Method, device, storage medium and electronic device for determining point trace set

Abstract

The present application discloses a method, device, storage medium and electronic device for determining a point trace set. The method includes: obtaining a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; the first number of first point trace objects included in the first point trace set, and a point trace processing identifier matching the historical point trace set collected in the previous frame, and when the target processing conditions are met, obtaining the first processing description parameter and the second processing description parameter matching the historical point trace set; determining the number of target point traces according to the first processing description parameter and the second processing description parameter; screening the first point trace object in the first point trace set according to the number of target point traces to obtain the second point trace set. The present application solves the technical problems of inaccurate determination of point trace sets and low efficiency in the related art.

Description

Technical Field

[0001] The present application relates to the field of autonomous driving, and more specifically, to a method, device, storage medium and electronic device for determining a set of point traces. Background Art

[0002] In scenes with more complex road environments, there are many real targets and multipath reflection points. When the number of output points is fixed, short-range targets that are not of interest will occupy the space of medium- and long-range targets of interest, resulting in the inability to output medium- and long-range targets normally, and ultimately causing abnormal alarms in the area of ​​interest function.

[0003] At present, more medium and long-range points are released by directly relaxing the limit on the number of final output points and giving priority to moving target points. However, the method of relaxing the overall output point will increase the time consumption and memory space usage. For vehicle-mounted millimeter-wave radars with limited memory and frame length, it is not the best solution. In addition, when environmental characteristics change, the time consumption between frames will also change accordingly. When the number of points in the environment is too large or the point characteristics meet certain conditions, it is easy to cause the problem of too long frame period, which will also affect the overall performance of the radar. In other words, there are technical problems in the prior art of inaccurately determining the point set and low efficiency. Summary of the invention

[0004] The embodiments of the present application provide a method, device, storage medium and electronic device for determining a point trace set, so as to at least solve the technical problems of inaccurate and low efficiency in determining a point trace set in the related art.

[0005] According to one aspect of an embodiment of the present application, a method for determining a point trace set is provided, comprising: obtaining a first point trace set collected by a vehicle object in a current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; a first number of first point trace objects included in the first point trace set, and a point trace processing identifier matching a historical point trace set collected in a previous frame, and obtaining a first processing description parameter and a second processing description parameter matching the historical point trace set when a target processing condition is met, wherein the first processing description parameter is used to indicate a point trace utilization rate of the historical point trace set in a previous frame processing cycle, and the second processing description parameter is used to indicate a set processing efficiency of the historical point trace set in a previous frame processing cycle; determining the number of target point traces according to the first processing description parameter and the second processing description parameter; screening the first point trace object in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0006] According to another aspect of an embodiment of the present application, a device for determining a point trace set is also provided, comprising: a first acquisition unit, which acquires a first point trace set collected by a vehicle object in a current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; a second acquisition unit, which acquires a first processing description parameter and a second processing description parameter matching the historical point trace set based on the first number of first point trace objects included in the first point trace set and a point trace processing identifier matching the historical point trace set collected in the previous frame, if a target processing condition is met, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; a first determination unit, which determines the number of target point traces according to the first processing description parameter and the second processing description parameter; a second determination unit, which screens the first point trace object in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0007] As an optional scheme, the above-mentioned point trace set determination device also includes: a third determination unit, used to determine the target description parameter based on the weighted sum of the first processing description parameter and the second processing description parameter; determine the target parameter interval from multiple candidate parameter intervals based on the target description parameter, wherein multiple continuous candidate parameter intervals correspond to multiple candidate point trace numbers, and the value of the candidate point trace number is positively correlated with the order of the candidate parameter intervals; determine the corresponding target point trace number based on the target parameter interval.

[0008] As an optional scheme, the above-mentioned third determination unit is also used to determine the ratio between the first number of historical points and the second number of historical points that match the historical point set in the previous frame processing cycle as the first processing description parameter, wherein the second number of historical points is the number of point objects included in the second historical point set after screening in the previous frame processing cycle, the first number of historical points is the number of point objects in the second historical point set that are outside the historical area of ​​interest, and the target point objects in the second historical point set that are within the historical area of ​​interest are used to determine the recognition result of historical object recognition in the previous frame processing cycle; the ratio between the historical processing time and the reference processing time of the previous frame processing cycle is determined as the second processing description parameter, wherein the reference processing time is the maximum frame time allowed for the point processing cycle.

[0009] As an optional scheme, the above-mentioned second determination unit includes: an identification module, which is used to determine the target boundary of the target area of ​​interest corresponding to the current frame based on the area boundaries of the historical areas of interest corresponding to multiple historical reference frames; according to the target boundary, determine the second point trace object in the second point trace set that is within the target boundary as the target point trace object; determine the recognition result of the object recognition based on the target point trace set including multiple target point trace objects.

[0010] As an optional scheme, the above-mentioned identification module is also used to determine the point trace processing identifier of the current frame as the first value when the ratio between the first target number of the reference point trace object and the second number of the second point trace object is greater than the first threshold, wherein the reference point trace object is a point trace outside the target boundary, and the first target number is used to indicate the number of static points; when the ratio between the second target number of the reference point trace object and the second number of the second point trace object is greater than the second threshold, the point trace processing identifier of the current frame is determined as the first value.

[0011] As an optional scheme, the above-mentioned point trace set determination device also includes a fourth determination module, which is used to: when the point trace processing identifier matched by the historical point trace set collected in the previous frame is a first value and the first quantity is greater than the first quantity threshold, determine the first quantity and the point trace processing identifier to meet the target processing condition; when the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value, and the weighted sum of the historical quantity corresponding to the historical point trace set and the first quantity is greater than the second quantity threshold, determine the first quantity and the point trace processing identifier to meet the target processing condition.

[0012] As an optional solution, the above-mentioned identification module is also used to obtain a boundary point description array that matches the area boundary corresponding to the historical reference frame, wherein the boundary point description array is used to indicate the correspondence between the boundary distance and the azimuth index of the boundary point; determine the coordinate position information of the boundary point according to the boundary point description array; and determine the target boundary of the target area of ​​interest corresponding to the current frame according to the coordinate position information.

[0013] As an optional scheme, the above-mentioned first acquisition unit includes an execution module, which is used to perform an object recognition operation according to the first point trace set when the first number of first point trace objects included in the first point trace set is less than or equal to the first number threshold; when the point trace processing identifier matched by the historical point trace set collected in the previous frame is a second value, perform an object recognition operation according to the first point trace set; when the motion state of the vehicle object is not a linear motion state, perform an object recognition operation according to the first point trace set.

[0014] According to another aspect of the embodiments of the present application, a computer program product or a computer program is provided, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the above method for determining a point trace set.

[0015] According to another aspect of an embodiment of the present application, there is also provided an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the method for determining a point trace set through the computer program.

[0016] In the above-mentioned embodiment of the present application, a first point trace set collected by the vehicle object in the current frame is obtained, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; a first number of first point trace objects included in the first point trace set, and a point trace processing identifier matching the historical point trace set collected in the previous frame, when the target processing conditions are met, a first processing description parameter and a second processing description parameter matching the historical point trace set are obtained, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; the number of target point traces is determined according to the first processing description parameter and the second processing description parameter; the first point trace object in the first point trace set is screened according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0017] Through the above-mentioned implementation mode of the present application, the first point trace set collected by the vehicle object in the current frame is first obtained, and the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; then, the first number of first point trace objects included in the first point trace set, and the point trace processing identifier matching the historical point trace set collected in the previous frame, when the target processing conditions are met, the first processing description parameter and the second processing description parameter matching the historical point trace set are obtained, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; thereby determining the number of target point traces according to the first processing description parameter and the second processing description parameter; and implementing the screening of the first point trace object in the first point trace set according to the number of target point traces to obtain the second point trace set, thereby solving the technical problems of inaccurate determination of point trace sets and low efficiency in the related art. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0019] Figure 1 is a schematic diagram of an application environment of an optional method for determining a point trace set according to an embodiment of the present application;

[0020] Figure 2 is a flowchart of an optional method for determining a point trace set according to an embodiment of the present application;

[0021] Figure 3 is a schematic diagram of an optional method for determining a point trace set according to an embodiment of the present application;

[0022] Figure 4 is a schematic diagram of another optional method for determining a point trace set according to an embodiment of the present application;

[0023] Figure 5 is a schematic diagram of another optional method for determining a point trace set according to an embodiment of the present application;

[0024] Figure 6 is a flowchart of another optional method for determining a point trace set according to an embodiment of the present application;

[0025] Figure 7 is a flowchart of another optional method for determining a point trace set according to an embodiment of the present application;

[0026] Figure 8 is a schematic diagram of a device for determining a point trace set according to an embodiment of the present application;

[0027] Fig. 9 It is a schematic diagram of the structure of an optional electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present application.

[0029] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to one aspect of an embodiment of the present application, a method for determining a point trace set is provided. Optionally, the method for determining a point trace set can be applied to, but is not limited to, Figure 1 In the hardware environment shown. Optionally, the method for determining the point trace set provided in the present application can be applied to a vehicle terminal. Figure 1 A side view of a vehicle terminal 101 is shown, and the vehicle terminal 101 can travel on a travel surface 113. The vehicle terminal 101 includes an onboard navigation system 103, a memory 102 storing a digitized road map 104, a space monitoring system 117, a vehicle controller 109, a GPS (Global Positioning System) sensor 110, an HMI (Human / Machine Interface) device 111, and also includes an autonomous controller 112 and a telematics controller 114.

[0031] In one embodiment, the space monitoring system 117 includes one or more space sensors and systems, which are used to monitor the visible area 105 in front of the vehicle terminal 101. The space monitoring system 117 also includes a space monitoring controller 118; the space sensors used to monitor the visible area 105 include a laser radar sensor 106, a radar sensor 107, a camera 108, etc. The space monitoring controller 118 can be used to generate data related to the visible area 105 based on the data input from the space sensor. The space monitoring controller 118 can determine the linear range, relative speed and trajectory of the vehicle terminal 101 based on the input from the space sensor, for example, determine the current speed of the vehicle and the relative speed compared to the front vehicle. The space sensor of the vehicle terminal space monitoring system 117 may include an object positioning sensing device, and the object positioning sensing device may include a range sensor, which can be used to locate the front object such as the front vehicle object.

[0032] The camera 108 is advantageously mounted and positioned on the vehicle terminal 101 in a position that allows capturing an image of the visible area 105, wherein at least a portion of the visible area 105 includes a portion of the travel surface 113 in front of the vehicle terminal 101 and including the trajectory of the vehicle terminal 101. The visible area 105 may also include the surrounding environment. Other cameras may also be used, for example, including a second camera disposed on the rear or side portion of the vehicle terminal 101 to monitor the rear of the vehicle terminal 101 and one of the right or left sides of the vehicle terminal 101.

[0033] The autonomous controller 112 is configured to implement autonomous driving or advanced driver assistance system (ADAS) vehicle terminal functionality. It should be noted that in this embodiment, it can also be applied to radar sensors. Such functionality may include a vehicle terminal onboard control system that can provide a certain level of driving automation. Driving automation may include a series of dynamic driving and vehicle terminal operations. Driving automation may include a certain level of automatic control or intervention involving a single vehicle terminal function (e.g., steering, acceleration and / or braking). For example, the above-mentioned autonomous controller can be used to generate a vehicle driving scenario of a vehicle terminal by performing the following steps:

[0034] S102, obtaining a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm;

[0035] S104, when the first number of first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing condition, obtain the first processing description parameter and the second processing description parameter matching the historical point trace set, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle;

[0036] S106, determining the number of target points according to the first processing description parameter and the second processing description parameter;

[0037] S108, screening the first point trace objects in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0038] The HMI device 111 provides human-machine interaction for the purpose of guiding the operation of the infotainment system, GPS (Global Positioning System) sensor 110, onboard navigation system 103 and the like, and includes a controller. The HMI device 111 monitors operator requests and provides the operator with status, service and maintenance information of the vehicle terminal system. The HMI device 111 communicates with multiple operator interface devices and / or controls the operation of multiple operator interface devices. The HMI device 111 may also communicate with one or more devices that monitor biometric data associated with the vehicle terminal operator. For simplicity of description, the HMI device 111 is depicted as a single device, but in the embodiments of the system described herein, it may be configured as multiple controllers and associated sensing devices.

[0039] Operator controls may be included in the passenger compartment of the vehicle terminal 101, and may include, by way of non-limiting example, a steering wheel, an accelerator pedal, a brake pedal, and an operator input device, which is an element of the HMI device 111. The operator controls enable a vehicle terminal operator to interact with the operating vehicle terminal 101 and direct the operation of the vehicle terminal 101 to provide passenger transportation.

[0040] The onboard navigation system 103 uses the digitized road map 104 for the purpose of providing navigation support and information to the vehicle terminal operator. The autonomous controller 112 uses the digitized road map 104 for the purpose of controlling the autonomous vehicle terminal operation or ADAS vehicle terminal functions.

[0041] The vehicle terminal 101 may include a telematics controller 114, which includes a wireless telematics communication system capable of communicating outside the vehicle terminal (including communicating with a communication network 115 having wireless and wired communication capabilities). The wireless telematics communication system includes an off-board server 116 capable of short-range wireless communication with a mobile terminal.

[0042] As an optional implementation, Figure 2 As shown, the method for determining the point trace set can be executed by an electronic device, such as Figure 1 The user device or server shown in the figure comprises:

[0043] S202, obtaining a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm;

[0044] S204, when the first number of first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing condition, obtain the first processing description parameter and the second processing description parameter matching the historical point trace set, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle;

[0045] S206, determining the number of target points according to the first processing description parameter and the second processing description parameter;

[0046] S208, screening the first point trace objects in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0047] In S202 of the above embodiment, the first point trace set collected by the vehicle object in the current frame is obtained, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm. The above first point trace object is first generated according to the distance speed RV diagram of the radar echo signal, and further performs constant false alarm detection (CFAR). The target point detected by CFAR, the above constant false alarm detection can maintain a constant false alarm probability in various complex environments by dynamically adjusting the detection threshold, and detect the target signal to the greatest extent. Specifically, the echo signal received by the millimeter wave radar will form a series of point traces after preprocessing, and each point trace represents a potential target or environmental noise. The CFAR detection algorithm will evaluate these point traces one by one and compare them with the dynamically adjusted threshold. If the signal strength of the point trace exceeds the threshold, it will be considered as a target signal, and thus marked and further processed; if it is lower than the threshold, it will be regarded as noise or interference and will not be further concerned by the radar system.

[0048] The radar echo signal can be generated by either general linear frequency modulation or step frequency modulation continuous wave radar, that is, the radar transmits electromagnetic waves to the target of interest, thereby receiving the echo signal reflected from the target of interest; further, the echo signal is processed by Fourier transform of distance and Doppler dimension respectively, and the range-velocity map (RV map) of the echo signal is obtained. The RV map contains the range-velocity information of all target points and clutter points in the current environment; thus, according to the range-velocity RV map generated by the radar echo signal, the constant false alarm detection (CFAR) is normally performed, and the point detected by CFAR is used as the first point track object mentioned above.

[0049] Further, in the above step S204, when the first number of first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing condition, the first processing description parameter and the second processing description parameter matching the historical point trace set are obtained, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle;

[0050] Optionally, the above-mentioned point trace processing identifier is used to indicate the full point state of the output point trace of the frame image, which may be that the number of point traces in the uninterested area in the output point trace set exceeds a preset threshold, and the above-mentioned uninterested area may be manually marked or determined by a statistical Cartesian coordinate system, which is not specifically limited here. The above-mentioned target processing condition may be, but is not limited to, that the first number is greater than the preset threshold, and the point trace processing identifier indicates that the points of uninterest in the previous frame exceed the preset threshold, and it is determined to be in an abnormal full point state. The above-mentioned historical point trace set may be a point trace set output by the previous frame of the current frame. The above-mentioned first processing description parameter may specifically be the ratio of the number of uninterested points in the previous frame to the total number of point traces output in the previous frame; the above-mentioned second processing description parameter may specifically be the ratio of the frame duration of the current frame to the theoretical maximum frame duration. It should be noted that the frame duration of the previous frame is obtained by multiplying the difference between the clock counters of the current frame and the previous frame by the CPU operating frequency. Since the frame duration belongs to the millisecond level, it is considered that the point trace characteristics in two consecutive frames change little, and the frame duration between the corresponding frames also changes little, that is, the calculated frame duration of the previous frame data can be recorded as the frame duration of the current frame. The theoretical maximum frame duration can be determined based on factors such as radar performance and the complexity of the processing algorithm.

[0051] Then in step S206, the number of target points is determined according to the first processing description parameter and the second processing description parameter; in an optional embodiment, for example, the first processing description parameter and the second processing description parameter can be weighted and summed, and the number of target points is determined according to the weighted summation result.

[0052] As an optional implementation, the threshold value of the number of output points that need to be set can be determined based on the numerical range corresponding to the weighted summation result. For example, the original point release threshold is preset to Nmax0. If the weighted summation result is less than the first threshold, it is necessary to reduce the output number by M based on the number of points corresponding to the previous frame, that is, the output point threshold (target number of points) of the current frame is Nmax0-M. If the weighted summation result is greater than the first threshold, it is necessary to increase the output number by N based on the number of points corresponding to the previous frame, that is, the output point threshold (target number of points) of the current frame is Nmax0+N; or the target number of points corresponding to the weighted average result (that is, the output point number threshold) can be determined based on historical experience. This is just an example.

[0053] Optionally, in the above step S208, the first point trace objects in the first point trace set are screened according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition;

[0054] After determining the above-mentioned target point quantity (i.e., the threshold value of the number of output points), the first point objects in the first point set are screened. Specifically, when the number of the first point objects exceeds the threshold value, it is necessary to screen and delete a certain number of points to obtain the second point set, that is, the second number of the second point objects in the second point set will not exceed the above-mentioned target point quantity.

[0055] Through the above-mentioned implementation mode of the present application, the first point trace set collected by the vehicle object in the current frame is first obtained, and the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; then, the first number of first point trace objects included in the first point trace set, and the point trace processing identifier matching the historical point trace set collected in the previous frame, when the target processing conditions are met, the first processing description parameter and the second processing description parameter matching the historical point trace set are obtained, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; thereby determining the number of target point traces according to the first processing description parameter and the second processing description parameter; and implementing the screening of the first point trace object in the first point trace set according to the number of target point traces to obtain the second point trace set, thereby solving the technical problems of inaccurate determination of point trace sets and low efficiency in the related art.

[0056] In an optional implementation, determining the number of target points according to the first processing description parameter and the second processing description parameter includes:

[0057] S1, determining a target description parameter according to a weighted sum of a first processing description parameter and a second processing description parameter;

[0058] S2, determining a target parameter interval from a plurality of candidate parameter intervals according to the target description parameter, wherein a plurality of continuous candidate parameter intervals correspond to a plurality of candidate point trace numbers, and the value of the candidate point trace number is positively correlated with the order of the candidate parameter intervals;

[0059] S3, determining the number of target points corresponding to the target parameter interval.

[0060] In the above step S1, the target description parameter is determined according to the weighted sum of the first processing description parameter and the second processing description parameter. m =α1*p before / M before +α2*T now / T max , p before / M before Indicates the ratio of the number of uninteresting points in the previous frame to the total number of points output in the previous frame, T now / T max Indicates the ratio of the frame duration of the current frame to the theoretical maximum frame duration. α1 and α2 are coefficients that are arbitrarily less than 1, and α1+α2=1. The setting of specific parameter values ​​can be dynamically adjusted according to radar performance and test requirements.

[0061] Furthermore, in steps S2-S3, a target parameter interval is determined from a plurality of candidate parameter intervals according to the target description parameters, wherein a plurality of consecutive candidate parameter intervals correspond to a plurality of candidate point trace numbers, respectively, and the value of the candidate point trace number is positively correlated with the order of the candidate parameter intervals; the corresponding target point trace number is determined according to the target parameter interval.

[0062] As an optional implementation, for example, if δ0<δ1<δ2<δ3 exists and there is a matching relationship: if the target description parameter is in the first candidate parameter interval (δ0<δ m <δ1), the corresponding number of candidate points is N0; if the target description parameter is in the second candidate parameter interval (δ1<δ m <δ2), the corresponding number of candidate points is N1; if the target description parameter is in the third candidate parameter interval (δ2<δ m <δ3), the number of candidate points corresponding to the above is N2, where N0 <N1<N2。

[0063] That is, when the target description parameter is in the first candidate parameter interval, the number of target points is determined to be N0; when the target description parameter is in the second candidate parameter interval, the number of target points is determined to be N1; when the target description parameter is in the third candidate parameter interval, the number of target points is determined to be N2. This is only an example and there is no specific restriction on the setting of the numerical value.

[0064] Through the above-mentioned implementation mode of the present application, the target description parameter is determined according to the weighted sum of the first processing description parameter and the second processing description parameter; and then the target parameter interval is determined from multiple candidate parameter intervals according to the target description parameter; the number of target points corresponding to the target parameter interval is determined according to the target parameter interval, and the proportion of uninteresting points in the previous frame is considered. The radar system can intelligently judge the existence of static obstacles or clutter in the current environment, so that in the processing of the current frame, the maximum number of points can be appropriately adjusted to avoid resources being occupied by unnecessary points; considering the proportion of frame duration, the response environment changes can be monitored and the number of points can be adjusted to avoid excessively long frame cycles.

[0065] In an optional implementation, obtaining a first processing description parameter and a second processing description parameter that match the historical point trace set includes:

[0066] S1, determining the ratio between the first number of historical traces and the second number of historical traces that match the historical trace set in the previous frame processing cycle as the first processing description parameter, wherein the second number of historical traces is the number of trace objects included in the second historical trace set after screening in the previous frame processing cycle, the first number of historical traces is the number of trace objects outside the historical interest area in the second historical trace set, and the target trace objects in the second historical trace set that are in the historical interest area are used to determine the recognition result of the historical object recognition in the previous frame processing cycle;

[0067] S2, determining the ratio between the historical processing duration of the previous frame processing cycle and the reference processing duration as the second processing description parameter, wherein the reference processing duration is the maximum frame duration allowed for the trace processing cycle.

[0068] In the above step S1, the ratio between the first number of historical points and the second number of historical points that match the historical point set in the previous frame processing cycle is determined as the first processing description parameter, wherein the second number of historical points is the number of point objects included in the second historical point set after screening in the previous frame processing cycle, the first number of historical points is the number of point objects in the second historical point set that are outside the historical area of ​​interest, and the target point objects in the second historical point set that are within the historical area of ​​interest are used to determine the recognition result of the historical object recognition in the previous frame processing cycle.

[0069] As an optional implementation, the first number of historical point traces may specifically be the number of uninteresting points in the previous frame, and the second number of historical point traces may specifically be the total number of point traces output in the previous frame, for example, the number of point traces output after preliminary screening after constant false alarm detection (CFAR). Specifically, the target point trace objects in the second historical point trace set that are in the historical region of interest are used to determine the recognition result of the historical object recognition in the previous frame processing cycle, that is, scene recognition is performed based on the points in the region of interest. The object recognition result may be, for example, recognition information such as the driving status of dynamic road objects with overtaking intentions in traffic scenes.

[0070] In the above step S2, the ratio between the historical processing time and the reference processing time of the previous frame processing cycle is determined as the second processing description parameter, wherein the reference processing time is the maximum frame time allowed for the point trace processing cycle, which can be determined together with event monitoring requirements, processor performance, and environmental (lighting, weather) factors.

[0071] In an optional implementation, after the first point trace objects in the first point trace set are screened according to the number of target point traces to obtain the second point trace set, the method further includes:

[0072] S1, determining a target boundary of a target region of interest corresponding to a current frame according to region boundaries of historical regions of interest corresponding to each of a plurality of historical reference frames;

[0073] S2, according to the target boundary, determining a second point trace object in the second point trace set that is within the target boundary as a target point trace object;

[0074] S3, determining a recognition result of the object recognition according to a target point trace set including a plurality of target point trace objects.

[0075] In the above steps S1-S2, the target boundary of the target region of interest corresponding to the current frame is determined according to the region boundaries of the historical regions of interest corresponding to each of the multiple historical reference frames; based on the target boundary, the second point object in the second point set that is within the target boundary is determined as the target point object.

[0076] As an optional implementation, for each historical reference frame, the system can determine the boundaries of the corresponding historical areas of interest through static point analysis and grid division, and record the boundary information; analyze the distribution trends of the boundaries of these historical areas of interest, and identify the laws of boundary changes; for example, based on road conditions such as urban roads, highway environments, rural or outdoor road environments, etc.

[0077] Taking urban roads as an example, the radar system records multiple historical reference frames of urban roads, which contain a large number of dynamic points (vehicles, pedestrians) and static points (buildings, street lights); based on the point data output by the historical reference frame, the system identifies the boundary positions of static obstacles (such as buildings, street lights, and curbstones) that may exist on both sides of the urban roads, and uses them as the boundaries of the area of ​​interest. On urban roads, the area at a certain distance ahead is usually focused on to ensure that vehicles and pedestrians ahead are detected in time. The radar system sets the area of ​​interest for urban roads to 100-200 meters directly in front of the vehicle, with a width covering all lanes. Therefore, when the current frame is an urban road, the setting method of the area of ​​interest corresponding to the historical frame of the above-mentioned urban road can be obtained to determine the area of ​​interest that matches the current frame.

[0078] Furthermore, in the above step S3, the recognition result of the object recognition is determined based on the target point track set including multiple target point track objects; the information in the target point track set is converted into the recognition result of the object recognition, which includes the recognition results such as the type, position, speed and possible motion trajectory of the vehicle traveling on the road.

[0079] Through the above implementation methods described in this application, the target boundary of the target region of interest corresponding to the current frame is determined based on the region boundaries of the historical regions of interest corresponding to each of the multiple historical reference frames; based on the target boundary, the second point trace object in the second point trace set that is within the target boundary is determined as the target point trace object; and the recognition result of the object recognition is determined based on the target point trace set including multiple target point trace objects. Accurate screening of the target point trace set ensures that the subsequent object recognition algorithm processes real dynamic target points, reduces the influence of noise and irrelevant points, and thus improves the accuracy of the object recognition results. For example, the recognition and classification of objects such as vehicles, pedestrians, and bicycles are more accurate.

[0080] In an optional implementation, after the first point trace objects in the first point trace set are screened according to the number of target point traces to obtain the second point trace set, at least one of the following is further included:

[0081] Method 1: when the ratio between the first target quantity of the reference point trace object and the second quantity of the second point trace object is greater than the first threshold, the point trace processing identifier of the current frame is determined to be the first value, wherein the reference point trace object is a point trace outside the target boundary, and the first target quantity is used to indicate the quantity of static point traces;

[0082] Method 2: when the ratio between the second target number of the reference point trace object and the second number of the second point trace object is greater than the second threshold, the point trace processing flag of the current frame is determined to be the first value.

[0083] Optionally, in the first method, the first target number of the reference point track object can be the number of static points outside the boundary of the region of interest obtained by calculating the horizontal and vertical coordinate information (xypos) of the points in the Cartesian coordinate system. It should be noted that the Cartesian coordinate system calculation can distinguish between dynamic and static points. In this method, the ratio of the number of static points of no interest outside the region of interest to the number of points entering the angle measurement module is calculated, and when the ratio result is greater than the first threshold, it is determined to be in an abnormal full point state. Specifically, the first value can be used to determine that the corresponding frame image is in an abnormal full point state.

[0084] In the above-mentioned method 2, the second target number of reference point track objects can be the number of points outside all areas of interest determined by generating the azimIdx-RIdx boundary of interest through multiple historical frames, and calculating the ratio of the number of points marked as not interested outside the area of ​​interest to the number of points entering the angle measurement module. When the ratio result is greater than the second threshold, it is determined to be in an abnormal full point state.

[0085] That is, if the number of points M output by the current frame (D1 frame) is greater than c1*initial preset output threshold, or the number of points N entering the angle measurement module is greater than or equal to the initial preset output threshold, then the number of points n1 in the area of ​​no interest in the Cartesian coordinate system is counted. If n1 is greater than c2*N, or the number of points marked as not interested is greater than c3*N, then the current frame is considered to be in an abnormally full-point state.

[0086] Through the above implementation methods recorded in this application, the full point state is determined according to the ratio of the number of points of no interest to the number of input points, and the millimeter wave radar system can effectively monitor the distribution of points in the current frame and promptly detect abnormal full point states. This monitoring mechanism helps the system to quickly adjust its processing strategy when the number of points increases abnormally, avoiding processing delays or performance degradation caused by this.

[0087] In an optional implementation, before obtaining the first processing description parameter and the second processing description parameter matching the historical point trace set, at least one of the following is further included:

[0088] Method 1: when the point trace processing identifier matched by the historical point trace set collected in the previous frame is the first value and the first number is greater than the first number threshold, determine the first number and the point trace processing identifier to meet the target processing condition;

[0089] Method 2: When the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value, and the weighted sum of the historical quantity corresponding to the historical point trace set and the first quantity is greater than the second quantity threshold, determine the first quantity and the point trace processing identifier to meet the target processing condition.

[0090] Optionally, in the above-mentioned method 1, when the point trace processing identifier matched by the historical point trace set collected in the previous frame is the first value and the first quantity is greater than the first quantity threshold, the first quantity and the point trace processing identifier are determined to meet the target processing condition.

[0091] Specifically, when the number of dots NR1 (corresponding to the above-mentioned first number) detected by CFAR in the current frame is greater than N_Raw1 (corresponding to the above-mentioned first number threshold) and the previous frame flag=1 (indicating that the previous frame is in an abnormally full-dot state), the corresponding dot processing identifier is the first value, and the first value is taken as "1" here to indicate that it is in an abnormally full-dot state. To determine that the target processing conditions are met, it is necessary to adjust the threshold of the number of dots detected by CFAR in the current frame, for example, trigger the point release mechanism to relax the threshold of the number of dots entering the angle measurement module; it can be understood that the above-mentioned abnormally full-dot state may refer to the reception or processing of a large amount of uninteresting signals containing static, noise, etc. in the historical frame.

[0092] As another optional implementation, in the above-mentioned method 2, when the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value, and the weighted sum of the historical quantity corresponding to the historical point trace set and the first quantity is greater than the second quantity threshold, the first quantity and the point trace processing identifier are determined to meet the target processing conditions.

[0093] Specifically, a weighted sum is performed based on the number of points detected by CFAR in the current frame and the previous frame (the first number NR1 and the historical number NR0). When the weighted sum result is greater than N_Raw2 (i.e., the second number threshold mentioned above), it is determined that the target processing conditions are met, and the threshold for the number of points detected by CFAR in the current frame needs to be adjusted to trigger a temporary point release mechanism to relax the limit on the number of points.

[0094] It should be noted that N_Raw1 and N_Raw2 are the CFAR detection points counted according to the abnormal full-point state, which are positive integer constants and can be dynamically adjusted according to actual conditions, for example, N_Raw2>N_Raw1.

[0095] Through the above implementation methods recorded in this application, when the point trace processing identifier matched by the historical point trace set collected in the previous frame is the first value, and the first number is greater than the first number threshold, the first number and the point trace processing identifier are determined to meet the target processing conditions; when the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value, and the weighted sum result between the historical number corresponding to the historical point trace set and the first number is greater than the second number threshold, the first number and the point trace processing identifier are determined to meet the target processing conditions. By setting different trigger conditions to adjust the point release restrictions in different situations, it can be ensured that all potential dynamic targets can be detected, and the system's adaptability and response speed to complex environments can be improved; and then the processing of static or irrelevant points can be reduced by marking the points in the area of ​​interest, reducing the false alarm rate and improving the accuracy of determining the point trace set.

[0096] In an optional implementation, determining a target boundary of a target region of interest corresponding to a current frame according to region boundaries of historical regions of interest corresponding to each of a plurality of historical reference frames includes:

[0097] S1, obtaining a boundary point description array that matches the region boundary corresponding to the historical reference frame, wherein the boundary point description array is used to indicate the corresponding relationship between the boundary distance and the azimuth index of the boundary point;

[0098] S2, determining the coordinate position information of the boundary points according to the boundary point description array;

[0099] S3, determining a target boundary of the target region of interest corresponding to the current frame according to the coordinate position information.

[0100] In the above steps S1-S3, a boundary point description array matching the area boundary corresponding to the historical reference frame is obtained, wherein the boundary point description array is used to indicate the correspondence between the boundary distance and the azimuth index of the boundary point; the coordinate position information of the boundary point is determined according to the boundary point description array; and the target boundary of the target area of ​​interest corresponding to the current frame is determined according to the coordinate position information.

[0101] As an optional implementation, the FFT angle measurement module is called to output the azimIdx of the detection points in the historical multiple frames, and based on the relationship between the boundary distance of the region of interest and the azimuth index (azimIdx-RIdx), the points outside the boundary of the region of interest can be marked as invalid points (InvalidFlag=1).

[0102] Specifically, the calculation of the horizontal and vertical positions (xpos and ypos) of the point track involves the calculation of angles and the conversion of the coordinate system (such as the formula: horizontal position: xpos=R*cos(θ)+longoffset; longitudinal position: ypos=R*sin(θ)+latoffset, which will increase the additional running time, where θ=azimuth0+yawAngle0, azimuth0 is the azimuth of the point track calculated by the azimuth index azimIdx0, R is the target distance, longoffset is half the length of the vehicle, latoffset is half the width of the vehicle, and yawAngle0 is the radar installation angle used for boundary statistical data.

[0103] It should be noted that the distance R and velocity V information of all points can be calculated and output according to the distance unit RIdx and Doppler unit VIdx information of the target point; linear frequency modulation: R=RIdx*Rres; V=VIdx*Vres; step frequency: R=RIdx*Rres-fc*VIdx*Vres / k; V=VIdx*Vres-Δf*RIdx*Rres / fc / PRT; among which Rres is the distance resolution, Vres is the velocity resolution, fc is the radar center frequency, Δf is the frequency step between adjacent chirp signals, k is the frequency modulation slope, and PRT is the chirp signal pulse repetition period.

[0104] In addition, it can be found from the following formula that after the azimIdx and RIdx of a point are determined, its corresponding xpos and ypos are also determined. Therefore, here we directly count the azimIdx-RIdx relationship of the boundary points based on the accumulated boundaries of interest in multiple frames to limit the marking boundaries.

[0105] In addition, considering the action areas of special functional scenarios such as RCTA and FCTA, the points in the close-range designated area are also relaxed, and finally the boundary of the area of ​​interest in the Cartesian coordinate system is generated as follows: Figure 3 As shown, the corresponding generated azimIdx-RIdx boundary of interest is as follows Figure 4 The final output of the boundary of interest gARIdx is a one-dimensional array, which represents the relationship between the angle index and the distance index of the boundary points of the region of interest. The size of the array is determined by the selected angle measurement step azi_step.

[0106] Further considering the compensation of the influence of the installation position and installation angle changes, when the radar installation angle yawAngle changes, it will affect θ, causing the boundary of the area of ​​interest written in the Cartesian coordinate system to shift (such as Figure 5As shown in the figure), the corresponding azimIdx-RIdx boundary will also be offset. Therefore, the deviation caused by the installation angle needs to be compensated before comparing the boundary values. The specific compensation formula is as follows: azimIdx=azimIdx0+(yawAngle-yawAngle0) / azi_step; where yawAngle is the radar installation angle after the change, and azi_step is the angle measurement step (unit: °).

[0107] According to the above method, the region of interest corresponding to the current frame is determined, and the points outside the region of interest are deleted, and the recognition result of the object recognition is determined using the points within the region of interest.

[0108] Through the above implementation, a boundary point description array matching the region boundary corresponding to the historical reference frame is obtained, wherein the boundary point description array is used to indicate the corresponding relationship between the boundary distance and the azimuth index of the boundary point; the coordinate position information of the boundary point is determined according to the boundary point description array; and the target boundary of the target region of interest corresponding to the current frame is determined according to the coordinate position information. Thus, the point traces located within the boundary can be selectively processed, while the point traces outside the boundary are ignored, thereby improving the accuracy of determining the point trace set and improving the object recognition result.

[0109] In an optional implementation, after obtaining the first point trace set collected by the vehicle object in the current frame, at least one of the following is further included:

[0110] Mode 1: When the first number of first point trace objects included in the first point trace set is less than or equal to the first number threshold, an object recognition operation is performed according to the first point trace set;

[0111] Method 2: when the point trace processing identifier matched by the historical point trace set collected in the previous frame is the second value, an object recognition operation is performed according to the first point trace set;

[0112] Method three: when the motion state of the vehicle object is not a linear motion state, an object recognition operation is performed according to the first point trace set.

[0113] In the above-mentioned first embodiment, when the first number of first point trace objects included in the first point trace set is less than or equal to the first quantity threshold, an object recognition operation is performed according to the first point trace set. Specifically, the first number NR1 of the first point trace objects outputted by all the collected detection points after CFAR detection (constant false alarm detection) is less than or equal to the first quantity threshold, and the above-mentioned first quantity threshold may be a preset point trace quantity threshold that can be input into the angle measurement module. It is achieved that when the number of first point trace objects in the first point trace set is less than or equal to the first quantity threshold, the system directly performs an object recognition operation based on the first point trace set, avoiding unnecessary point trace screening and processing, thereby optimizing computing resources and memory usage.

[0114] Optionally, in the above-mentioned second embodiment, when the point trace processing identifier matched by the historical point trace set collected in the previous frame is the second value, the object recognition operation is performed according to the first point trace set. For example, when the point trace processing identifier matched by the historical point trace set collected in the previous frame is 0, that is, when it is not in an abnormal full point state, the object recognition operation can be directly performed according to the first point trace set.

[0115] In the above-mentioned third embodiment, when the motion state of the vehicle object is not a linear motion state, the object recognition operation is performed according to the first point trace set. That is, when the vehicle object is in a straight-line driving state, the radar's field of view is relatively stable, and its main area of ​​concern is the long strip of space directly in front of the vehicle. In this field of view, the radar is more likely to encounter specific scenes, such as dense static obstacles (such as a row of continuous fences or iron walls), or a large number of dynamic targets (such as vehicles in traffic). These situations may lead to the generation of a large number of points, which in turn leads to challenges in radar processing, such as increased time consumption and increased memory usage. Therefore, in the straight-line state, the radar system needs a more flexible point trace processing strategy to deal with the possible full-point problem, and needs to perform a point release operation to release more medium and long-range target objects. In the non-straight driving state, the object recognition operation can be directly performed. In the non-straight-line scene, object recognition is directly performed to quickly adapt to changes in the field of view to ensure the safety of the vehicle during operations such as turning.

[0116] It can be understood that the above object recognition operation specifically inputs the detection points in the first point trace set into the original angle measurement module, and the original angle measurement module includes channel calibration, FFT angle measurement, DBF angle measurement and high-resolution angle measurement submodules for object recognition. It is realized that when the vehicle is not moving in a straight line, such as turning or changing lanes, the object recognition operation is directly performed based on the first point trace set, so that the system can quickly adapt to the change of motion state, avoiding the point trace re-evaluation and processing delay caused by the change of motion state.

[0117] The scheme recorded in this application is fully described below with a specific implementation method:

[0118] S1, obtaining the echo signal of the current frame (D1 frame). The radar echo signal can be generated by either general linear frequency modulation or step frequency modulation continuous wave radar, that is, the radar transmits electromagnetic waves to the target of interest, thereby receiving the echo signal reflected from the target of interest.

[0119] S2, process the echo signal of the current frame (D1 frame) to obtain a range-velocity map. By performing Fourier transform processing on the echo signal in terms of range and Doppler dimension, a range-velocity map (RV map) of the echo signal is obtained. The RV map contains the range-velocity information of all target points and clutter points in the current environment.

[0120] S3. Output the number of target points detected by CFAR for the current frame (D1 frame), as well as their corresponding range-Doppler cell indices. For the range-velocity RV map generated from the radar echo signal, constant false alarm rate (CFAR) detection is normally performed. Generally, points that can pass the CFAR detection are considered target points, and points that do not pass the CFAR are clutter points. However, due to the complexity of the road environment, even points that pass the CFAR detection may contain clutter points of no interest. Here, initially output the number of points NR1 that pass the CFAR detection, as well as the corresponding range cell index RIdx and DopIdx.

[0121] S4. Combine the flag_0 of the previous frame (D0 frame) and the information of the current frame (D1 frame) to determine whether to trigger the temporary point release mechanism and confirm whether to relax the limit on the number of tracks entering the channel matching, range, and velocity calculation modules. The specific judgment logic is as follows:

[0122] When the host vehicle is in a straight-line motion state, enter the temporary point release judgment module; otherwise, do not trigger the temporary point release mechanism, the limit on the number of tracks remains the original value Nmax0, and the frame counter NumCnt is decremented by 1 (i.e., U - 1).

[0123] Temporary point release judgment module: If condition 1) the number of tracks NR1 detected by CFAR in the current frame is greater than N_Raw1 and the flag of the previous frame = 1, or condition 2) the weighted sum of the number of tracks (NR1 and NR0) detected by CFAR in the current frame and the previous frame is greater than N_Raw2, then trigger the temporary point release mechanism to relax the limit on the number of tracks to Nmax1; otherwise, the limit on the number of tracks remains the original value Nmax0, and the frame counter NumCnt is decremented by 1 (i.e., U - 1).

[0124] Among them, N_Raw1 and N_Raw2 are the number of points detected by CFAR statistically based on the abnormal full-point state, which are positive integer constants that can be dynamically adjusted according to the actual situation, and generally N_Raw2 > N_Raw1. flag_0 is a flag bit indicating whether the data of the previous frame is in an abnormal full-point state, and its calculation method is the same as that of the current frame flag_1 described in step 8.

[0125] S5. Calculate the range and velocity information of the N detected points output after S4. According to the range cell RIdx and Doppler cell VIdx information of the target points, calculate and output the range R and velocity V information of all points. In the normal mode, the number of detected points N entering this module < Nmax0, and after successfully triggering the temporary point release mechanism, the number of points N entering this module < Nmax1, where Nmax0 < Nmax1. In addition, due to the existence of the limit on the number of tracks, the number of points output in this step is generally less than or equal to the number of points detected by CFAR, that is, N <= NR1.

[0126] Among them, linear frequency modulation: R = RIdx*Rres; V = VIdx*Vres; step frequency: R = RIdx*Rres-fc*VIdx*Vres / k; V = VIdx*Vres-Δf*RIdx*Rres / fc / PRT; Rres is the distance resolution, Vres is the velocity resolution, fc is the radar center frequency, Δf is the frequency step between adjacent chirp signals, k is the frequency modulation slope, and PRT is the chirp signal pulse repetition period.

[0127] S6, judging whether to trigger the region of interest screening module based on the number of detection points N, and marking the points outside the boundary of interest. If the number of detection points N is greater than Nmax0, that is, if S2 successfully triggers the temporary point release mechanism, the region of interest screening module is triggered, otherwise it jumps directly to S7.

[0128] Interested region screening module: N detection points first enter the channel calibration and FFT angle measurement module, output the azimuth index number azimIdx corresponding to the point trace, and save the FFT angle measurement result. Then, according to the relationship between the distance unit RIdx corresponding to the boundary point azimIdx in multi-frame statistics, the points outside the boundary of the interested region are marked as invalid points (InvalidFlag = 1). Among them, this module needs to perform external regularity statistics, input the boundary of the interested region and the compensation value of the installation angle change.

[0129] Calculation of the boundary of the region of interest: Since the scenes of missed detection of the target in the region of interest found so far mostly occur when the vehicle is driving straight through an environment with strong reflective targets such as large fences, the number of target points at close range and at far distance exceeds the limit of the number of traces Nmax0, resulting in the inability to detect moving targets at medium and long distances. By limiting the horizontal and vertical positions of the output traces in the Cartesian coordinate system, the memory occupation of the close-range uninteresting points can be released, which can be used to output the target points of interest at medium and long distances. The calculation of the horizontal and vertical positions (xpos and ypos) involves the calculation of angles and the conversion of the coordinate system (as shown in the following formula), which will increase the additional running time. In addition, it can be found from the following formula that after the azimIdx and RIdx of a trace are determined, its corresponding xpos and ypos are also determined. Therefore, here we directly count the azimIdx-RIdx relationship of the boundary points based on the accumulated boundary of interest in multiple frames to limit the marking boundary.

[0130] Lateral position: xpos=R*cos(θ)+longoffset, longitudinal position: ypos=R*sin(θ)+latoffset, where θ=azimuth0+yawAngle0, azimuth0 is the point azimuth calculated by the azimuth index azimIdx0, R is the target distance, longoffset is half the vehicle length, latoffset is half the vehicle width, and yawAngle0 is the radar installation angle used for boundary statistics.

[0131] In addition, considering the action areas of special functional scenarios such as RCTA and FCTA, the points in the close-range designated area are also relaxed, and finally the boundary of the area of ​​interest in the Cartesian coordinate system is generated as follows: Figure 3 As shown, the corresponding generated azimIdx-RIdx boundary of interest is as follows Figure 4 The final output of the boundary of interest gARIdx is a one-dimensional array, which represents the relationship between the angle index and the distance index of the boundary points of the region of interest. The size of the array is determined by the selected angle measurement step azi_step.

[0132] Compensation for the effects of changes in installation position and installation angle: When the radar installation angle yawAngle changes, it will affect θ, causing the boundary of the area of ​​interest written in the Cartesian coordinate system to shift (such as Figure 5 As shown in the figure), the corresponding azimIdx-RIdx boundary will also be offset, so the deviation caused by the installation angle needs to be compensated before comparing the boundary values. The specific compensation formula is as follows.

[0133] azimIdx=azimIdx0+(yawAngle-yawAngle0) / azi_step; wherein yawAngle is the radar installation angle after the change, and azi_step is the angle measurement step (unit: °).

[0134] S7. Enter different angle measurement modules according to the number of detection points N, and output the number of points M entering the angle measurement module. If the number of points N is less than or equal to Nmax0, that is, the temporary point release mechanism is not triggered, then all points directly enter the original angle measurement module, otherwise, only unmarked points (InvalidFlag=0) are allowed to enter the new angle measurement module, and the total number of points M entering should be less than or equal to Nmax0, so the number of points entering the angle measurement module M<=Nmax0. In addition, the original angle measurement module includes sub-modules such as channel calibration, FFT angle measurement, DBF angle measurement and high-resolution angle measurement, but in S6, if the region of interest screening module is triggered, the channel calibration and FFT angle measurement have been performed and the corresponding results have been saved, so the new angle measurement module here only includes the two main sub-modules of DBF angle measurement and high-resolution angle measurement.

[0135] S8. Output the flag bit flag_1 representing the full state of the D1 frame according to the information of the current frame (D1 frame). When the vehicle is in a straight-moving state, enter the flag assignment judgment module, otherwise directly output flag_1=0. In addition, if the value of the inter-frame counter (NumCnt) is greater than 0, it will not enter the flag assignment judgment, but directly output flag_1=1.

[0136] Flag assignment judgment module: If the number of points M output by the D1 frame is greater than c1*Nmax0, or the number of points N entering the angle measurement module is greater than or equal to Nmax0, then the number of points n1 in the uninterested area in the Cartesian coordinate system is counted. If n1 is greater than c2*N, or the number of points marked as uninteresting is greater than c3*N, then the current frame is considered to be in an abnormally full-point state, and flag_1 is set to 1 and the inter-frame counter NumCnt is set to U, otherwise flag_1 is output to 0 and NumCnt is cleared.

[0137] Among them, flag_i (i = 0, 1, 2, ..., Nf) is the flag bit representing the full-point state, Nf indicates that the radar frame number is any integer greater than or equal to 0, U indicates the number of frames that directly set flag_i = 1 without entering the flag assignment judgment (arbitrarily set a positive integer), c1, c2, c3 respectively represent the weight coefficient value range [0, 1], and the specific value can be adjusted according to the statistical value under the abnormal full-point state of the system.

[0138] S9, the flag_i value outputted by S8 is given to the next frame (frame D2). The flag_i value outputted by S8 is passed to the next frame data, and participates in the temporary placement point judgment described in S4, and then continues to execute S1 to S9 in a loop until the data processing of all frames is completed.

[0139] Flowchart Figure 6 The above process is explained as follows:

[0140] S602, acquiring the echo signal of the current frame radar, generating a range-velocity spectrogram according to the echo signal, outputting the points that pass the constant false alarm detection, and counting the number of output points;

[0141] S604, judging whether to trigger the temporary point release mechanism by combining the abnormal full point mark bit reserved in the previous frame, the number of constant false alarm output points and the constant false alarm output points of the current frame, and if triggered, relaxing the limit on the number of point traces and performing a subtraction operation on the inter-frame counter;

[0142] S606, judging whether to trigger the region of interest screening module according to the number of point traces, if triggered, marking the points outside the boundary of the region of interest as invalid points, and then confirming whether to allow entering the angle measurement module according to the mark, otherwise all points directly enter the angle measurement module;

[0143] S608, judging whether the current frame is in an abnormal full-dot state according to the value of the inter-frame counter or the number and position distribution of the dots, outputting an abnormal full-dot mark to participate in the temporary dot placement judgment of the next frame, and reassigning the inter-frame counter.

[0144] The scheme recorded in this application is fully described below with another specific implementation method:

[0145] S1. Evaluate the frame duration, memory conditions, and radar performance requirements to determine the maximum number of temporary points Nmax and the maximum number of points Mmax for the final output. Set different numbers of points, count the time required for all processing modules of the point traces under different numbers of points, and record the maximum number of points that meet the time requirements of a single frame as the maximum number of points Nmax1. At the same time, evaluate the remaining memory space. If the memory occupied by Nmax1 points exceeds the existing memory space limit, reduce the maximum number of points to Nmax based on memory usage, otherwise confirm that Nmax = Nmax1. Combine radar performance and customer needs to jointly determine the maximum number of output points Mmax of the radar, where Mmax <= Nmax.

[0146] S2, obtain the radar echo signal of the current frame and output the target point of the current frame. Perform constant false alarm detection (CFAR) on the echo signal of the current frame, and normally output all target points that pass the CFAR detection, and record the number of points NR1 that pass the CFAR detection in the current frame.

[0147] S3. Calculate the frame duration T0 of the current frame according to the input clock counter value and the CPU operating frequency. The frame duration of the previous frame can be obtained by multiplying the clock counter difference between the current frame and the previous frame by the CPU operating frequency. Since the frame duration is at the millisecond level, it is considered that the point trace characteristics in two consecutive frames change little, and the frame duration between the corresponding frames also changes little, that is, the calculated frame duration of the previous frame data can be recorded as the frame duration of the current frame.

[0148] S4. Calculate the ratio of the frame duration of the current frame to the theoretical maximum frame duration. According to the frame duration of the current frame obtained in S1, calculate its ratio to the theoretical maximum frame duration.

[0149] S5, determine the number of points Nm in the current frame based on the ratio of the proportion of uninteresting points in the previous frame to the frame duration of the current frame, and the number of points NR1 detected by the current frame through CFAR. Assuming that the number of points is divided into m blocks, the value δ obtained by weighted summation of the point proportion and the frame duration ratio is m When NRaw1 is in different intervals, the number of points Nm in the current frame is also assigned different values ​​accordingly.

[0150] δ m =α1*p before / M before +α2*Tnow / T max , where α1 and α2 are coefficients less than 1 and α1+α2=1, p before / M before Indicates the ratio of the number of uninteresting points in the previous frame to the total number of points output in the previous frame, T now / T max Indicates the ratio of the current frame duration to the theoretical maximum frame duration. In addition, the number of points here should be less than the maximum number of points Nmax determined in S1, and greater than the maximum number of output points Mmax determined according to the radar performance requirements, that is, Mmax<=Nm <Nmax。

[0151] S6, perform distance and speed measurement calculations on all Nm output points, and finally output Mnow points to enter the angle measurement module. Perform distance and speed measurement calculations on all points released by S5 to obtain the distance and speed information of the target. Before entering the angle measurement module, delete the points outside the boundary of the area of ​​interest according to the point trace characteristics to ensure that only Mnow points enter the angle measurement module. Here, Mnow should be less than or equal to Mmax.

[0152] S7. Dynamically determine the boundary of the region of interest based on the point characteristics of the current frame data, and count the number of uninteresting points outside the boundary of interest. It is generally believed that full points are likely to appear in scenes such as fences and iron walls. Therefore, the fence / iron wall is considered as the boundary of the region of interest. The boundary position is determined by grid division, and the number of uninteresting points outside the boundary pnow is counted.

[0153] According to the distribution of stationary points, the boundary is identified by grid division. First, based on the Cartesian coordinate system of the vehicle, the stationary points are grouped by grid in the horizontal position, and the two groups with the largest number of points in the horizontal grid are recorded. Then, the distribution of these two groups in the vertical position is counted. If the density of the point distribution in the vertical position meets certain conditions, the maximum value of the horizontal position of the two groups of points is recorded as the horizontal boundary value of the area of ​​interest.

[0154] S8, calculate the proportion of uninteresting points in the current frame, which is used to participate in the point placement judgment of the next frame. The uninteresting points in the current frame are divided by the total number of output points to obtain the proportion of uninteresting points in the current frame pnow / Mnow.

[0155] Flowchart Figure 7 The above process is explained as follows:

[0156] S702, evaluating the frame duration and memory conditions to determine the maximum number of points in the system;

[0157] S704, obtaining the echo signal of the current frame and performing constant false alarm detection normally;

[0158] S706, obtaining and calculating the echo signal processing time of the current frame, and calculating the ratio of the current frame time to the theoretical frame time;

[0159] S708, determining the number of points to be placed in the current frame by combining the frame duration ratio of the current frame and the percentage of points outside the boundary of interest of the previous frame;

[0160] S710, dynamically determine the boundary of the region of interest of the current frame and count the number of points outside the boundary, and calculate the proportion of uninteresting points in the current frame for participating in the point placement judgment of the next frame.

[0161] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0162] According to another aspect of the embodiment of the present application, a device for determining a point trace set for implementing the above-mentioned method for determining a point trace set is also provided. Figure 8 As shown, the device comprises:

[0163] A first acquisition unit 802 acquires a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm;

[0164] The second acquisition unit 804 acquires the first processing description parameter and the second processing description parameter matching the historical point trace set when the first number of first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing condition, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle;

[0165] A first determining unit 806 determines the number of target points according to the first processing description parameter and the second processing description parameter;

[0166] The second determination unit 808 filters the first point trace objects in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0167] Optionally, the above-mentioned point trace determination device also includes: a third determination unit, used to determine the target description parameter based on the weighted sum of the first processing description parameter and the second processing description parameter; determine the target parameter interval from multiple candidate parameter intervals based on the target description parameter, wherein multiple consecutive candidate parameter intervals correspond to multiple candidate point trace numbers, and the value of the candidate point trace number is positively correlated with the order of the candidate parameter intervals; determine the corresponding target point trace number based on the target parameter interval.

[0168] Optionally, the third determination unit is also used to determine the ratio between the first number of historical points and the second number of historical points that match the historical point set in the previous frame processing cycle as a first processing description parameter, wherein the second number of historical points is the number of point objects included in the second historical point set after screening in the previous frame processing cycle, the first number of historical points is the number of point objects in the second historical point set that are outside the historical area of ​​interest, and the target point objects in the second historical point set that are within the historical area of ​​interest are used to determine the recognition result of historical object recognition in the previous frame processing cycle; the ratio between the historical processing duration and the reference processing duration of the previous frame processing cycle is determined as a second processing description parameter, wherein the reference processing duration is the maximum frame duration allowed for the point processing cycle.

[0169] Optionally, the second determination unit 808 includes: an identification module, used to determine the target boundary of the target area of ​​interest corresponding to the current frame based on the area boundaries of the historical areas of interest corresponding to each of the multiple historical reference frames; based on the target boundary, determine the second point trace object in the second point trace set that is within the target boundary as the target point trace object; and determine the recognition result of the object recognition based on the target point trace set including multiple target point trace objects.

[0170] Optionally, the above-mentioned identification module is also used to determine the point trace processing identifier of the current frame as a first value when the ratio between the first target number of the reference point trace object and the second number of the second point trace objects is greater than a first threshold, wherein the reference point trace object is a point trace outside the target boundary, and the first target number is used to indicate the number of static points; when the ratio between the second target number of the reference point trace object and the second number of the second point trace objects is greater than a second threshold, the point trace processing identifier of the current frame is determined as the first value.

[0171] Optionally, the above-mentioned point trace set determination device also includes a fourth determination module, which is used to: when the point trace processing identifier matched by the historical point trace set collected in the previous frame is a first value and the first quantity is greater than the first quantity threshold, determine the first quantity and the point trace processing identifier to meet the target processing condition; when the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value and the weighted sum of the historical quantity corresponding to the historical point trace set and the first quantity is greater than the second quantity threshold, determine the first quantity and the point trace processing identifier to meet the target processing condition.

[0172] Optionally, the above-mentioned identification module is also used to obtain a boundary point description array that matches the area boundary corresponding to the historical reference frame, wherein the boundary point description array is used to indicate the correspondence between the boundary distance and the azimuth index of the boundary point; determine the coordinate position information of the boundary point according to the boundary point description array; and determine the target boundary of the target area of ​​interest corresponding to the current frame according to the coordinate position information.

[0173] Optionally, the first acquisition unit 802 includes an execution module, which is used to perform an object recognition operation according to the first point trace set when the first number of first point trace objects included in the first point trace set is less than or equal to a first quantity threshold; perform an object recognition operation according to the first point trace set when the point trace processing identifier matched by the historical point trace set collected in the previous frame is a second value; and perform an object recognition operation according to the first point trace set when the motion state of the vehicle object is not a linear motion state.

[0174] For a specific embodiment, reference may be made to the example shown in the method for determining a point trace set described above, which will not be described in detail in this example.

[0175] Among them, the memory 902 can be used to store software programs and modules, such as the program instructions / modules corresponding to the method and device for determining the point trace set in the embodiment of the present invention. The processor 904 executes various functional applications and data processing by running the software programs and modules stored in the memory 902, that is, realizing the above-mentioned method for determining the point trace set. The memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 902 may further include a memory remotely located relative to the processor 904, and these remote memories may be connected to the terminal via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof. Among them, the memory 902 can be specifically, but not limited to, used to store file information such as target files. As an example, such as Fig. 9As shown, the memory 902 may include, but is not limited to, the first acquisition unit 802, the second acquisition unit 804, the first determination unit 806, and the second determination unit 808 in the device for determining the point trace set. In addition, other module units in the device for determining the point trace set may also be included but are not limited to, which will not be described in detail in this example.

[0176] Optionally, the transmission device 906 is used to receive or send data via a network. Specific examples of the above-mentioned network may include a wired network and a wireless network. In one example, the transmission device 906 includes a network adapter (Network Interface Controller, NIC), which can be connected to other network devices and routers via a network cable so as to communicate with the Internet or a local area network. In one example, the transmission device 906 is a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0177] In addition, the electronic device mentioned above further includes: a display 908, and a connection bus 910, which is used to connect various module components in the electronic device mentioned above.

[0178] According to one aspect of the present application, a computer program product is provided, the computer program product comprising a computer program / instruction, the computer program / instruction comprising a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions provided by the embodiments of the present application are executed.

[0179] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0180] It should be noted that the computer system of the electronic device is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0181] In particular, according to an embodiment of the present application, the process described in each method flow chart can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a computer readable medium, and the computer program contains a program code for executing the method shown in the flow chart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication part, and / or installed from a removable medium. When the computer program is executed by a central processing unit, various functions defined in the system of the present application are executed.

[0182] According to one aspect of the present application, a computer-readable storage medium is provided, and a processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0183] Optionally, in this embodiment, the computer-readable storage medium may be configured to store a computer program for performing the following steps:

[0184] S1, obtaining a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm;

[0185] S2, when the first number of first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing conditions, obtain the first processing description parameter and the second processing description parameter matching the historical point trace set, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle;

[0186] S3, determining the number of target points according to the first processing description parameter and the second processing description parameter;

[0187] S4, screening the first point trace objects in the first point trace set according to the number of target point traces to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the number of target point traces, and the second point trace set is used for object recognition.

[0188] Optionally, in this embodiment, a person of ordinary skill in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing hardware related to the electronic device through a program, and the program may be stored in a computer-readable storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0189] The serial numbers of the above-mentioned embodiments of the present application are for description only and do not represent the advantages or disadvantages of the embodiments.

[0190] If the integrated units in the above embodiments are implemented in the form of software functional units and sold or used as independent products, they can be stored in the above computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling one or more computer devices (which can be personal computers, servers or network devices, etc.) to execute all or part of the steps of the methods of each embodiment of the present application.

[0191] In the above embodiments of the present application, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0192] In the several embodiments provided in the present application, it should be understood that the disclosed user equipment can be implemented in other ways. Among them, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, for example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0193] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0194] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0195] The above is only a preferred implementation of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

Claims

1. A method for determining a point trace set, characterized in that: include: Acquire a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm rate; When the first number of the first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing conditions, obtain the first processing description parameter and the second processing description parameter matching the historical point trace set, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; Determine the number of target points according to the first processing description parameter and the second processing description parameter; The first point trace objects in the first point trace set are screened according to the target point trace quantity to obtain a second point trace set, wherein a second number of second point trace objects included in the second point trace set is less than or equal to the target point trace quantity, and the second point trace set is used for object recognition.

2. The method according to claim 1, characterized in that: The determining the number of target points according to the first processing description parameter and the second processing description parameter includes: Determining a target description parameter according to a weighted sum of the first processing description parameter and the second processing description parameter; Determining a target parameter interval from a plurality of candidate parameter intervals according to the target description parameter, wherein a plurality of continuous candidate parameter intervals respectively correspond to a plurality of candidate point trace quantities, and the value of the candidate point trace quantity is positively correlated with the order of the candidate parameter intervals; The number of target points corresponding to the target parameter interval is determined according to the target parameter interval.

3. The method according to claim 2, characterized in that The obtaining of the first processing description parameter and the second processing description parameter matching the historical point trace set includes: Determine the first processing description parameter as the ratio between the first number of historical point traces and the second number of historical point traces that match the historical point trace set in the previous frame processing cycle, wherein the second number of historical point traces is the number of point trace objects included in the second historical point trace set after screening in the previous frame processing cycle, the first number of historical point traces is the number of point trace objects outside the historical interest region in the second historical point trace set, and the target point trace objects in the second historical point trace set that are within the historical interest region are used to determine the recognition result of the historical object recognition in the previous frame processing cycle; The ratio between the historical processing duration of the previous frame processing cycle and the reference processing duration is determined as the second processing description parameter, wherein the reference processing duration is the maximum frame duration allowed for the trace processing cycle.

4. The method according to claim 1, characterized in that: After the first point trace objects in the first point trace set are screened according to the number of the target point traces to obtain a second point trace set, the method further includes: Determining a target boundary of a target region of interest corresponding to the current frame according to region boundaries of historical regions of interest corresponding to each of a plurality of historical reference frames; According to the target boundary, determining the second point trace objects in the second point trace set that are within the target boundary as target point trace objects; A recognition result of the object recognition is determined according to a target point trace set including a plurality of the target point trace objects.

5. The method according to claim 4, characterized in that After the first point trace objects in the first point trace set are screened according to the number of the target point traces to obtain the second point trace set, the method further includes at least one of the following: When a ratio between a first target quantity of a reference point trace object and the second quantity of the second point trace object is greater than a first threshold, determining the point trace processing identifier of the current frame as a first value, wherein the reference point trace object is a point trace outside the target boundary, and the first target quantity is used to indicate the quantity of static point traces; When the ratio between the second target number of the reference point trace object and the second number of the second point trace object is greater than a second threshold, the point trace processing identifier of the current frame is determined to be the first value.

6. The method according to claim 5, characterized in that Before obtaining the first processing description parameter and the second processing description parameter matching the historical point trace set, at least one of the following is also included: When the point trace processing identifier matched by the historical point trace set collected in the previous frame is a first value and the first number is greater than a first number threshold, determining that the first number and the point trace processing identifier meet the target processing condition; When the point trace processing identifier matched by the historical point trace set collected in the previous frame is an arbitrary value, and the weighted sum of the historical quantity corresponding to the historical point trace set and the first quantity is greater than a second quantity threshold, it is determined that the first quantity and the point trace processing identifier meet the target processing condition.

7. The method according to claim 4, characterized in that The step of determining the target boundary of the target region of interest corresponding to the current frame according to the region boundaries of the historical regions of interest corresponding to each of the plurality of historical reference frames includes: Acquire a boundary point description array that matches the region boundary corresponding to the historical reference frame, wherein the boundary point description array is used to indicate a corresponding relationship between a boundary distance and an azimuth index of a boundary point; Determine the coordinate position information of the boundary point according to the boundary point description array; A target boundary of a target region of interest corresponding to the current frame is determined according to the coordinate position information.

8. The method according to claim 1, characterized in that After obtaining the first point trace set collected by the vehicle object in the current frame, the method further includes at least one of the following: When the first number of the first point trace objects included in the first point trace set is less than or equal to a first number threshold, performing an object recognition operation according to the first point trace set; When the point trace processing identifier matched by the historical point trace set collected in the previous frame is a second value, performing an object recognition operation according to the first point trace set; When the motion state of the vehicle object is not a linear motion state, an object recognition operation is performed according to the first point trace set.

9. A device for determining a point trace set, characterized in that: include: A first acquisition unit is configured to acquire a first point trace set collected by the vehicle object in the current frame, wherein the first point trace object in the first point trace set is a radar point trace object detected by constant false alarm; A second acquisition unit, when the first number of the first point trace objects included in the first point trace set and the point trace processing identifier matching the historical point trace set collected in the previous frame meet the target processing condition, acquires the first processing description parameter and the second processing description parameter matching the historical point trace set, wherein the first processing description parameter is used to indicate the point trace utilization rate of the historical point trace set in the previous frame processing cycle, and the second processing description parameter is used to indicate the set processing efficiency of the historical point trace set in the previous frame processing cycle; A first determining unit, determining the number of target points according to the first processing description parameter and the second processing description parameter; The second determination unit filters the first point trace objects in the first point trace set according to the target point trace quantity to obtain a second point trace set, wherein the second number of second point trace objects included in the second point trace set is less than or equal to the target point trace quantity, and the second point trace set is used for object recognition.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored program, wherein the program executes the method described in any one of claims 1 to 8 when executed by an electronic device.

11. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to execute the method according to any one of claims 1 to 8 through the computer program.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method described in any one of claims 1 to 8 are implemented.

Images