[0053] Figure 3 This is a schematic diagram of an optional maneuvering target tracking method according to an embodiment of this application; as shown... Figure 3 As shown, the gate can contain point cloud data and noise data related to the target.

[0054] In an optional implementation, by calculating P{θ k |Z k This can identify whether the target has maneuvered. k ={z k Z k-1} represents the measurement data from the initial time to time k. Z represents the measurement data at time k. k,i It represents the time i ∈ {1,2,…n} at time k. k} measurement data, n k The number of measurements at time k.

[0055] It should be noted that P{θ k |Z k} is given all historical measurement data Z k Under certain conditions, the probability of a match between the target motion model and the actual motion trajectory (target motion trajectory) can be calculated. By calculating the posterior probability, it can be determined whether the target's motion state has changed. Event θ k It can consist of the following mutually exclusive events:

[0056]

[0057] That is, it includes both cases where the target's measurement data originates from the target and cases where no measurement data originates from the target, in order to comprehensively assess the target's motion state.

[0058] Therefore, the probability can be calculated using the following formula:

[0059]

[0060] That is, event θ k The probability P{θ k |Z k The calculation of} can be divided into two cases, case one: event θ k The probability P{θ} of the event "no measurement originating from the target at time k" occurring simultaneously with the event "no measurement originating from the target" is... k X k,0 |Z k}; Case 2: Event θ k Measurement of z at time k of event k,i The probability of "originating from the target" occurring simultaneously.

[0061] It should be noted that P{θ k Xk,0 |Z k} can be calculated using the following formula:

[0062] P{θ k X k,0 |Z k}∝P{z k |θ k X k,0 n k Z k-1}P{n k |θ k X k,0 Z k-1}P{θ k X k,0 |Z k-1}

[0063] Where ∝ represents the proportional sign. Since all measurements within the gate are noise, then:

[0064]

[0065] Among them, V k This represents the area of ​​the gate. The gate can be understood as the continuous illumination area of ​​the radar. When using radar to detect targets, after the target is detected, the gate needs to be used to surround the target, that is, the radar continuously illuminates the selected target to obtain a continuous and complete target motion vector.

[0066] Assuming the amount of clutter within the gate follows a Poisson distribution, then:

[0067]

[0068] Where λ represents clutter density. Clutter density indicates the average number of clutter particles per unit volume or area in the radar detection space. It describes the distribution characteristics of clutter and is an important parameter for evaluating the intensity of clutter in the radar operating environment.

[0069] Use P D P represents the detection probability. G Let the gate probability be denoted by:

[0070] P{θ k , χ k,0 |Z k-1}=(1-P D P G )P{θ k |Z k-1}

[0071] Where, P{θ k |Z k-1} represents event θ kThe prior probability and detection probability refer to the probability that the system correctly determines "there is a signal" given that there is indeed a signal at the receiver. The gate probability is used to indicate the probability that the target is contained within the gate.

[0072] Alternatively, the formula for calculating the prior probability can be:

[0073]

[0074] Where, P{θ k =m|θ k-1 =i,Z k-1} represents the transition probability, m∈{1,2}, P{θ k-1 =i|Z k-1} represents event θ at time k-1. k-1 The first probability or the second probability.

[0075] It should be noted that, for case two, P{θ k , χ k，i |Z k The following formula can be used to calculate it:

[0076] P{θ k , χ k，i |Z k}∝P{z k |θ k , χ k，i n k Z k-1}P{n k |θ k , χ k，i Z k-1}

[0077] ×P{χ k，i |θ k Z k-1}P{θ k |Z k-1}

[0078] in,

[0079]

[0080]

[0081]

[0082] Wherein, p(z) k，i |θ k Z k-1 ) represents the likelihood probability.

[0083] In an optional implementation, substituting the calculation formulas for the two cases into the law of total probability yields the formula for calculating the first probability:

[0084]

[0085] The formula for calculating the second probability is:

[0086]

[0087] in,

[0088]

[0089]

[0090]

[0091]

[0092] That is, the first probability and the second probability can be calculated based on the prior probability pair and the likelihood probability pair. The following text will explain in detail how to determine the first probability and the second probability in the actual process, which will not be repeated here.

[0093] S206, if the first probability and the second probability meet the preset conditions in multiple consecutive frames, determine that the target motion trajectory does not match the target motion model, and update the parameters of the target motion model.

[0094] It should be noted that in step S204, the system has already calculated the probabilities of target matching (first probability) and non-matching (second probability) for each data frame. In S206, the system analyzes these probability sequences, paying particular attention to whether the second probability is significantly higher than the first probability in multiple consecutive frames. This indicates that the current motion model may not be able to accurately describe the true motion state of the target.

[0095] In optional implementations, the conditions typically include one or more thresholds and / or limits to determine whether the target's trajectory does not match the motion model. For example, the system may set a probability ratio threshold. When the ratio of the second probability to the first probability exceeds this threshold for multiple consecutive frames, or when the second probability itself exceeds an absolute threshold for multiple consecutive frames, the system determines that the above-mentioned preset condition is met. Once the first probability and the second probability meet the above-mentioned preset condition for multiple consecutive frames, that is, the second probability remains high, the system concludes that the target's actual trajectory does not match the current motion model. This usually means that the target has performed some kind of maneuver, such as sudden acceleration, deceleration, turning, or U-turn.

[0096] It should be noted that, in response to the target's maneuvering state, the system updates the parameters of the target motion model to improve the matching degree between the model and the target's actual motion state. This may involve adjusting the state transition matrix, process noise matrix, measurement noise matrix, etc., to reflect the target's motion characteristics after maneuvering. The updated parameters enable the tracking algorithm to more accurately predict the target's future position, thereby improving the tracking performance and safety of the radar system. Specifically, updating the target motion model parameters may employ the following strategies: adjusting the process noise matrix (Q) by increasing its value to reflect the increased uncertainty of the target's motion state; modifying the measurement noise matrix (R) to address potential changes in measurement errors during maneuvers, etc.

[0097] In this embodiment, a first noise matrix and a second noise matrix are determined. The first noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix indicates the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match. Based on a set of measurement data from multiple consecutive data frames, the first noise matrix, and the second noise matrix, a first probability and a second probability are calculated for each data frame. The first probability indicates the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability indicates the probability that the target motion model and the target motion trajectory do not match in the current data frame. If the first probability and the second probability in multiple consecutive frames meet preset conditions, it is determined that the target motion trajectory does not match the target motion model, and the parameters of the target motion model are updated. Different noise matrices are used as process noise covariance to characterize whether the target motion model and the target motion trajectory match. The first probability of a matching state and the second probability of a mismatch state are determined by combining the target position and Doppler information provided by multiple measurement data within the gate. By comparing the first probability and the second probability, it is determined whether the target has maneuvered, and tracking is performed after the target has maneuvered. The above method solves the technical problem of low resource utilization in target tracking algorithms provided by related technologies.

[0098] In an optional implementation, the above-mentioned calculation of the first probability and the second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix, and the second noise matrix includes: calculating the first probability and the second probability corresponding to the first data frame based on the measurement data set of the first data frame, the first noise matrix, and the second noise matrix, including: calculating the likelihood probability pair corresponding to each measurement data of the first data frame according to the measurement data set of the first data frame, the first noise matrix, and the second noise matrix; and calculating the first probability and the second probability corresponding to the first data frame using the initial prior probability pair and the likelihood probability pair corresponding to each measurement data of the first data frame, wherein the initial prior probability pair is used to indicate the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when no measurement data is received.

[0099] It should be noted that when starting the target motion determination, the first data set processed is the measurement data set of the first data frame. In this data frame, the specific steps for calculating the first and second probabilities are divided into two parts: 1. Calculating the likelihood probability pairs. For each measurement data point in the first data frame, the system will calculate the likelihood probability under "matching state" and "mismatching state" based on the measurement model, predicted state, first noise matrix, and second noise matrix. That is, for each measurement data point, the likelihood value is calculated under the conditions of matching and mismatching between the target motion model and the motion trajectory.

[0100] 2. Calculate the first and second probabilities using the initial prior probability and the likelihood probability. In the processing of the first data frame, it is necessary to combine the initial prior probability pair and the likelihood probability pair to calculate the first and second probabilities. The initial prior probability pair reflects the system's prior estimate of whether the target motion model matches or does not match the motion trajectory when no measurement data is received. It is usually based on the system's preset parameter settings, such as detection probability, gate probability, and expectations of the target's maneuvering behavior.

[0101] It should be noted that the initial prior probability pair is a tuple representing the matching probability and non-match probability of the target motion model and trajectory in the initial state. These probabilities are set at the beginning of the algorithm and are continuously updated in subsequent data frame processing to reflect the impact of the latest measurement data on the target state estimation.

[0102] It should be noted that once the probability pair for the first data frame is calculated, this probability pair will be used as the prior probability pair for the next data frame, and the measurement data of subsequent data frames will be processed, repeating the above process. In this way, with the processing of each data frame, the system's judgment of the target's maneuvering state will gradually become more accurate. Through the analysis of data from multiple consecutive frames, a more robust judgment can be made on the degree of matching between the target's motion trajectory and the motion model.

[0103] In an optional implementation, the above-mentioned calculation of the first probability and second probability corresponding to the k-th data frame based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix, where k is an integer greater than 1, includes: calculating the prior probability pair corresponding to the k-th data frame according to the first probability and second probability corresponding to the (k-1)-th data frame, wherein the prior probability pair is used to indicate the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when the measurement data of the k-th data frame is not received; calculating the likelihood probability pair corresponding to each measurement data of the k-th data frame according to the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix; and calculating the first probability and second probability corresponding to the k-th data frame using the prior probability pair corresponding to the k-th data frame and the likelihood probability pair corresponding to each measurement data of the k-th data frame.

[0104] As mentioned earlier, the first probability and the second probability can be determined by the prior probability pair and the likelihood probability pair. Therefore, in the k-th data frame, it is necessary to first calculate the prior probability pair and the likelihood probability pair before determining the first probability and the second probability.

[0105] It should be noted that before processing the k-th data frame, the system calculates the prior probability pair for the k-th data frame based on the first and second probabilities calculated from the (k-1)-th data frame. The prior probability pair contains the system's estimates of the probability of the target motion model matching and the probability of mismatch between the measured data and the actual motion trajectory before receiving the measurement data for the k-th data frame. After determining the prior probability pair, the system calculates the likelihood probability pair based on the measured data set of the k-th data frame, the first noise matrix, and the second noise matrix. The likelihood probability pair represents the probability of the target motion model matching and mismatching the actual target motion trajectory given the measured data. The first noise matrix and the second noise matrix represent the process noise of the target in non-maneuvering and maneuvering states, respectively, and are used to adjust for uncertainties during state transitions.

[0106] In an optional implementation, after obtaining the prior probability pair and likelihood probability pair for the k-th data frame, the system will use Bayes' theorem to calculate the posterior probability pair for that frame. This pair of probabilities represents the posterior probability (first probability) of the target motion model matching the actual target motion trajectory in the k-th data frame, and the posterior probability (second probability) of non-match.

[0107] Through the above-described embodiments of this application, each time a new data frame is processed, the prior probability of the current frame is determined using the posterior probability (first probability and second probability) of the previous frame, and the probability estimate is updated by combining the measurement data and noise matrix of the current frame. This method fully utilizes the continuity of time-series data, enabling the system to gradually learn and adapt to changes in the target's motion state. This allows for more effective identification and response to maneuvering targets in scenarios such as autonomous driving, improving the tracking performance and safety of the radar system. It enables the vehicle-mounted radar system to adjust its judgment of the target's maneuver state in real time, ensuring accurate target tracking even in complex and dynamic environments, providing crucial data support for the safe operation of autonomous vehicles.

[0108] In an optional implementation, the above-mentioned calculation of the first probability and the second probability corresponding to the k-th data frame using the prior probability pair corresponding to the k-th data frame and the likelihood probability pairs corresponding to each measurement data of the k-th data frame includes: obtaining a first parameter using the first prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, and obtaining a second parameter using the second prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, wherein the first parameter and the first prior probability correspond to the case where the target motion model and the target motion trajectory match, and the second parameter and the second prior probability correspond to the case where the target motion model and the target motion trajectory do not match; and calculating the likelihood probability pairs corresponding to each measurement data of the k-th data frame. The sum of the first likelihood probabilities is multiplied by the first prior probability corresponding to the k-th data frame to obtain the third parameter. The sum of the second likelihood probabilities in each likelihood probability pair corresponding to the measurement data of the k-th data frame is multiplied by the second prior probability corresponding to the k-th data frame to obtain the fourth parameter. The third parameter and the first likelihood probability correspond to the case where the target motion model and the target motion trajectory match, while the fourth parameter and the second likelihood probability correspond to the case where the target motion model and the target motion trajectory do not match. The ratio of the sum of the first parameter and the third parameter to the sum of the first parameter, the second parameter, and the third parameter and the fourth parameter is determined as the first probability. The ratio of the sum of the second parameter and the fourth parameter to the sum of the first parameter, the second parameter, the third parameter and the fourth parameter is determined as the second probability.

[0109] That is, the first probability and the second probability can be calculated by the following formula:

[0110]

[0111] in

[0112]

[0113]

[0114] in, The first probability of the k-th data frame. The second probability of the k-th data frame. It is one of the prior probability pairs corresponding to the k-th data frame. b is one of the likelihood probability pairs corresponding to the i-th measurement data in the k-th data frame. 0,1 b is the first parameter 0,2 b1 is the second parameter, b2 is the third parameter, and b2 is the fourth parameter.

[0115] It should be noted that the system needs to use the initialized radar parameter set and the prior probability calculated from the previous frame (the (k-1)th frame) to generate two preliminary parameters: a first parameter and a second parameter. These parameters are directly related to the matching or mismatch state of the target motion model and trajectory.

[0116] It should be noted that the first parameter indicates the system's calculation of the first parameter using the initial radar parameter set and the first prior probability when the target motion model matches the target trajectory (i.e., the target has not maneuvered). This parameter reflects the radar system's preliminary estimate of the target's motion state given the matching prior probability. Conversely, the second parameter indicates the system's calculation of the second parameter using the initial radar parameter set and the second prior probability when the target motion model does not match the target trajectory (i.e., the target may have maneuvered). The second parameter reflects the radar system's preliminary estimate of the target's motion state under the mismatch condition.

[0117] In an optional implementation, the system then calculates two more parameters—a third parameter and a fourth parameter—based on the likelihood probability pairs of all measurement data in the current frame (the k-th data frame), for use in the subsequent calculation of the first and second probabilities. The third parameter indicates the sum of the degree of matching among all measurement data when the target motion model matches the target motion trajectory. Specifically, the system adds the first likelihood probabilities of all measurement data in the current frame (i.e., the probability that the measurement data matches the predicted state in a matching state) and multiplies it by the first prior probability to obtain the third parameter. The fourth parameter is similar to the third parameter but focuses on the mismatch case; that is, it adds the second likelihood probabilities of all measurement data in the current frame (the probability that the measurement data does not match the predicted state in a mismatch case) and multiplies it by the second prior probability to obtain the fourth parameter.

[0118] In an optional implementation, the system uses the first, second, third, and fourth parameters calculated above to calculate the matching probability (first probability) and mismatch probability (second probability) of the target in the k-th data frame. The first probability indicates the likelihood of the target motion model matching the target trajectory after considering all measurement data and prior information. The first parameter represents a preliminary estimate of model matching when no measurement data is received, while the third parameter reflects the total contribution of measurement data to model matching. The sum of these two parameters, divided by the sum of all parameters, yields the final probability in the matching case. The second probability indicates the likelihood of the target motion model not matching the target trajectory. The second parameter represents a preliminary estimate in the mismatch case, while the fourth parameter reflects the total contribution of measurement data to the mismatch state. The sum of these two parameters, divided by the sum of all parameters, yields the final probability in the mismatch case.

[0119] Through the above-described embodiments of this application, the radar system can integrate previous judgments (i.e., prior probabilities) and the contribution of current measurement data (i.e., likelihood probabilities) to update the estimate of the matching degree between the target motion model and the actual motion trajectory in real time, thereby accurately determining whether the target has maneuvered. It not only considers the radar system's initial estimate when the target has not maneuvered (through the first and second parameters), but also combines the contribution of real-time measurement data (through the third and fourth parameters), ultimately determining the target's maneuvering state through probability ratio calculation. This method improves the radar system's response speed and judgment accuracy for maneuvering targets, contributing to safer and smarter vehicle driving assistance and autonomous driving functions.

[0120] In an optional implementation, the above-mentioned calculation of the likelihood probability pairs corresponding to each measurement data of the k-th data frame based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix includes: inputting the predicted state of the maneuvering target in the k-th data frame into the radar's measurement model to obtain the measurement mean, wherein the predicted state of the maneuvering target is determined according to the target motion model; obtaining the first covariance matrix and the second covariance matrix using the first noise matrix, the second noise matrix, and the predicted state of the maneuvering target corresponding to the k-th data frame; obtaining the first Gaussian distribution function based on the measurement mean and the first covariance matrix, and obtaining the second Gaussian distribution function based on the measurement mean and the second covariance matrix; and inputting the measurement data of the k-th data frame into the first Gaussian distribution function and the second Gaussian distribution function respectively to obtain the likelihood probability pairs.

[0121] It should be noted that the system can predict the target's position, velocity, and other state information in the k-th data frame based on the estimated state of the previous frame and the target motion model (such as constant velocity, constant acceleration, etc.). This predicted state reflects the target's expected position and motion characteristics under non-maneuvering conditions. The predicted state is input into the vehicle-mounted radar's measurement model, which is typically a mathematical function or model that transforms the state space (e.g., position, velocity) into the observation space (e.g., the point cloud position received by the radar). The output of the measurement model is the measurement mean, representing the expected value of the target measurement under the predicted state. Then, using the first noise matrix (corresponding to the process noise under non-maneuvering conditions) and the second noise matrix (corresponding to the process noise under maneuvering conditions), combined with the target's predicted state, the first covariance matrix and the second covariance matrix are obtained. The first covariance matrix reflects the prediction measurement uncertainty under non-maneuvering conditions, while the second covariance matrix reflects the prediction measurement uncertainty under maneuvering conditions.

[0122] In an optional implementation, a first Gaussian distribution function and a second Gaussian distribution function can be constructed based on the measurement mean and the two covariance matrices mentioned above. These two distribution functions describe the probability distribution of the measurement data given the measurement mean and covariance. The first Gaussian distribution function corresponds to the measurement data distribution in the non-maneuvering state, while the second Gaussian distribution function corresponds to the measurement data distribution in the maneuvering state. Then, each measurement data point in the k-th data frame is substituted into the first and second Gaussian distribution functions respectively to obtain two probability values: the likelihood probability of the measurement data in the non-maneuvering state and the likelihood probability of the measurement data in the maneuvering state. This likelihood probability pair reflects the degree of matching between the observed data and the predicted state and is an important input for updating the posterior probability in Bayesian inference.

[0123] Specifically, the likelihood probability can be calculated using the following formula:

[0124]

[0125] Where h(·) is the radar measurement model, X k|k-1 This represents the predicted state of the filter at time k. The covariance matrix of the predicted measurement is calculated using the following formula:

[0126]

[0127] Among them, H k Let H be the Jacobian matrix at time k. k T Representation matrix H k The transpose of P, where F is the state transition matrix of the filter, and P k-1|k-1 Let R be the state covariance matrix of the filter at time k-1. k，iFor measuring z k，i The covariance matrix of the filter, d∈[0,1] is the influence factor, and the influence of process noise in the filter on the motor recognition is adjusted.

[0128] Figure 4 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application; as shown Figure 4 As shown, the same measurement data has different likelihood values ​​under different covariances. The difference between small and large variances is quite significant.

[0129] It should be noted that the Jacobian matrix measures the model h(·) with respect to the state X. k|k-1 The derivative of can be obtained through mathematical differentiation. Specifically, if the measurement model h is a function of the state vector X, then the Jacobian matrix H is... k Each element is the partial derivative of h with respect to each element in X. In practical applications, this typically involves analytically calculating the derivative of the measurement model, or numerically approximating the derivative using finite difference methods.

[0130] The state transition matrix F describes the evolution of the system's state over time. It is typically determined based on a physical dynamic model of the system. In practical applications, F can be obtained through system identification, physical modeling, or fitting experimental data.

[0131] State covariance matrix P k-1|k-1 This describes the uncertainty in the state estimate at time k-1. It can be updated and predicted using a Bayesian filtering process. Specifically, at each time step, the filter updates the covariance matrix of the state estimate based on the new observation data. In the prediction step, P... k|k-1 Based on P k-1|k-1 It is calculated using process noise Q. In the update step, P... k|k Based on P k|k-1 It is updated with the observation noise R.

[0132] Measurement covariance matrix R k，i This describes the statistical characteristics of the measured noise. It is typically determined based on sensor specifications or experimental data. For example, if the sensor's noise characteristics are known, these characteristics can be directly used to set R. k，i In practical applications, R k，i It can be obtained through the calibration of measuring equipment, fitting of experimental data, or technical specifications provided by the manufacturer.

[0133] The influence factor d is an adjustment parameter used to adjust the impact of process noise in the filter on maneuver identification. It is typically set based on system characteristics and experimental data. In practical applications, d can be determined through system identification, experimental adjustments, or expert experience. It allows the filter to have better adaptability to different system dynamics.

[0134] Through the above-described embodiments of this application, the system can comprehensively consider the information from all measurement data, further combine prior probabilities, and use Bayesian rules to update the probability estimate of the target's current state, thereby determining whether the target has maneuvered. Overall, the above embodiments, through mathematical models, quantify the matching degree between measurement data and predicted states into likelihood probability pairs, providing a solid data foundation for subsequent probability updates and maneuver state judgments. This ensures that the vehicle-mounted radar system can accurately and promptly identify target maneuvers in complex environments, providing crucial information support for the safe operation of autonomous vehicles.

[0135] In an optional implementation, the above-mentioned calculation of the prior probability pair corresponding to the k-th data frame based on the first probability and the second probability corresponding to the (k-1)-th data frame includes: multiplying the first probability and the second probability corresponding to the (k-1)-th data frame with the transition probability matrix to obtain the prior probability pair corresponding to the k-th data frame, wherein the transition probability matrix is ​​used to indicate the probability of changes in the matching relationship between the target motion model and the target motion trajectory in the (k-1)-th and k-th data frames.

[0136] It should be noted that the transition probability matrix indicates the probability of a change in the matching state between the target motion model and the target motion trajectory between two consecutive frames of data. It is typically a two-dimensional matrix, where each row represents the matching state of the previous frame (e.g., non-maneuvering or maneuvering state), and each column represents the matching state of the current frame. The elements of the matrix represent the probability of transitioning from a certain state in the previous frame to another state in the current frame. For example, it could be a 2x2 transition probability matrix π = [π...]. ij ],in This represents the transition probability from time k-1 to time k.

[0137] In an optional implementation, as mentioned above, the target does not frequently perform maneuvers. To reflect reality, the transition probability matrix can satisfy:

[0138]

[0139] In an optional implementation, before the arrival of the kth data frame, the system calculates the prior probability pair of the kth data frame based on the first probability (the probability that the target motion model and the target motion trajectory match) and the second probability (the probability that the target motion model and the target motion trajectory do not match) corresponding to the (k-1)th data frame, as well as the aforementioned transition probability matrix.

[0140] The first and second probabilities can be combined into a probability vector, which is then updated using the transition probability matrix to obtain the prior probability vector of the k-th data frame. This update process can be achieved through matrix multiplication, as shown in the following formula:

[0141]

[0142] This calculation process combines historical data with statistical patterns of target motion changes to provide a more accurate prior estimate for judging the target's maneuvering state in the next frame. By continuously iterating this process, the system can gradually learn and adapt to the patterns of target maneuvering behavior, thereby improving the accuracy of identifying maneuvering targets.

[0143] The method described in this application, which updates prior probabilities based on historical and transition probability matrices, fully utilizes the continuity and dynamism of time-series data, ensuring that the system can adjust its estimation of target motion state in real time. In real-time target tracking and maneuver recognition in vehicle-mounted radar systems, this helps the system more accurately predict the target's possible state at the next moment, thereby optimizing the tracking algorithm parameters and improving the robustness and accuracy of the radar system in complex environments. This provides an effective mechanism for dynamically updating target maneuver state estimates for vehicle-mounted radar systems, which is crucial for realizing target tracking functions in advanced driver assistance systems (ADAS) and autonomous vehicles.

[0144] In an optional implementation, before calculating the first probability and second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix, and the second noise matrix, the following steps are included: setting initial values ​​for the radar clutter density, detection probability, and gate probability, and determining the initial values ​​of the radar clutter density, detection probability, and gate probability as the initial radar parameter set; setting the value of the transition matrix, wherein the transition matrix includes the probability that the target motion model and target motion trajectory are both in a matched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a matched state to a mismatched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a mismatched state to a matched state for two consecutive data frames, and the probability that the target motion model and target motion trajectory are both in a mismatched state for two consecutive data frames.

[0145] It should be noted that before the radar system begins operation, a set of initial parameters needs to be set. These parameters reflect the basic characteristics of the radar's operating environment and the system's prior estimates for target detection and judgment. Among these, clutter density λ measures the intensity or density of non-target source signals (i.e., clutter) in the radar's received signal, providing background information for determining whether the measured data represents a real target. Typically, clutter density estimation needs to consider factors such as the radar's operating frequency and environmental conditions (e.g., weather, terrain). Detection probability P D The gate probability P refers to the probability that a radar system correctly detects a target given that the target actually exists. It reflects the reliability of the radar's target identification and is closely related to the radar's performance parameters (such as sensitivity and resolution). G This refers to the probability that radar measurements fall within a certain threshold range of the predicted target location. This probability is used to quantify the degree of agreement between the measurement data and the predicted target location, and is crucial for correctly correlating the measurement data and the target.

[0146] In an optional implementation, an initial prior probability pair can also be determined. and And its corresponding first noise matrix Q1 and second noise matrix Q2. In practice, the target does not maneuver at the initial moment, and the initial prior probability pair can satisfy:

[0147]

[0148] Through the above-described embodiments of this application, the system can construct a probabilistic model to describe the evolution of the target's state over time. This provides a starting point for subsequent dynamic probability updates, enabling the system to gradually adjust and optimize its judgment of the target's maneuvering state based on prior knowledge of the environment and the target, thereby improving the performance and reliability of the vehicle-mounted radar system in complex environments. By reasonably setting initial parameters and the transition probability matrix, the system can more accurately identify changes in the target's motion state, providing crucial safety information for autonomous vehicles.

[0149] In an optional implementation, determining that the target motion trajectory does not match the target motion model when the first probability and the second probability in multiple consecutive frames meet the preset conditions includes: incrementing the count parameter by one when the first probability and the second probability in a data frame meet the preset conditions; resetting the count parameter to zero when the first probability and the second probability in a data frame do not meet the preset conditions; and determining that the target motion trajectory does not match the target motion model when the count parameter is greater than the count threshold.

[0150] It should be noted that the system needs to set a series of logical and numerical thresholds for subsequent judgment. These thresholds include preset conditions, counting parameters, and a counting threshold. The counting parameter is used to track the number of possible maneuvers the target may be in inertia across multiple consecutive frames of data. This parameter is incremented by one each time a possible maneuver is detected, and is reset to zero when the detection result does not support the maneuver. The threshold is a preset value used to determine whether the target has actually maneuvered. When the accumulated value of the counting parameter exceeds this threshold, the system will confirm that the target's trajectory does not match the motion model, indicating that the target has maneuvered.

[0151] In an optional implementation, for each frame of received radar measurement data, the system compares the ratio of the calculated first probability and the second probability to see if it meets a preset condition. If the ratio of the first probability to the second probability of the current frame is lower than a preset threshold, it indicates that the matching probability in that frame is lower than the mismatch probability, possibly indicating that the target has maneuvered. Based on the analysis results of the single frame data, the system updates the counting parameter. If the data of the current frame supports maneuvering indications, i.e., the ratio meets the preset condition, the counting parameter is incremented by one, indicating that the number of consecutive maneuvering indications detected has increased. Conversely, if the data of the current frame does not support maneuvering indications, the counting parameter is cleared to zero so that the detection series can restart. The accumulation of the counting parameter is key to the system's confirmation of the target's maneuvering status. When the counting parameter is greater than a preset counting threshold, it indicates that the system has continuously detected possible maneuvering indications in multiple consecutive frames of data. After a certain number of times, it is sufficient to confirm that the target's trajectory does not match the predicted motion model, i.e., the target has maneuvered.

[0152] Through the above-described embodiments of this application, the robustness and accuracy of the system in judging the target's maneuvering state are ensured by logical judgment and cumulative counting, avoiding misjudgment of target maneuvering due to accidental interference or noise in single-frame data. Through comprehensive analysis of continuous multi-frame data, the vehicle radar system can more reliably identify the target's maneuvering behavior, thereby providing more accurate target tracking and decision support for ADAS and autonomous vehicles.

[0153] In an optional implementation, the above-mentioned case where the first probability and the second probability in a data frame meet the preset conditions includes: determining that the preset conditions are met when the ratio of the first probability and the second probability is less than a preset ratio.

[0154] It should be noted that the preset ratio is a threshold value used to quantify and compare the relationship between the first probability (the probability that the target trajectory matches the motion model) and the second probability (the probability that the target trajectory does not match the motion model). This ratio is preset based on the system design requirements and the definition of the maneuver state, and usually requires extensive experiments and data analysis to determine a reasonable value to balance the sensitivity and accuracy of maneuver judgment.

[0155] In an optional implementation, when processing each frame of radar data, the system calculates the posterior probabilities of a target matching or not matching in the current frame based on Bayesian inference, namely a first probability and a second probability. The system then compares the ratio of these two probabilities to a preset ratio. If the ratio of the first probability to the second probability is less than the preset ratio, it means that the probability of a target mismatch (i.e., possible maneuvering) in the current data frame is higher than the probability of a match. This result is interpreted as the target possibly showing signs of maneuvering in the current frame. Conversely, if the ratio is greater than or equal to the preset ratio, the system considers the target to be in a non-maneuvering state in the current frame, or at least shows no obvious signs of maneuvering.

[0156] Through the above-described embodiments of this application, a quantitative standard is provided for vehicle-mounted radar systems by setting and comparing probability ratios, enabling real-time identification of target maneuvering states. The selection of the preset ratio is crucial. If the preset ratio is set too low, the system may become overly sensitive, misjudging some normal non-maneuvering states as maneuvers. Conversely, if the preset ratio is set too high, the system may become sluggish, making it difficult to detect target maneuvering behavior in a timely manner. Reasonably setting the preset ratio improves the sensitivity and accuracy of maneuver detection.

[0157] Figure 5 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application; as shown Figure 5 As shown, for target tracking, the following steps can be performed in sequence:

[0158] Step S502, initialize parameters. The parameters that need to be set are clutter density λ and detection probability P. D Gate probability P G The prior probability of event θ0 at the initial time and and their corresponding process noise covariance matrices Q1 and Q2, and the 2x2 transition probability matrix π = [π ij ],in This represents the transition probability from time k-1 to time k.

[0159] Step S504: Calculate the prior probability pair at time k. (Prior probability at time k) We can use the posterior probability at time k-1. and transition probability π ij The calculation is done using the following formula:

[0160]

[0161] Step S506: Calculate the likelihood probability pair at time k. Under the Gaussian assumption, measure z. k,i In event θ k The formula for calculating the likelihood probability under the condition = m is:

[0162]

[0163] Where h(·) is the radar measurement model, X k|k-1 This represents the predicted state of the filter at time k. The covariance matrix of the predicted measurement is calculated using the following formula:

[0164]

[0165] Among them, H k Let H be the Jacobian matrix at time k. k T Representation matrix H k The transpose of P, where F is the state transition matrix of the filter, and P k-1|k-1 Let R be the state covariance matrix of the filter at time k-1. k,i For measuring z k,i The covariance matrix of the filter, d∈[0,1] is the influence factor, and the influence of process noise in the filter on the motor recognition is adjusted.

[0166] Step S508: Calculate the first probability and the second probability at time k. The first probability and the second probability are calculated using the following formulas.

[0167]

[0168] in

[0169]

[0170]

[0171] Step S510: Determine whether the first probability and the second probability meet the preset conditions, and calculate the posterior probability ratio.

[0172] If the conditions are not met, proceed to step S512-1 to clear the count parameter to zero. If r k >G r The count parameter is cleared to zero.

[0173] If the conditions are met, execute step S512-2 to increment the counter parameter by one. If r k <G r The counting parameter is incremented by one.

[0174] Step S514: Determine whether the counting parameter is greater than the counting threshold. If it is not greater than the counting threshold, proceed to step S516-1 to determine the match between the target motion trajectory and the target motion model.

[0175] If the count exceeds the threshold, proceed to step S516-2 to determine that the target motion trajectory and the target motion model do not match.

[0176] Figure 6 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application; as shown Figure 6 As shown, the horizontal axis represents time, and the vertical axis represents the ratio of the first probability to the second probability. Figure 6 The result is from a simulation with the following parameters: sampling time of 0.1s and the target turning maneuvering at 30s.

[0177] Figure 7 This is a schematic diagram of another optional maneuvering target tracking method according to an embodiment of this application; as shown Figure 7 As shown, the horizontal axis represents time, and the vertical axis represents the ratio of the first probability to the second probability. Figure 7 The results are from 100 simulations, with a sampling time of 0.1s. The target makes a turning maneuver at 30s, and after 31s, the probability ratio drops below 1 for 3s.

[0178] In optional implementations, multiple noise matrices can be set to determine whether the target has maneuvered, or different measurement noises can be set to determine whether the target has maneuvered. Taking the setting of multiple noise matrices as an example, as mentioned above, only the first noise matrix indicates the matching state, and the second noise matrix indicates the mismatch state. The states between matching and mismatch can also be refined. For example, the first noise matrix can indicate a high degree of matching, the second noise matrix indicates matching, the third noise matrix indicates mismatch, and the fourth noise matrix indicates a large deviation, etc. The specific implementation method is similar to the aforementioned process, calculating the probability corresponding to each noise matrix, and determining the target's state based on the obtained probabilities.

[0179] In this embodiment, different noise matrices are used as process noise covariance to characterize whether there is a match between the target motion model and the target motion trajectory. The target position and Doppler information provided by multiple measurements within the gate are combined to determine a first probability of a matching state and a second probability of a mismatch state. By comparing the first and second probabilities, it is determined whether the target has maneuvered, and tracking is performed after the target has maneuvered. This method solves the technical problem of low resource utilization in target tracking algorithms provided by related technologies.

[0180] This application embodiment does not use multiple motion models, but shares a single motion model with the tracking algorithm. Therefore, it does not need to calculate and store the states and other related information of multiple motion models. Its storage requirements and computational complexity are approximately 1 / N of those of a multi-model algorithm (where N represents the number of motion models in the multi-model algorithm), thus exhibiting lower storage requirements and computational complexity. Secondly, by comprehensively considering all point cloud data within the association gate, using the likelihood probabilities provided by all point clouds and calculating the posterior probability, the proportion of the likelihood probability provided by a single clutter point is limited, and the target's maneuvering state is confirmed over multiple frames, which can effectively reduce interference from single clutter.

[0181] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0182] According to another aspect of the embodiments of this application, a mobile target tracking device for implementing the above-described mobile target tracking method is also provided. For example... Figure 8 As shown, the device includes:

[0183] The noise matrix determination unit 802 is used to determine a first noise matrix and a second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match.

[0184] The probability calculation unit 804 is used to calculate the first probability and the second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix and the second noise matrix. The first probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame match, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame do not match.

[0185] The motion judgment unit 806 is used to determine that the target motion trajectory does not match the target motion model when the first probability and the second probability meet the preset conditions in multiple consecutive frames, and to update the parameters of the target motion model.

[0186] Optionally, the probability calculation unit 804 includes: a first probability calculation module, used to calculate a first probability and a second probability corresponding to the first data frame based on the measurement data set, a first noise matrix, and a second noise matrix of the first data frame, including: calculating the likelihood probability pair corresponding to each measurement data of the first data frame according to the measurement data set, the first noise matrix, and the second noise matrix of the first data frame; calculating the first probability and the second probability corresponding to the first data frame using the initial prior probability pair and the likelihood probability pair corresponding to each measurement data of the first data frame, wherein the initial prior probability pair is used to indicate the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when no measurement data is received; a second probability calculation module, used to calculate the first probability and the second probability corresponding to the k-th data frame based on the measurement data set, the first noise matrix, and the second noise matrix of the first data frame. The data set, the first noise matrix, and the second noise matrix are used to calculate the first probability and the second probability corresponding to the k-th data frame, where k is an integer greater than 1. This includes: calculating the prior probability pair corresponding to the k-th data frame based on the first probability and the second probability corresponding to the (k-1)-th data frame, where the prior probability pair indicates the probability of the target motion model and the target motion trajectory matching and the probability of mismatch when the measurement data of the k-th data frame is not received; calculating the likelihood probability pair corresponding to each measurement data of the k-th data frame based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix; and calculating the first probability and the second probability corresponding to the k-th data frame using the prior probability pair corresponding to the k-th data frame and the likelihood probability pair corresponding to each measurement data of the k-th data frame.

[0187] Optionally, the probability calculation unit 804 includes: a first parameter calculation module, used to obtain a first parameter using the first prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, and to obtain a second parameter using the second prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, wherein the first parameter and the first prior probability correspond to the case where the target motion model and the target motion trajectory match, and the second parameter and the second prior probability correspond to the case where the target motion model and the target motion trajectory do not match; and a second parameter calculation module, used to calculate the sum of the first likelihood probabilities in the likelihood probability pairs corresponding to each measurement data of the k-th data frame and the first prior probability in the prior probability pair corresponding to the k-th data frame. The third parameter is obtained by multiplying the prior probabilities. The fourth parameter is obtained by multiplying the sum of the second likelihood probabilities of each likelihood probability pair corresponding to the measurement data of the k-th data frame with the second prior probability corresponding to the k-th data frame. The third parameter and the first likelihood probability correspond to the case where the target motion model and the target motion trajectory match, while the fourth parameter and the second likelihood probability correspond to the case where the target motion model and the target motion trajectory do not match. The probability determination module is used to determine the first probability by the ratio of the sum of the first parameter and the third parameter to the sum of the first parameter, the second parameter, and the third parameter and the fourth parameter; and to determine the second probability by the ratio of the sum of the second parameter and the fourth parameter to the sum of the first parameter, the second parameter, the third parameter and the fourth parameter.

[0188] Optionally, the probability calculation unit 804 includes: a mean calculation module, used to input the predicted state of the maneuvering target in the k-th data frame into the radar's measurement model to obtain the measurement mean, wherein the predicted state of the maneuvering target is determined according to the target motion model; a covariance matrix calculation module, used to obtain a first covariance matrix and a second covariance matrix using a first noise matrix, a second noise matrix, and the predicted state of the maneuvering target corresponding to the k-th data frame; a Gaussian distribution function calculation module, used to obtain a first Gaussian distribution function based on the measurement mean and the first covariance matrix, and to obtain a second Gaussian distribution function based on the measurement mean and the second covariance matrix; and a likelihood probability calculation module, used to input the measurement data of the k-th data frame into the first Gaussian distribution function and the second Gaussian distribution function respectively to obtain likelihood probability pairs.

[0189] Optionally, the probability calculation unit 804 includes: a prior probability calculation module, used to multiply the first probability and the second probability corresponding to the (k-1)th data frame with the transition probability matrix to obtain the prior probability pair corresponding to the kth data frame, wherein the transition probability matrix is ​​used to indicate the probability of changes in the matching relationship between the target motion model and the target motion trajectory in the (k-1)th data frame and the kth data frame.

[0190] Optionally, the aforementioned mobile target tracking device further includes: an initialization unit, configured to: set initial values ​​for the radar clutter density, detection probability, and gate probability, and determine the initial values ​​of the radar clutter density, detection probability, and gate probability as an initial radar parameter set; set the value of the transition matrix, wherein the transition matrix includes the probability that the target motion model and target motion trajectory are in a matched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a matched state to a mismatched state for two consecutive data frames, the probability that the target motion model and target motion trajectory change from a mismatched state to a matched state for two consecutive data frames, and the probability that the target motion model and target motion trajectory are in a mismatched state for two consecutive data frames.

[0191] Optionally, the aforementioned maneuver judgment unit 806 further includes: a counting module, used to increment the counting parameter by one when the first probability and the second probability in a data frame meet the preset conditions; and to clear the counting parameter to zero when the first probability and the second probability in a data frame do not meet the preset conditions; and a judgment module, used to determine that the target motion trajectory does not match the target motion model when the counting parameter is greater than the counting threshold.

[0192] Optionally, the above-mentioned counting module is further configured to: determine that a preset condition is met when the ratio of the first probability to the second probability is less than a preset ratio.

[0193] Optionally, in this embodiment, the implementation of each of the above-mentioned unit modules can be referred to the above-mentioned method embodiments, which will not be repeated here.

[0194] According to another aspect of the embodiments of this application, an electronic device for implementing the above-described maneuvering target tracking method is also provided. This electronic device may be... Figure 9 The terminal device or server shown. This embodiment uses this electronic device as an example for illustration. Figure 9 As shown, the electronic device includes a memory 902 and a processor 904. The memory 902 stores a computer program, and the processor 904 is configured to execute the steps of any of the above method embodiments through the computer program.

[0195] Optionally, in this embodiment, the aforementioned electronic device may be located in at least one of a plurality of network devices in a computer network.

[0196] Optionally, in this embodiment, the processor can be configured to perform the following steps via a computer program:

[0197] S1, determine the first noise matrix and the second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match;

[0198] S2, based on the measurement data set of multiple consecutive data frames, the first noise matrix and the second noise matrix, calculate the first probability and the second probability corresponding to each data frame, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame match, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame do not match.

[0199] S3, if the first probability and the second probability meet the preset conditions in multiple consecutive frames, determine that the target motion trajectory does not match the target motion model, and update the parameters of the target motion model.

[0200] Alternatively, as those skilled in the art will understand, Figure 9 The structure shown is for illustrative purposes only. Electronic devices can also be smartphones (such as Android phones, iOS phones, etc.), tablets, PDAs, mobile internet devices (MIDs), PADs, and other terminal devices. Figure 9 This does not limit the structure of the aforementioned electronic devices or electronic equipment. For example, electronic devices or electronic equipment may also include components that are more... Figure 9 The more or fewer components shown (such as network interfaces, etc.), or having the same Figure 9 The different configurations shown.

[0201] The memory 902 can be used to store software programs and modules, such as the program instructions / modules corresponding to the mobile target tracking method and apparatus in this embodiment. The processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, thereby realizing the aforementioned mobile target tracking method. The memory 902 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 902 may further include memory remotely located relative to the processor 904, and these remote memories can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Specifically, the memory 902 may be used, but is not limited to, for storing measurement data and other information. As an example, such as... Figure 9As shown, the memory 902 may include, but is not limited to, the noise matrix determination unit 802, the probability calculation unit 804, and the maneuver judgment unit 806 of the aforementioned maneuvering target tracking device. Furthermore, it may include, but is not limited to, other module units of the aforementioned maneuvering target tracking device, which will not be elaborated upon in this example.

[0202] Optionally, the transmission device 906 described above is used to receive or send data via a network. Specific examples of the network described above may include wired networks and wireless networks. In one example, the transmission device 906 includes a Network Interface Controller (NIC), which can be connected to other network devices and routers via a network cable to communicate with the Internet or a local area network. In another example, the transmission device 906 is a Radio Frequency (RF) module, used for wireless communication with the Internet.

[0203] In addition, the aforementioned electronic device also includes: a display 908 for displaying a simulated road scene; and a connection bus 910 for connecting the various module components in the aforementioned electronic device.

[0204] In other embodiments, the aforementioned terminal device or server can be a node in a distributed system, wherein the distributed system can be a blockchain system, which is a distributed system formed by connecting multiple nodes through network communication. The nodes can form a peer-to-peer (P2P) network, and any form of computing device, such as a server, terminal, or other electronic device, can become a node in the blockchain system by joining this peer-to-peer network.

[0205] According to one aspect of this application, a computer program product is provided, comprising a computer program / instructions containing program code for performing the methods shown in the flowchart. In such embodiments, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by a central processing unit, it performs various functions provided in embodiments of this application.

[0206] The sequence numbers of the embodiments in this application are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0207] According to one aspect of this application, a computer-readable storage medium is provided, wherein a processor of a computer device reads computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the aforementioned maneuvering target tracking method.

[0208] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0209] S1, determine the first noise matrix and the second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match;

[0210] S2, based on the measurement data set of multiple consecutive data frames, the first noise matrix and the second noise matrix, calculate the first probability and the second probability corresponding to each data frame, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame match, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory of the current data frame do not match.

[0211] S3, if the first probability and the second probability meet the preset conditions in multiple consecutive frames, determine that the target motion trajectory does not match the target motion model, and update the parameters of the target motion model.

[0212] Optionally, in this embodiment, those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0213] If the integrated units in the above embodiments are implemented as software functional units and sold or used as independent products, they can be stored in the aforementioned computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause one or more computer devices (which may be personal computers, servers, or network devices, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application.

[0214] In the above embodiments of this application, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0215] In the several embodiments provided in this application, it should be understood that the disclosed client can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0216] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0217] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0218] The above description is only a preferred embodiment of this application. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of this application, and these improvements and modifications should also be considered within the scope of protection of this application.

Claims

1. A method for tracking a maneuvering target, characterized in that, include: A first noise matrix and a second noise matrix are determined, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match; Based on the measurement data set of multiple consecutive data frames, the first noise matrix and the second noise matrix, calculate the first probability and the second probability corresponding to each data frame, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory do not match in the current data frame; If the first probability and the second probability meet the preset conditions in multiple consecutive frames, it is determined that the target motion trajectory does not match the target motion model, and the parameters of the target motion model are updated. Wherein, determining that the target motion trajectory does not match the target motion model when the first probability and the second probability meet preset conditions in multiple consecutive frames includes: If the first probability and the second probability in a data frame meet the preset conditions, the count parameter is incremented by one; If the first probability and the second probability in a data frame do not meet the preset conditions, the counting parameter is cleared to zero. If the counting parameter is greater than the counting threshold, it is determined that the target motion trajectory does not match the target motion model; Wherein, the situation where the first probability and the second probability in a data frame meet the preset conditions includes: If the ratio of the first probability to the second probability is less than a preset ratio, then the preset condition is determined to be met.

2. The method according to claim 1, characterized in that, The calculation of the first probability and second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix, and the second noise matrix includes: Based on the measurement data set of the first data frame, the first noise matrix, and the second noise matrix, the first probability and the second probability corresponding to the first data frame are calculated, including: Calculate the likelihood probability pairs corresponding to each measurement data in the first data frame based on the measurement data set of the first data frame, the first noise matrix, and the second noise matrix; The first probability and the second probability corresponding to the first data frame are calculated using the initial prior probability pair and the likelihood probability pair corresponding to each measurement data of the first data frame. The initial prior probability pair is used to indicate the probability that the target motion model and the target motion trajectory match and the probability that they do not match when no measurement data is received. Based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix, calculate the first probability and the second probability corresponding to the k-th data frame, where k is an integer greater than 1, including: The prior probability pair corresponding to the k-th data frame is calculated based on the first probability and the second probability corresponding to the (k-1)-th data frame. The prior probability pair is used to indicate the probability that the target motion model and the target motion trajectory match and the probability that they do not match when the measurement data of the k-th data frame is not received. Calculate the likelihood probability pairs corresponding to each measurement data of the kth data frame based on the measurement data set of the kth data frame, the first noise matrix, and the second noise matrix; The first probability and the second probability corresponding to the k-th data frame are calculated using the prior probability pair corresponding to the k-th data frame and the likelihood probability pair corresponding to each measurement data of the k-th data frame.

3. The method according to claim 2, characterized in that, The step of calculating the first probability and the second probability corresponding to the k-th data frame using the prior probability pair corresponding to the k-th data frame and the likelihood probability pair corresponding to each measurement data of the k-th data frame includes: A first parameter is obtained using the first prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame, and a second parameter is obtained using the second prior probability in the prior probability pair corresponding to the initial radar parameter set and the k-th data frame. The first parameter and the first prior probability correspond to the case where the target motion model and the target motion trajectory match, and the second parameter and the second prior probability correspond to the case where the target motion model and the target motion trajectory do not match. The third parameter is obtained by multiplying the sum of the first likelihood probabilities in the likelihood probability pairs corresponding to each measurement data of the k-th data frame with the first prior probability corresponding to the k-th data frame. The fourth parameter is obtained by multiplying the sum of the second likelihood probabilities in the likelihood probability pairs corresponding to each measurement data of the k-th data frame with the second prior probability corresponding to the k-th data frame. The third parameter and the first likelihood probability correspond to the case where the target motion model and the target motion trajectory match, and the fourth parameter and the second likelihood probability correspond to the case where the target motion model and the target motion trajectory do not match. The ratio of the sum of the first parameter and the third parameter to the sum of the first parameter, the second parameter, the third parameter and the fourth parameter is determined as the first probability; The ratio of the sum of the second parameter and the fourth parameter to the sum of the first parameter, the second parameter, the third parameter, and the fourth parameter is determined as the second probability.

4. The method according to claim 2, characterized in that, The step of calculating the likelihood probability pairs corresponding to each measurement data of the k-th data frame based on the measurement data set of the k-th data frame, the first noise matrix, and the second noise matrix includes: The predicted state of the maneuvering target in the kth data frame is input into the radar's measurement model to obtain the measurement mean, wherein the predicted state of the maneuvering target is determined according to the target motion model; The first covariance matrix and the second covariance matrix are obtained using the first noise matrix, the second noise matrix, and the predicted state of the maneuvering target corresponding to the kth data frame; A first Gaussian distribution function is obtained based on the measurement mean and the first covariance matrix, and a second Gaussian distribution function is obtained based on the measurement mean and the second covariance matrix. The measurement data of the kth data frame is input into the first Gaussian distribution function and the second Gaussian distribution function respectively to obtain the likelihood probability pair.

5. The method according to claim 2, characterized in that, The step of calculating the prior probability pair corresponding to the k-th data frame based on the first probability and the second probability corresponding to the (k-1)-th data frame includes: The prior probability pair corresponding to the k-1th data frame is obtained by multiplying the first probability and the second probability corresponding to the k-th data frame with the transition probability matrix, wherein the transition probability matrix is ​​used to indicate the probability of the change in the matching relationship between the target motion model and the target motion trajectory in the k-1th and k-th data frames.

6. The method according to any one of claims 1 to 5, characterized in that, Before calculating the first probability and second probability corresponding to each data frame based on the measurement data set of multiple consecutive data frames, the first noise matrix, and the second noise matrix, the process includes: Set initial values ​​for the clutter density, detection probability, and gate probability of the radar, and determine the initial values ​​for the clutter density, detection probability, and gate probability of the radar as the initial radar parameter set; The transition matrix is ​​set to include the probability that the target motion model and the target motion trajectory are in a matching state for two consecutive data frames, the probability that the target motion model and the target motion trajectory change from a matching state to a mismatched state for two consecutive data frames, the probability that the target motion model and the target motion trajectory change from a mismatched state to a matching state for two consecutive data frames, and the probability that the target motion model and the target motion trajectory are in a mismatched state for two consecutive data frames.

7. A mobile target tracking device, characterized in that, include: A noise matrix determination unit is used to determine a first noise matrix and a second noise matrix, wherein the first noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory match, and the second noise matrix is ​​used to indicate the uncertainty of the target motion model when the target motion model and the target motion trajectory do not match. The probability calculation unit is used to calculate a first probability and a second probability corresponding to each data frame based on a set of measurement data of multiple consecutive data frames, a first noise matrix and a second noise matrix, wherein the first probability is used to indicate the probability that the target motion model and the target motion trajectory match in the current data frame, and the second probability is used to indicate the probability that the target motion model and the target motion trajectory do not match in the current data frame. The motion determination unit is used to determine that the target motion trajectory does not match the target motion model when the first probability and the second probability meet preset conditions in multiple consecutive frames, and to update the parameters of the target motion model. Wherein, determining that the target motion trajectory does not match the target motion model when the first probability and the second probability meet preset conditions in multiple consecutive frames includes: If the first probability and the second probability in a data frame meet the preset conditions, the count parameter is incremented by one; If the first probability and the second probability in a data frame do not meet the preset conditions, the counting parameter is cleared to zero. If the counting parameter is greater than the counting threshold, it is determined that the target motion trajectory does not match the target motion model; Wherein, the situation where the first probability and the second probability in a data frame meet the preset conditions includes: If the ratio of the first probability to the second probability is less than a preset ratio, then the preset condition is determined to be met.

8. A computer-readable storage medium, characterized in that, The computer-readable storage medium includes a stored program, wherein the program, when executed, performs the method according to any one of claims 1 to 6.

9. A computer program product, comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the method described in any one of claims 1 to 6.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to execute the method described in any one of claims 1 to 6 through the computer program.

Images