WO2023016350A1

WO2023016350A1 - Seat occupancy identification method and vehicle control method using same

Info

Publication number: WO2023016350A1
Application number: PCT/CN2022/110322
Authority: WO
Inventors: 包红燕; 李梦; 杨长林; 刘啸天; 李棋; 秦屹
Original assignee: 森思泰克河北科技有限公司
Priority date: 2021-08-12
Filing date: 2022-08-04
Publication date: 2023-02-16

Abstract

A seat occupancy identification method and a vehicle control method using same. The seat occupancy identification method comprises: sampling each antenna echo signal within a preset area, so as to obtain a time-domain echo signal set, wherein each antenna echo signal within the preset area is an echo signal that is obtained by means of performing detection on the preset area inside a vehicle; for each time-domain echo signal in the time-domain echo signal set, performing one-dimensional FFT processing on the time-domain echo signal, so as to obtain distance information of the time-domain echo signal; and according to the distance information of each time-domain echo signal in the time-domain echo signal set, determining valid echo signal sets respectively corresponding to seat occupancy areas inside the vehicle, and according to the valid echo signal sets respectively corresponding to the seat occupancy areas, respectively determining whether the seat occupancy area are occupied.

Description

Occupancy recognition method and vehicle control method using same

This patent application claims the priority of Chinese patent applications No. CN202110926413.2 and No. CN202110926416.6 submitted on August 12, 2021. The disclosure of the prior application is incorporated by reference in its entirety into this application.

technical field

The present application belongs to the technical field of radar, and in particular relates to an occupancy recognition method and a vehicle control method using the same.

Background technique

With the popularization of vehicles, vehicle safety has been paid more and more attention. As an important protective device to ensure the safety of drivers and passengers, seat belts are particularly important in vehicle safety. Vehicle security is gradually shifting from physical security to cyber security and safety assistance systems. At present, vehicle occupancy recognition (that is, judging whether a certain seat is occupied) is mostly detected by a pressure sensor, and then judged by the wearing state of the seat belt whether to issue an alarm. Or, collect the image information of a certain location through the camera, and then judge whether there is a person in the location, and then judge whether to issue an alarm based on the wearing status of the seat belt.

The misjudgment rate of the pressure sensor is high, which leads to a low accuracy rate of the seat belt warning. The camera has extremely high requirements on light, is easily affected by dust, etc., and has high cost, and also has the problem of high misjudgment rate. That is, the existing seat belt warning method is prone to misjudgment, and the accuracy of occupancy recognition is poor.

technical problem

The present application provides an occupancy recognition method and a vehicle control method using the same, aiming to solve the problems of easy misjudgment and poor occupancy recognition accuracy in existing seat belt warning methods.

technical solution

In a first aspect, the present application provides a method for occupancy identification, including:

Sampling each antenna echo signal in the preset area separately to obtain a time-domain echo signal set; each antenna echo signal in the preset area is an echo signal obtained by detecting a preset area inside the vehicle;

For each time-domain echo signal in the time-domain echo signal set, perform one-dimensional FFT (Fast Fourier Transform, Fast Fourier Transform) processing on the time-domain echo signal to obtain distance information of the time-domain echo signal;

According to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupancy area inside the vehicle, and according to the effective echo signal sets corresponding to each occupancy area, Determine whether each occupied area is occupied.

In a second aspect, the present application provides an occupancy recognition device, including:

The sampling module is used to sample each antenna echo signal in the preset area to obtain a time-domain echo signal set; each antenna echo signal in the preset area is the echo obtained by detecting the preset area inside the vehicle wave signal;

The transformation module is used for performing one-dimensional FFT processing on each time domain echo signal in the time domain echo signal set to obtain the distance information of the time domain echo signal;

The judging module is configured to determine the time domain echo signals corresponding to each occupying area inside the vehicle according to the distance information of each time domain echo signal in the time domain echo signal set, and determine the time domain echo signals corresponding to each occupying area respectively according to the distance information of each occupying area in the time domain echo signal set domain echo signals to determine whether each occupancy area is occupied.

In a third aspect, the present application provides a first millimeter-wave radar, 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-mentioned first aspect is realized. Steps of the placeholder recognition method.

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

In a fifth aspect, the present application provides a vehicle control method, including:

Acquire vehicle status signals; vehicle status signals include unlock status signals, driving status signals or locking status signals;

When the vehicle state signal is an unlocked state signal, send a detection signal to the first preset area; perform gesture recognition on the received echo signal in the first preset area, and control the vehicle to perform the corresponding preset operation according to the gesture recognition result ;

When the vehicle state signal is a driving state signal, send a detection signal to the first preset area and the second preset area; perform gesture recognition on the received echo signal in the first preset area, and control the vehicle according to the gesture recognition result Execute the corresponding preset operation; perform occupancy identification on the echo signal received in the second preset area, and determine whether to perform a seat belt warning according to the occupancy identification result;

When the vehicle state signal is a locked state signal, send a detection signal to the third preset area; perform life body identification on the received echo signal in the third preset area, and determine whether to perform a personnel detention alarm according to the life body identification result .

In a sixth aspect, the present application provides a vehicle control device, including:

The acquiring module is used to acquire the vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal;

The first control module is configured to send a detection signal to the first preset area when the vehicle state signal is an unlocked state signal; perform gesture recognition on the received echo signal in the first preset area, and control the vehicle according to the gesture recognition result The vehicle performs the corresponding preset operation;

The second control module is configured to send detection signals to the first preset area and the second preset area when the vehicle status signal is a driving status signal; perform gesture recognition on the received echo signal in the first preset area, And control the vehicle to perform the corresponding preset operation according to the gesture recognition result; perform occupancy recognition on the echo signal received in the second preset area, and determine whether to perform a seat belt warning according to the occupancy recognition result;

The third control module is configured to send a detection signal to the third preset area when the vehicle status signal is a locked status signal; perform life body identification on the received echo signal in the third preset area, and identify the life body according to the life body identification As a result, it is determined whether to carry out an alarm for personnel retention.

In a seventh aspect, the present application provides a second millimeter-wave radar, 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 vehicle described in the fifth aspect above The steps of the control method.

In an eighth aspect, the present application provides a second computer-readable storage medium, where a computer program is stored in the second computer-readable storage medium, and when the computer program is executed by a processor, the steps of the vehicle control method described in the above-mentioned first aspect are realized.

Beneficial effect

Compared with the prior art, the occupancy identification method provided by the present application realizes occupancy identification through the following steps: separately sample the echo signals of each antenna in the preset area to obtain a time-domain echo signal set; the preset area Each antenna echo signal is an echo signal obtained by detecting a preset area inside the vehicle; for each time domain echo signal in the time domain echo signal set, perform a one-dimensional FFT transformation on the time domain echo signal processing to obtain the distance information of the time-domain echo signal; determine the effective echo signal sets corresponding to each occupying area inside the vehicle according to the distance information of each time-domain echo signal in the time-domain echo signal set, and according to each The valid echo signal sets corresponding to the occupied areas respectively determine whether each occupied area is occupied. During the above occupancy identification process, the antenna echo signal can accurately reflect the situation in the vehicle; by processing the antenna echo signal to determine whether the occupancy area is occupied, the accuracy of occupancy identification can be improved, thereby preventing misjudgment , Timely remind drivers and passengers to fasten their seat belts to ensure their personal safety.

Compared with the prior art, the vehicle control method provided by the present application controls the vehicle through the following steps: acquiring a vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal; when it is an unlocked state signal, Perform gesture recognition on the echo signal received in the first preset area, and control the vehicle to perform the corresponding preset operation according to the gesture recognition result; when it is a driving state signal, the received echo signal in the first preset area Perform gesture recognition on the signal, and control the vehicle to perform the corresponding preset operation according to the gesture recognition result, perform occupancy recognition on the echo signal received in the second preset area, and determine whether to perform a seat belt warning according to the occupancy recognition result; When the signal is in a locked state, the received echo signal in the third preset area is identified as a living body, and it is determined whether to perform a personnel detention alarm according to the result of the living body identification. In the above vehicle control process, when the vehicle is in different states, the millimeter-wave radar is used to obtain the echo signals in different areas, and the echo signals are analyzed to realize the gesture recognition of the vehicle, the judgment of the seat belt warning and the judgment of the personnel stranded warning; Therefore, according to the different states of the vehicle, the multifunctional intelligent auxiliary control of the vehicle can be realized, the control mode of the vehicle becomes diversified, the vehicle is more intelligent, and the user experience is optimized.

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 occupancy identification method provided by the embodiment of the present application;

Fig. 2 is a schematic diagram of the structural composition of the occupancy recognition device provided by the embodiment of the present application;

Fig. 3 is a schematic diagram of a first millimeter-wave radar provided by an embodiment of the present application.

Fig. 4 is an implementation flow chart of the vehicle control method provided by the embodiment of the present application;

Fig. 5 is a schematic diagram of the structural composition of the vehicle control device provided by the embodiment of the present application;

FIG. 6 is a schematic diagram of a second millimeter-wave radar provided by an embodiment of the present application.

Detailed ways

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.

Both the occupancy recognition method and the vehicle control method provided in the present application can be implemented using millimeter wave radar. Millimeter wave radar can be installed on the roof of the vehicle. Millimeter wave radar can use monolithic microwave integrated circuit (Monolithic Microwave Integrated Circuit, MMIC) and multiple input multiple output (Multiple Input Multiple Output, MIMO) technology. MMIC's highly integrated processor and sensors can reduce the size of mmWave radar. The arrangement of the MIMO array antenna can not only reduce the size of the antenna, but also ensure good angular resolution.

The millimeter-wave radar can adopt the CAN (Controller Area Network, controller area network) communication method, and supports sleep wake-up network management and remote firmware flashing and upgrading functions. At the same time, advanced signal processing technology can be used to enable millimeter-wave radar to achieve multi-dimensional resolution such as distance, speed, azimuth and elevation angle, and further improve the recognition performance of targets in the vehicle.

Compared with externally installed sensors such as ultrasonic waves and cameras, since the electromagnetic waves emitted by the radar can penetrate the roof material of the vehicle, the radar can be installed in a non-exposed manner, that is, the radar can be installed between the inner roof of the vehicle and the outer sheet metal of the vehicle. This non-exposed installation method not only prevents the car body material from being cut and damaged, but also facilitates the installation of the radar, and makes the radar hidden between the ceiling and the sheet metal, so that passengers cannot feel the existence of the radar device at all, and will not give Passengers feel stressed.

Referring to FIG. 1 , it shows a flow chart of realizing the occupancy recognition method provided by the present application. As shown in FIG. 1 , in one embodiment, the occupancy identification method provided by the present application may include steps S101 to S103. The three steps are described below.

S101. Sampling each antenna echo signal in the preset area separately to obtain a time-domain echo signal set; each antenna echo signal in the preset area is an echo signal obtained by detecting a preset area inside the vehicle .

Optionally, the occupancy recognition method provided in the present application is executed by a millimeter-wave radar, and the preset area is an area that the millimeter-wave radar can detect inside the vehicle. For example, the preset area may include a front seat area inside the vehicle, and/or a rear seat area inside the vehicle. Each antenna corresponds to one time-domain echo signal, and the time-domain echo signals of all antennas form a time-domain echo signal set.

In the field of radar, three-dimensional data of distance dimension, azimuth dimension and pitch dimension can be used to represent the three-dimensional spatial position of the measured object in spherical coordinates. The sampling described in step S101 may be to perform ADC (Analog-to-Digital Converter) sampling on the antenna echo signal along the distance dimension and the time dimension for each antenna; when sampling, a fast time sampling method may be selected.

In this application, the millimeter wave radar includes multiple transmitting antennas and multiple receiving antennas arranged in an array. When the millimeter-wave radar is in working state, the millimeter-wave radar transmits multiple detection signals to the interior of the vehicle through multiple transmitting antennas, and receives corresponding multiple antenna echo signals through multiple receiving antennas.

Specifically, the millimeter-wave radar is powered on, and the transmitting antenna transmits electromagnetic waves of a specific frequency to the preset area; the electromagnetic waves are reflected by objects, and the reflected electromagnetic waves carry target information. The target information includes the distance of the measured object in the preset area , speed, and spatial angle information; the receiving antenna receives the reflected electromagnetic wave (ie, echo signal), and samples the reflected electromagnetic wave to obtain a time-domain echo signal.

S102. For each time-domain echo signal in the time-domain echo signal set, perform one-dimensional FFT (Fast Fourier Transform, Fast Fourier Transform) processing on the time-domain echo signal to obtain the distance of the time-domain echo signal information.

In step S102, the one-dimensional FFT processing can transform the time-domain echo signal into the frequency-domain echo signal, and then obtain the distance information of the time-domain echo signal in the preset area, that is, the time-domain echo signal can be obtained at The distance distribution of the preset area.

S103, according to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupancy area inside the vehicle, and according to the effective echo signals corresponding to each occupancy area set to determine whether each occupancy area is occupied.

The occupied area mentioned in step S103 may be a part of the preset area; for example, the preset area may be the front seat space inside the vehicle, and the occupied area may be the main driving area and/or the co-driving area. The occupancy area can be understood as the occupancy area is occupied; for example, one occupancy area is the co-pilot, and the occupancy area is occupied by the co-pilot.

To sum up, steps S101 to S103 perform occupancy identification through the following steps: each antenna echo signal in the preset area is sampled separately to obtain a time-domain echo signal set; each antenna echo signal in the preset area is a pair of The echo signal obtained by detecting the preset area inside the vehicle; for each time domain echo signal in the time domain echo signal set, perform one-dimensional FFT processing on the time domain echo signal to obtain the time domain echo signal Distance information; according to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupancy area inside the vehicle, and according to the effective echo signals corresponding to each occupancy area The signal set is used to determine whether each occupied area is occupied. In the above process of occupancy recognition, the antenna echo signal can accurately reflect the situation inside the vehicle; by processing the antenna echo signal, it is judged whether the occupancy area is occupied, which can improve the accuracy of occupancy recognition and prevent misjudgment. Timely remind drivers and passengers to fasten their seat belts to ensure their personal safety.

In an embodiment of the present application, each time-domain echo signal in the time-domain echo signal set includes echo signals of multiple sampling points; the distance information of the time-domain echo signal includes the corresponding The distance value of the echo signal of multiple sampling points.

In the above S103, "according to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupying area inside the vehicle", may include the following steps:

S1031, for each time-domain echo signal in the time-domain echo signal set, from all distance values in the time-domain echo signal, select an echo signal at a sampling point within a preset range as the time-domain echo signal The effective echo signal corresponding to the wave signal;

S1032. Perform two-dimensional DOA (Direction Of Arrival, direction of arrival) estimation on each effective echo signal, and obtain position information of sampling points corresponding to each effective echo signal;

S1033. According to the location information of the sampling points corresponding to each effective echo signal, determine the effective echo signal sets corresponding to each occupied area inside the vehicle.

The preset range described in step S1031 may be a range not smaller than the first preset distance value and not larger than the second preset distance value; wherein, the first preset distance value is smaller than the second preset distance value. The preset range can be determined according to the distance between the passenger and the millimeter wave radar.

Exemplarily, the distance between the passenger and the millimeter-wave radar is greater than 0.5m, so the preset range can be set to 0.5m~1.5m. In this way, step S1031 selects time-domain echo signals whose distance values are in the range of 0.5m-1.5m as effective echo signals. The area within the preset range may be referred to as an effective area inside the vehicle, and each of the effective echo signals is an echo signal within the effective area. Step S1032 obtains position information of each effective echo signal by processing each effective echo signal in the effective area. The location information may include elevation angle information and azimuth angle information. Step S1033, according to the location information of each effective echo signal (for example, pitch angle information and azimuth angle information), associate each effective echo signal with each occupancy area, (that is, determine which occupancy area each effective echo signal comes from bit area), and then determine the effective echo signal set corresponding to each occupied area. According to the effective echo signal set corresponding to the occupied area, it can be further judged whether each occupied area is occupied.

Optionally, each sampling point corresponds to an actual point in a preset area. In S1032, two-dimensional DOA estimation in azimuth (horizontal) and pitch (longitudinal) directions between multiple antennas can be performed on each effective echo signal to obtain the position information of the sampling points corresponding to each effective echo signal, namely The position information of each sampling point within the preset distance range can be obtained. Through two-dimensional DOA estimation, the power of the signal in the specified direction can be enhanced, and at the same time, sidelobe cancellation can be performed on the antenna to reduce clutter interference.

Exemplarily, the process of two-dimensional DOA estimation can be:

Let the steering vector of the target azimuth angle θ be α , and the covariance matrix of the space-time sampling data of each azimuth R _i array be R , then the optimal weight coefficient W = μRα , where μ is a constant; then find min( W ^H RW ) θ is the best target direction θ . In the same way, the pitch direction Ψ is obtained, that is, the two-dimensional DOA estimation of azimuth and pitch is completed.

With the millimeter-wave radar as the center, the positions of each occupied area relative to the millimeter-wave radar are different. For example, the position of the main driver relative to the millimeter-wave radar is different from that of the co-pilot relative to the millimeter-wave radar. In step S1033, each occupancy area inside the vehicle and the time-domain echo signal corresponding to each occupancy area may be determined according to the location information of the sampling points corresponding to each effective echo signal.

In one embodiment of the present application, the above S103 of "determining whether each occupied area is occupied according to the effective echo signal sets corresponding to each occupied area" may include the following steps:

S1034. Obtain point cloud information of each occupied area according to the effective echo signal sets corresponding to each occupied area;

S1035. For each occupied area, calculate the fretting speed of each point cloud in the occupied area according to the point cloud information of the occupied area, and determine the fretting speed of each point cloud in the occupied area. Whether the occupied area is occupied.

Optionally, each occupancy area may correspond to a piece of point cloud information, and the point cloud information may include three-dimensional coordinates of each point cloud corresponding to the occupancy area. In S1035, according to the point cloud information of the occupied area, the fretting velocity of each point cloud of the occupied area may be calculated by means of existing technologies.

Optionally, each occupancy area may also include multiple point cloud information. Each point cloud information includes the three-dimensional coordinates of each point cloud therein. Exemplarily, according to the layout of the occupancy area of the vehicle seat, the time-domain echo signals including distance, azimuth, and elevation angle on each occupancy area can be pre-extracted to obtain the point cloud of each occupancy area information.

In one embodiment of the present application, "determine whether the occupied area is occupied according to the fretting speed of each point cloud of the occupied area" in the above S1035 may include the following steps:

S1036, if in the occupied area, the number of point clouds whose inching speed is greater than the preset inching speed is greater than the preset number, then it is determined that the occupied area is occupied.

Correspondingly, if the number of point clouds whose inching speed is greater than the preset inching speed in the occupied area is not greater than the preset number, it is determined that the occupied area is not occupied.

In the embodiment corresponding to S1036, it is judged whether the occupied area is occupied according to the two conditions of the fretting speed and the number of point clouds, which can eliminate some occasional interference factors, which is more accurate than the judgment of a single condition.

In an embodiment of the present application, each time-domain echo signal in the time-domain echo signal set includes echo signals of multiple sampling points;

In step S102, before "performing one-dimensional FFT processing on the time-domain echo signal", the occupancy identification method provided by the present application may further include the following steps:

S104, calculating the signal average value of the echo signals at each sampling point in the time-domain echo signal;

S105, making a difference between the echo signal of each sampling point in the time domain echo signal and the corresponding signal average value, to obtain a filtered time domain echo signal of the time domain echo signal;

Correspondingly, in step S102, "performing one-dimensional FFT processing on the time-domain echo signal to obtain the distance information of the time-domain echo signal" includes the following steps:

S106. Perform one-dimensional FFT processing on the filtered time-domain echo signal to obtain distance information of the time-domain echo signal.

The process described in steps S104 to S106 realizes the static clutter removal of the echo signal in the time domain. Since the body micro-movement signal is a weak target, it is easily interfered by the complex echo of the cockpit. Steps S104 to S106 improve the accuracy of occupancy identification by performing static clutter removal on the time-domain echo signal.

In one embodiment of the present application, in step S104, the formula for obtaining the signal average value of the echo signal at the sampling point is:

Wherein, the time-domain echo signal is S = [ S ₁ , S ₂ , ..., S _n ], S _i = [ S _i S ₁ , S _i S ₂ , ..., S _i S _j , ..., S _i S _m ]; S _meani is the signal mean value of the echo signal S _i of the i -th sampling point in the time domain echo signal, i =1～ n , j =1～ m , n is the time domain echo signal The number of echo signals of the sampling points included, m is the number of time points, S _i S _m is the signal of the echo signal S _i at time m .

Exemplarily, for a certain time-domain echo signal, an average value along the time dimension of each sampling point in the distance dimension may be calculated, and the average value may be subtracted to obtain a filtered time-domain echo signal.

For example, suppose the time-domain echo signal of an antenna is S =[ S ₁ , S ₂ ,…, S _n ], where S _i =[ S _i S ₁ , S _i S ₂ ,…, S _i S _j ,…, S _i S _m ], i =1～ n , j =1～ m , n is the sampling point in the distance dimension, m is the sampling point in the time dimension, the mean value S _mean =[ S _mean ₁ , S _mean ₂ ,…, S _mean _n ],

,

The time-domain echo signal S '=[ S ₁ - S _mean , S ₂ - S _mean , ..., S _n - S _mean ] after removing static clutter is obtained; in this way, the interference of static clutter can be reduced.

In one embodiment of the present application, the occupancy identification method may further include the following steps:

S107, sending the occupancy determination results of each occupancy area to the vehicle's central control system (referred to as "vehicle central control");

S108, for the occupancy determination result of each occupancy area, when the occupancy determination result is that the occupancy area is occupied, and the vehicle central control detects that the seat belt of the occupancy area is not fastened, and detects that the vehicle When the speed of the vehicle is greater than the preset speed threshold, the audible and visual warning of the seat belt in the occupied area will be performed.

In step S108, the vehicle's millimeter-wave radar can send the occupancy determination result to the vehicle's central control, and the vehicle's central control determines whether to issue a seat belt audible and visual warning based on the occupancy determination result and in combination with the other two conditions.

Corresponding to step S108, when the occupancy determination result is that the occupancy area is not occupied, or the vehicle central control detects that the seat belt in the occupancy area is fastened, or detects that the speed of the vehicle is not greater than the preset speed threshold, do not proceed. Seat belt sound and light warning. In one embodiment, through the occupancy recognition method provided in this application, the process of performing seat belt warning may include the following six steps:

Step 1. The millimeter-wave radar sends detection signals to the preset area in the vehicle through multiple antennas, and samples the echo signals received from each antenna to obtain a time-domain echo signal set.

Step 2: Static clutter removal is performed on each of the time-domain echo signals in the time-domain echo signal set to obtain a filtered time-domain echo signal set.

Step 3: Perform one-dimensional FFT processing on the time-domain echo signals in the filtered time-domain echo signal set to obtain distance information of each time-domain echo signal.

Step 4: According to the distance information of each time-domain echo signal, determine which occupancy area each time-domain echo signal corresponds to and the effective echo signal set corresponding to each occupancy area. From the distance information, select time-domain echo signals within a preset range as effective echo signals; perform two-dimensional DOA estimation on each effective echo signal, and obtain sampling points corresponding to each effective echo signal respectively The position information of each effective echo signal; determine the point cloud information of each occupied area according to the position information of the sampling points corresponding to each effective echo signal.

Step 5. For each occupied area, calculate the fretting speed of each point cloud in the occupied area according to the point cloud information of the occupied area, and determine Whether the occupied area is occupied.

Step 6: Send the occupancy determination result to the vehicle central control, and instruct the vehicle central control whether to issue seat belt audible and visual warnings.

It should be understood that in the above embodiment of the occupancy identification method, the size of the sequence number of each step does 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 be used in the embodiment of the present application. The implementation process constitutes no limitation.

The following are device embodiments corresponding to the occupancy recognition method provided in this application. For details not described in detail therein, reference may be made to the above embodiments of the occupancy recognition method.

Fig. 2 is a schematic diagram of the structural composition of the occupancy recognition device provided by the present application. For ease of description, FIG. 2 only shows the parts related to the present application, which are described in detail as follows.

As shown in FIG. 2 , the occupancy identification device 20 may include a sampling module 201 , a transformation module 202 and a judging module 203 .

The sampling module 201 is used to execute step S101, that is, to sample each antenna echo signal in the preset area respectively to obtain a time-domain echo signal set; each antenna echo signal in the preset area is a preview of the vehicle interior The echo signal obtained by setting the area for detection.

The transformation module 202 is configured to execute step S102, that is, for each time-domain echo signal in the time-domain echo signal set, perform one-dimensional FFT processing on the time-domain echo signal to obtain distance information of the time-domain echo signal.

The judging module 203 is used to execute step S103, that is, determine the effective echo signal sets corresponding to each occupied area inside the vehicle according to the distance information of each time-domain echo signal in the time-domain echo signal set, and The valid echo signal sets corresponding to the areas respectively determine whether each occupied area is occupied.

In an embodiment of the present application, each time-domain echo signal in the time-domain echo signal set includes echo signals of multiple sampling points; the distance information of the time-domain echo signal includes the corresponding The distance value of the echo signal of multiple sampling points. In this embodiment, the judging module 203 may include an effective signal selection unit, an estimation unit, and an effective signal determination unit.

The effective signal selection unit is used to perform step S1031, that is, for each time-domain echo signal in the time-domain echo signal set, from all distance values in the time-domain echo signal, select a distance within a preset range The echo signal at the sampling point is used as an effective echo signal corresponding to the time-domain echo signal.

The estimating unit is configured to execute step S1032, that is, perform two-dimensional DOA estimation on each effective echo signal respectively, to obtain position information of sampling points corresponding to each effective echo signal.

The effective signal determining unit is configured to perform step S1033, that is, determine effective echo signal sets corresponding to respective occupied areas inside the vehicle according to position information of sampling points corresponding to respective effective echo signals.

In an embodiment of the present application, the judging module 203 may further include a point cloud information determination unit and a calculation unit.

The point cloud information determining unit is configured to execute step S1034, that is, obtain point cloud information of each occupied area according to the effective echo signal sets corresponding to each occupied area.

The calculation unit is used to execute step S1035, that is, for each occupied area, calculate the fretting velocity of each point cloud of the occupied area according to the point cloud information of the occupied area, and calculate the fretting speed of each point cloud of the occupied area according to the The fretting speed of each point cloud determines whether the occupied area is occupied.

In one embodiment of the present application, the calculation unit is further configured to execute step S1036, that is, if the number of point clouds whose inching speed is greater than the preset inching speed in the occupied area is greater than the preset number, then It is determined that the occupied area is occupied.

In one embodiment of the present application, each time domain echo signal in the time domain echo signal set includes echo signals of multiple sampling points; in this embodiment, the occupancy identification device 20 may also include a preprocessing module and difference modules.

The pre-processing module is used to execute step S104, that is, calculating the signal average value of the echo signals at each sampling point in the time-domain echo signal.

The difference module is used to execute step S105, that is, the echo signal of each sampling point in the time-domain echo signal is respectively different from the corresponding signal average value to obtain the filtered time-domain echo signal time-domain echo signal.

Correspondingly, the transformation module 202 is further configured to execute step S106, that is, perform one-dimensional FFT processing on the filtered time-domain echo signal to obtain distance information of the time-domain echo signal.

In an embodiment of the present application, the occupancy identification device 20 may further include an occupancy sending module.

The occupancy sending module is used to execute steps S107 and S108, that is, to send the occupancy determination results of each occupancy area to the vehicle central control; for the occupancy determination results of each occupancy area, when the occupancy determination result When the occupancy area is occupied, and the vehicle central control detects that the seat belt in the occupancy area is not fastened, and when the speed of the vehicle is detected to be greater than the preset speed threshold, the audible and visual warning of the seat belt in the occupancy area will be performed. .

Fig. 3 is a schematic diagram of the first millimeter-wave radar provided by the present application. As shown in FIG. 3 , the first millimeter wave radar 30 includes a processor 300 , a memory 301 , and a computer program 302 stored in the memory 301 and operable on the processor 300 . When the processor 300 executes the computer program 302, it can realize the steps in the above embodiments of the occupancy recognition method, for example, steps S101 to S103 shown in FIG. 1 . Alternatively, when the processor 300 executes the computer program 302, the functions of the modules/units in the above-mentioned device embodiments are realized, for example, the functions of the modules 201 to 203 shown in FIG. 2 .

Exemplarily, the computer program 302 can be divided into one or more modules/units, and these modules/units can be stored in the memory 301 and executed by the processor 300, so as to realize the inventive concept of the present application. These modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and these instruction segments are used to describe the execution process of the computer program 302 in the first millimeter wave radar 30 . For example, the computer program 302 may be divided into instruction segments corresponding to the modules 201 to 203 shown in FIG. 2 .

The first millimeter wave radar 30 may include, but not limited to, a processor 300 and a memory 301 . Those skilled in the art can understand that FIG. 3 is only an example of the first millimeter-wave radar 30 , and does not constitute a limitation to the first millimeter-wave radar 30 . The first millimeter wave radar may include more or fewer components than shown, or combine certain components, or different components.

The present application also provides a first computer-readable storage medium. The storage medium stores a computer program. When the computer program is executed by the processor, the steps described in the embodiments corresponding to the above-mentioned occupancy identification method can be realized, and the occupancy identification of the vehicle can be realized.

The present application also provides a vehicle control method.

With the development of society and the improvement of people's living standards, vehicles are used as a means of transportation, whether in families, individuals, companies, collectives, etc., the popularity of cars continues to rise. The driving safety of vehicles has attracted more and more attention.

Driving safety is gradually shifting from physical safety to network safety and safety assistance systems. At present, the gesture control of the vehicle can collect images through the camera, and then recognize the image; then recognize the movement of the person, and then perform gesture control according to the recognition result. However, this control method is relatively simple and cannot meet user needs. The vehicle control method provided in the present application can realize gesture recognition through vehicle radar. Not only that, but the method can also realize the identification of living body and occupancy, so that the control mode of the vehicle becomes diversified, and the vehicle is also more intelligent.

Fig. 4 is a flow chart of the implementation of the vehicle control method provided by the present application. As shown in Fig. 4, the vehicle control method provided by the present application may include steps S401 to S404. The four steps are described below.

S401. Acquire a vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal.

Optionally, the vehicle control method provided in this application is executed by a millimeter-wave radar. The unlocked status signal indicates that the vehicle has been unlocked, but has not been started, and the vehicle is in a stationary state. The driving state signal indicates that the vehicle is running and the vehicle is in motion. The locked state signal indicates that the vehicle's power source (such as the engine or electric motor) has stopped, the doors are locked, and the vehicle is stationary.

Optionally, the unlocked state signal may be a signal sent by a car key, or a signal sent by a main driver's door lock. The locked state signal can be a signal sent by the car key, or a signal sent by the main driver's door lock.

S402. When the vehicle state signal is an unlocked state signal, send a detection signal to the first preset area; perform gesture recognition on the received echo signal in the first preset area, and control the vehicle to perform a corresponding preset according to the gesture recognition result. set operation.

Optionally, the first preset area may be a fixed gesture area. The interior equipment of the vehicle may include a sunroof or an air conditioner and the like. Gesture recognition in the unlocked state of the vehicle allows the driver to use gestures to turn on or off various functions of the vehicle, or to control various parameters of the vehicle, thus (especially when the vehicle is driving) to make the driver's attention more focused Focus more on observing the surrounding environment of the vehicle to better ensure driving safety.

Specifically, when the millimeter-wave radar is powered on, when the millimeter-wave radar obtains the unlock status signal, the transmitting antenna of the millimeter-wave radar transmits electromagnetic waves of a specific frequency to the fixed gesture area; the electromagnetic waves are reflected by objects, and the reflected electromagnetic waves (ie Echo signal) carries various information of the fixed gesturing area; the receiving antenna of the millimeter wave radar receives the echo signal of the fixed gesturing area, and performs gesture recognition according to the echo signal; and then controls the vehicle according to the gesture recognition result Execute the corresponding preset operation. For example, the vehicle's air conditioner or sunroof can be controlled according to the result of gesture recognition.

S403. When the vehicle state signal is a driving state signal, send a detection signal to the first preset area and the second preset area; perform gesture recognition on the received echo signal in the first preset area, and perform gesture recognition based on the gesture recognition result The vehicle is controlled to perform a corresponding preset operation; occupancy identification is performed on the echo signal received in the second preset area, and whether to perform a seat belt warning is determined according to the occupancy identification result.

It should be noted that, in step S403, when identifying the occupancy of the echo signal in the second preset area, the occupancy identification method provided in the present application may be used, or the occupancy identification method in the prior art may be used.

As mentioned above, the second preset area is an area within the vehicle that can be detected by the millimeter-wave radar. For example, the second preset area may include a front seat area inside the vehicle, and/or a rear seat area inside the vehicle.

Specifically, when the vehicle state signal acquired by the millimeter-wave radar is a driving state signal, gesture recognition and/or occupancy recognition may be performed. Gesture recognition in the driving state of the vehicle can make the driver pay more attention to driving safety, avoid auxiliary operations such as switching the air conditioner or sunroof from distracting the driver's attention, and ensure the driving safety of the vehicle. In the driving state of the vehicle, the occupancy recognition through the detection signal can make the vehicle judge whether to carry out the seat belt warning, so as to remind the drivers and passengers who are not wearing seat belts in the driving state to wear seat belts, and provide safety protection for the drivers and passengers. Reduce or avoid injuries in the event of traffic accidents.

Specifically, the millimeter-wave radar works when it is powered on. When the millimeter-wave radar acquires the driving status signal, the transmitting antenna of the millimeter-wave radar emits electromagnetic waves of a specific frequency to the second preset area; the electromagnetic waves are reflected by objects, and the reflected electromagnetic waves ( That is, the echo signal) carries various information of the second preset area; the receiving antenna of the millimeter-wave radar receives the echo signal of the second preset area, and performs occupancy identification according to the echo signal, and then judges whether Carry out seat belt warning.

S404. When the vehicle state signal is a locked state signal, send a detection signal to the third preset area; perform life body identification on the received echo signal in the third preset area, and determine whether to carry out personnel identification according to the life body identification result. Stay alert.

Optionally, the third preset area is a specific area inside the vehicle, which may include the passenger area and the trunk area, or may only be the passenger area. Identifying living organisms when the vehicle is locked can effectively prevent living organisms such as children or pets from being left in the vehicle and prevent tragedies from happening.

Specifically, the millimeter-wave radar is powered on and works. When the millimeter-wave radar acquires the signal of the locked state, the transmitting antenna of the millimeter-wave radar transmits electromagnetic waves of a specific frequency to the third preset area; the electromagnetic waves are reflected by objects, and the reflected electromagnetic waves ( That is, the echo signal) carries various information of the third preset area; the receiving antenna of the millimeter-wave radar receives the echo signal of the third preset area, and performs living body identification according to the echo signal, and then judges whether Carry out personnel stranded alarm.

Optionally, the personnel retention alarm can realize the anti-forgetting function of children. The millimeter-wave radar used in this application is not only suitable for detecting large-scale moving targets, but also has high detection accuracy for chest micro-movement signals. The millimeter-wave radar uses a large bandwidth of 4GHz, which can convert small chest displacements into obvious phase changes. When the frequency and correlation information of the phase meet the threshold requirements, it is determined that there is a real target, that is, there is a living body in the vehicle.

To sum up, steps S401 to S404 carry out vehicle control through the following steps: acquire the vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal; The area sends detection signals, performs gesture recognition on the received echo signals in the first preset area, and controls the vehicle to perform corresponding preset operations according to the gesture recognition results; Send detection signals from the set area and the second preset area, perform gesture recognition on the echo signal received in the first preset area, and control the vehicle to perform the corresponding preset operation according to the gesture recognition result, and perform gesture recognition on the received second preset area. Set the echo signal of the area for occupancy identification, and determine whether to issue a seat belt warning according to the occupancy identification result; The echo signal in the preset area is used to identify the living body, and according to the result of the living body identification, it is determined whether to issue an alarm for personnel retention. In the above vehicle control process, the echo signals in different areas are obtained through the millimeter wave radar, and the echo signals are analyzed to realize the gesture recognition of the vehicle, the judgment of the safety belt warning and the judgment of the personnel stranded warning; thus, it can be based on different states of the vehicle. , realize the multi-functional intelligent auxiliary control of the vehicle, diversify the control methods of the vehicle, make the vehicle more intelligent, and optimize the user experience.

In one embodiment of the present application, as described above (steps S107 and S108), the "determining whether to issue a seat belt warning based on the occupancy recognition result" in the above S403 may include the following steps:

S4031: Send the occupancy recognition result to the vehicle central control (that is, the vehicle's central control system), when the occupancy recognition result is that the occupancy area is occupied, and the vehicle central control detects the seat belt in the occupancy area When it is not fastened and it is detected that the driving speed of the vehicle is greater than a preset speed threshold, a seat belt warning is issued in the occupied area; wherein the occupied area is an area in the second preset area.

As mentioned above, the occupied area may be the main driving area and/or the co-driving area, both of which belong to the second preset area. The alarm form can be sound and light alarm.

Exemplarily, there may be multiple occupancy areas, and step S4031 may send the occupancy recognition results of each occupancy area to the vehicle central control.

For the occupancy recognition result of each occupancy area, when the occupancy identification result is that the occupancy area is occupied, and the vehicle central control detects that the seat belt of the occupancy area is not fastened, and detects that the vehicle When the speed of the vehicle is greater than the preset speed threshold, the audible and visual warning of the seat belt in the occupied area will be carried out.

Optionally, when the occupancy recognition result shows that the occupancy area is not occupied, or it is detected that the seat belt in the occupancy area has been fastened, or when it is detected that the speed of the vehicle is not greater than the preset speed threshold, no seat belt is performed. alarm.

In one embodiment of the present application, the "determining whether to perform a personnel detention alarm based on the result of the living body identification" in the above S404 may include the following steps:

S4041. Send the living body identification result to the vehicle central control, and when the living body identification result shows that there is a living body in the third preset area, perform an alarm for people staying in the third preset area.

Correspondingly, when the result of the identification of the living body is that there is no living body in the third preset area, an alarm for personnel staying in the third preset area is not performed.

Optionally, if a living body is detected in the vehicle, the identification result of the living body can be sent to the vehicle central control through the CAN bus, and the vehicle will be controlled to give a double-flashing whistle alarm; at the same time, the vehicle central control can send the alarm to The information is sent to the client's mobile phone, and a double alarm is issued to further protect the safety of stranded children.

In one embodiment of the present application, the vehicle control method may further include the following steps:

S405, recording and uploading the seat belt warning and personnel detention warning;

S406. Sending the people retention alarm to the user terminal.

The above two steps record the seat belt warning and personnel retention warning, so that the generation and application process of vehicle warning information can be further optimized through data analysis.

In one embodiment of the present application, when the vehicle state signal is a locked state signal, the vehicle control method further includes the following steps:

S407. When the duration of the locked state signal is greater than the preset time threshold, stop sending the detection signal to the third preset area.

Exemplarily, the working logic of vehicle control can be expressed as:

When the vehicle is unlocked, the millimeter-wave radar can realize the gesture recognition function, and then control the sunroof switch and the temperature of the air conditioner;

When the vehicle is running, the millimeter-wave radar detects whether there is a person on the seat. When the vehicle speed is greater than a certain speed and there are people without seat belts, an audible and visual alarm will be issued to remind drivers and passengers to fasten their seat belts;

When the vehicle is locked, within 30 minutes after the self-locking action occurs, it will detect whether there are children stranded in the vehicle to prevent the occurrence of high temperature suffocation accidents. In general, the working time can be set by the user (for example, the above-mentioned 30min); after the working time is over, the millimeter-wave radar enters the sleep mode, the working current is <100uA, and the power consumption is extremely low, which meets the vehicle safety requirements.

In one embodiment of the present application, as described above (steps S101 to S103), the "occupancy identification of the received echo signal in the second preset area" in the above S403 may include the following steps S4031 to S4033. The three steps are described below.

S4031. Sampling each antenna echo signal in the second preset area respectively to obtain a time-domain echo signal set; each antenna echo signal in the second preset area is a second preset area inside the vehicle. The detected echo signal.

Optionally, each antenna corresponds to one time-domain echo signal, and the time-domain echo signals of all antennas form a time-domain echo signal set. In the field of radar, three-dimensional data of distance dimension, azimuth dimension and pitch dimension can be used to represent the three-dimensional position information of the measured object in spherical coordinates. The sampling described in step S4031 may be to perform ADC sampling on the antenna echo signal along the distance dimension and the time dimension for each antenna; when sampling, a fast time sampling method may be selected. The echo signals in the second preset area include multi-channel antenna echo signals.

S4032. For each time-domain echo signal in the time-domain echo signal set, perform one-dimensional FFT processing on the time-domain echo signal to obtain distance information of the time-domain echo signal.

In step S4032, the one-dimensional FFT processing can transform the time-domain echo signal into the frequency-domain echo signal, and then obtain the distance information of the time-domain echo signal in the second preset area, that is, the time-domain echo signal can be obtained The distance distribution in the second preset area.

S4033. According to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupancy area inside the vehicle, and according to the effective echo signals corresponding to each occupancy area set to determine whether each occupancy area is occupied.

The occupancy area is occupied can be understood as the occupancy area is occupied; for example, an occupancy area is the co-pilot, and the occupancy area is occupied by the co-pilot.

In one embodiment of the vehicle control method provided by the present application, as described above, each time-domain echo signal in the time-domain echo signal set includes echo signals of multiple sampling points; the distance of the time-domain echo signal The information includes distance values of echo signals at multiple sampling points corresponding to the time-domain echo signal.

In the above-mentioned step S4033, "determining the effective echo signal sets corresponding to each occupancy area inside the vehicle according to the distance information of each time-domain echo signal in the time-domain echo signal set" may include the following steps:

S4033-1. For each time-domain echo signal in the time-domain echo signal set, select an echo signal at a sampling point within a preset range from all distance values in the time-domain echo signal as the time-domain echo signal. Effective echo signal corresponding to domain echo signal;

S4033-2, respectively performing two-dimensional DOA estimation on each effective echo signal, and obtaining position information of sampling points respectively corresponding to each effective echo signal;

S4033-3. According to the location information of the sampling points corresponding to each effective echo signal, determine the effective echo signal sets corresponding to each occupying area inside the vehicle.

In one embodiment of the present application, the "gesture recognition of the received echo signal in the first preset area" in the above S402 or S403 may include the following steps:

S4021. Sampling each antenna echo signal in the first preset area to obtain a gesture echo signal set; each antenna echo signal in the first preset area is obtained by detecting the first preset area inside the vehicle the echo signal;

S4022. Perform one-dimensional FFT on each gesture echo signal in the gesture echo signal set, and perform two-dimensional FFT on each gesture echo signal after one-dimensional transformation, to obtain point cloud data of each sampling point in the first preset area ; Point cloud data includes distance information and velocity information of each sampling point;

S4023. Calculate the point cloud data of all sampling points whose speed is not zero in the first preset area, and obtain the amplitude of the point cloud data of each sampling point whose speed is not zero;

S4024, perform non-coherent accumulation processing on the magnitude of each point cloud data whose speed is not zero, and select all point cloud data whose magnitude after non-coherent accumulation processing is greater than the preset magnitude to form a target point cloud data set;

S4025. Perform two-dimensional DOA estimation on the target point cloud data set, and obtain spatial angle information of each point cloud data corresponding to the sampling point in the target point cloud data set;

S4026. Perform gesture recognition according to spatial angle information of sampling points corresponding to each point cloud data in the target point cloud data set.

Optionally, the distance between the first preset area and the radar is less than 0.5m, and the gesture is an action with speed, so steps S4021 to S4026 can intercept point cloud data within 0~0.5m and with a non-zero speed; The point cloud data is subjected to non-coherent accumulation processing, and all point cloud data whose magnitude after non-coherent accumulation processing is greater than the preset magnitude are selected to form the target point cloud data set. Non-coherent accumulation is a well-known technique in the art.

Optionally, each point cloud data in the target point cloud dataset includes multi-dimensional information such as distance, velocity, azimuth, and pitch angle.

Exemplarily, the process of gesture recognition can be:

Setting 1: The left side of the first preset area corresponds to the negative angle of the millimeter-wave radar azimuth, and the right side of the first preset area corresponds to the positive angle of the millimeter-wave radar azimuth;

Setting 2: A group of gestures that slide from left to right at a constant speed within 30cm from the millimeter-wave radar lasts for 60 frames. According to the time sequence, the 60 frames are divided into three stages (here for illustration, the three stages are For example, the actual can be further refined);

Then the point set trajectory should be rendered as:

In the first stage (1~20 frames), the point set is concentrated on the negative angle of azimuth;

In the second stage (21~40 frames), the point set is concentrated on the zero angle of orientation;

In the third stage (41~60 frames), the point set is concentrated on the positive angle of azimuth.

All motion gestures are classified according to the above-mentioned trajectory principle, and the point set trajectory information presented by different motion gestures is different, and the type of the gesture can be judged, thereby realizing gesture recognition.

The millimeter wave technology used in this application has high frequency band, wide bandwidth, high detection accuracy, and is not affected by light, temperature, dust, climate, etc.; millimeter wave technology can use the Doppler effect to sensitively monitor the movement of the occupants in the car. Perception, high detection accuracy; millimeter wave technology can realize gesture recognition, occupancy seat belt reminder, children's anti-forgetting and other functions, providing an intelligent solution for the development of intelligent vehicle alarms.

It should be understood that in the above embodiments of the vehicle control method, the sequence numbers of the steps do not mean the order of execution, and the execution order of each process should be determined by its functions and internal logic, and should not be used in the implementation of the embodiment of the present application. process constitutes any qualification.

The following are device embodiments corresponding to the vehicle control method provided in this application. For details not described in detail, reference may be made to the above embodiments of the vehicle control method.

Fig. 5 is a schematic diagram of the structural composition of the vehicle control device provided by the present application. For ease of description, FIG. 5 only shows the parts related to the present application, which are described in detail as follows.

As shown in FIG. 5 , the vehicle control device 50 may include an acquisition module 501 , a first control module 502 , a second control module 503 and a third control module 504 .

The acquiring module 501 is configured to execute step S401, that is, acquiring a vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal.

The first control module 502 is configured to execute step S402, that is, when the vehicle state signal is an unlocked state signal, send a detection signal to the first preset area; perform gesture recognition on the received echo signal in the first preset area, And control the vehicle to perform the corresponding preset operation according to the gesture recognition result.

The second control module 503 is configured to execute step S403, that is, when the vehicle state signal is a driving state signal, send detection signals to the first preset area and the second preset area; wave signal for gesture recognition, and control the vehicle to perform the corresponding preset operation according to the gesture recognition result; adopt the above-mentioned occupancy recognition method provided by this application to perform the echo signal received in the second preset area Occupancy recognition, and according to the result of occupancy recognition, it is determined whether to issue a seat belt warning.

The third control module 504 is configured to execute step S404, that is, when the vehicle state signal is a locked state signal, send a detection signal to the third preset area; perform life recognition on the received echo signal in the third preset area , and determine whether to perform a personnel detention alarm according to the result of the identification of the living body.

In an embodiment of the present application, the second control module 203 may include an occupancy recognition unit.

The occupancy identification unit is used to execute step S4031, that is, to send the occupancy identification result to the vehicle central control (that is, the vehicle's central control system), when the occupancy identification result is that the occupancy area is occupied, and the When the vehicle central control detects that the seat belt in the occupied area is not fastened, and detects that the driving speed of the vehicle is greater than the preset speed threshold, a seat belt alarm is issued in the occupied area; wherein, the occupied area is the second preset area in the area.

In an embodiment of the present application, the third control module 204 may include a living body identification unit.

The living body identification unit is used to execute step S4041, that is, to send the living body identification result to the vehicle central control, and when the living body identification result shows that there is a living body in the third preset area, perform the identification of the third preset area. Personnel stranded alarm.

In an embodiment of the present application, the third control module 204 may further include a sleep unit.

The dormancy unit is configured to execute step S407, that is, when the vehicle status signal is a locked status signal, and when the duration of the locked status signal is greater than a preset time threshold, stop sending detection signals to the third preset area.

In an embodiment of the present application, the second control module 203 may include an occupancy sampling unit, an occupancy conversion unit, and a judging unit.

The occupancy sampling unit is used to perform step S4031, that is, to sample each antenna echo signal in the second preset area respectively to obtain a time-domain echo signal set; each antenna echo signal in the second preset area The signal is an echo signal obtained by detecting the second preset area inside the vehicle.

The occupancy transformation unit is configured to perform step S4032, that is, for each time domain echo signal in the time domain echo signal set, perform one-dimensional FFT processing on the time domain echo signal to obtain the time domain echo signal distance information.

The judging unit is used to execute step S4033, that is, according to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupied area inside the vehicle, and according to each The effective echo signal sets corresponding to the occupied areas respectively determine whether each occupied area is occupied.

In an embodiment of the present application, each time-domain echo signal in the time-domain echo signal set includes echo signals of multiple sampling points; the distance information of the time-domain echo signal includes the corresponding The distance value of the echo signal of multiple sampling points. In this case, the judgment unit may include a selection subunit, an estimation subunit and an echo determination subunit.

The selection subunit is used to perform step S4033-1, that is, for each time domain echo signal in the time domain echo signal set, from all the distance values in the time domain echo signal, select The echo signal at the sampling point is used as the effective echo signal corresponding to the time-domain echo signal.

The estimating subunit is used to perform step S4033-2, that is, perform two-dimensional DOA estimation on each effective echo signal respectively, and obtain position information of sampling points corresponding to each effective echo signal;

The echo determination subunit is configured to perform step S4033-3, that is, determine the time-domain echo signals corresponding to each occupied area inside the vehicle according to the location information of the sampling points corresponding to each effective echo signal.

In an embodiment of the present application, both the first control module 502 and the second control module 503 may include a gesture sampling unit, a gesture transformation unit, a gesture calculation unit, a gesture processing unit, a gesture estimation unit and a gesture recognition unit.

The gesture sampling unit is used to perform step S4021, that is, to sample each antenna echo signal in the first preset area to obtain a gesture echo signal set; each antenna echo signal in the first preset area is a pair of The echo signal obtained by detecting the first preset area inside the vehicle.

The gesture transformation unit is used to perform step S4022, that is, perform one-dimensional FFT transformation on each gesture echo signal in the gesture echo signal set, and perform two-dimensional FFT transformation on each gesture echo signal after one-dimensional transformation, to obtain The point cloud data of each sampling point in the first preset area; the point cloud data of the sampling point includes the distance and speed of the sampling point;

The gesture calculation unit is used to execute step S4023, that is, to calculate the point cloud data of all sampling points whose speed is not zero in the first preset area, and obtain the magnitude of the point cloud data of each sampling point whose speed is not zero ;

The gesture processing unit is used to execute step S4024, that is, perform non-coherent accumulation processing on the amplitude of the point cloud data of each sampling point whose speed is not zero, and select all amplitudes after non-coherent accumulation processing that are greater than the preset The point cloud data of the sampling point of the amplitude forms the target point cloud data set;

The gesture estimation unit is used to perform step S4025, that is, perform two-dimensional DOA wave-of-arrival estimation on the target point cloud data set, and obtain the spatial angle information of each point cloud data corresponding to the sampling point in the target point cloud data set;

The gesture recognition unit is configured to perform step S4026, that is, perform gesture recognition according to the spatial angle information of the sampling points corresponding to each point cloud data in the target point cloud dataset.

FIG. 6 is a schematic diagram of a second millimeter-wave radar provided by the present application. As shown in FIG. 6 , the second millimeter wave radar 60 includes a processor 600 , a memory 601 , and a computer program 602 stored in the memory 601 and operable on the processor 600 . When the processor 600 executes the computer program 602 , the steps in the above-mentioned embodiments of the vehicle control method are realized, such as S401 to S404 shown in FIG. 4 . Alternatively, when the processor 600 executes the computer program 602, the functions of the modules/units in the above-mentioned device embodiments are implemented, for example, the functions of the modules 501 to 504 shown in FIG. 5 .

Exemplarily, the computer program 602 can be divided into one or more modules/units, and these modules/units are stored in the memory 601 and executed by the processor 600, so as to realize the inventive concept of the present application. These modules/units may be a series of computer program instruction segments capable of accomplishing specific functions, and these instruction segments are used to describe the execution process of the computer program 602 in the second millimeter wave radar 60 . For example, the computer program 602 may be divided into instruction segments corresponding to the modules 501 to 504 shown in FIG. 2 .

The second millimeter wave radar 30 may include, but not limited to, a processor 600 and a memory 601 . Those skilled in the art can understand that FIG. 3 is only an example of the second millimeter-wave radar 60 , and does not constitute a limitation to the second millimeter-wave radar 60 . The second mmWave radar may include more or fewer components than shown, or combine certain components, or different components

The present application also provides a second computer-readable storage medium. The storage medium stores a computer program. When the computer program is executed by the processor, the steps described in the embodiments corresponding to the above-mentioned vehicle control method can be realized, and the control of various auxiliary functions of the vehicle can be realized.

Those skilled in the art can clearly understand that, for convenience and brevity of description, only the division of the above functional units and modules is used as an example for illustration. In practical applications, the above function allocation can be completed by different functional units or modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment of the present application may be integrated into one processing unit, or each unit may physically exist separately, 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. 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 each unit and module in the present application, reference may be made to the process described in the corresponding method embodiment, which will not be repeated here.

In the embodiments of the present application, the description of each embodiment has its own focus; for the part that is 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. Professionals may use different methods to implement the described functions for each specific application, but such implementation should not be regarded as exceeding the protection scope of the present application.

In the embodiments provided in the present application, it should be understood that the device/terminal and method disclosed in the present application can also be implemented in other deformation manners that can be obtained without any creative effort. That is to say, the device/terminal embodiments described above are only illustrative; for example, the division of the above modules or units is only a logical function division, and there may be other division methods in actual implementation. For example, several units or modules may be combined or may be 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 displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or may 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.

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 such an understanding, the implementation of all or part of the procedures in the methods of the above-mentioned embodiments in the present application may also be completed by computer program instructions related hardware. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can realize the steps of the above embodiments of the occupancy recognition method and/or the vehicle control method. Wherein, the computer program includes computer program code. The computer program code may be in source code form, object code form, executable file or some intermediate form, etc. 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 method for occupancy identification, characterized in that it comprises:

Sampling each antenna echo signal in the preset area separately to obtain a time-domain echo signal set; each antenna echo signal in the preset area is an echo signal obtained by detecting a preset area inside the vehicle ;

For each time-domain echo signal in the time-domain echo signal set, perform one-dimensional FFT (Fast Fourier Transform, Fast Fourier Transform) processing on the time-domain echo signal to obtain the distance of the time-domain echo signal information;

According to the distance information of each time-domain echo signal in the time-domain echo signal set, determine the effective echo signal sets corresponding to each occupancy area inside the vehicle, and according to the effective echo signals corresponding to each occupancy area set to determine whether each occupancy area is occupied.
The occupancy identification method according to claim 1, wherein each time domain echo signal in the time domain echo signal set includes echo signals of a plurality of sampling points; the distance information of the time domain echo signals including distance values of echo signals of multiple sampling points corresponding to the time-domain echo signal;

The determining, according to the distance information of each time-domain echo signal in the time-domain echo signal set, the effective echo signal sets corresponding to each occupying area inside the vehicle respectively, includes:

For each time domain echo signal in the time domain echo signal set, from all distance values in the time domain echo signal, select an echo signal at a sampling point within a preset range as the time domain echo signal The effective echo signal corresponding to the wave signal;

Two-dimensional DOA (Direction Of Arrival (direction of arrival) estimation to obtain the position information of the sampling points corresponding to each effective echo signal;

According to the position information of the sampling points corresponding to each effective echo signal, the effective echo signal sets corresponding to each occupying area inside the vehicle are respectively determined.
The occupancy identification method according to claim 1, wherein, according to the effective echo signal sets corresponding to each occupancy area, respectively determining whether each occupancy area is occupied comprises:

According to the effective echo signal sets corresponding to each occupied area, the point cloud information of each occupied area is obtained;

For each occupancy area, calculate the fretting speed of each point cloud in the occupancy area according to the point cloud information of the occupancy area, and determine the occupancy area according to the fretting speed of each point cloud in the occupancy area Whether the region is occupied.
The occupancy recognition method according to claim 3, wherein said determining whether the occupancy area is occupied according to the fretting speed of each point cloud of the occupancy area comprises:

If the number of point clouds whose inching speed is greater than the preset inching speed in the occupied area is greater than the preset number, it is determined that the occupied area is occupied.
The occupancy identification method according to claim 1, wherein each time-domain echo signal in the time-domain echo signal set includes echo signals of a plurality of sampling points;

Before performing one-dimensional FFT processing on the time-domain echo signal, the method also includes:

Calculating the signal average value of the echo signals at each sampling point in the time-domain echo signal;

The echo signal of each sampling point in the time-domain echo signal is respectively different from the corresponding signal average value to obtain a filtered time-domain echo signal of the time-domain echo signal;

Correspondingly, performing one-dimensional FFT processing on the time-domain echo signal to obtain distance information of the time-domain echo signal, including:

One-dimensional FFT processing is performed on the filtered time-domain echo signal to obtain distance information of the time-domain echo signal.
The occupancy identification method according to any one of claims 1 to 5, wherein the method further comprises:

Send the occupancy determination results of each occupancy area to the central control system of the vehicle;

For the occupancy determination result of each occupancy area, when the occupancy determination result is that the occupancy area is occupied, and the central control system detects that the seat belt of the occupancy area is not fastened, and detects that the vehicle When the speed of the vehicle is greater than the preset speed threshold, the audible and visual warning of the seat belt in the occupied area will be performed.
An occupancy recognition device, characterized in that it comprises:

The sampling module is used to sample each antenna echo signal in the preset area separately to obtain a time-domain echo signal set; each antenna echo signal in the preset area is used to detect the preset area inside the vehicle The echo signal obtained;

A transformation module, configured to perform one-dimensional FFT processing on each time-domain echo signal in the time-domain echo signal set to obtain distance information of the time-domain echo signal;

A judging module, configured to determine, according to the distance information of each time-domain echo signal in the time-domain echo signal set, the valid echo signal sets corresponding to each occupancy area inside the vehicle, and corresponding to each occupancy area The effective echo signal set is used to determine whether each occupancy area is occupied.
A millimeter-wave radar, 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 realized. Steps of the occupancy recognition method described in any one of 6.
A computer-readable storage medium, the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the occupancy identification method as described in any one of claims 1 to 6 is implemented A step of.
A vehicle control method, characterized by comprising:

Obtaining a vehicle state signal; the vehicle state signal includes an unlocked state signal, a driving state signal or a locked state signal;

When the vehicle state signal is an unlocked state signal, send a detection signal to the first preset area; perform gesture recognition on the received echo signal in the first preset area, and control the vehicle to perform corresponding actions according to the gesture recognition result. default operation;

When the vehicle state signal is a driving state signal, sending a detection signal to the first preset area and the second preset area; performing gesture recognition on the received echo signal in the first preset area, and Controlling the vehicle to perform a corresponding preset operation according to the gesture recognition result; using the occupancy recognition method according to any one of claims 1 to 6 to perform occupancy recognition on the received echo signal in the second preset area, And according to the occupancy recognition result, it is determined whether to carry out the seat belt warning;

When the vehicle state signal is a locked state signal, send a detection signal to the third preset area; perform life body identification on the received echo signal in the third preset area, and determine whether to Carry out personnel stranded alarm.
The vehicle control method according to claim 10, wherein the determining whether to perform seat belt warning according to the occupancy recognition result comprises:

Sending the occupancy identification result to the central control system of the vehicle, when the occupancy identification result is that the occupancy area is occupied, and the central control system detects that the seat belt in the occupancy area is not fastened, And when it is detected that the driving speed of the vehicle is greater than a preset speed threshold, a seat belt warning is performed in the occupied area; wherein the occupied area is an area in the second preset area.
The vehicle control method according to claim 10, characterized in that the determining whether to perform an alarm for personnel retention according to the life body identification result comprises:

The living body identification result is sent to the central control system of the vehicle, and when the living body identification result shows that there is a living body in the third preset area, an alarm for personnel staying in the third preset area is issued.
The vehicle control method according to claim 10, wherein when the vehicle state signal is a locked state signal, the method further comprises:

When the duration of the locked state signal is greater than a preset time threshold, stop sending detection signals to the third preset area.
The vehicle control method according to any one of claims 10 to 13, wherein the gesture recognition of the received echo signal in the first preset area comprises:

Sampling each antenna echo signal in the first preset area to obtain a gesture echo signal set; each antenna echo signal in the first preset area is for the first preset area inside the vehicle The detected echo signal;

Performing a one-dimensional FFT on each gesture echo signal in the gesture echo signal set, and performing a two-dimensional FFT on each gesture echo signal after the one-dimensional transformation, to obtain point cloud data of each sampling point in the first preset area; sampling Point cloud data includes the distance and velocity of the sampling point;

Calculating the point cloud data of all sampling points whose velocity is not zero in the first preset area to obtain the magnitude of the point cloud data of each sampling point whose velocity is not zero;

Perform non-coherent accumulation processing on the amplitude of the point cloud data of each sampling point whose speed is not zero, and select all point cloud data of the sampling point whose amplitude after non-coherent accumulation processing is greater than the preset amplitude to form the target point cloud data set;

Perform two-dimensional DOA wave-of-arrival estimation on the target point cloud data set, and obtain the spatial angle information of each point cloud data corresponding to the sampling point in the target point cloud data set;

Gesture recognition is performed according to the spatial angle information of the sampling points corresponding to each point cloud data in the target point cloud data set.
A millimeter-wave radar, 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 10 to 10 are realized. The steps of the vehicle control method described in any one of 14.