Tailgate control method, vehicle, device, electronic device and readable storage medium

Abstract

The present invention provides a tailgate control method, a vehicle, a device, an electronic device and a readable storage medium. The tailgate control method comprises: controlling a projection device to project a projection area on the ground, and controlling a radar to transmit a first detection signal; according to the first detection signal, obtaining a body movement sequence, determining whether the body movement sequence conforms to a target movement mode, and whether the body movement sequence is executed in the projection area, and obtaining a judgment result; if the judgment result meets a preset condition, the tailgate is controlled to execute a closing or opening operation according to the state information of whether the tailgate is open or closed. The radar is combined with the projection device, and the effective range of the radar for identifying the kicking action is limited by the projection area. By judging whether the body movement conforms to the standard, the false triggering caused by environmental factors can be effectively reduced, and the misjudgment caused by the excessively large recognition range can be reduced.

Description

Technical Field

[0001] The present invention relates to the field of intelligent automobile technology, and in particular to a tailgate control method, a vehicle, a device, an electronic device and a readable storage medium. Background Art

[0002] With the rapid development of science and technology, the level of automobile industry is constantly improving. Automobiles have brought more and more convenience to people's lives. Correspondingly, users have higher requirements for various performances of automobiles. In order to provide better user experience and facilitate users to open the tailgate of the car more conveniently when their hands are full of things, kick sensors have become the mainstream with the characteristics of comfort, convenience and safety.

[0003] The current sensing method of the kick sensor, for example, utilizes a capacitive sensor to recognize a person's kicking action through a capacitive strip, thereby controlling the tailgate to open.

[0004] However, this kicking method has a high false alarm rate when encountering dust or rainy or snowy weather, and it is difficult to achieve normal use. Summary of the invention

[0005] Embodiments of the present invention provide a tailgate control method, a vehicle, a device, an electronic device, and a readable storage medium to solve the problem of high false alarm rate of tailgate control in the prior art.

[0006] In a first aspect, an embodiment of the present invention provides a tailgate control method, the method comprising:

[0007] Controlling the projection device to project a projection area on the ground, and controlling the radar to transmit a first detection signal;

[0008] Acquire a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result;

[0009] If the judgment result meets the preset condition, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is opened or closed.

[0010] Optionally, when the vehicle is stationary and the vehicle key is within a first preset range from the vehicle, controlling the projection device to project a projection area on the ground includes:

[0011] When the vehicle is stationary and the vehicle key is within a first preset range from the vehicle, controlling the radar to emit a second detection signal;

[0012] determining the distance between the human body and the radar according to the second detection signal;

[0013] When the distance is within the second preset range, the projection device is controlled to project a projection area on the ground.

[0014] Optionally, acquiring a limb motion sequence according to the first detection signal includes:

[0015] receiving a feedback signal for the first detection signal;

[0016] Preprocessing the feedback signal and extracting limb point cloud data;

[0017] According to each frame of limb point cloud data, the limb movement sequence is determined.

[0018] Optionally, preprocessing the feedback signal and extracting limb point cloud data includes:

[0019] Performing range-dimensional Fourier transform and Doppler-dimensional Fourier transform on the feedback signal to obtain frequency spectrum data of multiple channels;

[0020] Performing non-coherent accumulation processing on the spectrum data to obtain a range Doppler matrix;

[0021] Performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix;

[0022] According to the average constant false alarm detection matrix, the limb point cloud data is extracted.

[0023] Optionally, performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix includes:

[0024] Performing average constant false alarm detection on the range data of each Doppler unit in the range Doppler matrix to obtain a first detection value;

[0025] Performing average constant false alarm detection on the Doppler data of each range unit in the range Doppler matrix to obtain a second detection value;

[0026] An average constant false alarm detection matrix is ​​determined according to the first detection value and the second detection value.

[0027] Optionally, determining whether the limb movement sequence conforms to the target movement pattern includes:

[0028] Cluster each frame of limb point cloud data to obtain the target cluster data corresponding to each frame of limb point cloud data;

[0029] Determine feature data of each frame of limbs according to the target cluster data; the feature data includes: center position, speed and orientation;

[0030] Determine whether the limb movement sequence conforms to the target movement pattern according to the feature data.

[0031] Optionally, determining whether the limb movement sequence conforms to the target movement pattern according to the feature data includes:

[0032] Determining, based on the characteristic data, whether the limb motion sequence includes a first sequence characterizing that the limb enters the projection area, and a second sequence characterizing that the limb leaves the projection area;

[0033] In case of including a first sequence and a second sequence, whether the limb motion sequence conforms to the target motion pattern is determined according to the duration of the first sequence and the second sequence.

[0034] Optionally, determining, based on the characteristic data, whether the limb action sequence includes a first sequence characterizing that the limb enters the projection area, and a second sequence characterizing that the limb leaves the projection area comprises:

[0035] Determine the speed and direction of the limb movement according to the characteristic data;

[0036] The limb point cloud data whose speed direction of the limb movement is a first direction is determined as a first sequence, and the limb point cloud data whose speed direction of the limb movement is a second direction is determined as a second sequence.

[0037] Optional, Said According to the duration of the first sequence and the second sequence, determining whether the limb movement sequence conforms to the target movement pattern. Including:

[0038] Obtaining the number of point cloud data of each frame in the first sequence and the second sequence;

[0039] Determining the duration of the first sequence and the second sequence according to the amount of the point cloud data;

[0040] When the duration falls within a preset time range, it is determined that the limb movement sequence conforms to the target movement pattern.

[0041] Optionally, the limb movement sequence includes any one of a foot movement sequence and a hand movement sequence.

[0042] In a second aspect, an embodiment of the present invention provides a vehicle, the vehicle comprising: a radar, a projection device and a controller;

[0043] The controller is used to control the projection device to project a projection area on the ground, and to control the radar to transmit a first detection signal;

[0044] The radar is used to obtain a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result;

[0045] The controller is used for controlling the tailgate to close or open according to the state information of the tailgate being opened or closed if the judgment result meets the preset condition.

[0046] In a third aspect, an embodiment of the present invention provides a tailgate control device, comprising:

[0047] A first control module, used to control the projection device to project a projection area on the ground, and to control the radar to transmit a first detection signal;

[0048] A judgment module, used to obtain a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result;

[0049] The second control module is used for controlling the tailgate to close or open according to the state information of the tailgate being opened or closed if the judgment result meets the preset condition.

[0050] In a fourth aspect, an embodiment of the present invention provides an electronic device, comprising: a processor, a communication interface, a memory, and a communication bus; wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0051] Memory, used to store computer programs;

[0052] The processor is used to implement the steps of the tailgate control method described in the first aspect when executing the program stored in the memory.

[0053] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps in the tailgate control method described in the first aspect above.

[0054] Compared with the prior art, the present invention has the following advantages:

[0055] In an embodiment of the present invention, the projection device is controlled to project a projection area on the ground, and the radar is controlled to emit a first detection signal; according to the first detection signal, a limb movement sequence is obtained to determine whether the limb movement sequence meets the target movement mode and whether the limb movement sequence is executed in the projection area, and a judgment result is obtained; if the judgment result meets the preset conditions, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is open or closed. The present application uses radar to identify kicking actions, combines radar with a projection device, and limits the effective range of radar identification of kicking actions through the projection area. By identifying whether the limb movement sequence meets the target movement mode and is executed in the projection area, it is judged whether the limb movement meets the standard. The method of the present invention can effectively reduce false triggering caused by environmental factors, and limit the recognition range of limb movements to the projection area, reducing misjudgment caused by excessive recognition range.

[0056] The above description is only an overview of the technical solution of the present invention. In order to more clearly understand the technical means of the present invention, it can be implemented according to the contents of the specification. In order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for describing the embodiments are briefly introduced below.

[0058] Figure 1 A schematic diagram of a tailgate control method provided by an embodiment of the present invention;

[0059] Figure 2 A schematic diagram of another tailgate control method provided by an embodiment of the present invention;

[0060] Figure 3 is a schematic diagram of the working range of a radar and a projection device provided by an embodiment of the present invention;

[0061] Figure 4 This is a kicking action recognition process provided by an embodiment of the present invention;

[0062] Figure 5 This is a schematic diagram of a radar working process provided by an embodiment of the present invention;

[0063] Figure 6 is a schematic diagram of a tailgate control device provided by an embodiment of the present invention;

[0064] Figure 7 is a block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can also be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided in order to enable a more thorough understanding of the present invention and to enable the scope of the present invention to be fully communicated to those skilled in the art.

[0066] Figure 1 A tailgate control method provided by an embodiment of the present invention includes steps 101 to 103:

[0067] Step 101: Control the projection device to project a projection area on the ground, and control the radar to transmit a first detection signal.

[0068] In an embodiment of the present invention, the prerequisite for controlling the projection device to project a projection area on the ground may be: the vehicle is stationary and the car key is within a first preset range from the vehicle, that is, the vehicle is stationary, but the vehicle and the car key can match, and the vehicle is powered on. At this time, the projection device can be controlled to project the projection area on the ground, and the radar can be controlled to transmit the first detection signal. Of course, the projection device can also continuously project the projection area and the radar can transmit the first detection signal, which is not limited by the vehicle state, and this application is not limited here. The projection device in this application can be a device that can project light, such as a projection lamp, and the radar can be a device for distance detection or target detection, such as a millimeter wave radar. Millimeter wave radar refers to a radar sensor that works in the millimeter wave frequency band and is suitable for close-range scenes. The projection device and the radar can be set at a position below the rear bumper of the rear of the vehicle. The setting position of the projection device and the radar can be set according to the projection area and the detection range of the radar, and this application is not limited here.

[0069] Furthermore, when the vehicle is stationary and the car key is within a first preset range from the vehicle, it can be considered that the conditions for opening or closing the tailgate of the car are met, and in this state, there may be a need to open or close the tailgate of the car. At this time, the projection device can be controlled to project a projection area on the ground, and the projection area is used to indicate that the user performs a kicking action in the area, thereby increasing the success rate of the user performing a correct kicking action. If there is no object passing by the periphery of the car for a long time, the radar may be in a dormant state. Therefore, after determining that the current state of the car meets the execution conditions for opening or opening the tailgate, the radar is also controlled to emit a first detection signal to detect the user's kicking action in the projection area and determine whether the user has performed a correct kicking action.

[0070] Step 102: Acquire a limb movement sequence according to the first detection signal, determine whether the limb movement sequence conforms to the target movement pattern, and whether the limb movement sequence is performed in the projection area, and obtain a judgment result.

[0071] In an embodiment of the present invention, after the radar transmits the first detection signal, if there is an object in the projection area, the first detection signal can be reflected by the object and returned to the radar. According to the time when the radar transmits the signal, the time when the signal is received, the propagation rate of the signal, and the calculation of the radar wave phase difference, the distance, speed, azimuth and other information of the object relative to the radar can be determined. According to the multiple signals returned to the radar by the limbs, the limb point cloud data can be determined to form a limb action sequence. Then, by analyzing each frame of limb point cloud data and combining it with all limb point cloud data, the limb action can be determined. For example, the target action mode can be an action of first entering the projection area and then leaving the projection area. Through multiple frames of point cloud data, the limb action can be analyzed to determine whether the limb action meets the target working mode. If the limb action sequence does not meet the target action mode, it is considered that the detected limb action does not meet the standard, and the opening or closing state of the tailgate is not changed to avoid false detection.

[0072] Furthermore, it is also detected whether the body movement is performed in the projection area. Since the detection range of the radar may be larger than the range of the projection area, a detection range that is too large may also cause the body movement that is not performed in the designated area to be misjudged, and an erroneous instruction to change the state of the tailgate is issued. Therefore, the present application also detects whether the body movement is performed in the projection area. If the body movement is performed in the projection area, it is considered that the detected action is in line with the control of the tailgate state. If the body movement is not performed in the projection area, the state of the tailgate is not changed, and the next kicking action is detected. The present application effectively improves the recognition accuracy of the kicking action by limiting the recognition range of the kicking action.

[0073] Step 103: If the judgment result meets the preset condition, the tailgate is controlled to close or open according to the status information of whether the tailgate is open or closed.

[0074] In an embodiment of the present invention, the preset conditions may be: the limb movement sequence conforms to the target movement pattern, and the limb movement sequence is performed in the projection area. If the judgment result meets the preset conditions, it can be considered that a standard kicking action is detected. At this time, the radar can send a control instruction to the controller to control the tailgate to open or close.

[0075] Furthermore, before controlling the tailgate to be opened or closed, the current state of the tailgate is also obtained, and the operation to be performed on the tailgate is determined according to the current state of the tailgate. For example, if the current state of the tailgate is closed, after a kicking action that meets the preset conditions is detected, the tailgate is opened; if the current state of the tailgate is open, after a kicking action that meets the preset conditions is detected, the tailgate is closed.

[0076] In an embodiment of the present invention, the projection device is controlled to project a projection area on the ground, and the radar is controlled to emit a first detection signal; according to the first detection signal, a limb movement sequence is obtained to determine whether the limb movement sequence meets the target movement mode and whether the limb movement sequence is executed in the projection area, and a judgment result is obtained; if the judgment result meets the preset conditions, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is open or closed. The present application uses radar to identify kicking actions, combines radar with a projection device, and limits the effective range of radar identification of kicking actions through the projection area. By identifying whether the limb movement sequence meets the target movement mode, it is judged whether the limb movement meets the standard. The method of the present invention can effectively reduce false triggering caused by environmental factors, and limit the recognition range of limb movements to the projection area, reducing misjudgment caused by excessive recognition range.

[0077] Figure 2 2 is a schematic diagram of another tailgate control method provided by an embodiment of the present invention, the method comprising steps 201 to 205:

[0078] Step 201: When the vehicle is stationary and the vehicle key is within a first preset range from the vehicle, control the radar to emit a second detection signal.

[0079] In an embodiment of the present invention, when the vehicle is stationary and the car key is within a first preset range from the vehicle, the radar can be controlled to emit a second detection signal, and the second detection signal can be used to detect whether there is someone approaching the periphery of the vehicle. If the second detection signal does not detect that someone is approaching, there is no need to turn on the projection device, and there is no need to recognize body movements. If the second detection signal detects that someone is gradually approaching, or that the distance between someone and the radar is within a preset range, it can be considered that the user has the intention to open or close the tailgate, and at this time the projection device can be controlled to project a projection area to instruct the user to complete the kicking action in the projection area.

[0080] Furthermore, the power consumption can be reduced by setting the time interval for the radar to transmit the second detection signal. For example, the power consumption can be reduced by increasing the detection interval between two second detection signals.

[0081] Step 202: Determine the distance between the human body and the radar according to the second detection signal.

[0082] In the embodiment of the present invention, after the radar transmits the second detection signal, if there is a target within the detection range of the second detection signal of the radar, the target can return a feedback signal to the radar based on the second detection signal. Based on the time of transmitting the signal, the time of receiving the signal and the propagation speed of the signal, the relative distance between the target and the radar can be determined.

[0083] For example, taking millimeter-wave radar as an example, the ranging capability of millimeter-wave radar is related to factors such as transmission power, antenna gain, antenna beam angle, and object reflection cross-sectional area. Generally, the greater the transmission power, the higher the antenna gain, the narrower the antenna beam angle, and the larger the object reflection cross-sectional area, the stronger the effective echo that the radar can detect, and the longer the measurement distance. The ranging of millimeter-wave radar mainly uses the time delay between the transmission signal and the echo signal, combined with the millimeter-wave propagation speed, and the relative speed of the target and the radar, to deduce the relative distance between the millimeter-wave radar and the detection target.

[0084] Step 203: When the distance is within a second preset range, control the projection device to project a projection area on the ground, and control the radar to transmit a first detection signal.

[0085] In an embodiment of the present invention, when it is determined that the distance between the human body and the radar is within the second preset range, it can be considered that the human body is close to the rear of the car and has the intention to open or close the tailgate. At this time, the projection device can be controlled to project a projection area on the ground, instructing the user to perform a kicking action in the projection area, and the radar can be controlled to emit a first detection signal to identify the kicking action, determine that the user has performed a standard kicking action, and then control the opening or closing of the tailgate.

[0086] refer to Figure 3 , Figure 3 A schematic diagram of the working range of a radar and a projection device is shown. In the process of identifying a kicking action, the present invention combines the radar and the projection device into a radar projection sensing tailgate control module. The radar and the projection device can be in the same vertical position. In the present invention, the projection area projected by the projection device on the ground limits the effective range of the radar for identifying the kicking action. The radar is on the left and the projection device is on the right. This spatial arrangement makes the final projection area deviate from the center position of the radar detection area, but does not make the projection area exceed the boundary of the radar detection area, which can effectively improve the recognition accuracy of body movements.

[0087] Step 204: Acquire a limb movement sequence according to the first detection signal, determine whether the limb movement sequence conforms to the target movement pattern, and whether the limb movement sequence is performed in the projection area, and obtain a judgment result.

[0088] This step may refer to step 102 and will not be described again here.

[0089] Optionally, step 204 specifically includes:

[0090] Sub-step 2041, receiving a feedback signal for the first detection signal;

[0091] Sub-step 2042, pre-processing the feedback signal and extracting limb point cloud data;

[0092] In the embodiment of the present invention, for sub-steps 2041 and 2042, the transmitting antenna in the radar transmits electromagnetic waves (for example, the signal form of the electromagnetic waves can be a linear frequency modulation signal FMCW), that is, a first detection signal, and the transmitted first detection signal is reflected by the target in the projection area, and the reflected feedback signal is received by the receiving antenna in the radar. After receiving the feedback signal, the feedback signal is pre-processed to extract the limb point cloud data according to the feedback signal.

[0093] Furthermore, the preprocessing may be to perform a distance-dimensional Fourier transform and a Doppler-dimensional Fourier transform on the feedback signal to sample the feedback signal, and extract the limb point cloud data according to the sampling results.

[0094] Optionally, sub-step 2042 specifically includes:

[0095] Sub-step 20421, performing range-dimensional Fourier transform and Doppler-dimensional Fourier transform on the feedback signal to obtain frequency spectrum data of multiple channels.

[0096] In an embodiment of the present invention, the feedback signal propagates in space as an analog waveform, and the feedback signal needs to be digitized when it is processed. This includes: performing distance-dimensional Fourier transform and Doppler-dimensional Fourier transform on the feedback signal to obtain spectrum data of multiple channels. For example: if two transmitting ends transmit signals in turn and receive data returned by two receiving ends each time, then for the same target, spectrum data of four channels can be obtained. The spectrum data of different channels can be used to determine the position of the target later.

[0097] Sub-step 20422, performing non-coherent accumulation processing on the spectrum data to obtain a range Doppler matrix;

[0098] In an embodiment of the present invention, non-coherent accumulation is used to improve the signal-to-noise ratio of a signal. Signal-to-Noise Ratio (SNR) refers to the ratio of a signal to noise, usually expressed in decibels (dB). The higher the signal-to-noise ratio, the greater the proportion of the signal, and the better the quality of the signal. Non-coherent accumulation is a signal processing technique that uses an average of multiple sampled signals to improve the signal-to-noise ratio of the signal. In each sampling period, the amplitudes of the signal and the noise are added and averaged to obtain a better signal-to-noise ratio. Taking the spectrum data of four channels as an example, the spectrum data of the four channels can be non-coherently accumulated to increase the amplitude energy, reduce the influence of noise, and improve the detection effect. Due to the presence of Gaussian distributed noise and clutter with unknown distribution (including ground clutter, object clutter, etc.) in a complex environment, the presence of noise and clutter can easily submerge the real target signal. The method proposed in the present invention effectively improves the energy of the target signal, thereby suppressing the influence of noise and clutter on body movement recognition.

[0099] Sub-step 20423, performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix;

[0100] Constant False-Alarm Rate (CFAR) is a technology that radar systems use to distinguish the signal and noise output by the receiver under the condition of keeping the false alarm probability constant to determine whether the target signal exists. Signal detection is to process the mixed signal composed of signal, noise and other interference output by the receiver, and output the desired useful signal with a specified detection probability, while noise and other interference will generate random false alarms with a low probability (usually under the condition of a certain false alarm probability). Radar systems are usually required to be able to detect the existence of targets in a background environment that is more complex and uncertain than noise and maintain a given false alarm probability. The basic process of constant false alarm detection processing is to estimate the noise and interference levels in the unit to be detected, set the threshold according to the estimated value, and then compare it with the detection unit signal to determine whether the target exists.

[0101] Furthermore, the results of spectrum data analysis can be stored in the range-Doppler matrix, and the detection of the target is to determine where the target exists in the matrix. Specifically, average constant false alarm detection can be performed on each row and each column of the range-Doppler matrix, and the average constant false alarm detection matrix can be determined based on the detection results of each row and each column.

[0102] Optionally, sub-step 20423 specifically includes:

[0103] Sub-step A1, performing average constant false alarm detection on the range data on each Doppler unit in the range-Doppler matrix to obtain a first detection value;

[0104] Sub-step A2, performing average constant false alarm detection on the Doppler data of each range unit in the range-Doppler matrix to obtain a second detection value;

[0105] Sub-step A3: determining an average constant false alarm detection matrix according to the first detection value and the second detection value.

[0106] In an embodiment of the present invention, for sub-steps A1-A3, average constant false alarm detection is performed on the distance data on each Doppler unit in the range Doppler matrix, and average constant false alarm detection can be performed on the Doppler unit of each row of the range Doppler matrix. Average constant false alarm detection is performed on the Doppler data on each distance unit in the range Doppler matrix, and average constant false alarm detection can be performed on the distance unit of each column of the range Doppler matrix. If the value "1" is used to represent the presence of a target and the value "0" is used to represent the absence of a target, then for the same detection unit, an AND operation is performed on the corresponding units in the two average constant false alarm detection matrices to obtain an average constant false alarm detection matrix after the AND operation.

[0107] Sub-step 20424, extracting limb point cloud data according to the average constant false alarm detection matrix.

[0108] In an embodiment of the present invention, the point information corresponding to the position where the unit value in the average constant false alarm detection matrix is ​​1 is extracted, that is, the limb point cloud data is obtained. The limb point cloud data can be saved in a point cloud data set for subsequent limb movement recognition.

[0109] Sub-step 2043, determining the limb action sequence according to each frame of limb point cloud data.

[0110] In an embodiment of the present invention, feedback signals within a period of time can be collected according to the interval of the radar's transmitting signals, and each frame of limb point cloud data can be determined based on the feedback signal of each frame, and then the limb movement sequence can be determined.

[0111] Optionally, step 204 specifically includes:

[0112] Sub-step 2044, clustering each frame of limb point cloud data to obtain target cluster data corresponding to each frame of limb point cloud data;

[0113] In the embodiment of the present invention, the purpose of clustering is to divide a group of point cloud data points into groups or clusters with similar characteristics or attributes. The clustering of point cloud data can be achieved by existing clustering algorithms, such as hierarchical clustering algorithms, density clustering algorithms, etc., which are not limited in this application. By clustering each frame of limb point cloud data, the target cluster data corresponding to each frame of limb point cloud data can be obtained.

[0114] Furthermore, target cluster data can represent different patterns, clusters or distributions of data. By placing similar data points in the same cluster, the inherent structure and organization of the data can be revealed. By dividing point cloud data into different target clusters, the complexity and noise of the data can be reduced, key features can be extracted, and subsequent data analysis tasks can be simplified. For example, the shape features of the target can be extracted. Clustering can also identify and exclude abnormal points or noise data. Abnormal points may be outliers, outliers or erroneous data in the data. By excluding abnormal points, the accuracy of point cloud data analysis can be improved.

[0115] Sub-step 2045, determining feature data of each frame of the limb according to the target cluster data; the feature data includes: center position, speed and orientation.

[0116] In the embodiment of the present invention, the feature data of each frame of the limb can be determined based on the target cluster data, that is, by extracting and converting the features of the point space or local space in the target cluster data, various feature data of the point data can be obtained, such as: center position, speed and orientation.

[0117] Sub-step 2046, determining whether the limb movement sequence conforms to the target movement pattern based on the characteristic data.

[0118] In the embodiment of the present invention, whether the limb motion sequence conforms to the target motion pattern can be determined based on the feature data. For example, for the same point data, by analyzing the center position, speed and orientation of the point data at different time points, the movement direction, movement speed and other information of the point data can be determined, and based on this information, whether the limb motion sequence conforms to the target motion pattern can be determined.

[0119] Furthermore, after determining the center position, speed and orientation, the characteristic data is converted to the rectangular coordinate system where the radar is located to determine the position of the point in the rectangular coordinate system.

[0120] Optionally, sub-step 2046 specifically includes:

[0121] Sub-step 20461, based on the characteristic data, determines whether the limb movement sequence includes a first sequence representing the limb entering the projection area, and a second sequence representing the limb leaving the projection area.

[0122] In an embodiment of the present invention, the target action pattern may include the action of a limb entering the projection area and the action of a limb leaving the projection area. The sequence formed by the limb entering the projection area may be the first sequence, and the action formed by the limb leaving the projection area may be the second sequence. When judging the limb action sequence, it is possible to analyze whether the limb feature sequence completely includes the first sequence and the second sequence based on the feature data. For example, if the limb action is a foot action, it is possible to determine whether the projection area has a kicking action by determining whether the first sequence of foot stepping in and the second sequence of foot leaving are included. If the limb feature sequence does not include the first sequence and / or the second sequence, it is considered that the limb feature sequence does not meet the target action pattern. If the limb feature sequence includes the first sequence and the second sequence, it is necessary to further determine the limb residence time to further determine whether the limb action is a standard action to avoid false detection.

[0123] Optionally, sub-step 20461 specifically includes:

[0124] Sub-step B1, determining the speed direction of the limb movement according to the characteristic data;

[0125] Sub-step B2, determining the limb point cloud data whose speed direction of the limb movement is a first direction as a first sequence, and determining the limb point cloud data whose speed direction of the limb movement is a second direction as a second sequence.

[0126] In the embodiment of the present invention, taking the millimeter wave radar as an example, the millimeter wave radar usually uses the Doppler effect to determine the radial velocity of the target. When the target approaches the radar antenna, the frequency of the reflected signal will be higher than the transmitter frequency; conversely, when the target moves away from the antenna, the frequency of the reflected signal will be lower than the transmitter frequency. The speed measurement range of the millimeter wave radar is related to the target movement direction. When the target moves radially close to the radar, the target speed is negative; when the target moves radially away from the radar, the target speed is positive.

[0127] Therefore, the judgment of the limbs entering the projection area and the limbs moving out of the projection area in the standard limb movement can be distinguished by the positive and negative speed of the target. When the limb enters the projection area, it is the process of the limb approaching the radar, and the speed of the target in this process is negative. When the limb moves out of the projection area, it is the process of the limb moving away from the radar, and the speed of the target in this process is positive. Based on the feature data, the positive and negative speed of the point cloud data can be analyzed, and then the first sequence and the second sequence can be distinguished from the limb point cloud data.

[0128] Sub-step 20462, in the case of including a first sequence and a second sequence, determines whether the limb movement sequence conforms to the target movement pattern according to the duration of the first sequence and the second sequence.

[0129] In the embodiment of the present invention, the judgment of the standard kicking action also needs to detect the time the foot stays in the projection area. The time the foot stays in the projection area can be determined by the duration of the first sequence and the second sequence. When the duration falls within the preset time range, it is determined whether the limb action sequence meets the target action mode.

[0130] For example, the duration of a normal kicking action is 2-3 seconds, so the time range of the duration here can be 2-3 seconds, and the embodiments of the present application are not limited here. When it is judged that the duration belongs to the preset time range, it is determined that the body movement sequence meets the target action mode, and the tailgate can be opened or closed. When it is judged that the duration belongs to the preset time range, for example, the duration is 1 second or 5 seconds, it is judged that the body movement recognized in the projection area does not meet the target action mode, and the tailgate is not opened or closed. By judging the duration, the probability of false detection can be effectively reduced.

[0131] Optionally, sub-step 20461 specifically includes:

[0132] Sub-step C1, obtaining the number of point cloud data of each frame in the first sequence and the second sequence;

[0133] Sub-step C2, determining the duration of the first sequence and the second sequence according to the amount of the point cloud data;

[0134] Sub-step C3, when the duration falls within a preset time range, determining that the limb movement sequence conforms to the target movement pattern.

[0135] In the embodiment of the present invention, for sub-steps C1 to C3, the time that the limb stays in the projection area can be determined by the amount of point cloud data. When the limb enters the projection area, there is a certain amount of point cloud data in the projection area, and when the limb is not in the projection area, there is almost no point cloud data in the projection area.

[0136] Therefore, the number of point cloud data in each frame of the first sequence and the second sequence can be obtained; if the number of point cloud data detected in the projection area meets the point cloud number requirement when the limb is in the projection area, it is determined that the limb stays in the projection area, and the duration of the first sequence and the second sequence can be determined according to the duration that the number of point cloud data meets the point cloud number requirement when the limb is in the projection area. When the duration falls within the preset time range, it is determined that the limb movement sequence meets the target movement mode.

[0137] refer to Figure 4 , Figure 4A limb movement recognition process is disclosed. The limb movement recognition method requires a set of limb movement process data sets. Single-frame data cannot solve the limb movement recognition problem, so it is necessary to extract the features of limb movement from several consecutive frames of data (point cloud data and feature data). Including: S1, obtain the number of point clouds and the maximum speed of the point cloud in the current frame; S2, refresh the historical point cloud number set and the historical point cloud speed set through the data of S1; S3, obtain the historical point cloud number accumulation and the historical point cloud speed accumulation; S4, obtain the current action speed accumulation and action point cloud number accumulation; S5, based on the analysis of S3 and S4, realize standard limb movement recognition. The radar works once each scan, Figure 4 The body movement recognition process in is executed once.

[0138] Step 205: If the judgment result meets the preset condition, the tailgate is controlled to execute a closing or opening operation according to the state information of the tailgate being opened or closed.

[0139] This step can refer to the detailed description of step 103, which will not be repeated here.

[0140] Optionally, the limb movement sequence includes any one of a foot movement sequence and a hand movement sequence.

[0141] In the embodiment of the present application, the limb movement may be a kicking movement performed by the foot, a reaching movement performed by the hand, or a movement performed by other parts such as the elbow, etc., which is not limited in the embodiment of the present application.

[0142] The solution of this application is based on the radar processing chip. Figure 5 , Figure 5 It is a schematic diagram of a radar working process provided by an embodiment of the present application, which divides the working state of the entire radar into an idle state and a scanning state. Taking the identification of a kicking action as an example, the working process may include: T1, first initialize the initial state of the radar to an idle state, T2, judge the working state of the radar, divided into T3, an idle state or T4, a scanning state, when the radar is in an idle state, data preparation work can be performed, waiting for the scanning instruction, when the radar is in a scanning state, through T6, transmit or receive signals to complete signal sampling, T7, signal processing and target clustering and other processes, T8, realize kicking action recognition. The present invention fully mines the historical information of the target with the help of the working characteristics of the radar, and makes a more reasonable judgment on the target's action recognition in combination with the current information. The identification of the kicking action is completed by more fully mining the historical information of the target and combining the current information.

[0143] In an embodiment of the present invention, the projection device is controlled to project a projection area on the ground, and the radar is controlled to emit a first detection signal; according to the first detection signal, a limb movement sequence is obtained to determine whether the limb movement sequence meets the target movement mode and whether the limb movement sequence is executed in the projection area, and a judgment result is obtained; if the judgment result meets the preset conditions, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is open or closed. The present application uses radar to identify kicking actions, combines radar with a projection device, and limits the effective range of radar identification of kicking actions through the projection area. By identifying whether the limb movement sequence meets the target movement mode, it is judged whether the limb movement meets the standard. The method of the present invention can effectively reduce false triggering caused by environmental factors, and limit the recognition range of limb movements to the projection area, reducing misjudgment caused by excessive recognition range.

[0144] Figure 6 is a schematic diagram of a tailgate control device provided by an embodiment of the present invention, the device comprising:

[0145] The first control module 301 is used to control the projection device to project a projection area on the ground, and control the radar to transmit a first detection signal;

[0146] A judgment module 302 is used to obtain a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result;

[0147] The second control module 303 is configured to control the tailgate to close or open according to the status information of whether the tailgate is open or closed if the judgment result meets a preset condition.

[0148] Optionally, the first control module includes:

[0149] The first control submodule is used to control the radar to transmit a second detection signal when the vehicle is stationary and the vehicle key is within a first preset range from the vehicle;

[0150] a distance determination submodule, used to determine the distance between the human body and the radar according to the second detection signal;

[0151] The second control submodule is used to control the projection device to project a projection area on the ground when the distance is within a second preset range.

[0152] Optionally, the judging module includes:

[0153] A receiving submodule, configured to receive a feedback signal for the first detection signal;

[0154] A preprocessing submodule, used for preprocessing the feedback signal and extracting limb point cloud data;

[0155] The sequence determination submodule is used to determine the limb movement sequence based on each frame of limb point cloud data.

[0156] Optionally, the preprocessing submodule includes:

[0157] A transform calculation subunit, used for performing a range-dimensional Fourier transform and a Doppler-dimensional Fourier transform on the feedback signal to obtain spectrum data of multiple channels;

[0158] A signal enhancement subunit, used for performing non-coherent accumulation processing on the spectrum data to obtain a range Doppler matrix;

[0159] A detection subunit, used for performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix;

[0160] The extraction subunit is used to extract limb point cloud data according to the average constant false alarm detection matrix.

[0161] Optionally, the detection subunit is further used for:

[0162] Performing average constant false alarm detection on the range data of each Doppler unit in the range Doppler matrix to obtain a first detection value;

[0163] Performing average constant false alarm detection on the Doppler data of each range unit in the range Doppler matrix to obtain a second detection value;

[0164] An average constant false alarm detection matrix is ​​determined according to the first detection value and the second detection value.

[0165] Optionally, the judging module includes:

[0166] A clustering submodule is used to cluster each frame of limb point cloud data to obtain target cluster data corresponding to each frame of limb point cloud data;

[0167] A feature determination submodule, used to determine feature data of each frame of limbs according to the target cluster data; the feature data includes: center position, speed and orientation;

[0168] The judgment submodule is used to determine whether the limb movement sequence conforms to the target movement pattern according to the characteristic data.

[0169] Optionally, the judgment submodule includes:

[0170] A sequence determination subunit, used to determine, based on the characteristic data, whether the limb action sequence includes a first sequence representing that the limb enters the projection area, and a second sequence representing that the limb leaves the projection area;

[0171] The time determination subunit is used to determine whether the limb movement sequence conforms to the target movement pattern according to the duration of the first sequence and the second sequence when the sequence includes the first sequence and the second sequence.

[0172] Optionally, the sequence determination subunit is further used for:

[0173] Determine the speed and direction of the limb movement according to the characteristic data;

[0174] The limb point cloud data whose speed direction of the limb movement is a first direction is determined as a first sequence, and the limb point cloud data whose speed direction of the limb movement is a second direction is determined as a second sequence.

[0175] Optionally, the time determination subunit is further used for:

[0176] Obtaining the number of point cloud data of each frame in the first sequence and the second sequence;

[0177] Determining the duration of the first sequence and the second sequence according to the amount of the point cloud data;

[0178] When the duration falls within a preset time range, it is determined that the limb movement sequence conforms to the target movement pattern.

[0179] Optionally, the limb movement sequence includes any one of a foot movement sequence and a hand movement sequence.

[0180] As for the above-mentioned device embodiment, since it is basically similar to the tailgate control method embodiment, the relevant parts can be referred to the partial description of the method embodiment.

[0181] In an embodiment of the present invention, the projection device is controlled to project a projection area on the ground, and the radar is controlled to emit a first detection signal; according to the first detection signal, a limb movement sequence is obtained to determine whether the limb movement sequence meets the target movement mode and whether the limb movement sequence is executed in the projection area, and a judgment result is obtained; if the judgment result meets the preset conditions, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is open or closed. The present application uses radar to identify kicking actions, combines radar with a projection device, and limits the effective range of radar identification of kicking actions through the projection area. By identifying whether the limb movement sequence meets the target movement mode, it is judged whether the limb movement meets the standard. The method of the present invention can effectively reduce false triggering caused by environmental factors, and limit the recognition range of limb movements to the projection area, reducing misjudgment caused by excessive recognition range.

[0182] The embodiment of the present invention further provides an electronic device, such as Figure 7 As shown, it includes a processor 801 , a communication interface 802 , a memory 803 and a communication bus 804 , wherein the processor 801 , the communication interface 802 , and the memory 803 communicate with each other via the communication bus 804 .

[0183] The memory 803 is used to store computer programs.

[0184] When the processor 801 is used to execute the program stored in the memory 803, the following steps are implemented: controlling the projection device to project a projection area on the ground, and controlling the radar to transmit a first detection signal; obtaining a limb movement sequence based on the first detection signal, determining whether the limb movement sequence conforms to the target movement pattern, and whether the limb movement sequence is executed in the projection area, and obtaining a judgment result; if the judgment result meets the preset conditions, then controlling the tailgate to execute a closing or opening operation based on the state information of whether the tailgate is open or closed.

[0185] The processor 801 may also implement other steps in the above-mentioned tailgate control method, which will not be described in detail here.

[0186] The communication bus mentioned in the above electronic device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0187] The communication interface is used for communication between the above electronic device and other devices.

[0188] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0189] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0190] In another embodiment of the present invention, a computer-readable storage medium is provided. The computer-readable storage medium stores instructions. When the instructions are executed on a computer, the computer executes the tailgate control method described in the above embodiment.

[0191] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer executes the tailgate control method described in the above embodiment.

[0192] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center to another website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state hard disk Solid State Disk (SSD)), etc.

[0193] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0194] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. For the embodiments of the device, electronic device, computer-readable storage medium and computer program products containing instructions, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0195] The above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention are included in the protection scope of the present invention.

Claims

1. A tailgate control method, characterized in that: The method comprises: Controlling the projection device to project a projection area on the ground, and controlling the radar to transmit a first detection signal; Acquire a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result; If the judgment result meets the preset condition, the tailgate is controlled to perform a closing or opening operation according to the state information of whether the tailgate is opened or closed.

2. The method according to claim 1, characterized in that The controlling the projection device to project a projection area on the ground comprises: When the vehicle is stationary and the vehicle key is within a first preset range from the vehicle, controlling the radar to emit a second detection signal; determining the distance between the human body and the radar according to the second detection signal; When the distance is within the second preset range, the projection device is controlled to project a projection area on the ground.

3. The method according to claim 1, characterized in that The step of acquiring a limb motion sequence according to the first detection signal comprises: receiving a feedback signal for the first detection signal; Preprocessing the feedback signal and extracting limb point cloud data; According to each frame of limb point cloud data, the limb movement sequence is determined.

4. The method according to claim 3, characterized in that: The preprocessing of the feedback signal and extraction of limb point cloud data includes: Performing range-dimensional Fourier transform and Doppler-dimensional Fourier transform on the feedback signal to obtain frequency spectrum data of multiple channels; Performing non-coherent accumulation processing on the spectrum data to obtain a range Doppler matrix; Performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix; According to the average constant false alarm detection matrix, the limb point cloud data is extracted.

5. The method according to claim 4, characterized in that The performing constant false alarm detection on the range Doppler matrix to determine an average constant false alarm detection matrix includes: Performing average constant false alarm detection on the range data of each Doppler unit in the range Doppler matrix to obtain a first detection value; Performing average constant false alarm detection on the Doppler data of each range unit in the range-Doppler matrix to obtain a second detection value; An average constant false alarm detection matrix is ​​determined according to the first detection value and the second detection value.

6. The method according to claim 4, characterized in that Determining whether the limb movement sequence conforms to the target movement pattern includes: Cluster each frame of limb point cloud data to obtain the target cluster data corresponding to each frame of limb point cloud data; Determine feature data of each frame of limbs according to the target cluster data; the feature data includes: center position, speed and orientation; Determine whether the limb movement sequence conforms to the target movement pattern according to the feature data.

7. The method according to claim 6, characterized in that The step of determining whether the limb movement sequence conforms to the target movement pattern according to the feature data comprises: Determining, based on the characteristic data, whether the limb motion sequence includes a first sequence characterizing that the limb enters the projection area, and a second sequence characterizing that the limb leaves the projection area; In case of including a first sequence and a second sequence, whether the limb motion sequence conforms to the target motion pattern is determined according to the duration of the first sequence and the second sequence.

8. The method according to claim 7, characterized in that The determining, based on the characteristic data, whether the limb action sequence includes a first sequence representing a limb entering a projection area, and a second sequence representing a limb leaving the projection area comprises: Determine the speed and direction of the limb movement according to the characteristic data; The limb point cloud data whose speed direction of the limb movement is a first direction is determined as a first sequence, and the limb point cloud data whose speed direction of the limb movement is a second direction is determined as a second sequence.

9. The method according to claim 7, characterized in that: The step of determining whether the limb motion sequence conforms to the target motion pattern according to the duration of the first sequence and the second sequence comprises: Obtaining the number of point cloud data of each frame in the first sequence and the second sequence; Determining the duration of the first sequence and the second sequence according to the amount of the point cloud data; When the duration falls within a preset time range, it is determined that the limb movement sequence conforms to the target movement pattern.

10. The method according to claim 1, characterized in that The limb movement sequence includes any one of a foot movement sequence and a hand movement sequence.

11. A vehicle, characterized in that: The vehicle comprises: a radar, a projection device and a controller; The controller is used to control the projection device to project a projection area on the ground, and to control the radar to transmit a first detection signal; The radar is used to obtain a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result; The controller is used for controlling the tailgate to close or open according to the state information of the tailgate being opened or closed if the judgment result meets the preset condition.

12. A tailgate control device, characterized in that: The device comprises: A first control module, used to control the projection device to project a projection area on the ground, and to control the radar to transmit a first detection signal; A judgment module, used to obtain a limb motion sequence according to the first detection signal, determine whether the limb motion sequence conforms to a target motion pattern, and whether the limb motion sequence is performed in the projection area, and obtain a judgment result; The second control module is used for controlling the tailgate to close or open according to the state information of the tailgate being opened or closed if the judgment result meets the preset condition.

13. An electronic device, characterized in that: include: A processor, a communication interface, a memory and a communication bus; wherein the processor, the communication interface and the memory communicate with each other via the communication bus; Memory, used to store computer programs; The processor is used to implement the steps of the tailgate control method according to any one of claims 1 to 10 when executing the program stored in the memory.

14. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the steps of the tailgate control method according to any one of claims 1 to 10 are implemented.

Images