A millimeter wave radar target tracking method, device, equipment and storage medium

Abstract

The application discloses a millimeter wave radar target tracking method, device and equipment and a storage medium. The method comprises the following steps: according to a plurality of types of target rectangular frames, target point information output by a millimeter wave radar is classified to determine the type of the target point information output by the millimeter wave radar; a target point in the target point type is taken as a first coordinate, and target points output by the millimeter wave radar in real time are converted to the first coordinate system to determine the pose change of the target points output by the millimeter wave radar relative to the first coordinate; according to the pose change of the target points output by the millimeter wave radar relative to the first coordinate, a moving track of the target points is drawn, and whether the target points belong to the same object is judged; target points of the same object are linked to generate a target envelope track, and a target vehicle is tracked through the target envelope track. The application can improve the timeliness of risk target judgment.

Description

Technical Field

[0001] This invention relates to the field of autonomous driving technology, and in particular to a millimeter-wave radar target tracking method, apparatus, device, and storage medium. Background Technology

[0002] With the continuous improvement of automotive electronics and intelligence, advanced driver assistance systems (ADAS) are receiving increasing attention from automakers and consumers, as these functions play a crucial role in enhancing vehicle driving safety. Millimeter-wave radar, as an all-weather road target detection sensor, features high operating frequency, short wavelength, small antenna size, and strong environmental adaptability. It can effectively detect target distance, relative speed, and azimuth, providing stable sensor-level target data for the development of ADAS functions.

[0003] Current automotive millimeter-wave radar systems can track and scan target vehicles within a certain range. However, existing millimeter-wave radar tracking relies on data accuracy and is easily affected by test noise, resulting in poor target tracking accuracy.

[0004] Therefore, how to accurately track targets using millimeter-wave radar is a technical problem that urgently needs to be solved. Summary of the Invention

[0005] The main objective of this invention is to provide a millimeter-wave radar target tracking method, device, equipment, and storage medium that can eliminate the influence of abnormal data within a period, while reducing the number of target points that need to be processed, so as to facilitate rapid processing of target points, speed up software operation efficiency, and improve the timeliness of risk target judgment.

[0006] In a first aspect, this application provides a millimeter-wave radar target tracking method, which includes the following steps: Based on multiple preset target rectangles, the target point information output by the millimeter-wave radar is classified to determine the target point type output by the millimeter-wave radar. The vehicle's pose corresponding to one of the target points of the target point type is used as the first coordinate, and the target point output by the millimeter-wave radar in real time is transformed to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate. Based on the pose change of the target point relative to the first coordinate in real time output by the millimeter-wave radar, the movement trajectory of the target point is plotted, and it is determined whether the target point belongs to the same object. Target points of the same object are linked together to generate a target envelope trajectory, and the target vehicle is tracked using the target envelope trajectory.

[0007] In conjunction with the first aspect above, as an optional implementation, the target point is compared with the target point type output by the millimeter-wave radar according to the movement trajectory of the target point. When the overlap rate of the two is greater than a preset value, it is determined that the target points in the target point type belong to the same object. When the overlap rate between the two is less than a preset value, it is determined that the target points in the target point type do not belong to the same object.

[0008] In conjunction with the first aspect mentioned above, as an optional implementation method, the trajectory overlap ratio between different objects is judged. If it is greater than a set value and the relative distance is less than a preset safety distance, they are determined to be different scanning points of the same object.

[0009] In conjunction with the first aspect mentioned above, as an optional implementation, the first target point in the target point type is taken as the first coordinate origin; Based on the vehicle's speed, yaw angle, and steering wheel angle at each moment, calculate the vehicle's attitude update matrix relative to the first coordinate origin; The target point output by the millimeter-wave radar in real time is transformed to the coordinate system corresponding to the first coordinate origin through the attitude update matrix, so as to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate system.

[0010] In conjunction with the first aspect mentioned above, as an optional implementation method, the relative distance between the first target point in the target point type and the surrounding target points is calculated, and it is determined whether the relative distance is less than a preset rectangle. When the relative distance is less than the set rectangle, the first target point is associated with the surrounding target points; When the relative distance is greater than the set rectangle, the first target point is taken as a new target point type, wherein the new target point type is one of a set of preset types.

[0011] In conjunction with the first aspect mentioned above, as an optional implementation method, the preset multiple target rectangles include: motor vehicle rectangle, non-motor vehicle rectangle, and pedestrian rectangle; When the millimeter-wave radar outputs target point information, the type of the target point output by the radar is determined by the RCS value.

[0012] In conjunction with the first aspect mentioned above, as an optional implementation, when the RCS value of the radar output target point is less than a first set threshold, it is classified as an object of the same category. When the RCS value of the radar output target point is greater than the first preset threshold, the velocity of the radar output target point is determined; When the speed of the target point output by the radar is greater than the set speed, it is classified into different categories of objects.

[0013] Secondly, this application provides a millimeter-wave radar target tracking device, the device comprising: The classification module is used to classify the target point information output by the millimeter-wave radar according to multiple preset target rectangles in order to determine the target point type output by the millimeter-wave radar. The determination module is used to take the vehicle pose corresponding to a target point of the target point type as the first coordinate and convert the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate. The judgment module is used to draw the movement trajectory of the target point based on the pose change of the target point relative to the first coordinate in real time output by the millimeter-wave radar, and to determine whether the target point belongs to the same object. The processing module is used to link target points of the same object to generate a target envelope trajectory, and to track the target vehicle through the target envelope trajectory.

[0014] Thirdly, this application also provides an electronic device, the electronic device comprising: a processor; and a memory storing computer-readable instructions, which, when executed by the processor, implement the method described in any one of the first aspects.

[0015] Fourthly, this application also provides a computer-readable storage medium storing computer program instructions that, when executed by a computer, cause the computer to perform the method described in any of the first aspects.

[0016] This application provides a millimeter-wave radar target tracking method, apparatus, device, and storage medium. The method includes the following steps: classifying target point information output by the millimeter-wave radar according to multiple preset target bounding boxes to determine the target point type output by the millimeter-wave radar; using the vehicle pose corresponding to a target point of one of the target point types as a first coordinate, and transforming the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate; drawing the movement trajectory of the target point based on the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate, and determining whether the target point belongs to the same object; linking target points of the same object to generate a target envelope trajectory, and tracking the target vehicle through the target envelope trajectory. This application can eliminate the influence of abnormal data within the period, and at the same time reduce the number of target points that need to be processed, so as to facilitate rapid processing of target points, speed up software operation efficiency, and improve the timeliness of risk target judgment.

[0017] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit the invention. Attached Figure Description

[0018] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0019] Figure 1 This is a flowchart of a millimeter-wave radar target tracking method provided in the embodiments of this application; Figure 2 This is a schematic diagram of a millimeter-wave radar target tracking device provided in the embodiments of this application; Figure 3 This is a schematic diagram of an electronic device provided in an embodiment of this application; Figure 4 This is a schematic diagram of a computer-readable program medium provided in an embodiment of this application. Detailed Implementation

[0020] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of apparatuses and methods consistent with some aspects of the invention as detailed in the appended claims.

[0021] Furthermore, the accompanying drawings are merely illustrative of this disclosure and are not necessarily drawn to scale. Some of the block diagrams shown in the drawings represent functional entities and do not necessarily correspond to physically or logically independent entities.

[0022] This application provides a millimeter-wave radar target tracking method, apparatus, device, and storage medium that can eliminate the influence of abnormal data within a period, while reducing the number of target points that need to be processed, so as to facilitate rapid processing of target points, speed up software operation efficiency, and improve the timeliness of risk target judgment.

[0023] To achieve the aforementioned technical effects, the general concept of this application is as follows: A millimeter-wave radar target tracking method, the method comprising the following steps: S101: Based on multiple preset target rectangle types, classify the target point information output by the millimeter-wave radar to determine the target point type output by the millimeter-wave radar.

[0024] S102: Take the vehicle pose corresponding to one of the target points of the target point type as the first coordinate, and transform the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate.

[0025] S103: Based on the pose change of the target point relative to the first coordinates output in real time by the millimeter-wave radar, draw the movement trajectory of the target point and determine whether the target point belongs to the same object.

[0026] S104: Link target points of the same object to generate a target envelope trajectory, and track the target vehicle through the target envelope trajectory.

[0027] The embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0028] Reference Figure 1 , Figure 1 The diagram shown is a flowchart of a millimeter-wave radar target tracking method provided by the present invention. Figure 1 As shown, the method includes the following steps: Step S101: Classify the target point information output by the millimeter-wave radar according to the preset multiple types of target rectangles to determine the target point type output by the millimeter-wave radar.

[0029] Specifically, different types of target rectangles are first preset, mainly divided into three categories: motor vehicles, non-motor vehicles, and pedestrians. For motor vehicles, the preset rectangle dimensions are: length * width * height: 11 * 1.5 * 3; for non-motor vehicles, the preset rectangle dimensions are: length * width * height: 2 * 1 * 1; and for pedestrians, the preset rectangle dimensions are: length * width * height: 1 * 0.5 * 1. It should be noted that the target category and / or target rectangle and / or target type include: motor vehicles, non-motor vehicles, and pedestrians. In essence, by using preset rectangles to select target points for radar scanning, the category of motor vehicle, non-motor vehicle, or pedestrian within the rectangle is determined.

[0030] When the millimeter-wave radar scans target point information, it determines which of the three preset target rectangles the target point information scanned by the millimeter-wave radar belongs to.

[0031] Optionally, when the millimeter-wave radar outputs target point information, the target point can be selected as the midpoint or corner point of a rectangle to select points with similar velocities within the area of ​​the rectangle, and points with dissimilar velocities within the area of ​​the rectangle can be discarded.

[0032] In one embodiment, the target points selected by the rectangular frame are divided into objects by the RCS value. It can be understood that a target category has multiple target points. That is, the target category of motor vehicles is composed of multiple target points. Similarly, non-motor vehicles and pedestrians can also have multiple target points. It can be understood that there can be multiple target points in a target category. Therefore, the target points in the target category are divided to determine whether they belong to the same target category. If they are not the same object, the target points that are not the same object are removed.

[0033] In one embodiment, objects are classified in the selected points by their RCS values. When the RCS value of the radar output target point is less than ±5dB, the objects are classified into the same category. When the RCS value of the radar output target point is greater than ±5dB, the speed of the radar output target point is determined. When the speed of the radar output target point is greater than a set speed, the objects are classified into different categories, and the target points of the different categories are removed.

[0034] In one embodiment, target data output by radar is acquired, and three different sized bounding boxes are selected to identify points within the recognition range, while considering that the difference in RCS values ​​within the selected range does not exceed a set value (±5). This is used to classify the targets.

[0035] Optionally, points with speeds less than a set threshold can be uniformly classified as stationary objects.

[0036] Optionally, after dividing the radar output points into different objects, the system can obtain the following information: system time, yaw rate, steering wheel angle, and vehicle speed. The information of the target points is stored in lists according to different objects. It can be understood that there is one list for each target, meaning that there may be multiple lists of pedestrian targets, motor vehicles, or non-motor vehicles.

[0037] It's important to note that millimeter-wave radar works by identifying targets through the Doppler effect of reflected waves. Since different objects have different materials and absorb millimeter waves at varying intensities, this is typically expressed as an RCS value. Besides the object's surface material, the angle of illumination also affects the RCS value. As a vehicle's attitude changes dynamically during movement, the RCS value of the same object in front of it will fluctuate. Because the radar emits a fan-shaped wave, multiple reflection points are formed when it sweeps across an object. Although radar suppliers generally cluster these reflections based on accuracy and intensity to reduce the number of points, long vehicles or vehicles with strong reflective sources, such as trailers and long flatbed trucks carrying metal objects, can still be identified as multiple points for a single vehicle. If these multiple points are not properly processed, they can complicate subsequent processing modules.

[0038] Step S102: Take the vehicle pose corresponding to one of the target points of the target point type as the first coordinate, and transform the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate.

[0039] Specifically, after determining the target type by scanning the target point information by radar, the vehicle's pose corresponding to a target point of the determined target type is taken as the first coordinate origin. Based on the vehicle's speed, yaw angle, and steering wheel angle at each moment, the attitude update matrix of the vehicle relative to the first coordinate is calculated, i.e., the rotation and translation matrix. The target point output by the millimeter-wave radar in real time is transformed to the coordinate system corresponding to the first coordinate origin through the attitude update matrix, so as to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate system.

[0040] The vehicle has a turning angle change in each cycle. Based on the coordinates of the first cycle, the coordinate change of each cycle relative to the first cycle can be calculated according to this turning angle and the distance traveled. The position of the vehicle in the first coordinate can be calculated according to the real-time output of the millimeter-wave radar.

[0041] It should be noted that the vehicle attitude is inconsistent in each cycle. If it is not converted to the first coordinate system, they will not be in the same relative position. Therefore, it is necessary to convert them before they can be tracked and evaluated in a coordinate system.

[0042] In one embodiment, when a point appears in the radar scan for the first time, the relative distance information of the point is transformed and projected onto the first coordinate system corresponding to a target point within the already determined target type using a rotation and translation matrix. Then, the relative distance between the point and the target points surrounding the target points in the target frame of the target type is calculated. When the relative distance between the point and the surrounding target points is less than a set rectangle, the target point is associated with the surrounding target points and set as a point of the same object. When the distance is greater than the set rectangle, the target point is set as a new target point type. The moment and vehicle attitude are recorded as a new target category. Subsequently, the information updated by the point in each cycle is transformed and projected onto the first coordinate system using a rotation and translation matrix. The new target point type is one of a set of multiple types.

[0043] Understandably, if a new target is identified, the vehicle's pose corresponding to a target point within this new target category will be used as the first coordinate system, and the real-time output of the millimeter-wave radar will be transformed into this first coordinate system through a rotation and translation matrix.

[0044] In one embodiment, if information is lost during the recording process for each target point, the information is estimated by its relative motion state in the first coordinate system. This information is then transformed into the vehicle coordinate system at the current moment using an inverse rotation and translation matrix. After N cycles, the target information can be determined to be valid information.

[0045] Optionally, when there are 3 points within the defined rectangular box category and have the same RCS value, the vehicle pose corresponding to the first data in the array corresponding to the 3 points is taken as the first coordinate origin. The vehicle's attitude update matrix (A) towards the first coordinate origin is calculated based on the vehicle's speed, yaw angle and steering wheel angle at each moment: F(x+1) = A*F(x). The target points output by the radar in real time are then transferred to the coordinate system corresponding to the first coordinate origin according to this matrix. Then the data in the array is the pose change of the 3 target points relative to the first coordinate system.

[0046] Step S103: Based on the pose change of the target point relative to the first coordinates output in real time by the millimeter-wave radar, draw the movement trajectory of the target point and determine whether the target point belongs to the same object.

[0047] Specifically, after converting the target point output by the millimeter-wave radar in real time to the first coordinate system, it is represented as the movement trajectory of a target point throughout the measurement time during the linking process. The movement trajectory of the target point is compared with the target point type output by the millimeter-wave radar. When the overlap rate of the two is greater than a preset value, it is determined that the target points in the target point type belong to the same object. When the overlap rate of the two is less than the preset value, it is determined that the target points in the target point type do not belong to the same object.

[0048] Step S104: Link the target points of the same object to generate a target envelope trajectory, and track the target vehicle through the target envelope trajectory.

[0049] Specifically, after determining the overlap rate, the target points of the same object are translated to construct the outer contour of the object, forming an envelope, which is then used to track the target vehicle.

[0050] Understandably, when dividing several points of the same object, the corresponding target rectangles in three preset rectangles are selected, and the points on multiple periodic target rectangles are linked to form the selected area, which is used for overlap calculation.

[0051] Optionally, the trajectory overlap ratio between newly identified different objects is judged. If the overlap ratio meets the threshold requirement and the relative distance is less than the safe distance, then the two points can be identified as scan points of the same object. It can be understood that a target category has multiple target points. When the trajectory overlap ratio between newly identified different objects is judged, if the overlap ratio meets the requirement and the relative distance is less than the preset distance, then they are determined to be different scan points of the same object.

[0052] Optionally, for different scan points of the same target, relevant envelopes are generated based on their location. For lateral targets, the point with the smallest longitudinal relative distance needs to be translated towards the point with the smallest lateral relative distance and relinked with other target points. For forward targets, points with different lateral distances need to be translated towards the point with the smallest longitudinal distance and relinked with other target points. It can be understood that there will be multiple points on a target with different lateral and longitudinal distance values. The one with the smallest value is selected. Translation means replacing the longitudinal or lateral values. Linking means associating the index values ​​of two point lists. Adding information to the list indicates the association relationship. It should be noted that there is one list for each target, meaning that there may be multiple identical target lists.

[0053] During road travel, traffic participants generally focus only on the nearby side of other targets. Therefore, the envelope ultimately forms a line describing the outer contour of the target object. The trajectory of the movement along this line can then be used to make relevant judgments based on the already determined target type.

[0054] It should be noted that traffic participants on the road generally maintain a relative safe distance, and this safe distance increases with the increase of absolute speed. Conversely, if relevant target points are always present within the safe distance, they can be identified as the same object. When a real target appears within the millimeter-wave detection range, its motion posture will not change drastically in a short period of time, and the relevant information will exist for a certain period of time. Based on the above principles, the target point can be re-evaluated and then translated to complete the envelope.

[0055] It should be noted that radar measurement characteristics are subject to noise. Therefore, a real target will be continuously measured once it appears, but a false target will only exist for a few short periods of time.

[0056] Understandably, the radar scan points are classified into targets by setting the target's bounding box size and RCS value. The target points in the classified target categories are then transformed to a set first coordinate system using a translation and rotation matrix. Motion state analysis is performed in the same coordinate system. Based on the motion state analysis results, it is determined whether the target points in the target category belong to the same object. The scan points determined to be the same object are translated as required to construct the object's outer contour line, generating a target envelope. The target is then tracked based on the target envelope.

[0057] Reference Figure 2 , Figure 2 The diagram shown is a schematic of a millimeter-wave radar target tracking device provided by the present invention. Figure 2 As shown, the device includes: Classification module 201: It is used to classify the target point information output by the millimeter-wave radar according to multiple preset target rectangles, so as to determine the target point type output by the millimeter-wave radar.

[0058] Determining module 202: It is used to take the vehicle pose corresponding to a target point of the target point type as the first coordinate, and convert the target point output by the millimeter-wave radar in real time to the first coordinate system, so as to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate.

[0059] Judgment module 203: It is used to draw the movement trajectory of the target point based on the pose change of the target point relative to the first coordinate in real time output by the millimeter-wave radar, and to determine whether the target point belongs to the same object.

[0060] Processing module 204: It is used to link target points of the same object to generate target envelope trajectory, and to track target vehicles through the target envelope trajectory.

[0061] Furthermore, in one possible implementation, the determination module 203 is also used to compare the target point type output by the millimeter-wave radar according to the movement trajectory of the target point, and when the overlap rate of the two is greater than a preset value, determine that the target points in the target point type belong to the same object. When the overlap rate between the two is less than a preset value, it is determined that the target points in the target point type do not belong to the same object.

[0062] Furthermore, in one possible implementation, the judgment module 203 is also used to judge the trajectory overlap ratio between different objects, and if it is greater than a set value and the relative distance is less than a preset safety distance, it is determined to be different scanning points of the same object.

[0063] Furthermore, in one possible implementation, the determining module 202 is also used to, The first target point in the target point type is taken as the first coordinate origin; Based on the vehicle's speed, yaw angle, and steering wheel angle at each moment, calculate the vehicle's attitude update matrix relative to the first coordinate origin; The target point output by the millimeter-wave radar in real time is transformed to the coordinate system corresponding to the first coordinate origin through the attitude update matrix, so as to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate system.

[0064] Furthermore, in one possible implementation, the determining module 202 is also used to calculate the relative distance between the first target point in the target point type and the surrounding target points, and to determine whether the relative distance is less than a preset rectangle. When the relative distance is less than the set rectangle, the first target point is associated with the surrounding target points; When the relative distance is greater than the set rectangle, the first target point is taken as a new target point type, wherein the new target point type is one of a set of preset types.

[0065] Furthermore, in one possible implementation, the classification module 201 is also used to determine the category of the radar-output target point by using the RCS value when the millimeter-wave radar outputs target point information, including: a motor vehicle rectangle, a non-motor vehicle rectangle, and a pedestrian rectangle.

[0066] Furthermore, in one possible implementation, the classification module 201 is also used to classify objects into the same category when the RCS value of the radar output target point is less than a first set threshold. When the RCS value of the radar output target point is greater than the first preset threshold, the velocity of the radar output target point is determined; When the speed of the target point output by the radar is greater than the set speed, it is classified into different categories of objects.

[0067] The following reference Figure 3 To describe an electronic device 300 according to this embodiment of the present invention. Figure 3 The electronic device 300 shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0068] like Figure 3 As shown, the electronic device 300 is presented in the form of a general-purpose computing device. The components of the electronic device 300 may include, but are not limited to: at least one processing unit 310, at least one storage unit 320, and a bus 330 connecting different system components (including storage unit 320 and processing unit 310).

[0069] The storage unit stores program code that can be executed by the processing unit 310, causing the processing unit 310 to perform the steps described in the "Embodiment Methods" section of this specification according to various exemplary embodiments of the present invention.

[0070] Storage unit 320 may include readable media in the form of volatile storage units, such as random access memory (RAM) 321 and / or cache memory 322, and may further include read-only memory (ROM) 323.

[0071] Storage unit 320 may also include a program / utility 324 having a set (at least one) of program modules 325, including but not limited to: an operating system, one or more application programs, other program modules, and program data, each or some combination of these examples may include an implementation of a network environment.

[0072] Bus 330 can represent one or more of several types of bus structures, including a memory cell bus or memory cell controller, a peripheral bus, a graphics acceleration port, a processing unit, or a local bus using any of the various bus structures.

[0073] Electronic device 300 can also communicate with one or more external devices (e.g., keyboard, pointing device, Bluetooth device, etc.), one or more devices that enable a user to interact with electronic device 300, and / or any device that enables electronic device 300 to communicate with one or more other computing devices (e.g., router, modem, etc.). This communication can be performed via input / output (I / O) interface 350. Furthermore, electronic device 300 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 360. As shown, network adapter 360 communicates with other modules of electronic device 300 via bus 330. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with electronic device 300, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0074] From the above description of the embodiments, those skilled in the art will readily understand that the exemplary embodiments described herein can be implemented by software or by combining software with necessary hardware. Therefore, the technical solutions according to the embodiments of this disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as a CD-ROM, USB flash drive, external hard drive, etc.) or on a network, including several instructions to cause a computing device (such as a personal computer, server, terminal device, or network device, etc.) to execute the methods according to the embodiments of this disclosure.

[0075] According to the present disclosure, a computer-readable storage medium is also provided, on which a program product capable of implementing the methods described above is stored. In some possible embodiments, various aspects of the present invention can also be implemented as a program product comprising program code that, when the program product is run on a terminal device, causes the terminal device to perform the steps of the various exemplary embodiments of the present invention described in the "Exemplary Methods" section above.

[0076] refer to Figure 4 As shown, a program product 400 for implementing the above-described method according to an embodiment of the present invention is described. This product may employ a portable compact disc read-only memory (CD-ROM) and include program code, and may run on a terminal device, such as a personal computer. However, the program product of the present invention is not limited thereto. In this document, the readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.

[0077] The program product may employ any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0078] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A readable signal medium may also be any readable medium other than a readable storage medium, capable of sending, propagating, or transmitting programs for use by or in conjunction with an instruction execution system, apparatus, or device.

[0079] The program code contained on the readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical fiber, RF, etc., or any suitable combination thereof.

[0080] Program code for performing the operations of this invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java and C++, and conventional procedural programming languages ​​such as C or similar languages. The program code can execute entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving remote computing devices, the remote computing device can be connected to the user's computing device via any type of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computing device (e.g., via the Internet using an Internet service provider).

[0081] Furthermore, the above figures are merely illustrative of the processes included in the method according to exemplary embodiments of the present invention, and are not intended to be limiting. It is readily understood that the processes shown in the above figures do not indicate or limit the temporal order of these processes. Additionally, it is readily understood that these processes may be executed synchronously or asynchronously, for example, in multiple modules.

[0082] In summary, this application provides a millimeter-wave radar target tracking method, apparatus, device, and storage medium. The method includes the following steps: classifying target point information output by the millimeter-wave radar according to multiple preset target bounding boxes to determine the target point type output by the millimeter-wave radar; using the vehicle pose corresponding to a target point of one of the target point types as the first coordinate, and transforming the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate; drawing the movement trajectory of the target point based on the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate, and determining whether the target point belongs to the same object; linking target points of the same object to generate a target envelope trajectory, and tracking the target vehicle through the target envelope trajectory. This application can eliminate the influence of abnormal data within the period, and at the same time reduce the number of target points that need to be processed, so as to facilitate rapid processing of target points, speed up software operation efficiency, and improve the timeliness of risk target judgment.

[0083] The above description is merely a specific embodiment of this application, enabling those skilled in the art to understand or implement this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0084] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

Claims

1. A millimeter wave radar target tracking method, characterized by, include: Based on multiple preset target rectangles, the target point information output by the millimeter-wave radar is classified to determine the target point type output by the millimeter-wave radar. The vehicle's pose corresponding to one of the target points of the target point type is used as the first coordinate, and the target point output by the millimeter-wave radar in real time is transformed to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate. Based on the pose change of the target point relative to the first coordinate in real time output by the millimeter-wave radar, the movement trajectory of the target point is plotted, and it is determined whether the target point belongs to the same object. Link target points of the same object to generate a target envelope trajectory, and track the target vehicle using the target envelope trajectory; The first target point in the target point type is taken as the first coordinate origin; Based on the vehicle's speed, yaw angle, and steering wheel angle at each moment, calculate the vehicle's attitude update matrix relative to the first coordinate origin; The target point output in real time by the millimeter-wave radar is transformed to the coordinate system corresponding to the first coordinate origin through the attitude update matrix; Calculate the relative distance between the first target point in the target point type and the surrounding target points, and determine whether the relative distance is less than a preset rectangle; When the relative distance is less than the set rectangle, the first target point is associated with the surrounding target points; When the relative distance is greater than the set rectangle, the first target point is taken as a new target point type to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate system, wherein the new target point type is one of a set of preset types.

2. The method of claim 1, wherein, The step of determining whether the target points belong to the same object includes: Based on the movement trajectory of the target point, the target point type output by the millimeter-wave radar is compared. When the overlap rate of the two is greater than a preset value, it is determined that the target points in the target point type belong to the same object. When the overlap rate between the two is less than a preset value, it is determined that the target points in the target point type do not belong to the same object.

3. The method of claim 2, wherein, After determining that the target points in the target point type do not belong to the same object, the process includes: The system determines the overlap ratio of trajectories between different objects. If the overlap ratio is greater than a set value and the relative distance is less than a preset safety distance, the objects are identified as different scanning points of the same object.

4. The method of claim 1, wherein, The classification of target point information output by the millimeter-wave radar based on multiple preset target bounding boxes includes: The preset target rectangles include: vehicle rectangles, non-motor vehicle rectangles, and pedestrian rectangles; When the millimeter-wave radar outputs target point information, the type of the target point output by the radar is determined by the RCS value.

5. The method according to claim 4, characterized in that: When the RCS value of the target point output by the radar is less than a first set threshold, it is classified as an object of the same category. When the RCS value of the radar output target point is greater than the first preset threshold, the velocity of the radar output target point is determined; When the speed of the target point output by the radar is greater than the set speed, it is classified into different categories of objects.

6. A millimeter wave radar target tracking apparatus, characterized by, include: The classification module is used to classify the target point information output by the millimeter-wave radar according to multiple preset target rectangles in order to determine the target point type output by the millimeter-wave radar. The determination module is used to take the vehicle pose corresponding to a target point of the target point type as the first coordinate and convert the target point output by the millimeter-wave radar in real time to the first coordinate system to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate. The judgment module is used to draw the movement trajectory of the target point based on the pose change of the target point relative to the first coordinate in real time output by the millimeter-wave radar, and to determine whether the target point belongs to the same object. The processing module is used to link target points of the same object to generate a target envelope trajectory, and to track the target vehicle through the target envelope trajectory; The determining module is also used to take the first target point in the target point type as the first coordinate origin; Based on the vehicle's speed, yaw angle, and steering wheel angle at each moment, calculate the vehicle's attitude update matrix relative to the first coordinate origin; The target point output in real time by the millimeter-wave radar is transformed to the coordinate system corresponding to the first coordinate origin through the attitude update matrix; Calculate the relative distance between the first target point in the target point type and the surrounding target points, and determine whether the relative distance is less than a preset rectangle; When the relative distance is less than the set rectangle, the first target point is associated with the surrounding target points; When the relative distance is greater than the set rectangle, the first target point is taken as a new target point type to determine the pose change of the target point output by the millimeter-wave radar in real time relative to the first coordinate system, wherein the new target point type is one of a set of preset types.

7. An electronic device, comprising: The electronic device includes: processor; A memory storing computer-readable instructions that, when executed by the processor, implement the method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, It stores computer program instructions that, when executed by a computer, cause the computer to perform the method according to any one of claims 1 to 5.

Images