A method, device, equipment and medium for generating a track of a vehicle-mounted radar

Abstract

The application provides a track generation method of a vehicle-mounted radar, comprising the following steps: obtaining echo data sets sent by the radar; performing point track condensation processing on the echo data sets to form point track data, wherein the point track data is divided into high-quality point track data and common point track data; performing association processing on the point track data of a current frame and track data, wherein the track data is divided into high-quality track data and common track data, the association between the high-quality point track data and the high-quality track data is preferentially performed, the track data is updated, and the updated track data is saved to a track data set; and generating a target track according to the track data set. The track generation method of the vehicle-mounted radar can effectively improve the accuracy of the generated target track.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle-mounted radars, and in particular to a method and device for generating a track of a vehicle-mounted radar, equipment and a medium. BACKGROUND

[0002] After scanning the surrounding environment, a vehicle-mounted radar generates corresponding echo data. A large number of false targets exist in the echo data. If the false targets are not removed, the tracks generated by the false targets and the tracks generated by real targets will be mixed, which results in that the real tracks cannot be obtained, the real targets cannot be obtained, and a series of subsequent applications based on the real targets are affected. SUMMARY

[0003] In view of the above-mentioned shortcomings of the prior art, the purpose of the present application is to provide a method and device for generating a track of a vehicle-mounted radar, and equipment and a medium, which can effectively improve the accuracy of the generated target track.

[0004] To achieve the above-mentioned purpose and other related purposes, the present application provides a method for generating a track of a vehicle-mounted radar, comprising: obtaining an echo data set sent by a radar;

[0005] performing a plot condensation process on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and ordinary plot data;

[0006] performing an association process on the plot data of a current frame and track data, wherein the track data is divided into high-quality track data and ordinary track data, the association of the high-quality plot data and the high-quality track data is preferentially performed, the track data is updated, and the updated track data is saved in a track data set; and

[0007] generating a target track according to the track data set.

[0008] In an embodiment of the present application, after obtaining the echo data set sent by the radar, the method further comprises judging whether the energy of each echo point in the echo data set is greater than a first energy preset value, so as to retain the echo data set. The step of judging whether the energy of each echo point in the echo data set is greater than the first energy preset value, so as to retain the echo data set, comprises:

[0009] judging whether the energy sum of each echo point in the echo data set is less than the first energy preset value;

[0010] if the energy sum is less than the first energy preset value, the echo data set is deleted;

[0011] if the energy sum is not less than the first energy preset value, the echo data set is retained.

[0012] In an embodiment of the present application, the determination of the high-quality plot data comprises:

[0013] determining whether the energy sum of each echo point contained in the plot data is greater than an energy preset value;

[0014] if the energy sum is greater than the energy preset value, the plot data is high-quality plot data;

[0015] if the energy sum is not greater than the energy preset value, the plot data is normal plot data;

[0016] and / or, determining whether the plot data is formed by condensation of no less than three echo point data;

[0017] if the plot data is formed by condensation of no less than three echo point data, the plot data is high-quality plot data;

[0018] if the plot data is formed by condensation of less than three echo point data, the plot data is normal plot data;

[0019] and / or, determining whether the radar adopts a far-near switching mode, and whether each echo point contained in the plot data includes both an echo point obtained in the far mode and an echo point obtained in the near mode;

[0020] if the plot data includes both an echo point obtained in the far mode and an echo point obtained in the near mode, the plot data is high-quality plot data;

[0021] if the plot data does not include both an echo point obtained in the far mode and an echo point obtained in the near mode, the plot data is normal plot data.

[0022] In an embodiment of the present application, the determination of the high-quality track data comprises:

[0023] if the plot data corresponding to the track data is high-quality plot data, the track data is the high-quality track data;

[0024] and / or, if the plot data corresponding to the track data is formed by condensation of two or more echo points, the track data is the high-quality track data;

[0025] and / or, if the energy sum of the plot data corresponding to the track data is greater than a second energy preset value, the track data is the high-quality track data;

[0026] and / or, if the existence time of the track data is greater than a time preset value, the track data is the high-quality track data.

[0027] In an embodiment of the present application, the step of associating the point data of the current frame with the track data, and updating the track data, and saving the updated track data into the track data set, comprises:

[0028] comparing the point data of the current frame with the track data, and determining whether the high-quality point data is associated with the high-quality track data;

[0029] if the high-quality point data is associated with the high-quality track data, updating the track data according to the point data of the current frame, and generating corresponding track data;

[0030] if the high-quality point data is not associated with the high-quality track data, determining whether the high-quality point data is associated with the normal track data;

[0031] if the high-quality point data is associated with the normal track data, updating the track data according to the point data of the current frame, and generating corresponding track data;

[0032] if the high-quality point data is not associated with the normal track data, determining whether the normal point data is associated with the high-quality track data;

[0033] if the normal point data is associated with the high-quality track data, updating the track data according to the point data of the current frame, and generating corresponding track data;

[0034] if the normal point data is not associated with the high-quality track data, determining whether the normal point data is associated with the normal track data;

[0035] if the normal point data is associated with the normal track data, updating the track data according to the point data of the current frame, and generating corresponding track data;

[0036] if the normal point data is not associated with the normal track data, performing track initiation processing on the point data of the current frame, and generating corresponding track data;

[0037] saving the updated track data into the track data set.

[0038] In an embodiment of the present application, when the high-quality point data is associated with the high-quality track data, the association threshold between the high-quality point data and the high-quality track data is greater than a normal association threshold, and the normal association threshold represents an association threshold between normal point data and normal track data.

[0039] In an embodiment of the present application, when the point data is associated with high-quality track data and common track data simultaneously, the point data is associated with the high-quality track data preferentially, when the point data is associated with multiple high-quality track data simultaneously, the point data is associated with the high-quality track data with the longest existence time, and when the point data is associated with multiple common track data simultaneously, the point data is associated with the common track data with the longest existence time.

[0040] The present application also provides a track generation device of a vehicle-mounted radar, comprising:

[0041] a data acquisition module configured to acquire a set of echo data sent by the radar;

[0042] a point condensation module configured to perform point condensation processing on the set of echo data to form point data, wherein the point data is divided into high-quality point data and common point data;

[0043] a data association module configured to associate the point data of a current frame with track data, wherein the track data is divided into high-quality track data and common track data, the association of the high-quality point data with the high-quality track data is performed preferentially to update the track data, and the updated track data is saved to a track data set; and

[0044] a track generation module configured to generate a target track according to the track data set.

[0045] The present application also provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the track generation method of the vehicle-mounted radar when executing the computer program.

[0046] The present application also provides a computer-readable storage medium storing a computer program, wherein the computer program is executable on a processor to implement the steps of the track generation method of the vehicle-mounted radar.

[0047] As described above, the present application provides a track generation method, device, equipment and medium of a vehicle-mounted radar, wherein the track of a real target is high-quality track, the point data is divided into high-quality point data and common point data, and the track data is divided into high-quality track data and common track data to distinguish the real target from the false target, thereby eliminating the false target. Meanwhile, the track association is performed by preferentially associating the high-quality point data with the high-quality track data, which can ensure that the track of the real target can exist stably and continuously for subsequent observation of the real target and other applications, and can effectively improve the accuracy of the generated target track. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required to be used in the following embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of these drawings.

[0049] Figure 1 The flow chart of the method for generating the track of the vehicle-mounted radar is shown.

[0050] Figure 2 The flow chart of the method for generating the track of the vehicle-mounted radar is shown. Figure 1 The flow chart of the method for generating the track of the vehicle-mounted radar is shown.

[0051] Figure 3 The flow chart of the method for generating the track of the vehicle-mounted radar is shown. Figure 1 The flow chart of the method for generating the track of the vehicle-mounted radar is shown.

[0052] Figure 4 The structural schematic diagram of the track generating device of the vehicle-mounted radar is shown.

[0053] Figure 5 The schematic diagram of the computer device is shown.

[0054] Figure 6 The schematic diagram of the computer device is shown.

[0055] Element number explanation:

[0056] 10, data acquisition module; 20, plot condensation module; 30, data association module; 40, track generating module 40. DETAILED DESCRIPTION

[0057] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the protection scope of the present application.

[0058] Please refer to Figure 1 As shown in the drawings, the present application provides a method for generating the track of the vehicle-mounted radar, which can be applied in the vehicle-mounted radar of the automobile to manage the running track of the automobile. The vehicle-mounted radar generally adopts the millimeter wave radar. The millimeter wave radar will mix a large amount of false data in the obtained echo data, and the false data needs to be eliminated to improve the accuracy of the generated track. The method for generating the track of the vehicle-mounted radar provided by the present application can include the following steps:

[0059] Step S10, obtaining a radar echo data set sent by the radar;

[0060] Step S20, performing a plot condensation process on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and ordinary plot data;

[0061] Step S30, performing an association process on the plot data of the current frame and the track data, wherein the track data is divided into high-quality track data and ordinary track data, the association of the high-quality plot data and the high-quality track data is preferentially performed, the track data is updated, and the updated track data is saved to a track data set; and

[0062] Step S40, generating a target track according to the track data set.

[0063] Please refer to Figure 2 In an embodiment of the present application, after step S10 is performed, a step of judging whether the energy of each echo point in the echo data set is greater than a first energy preset value can be further included to reserve the echo data set, and step S10 can include:

[0064] Step S11, obtaining a radar echo data set sent by the radar;

[0065] Step S12, judging whether the energy of each echo point in the echo data set is less than a first energy preset value;

[0066] Step S13, if the energy of each echo point in the echo data set is less than the first energy preset value, deleting the echo data set;

[0067] Step S14, if the energy of each echo point in the echo data set is not less than the first energy preset value, reserving the echo data set.

[0068] In one embodiment of the present invention, when steps S10 and S20 are executed, the radar can be a millimeter-wave radar, which can be installed on a vehicle. When the vehicle is driving and needs to scan the surrounding environment, the radar can be activated to continuously scan the surrounding environment and generate corresponding echo datasets. During the scanning process, multiple frames of echo datasets are generated. The first frame of echo dataset sent by the radar can be obtained first and represented as the echo dataset. Alternatively, a frame of echo dataset sent by the radar during operation can also be obtained and represented as the echo dataset. Then, it is necessary to determine whether the sum of the energy of each echo point in the echo dataset is less than a first preset energy value. If it is less than the first preset energy value, it indicates that the echo dataset is of poor quality and can be directly deleted to reduce unnecessary storage space and computation. If it is not less than the first preset energy value, it indicates that the echo dataset is of good quality and can be processed to form point data. The first preset energy value can be determined based on experience or multiple statistical values; for example, it can be set to 10 dB, 15 dB, or 20 dB. Dot clustering can be performed using clustering algorithms to group the acquired echo dataset. Clustering algorithms can include k-means, DBSCAN, and Euclidean clustering. A suitable clustering algorithm can be selected to perform dot clustering on the echo dataset to generate dot data.

[0069] Please see Figure 3 As shown, in one embodiment of the present invention, when step S30 is executed, the point data and track data of the current frame are associated. The track data is divided into high-quality track data and ordinary track data. High-quality point data is associated with high-quality track data first to update the track data, and the updated track data is saved to the track dataset. Specifically, step S30 may include:

[0070] Step S301: Compare the point data and track data of the current frame to determine whether the high-quality point data and the high-quality track data are related.

[0071] Step S302: If high-quality spot data is associated with high-quality track data, then update the track data according to the spot data of the current frame and generate the corresponding track data.

[0072] Step S303: If high-quality spot data and high-quality track data are not associated, then determine whether high-quality spot data and ordinary track data are associated.

[0073] Step S304: If high-quality spot data is associated with ordinary track data, then update the track data according to the spot data of the current frame and generate corresponding track data.

[0074] Step S305, if the high-quality point data is not associated with the common track data, it is judged whether the common point data is associated with the high-quality track data;

[0075] Step S306, if the common point data is associated with the high-quality track data, the track data is updated according to the point data of the current frame, and corresponding track data is generated;

[0076] Step S307, if the common point data is not associated with the high-quality track data, it is judged whether the common point data is associated with the common track data;

[0077] Step S308, if the common point data is associated with the common track data, the track data is updated according to the point data of the current frame, and corresponding track data is generated;

[0078] Step S309, if the common point data is not associated with the common track data, track initiation processing is performed on the point data of the current frame, and corresponding track data is generated;

[0079] Step S310, the updated track data is saved to the track data set.

[0080] In an embodiment of the present application, since the width and length of the target in the environment around the automobile are greater than the width of the beam, when the same target is detected by the radar, the target will be split into many echo points. The echo points of the same target are clustered, and if the target is more reliable, the greater the volume of the target, the more the number of split echo points. Therefore, when the point data is generated, it is necessary to judge whether the point data is high-quality point data and whether the track data is high-quality track data, so that the high-quality point data and the high-quality track data can be preferentially associated.

[0081] In an embodiment of the present application, the determination of the high-quality plot data can include determining whether the energy of each echo point contained in the plot data is greater than an energy preset value, if greater than the energy preset value, the plot data is high-quality plot data, if not greater than the energy preset value, the plot data is ordinary plot data, wherein the energy preset value can be confirmed according to experience or multiple statistical values, for example, can be set to 10db, can also be set to 15db, and can also be set to 20db. And / or, the determination of the high-quality plot data can also include determining whether the plot data is formed by not less than three echo point data condensation, if formed by not less than three echo point data condensation, the plot data is high-quality plot data, if formed by less than three echo point data condensation, the plot data is ordinary plot data. And / or, the determination of the high-quality plot data can also determine whether the radar adopts a far-near switching mode, whether each echo point contained in the plot data has both echo points obtained in the far mode and echo points obtained in the near mode, if both the echo points obtained in the far mode and the echo points obtained in the near mode are included, the plot data is high-quality plot data, if the echo points obtained in the far mode and the echo points obtained in the near mode are not included at the same time, the plot data is ordinary plot data.

[0082] In an embodiment of the present application, the determination of the high-quality plot data can include determining whether the energy of each echo point contained in the plot data is greater than an energy preset value, if greater than the energy preset value, the plot data is high-quality plot data, if not greater than the energy preset value, the plot data is ordinary plot data, wherein the energy preset value can be confirmed according to experience or multiple statistical values, for example, can be set to 10db, can also be set to 15db, and can also be set to 20db. And / or, the determination of the high-quality plot data can also include determining whether the plot data is formed by not less than three echo point data condensation, if formed by not less than three echo point data condensation, the plot data is high-quality plot data, if formed by less than three echo point data condensation, the plot data is ordinary plot data. And / or, the determination of the high-quality plot data can also determine whether the radar adopts a far-near switching mode, whether each echo point contained in the plot data has both echo points obtained in the far mode and echo points obtained in the near mode, if both the echo points obtained in the far mode and the echo points obtained in the near mode are included, the plot data is high-quality plot data, if the echo points obtained in the far mode and the echo points obtained in the near mode are not included at the same time, the plot data is ordinary plot data.

[0083] In one embodiment of the present application, since at least one track data is included in the track data set, the point data can be compared with any track data in the track data set to determine whether the point data is associated with the track data. When the point data is associated with a certain track data in the track data set, the track data can be updated according to the point data, and the corresponding track data is generated. Since the point data can be associated with multiple track data, the optimal track data needs to be selected for association. Since the multiple track data can include high-quality track data and normal track data, a judgment needs to be made. The point data of the current frame is compared with the track data to determine whether the high-quality point data is associated with the high-quality track data. If the high-quality point data is associated with the high-quality track data, the track data is updated according to the point data of the current frame, and the corresponding track data is generated. If the high-quality point data is not associated with the high-quality track data, it is determined whether the high-quality point data is associated with the normal track data. If the high-quality point data is associated with the high-quality track data, the track data is updated according to the point data of the current frame, and the corresponding track data is generated. If the high-quality point data is not associated with the high-quality track data, it is determined whether the normal point data is associated with the high-quality track data. If the normal point data is associated with the high-quality track data, the track data is updated according to the point data of the current frame, and the corresponding track data is generated. If the normal point data is not associated with the high-quality track data, it is determined whether the normal point data is associated with the normal track data. If the normal point data is associated with the normal track data, the track data is updated according to the point data of the current frame, and the corresponding track data is generated. If the normal point data is not associated with the normal track data, the point data of the current frame is subjected to track initiation processing, and the corresponding track data is generated. The updated track data is saved to the track data set.

[0084] In one embodiment of the present application, when the point data is associated with the high-quality track data and the normal track data at the same time, the point data is preferentially associated with the high-quality track data. When the point data is associated with multiple high-quality track data at the same time, the point data is associated with the high-quality track data with the longest existence time. When the point data is associated with multiple normal track data at the same time, the point data is associated with the normal track data with the longest existence time. When the high-quality point data is associated with the high-quality track data, the association threshold between the high-quality point data and the high-quality track data is greater than the normal association threshold, which represents the association threshold between the normal point data and the normal track data. The association threshold between the high-quality point data and the high-quality track data can be set to 1.5 to 2 times the normal association threshold.

[0085] In an embodiment of the present application, when the common point data is not associated with the common track data, track initiation processing is required for the point data of the current frame to generate corresponding track data. Specifically, the track data can be subjected to multiple extrapolation processing according to the track data history information. When the track data is common track data, X times of extrapolation processing can be performed. When the track data is high-quality track data, Y times of extrapolation processing can be performed. X < Y, for example, X can be 5, 6, 7, etc., and Y can be 9, 10, 11, etc. After X times or Y times of extrapolation processing, if the point data is still not associated with the track data, the point data is deleted until there is no data in the track data set. After the point data is deleted, the position prediction value of the track data can be used as the position of the next frame, and the track data is continuously retained for track association to generate a target track. The position prediction value is the historical speed of the track data multiplied by the time difference between two frames.

[0086] In an embodiment of the present application, when step S40 is performed, a target track is generated according to the track data set. Since the radar continuously sends the echo data set, the track data set needs to be continuously updated until the radar does not send a new echo data set or the track data set is empty. At this time, the target track data set can be obtained, and a target track is generated according to the target track data set.

[0087] It can be seen that in the above scheme, the track generated by the real target is high-quality track, the point data is divided into high-quality point data and common point data, the track data is divided into high-quality track data and common track data, the real target and the false target are distinguished, and the false target is eliminated. At the same time, by increasing the priority association of the high-quality point data and the high-quality track data in track association, the track of the real target can be as stable and continuous as possible for subsequent observation of the real target and other applications, and the accuracy of the generated target track can be effectively improved.

[0088] Referring to Figure 4 The present application also provides a track generation device of a vehicle-mounted radar, which corresponds to the track generation method of the vehicle-mounted radar in the above embodiment. The track generation device of the vehicle-mounted radar can include a data acquisition module 10, a point data condensation module 20, a data association module 30, and a track generation module 40.

[0089] In one embodiment of the present application, the data acquisition module 10 can be configured to acquire a radar transmitted echo data set, perform plot condensation on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and normal plot data, and perform association between the plot data of the current frame and track data, wherein the track data is divided into high-quality track data and normal track data, and preferentially perform association between the high-quality plot data and the high-quality track data to update the track data, and save the updated track data to a track data set, and generate a target track according to the track data set.

[0090] In one embodiment of the present application, the plot condensation module 20 can be configured to perform plot condensation on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and normal plot data.

[0091] In one embodiment of the present application, the data association module 30 can be configured to perform association between the plot data of the current frame and track data, wherein the track data is divided into high-quality track data and normal track data, and preferentially perform association between the high-quality plot data and the high-quality track data to update the track data, and save the updated track data to a track data set. Specifically, the plot data of the current frame is compared with the track data to determine whether the high-quality plot data is associated with the high-quality track data. If the high-quality plot data is associated with the high-quality track data, the track data is updated according to the plot data of the current frame to generate corresponding track data. If the high-quality plot data is not associated with the high-quality track data, it is determined whether the high-quality plot data is associated with the normal track data. If the high-quality plot data is associated with the normal track data, the track data is updated according to the plot data of the current frame to generate corresponding track data. If the high-quality plot data is not associated with the normal track data, it is determined whether the normal plot data is associated with the high-quality track data. If the normal plot data is associated with the high-quality track data, the track data is updated according to the plot data of the current frame to generate corresponding track data. If the normal plot data is not associated with the high-quality track data, it is determined whether the normal plot data is associated with the normal track data. If the normal plot data is associated with the normal track data, the track data is updated according to the plot data of the current frame to generate corresponding track data. If the normal plot data is not associated with the normal track data, the plot data of the current frame is subjected to track initiation processing to generate corresponding track data, and the updated track data is saved to the track data set.

[0092] In one embodiment of the present application, the track generation module 40 can be used to generate the target track according to the track data set. Specifically, since the radar is continuously sending the echo data set, the track data set needs to be updated continuously until the radar does not send a new echo data set or the track data set is empty. At this time, the target track data set can be obtained, and the target track can be generated according to the target track data set.

[0093] The specific limitations of the generation device can be referred to the limitations of the generation method in the above, which will not be repeated here. Each module in the above generation device can be realized by software, hardware and their combination in whole or in part. The above modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so that the processor calls and executes the operations corresponding to the above modules.

[0094] Please refer to Figure 4 As shown in the figure, the present application also provides a computer device, which can be a server. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes non-volatile and / or volatile storage medium, internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external client through the network connection. The computer program is executed by the processor to realize the function or step of the big data platform encryption and decryption processing method.

[0095] Please refer to Figure 5 As shown in the figure, the present application also provides another computer device, which can be a client. The computer device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control ability. The memory of the computer device includes non-volatile storage medium, internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the computer device is used to communicate with the external server through the network connection. The computer program is executed by the processor to realize the function or step of the big data platform encryption and decryption processing method.

[0096] In one embodiment of the present application, a computer device is provided, including a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor executes the computer program to realize the following steps:

[0097] obtain a radar echo data set transmitted by a radar;

[0098] perform a plot condensation process on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and common plot data;

[0099] perform an association process on the plot data of the current frame and track data, wherein the track data is divided into high-quality track data and common track data, the association of the high-quality plot data and the high-quality track data is preferentially performed to update the track data, and the updated track data is saved into a track data set; and

[0100] generate a target track according to the track data set.

[0101] In an embodiment of the present application, a computer readable storage medium is provided, and a computer program is stored on the computer readable storage medium. The computer program is executed by a processor to implement the following steps:

[0102] obtain a radar echo data set transmitted by a radar;

[0103] perform a plot condensation process on the echo data set to form plot data, wherein the plot data is divided into high-quality plot data and common plot data;

[0104] perform an association process on the plot data of the current frame and track data, wherein the track data is divided into high-quality track data and common track data, the association of the high-quality plot data and the high-quality track data is preferentially performed to update the track data, and the updated track data is saved into a track data set; and

[0105] generate a target track according to the track data set.

[0106] It should be noted that the functions or steps that can be achieved by the computer readable storage medium or the computer device described above can be referred to the method embodiments described above, and thus will not be described here again.

[0107] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, storage, database or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0108] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of functional units and modules is exemplified. In actual application, the above-mentioned functions can be completed by different functional units or modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the above-described functions.

[0109] In the description of the present specification, the description of the terms "the present embodiment", "example", "specific example" and the like means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In the present specification, the illustrative description of the above-mentioned terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0110] The above-disclosed embodiments of the present application are only used to help explain the present application. The embodiments do not describe all the details, nor limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the content of the present specification. The present specification selects and specifically describes these embodiments in order to better explain the principles and practical applications of the present application, so that those skilled in the art can well understand and utilize the present application. The present application is limited by the claims and their entire scope and equivalents.

Claims

1. A method for generating a flight path of a vehicle-mounted radar, characterized in that, include: Obtain the radar echo dataset; The echo dataset is subjected to point clustering processing to form point data, wherein the point data is distinguished into high-quality point data and ordinary point data. The current frame's point data and track data are associated. The track data is divided into high-quality track data and ordinary track data. The association of high-quality point data with the high-quality track data is prioritized to update the track data. The updated track data is then saved to the track dataset. Generate the target trajectory based on the trajectory dataset; Wherein, when the high-quality point data is associated with the high-quality track data, the association threshold between the high-quality point data and the high-quality track data is greater than the normal association threshold, where the normal association threshold represents the association threshold between ordinary point data and ordinary track data; the association threshold between the high-quality point data and the high-quality track data is set to 1.5 to 2 times the normal association threshold; When the point data is associated with both high-quality track data and ordinary track data, the point data is preferentially associated with the high-quality track data. When the point data is associated with multiple high-quality track data at the same time, the point data is associated with the high-quality track data that has existed for the longest time. When the point data is associated with multiple ordinary track data simultaneously, the point data is associated with the ordinary track data that has existed for the longest time.

2. The method for generating the trajectory of a vehicle-mounted radar according to claim 1, characterized in that, After acquiring the radar echo dataset, the method further includes determining whether the energy of each echo point in the echo dataset is greater than a first preset energy value, in order to retain the echo dataset. The step of determining whether the energy of each echo point in the echo dataset is greater than the first preset energy value, in order to retain the echo dataset, includes: Determine whether the sum of the energies of each echo point in the echo dataset is less than a first preset energy value; If the value is less than the first preset energy value, then delete the echo dataset; If the energy value is not less than the first preset energy value, then the echo dataset is retained.

3. The method for generating the trajectory of a vehicle-mounted radar according to claim 1, characterized in that, The determination of high-quality point data includes: Determine whether the sum of the energies of each echo point contained in the trace data is greater than a preset energy value; If the energy value is greater than the preset energy value, then the dot data is high-quality dot data; If the energy value is not greater than the preset energy value, then the dot data is ordinary dot data; And / or, determine whether the point data is formed by the aggregation of no less than three echo point data; If the trace data is formed by the aggregation of no less than three echo point data, then the trace data is high-quality trace data; If the trace data is formed by the aggregation of less than three echo point data, then the trace data is ordinary trace data; And / or, determine whether the radar adopts a near-far switching mode, and whether the echo points included in the trace data contain both echo points acquired in the far-far mode and echo points acquired in the near-far mode. If echo points acquired in both far mode and near mode are included, then the trace data is high-quality trace data. If echo points acquired in far mode and echo points acquired in near mode are not included simultaneously, then the spot data is ordinary spot data.

4. The method for generating the trajectory of a vehicle-mounted radar according to claim 1, characterized in that, The determination of high-quality flight track data includes: If the point data corresponding to the track data is high-quality point data, then the track data is the high-quality track data; And / or, if the point data corresponding to the track data is agglomerated by two or more echo points, then the track data is the high-quality track data; And / or, if the sum of the energy of the point data corresponding to the track data is greater than the second preset energy value, then the track data is the high-quality track data; And / or, if the time of the track data is longer than a preset time value, then the track data is the high-quality track data.

5. The method for generating the trajectory of a vehicle-mounted radar according to claim 1, characterized in that, The step of associating the current frame's point data with the track data, prioritizing the association of high-quality point data with high-quality track data to update the track data, and saving the updated track data to the track dataset includes: The point data and the track data of the current frame are compared to determine whether the high-quality point data and the high-quality track data are related. If the high-quality spot data is associated with the high-quality track data, then the track data is updated according to the spot data of the current frame to generate corresponding track data; If the high-quality point data is not associated with the high-quality track data, then determine whether the high-quality point data is associated with the ordinary track data; If the high-quality spot data is associated with the ordinary track data, the track data is updated according to the spot data of the current frame to generate corresponding track data; If the high-quality spot data is not associated with the ordinary track data, then determine whether the ordinary spot data is associated with the high-quality track data. If the ordinary spot data is associated with high-quality track data, the track data is updated according to the spot data of the current frame to generate corresponding track data; If the ordinary point data is not associated with the high-quality track data, then determine whether the ordinary point data is associated with the ordinary track data. If the ordinary spot data is associated with ordinary track data, the track data is updated according to the spot data of the current frame to generate corresponding track data; If the ordinary point data is not associated with the ordinary track data, then track initiation processing is performed on the point data of the current frame to generate the corresponding track data; Save the updated track data to the track dataset.

6. A device for generating the trajectory of a vehicle-mounted radar, characterized in that, The method for generating a flight path using a vehicle-mounted radar as described in any one of claims 1 to 5, wherein the generating apparatus comprises: The data acquisition module is used to acquire the echo dataset transmitted by the radar; The dot aggregation module is used to perform dot aggregation processing on the echo dataset to form dot data, wherein the dot data is divided into high-quality dot data and ordinary dot data. The data association module is used to associate the point data and track data of the current frame. The track data is divided into high-quality track data and ordinary track data. The association of high-quality point data with the high-quality track data is prioritized to update the track data, and the updated track data is saved to the track dataset. The track generation module is used to generate a target track based on the track dataset.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it performs the step of generating the track of the vehicle-mounted radar as described in any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for generating the track of the vehicle-mounted radar as described in any one of claims 1 to 5.

Images