Multi-target tracking trajectory creation and deletion method, device, equipment and storage medium

Abstract

The application relates to the technical field of intelligent driving of vehicles, in particular to a multi-target tracking trajectory creation and deletion method and device, equipment and a storage medium, wherein the method comprises the following steps: judging whether a new obstacle is detected; if the new obstacle is detected, judging whether a preset association relationship exists between the new obstacle and a current existing obstacle trajectory; if the preset association relationship does not exist between the new obstacle and the current existing obstacle trajectory, creating a potential trajectory; when the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, confirming the potential trajectory; and when the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold, deleting the potential trajectory. Thus, the problem that many obstacles are miscreated or missed created due to the rules set by people is solved, compared with a traditional algorithm, the trajectory can be reasonably created and eliminated, and the reliability and stability of the system are improved.

Description

Technical Field

[0001] This application relates to the field of intelligent driving technology for vehicles, and in particular to a method, apparatus, device, and storage medium for creating and deleting multi-target tracking trajectories. Background Technology

[0002] Intelligent driving technology is a technology that enables vehicles to perceive their surroundings and navigate without human intervention. It utilizes various technologies, including radar, laser, ultrasound, GPS (Global Positioning System), odometers, and computer vision, to perceive the surrounding environment. Through advanced computing and control systems, it identifies obstacles and various signs, and plans appropriate routes to control the vehicle's movement. Target tracking technology mainly refers to the use of computer technology or other specialized equipment and a specific algorithm to track and locate targets. It uses specific location and movement information as a basis to take corresponding processing measures.

[0003] In related technologies, the creation of the tracked target in target tracking technology largely depends on the rules selected by humans to achieve the tracking and positioning of the target.

[0004] However, the rules of this method are set manually, so they rely heavily on human subjective judgment, which can lead to the creation of many obstacles by mistake or omission, and this problem urgently needs to be solved. Summary of the Invention

[0005] This application provides a method, apparatus, device, and storage medium for creating and deleting multi-target tracking trajectories to solve the problem that many obstacles are mistakenly created or missed due to rules set by humans. Compared with traditional algorithms, it can reasonably create and eliminate trajectories, thereby improving the reliability and stability of the system.

[0006] The first aspect of this application provides a method for creating and deleting multi-target tracking trajectories, including the following steps:

[0007] Determine if a new obstacle has been detected;

[0008] If the new obstacle is detected, it is determined whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacles;

[0009] If the new obstacle does not have the preset association relationship with the existing obstacle trajectory, a new potential trajectory is created. When the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, the potential trajectory is confirmed. When the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold, the potential trajectory is deleted.

[0010] According to one embodiment of this application, after determining whether the new obstacle and the trajectory of the existing obstacle have the preset association relationship, the method further includes:

[0011] If the new obstacle has the preset association relationship with the existing obstacle trajectory, then the logarithm of the existence probability of the existing obstacle trajectory is updated based on the first preset update strategy.

[0012] According to one embodiment of this application, the first preset update strategy is:

[0013] LLR 更新后 =LLR 更新前 +LLR object +log(P D / λ clutter );

[0014] LLR object = -0.5*(z-Hx) T *S -1 *(z-Hx)-D*log(2*π) / 2-0.5*log(|S|);

[0015] S = HPH T +R;

[0016] Among them, LLR 更新前 and LLR 更新后 Both are the logarithms of the existing probability of the existence of the obstacle trajectory, λ clutter P represents the probability of noise generation in the current detection area. D Let x be the probability that an obstacle is detected, D be the dimension of the state vector x, |S| be the determinant of matrix S, x be the state vector, z be the observation vector, H be the observation matrix, and R be the observation noise.

[0017] According to one embodiment of this application, after determining that the new obstacle and the trajectory of the existing obstacle do not have the preset association relationship, the method further includes:

[0018] The logarithm of the probability of the existence of the existing obstacle trajectory is updated based on the second preset update strategy.

[0019] According to one embodiment of this application, the second preset update strategy is:

[0020] LLR 更新后 =LLR 更新前 +log((1-P D ) / λ clutter ).

[0021] The multi-target tracking trajectory creation and deletion method proposed in this application creates a potential trajectory when there is no preset association between the new obstacle and the existing obstacle trajectory. The potential trajectory is confirmed when the logarithm of its existence probability is greater than a preset upper threshold, and deleted when the logarithm of its existence probability is less than a preset lower threshold. This solves the problem of manually set rules leading to the erroneous or missed creation of many obstacles. Compared to traditional algorithms, it can reasonably create and eliminate trajectories, improving the reliability and stability of the system.

[0022] A second aspect of this application provides a multi-target tracking trajectory creation and deletion apparatus, comprising:

[0023] The first judgment module is used to determine whether a new obstacle has been detected.

[0024] The second judgment module is used to determine whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacle when the new obstacle is detected.

[0025] The processing module is configured to create a new potential trajectory if there is no preset association between the new obstacle and the existing obstacle trajectory, confirm the potential trajectory if the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, and delete the potential trajectory if the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold.

[0026] According to one embodiment of this application, after determining whether the new obstacle and the trajectory of the existing obstacle have the preset association relationship, the second determining module is further configured to:

[0027] If the new obstacle has the preset association relationship with the existing obstacle trajectory, then the logarithm of the existence probability of the existing obstacle trajectory is updated based on the first preset update strategy.

[0028] According to one embodiment of this application, the first preset update strategy is:

[0029] LLR 更新后 =LLR 更新前 +LLR object +log(P D / λ clutter );

[0030] LLR object = -0.5*(z-Hx) T *S -1 *(z-Hx)-D*log(2*π) / 2-0.5*log(|S|);

[0031] S = HPHT +R;

[0032] Among them, LLR 更新前 and LLR 更新后 Both are the logarithms of the existing probability of the existence of the obstacle trajectory, λ clutter P represents the probability of noise generation in the current detection area. D Let x be the probability that an obstacle is detected, D be the dimension of the state vector x, |S| be the determinant of matrix S, x be the state vector, z be the observation vector, H be the observation matrix, and R be the observation noise.

[0033] According to one embodiment of this application, after determining that the new obstacle and the trajectory of the existing obstacle do not have the preset association relationship, the second determining module is further configured to:

[0034] The logarithm of the probability of the existence of the existing obstacle trajectory is updated based on the second preset update strategy.

[0035] According to one embodiment of this application, the second preset update strategy is:

[0036] LLR 更新后 =LLR 更新前 +log((1-P D ) / λ clutter ).

[0037] The multi-target tracking trajectory creation and deletion device proposed in this application creates a potential trajectory when it determines that there is no preset association between the new obstacle and the existing obstacle trajectory. The potential trajectory is confirmed when the logarithm of its existence probability is greater than a preset upper threshold, and deleted when the logarithm of its existence probability is less than a preset lower threshold. This solves the problem of manually set rules leading to the erroneous or missed creation of many obstacles. Compared to traditional algorithms, it can reasonably create and eliminate trajectories, improving the reliability and stability of the system.

[0038] A third aspect of this application provides an electronic device, including: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the multi-target tracking trajectory creation and deletion method as described in the above embodiments.

[0039] A fourth aspect of this application provides a computer-readable storage medium having a computer program stored thereon, which is executed by a processor to implement the multi-target tracking trajectory creation and deletion method as described in the above embodiments.

[0040] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description

[0041] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:

[0042] Figure 1 This is a flowchart of a method for creating and deleting multi-target tracking trajectories according to an embodiment of this application;

[0043] Figure 2 This is a flowchart of a novel obstacle detection and creation method according to an embodiment of this application;

[0044] Figure 3 This is a flowchart of an existing trajectory preservation or deletion method according to an embodiment of this application;

[0045] Figure 4 This is a block diagram of a multi-target tracking trajectory creation and deletion device according to an embodiment of this application;

[0046] Figure 5 This is a schematic diagram of the structure of an electronic device according to an embodiment of this application. Detailed Implementation

[0047] The embodiments of this application are described in detail below. Examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.

[0048] The following describes a method, apparatus, device, and storage medium for creating and deleting multi-target tracking trajectories according to embodiments of this application, with reference to the accompanying drawings. Addressing the problem mentioned in the background art where manually set rules lead to the erroneous or missed creation of many obstacles, this application provides a method for creating and deleting multi-target tracking trajectories. In this method, when it is determined that a new obstacle does not have a preset association with existing obstacle trajectories, a new potential trajectory is created. If the logarithm of the probability of existence of a potential trajectory is greater than a preset upper threshold, the potential trajectory is confirmed. If the logarithm of the probability of existence of a potential trajectory is less than a preset lower threshold, the potential trajectory is deleted. This solves the problem of erroneous or missed creation of many obstacles due to manually set rules. Compared to traditional algorithms, it can reasonably create and eliminate trajectories, improving the reliability and stability of the system.

[0049] Specifically, Figure 1This is a flowchart illustrating a method for creating and deleting multi-target tracking trajectories provided in an embodiment of this application.

[0050] like Figure 1 As shown, the method for creating and deleting multi-target tracking trajectories includes the following steps:

[0051] In step S101, it is determined whether a new obstacle has been detected.

[0052] Obstacle detection can be achieved using relevant technologies, such as lidar detection technology. Lidar detection technology is a radar system that uses laser beams to detect the position, velocity, and other characteristics of a target. Its working principle is to emit a detection signal (laser beam) towards the target, and then compare the received signal reflected back from the target (target echo) with the emitted signal. After appropriate processing, relevant information about the target can be obtained, such as the target's distance, azimuth, altitude, speed, attitude, and even shape parameters, thereby enabling the detection, tracking, and identification of targets such as aircraft and missiles.

[0053] In step S102, if a new obstacle is detected, it is determined whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacle.

[0054] It is understandable that if the radar detection technology detects a new obstacle, the embodiments of this application can set the obstacle (object) detected by the radar in each frame as O [O1, O2...], set the current existing obstacle trajectory (track) as T, and determine whether there is a preset correlation between the new obstacle and the current existing obstacle trajectory.

[0055] Furthermore, in some embodiments, after determining whether there is a preset association between the new obstacle and the existing obstacle trajectory, the method further includes: if there is a preset association between the new obstacle and the existing obstacle trajectory, then updating the logarithm of the existence probability of the existing obstacle trajectory based on the first preset update strategy.

[0056] Specifically, there are multiple methods to determine whether there is a pre-defined correlation between the trajectory of a new obstacle and the trajectory of an existing obstacle. For example, one can determine the Mahalanobis distance between the predicted observation vector Hx obtained from the state matrix of the existing obstacles and the actual observation result z, i.e., dis = (z - Hx). T S(z-Hx), if this distance is less than a certain value, it is considered that the new obstacle has a preset correlation with the trajectory of the existing obstacle.

[0057] Furthermore, in this embodiment, a parameter LLR is set for each track, which is the logarithm of the existence probability of the current track, with an initial value of LLR = log(λ). new / λ clutter ), where λnew This represents the probability of a new obstacle being generated in the current detection area. If a newly detected obstacle has a preset association with a track (i.e., the association is successful), the logarithm of the existence probability of the existing obstacle trajectory is updated based on the first preset update strategy.

[0058] In some embodiments, the first preset update strategy is:

[0059] LLR 更新后 =LLR 更新前 +LLR object +log(P D / λ clutter );

[0060] LLR object = -0.5*(z-Hx) T *S -1 *(z-Hx)-D*log(2*π) / 2-0.5*log(|S|);

[0061] S = HPH T +R;

[0062] Among them, LLR 更新前 and LLR 更新后 Both are the logarithms of the existing probability of the existence of obstacle trajectories, λ clutter P represents the probability of noise generation in the current detection area. D Let x be the probability that an obstacle is detected, D be the dimension of the state vector x, |S| be the determinant of matrix S, x be the state vector, z be the observation vector, H be the observation matrix, and R be the observation noise.

[0063] In addition, in some embodiments, after determining that there is no preset association between the new obstacle and the existing obstacle trajectory, the method further includes: updating the logarithm of the existence probability of the existing obstacle trajectory based on a second preset update strategy.

[0064] Specifically, if a newly detected obstacle does not have a preset association with a track (i.e., a track is not successfully associated with any object in the current frame), the logarithm of the existence probability of the existing obstacle trajectory is updated based on the second preset update strategy.

[0065] In some embodiments, the second preset update strategy is:

[0066] LLR 更新后 =LLR 更新前 +log((1-P D ) / λ clutter ).

[0067] It can be understood that the embodiment of the present application is based on a mathematical probability distribution method to statistically calculate the probability of the existence of obstacles. By continuously superimposing the probabilities of obstacles in each frame, the existence probability of the current trajectory is calculated, avoiding the uncertain influence of the logic of artificial creation and elimination on the entire multi-target tracking system.

[0068] In step S103, if there is no preset association relationship between the new obstacle and the current existing obstacle trajectory, a new potential trajectory is created. When the logarithm of the existence probability of the potential trajectory is greater than the preset upper threshold, the potential trajectory is confirmed; when the logarithm of the existence probability of the potential trajectory is less than the preset lower threshold, the potential trajectory is deleted.

[0069] It can be understood that after the embodiment of the present application determines that there is no preset association relationship between the new obstacle and the current existing obstacle trajectory, a new potential trajectory can be created, and the false positive rate and false negative rate are set at the same time. When the existence probability of the potential trajectory meets certain conditions, the potential trajectory is selected and confirmed or deleted.

[0070] Specifically, the embodiment of the present application can set the tolerance ratio of False Positive (false positive) to be p. If LLR < p / (1 - p) (that is, the logarithm of the existence probability of the potential trajectory is less than the preset lower threshold), then this track (that is, the potential trajectory) needs to be deleted; if LLR > (1 - p) / p (that is, the logarithm of the existence probability of the potential trajectory is greater than the preset upper threshold), then this track can be confirmed as the track of the obstacle, that is, the potential trajectory is confirmed.

[0071] To facilitate those skilled in the art to further understand the multi-target tracking trajectory creation and deletion method proposed in the embodiment of the present application, the following is combined with Figure 2 and Figure 3 for further illustration.

[0072] As Figure 2 shown, Figure 2 is a flowchart of a new detected obstacle creation method according to an embodiment of the present application. The method includes the following steps:

[0073] Step S201, a new obstacle is detected.

[0074] Step S202, (judge) whether it is associated with the existing trajectory.

[0075] If so, execute step S203 to update the LLR of the existing trajectory.

[0076] If not, execute step S204 to create a new potential trajectory and initialize the LLR.

[0077] Step S205, (judge) whether the LLR is greater than the upper threshold.

[0078] If so, proceed to step S206 to confirm the trajectory.

[0079] If not, proceed to step S207 to determine whether the LLR is less than the lower threshold.

[0080] If so, proceed to step S208 to delete the potential trajectory;

[0081] If not, proceed to step S209 and continue waiting for the next result.

[0082] like Figure 3 As shown, Figure 3 This is a flowchart of an existing trajectory preservation or deletion method according to an embodiment of this application, the method including the following steps:

[0083] Step S301: The current trajectory already exists.

[0084] Step S302, (determine) whether it is associated with a new obstacle.

[0085] If so, proceed to step five, S303, to update the LLR of the existing trajectory.

[0086] If not, proceed to step S304 to update the LLR as if no obstacle is associated.

[0087] Step S305, (determine) whether LLR is less than the lower threshold.

[0088] If so, proceed to step S306 to delete the trajectory.

[0089] If not, proceed to step S307 to maintain the trajectory.

[0090] The multi-target tracking trajectory creation and deletion method proposed in this application involves creating a potential trajectory when there is no preset association between the new obstacle and the existing obstacle trajectory. The potential trajectory is confirmed when the logarithm of its existence probability is greater than a preset upper threshold, and deleted when the logarithm is less than a preset lower threshold. This solves the problem of manually set rules leading to the erroneous or missed creation of many obstacles. Compared to traditional algorithms, it can reasonably create and eliminate trajectories, improving the reliability and stability of the system.

[0091] Next, referring to the accompanying drawings, a multi-target tracking trajectory creation and deletion apparatus according to an embodiment of this application is described.

[0092] Figure 4 This is a block diagram of a multi-target tracking trajectory creation and deletion device according to an embodiment of this application.

[0093] like Figure 4As shown, the multi-target tracking trajectory creation and deletion device 10 includes: a first judgment module 100, a second judgment module 200, and a processing module 300.

[0094] The first judgment module 100 is used to determine whether a new obstacle has been detected.

[0095] The second judgment module 200 is used to determine whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacle when a new obstacle is detected.

[0096] The processing module 300 is used to create a new potential trajectory if there is no preset association between the new obstacle and the existing obstacle trajectory, and to confirm the potential trajectory when the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, and to delete the potential trajectory when the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold.

[0097] Furthermore, in some embodiments, after determining whether there is a preset correlation between the trajectory of the new obstacle and the trajectory of the existing obstacle, the second determination module 200 is further configured to:

[0098] If a new obstacle has a preset association with the trajectory of an existing obstacle, then the logarithm of the probability of the existence of the existing obstacle trajectory is updated based on the first preset update strategy.

[0099] Furthermore, in some embodiments, the first preset update strategy is:

[0100] LLR 更新后 =LLR 更新前 +LLR object +log(P D / λ clutter );

[0101] LLR object = -0.5*(z-Hx) T *S -1 *(z-Hx)-D*log(2*π) / 2-0.5*log(|S|);

[0102] S = HPH T +R;

[0103] Among them, LLR 更新前 and LLR 更新后 Both are the logarithms of the existing probability of the existence of obstacle trajectories, λ clutter P represents the probability of noise generation in the current detection area. D Let x be the probability that an obstacle is detected, D be the dimension of the state vector x, |S| be the determinant of matrix S, x be the state vector, z be the observation vector, H be the observation matrix, and R be the observation noise.

[0104] Furthermore, in some embodiments, after determining that there is no preset correlation between the new obstacle and the trajectory of the existing obstacle, the second determination module 200 is further configured to:

[0105] The logarithm of the probability of the existence of existing obstacle trajectories is updated based on the second preset update strategy.

[0106] Furthermore, in some embodiments, the second preset update strategy is:

[0107] LLR 更新后 =LLR 更新前 +log((1-P D ) / λ clutter ).

[0108] It should be noted that the foregoing explanation of the multi-target tracking trajectory creation and deletion method embodiment also applies to the multi-target tracking trajectory creation and deletion device of this embodiment, and will not be repeated here.

[0109] The multi-target tracking trajectory creation and deletion device proposed in this application creates a potential trajectory when it determines that there is no preset association between the new obstacle and the existing obstacle trajectory. The potential trajectory is confirmed when the logarithm of its existence probability is greater than a preset upper threshold, and deleted when the logarithm of its existence probability is less than a preset lower threshold. This solves the problem of manually set rules leading to the erroneous or missed creation of many obstacles. Compared to traditional algorithms, it can reasonably create and eliminate trajectories, improving the reliability and stability of the system.

[0110] Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device may include:

[0111] The memory 501, the processor 502, and the computer program stored on the memory 501 and capable of running on the processor 502.

[0112] When the processor 502 executes the program, it implements the multi-target tracking trajectory creation and deletion method provided in the above embodiments.

[0113] Furthermore, electronic devices also include:

[0114] Communication interface 503 is used for communication between memory 501 and processor 502.

[0115] The memory 501 is used to store computer programs that can run on the processor 502.

[0116] The memory 501 may include high-speed RAM (Random Access Memory) memory, and may also include non-volatile memory, such as at least one disk storage.

[0117] If the memory 501, processor 502, and communication interface 503 are implemented independently, then the communication interface 503, memory 501, and processor 502 can be interconnected via a bus to complete communication between them. The bus can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 5 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0118] Optionally, in a specific implementation, if the memory 501, processor 502, and communication interface 503 are integrated on a single chip, then the memory 501, processor 502, and communication interface 503 can communicate with each other through an internal interface.

[0119] Processor 502 may be a CPU (Central Processing Unit), an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits configured to implement embodiments of this application.

[0120] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for creating and deleting multi-target tracking trajectories.

[0121] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0122] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0123] Any process or method described in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more N executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.

[0124] It should be understood that the various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, the N steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (FPGAs), field-programmable gate arrays (FPGAs), etc.

[0125] Those skilled in the art will understand that all or part of the steps of the methods described in the above embodiments can be implemented by a program instructing related hardware, and the program can be stored in a computer-readable storage medium. When executed, the program includes one or a combination of the steps of the method embodiments.

[0126] Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of this application.

Claims

1. A method for creating and deleting multi-target tracking trajectories, characterized in that, Includes the following steps: Determine if a new obstacle has been detected; If the new obstacle is detected, it is determined whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacles; as well as If the new obstacle does not have the preset association relationship with the existing obstacle trajectory, a new potential trajectory is created. When the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, the potential trajectory is confirmed. When the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold, the potential trajectory is deleted. After determining whether the new obstacle and the trajectory of the existing obstacle have the preset correlation relationship, the method further includes: If the new obstacle has the preset association relationship with the existing obstacle trajectory, then the logarithm of the existence probability of the existing obstacle trajectory is updated based on the first preset update strategy; After determining that the new obstacle does not have the preset correlation with the trajectory of the existing obstacle, the method further includes: The logarithm of the existence probability of the current obstacle trajectory is updated based on the second preset update strategy; Determine the Mahalanobis distance between the predicted observation vector Hx obtained from the state matrix of the existing obstacles and the actual observation result z. If the Mahalanobis distance is less than a certain value, it is determined that the new obstacle and the trajectory of the existing obstacles have a preset correlation relationship. After creating the potential trajectory, the method further includes: setting an initial value for the logarithm of the initial existence probability of the potential trajectory, wherein the initial value is configured to make the potential trajectory be in a pending confirmation state after initialization.

2. The method according to claim 1, characterized in that, The first preset update strategy is: ； ； ； in, LLR 更新前 and LLR 更新后 Each of these is the logarithm of the probability of the existence of the currently existing obstacle trajectory. This represents the probability of noise generation in the current detection area. This represents the probability that the obstacle is detected. D State vector x dimensionality It is a matrix S The value of the determinant, x For state vectors, z For the observation vector, H For the observation matrix, R To observe noise.

3. The method according to claim 2, characterized in that, The second preset update strategy is: 。 4. A device for creating and deleting multi-target tracking trajectories, characterized in that, include: The first judgment module is used to determine whether a new obstacle has been detected. The second judgment module is used to determine whether there is a preset correlation between the new obstacle and the trajectory of the existing obstacle when the new obstacle is detected. as well as The processing module is configured to create a new potential trajectory when there is no preset association between the new obstacle and the existing obstacle trajectory, and to confirm the potential trajectory when the logarithm of the existence probability of the potential trajectory is greater than a preset upper threshold, and to delete the potential trajectory when the logarithm of the existence probability of the potential trajectory is less than a preset lower threshold. After determining whether the new obstacle and the trajectory of the existing obstacle have the preset correlation relationship, the second determination module is further configured to: If the new obstacle has the preset association relationship with the existing obstacle trajectory, then the logarithm of the existence probability of the existing obstacle trajectory is updated based on the first preset update strategy; After determining that the new obstacle does not have the preset correlation with the trajectory of the existing obstacle, the method further includes: The logarithm of the existence probability of the current obstacle trajectory is updated based on the second preset update strategy; Determine the Mahalanobis distance between the predicted observation vector Hx obtained from the state matrix of the existing obstacles and the actual observation result z. If the Mahalanobis distance is less than a certain value, it is determined that the new obstacle and the trajectory of the existing obstacles have a preset correlation relationship. After creating the potential trajectory, the method further includes: setting an initial value for the logarithm of the initial existence probability of the potential trajectory, wherein the initial value is configured to make the potential trajectory be in a pending confirmation state after initialization.

5. The apparatus according to claim 4, characterized in that, The first preset update strategy is: ； ； ； in, LLR 更新前 and LLR 更新后 Each of these is the logarithm of the probability of the existence of the currently existing obstacle trajectory. This represents the probability of noise generation in the current detection area. This represents the probability that the obstacle is detected. D State vector x dimensionality It is a matrix S The value of the determinant, x For state vectors, z For the observation vector, H For the observation matrix, R To observe noise.

6. An electronic device, characterized in that, include: The memory, the processor, and the computer program stored in the memory and executable on the processor, the processor executing the program to implement the multi-target tracking trajectory creation and deletion method as described in any one of claims 1-3.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, The program is executed by the processor to implement the multi-target tracking trajectory creation and deletion method as described in any one of claims 1-3.

Images