WO2022267845A1

WO2022267845A1 - Kick signal recognition method and apparatus, and terminal

Info

Publication number: WO2022267845A1
Application number: PCT/CN2022/096335
Authority: WO
Inventors: 郜丽敏; 杨长林; 包红燕; 秦屹
Original assignee: 森思泰克河北科技有限公司
Priority date: 2021-06-24
Filing date: 2022-05-31
Publication date: 2022-12-29
Also published as: CN113589274A; CN113589274B

Abstract

The present application provides a kick signal recognition method and apparatus, a terminal, and a storage medium. The method comprises: acquiring point cloud information of each echo data frame detected by a radar; determining whether the point cloud information satisfies a preset condition, and if the point cloud information satisfies the preset condition, marking the data frame corresponding to the point cloud information; when the number of acquired data frames reaches a preset value n, every time a new data frame is acquired, counting the number of marked data frames in the first n data frames of the newly acquired data frame to obtain a continuously updated quantity sequence; and recognizing kick signals according to the continuously updated quantity sequence. The present application can improve recognition accuracy of the kick signals.

Description

Kick signal recognition method, device and terminal

This patent application claims the priority of Chinese Patent Application No. CN202110707110.1 submitted on June 24, 2021. The disclosure of the prior application is incorporated by reference in its entirety into this application.

technical field

The present application relates to the technical field of radar detection, in particular to a kick signal recognition method, device and terminal.

Background technique

By kicking to open the door, the door can be opened conveniently and quickly, which satisfies people's pursuit of vehicle intelligence and convenient performance, and is favored by people. Millimeter wave radar has the characteristics of strong penetrating ability, small size and light weight, and is widely used in kick recognition technology.

However, the existing kick recognition methods based on millimeter-wave radar all count the number of target points in a fixed frame for judgment. This recognition method is prone to false alarms due to the interference of external factors, resulting in missing kicks and multiple kicks in the detection results, and the accuracy of kick recognition is low.

technical problem

The present application provides a kick signal recognition method, device and terminal to solve the problem of low recognition accuracy in the kick recognition method based on millimeter wave radar in the prior art.

technical solution

In a first aspect, the present application provides a kick signal recognition method, the method comprising:

Obtain the point cloud information of each frame of echo data detected by the radar;

Judging whether the point cloud information satisfies the preset condition, if the point cloud information satisfies the preset condition, then mark the data frame corresponding to the point cloud information;

When the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, the number of marked data frames in the first n data frames of the latest acquired data frame is counted to obtain a continuously updated number sequence;

The kick signal is recognized from a continuously updated sequence of numbers.

In a possible implementation manner, judging whether the point cloud information satisfies a preset condition includes:

Judging whether there is a target point in the point cloud information, if there is no target point in the point cloud information, it is determined that the point cloud information does not meet the preset conditions;

If there are target points in the point cloud information, determine the maximum distance and maximum pitch angle according to the distance and pitch angle of each target point in the point cloud information relative to the radar;

If the maximum distance is less than the preset distance threshold, and the maximum pitch angle is smaller than the preset pitch angle threshold, it is determined that the point cloud information meets the preset condition;

If the maximum distance is not less than the preset distance threshold, or the maximum pitch angle is not smaller than the preset pitch angle threshold, it is determined that the point cloud information does not meet the preset condition.

In a possible implementation manner, updating the quantity sequence includes:

Add the number of marked data frames in the first n data frames of the latest acquired data frame as an update value to the existing number sequence;

Kick signals are identified based on a continuously updated sequence of quantities, including:

Each time the quantity sequence is updated, it is judged whether the update value is 1;

If the update value is 1, count the number of peaks, the maximum peak, and the duration corresponding to the non-zero interval in the quantity sequence after this update; where the non-zero interval is the first non-zero value of the quantity sequence update to the current update value the interval between

If there is only one peak value, and the duration corresponding to the non-zero interval is less than the first preset threshold, and the maximum peak value is greater than the second preset threshold, it is determined that a kick signal is detected.

In a possible implementation, the statistical method of the duration corresponding to the non-zero interval includes:

Obtain the detection frequency of the radar;

Count the number of values in the non-zero interval;

According to the detection frequency and the number of values in the non-zero interval, determine the corresponding duration of the non-zero interval.

In a possible implementation manner, after the kick signal is detected, the kick signal recognition method provided in the present application further includes:

Delete all the values in the current number sequence, and proceed to update the number sequence and identify the kick signal according to the continuously updated number sequence.

In a possible implementation manner, the length of the quantity sequence does not exceed a preset length threshold k;

The kick signal identification method provided by this application also includes:

If the length of the quantity sequence after an update exceeds the preset length threshold k, delete the first k values of the quantity sequence.

In a second aspect, the present application provides a kick signal recognition device, which includes:

An acquisition module, configured to acquire point cloud information of each frame of echo data detected by the radar;

Judging module, used for judging whether the point cloud information satisfies the preset condition, if the point cloud information satisfies the preset condition, then the data frame corresponding to the point cloud information is marked;

The statistical module is used to obtain a new data frame each time after the number of acquired data frames reaches the preset value n, count the number of marked data frames in the first n data frames of the latest acquired data frame, and obtain a continuously updated sequence of numbers;

The identification module is used for identifying the kick signal according to the continuously updated quantity sequence.

In a possible implementation manner, the judging module is specifically used for:

In a third aspect, the present application provides a terminal, which includes a memory, a processor, and a computer program stored in the memory and operable on the processor. When the processor executes the computer program, the above script of the first aspect is implemented. Steps of the kick signal identification method.

In a fourth aspect, the present application provides a computer-readable storage medium, where a computer program is stored in the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the kick signal recognition method in the first aspect as described above are implemented.

Beneficial effect

This application obtains the point cloud information of each frame of echo data detected by the radar, and when the point cloud information satisfies a preset condition, marks the data frame corresponding to the point cloud information. When the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, the number of marked data frames in the latest acquired first n data frames is counted to obtain a continuously updated quantity sequence. The kick signal is identified based on this sequence of numbers. Compared with the method of counting the number of target points in the fixed frame in the prior art to identify the kick signal, the kick recognition method provided in the present application analyzes the point cloud information characteristics of the entire data frame sequence, so it is not easy to be affected by the outside world. The interference of factors can effectively avoid the phenomenon of missing kicks and multiple kicks, and improve the recognition accuracy of kick signals.

Description of drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present application, the accompanying drawings that need to be used in the descriptions of the embodiments or the prior art will be briefly introduced below. Obviously, the accompanying drawings in the following description are only for the present application For some embodiments, those of ordinary skill in the art can also obtain other drawings based on these drawings without paying creative efforts.

Fig. 1 is the implementation flowchart of the kick signal identification method provided by the embodiment of the present application;

Fig. 2 is the implementation flowchart of the kick signal identification method provided by the embodiment of the present application;

3 is a schematic structural diagram of a kick signal recognition device provided in an embodiment of the present application;

FIG. 4 is a schematic diagram of a terminal provided by an embodiment of the present application.

detailed description

In the following description, specific details such as specific system structures and technologies are presented for the purpose of illustration rather than limitation, so as to thoroughly understand the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.

In order to make the purpose, technical solution and advantages of the present application clearer, specific embodiments will be described below in conjunction with the accompanying drawings.

An embodiment of the present application provides a method for identifying a kick signal. Referring to FIG. 1 , the method includes step S101: acquiring point cloud information of each frame of echo data detected by the radar.

In the embodiment of this application, the radar performs FFT (Fast Fourier Transform, Fast Fourier Transform) processing to obtain the range-Doppler spectrogram. Then, constant false alarm detection is performed on the range-Doppler spectrogram to obtain multiple target points. The distance, pitch angle, and azimuth angle of each target point relative to the radar form point cloud information.

Please continue to refer to Figure 1, the kick signal recognition method provided by the present application also includes step S102: judge whether the point cloud information meets the preset conditions, and if the point cloud information meets the preset conditions, then mark the data frame corresponding to the point cloud information .

In the embodiment of the present application, by setting a preset condition, it is judged whether the data frame should be marked. When the point cloud information meets the preset conditions, it means that the radar has detected the target in the current frame, and the frame is marked.

Please continue to refer to Figure 1, the kick signal recognition method provided by the present application also includes step S103: when the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, count the first n of the latest acquired data frames The number of marked data frames in a data frame, to get a continuously updated sequence of numbers.

In the embodiment of the present application, when the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, the number of marked data frames in the latest acquired first n data frames is counted. In this way, the real-time performance of the detection can be guaranteed, and a complete quantitative sequence can be formed, and then the kick signal can be identified by analyzing the characteristics of the quantitative sequence.

Please continue to refer to FIG. 1 , the kick signal identification method provided in the present application further includes step S104 : identify the kick signal according to the continuously updated quantity sequence.

In the embodiment of the present application, before the kick signal appears, there is no target point in the point cloud information detected by the radar, and the point cloud information does not meet the preset condition at this time. When the kick signal appears, there are target points in the continuous multi-frame point cloud information detected by the radar, and the point cloud information meets the preset conditions at this time. When the kick signal disappears, there is no target point in the point cloud information detected by the radar, and the point cloud information does not meet the preset conditions at this time. Therefore, when the kick signal appears, the value of the current element in the continuously updated quantity sequence should increase from 1 to n, and then gradually decrease from n to 1. By analyzing this dynamic feature of the number sequence, the kick signal can be identified.

It can be seen that, in the embodiment of the present invention, by acquiring the point cloud information of each frame of echo data detected by the radar, when the point cloud information satisfies the preset condition, the data frame corresponding to the point cloud information is marked, and when the acquired data frame After the number reaches the preset value n, each time a new data frame is acquired, the number of marked data frames in the first n data frames of the latest acquired data frame is counted, and a continuously updated number sequence is obtained to identify the kick signal. Compared with the method of identifying the kick signal by counting the number of target points in the fixed frame in the prior art, the present invention is not easily disturbed by external factors because it analyzes the point cloud information characteristics of the entire data frame sequence, and can effectively avoid The phenomenon of missing kicks and multiple kicks improves the recognition accuracy of kick signals.

The method (step S101 to step S104) provided in this application is to identify the kick signal through the dynamic features of the quantity sequence. However, the method in the prior art uses static features (the number of target points in a fixed frame) for identification. The dynamic characteristics of the number sequence actually reflect the dynamic characteristics of the kicking process. Compared with one or several parameters of static features, the dynamic characteristics of the kicking action can more accurately reflect whether the kicking action occurs. Therefore, using the dynamic features of the kick action can identify the kick signal more accurately and prevent misjudgment, thereby effectively avoiding the problems of missed kicks and multiple kicks.

Optionally, in a possible implementation manner, judging whether the point cloud information satisfies a preset condition may be implemented through the following steps:

In the embodiment of the present application, it is determined whether the radar has detected a target in the current frame according to whether there is a target point in the point cloud information, and further judgment and screening are performed on the target point. When all target points are target points meeting the threshold condition, it is considered that a correct kicking target has been detected. This can further improve the recognition accuracy.

Optionally, in a possible implementation manner, updating the number sequence may be implemented through the following steps: adding the number of marked data frames in the latest acquired first n data frames as an update value to the existing number sequence.

The kick signal can be identified according to the continuously updated sequence of numbers, which can be achieved through the following steps:

It should be noted that the above "peak value in the quantitative sequence" refers to the extremum of a two-dimensional curve, the two-dimensional curve takes time as the abscissa and the value of the element in the quantitative sequence as the ordinate. The above "maximum peak value" refers to the largest one among several possible extreme values. There may be only one extreme value, and at this time, the only extreme value is the largest peak value.

In the embodiment of the present application, when the kick signal starts to appear and is about to disappear, the update value of the quantity sequence is 1. Moreover, in the case of filtering out interference, the peak value of the non-zero interval corresponding to the kick signal in the quantity sequence should be only one and greater than a certain value (the value of the element in the non-zero interval gradually changes from 1 to the maximum value and then converges to 1) , the duration should be less than a certain value. Therefore, when the update value is 1, the judgment of the number of peaks, the maximum peak value, and the duration corresponding to the non-zero interval, when the number of peaks, the maximum peak value, and the duration corresponding to the non-zero interval all meet the characteristics of the kick signal, then A complete kick signal is considered to be identified; otherwise, non-zero intervals are considered to be generated by interference signals. Through this method, the real kick signal can be accurately identified and the interference can be filtered out.

Optionally, in a possible implementation manner, the statistical method of the duration corresponding to the non-zero interval may include but not limited to the following steps:

Obtain the detection frequency of the radar;

Count the number of values in the non-zero interval;

In the embodiment of the present application, every time the radar detects a frame, it counts the number of marked data frames and updates the number sequence. Therefore, the number of values in the non-zero interval is multiplied by the radar sampling time interval (the reciprocal of the detection frequency), that is, the duration corresponding to the entire non-zero interval.

Optionally, in a possible implementation manner, after the kick signal is detected, the kick signal recognition method provided in the present application further includes the following steps:

In the embodiment of the present application, after the kick signal is detected, the data in the number sequence is deleted in time, so as to prepare for the detection of the next kick signal.

Optionally, in a possible implementation manner, the length of the quantity sequence does not exceed a preset length threshold k. The kick signal recognition method provided by the present application also includes the following steps:

If the length of an updated quantity sequence exceeds a preset length threshold k, delete the first k values of the quantity sequence.

In the embodiment of the present application, if the kick signal is not detected for a long time, the number sequence needs to be cleared periodically to avoid the number sequence being too long and occupying a lot of memory.

In addition, in the embodiment of the present application, the preset value n, the preset distance threshold, the preset pitch angle threshold, the first preset threshold, the second preset threshold, and the preset length threshold k can all be based on a large number of tests Determine the most appropriate value to improve recognition accuracy.

The embodiment of the present application provides a kick signal recognition method, the method includes the following steps:

Step S105: Obtain point cloud information of each frame of echo data detected by the radar in real time.

Step S106: Determine whether the point cloud information satisfies the preset condition, and if the point cloud information satisfies the preset condition, mark the data frame corresponding to the point cloud information.

In step S106, judging whether the point cloud information satisfies the preset condition can be realized by the following steps:

The kick signal identification method provided by the embodiment of the present application further includes step S107: when the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, the first n data frames of the latest acquired data frames are counted The number of marked data frames is obtained by a continuously updated number sequence, and it is judged in real time whether the length of the number sequence exceeds the preset length threshold k, and if it exceeds, the first k values of the number sequence are deleted.

In step S107, updating the quantity sequence can be realized through the following steps:

Add the number of marked data frames in the first n data frames of the latest acquired data frame as an update value to the existing number sequence.

The kick signal identification method provided in the embodiment of the present application further includes step S108: identifying the kick signal according to the continuously updated quantity sequence.

In step S108, the recognition of the kick signal can be realized through the following steps:

Step S1081 , judging whether the update value is 1 each time the quantity sequence is updated.

Step S1082, if the update value is 1, count the number of peaks, the maximum peak value, and the duration corresponding to the non-zero interval in the quantity sequence after this update; where the non-zero interval is the first non-zero value updated in the quantity sequence to The interval between the current update values.

In step S1082, the statistical method of the duration corresponding to the non-zero interval may include the following steps:

Obtain the detection frequency of the radar;

Count the number of values in the non-zero interval;

A time length corresponding to the non-zero interval is determined according to the detection frequency and the number of values in the non-zero interval.

In step S108, the identification of the kick signal also includes step S1083: if there is only one peak value, and the duration corresponding to the non-zero interval is less than the first preset threshold, and the maximum peak value is greater than the second preset threshold, it is determined that a kick is detected Signal.

The kick signal identification method provided by the embodiment of the present application further includes step S109: after the kick signal is detected, delete all the values in the current number sequence, and continue to update the number sequence in steps S107 to S108 and according to the constantly updated Quantitative sequence to operate on the recognition of the kick signal.

The kick signal recognition method provided in the embodiment of the present application is mainly but not limited to be applied in the vehicle-mounted millimeter-wave radar. Exemplarily, the radar is installed on a car door at a certain height from the ground, and is inclined downward at a certain angle. When the toes of the human body kick to the center of the radar beam, the kick signal can be accurately identified according to the point cloud information of the echo data detected by the radar. After recognizing the kick signal, send a CAN message to the door controller to control the door to open. When no kick signal is detected, the doors remain locked. Among them, the radar can adopt the Multiple-Input Multiple-Output (MIMO) design scheme, which has a high degree of integration, including RF front-end and signal processing modules, and rich peripheral interfaces. The work of analyzing the point cloud information detected by the radar signal can be completed by a processing chip. The processing chip can be set inside or outside the radar, and can be connected via CAN (Controller Area Network) to send the recognition results to the body controller to realize the sleep wake-up function. The processing chip supports FOTA (Firmware Over the Air) remote upgrade function.

Referring to Figure 2, the embodiment of the present application also provides a more specific kick signal recognition process:

(1) When the body is unlocked, the radar is powered on and activated to start working. Radar sends electromagnetic waves of a specific frequency to the target detection area through the transmitting antenna. The electromagnetic wave is reflected by the object, and the receiving antenna receives the echo signal. After ADC sampling and band-pass filtering processing, the out-of-band interference signal is filtered out to a certain extent, and the kick fixed distance dimension interval (that is, the distance interval with a fixed range on the distance dimension; for example, this interval can be -60cm to 60cm) of single-frame point cloud information. Each single frame of point cloud information can include a large number of point clouds. Different point clouds correspond to different distances, azimuths, and elevations. The information of these point clouds can be arranged by distance from near to far. Each echo signal corresponds to a single frame of point cloud information. After a period of time, multiple frames of point cloud information will be obtained.

(2) Determine whether the point cloud information meets the preset conditions, and if the point cloud information meets the preset conditions, mark the data frame corresponding to the point cloud information.

In this step, it is first judged whether there is a target point in the point cloud information of a single frame. If the number of target points in a single frame of point cloud information is 0, it is determined that the point cloud information does not meet the preset conditions, and the data frame is directly marked as num=0. If the number of target points in the single-frame point cloud information is not 0, and the distance corresponding to each target point is less than the preset distance threshold THr1, and the pitch angle corresponding to each target point is smaller than the preset pitch angle threshold THr2, then the The dataframe is marked with num=1, otherwise num=0. The tag values of each frame are put into KnickBuffer1 between buffers according to time order to form an array Matrix1 (for example, 0001111000).

(3) When the number of acquired data frames reaches the preset value n, the number of marked data frames in the first n data frames of the latest acquired data frames is counted by setting a sliding window KnickBuffer1 with a size of n. The sliding step of the sliding window KnickBuffer1 is 1. As the data frame is updated, KnickBuffer1 slides from left to right in the array Matrix1, and calculates the sum of values in the sliding window for each slide. Arrange the values of these sums in order to obtain the array Matrix2, which is the above-mentioned continuously updated sequence of numbers (for example, when n is 3, the sliding window slides on the above-mentioned Matrix1, and Matrix2 is 01233210).

(4) Set KnickBuffer2 between buffers with a preset capacity, and assign the values of the array Matrix2 to KnickBuffer2 in turn. The capacity of KnickBuffer2 is k, and when KnickBuffer2 reaches the capacity upper limit k, it will be cleared to realize that the length of the quantity sequence does not exceed the preset length threshold k.

(5) When the value of the element in KnickBuffer2 is 1, count the number of peaks in KnickBuffer2, the maximum peak value and the corresponding duration of the non-zero interval. If there is only one peak number (for example, there is only one 3 in the above-mentioned Matrix2, and there are often multiple peaks in the interference signal), and the corresponding duration of the non-zero interval (the time elapsed in the 123321 segment in the above-mentioned Matrix2) is less than the first If the preset threshold and the maximum peak value are greater than the second preset threshold, it is determined that a kick signal is detected.

(6) Send the CAN message to the door controller to control the opening of the door.

It should be understood that the sequence numbers of the steps in the above embodiments do not mean the order of execution, and the execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiment of the present application.

The embodiment of the present application also provides a kick signal recognition device 30, as shown in FIG. 3, the recognition device 30 includes:

The acquiring module 31 is configured to acquire point cloud information of each frame of echo data detected by the radar.

The judging module 32 is used to judge whether the point cloud information satisfies the preset condition, and if the point cloud information satisfies the preset condition, mark the data frame corresponding to the point cloud information.

The statistics module 33 is used to obtain a new data frame each time after the number of acquired data frames reaches the preset value n, and count the number of marked data frames in the latest acquired first n data frames to obtain a constantly updated quantity sequence.

The identification module 34 is configured to identify the kick signal according to the continuously updated quantity sequence.

Optionally, in a possible implementation manner, the judging module 31 is specifically used for:

Optionally, in a possible implementation manner, the identification module 34 is specifically used to:

Add the number of marked data frames in the latest acquired first n data frames as an update value to the existing number sequence to update the number sequence;

Obtain the detection frequency of the radar;

Count the number of values in the non-zero interval;

Optionally, in a possible implementation, after the kick signal is detected, the identification module 34 is also used to:

Optionally, in a possible implementation manner, the length of the quantity sequence does not exceed a preset length threshold k, and the statistics module 33 is also used for:

As shown in FIG. 4 , the embodiment of the present application also provides a terminal 40 . The terminal 40 includes a processor 41 , a memory 42 and a computer program 43 stored in the memory 42 and executable on the processor 41 . When the processor 41 executes the computer program 43 , the steps in the above embodiments of the kick signal recognition method are implemented, for example, steps S101 to S104 shown in FIG. 1 . Alternatively, when the processor 41 executes the computer program 43, it realizes the functions of the modules in the above-mentioned device embodiments, such as the functions of the modules 31 to 34 shown in FIG. 3 .

Exemplarily, the computer program 43 can be divided into one or more modules/units, and these modules/units can be stored in the memory 42 and executed by the processor 41 to complete and realize the functions provided by the embodiments of the present application. Technical solutions. These modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and these instruction segments can describe the execution process of the computer program 43 in the terminal 40 . For example, the computer program 43 may be divided into modules 31 to 34 shown in FIG. 3 .

The terminal 40 may be a computing device such as a desktop computer, a notebook, a palmtop computer, or a cloud server. The terminal 40 may include, but not limited to, a processor 41 and a memory 42 . Those skilled in the art can understand that FIG. 4 is only an example of the terminal 40, and does not constitute a limitation on the terminal 40. It may include more or less components than those shown in the figure, or combine certain components, or different components, such as Terminals may also include input and output devices, network access devices, buses, and so on.

Processor 41 may be a central processing unit (Central Processing Unit, CPU), can also be other general-purpose processors, digital signal processors (Digital Signal Processor, DSP), application specific integrated circuits (Application Specific Integrated Circuit, ASIC), field programmable gate array (Field-Programmable Gate Array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any other conventional processor or the like.

The storage 42 may be an internal storage unit of the terminal 40 , such as a hard disk or memory of the terminal 40 . The memory 42 can also be an external storage device of the terminal 40, such as a plug-in hard disk equipped on the terminal 40, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash memory card (Flash Card) Wait. Further, the memory 42 may also include both an internal storage unit of the terminal 40 and an external storage device. The memory 42 is used to store computer programs and programs and data required by the terminal. The memory 42 can also be used to temporarily store data that has been output or will be output.

Those skilled in the art can clearly understand that for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used for illustration. In practical applications, the above-mentioned functions can be assigned to different functional units, Completion of modules means that the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment may be integrated into one processing unit, or each unit may exist separately physically, or two or more units may be integrated into one unit, and the above-mentioned integrated units may adopt hardware It can also be implemented in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the present application. For the specific working process of the units and modules in the above system, reference may be made to the corresponding process in the foregoing method embodiments, and details will not be repeated here.

In the above-mentioned embodiments, the descriptions of each embodiment have their own emphases, and for parts that are not detailed or recorded in a certain embodiment, refer to the relevant descriptions of other embodiments.

Those skilled in the art can appreciate that the units and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed by hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the scope of the present application.

In the embodiments provided in this application, it should be understood that the disclosed device/terminal and method may be implemented in other ways. The device/terminal embodiments described above are only illustrative, and the division of modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, several units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In another point, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be in electrical, mechanical or other forms.

A unit described as a separate component may or may not be physically separated, and a component shown as a unit may or may not be a physical unit, that is, it may be located in one place, or may also be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

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

If an integrated module/unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application realizes all or part of the processes in the methods of the above embodiments, and can also be completed by instructing related hardware through computer programs, and the computer programs can be stored in a computer-readable storage medium. When executed by the processor, the steps in the above embodiments of the kick signal recognition method can be realized. Wherein, the computer program includes computer program code, and the computer program code may be in the form of source code, object code, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying computer program code, recording medium, U disk, removable hard disk, magnetic disk, optical disk, computer memory, read-only memory (Read-Only Memory, ROM), random access Memory (Random Access Memory, RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained on computer readable media may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer readable media does not include It is an electrical carrier signal and a telecommunication signal.

The above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: it can still apply to the foregoing embodiments Modifications to the technical solutions recorded, or equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of each embodiment of the application, and should be included in this application. within the scope of protection.

Claims

A kick signal identification method, characterized in that it comprises:

Obtain the point cloud information of each frame of echo data detected by the radar;

Judging whether the point cloud information satisfies a preset condition, if the point cloud information satisfies a preset condition, then marking the data frame corresponding to the point cloud information;

When the number of acquired data frames reaches the preset value n, each time a new data frame is acquired, the number of marked data frames in the latest acquired first n data frames is counted to obtain a continuously updated number sequence;

The kick signal is identified according to the constantly updated sequence of numbers.
The kick signal recognition method according to claim 1, wherein judging whether the point cloud information satisfies preset conditions includes:

Judging whether there is a target point in the point cloud information, if there is no target point in the point cloud information, then determining that the point cloud information does not meet the preset condition;

If there is a target point in the point cloud information, then determine the maximum distance and the maximum pitch angle according to the distance and pitch angle of each target point in the point cloud information relative to the radar;

If the maximum distance is less than a preset distance threshold, and the maximum pitch angle is smaller than a preset pitch angle threshold, it is determined that the point cloud information satisfies a preset condition;

If the maximum distance is not less than a preset distance threshold, or the maximum pitch angle is not smaller than a preset pitch angle threshold, it is determined that the point cloud information does not meet a preset condition.
The kick signal recognition method according to claim 1, wherein updating the sequence of numbers comprises:

Add the number of marked data frames in the first n data frames of the latest acquired data frame as an update value to the existing number sequence;

The kick signal is identified based on the continuously updated sequence of numbers, including:

Each time the quantity sequence is updated, it is judged whether the update value is 1;

If the update value is 1, count the number of peaks, the maximum peak value, and the duration corresponding to the non-zero interval in the quantity sequence after this update; wherein, the non-zero interval is the first update of the quantity sequence The interval between a non-zero value and the current update value;

If there is only one peak value, and the duration corresponding to the non-zero interval is less than a first preset threshold, and the maximum peak value is greater than a second preset threshold, it is determined that a kick signal is detected.
The kick signal recognition method according to claim 3, wherein the statistical method of the duration corresponding to the non-zero interval comprises:

Obtain the detection frequency of the radar;

Count the number of values in the non-zero interval;

A time length corresponding to the non-zero interval is determined according to the detection frequency and the number of values in the non-zero interval.
The kick signal recognition method according to claim 3, wherein, after the kick signal is detected, the kick signal recognition method further comprises:

All values in the current number sequence are deleted, and the operation of updating the number sequence and identifying kick signals according to the continuously updated number sequence is continued.
The kick signal recognition method according to any one of claims 1-5, wherein the length of the sequence of numbers does not exceed a preset length threshold k;

The kick signal identification method also includes:

If the length of the number sequence exceeds a preset length threshold k after an update, the first k values of the number sequence are deleted.
A kick signal recognition device is characterized in that it comprises:

An acquisition module, configured to acquire point cloud information of each frame of echo data detected by the radar;

A judging module, configured to judge whether the point cloud information satisfies a preset condition, and if the point cloud information satisfies a preset condition, mark the data frame corresponding to the point cloud information;

The statistical module is used to obtain a new data frame each time after the number of acquired data frames reaches the preset value n, count the number of marked data frames in the first n data frames of the latest acquired data frame, and obtain a continuously updated sequence of numbers;

The identification module is configured to identify the kick signal according to the continuously updated quantity sequence.
The kick signal recognition device according to claim 7, wherein the judging module is specifically used for:

Judging whether there is a target point in the point cloud information, if there is no target point in the point cloud information, then determining that the point cloud information does not meet the preset condition;

If there is a target point in the point cloud information, then determine the maximum distance and the maximum pitch angle according to the distance and pitch angle of each target point in the point cloud information relative to the radar;

If the maximum distance is less than a preset distance threshold, and the maximum pitch angle is smaller than a preset pitch angle threshold, it is determined that the point cloud information satisfies a preset condition;

If the maximum distance is not less than a preset distance threshold, or the maximum pitch angle is not smaller than a preset pitch angle threshold, it is determined that the point cloud information does not meet a preset condition.
A terminal, comprising a memory, a processor, and a computer program stored in the memory and operable on the processor, characterized in that, when the processor executes the computer program, the above claims 1 to 1 are implemented. The steps of any one of the methods described in 6.
A computer-readable storage medium, the computer-readable storage medium stores 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 6 above are implemented .