A sensorless vehicle entry method and a sensorless vehicle entry system

Abstract

The present invention relates to a method and device for entering a vehicle by induction. The method includes: establishing a Bluetooth communication connection between the vehicle and a mobile terminal held by a user, and obtaining the position information of the mobile terminal based on Bluetooth positioning; when it is determined according to the position information of the mobile terminal that the mobile terminal is located in the induction area for entering the vehicle without sensing, waking up the vehicle to start performing millimeter-wave sensing; the vehicle obtaining the position information of one or more pedestrians in the induction area based on millimeter-wave sensing positioning, matching the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning with the position information of the mobile terminal obtained based on Bluetooth positioning to determine the actual user entering the vehicle, obtaining the point cloud sub-data of the actual user entering the vehicle, and determining the identity information of the actual user entering the vehicle based on the point cloud sub-data; determining whether to perform the unlocking control of the vehicle based on the identity information of the actual user entering the vehicle.

Description

Technical Field

[0001] The present invention relates to vehicle networking technology, and specifically to a method and system for entering a vehicle without sensing based on Bluetooth positioning and millimeter-wave gait perception. Background Art

[0002] The existing technical solutions for entering a vehicle without sensing mainly include the following three types:

[0003] One is the digital key technology solution based on Bluetooth. According to the Bluetooth RSSI positioning principle, the position of the mobile terminal is obtained in real time to achieve automatic unlocking and locking.

[0004] The second is the digital key technology solution based on UWB. Utilizing the high positioning accuracy of UWB technology, the position of the digital key of the mobile terminal based on the vehicle is obtained in real time to control the unlocking and locking of the vehicle.

[0005] The third is the digital key technology solution based on NFC. Utilizing NFC communication technology to achieve the authentication and identification of the digital key of the mobile terminal by the vehicle end, and controlling the vehicle to automatically unlock and lock.

[0006] However, in the existing technology, the solutions for entering a vehicle without sensing based on Bluetooth and UWB only rely on the positioning of the mobile terminal by the vehicle end. If the mobile terminal is lost, lent out, or the communication between the mobile terminal and the vehicle end encounters a relay attack, there will be a risk of vehicle theft. And the solution for entering a vehicle without sensing based on NFC requires the user to take out the mobile terminal and complete the card swiping identification at a position relatively close to the vehicle, and cannot achieve true entry into the vehicle without sensing. Summary of the Invention

[0007] In view of the above problems, the present invention aims to propose a method and system for entering a vehicle without sensing that can improve the security of entering a vehicle without sensing.

[0008] Furthermore, the present invention also aims to propose a method and system for entering a vehicle without sensing that can integrate Bluetooth technology and millimeter-wave technology and at the same time reduce the complexity of millimeter-wave multi-person gait perception.

[0009] Furthermore, the present invention also aims to propose a method and system for entering a vehicle without sensing that can solve the matching problem between Bluetooth positioning and millimeter-wave sensing and ensure that the positioning results of both are the same.

[0010] The method for entering a vehicle without sensing according to one aspect of the present invention is characterized by including:

[0011] A positioning step, in which the vehicle establishes a Bluetooth communication connection with the mobile terminal held by the user, and obtains the position information of the mobile terminal based on Bluetooth positioning through Bluetooth communication;

[0012] Wake-up step: When it is determined according to the position information of the mobile terminal obtained by Bluetooth positioning that the mobile terminal enters the induction area for seamless entry into the vehicle, wake up the vehicle to start performing millimeter-wave sensing, where the induction area for seamless entry into the vehicle is within a preset range around the vehicle.

[0013] Sensing step: The vehicle obtains the position information of one or more pedestrians within the induction area based on millimeter-wave sensing positioning, matches the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning with the position information of the mobile terminal obtained based on Bluetooth positioning to determine the actual user entering the vehicle, obtains the point cloud sub-data of the actual user entering the vehicle, and determines the identity information of the actual user entering the vehicle based on the point cloud sub-data.

[0014] Unlocking step: Determine whether the identity information of the actual user entering the vehicle is consistent with the pre-registered unlocking user identity information, and perform the unlocking action of the vehicle when they are consistent.

[0015] Optionally, the positioning step includes:

[0016] Complete security authentication between the vehicle and the mobile terminal held by the user, and establish a Bluetooth communication connection;

[0017] Obtain the Bluetooth signal strength of the mobile terminal in real time; and

[0018] Based on the Bluetooth signal strength, obtain the position information of the mobile terminal in real time according to Bluetooth RSSI positioning.

[0019] Optionally, the sensing step includes:

[0020] The vehicle detects one or more pedestrians within the induction area through millimeter-wave sensing, and obtains one or more frames of point cloud data;

[0021] Match the position information of the mobile terminal obtained based on Bluetooth positioning with the position information of the reflection points in the point cloud data obtained based on millimeter-wave detection, and regard the pedestrians with consistent information as the actual users entering the vehicle;

[0022] Obtain the point cloud sub-data of the actual user entering the vehicle;

[0023] Match the point cloud sub-data of the actual user entering the vehicle in each frame to obtain the gait point cloud sequence of the actual user entering the vehicle;

[0024] Input the gait point cloud sequence of the actual user entering the vehicle into a gait recognition model for identifying gait features, identify the gait features through the gait recognition model, and obtain the identity information of the actual user entering the vehicle corresponding to the identified gait features according to the pre-established and stored correspondence between the gait features and the user's identity information.

[0025] Optionally, the point cloud data includes a plurality of reflected point data, and each reflected point data includes the three-dimensional coordinates and velocity information of the reflected point.

[0026] Optionally, the matching of the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning with the position information of the mobile terminal obtained based on Bluetooth positioning includes:

[0027] Pre-estimating the error between millimeter-wave sensing positioning and Bluetooth positioning to obtain an error estimation value between millimeter-wave sensing positioning and Bluetooth positioning; and

[0028] After calibrating the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning or the position information of the mobile terminal obtained based on Bluetooth positioning based on the error estimation value, then perform the matching between the two.

[0029] Optionally, the error estimation value between the millimeter-wave sensing positioning and Bluetooth positioning is obtained through the following steps:

[0030] Collection step, collecting the position data of Bluetooth positioning and millimeter-wave sensing positioning for the same target;

[0031] Coordinate transformation step, transforming the position data of the same target to the same measurement coordinate system,

[0032] Time synchronization step, taking the acquisition time point of one of Bluetooth positioning and millimeter-wave sensing positioning as a reference, and performing time synchronization on the acquisition data of the misaligned time point of the other party by means of linear interpolation between the two closest points; and

[0033] System error estimation step, establishing a system error estimation model based on slant range, azimuth angle, and elevation angle, and obtaining the error estimation value between the millimeter-wave sensing positioning and Bluetooth positioning based on the system error estimation model.

[0034] Optionally, the time synchronization step includes:

[0035] Taking millimeter-wave sensing positioning as a reference, assuming that the time stamp of the nth data item of millimeter-wave sensing positioning is t 1n ;

[0036] Finding the two time stamps t 1n closest to the time stamp t 2l in the data of Bluetooth positioning, 2h and setting the data of Bluetooth positioning at these two time stamps as X 2l and X 2h respectively;

[0037] Obtaining the data of Bluetooth positioning at the time stamp t 1n ​Data interpolation of the moment X 2n is:

[0038]

[0039] Optionally, the system error estimation step includes:

[0040] Assume that the target positions observed by millimeter-wave sensing positioning and Bluetooth positioning at the t-th moment are R A (t) and R B (t), which can be expressed as:

[0041]

[0042]

[0043] where r, θ, are the slant range, azimuth angle, and elevation angle respectively.

[0044]

[0045] Here, respectively represent the true position information observed by the millimeter-wave radar and the Bluetooth radar without errors. Among them, Δ A , Δ B are fixed biases, and σ A , σ B are random noises.

[0046] Assume that in the common coordinate system, the position coordinates of the millimeter-wave radar and the Bluetooth radar at the k-th moment are X A (t), X B (t), which are respectively expressed as:

[0047] X A (t) = [x A (t), y A (t), z A (t)] T

[0048] X B (t) = [x B (t), y B (t), z B (t)] T

[0049] Then the relationship Z A (t) between X A (t) and R B (t), X B (t) and R BA (t) can be established, which is expressed as:

[0050] Z BA Z(t)=X B Z(t)-X A Z(t),

[0051] By substitution and transformation, Z BA Z(t) with respect to Δ A 、Δ B 、σ A Z(t)、σ B Z(t) is obtained as a systematic error estimation model;

[0052] By estimating the fixed error using the least squares method, an estimated value of the fixed deviation can be obtained.

[0053] Optionally, in the unlocking step, when it is determined that the identity information of the actual user getting into the vehicle is consistent with the identity information of the pre-registered unlocking user and it is determined that the actual user getting into the vehicle is within the unlocking area of the sensing area, the unlocking action of the vehicle is performed.

[0054] The touchless entry system according to one aspect of the present invention is characterized in that it includes: a mobile terminal, a vehicle terminal, and a background server,

[0055] wherein, the mobile terminal is used to establish a Bluetooth communication connection with the vehicle terminal,

[0056] the vehicle terminal is used to establish a Bluetooth communication connection with the mobile terminal and obtain the position information of the mobile terminal based on Bluetooth positioning, and upload the position information of the mobile terminal to the background server,

[0057] the background server is used to receive the position information of the mobile terminal and issue a wake-up command for waking up millimeter-wave sensing and positioning to the vehicle terminal when it is determined according to the position information of the mobile terminal that the mobile terminal is within the sensing area of touchless entry, wherein, the sensing area of touchless entry is within a preset range around the vehicle,

[0058] the vehicle terminal performs millimeter-wave sensing and positioning according to the wake-up command, obtains the position information of one or more pedestrians within the sensing area and obtains corresponding one or more pedestrian point cloud sub-data, and sends the one or more pedestrian point cloud sub-data to the background server,

[0059] The background server matches the location information of the mobile terminal obtained based on Bluetooth positioning with the one or more pedestrian point cloud subsets to determine the actual user getting into the vehicle, obtains the point cloud sub-data of the actual user getting into the vehicle, matches the point cloud sub-data of the actual user getting into the vehicle in each frame, obtains the gait point cloud sequence of the actual user getting into the vehicle and inputs it into a gait recognition model for identifying gait features, identifies the gait features of the actual user getting into the vehicle through the gait recognition model, obtains the identity information of the actual user getting into the vehicle corresponding to the identified gait features according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server, determines whether the identity information of the actual user getting into the vehicle is consistent with the pre-registered unlocking user identity information, and issues an unlocking instruction to the vehicle terminal when they are consistent.

[0060] The vehicle terminal executes the unlocking action of the vehicle according to the unlocking instruction.

[0061] Optionally, the mobile terminal includes:

[0062] A first Bluetooth module for establishing a Bluetooth communication connection with the vehicle terminal;

[0063] A digital key module for executing the unlocking action of the vehicle according to the received unlocking instruction.

[0064] Optionally, the vehicle terminal includes:

[0065] A second Bluetooth module for establishing a Bluetooth communication connection with the mobile terminal, obtaining the strength of the Bluetooth signal sent by the first Bluetooth module of the mobile terminal and sending it to the background server; and

[0066] A millimeter wave module for performing millimeter wave sensing positioning according to the wake-up instruction, obtaining the position information of one or more pedestrians in the sensing area based on the millimeter wave sensing positioning and obtaining one or more frames of corresponding point cloud data, and sending the point cloud data to the background server.

[0067] Optionally, the background server includes:

[0068] A wake-up module for receiving the location information of the mobile terminal and issuing a wake-up instruction to wake up the millimeter wave sensing positioning of the vehicle terminal when it is determined according to the location information of the mobile terminal that the mobile terminal is located in the sensing area of touchless entry into the vehicle;

[0069] A matching module for matching the location information of the mobile terminal obtained based on Bluetooth positioning with the point cloud subsets to determine the actual user getting into the vehicle, obtaining the point cloud sub-data of the actual user getting into the vehicle, and determining the identity information of the actual user getting into the vehicle based on the point cloud sub-data of the actual user getting into the vehicle; and

[0070] A judgment module determines whether the identity information of the actual user getting into the vehicle is consistent with the identity information of the pre-registered unlocking user, and issues an unlocking instruction to the vehicle terminal when they are consistent.

[0071] Optionally, in the matching module, the position information of the mobile terminal obtained based on Bluetooth positioning is matched with the one or more pedestrian point cloud sub-data to determine the actual user getting into the vehicle, and the point cloud sub-data of this actual user getting into the vehicle is obtained. The point cloud sub-data of the actual user getting into the vehicle in each frame is matched to obtain the gait point cloud sequence of the actual user getting into the vehicle and input it into a gait recognition model for identifying gait features. The gait features of the actual user getting into the vehicle are identified through the gait recognition model, and the identity information of the actual user getting into the vehicle corresponding to the identified gait features is obtained according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server.

[0072] Optionally, the point cloud data includes a plurality of reflection point data, and each reflection point data includes the three-dimensional coordinates and velocity information of the reflection point.

[0073] Optionally, the matching of the position information of the mobile terminal obtained based on Bluetooth positioning with the position information of the reflection points in the point cloud data obtained based on millimeter-wave detection includes:

[0074] Pre-estimate the error between millimeter-wave perception positioning and Bluetooth positioning in advance to obtain an error estimate value between millimeter-wave perception positioning and Bluetooth positioning; and

[0075] After calibrating the position information of one or more pedestrians obtained based on millimeter-wave perception positioning or the position information of the mobile terminal obtained based on Bluetooth positioning based on the error estimate value, then perform the matching of the two.

[0076] Optionally, the error estimate value between the millimeter-wave perception positioning and the Bluetooth positioning is obtained through the following method:

[0077] Collect the position data of the same target for Bluetooth positioning and millimeter-wave perception positioning;

[0078] Convert the position data of the same target to the same measurement coordinate system,

[0079] Taking the acquisition time point of one of Bluetooth positioning and millimeter-wave perception positioning as a reference, perform time synchronization on the acquisition data of the misaligned time point of the other party through linear interpolation of the nearest two points; and

[0080] Based on the slant range, azimuth angle, and elevation angle, establish a system error estimation model, and obtain the error estimate value between the millimeter-wave perception positioning and the Bluetooth positioning based on the system error estimation model.

[0081] Optionally, in the determination module, when it is determined that the identity information of the actual user getting into the vehicle is consistent with the identity of the unlocking user for keyless entry of the mobile terminal, and when it is determined that the actual user getting into the vehicle is within the unlocking area of the sensing area, an unlocking instruction is issued.

[0082] A computer-readable medium according to one aspect of the present invention, on which a computer program is stored, characterized in that when the computer program is executed by a processor, the keyless entry method described above is implemented.

[0083] A computer device according to one aspect of the present invention, including a storage module, a processor, and a computer program stored on the storage module and executable on the processor, wherein when the processor executes the computer program, the keyless entry method described above is implemented. BRIEF DESCRIPTION OF THE DRAWINGS

[0084] Figure 1 It is a schematic structural diagram showing the keyless entry system of the present invention.

[0085] Figure 2 It is a schematic flowchart showing the general process of the keyless entry method of the present invention.

[0086] Figure 3 It is a schematic diagram showing the vehicle sensing area.

[0087] Figure 4 It is a schematic timing diagram showing a specific embodiment of the keyless entry method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0088] The following describes some of the multiple embodiments of the present invention, aiming to provide a basic understanding of the present invention. It is not intended to identify the key or decisive elements of the present invention or to limit the scope to be protected.

[0089] For the sake of simplicity and illustrative purposes, the principles of the present invention are mainly described herein with reference to its exemplary embodiments. However, those skilled in the art will readily recognize that the same principles can be equivalently applied to all types of keyless entry methods and keyless entry systems and can be implemented therein, and any such variations do not depart from the true spirit and scope of this patent application.

[0090] Moreover, in the following description, reference is made to the accompanying drawings which illustrate specific exemplary embodiments. Electrical, mechanical, logical, and structural changes may be made to these embodiments without departing from the spirit and scope of the present invention. Additionally, although a feature of the present invention is disclosed in conjunction with only one of several implementations / embodiments, this feature may be combined with one or more other features of other implementations / embodiments as may be desired and / or advantageous for any given or identifiable function. Accordingly, the following description should not be taken in a limiting sense, and the scope of the present invention is defined by the appended claims and their equivalents.

[0091] Terms such as "comprising" and "including" indicate that in addition to having the units (modules) and steps directly and explicitly stated in the specification and claims, the technical solutions of the present invention do not exclude the case of having other units (modules) and steps not directly or explicitly stated.

[0092] Figure 1 It is a schematic structural diagram showing the passive entry vehicle system of the present invention.

[0093] As Figure 1 shown, the passive entry vehicle system of the present invention includes: a mobile terminal 100, a vehicle terminal 200, and a background server 300. The mobile terminal 100 includes: a first Bluetooth module 110 and a digital key module 120. The vehicle terminal 200 includes: a second Bluetooth module 210 and a millimeter wave module 220. The background server 300 includes: a wake-up module 310, a matching module 320, and a judgment module 330. The specific functions of these modules will be described later. Here, the passive entry vehicle method of the present invention will be described first.

[0094] Figure 2 It is a schematic overview flowchart showing the passive entry vehicle method of the present invention.

[0095] As Figure 1 shown, the passive entry vehicle method of the present invention can be roughly divided into the following steps:

[0096] (1) Mobile terminal positioning step S100

[0097] A security authentication is completed between the first Bluetooth module 110 of the mobile terminal 100 and the second Bluetooth module 210 of the vehicle terminal 200 to establish a Bluetooth communication connection. The second Bluetooth module 210 continuously obtains the Bluetooth signal strength sent by the mobile terminal 100 and sends it to the background server 300. The background server 300 calculates and obtains the position of the mobile terminal 100 in real time based on the Bluetooth RSSI positioning principle.

[0098] Among them, RSSI is the abbreviation of Received Signal Strength Indication, which is the received signal strength indication, an optional part of the wireless transmission layer, used to determine the link quality and whether to increase the broadcast transmission intensity. It is a positioning technology that measures the distance between the signal point and the receiving point through the strength of the received signal, and then performs positioning calculations based on the corresponding data. Bluetooth RSSI positioning refers to a positioning method that calculates the location of the Bluetooth terminal using the correlation between the attenuation of the Bluetooth RSSI signal and the distance.

[0099] (2) Millimeter-wave sensing wake-up step S200

[0100] When the background server 300 locates that the mobile terminal 100 enters the sensing area (as Figure 3 shown), the background server 300 wakes up the millimeter-wave module 220 to make it enter the sensing state. Figure 3 It is a schematic diagram showing the vehicle sensing area. Figure 3 In, the large circle A circled around the vehicle represents the sensing area (i.e., the sensing area is located within the preset range around the vehicle), and within this sensing area, there can further be an unlocking area represented by the small circle B. The sizes of the sensing area and the unlocking area can be preset according to the actual situation, and in the present invention, no limitation is made on their sizes as long as the unlocking area is within the sensing area.

[0101] In step S200, since the millimeter-wave module 220 is woken up based on the result of Bluetooth positioning, in this way, the millimeter-wave module 220 does not need to be in the working state all the time, thus effectively reducing power consumption.

[0102] (3) Millimeter-wave gait sensing step S300

[0103] This step S300 mainly includes the following sub-steps:

[0104] The millimeter-wave module 220 detects multiple users in the vehicle sensing area, obtains multiple frames of point cloud data and sends it to the background server 300;

[0105] The background server 300 compares the position information of the mobile terminal 100 obtained based on Bluetooth positioning with the position information of the reflection points in the point cloud data, locks the user holding the mobile terminal 100 as the actual user getting into the vehicle, and obtains its point cloud sub-data;

[0106] Match the point cloud sub-data of the actual user getting into the vehicle in each frame to obtain the gait point cloud sequence of the actual user getting into the vehicle;

[0107] Input the gait point cloud sequence of the actual vehicle-entering user into the gait recognition model for identifying gait features to obtain the gait features of the actual vehicle-entering user, and compare the gait features with the gait features stored in the background server 300. Among them, the background server 300 pre-stores the corresponding relationship between the gait features and the user identities, and based on this corresponding relationship, the corresponding user identity, that is, the identity information of the actual vehicle-entering user, can be obtained based on the gait features.

[0108] In this step S300, the background server 300 can identify the actual vehicle-entering user from the point cloud data of multiple users obtained from the millimeter-wave module 220 based on the position information of the mobile terminal 100 obtained by Bluetooth positioning, so as to obtain the gait point cloud data of the actual vehicle-entering user. Thus, the complexity of millimeter-wave multi-person gait perception can be reduced.

[0109] (4) Automatic unlocking step S400

[0110] The background server 300 determines whether the actual vehicle-entering user is consistent with the pre-registered unlocking user identity information in the digital key module 120 of the mobile terminal 100 (for example, the pre-registered unlocking user identity information in the digital key module 120 is pre-saved in the background server 300. When judging, the background server 300 compares whether the identity information of the actual vehicle-entering user obtained in the millimeter-wave gait perception step S300 is consistent with the pre-registered unlocking user identity information). If they are consistent, and when it is located that the actual vehicle-entering user and its mobile terminal 100 have entered the unlocking area, then the background server 300 issues an unlocking instruction to the vehicle terminal 200, and the vehicle terminal 200 executes the unlocking of the vehicle according to the unlocking instruction.

[0111] Next, a specific embodiment of the keyless vehicle entry method of the present invention will be described.

[0112] Figure 4 It is a timing schematic diagram showing a specific embodiment of the keyless vehicle entry method of the present invention.

[0113] As Figure 4 shown, a specific embodiment of the keyless vehicle entry method of the present invention includes the following specific steps:

[0114] S1: The first Bluetooth module 110 of the mobile terminal 100 held by the user and the second Bluetooth module 120 of the vehicle terminal 200 complete security authentication and establish a Bluetooth communication connection.

[0115] S2: The second Bluetooth module 120 of the vehicle terminal 200 continuously obtains the Bluetooth signal strength sent by the first Bluetooth module 110 of the mobile terminal 100 and sends it to the background server 300.

[0116] S3: The backend server 300 calculates the location information of the mobile terminal 100 according to the Bluetooth RSSI positioning algorithm, and determines whether the user has entered the Figure 3 sensing area.

[0117] S4: When it is located that the user has entered the sensing area, the background server 300 wakes up the millimeter wave sensing module 220 and puts it into a sensing working state.

[0118] S5: The millimeter wave sensing module 220 detects multiple users in the sensing area, obtains point cloud data of the multiple users and sends it to the background server 300, where the point cloud data includes multiple reflection point data, and each reflection point data includes the three-dimensional coordinates, speed and other information of the reflection point.

[0119] S6: The backend server 300 compares the position information of the reflection point in the point cloud data with the position information of the mobile terminal obtained according to the Bluetooth RSSI positioning algorithm, locks the user holding the mobile terminal as the actual user entering the vehicle, and obtains his point cloud sub-data.

[0120] In this step, the combination of Bluetooth positioning and millimeter wave sensing technology will bring about a new technical problem: due to the existence of errors, the mobile terminal location data obtained by the second Bluetooth module 210 and the reflection point location data in the pedestrian point cloud data obtained by the millimeter wave sensing module 220 cannot match, resulting in the inability to use the mobile terminal location to quickly lock the actual user who has entered the vehicle with the handheld mobile terminal.

[0121] In order to solve this problem, the present invention proposes a method for matching the positioning data of the second Bluetooth module 210 and the millimeter wave sensing module 220 in advance. The specific steps are as follows:

[0122] (1) Raw data collection

[0123] When the second Bluetooth module 210 and the millimeter wave sensing module 220 collect position data of the same target, the position data obtained may be different due to the existence of errors.

[0124] (2) Coordinate transformation

[0125] The measurement data of the second Bluetooth module 210 and the millimeter wave sensing module 220 are converted into the same measurement coordinate system.

[0126] (3) Time synchronization

[0127] This step is to avoid position deviation caused by asynchronous sampling moments. Only position information obtained at the same sampling moment is comparable. In the present invention, the measurement time of the millimeter-wave radar in the millimeter-wave sensing module 220 is selected as the benchmark, and the measurement data at the time points misaligned by the second Bluetooth module 210 (hereinafter also referred to as "Bluetooth radar" for convenient comparison) is time-synchronized by the method of linear interpolation between the two closest points.

[0128] As an embodiment, for example, taking the millimeter-wave radar as the benchmark, the time stamp of the nth data item measured by the millimeter-wave radar is t 1n , and find the two time stamps t 1n in the measurement data of the Bluetooth radar that are closest to t 2l and t 2h . The data of the Bluetooth radar at these two time stamps are X 2l and X 2h respectively. Then, the data interpolation X 1n of the Bluetooth radar at time t 2n is obtained by linear interpolation as:

[0129]

[0130] (4) System error estimation.

[0131] Through the above steps, the errors caused by different coordinate systems and different sampling moments are excluded. Next, the system itself error is further estimated, and the slant range r, azimuth angle θ, and elevation angle are selected to estimate the three factors that have the greatest impact on the system error.

[0132] First, establish a system error estimation model for the three parameters.

[0133] Assume that the target positions observed by the millimeter-wave radar and the Bluetooth radar at the t-th moment are R A (t) and R B (t) respectively, and they can be expressed as:

[0134]

[0135]

[0136] Among them, r, θ, and are the slant range, azimuth angle, and elevation angle respectively.

[0137]

[0138] Here, respectively represent the true position information observed by the millimeter-wave radar and the Bluetooth radar without errors. Among them, Δ A, Δ B is the fixed deviation, σ A , σ B is the random noise. Among them, the fixed deviation is estimated by the least squares method, and the random noise can be ignored. The above formula aims to express that the error between the target position information measured by the sensor and the true position information of the target is caused by the fixed deviation and random noise.

[0139] Assume that in the common coordinate system, the position coordinates of the millimeter-wave radar and the Bluetooth radar at time k are X A (t), X B (t), and they can be expressed as follows:

[0140] X A (t) = [x A (t), y A (t), z A (t)] T

[0141] X B (t) = [x B (t), y B (t), z B (t)] T 25

[0142] Then, the relationship Z A (t) between X A (t) and R B (t), and the relationship Z B (t) between X BA (t) and R

[0143] Z BA (t) = X B (t) - X A (t),

[0144] Finally, through substitution and transformation, the relationship of Z BA (t) with respect to Δ A , Δ B , σ A (t), σ B (t) can be obtained as the error estimation model.

[0145] Then, the estimated value of the fixed deviation can be obtained by estimating the fixed error through the least squares method.

[0146] Among them, the specific calculation process of obtaining the error estimation model through substitution and transformation and estimating the fixed error by the least squares method to obtain the estimated value of the fixed deviation is as follows:

[0147] ① The target position observed by millimeter-wave sensor A at time t is The target position observed by Bluetooth sensor B at time t is where r, θ, are the slant range, azimuth angle, and elevation angle, respectively;

[0148] ② In the case of no error, the target positions observed by A and B at time t are

[0149] ③ The fixed biases observed by A and B at time t are

[0150] ④ The random noises observed by A and B at time t are

[0151] ⑤ Then:

[0152]

[0153] ⑥ Convert to the Cartesian coordinate system [x A (t), y A (t), z A (t)], [x B (t), y B (t), z B (t)],

[0154] Then,

[0155] ⑦ Substitute Equation 1 into Equation 2 to obtain:

[0156] x A (t) = …, y A (t) = …, z A (t) = …, x B (t) = …, y B (t) = …, z B (t) = …;

[0157] ⑧ Let Perform linearization on z BA (t),

[0158] Using the first-order Taylor expansion, we can obtain:

[0159] The relationship between z BA (t) and , that is, the error estimation model;

[0160] ⑨ Use the least squares method for the fixed biases Δ A and Δ BEstimation is carried out, ignoring the random noises σA and σB, and the objective function is

[0161]

[0162] That is, the sum of the squares of the errors is minimized, and the summation is solved to obtain the estimated value of the fixed bias value.

[0163] (5) Position calibration.

[0164] The result obtained by error estimation is used to adjust and compensate the subsequent measurement data, so that the measurement data of the second Bluetooth module 210 and the millimeter-wave sensing module 220 for the same target can be matched.

[0165] Here, it should also be noted that the calculation of the above fixed bias value can be carried out in advance and the calculated estimated value can be saved. In the actual application process of entering the vehicle without sensing, only the estimated value of the saved fixed bias value needs to be used to correct the positioning data of the second Bluetooth module 210 and the millimeter-wave sensing module 220, so that it will not affect the data processing speed in the actual application process of entering the vehicle without sensing.

[0166] S7: The background server 300 matches the point cloud sub-data of the actual vehicle-entering user in each frame to determine its gait point cloud sequence.

[0167] S8: The background server 300 inputs the gait point cloud sequence of the actual vehicle-entering user into the gait recognition model for identifying gait features to obtain its gait recognition result, that is, the gait features. At the same time, according to the corresponding relationship between the gait features and the user's identity information pre-established and stored in the background server 300, the identity information of the actual vehicle-entering user corresponding to the identified gait features is obtained.

[0168] S9: The background server 300 compares the identity information of the actual vehicle-entering user obtained in S⑧ with the pre-registered unlocking user identity information and the target user has entered Figure 3 the unlocking area, and then sends an unlocking instruction to the vehicle terminal 200.

[0169] As described above, according to the method for entering the vehicle without sensing of the present invention, by adding user identity information verification based on millimeter-wave gait sensing, it can be ensured that the user identity information corresponding to the digital key is consistent with the identity information of the actual vehicle-entering user, improving the security of entering the vehicle without sensing. Moreover, through the fusion of Bluetooth technology and millimeter-wave sensing technology, based on the positioning result of the mobile terminal by Bluetooth technology, the sub-data of the actual vehicle-entering user can be quickly locked from the multi-person data sensed by millimeter waves, thereby reducing the complexity of multi-person gait sensing.

[0170] The above has described the method for entering the vehicle without sensing of the present invention. Finally, referring to Figure 1The specific structure of the passive entry vehicle system of the present invention will be described.

[0171] As Figure 1 shown, the passive entry vehicle system of the present invention includes: a mobile terminal 100, a vehicle terminal 200, and a background server 300.

[0172] The mobile terminal 100 is used to establish a Bluetooth communication connection with the vehicle terminal.

[0173] The vehicle terminal 200 is used to establish a Bluetooth communication connection with the mobile terminal 100, obtain the position information of the mobile terminal based on Bluetooth positioning, and upload the position information of the mobile terminal 100 to the background server 300.

[0174] The background server 300 is used to receive the position information of the mobile terminal 100 and send a wake-up instruction to wake up millimeter-wave sensing positioning to the vehicle terminal 200 when it is determined according to the position information of the mobile terminal 100 that the mobile terminal 100 is located in the sensing area of passive entry into the vehicle. The vehicle terminal 200 performs millimeter-wave sensing positioning according to the wake-up instruction, obtains the position information of one or more pedestrians in the sensing area and obtains corresponding one or more pedestrian point cloud sub-data, and sends the one or more pedestrian point cloud sub-data to the background server 300.

[0175] The background server 300 matches the position information of the mobile terminal obtained based on Bluetooth positioning with the one or more pedestrian point cloud sub-data to determine the actual user entering the vehicle, obtains the point cloud sub-data of the actual user entering the vehicle, determines the identity information of the actual user entering the vehicle based on the point cloud sub-data of the actual user entering the vehicle, determines whether the identity information of the actual user entering the vehicle is consistent with the user identity of the pre-registered unlocking user identity, and issues an unlocking instruction to the vehicle terminal in the case of consistency. The vehicle terminal 200 opens the vehicle door according to the unlocking instruction.

[0176] Specifically, the mobile terminal 100 includes:

[0177] A first Bluetooth module 110 for establishing a Bluetooth communication connection with the vehicle terminal;

[0178] A digital key module 120 for performing an unlocking action of the vehicle according to the received unlocking instruction.

[0179] The vehicle terminal 200 includes:

[0180] A second Bluetooth module 210 for establishing a Bluetooth communication connection with the mobile terminal, obtaining the strength of the Bluetooth signal sent by the first Bluetooth module of the mobile terminal, and sending it to the background server; and

[0181] The millimeter-wave module 220 is configured to perform millimeter-wave sensing and positioning according to the wake-up instruction, obtain the position information of one or more pedestrians in the sensing area based on the millimeter-wave sensing and positioning, and obtain one or more frames of corresponding point cloud data, and send the point cloud data to the background server.

[0182] The background server 300 includes:

[0183] The wake-up module 310 is configured to receive the position information of the mobile terminal and send a wake-up instruction for waking up millimeter-wave sensing and positioning to the vehicle terminal 200 when it is determined according to the position information of the mobile terminal 100 that the mobile terminal 100 is located in the sensing area of the keyless entry into the vehicle;

[0184] The matching module 320 matches the position information of the mobile terminal 100 obtained based on Bluetooth positioning with the point cloud sub-data to determine the actual user entering the vehicle, obtains the point cloud sub-data of the actual user entering the vehicle, and determines the identity information of the actual user entering the vehicle based on the point cloud sub-data of the actual user entering the vehicle; and

[0185] The judgment module 330 judges whether the identity information of the actual user entering the vehicle is consistent with the pre-registered unlocking user identity information, and issues an unlocking instruction to the vehicle terminal 200 in the case of consistency.

[0186] Among them, in the matching module 320, the position information of the mobile terminal obtained based on Bluetooth positioning is matched with the one or more pedestrian point cloud sub-data to determine the actual user entering the vehicle, obtains the point cloud sub-data of the actual user entering the vehicle, matches the point cloud sub-data of the actual user entering the vehicle in each frame, obtains the gait point cloud sequence of the actual user entering the vehicle and inputs it into a gait recognition model for recognizing gait features, recognizes the gait features of the actual user entering the vehicle through the gait recognition model, and obtains the identity information of the actual user entering the vehicle corresponding to the recognized gait features according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server.

[0187] As described above, according to the keyless entry method and the keyless entry system of the present invention, the following technical effects can be obtained:

[0188] By adding an identity information verification link based on millimeter-wave gait sensing on the basis of the digital key positioning of the mobile terminal, it can be ensured that the identity information of the actual user entering the vehicle (obtained through millimeter-wave gait sensing) is consistent with the user identity information corresponding to the digital key of the mobile terminal (obtained through Bluetooth interaction), avoiding the risk of vehicle theft in the case of loss, external borrowing of the smart terminal or relay attack on the communication between the smart terminal and the vehicle terminal, and improving the security of the keyless entry technical solution;

[0189] Through the integration of Bluetooth and millimeter-wave sensing technology, based on the positioning result of the digital key of the mobile terminal by Bluetooth, the sub-data of the actual user getting into the vehicle can be quickly locked from multiple pedestrian data sensed by millimeter-wave in the sensing area, reducing the complexity of millimeter-wave multi-person gait sensing; and

[0190] Aiming at the problem that the positioning data of the mobile terminal obtained by Bluetooth technology and the pedestrian data sensed by the millimeter-wave module may not overlap and cannot be matched, this invention proposes a method for pre-matching the positioning data obtained by Bluetooth technology and the positioning data of the millimeter-wave module. Through steps such as coordinate transformation, time synchronization, system error estimation, and error compensation correction, it is ensured that the positioning results of both for the same target are the same.

[0191] The above examples mainly illustrate the keyless entry method and the keyless entry system. Although only some specific embodiments of the present invention have been described, those of ordinary skill in the art should understand that the present invention can be implemented in many other forms without departing from its gist and scope. Therefore, the examples and embodiments shown are regarded as illustrative rather than restrictive, and the present invention may cover various modifications and substitutions without departing from the spirit and scope of the present invention as defined by the appended claims.

Claims

1. A method for entering a vehicle without sensing, characterized in that, Including: A positioning step, in which the vehicle establishes a Bluetooth communication connection with a mobile terminal held by the user, and based on the Bluetooth communication, obtains the position information of the mobile terminal through Bluetooth positioning; A wake-up step, in which when it is determined according to the position information of the mobile terminal obtained by the Bluetooth positioning that the mobile terminal enters the induction area for keyless entry into the vehicle, the vehicle is woken up to start performing millimeter-wave sensing, where the induction area for keyless entry into the vehicle is within a preset range around the vehicle; A sensing step, in which the vehicle obtains the position information of one or more pedestrians within the induction area based on millimeter-wave sensing positioning, matches the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning with the position information of the mobile terminal obtained based on Bluetooth positioning to determine the actual user entering the vehicle, obtains the point cloud sub-data of the actual user entering the vehicle, and determines the identity information of the actual user entering the vehicle based on the point cloud sub-data; and An unlocking step, in which it is determined whether the identity information of the actual user entering the vehicle is consistent with the pre-registered unlocking user identity information, and if they are consistent, the unlocking action of the vehicle is performed, wherein, the matching of the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning with the position information of the mobile terminal obtained based on Bluetooth positioning includes: Previously estimating the error between millimeter-wave sensing positioning and Bluetooth positioning to obtain an error estimation value between millimeter-wave sensing positioning and Bluetooth positioning; and Calibrating the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning or the position information of the mobile terminal obtained based on Bluetooth positioning based on the error estimation value and then performing the matching of the two, In the unlocking step, when it is determined that the identity information of the actual user entering the vehicle is consistent with the pre-registered unlocking user identity information and it is determined that the actual user entering the vehicle is within the unlocking area of the induction area, the unlocking action of the vehicle is performed.

2. The touchless vehicle entry method according to claim 1, characterized in that, The positioning step includes: Completing security authentication between the vehicle and the mobile terminal held by the user and establishing a Bluetooth communication connection; Obtaining the Bluetooth signal strength of the mobile terminal in real time; and Based on the Bluetooth signal strength, obtaining the position information of the mobile terminal in real time according to Bluetooth RSSI positioning.

3. The method for entering the vehicle without sensing as claimed in claim 1, wherein In the sensing step, it includes: The vehicle detects one or more pedestrians within the induction area through millimeter-wave sensing and obtains one or more frames of point cloud data; Matching the position information of the mobile terminal obtained based on Bluetooth positioning with the position information of the reflection points in the point cloud data obtained based on millimeter-wave detection, and taking the pedestrians with consistent information as the actual users entering the vehicle; Obtaining the point cloud sub-data of the actual user entering the vehicle; Matching the point cloud sub-data of the actual user entering the vehicle in each frame to obtain the gait point cloud sequence of the actual user entering the vehicle; Inputting the gait point cloud sequence of the actual user entering the vehicle into a gait recognition model for recognizing gait features, recognizing the gait features through the gait recognition model, and obtaining the identity information of the actual user entering the vehicle corresponding to the recognized gait features according to the pre-established and stored corresponding relationship between the gait features and the user's identity information.

4. The keyless entry method according to claim 3, characterized in that, The point cloud data includes a plurality of reflection point data, and each reflection point data includes the three-dimensional coordinates and velocity information of the reflection point.

5. The touchless vehicle entry method according to claim 1, wherein the error estimation value between the millimeter-wave perception positioning and the Bluetooth positioning is obtained through the following steps: An acquisition step of acquiring the position data of the same target by Bluetooth positioning and millimeter-wave perception positioning; A coordinate conversion step of converting the position data of the same target to the same measurement coordinate system; A time synchronization step of taking the acquisition time point of one of the Bluetooth positioning and the millimeter-wave perception positioning as a reference, and performing time synchronization on the acquisition data of the non-aligned time point of the other party by means of linear interpolation of the nearest two points; and A system error estimation step of establishing a system error estimation model based on the slant range, azimuth angle, and elevation angle, and obtaining the error estimation value between the millimeter-wave perception positioning and the Bluetooth positioning based on the system error estimation model.

6. The method for entering a vehicle without sensing as claimed in claim 5, wherein, The time synchronization step includes: Based on millimeter-wave perception positioning as a benchmark, assume that the timestamp of the nth data item of millimeter-wave perception positioning is t 1n ; Find the two timestamps t that are closest in time to the timestamp t in the Bluetooth positioning data 1n among the Bluetooth positioning data 2l 、t 2h . Assume that the data of the Bluetooth positioning at these two timestamps are X 2l 、X 2h ; Obtain the data interpolation X of Bluetooth positioning at the timestamp t through linear interpolation 1n at the moment 2n as follows:

7. The method for entering a vehicle without sensing as claimed in claim 6, wherein The system error estimation step includes: Suppose the target positions observed by millimeter-wave sensing and positioning and Bluetooth positioning at the t-th moment are R A (t) and R B (t), which can be expressed as: where r, θ, are the slant range, azimuth angle, and elevation angle, respectively, Here, respectively represent the true position information observed by the millimeter-wave radar and the Bluetooth radar without errors, where Δ A , Δ B are fixed biases, and σ A , σ B are random noises. Assume that in a common coordinate system, the position coordinates of the millimeter-wave radar and the Bluetooth radar at time k are X A (t) and X B (t), which are respectively expressed as: X A (t) = [x A (t), y A (t), z A (t)] T X B (t) = [x B (t), y B (t), z B (t)] T Then the relationship between X A (t) and R A (t), X B (t) and R B (t) can be established as relationship Z BA (t), which is expressed as: Z BA (t) = X B (t) - X A (t), By substitution and transformation, Z is obtained BA (t) with respect to Δ A 、Δ B 、σ A (t), σ B (t), as the systematic error estimation model; Estimating the fixed error by the least squares method to obtain an estimated value of the fixed bias value.

8. A keyless entry system for vehicles, characterized in that, Including: A mobile terminal, a vehicle terminal, and a background server; wherein the mobile terminal is used to establish a Bluetooth communication connection with the vehicle terminal; the vehicle terminal is used to establish a Bluetooth communication connection with the mobile terminal and obtain the position information of the mobile terminal based on Bluetooth positioning, and upload the position information of the mobile terminal to the background server; the background server is used to receive the position information of the mobile terminal and issue a wake-up command to wake up the millimeter-wave perception positioning to the vehicle terminal when it is determined according to the position information of the mobile terminal that the mobile terminal is located in the induction area of the touchless vehicle entry. The induction area of the touchless vehicle entry is located in a preset range around the vehicle; the vehicle terminal performs millimeter-wave perception positioning according to the wake-up command, obtains the position information of one or more pedestrians in the induction area based on the millimeter-wave perception positioning and obtains corresponding one or more pedestrian point cloud sub-data, and sends the one or more pedestrian point cloud sub-data to the background server; the background server matches the position information of the mobile terminal obtained based on Bluetooth positioning with the one or more pedestrian point cloud sub-data to determine the actual vehicle entry user, obtains the point cloud sub-data of the actual vehicle entry user, matches the point cloud sub-data of the actual vehicle entry user in each frame, obtains the gait point cloud sequence of the actual vehicle entry user and inputs it into a gait recognition model for recognizing gait features, recognizes the gait features of the actual vehicle entry user through the gait recognition model, obtains the identity information of the actual vehicle entry user corresponding to the recognized gait features according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server, determines whether the identity information of the actual vehicle entry user is consistent with the pre-registered unlocking user identity information, and issues an unlocking command to the vehicle terminal in the case of consistency; the vehicle terminal performs an unlocking action on the vehicle according to the unlocking command. Among them, the matching of the position information of the mobile terminal obtained based on Bluetooth positioning and the position information of the reflection points in the point cloud data obtained based on millimeter-wave detection includes: Estimating the error between millimeter-wave sensing positioning and Bluetooth positioning in advance to obtain an error estimation value between millimeter-wave sensing positioning and Bluetooth positioning; and Calibrating the position information of one or more pedestrians obtained based on millimeter-wave sensing positioning or the position information of the mobile terminal obtained based on Bluetooth positioning based on the error estimation value and then performing the matching between the two. Among them, in the judgment module, when it is judged that the identity information of the actual user getting into the vehicle is consistent with the identity of the unlocking user for touchless entry of the mobile terminal and it is judged that the actual user getting into the vehicle is within the unlocking area of the sensing area, an unlocking instruction is issued.

9. The passive entry vehicle system according to claim 8, wherein, The mobile terminal includes: A first Bluetooth module for establishing a Bluetooth communication connection with the vehicle terminal; A digital key module for performing an unlocking action on the vehicle according to the received unlocking instruction.

10. The keyless entry vehicle system according to claim 9, wherein The vehicle terminal includes: A second Bluetooth module for establishing a Bluetooth communication connection with the mobile terminal, obtaining the strength of the Bluetooth signal sent by the first Bluetooth module of the mobile terminal and sending it to the background server; and A millimeter-wave module for performing millimeter-wave sensing positioning according to the wake-up instruction, obtaining the position information of one or more pedestrians within the sensing area based on millimeter-wave sensing positioning and obtaining one or more frames of corresponding point cloud data, and sending the point cloud data to the background server.

11. The keyless entry system according to claim 10, wherein The background server includes: A wake-up module for receiving the position information of the mobile terminal and sending a wake-up instruction for waking up millimeter-wave sensing positioning to the vehicle terminal when it is judged that the mobile terminal is within the sensing area for touchless entry according to the position information of the mobile terminal; A matching module for matching the position information of the mobile terminal obtained based on Bluetooth positioning with the point cloud sub-data to determine the actual user getting into the vehicle, obtaining the point cloud sub-data of the actual user getting into the vehicle, matching the point cloud sub-data of the actual user getting into the vehicle in each frame to obtain a gait point cloud sequence of the actual user getting into the vehicle and inputting it into a gait recognition model for recognizing gait features, and obtaining the identity information of the actual user getting into the vehicle corresponding to the recognized gait features according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server; and A judgment module for judging whether the identity information of the actual user getting into the vehicle is consistent with the pre-registered unlocking user identity information and issuing an unlocking instruction to the vehicle terminal when they are consistent.

12. The touchless entry system according to claim 11, wherein In the matching module, the position information of the mobile terminal obtained based on Bluetooth positioning is matched with the one or more pedestrian point cloud sub-data to determine the actual user getting into the vehicle, obtain the point cloud sub-data of the actual user getting into the vehicle, match the point cloud sub-data of the actual user getting into the vehicle in each frame, obtain a gait point cloud sequence of the actual user getting into the vehicle and input it into a gait recognition model for recognizing gait features, and obtain the identity information of the actual user getting into the vehicle corresponding to the recognized gait features according to the corresponding relationship between the gait features and the user's identity information pre-established and stored by the background server.

13. The touchless entry system according to claim 12, wherein The point cloud data includes a plurality of reflected point data, and each reflected point data includes the three-dimensional coordinates and velocity information of the reflected point.

14. The touchless vehicle entry system according to claim 8, wherein the error estimation value between the millimeter-wave perception positioning and the Bluetooth positioning is obtained by the following method: collect the position data of the Bluetooth positioning and the millimeter-wave perception positioning for the same target; convert the position data of the same target to the same measurement coordinate system, taking the acquisition time point of one of the Bluetooth positioning and the millimeter-wave perception positioning as a reference, perform time synchronization on the acquisition data of the misaligned time point of the other party by means of linear interpolation of the nearest two points; and establish a system error estimation model based on the slant range, azimuth angle, and elevation angle, and obtain the error estimation value between the millimeter-wave perception positioning and the Bluetooth positioning based on the system error estimation model.

15. A computer-readable medium, on which a computer program is stored, wherein when the computer program is executed by a processor, it implements the touchless vehicle entry method according to any one of claims 1 to 7.

16. A computer device, comprising a storage module, a processor, and a computer program stored on the storage module and executable on the processor, wherein when the processor executes the computer program, it implements the touchless vehicle entry method according to any one of claims 1 to 7.

Images