In-vehicle person heart rate monitoring method and system based on radar

Abstract

The invention discloses an in-vehicle person heart rate monitoring method and system based on radar, and belongs to the technical field of vital sign detection.The method comprises the steps that radar echo signals for monitoring vital signs of in-vehicle persons are obtained; according to the obtained radar echo signal, determining phase signals of a range gate where the human body target is located and a range gate nearby the human body target; extracting spatial features of phase signals of a range gate where the human body target is located and a range gate nearby; extracting time sequence features from the extracted spatial features; heartbeat signals of people in the vehicle are obtained according to the time sequence characteristics; according to the heartbeat signal of the person in the vehicle, the heart rate of the person in the vehicle is obtained. And the accuracy of monitoring the heart rate of the person in the vehicle is improved.

Description

Technical Field

[0001] The present application relates to the technical field of vital sign detection, and in particular to a radar-based method and system for monitoring the heart rate of people in a vehicle. Background Art

[0002] When the driver's vital signs are abnormal, it will affect the safety of vehicle driving. Heart rate is an important indicator of vital signs. Accurate monitoring of the driver's heart rate is an important measure to ensure safe vehicle driving.

[0003] In the related technology, there is a method of detecting the vital signs of the driver using radar; this method obtains the radar echo signal, then extracts the heartbeat signal from the radar echo signal; finally, the discrete Fourier transform is used to calculate the frequency of the breathing and heartbeat signals in the frequency domain to detect the vital signs of the driver.

[0004] However, in heart rate detection based on frequency modulated continuous wave radar, the vital sign-related heartbeat signal in the radar echo is very weak and is often submerged in strong clutter. At the same time, the harmonics of the respiratory signal have a great interference on the heartbeat signal. The method of using radar to detect the driver's vital signs in related technologies is difficult to deal with the interference of respiratory harmonics on the heartbeat signal, resulting in limited accuracy in detecting the driver's heart rate. Summary of the invention

[0005] The present application provides a radar-based heart rate monitoring method and system for people in a vehicle, which can solve the problem in the related art that the breathing signal interferes with the heartbeat signal, resulting in inaccurate heartbeat signal detection and ultimately inaccurate heart rate detection.

[0006] To achieve the above object, the present invention adopts the following technical solution:

[0007] On the one hand, a radar-based method for monitoring the heart rate of a person in a vehicle is provided, comprising:

[0008] Obtain radar echo signals for monitoring the vital signs of people in the vehicle;

[0009] According to the acquired radar echo signal, determine the phase signal of the range gate where the human target is located and the range gates nearby;

[0010] Extract the spatial characteristics of the phase signals of the range gate where the human target is located and its nearby range gates;

[0011] Extracting temporal features from the extracted spatial features;

[0012] Obtain the heartbeat signal of the person in the car according to the time series characteristics;

[0013] The heart rate of the occupant is obtained according to the heartbeat signal of the occupant.

[0014] Optionally, performing a range-dimensional fast Fourier transform on the radar echo signal to obtain a frequency-domain signal;

[0015] The frequency domain signal is stored in a two-dimensional matrix R, which includes two dimensions: a slow time dimension and a fast time dimension;

[0016] Calculate the variance of the matrix R along the slow time dimension;

[0017] The maximum value of the variance is determined along the fast time dimension. The maximum value is the range gate where the person is located. The range gates on the left and right sides of the range gate where the person is located are the range gates near the range gate where the person is located.

[0018] Phase extraction and de-wrapping are performed on the frequency domain signals at the range gate where the human target is located and the range gates nearby to obtain the phase signals of the range gate where the human target is located and the range gates nearby.

[0019] Optionally, the I / Q signal of the radar echo signal is compensated and filtered to obtain a compensated filtered signal; and the compensated filtered signal is subjected to a range-dimensional fast Fourier transform to obtain a frequency domain signal.

[0020] Optionally, a convolutional neural network is used to extract spatial features of phase signals of range gates where the human target is located and its nearby range gates; and a bidirectional long short-term memory neural network is used to extract temporal features from the extracted spatial features.

[0021] Optionally, peak values ​​with amplitudes greater than a set heartbeat signal threshold are searched in the time domain of the heartbeat signal, and the average time interval between these peak values ​​is calculated to obtain the heartbeat cycle and heart rate.

[0022] Optionally, it is determined whether the heart rate of the person in the vehicle is abnormal; when the heart rate of the person in the vehicle is abnormal, an alarm message is issued.

[0023] On the other hand, a radar-based in-vehicle heart rate monitoring system is provided, comprising:

[0024] A signal acquisition module is used to acquire radar echo signals for monitoring the vital signs of people in the vehicle;

[0025] A phase signal extraction module is used to determine the phase signals of the range gate where the human target is located and the range gates nearby according to the acquired radar echo signal;

[0026] The heartbeat signal extraction module is used to extract the spatial features of the phase signals of the range gate where the human target is located and the range gates near it; extract the time series features from the extracted spatial features; and obtain the heartbeat signal of the person in the car based on the time series features;

[0027] The heart rate determination module is used to obtain the heart rate of the occupant of the vehicle based on the heartbeat signal of the occupant of the vehicle.

[0028] In another aspect, a computer device is provided, the device comprising:

[0029] a processor adapted to execute a computer program;

[0030] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, a radar-based heart rate monitoring method for occupants in a vehicle proposed in the first aspect is implemented.

[0031] On the other hand, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing a radar-based in-vehicle occupant heart rate monitoring method proposed in the first aspect.

[0032] On the other hand, a computer program product is provided, which includes a computer program. When the computer program is executed by a processor, the radar-based heart rate monitoring method for a person in a vehicle proposed in the first aspect is implemented.

[0033] The technical solution provided by this application can at least bring the following beneficial effects:

[0034] The present application provides a radar-based heart rate monitoring method and system for people in a vehicle. The method determines the phase signals of the range gate where the human target is located and its nearby range gates according to the radar echo signal, and uses the phase signals of multiple range gates to extract the heartbeat signal, thereby improving the accuracy of the heartbeat signal extraction. On the basis of accurately obtaining the heartbeat signal, accurate monitoring of the heart rate of people in the vehicle is achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0036] Figure 1 is a flow chart of a radar-based in-vehicle heart rate monitoring method provided in an embodiment of the present application;

[0037] Figure 2 is a schematic diagram of phase signal extraction provided in an embodiment of the present application;

[0038] Figure 3 is a phase signal extraction flow chart provided in an embodiment of the present application;

[0039] Figure 4A schematic diagram of the structure of the vital sign information extraction model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0040] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the implementation methods of the present application will be further described in detail below in conjunction with the accompanying drawings.

[0041] Before explaining in detail the vital sign signal monitoring method provided in the embodiment of the present application, the application scenario provided in the embodiment of the present application is first introduced.

[0042] The radar-based in-vehicle heart rate monitoring method provided in the embodiment of the present application can be applied to a variety of scenarios. For example, in a vehicle driving scenario, if the driver's heart rate is abnormal, it will affect the safety of vehicle driving. At this time, the driver's heart rate can be monitored by the radar installed in the vehicle according to the radar-based in-vehicle heart rate monitoring method provided in the embodiment of the present application. When the driver's heart rate is abnormal, an alarm message is generated to remind the driver to avoid possible risks in advance.

[0043] The radar-based heart rate monitoring method for a person in a vehicle provided in an embodiment of the present application can be performed by a vehicle. Furthermore, the radar-based heart rate monitoring method for a person in a vehicle provided in an embodiment of the present application can also be implemented by a vital sign signal monitoring device, which will be described later using a vehicle as an example.

[0044] Among them, the vital sign signal monitoring device can be any electronic product that can interact with the user through one or more methods such as keyboard, touchpad, touch screen, remote control, voice interaction or handwriting device, such as PC (Personal Computer), mobile phone, smart phone, PDA (Personal Digital Assistant), PPC (Pocket PC), tablet computer, smart car machine, smart TV, smart speaker, etc.

[0045] Those skilled in the art should understand that the above-mentioned application scenarios and vital sign signal monitoring devices are only examples, and other existing or future application scenarios and vital sign signal monitoring devices, if applicable to the embodiments of the present application, should also be included in the protection scope of the embodiments of the present application and are included here by reference.

[0046] It should be noted that the business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0047] Next, a radar-based heart rate monitoring method for occupants in a vehicle provided in an embodiment of the present application is explained in detail. Figure 1 This is a flow chart of a radar-based in-vehicle heart rate monitoring method provided in an embodiment of the present application. Please refer to Figure 1 , the method comprises the following steps.

[0048] Step 101: Acquire a radar echo signal for monitoring the vital signs of a person in the vehicle.

[0049] The embodiment of the present application uses a radar in a vehicle to transmit a frequency modulated continuous wave (FMCW) radar signal to the occupants of the vehicle to monitor their vital signs. The transmitted radar signal generates backscattering after encountering the human body, and is then received by an antenna to form a radar echo signal.

[0050] The frequency modulated continuous wave radar signal is the most common linear frequency modulated continuous wave signal, that is, the transmitted radar signal x T (t) The frequency changes linearly with time and can be expressed as:

[0051]

[0052] Among them, A T is the transmitted signal amplitude, f c is the center frequency, B is the radar signal bandwidth, Tc is the radar signal duration, is the phase noise of the transmitter. Radar echo signal x R (t) is the delayed signal after the transmitted signal is reflected by the human body, expressed as:

[0053]

[0054] Where, AR is the amplitude of the received radar echo signal, t d is the radar echo time delay associated with the detected target, which can be expressed as:

[0055]

[0056] Among them, R0 is the distance from the radar to the center of the chest of the person in the car, R(t) is the distance change caused by the movement of the human chest, and c is the speed of light. The phase of the intermediate frequency signal is the difference between the transmitted signal and the received signal, which can be expressed as:

[0057]

[0058] In practice, td is very small, π, B, T c , t, and 2d can be ignored. At the same time, when using FMCW radar to measure objects at short distances, the residual phase noise It can also be ignored, so the simplified intermediate frequency signal phase expression is:

[0059]

[0060] Among them, f IF =2B(R0+R(t)) / cT c , f IF and They all contain information about the chest displacement R(t) of the chest cavity, but since the chest displacement caused by breathing and heartbeat is very small, it is actually difficult to pass the detection. IF To obtain the displacement of the chest cavity, It is sensitive to changes in chest displacement, so it is necessary to detect the intermediate frequency signal The changes in the chest displacement are used to obtain the changing rules, and thus the changing characteristics of human breathing and heartbeat are obtained.

[0061] Step 102: Determine the phase signals of the range gate where the human target is located and the range gates nearby according to the acquired radar echo signal.

[0062] The human target refers to the chest reflection point of a person; phase signal extraction is analyzed from the principle of frequency modulated continuous wave radar detection. It can be seen that breathing and heartbeat will cause the chest to move. By detecting the displacement of the chest, information related to breathing and heartbeat can be obtained. The phase of the intermediate frequency signal is linearly related to the displacement of the chest. Therefore, the detection of vital signs requires the extraction of the phase signal of the chest reflection point of the person. The principle diagram of extracting the phase signal is shown in the figure. Figure 2 As shown,

[0063] Perform range-dimensional fast Fourier transform (FFT) on the radar echo signal to obtain a frequency-domain signal;

[0064] The frequency domain signal is stored in a two-dimensional matrix R, which includes two dimensions: a slow time dimension and a fast time dimension;

[0065] Calculate the variance of the matrix R along the slow time dimension;

[0066] The maximum value of the variance is determined along the fast time dimension. The maximum value is the range gate corresponding to the human target. The range gates on the left and right sides of the range gate where the human target is located are the range gates near the range gate where the human target is located.

[0067] Phase extraction and de-wrapping are performed on the frequency domain signals at the range gate where the human target is located and the range gates nearby to obtain the phase signals of the range gate where the human target is located and the range gates nearby.

[0068] Preferably, the I / Q signal of the radar echo signal is compensated and filtered to obtain a compensated filtered signal; and the compensated filtered signal is subjected to a range-dimensional fast Fourier transform to obtain a frequency domain signal.

[0069] The embodiment of the present application forms a two-dimensional matrix R of the frequency domain signal along the slow time dimension, and processes the frequency domain signal in an observation window of size N to determine the human target position, and finally extracts the phase signal at the target position.

[0070] The flow chart of phase signal extraction is as follows: Figure 3 As shown in the figure, due to the incomplete matching of the characteristics of the devices of the radar I / Q channels, phase offset and amplitude error are generated in the I / Q channels, resulting in unequal amplitudes and incomplete orthogonal phases of the I / Q intermediate frequency signals. Therefore, it is necessary to compensate the two signals, and the algorithm in the literature is used to compensate the I / Q signals. In addition, in the actual radar data, not only the chest motion-related signals of the target are included, but also the static clutter related to the target's surrounding environment. These clutters will not only affect the positioning of the target, but also introduce phase noise. Therefore, these clutters need to be removed.

[0071] Therefore, the embodiment of the present application compensates and filters the I / Q signal of the radar echo signal to obtain a compensated filtered signal; and performs a distance-dimensional fast Fourier transform on the compensated filtered signal to obtain a frequency domain signal.

[0072] Preferably, the method of phase mean cancellation is used to eliminate static clutter, and the implementation formula is:

[0073]

[0074] R[m,n]=R[m,n]-C[m]

[0075] Among them, R is a matrix composed of N distance dimension frequency domain data (FFT data), m is the fast time dimension sampling point, and n is the slow time dimension sampling point.

[0076] Since heartbeat and breathing can cause tiny fluctuations in the phase intermediate frequency signal, the variance of the matrix R can be calculated along the slow time dimension, and then the maximum variance can be calculated in the fast time dimension. The maximum value is the range gate corresponding to the human target.

[0077] Compared with the AT demodulation algorithm that directly calculates the inverse tangent, the DACM demodulation algorithm can avoid the occurrence of DC bias and orthogonal imbalance to a certain extent. Therefore, the embodiment of the present application uses the DACM demodulation algorithm to perform phase extraction and unwrapping on the FFT data of the distance at the range gate where the target is located.

[0078] Assuming that the signal of the range gate where the target is located is R(t)=I(t)+jQ(t), the derivative of the phase signal is:

[0079]

[0080] Among them, I(t)′ and Q(t)′ are the derivatives of I(t) and Q(t), respectively. I(t) and Q(t) are the echo data I / Q signals when the sampling point is t.

[0081] Further discretizing the above formula and summing it up, the discrete phase signal expression can be obtained as follows:

[0082]

[0083] Step 103: Extract the spatial features of the phase signals of the range gate where the human target is located and its nearby range gates; extract the timing features from the extracted spatial features; and obtain the heartbeat signal of the person in the car based on the timing features.

[0084] The embodiment of the present application uses a convolutional neural network to extract the spatial features of the phase signals of the range gate where the human target is located and its nearby range gates; and uses a bidirectional long short-term memory neural network to extract temporal features from the extracted spatial features.

[0085] The phase signal contains information related to the target person's breathing and heartbeat. After the phase signal is obtained, the breathing signal and heartbeat signal can be extracted from the phase signal. The embodiment of the present application uses a trained life feature extraction model to extract the breathing signal and heartbeat signal of the person in the car; the life feature extraction model is constructed using a convolutional bidirectional long short-term memory neural network (CNN-BiLSTM).

[0086] In order to make full use of the information in the radar echo and improve the detection accuracy, unlike the previous use of data from only one range gate for vital sign detection, the embodiment of the present application uses the distance FFT data of the range gate where the target is located and the range gates near it for the extraction of respiratory signals and heartbeat signals, that is, extracts the phase signal from the range gate where the target is located and the range gates near it as the input of the neural network. Since in the distance dimension FFT data matrix, the human target will occupy multiple adjacent range gates, and these range gates all contain information related to vital signs. Therefore, using the phase signals of multiple range gates as the input of the neural network can improve the extraction accuracy of respiratory signals and heartbeat signals. In addition, due to the random movement of the human body and clutter interference, the range gate of the actual target will fluctuate near the detected range gate. Traditional algorithms that only use a single range gate find it difficult to solve this problem. Using multiple range gates can reduce the impact of random movement of the human body and clutter interference and increase the stability of the algorithm. The structure of the convolutional bidirectional long short-term memory neural network is as follows Figure 4 As shown in the figure, the network consists of a one-dimensional convolutional neural network (CNN), a bidirectional long short-term memory neural network (BiLSTM) and two multi-layer fully connected networks. The one-dimensional convolutional neural network includes three layers of convolution and three layers of transposed convolution. The phase signals of the range gate where the human target is located and the range gates nearby are normalized, and the normalized phase signals are input into the one-dimensional convolutional neural network. After three layers of convolution and three layers of transposed convolution, the spatial features of the phase signals of the range gate where the human target is located and the range gates nearby are obtained; the spatial features output by the one-dimensional convolutional neural network are input into the bidirectional long short-term memory network, and the temporal features of the spatial features are extracted through the bidirectional long short-term memory network; then, the temporal features are respectively generated into breathing signals and heartbeat signals through two multi-layer fully connected networks.

[0087] The bidirectional long short-term memory network uses bidirectional overlapping calculation to make up for the shortcoming of the long short-term memory network that cannot extract information from the back and forward at the same time, and can better capture the bidirectional time series features. However, the bidirectional long short-term memory neural network has poor applicability in expressing the spatial dimension characteristics of the data, and it is difficult to fully extract the spatial position characteristics of the data. Therefore, a hybrid structure of a one-dimensional convolutional neural network and a bidirectional long short-term memory neural network is used to extract features related to breathing and heartbeat. Combining the advantages of convolutional neural networks in spatial feature extraction with the advantages of bidirectional long short-term memory units in temporal feature extraction, the feature information in both space and time is fully utilized to enhance the data mining ability of the model and achieve accurate extraction of breathing signals and heartbeat signals. In addition, the one-dimensional convolutional neural network part adopts a serial structure of convolution plus transposed convolution. In the convolution part, a large step size is used to reduce the size of the output feature map and increase the receptive field, and then multi-layer transposed convolution is used to complete upsampling. Through this structure, the spatial feature extraction process can be optimized and the model performance can be improved.

[0088] The embodiment of the present application utilizes the phase signals of the marked heartbeat signal and the respiratory signal to train the constructed life feature extraction model, and after the training is completed, a trained life feature extraction model is obtained.

[0089] Step 104: Obtain the heart rate of the occupant according to the heartbeat signal of the occupant.

[0090] After acquiring the heartbeat signal of the person in the car, the embodiment of the present application searches for peaks with amplitudes greater than a set heartbeat signal threshold in the time domain of the heartbeat signal, and calculates the average time interval of these peaks to obtain the heartbeat cycle and heart rate.

[0091] Since the embodiment of the present application obtains the breathing signal at the same time as the heartbeat signal, when determining the heartbeat cycle and heart rate, it also searches for peaks with amplitudes greater than the set breathing signal threshold in the time domain of the breathing signal, and calculates the average time interval of these peaks to obtain the breathing cycle and breathing frequency.

[0092] In actual detection, there may be serious interference in the radar echo signal, which makes the neural network unable to effectively extract the breathing and heartbeat signals from the phase signal. At this time, the amplitude of the neural network output signal is usually small. In order to reduce the impact of interference on the estimation of vital sign parameters, the threshold is used to filter the peak value. This processing can improve the accuracy of vital sign parameter estimation.

[0093] After acquiring the heart rate of the person in the car, the embodiment of the present application also determines whether the heart rate of the person in the car is abnormal; when the heart rate of the person in the car is abnormal, an alarm message is issued.

[0094] Preferably, the host voice assistant and IHU are combined to continuously monitor the heart rate status of the people in the car. When the heart rate of the people in the car exceeds the set heart rate threshold, it is determined that the heart rate of the people in the car is abnormal, and an alarm message is issued through voice and IHU to prompt the heart rate health status.

[0095] Among them, the heartbeat signal threshold, breathing signal threshold and heart rate threshold are all pre-set and can be adjusted according to different needs.

[0096] In the vehicle driving scenario, when the heart rate of the occupants is abnormal, an alarm message is generated to remind the occupants. In this way, the occupants can take relevant measures in time to maintain their personal safety. Moreover, after the alarm message continues for a preset period of time, the central gateway can also control the vehicle braking based on the alarm message to further maintain the personal safety of the occupants.

[0097] For another example, when the vehicle is not in a driving state and the heartbeat signal or the breathing signal is not zero, the temperature inside the vehicle and / or the vehicle unlocking information is obtained, and when the temperature inside the vehicle is not within the target temperature range or the vehicle unlocking information indicates illegal unlocking, an alarm message is generated. That is, if the vehicle is not in a driving state and the heartbeat signal or the breathing signal is not zero, it indicates that there are people left behind in the vehicle, or outsiders have broken into the vehicle. At this time, when the temperature inside the vehicle is not within the target temperature range, an alarm message is generated to remind the driver that the current temperature inside the vehicle is high and there are people left behind in the vehicle. When the vehicle unlocking information indicates illegal unlocking, an alarm message is generated to remind the driver that there are outsiders who have illegally unlocked and broken into the vehicle.

[0098] The target temperature range is set in advance and can be adjusted according to different requirements.

[0099] When the heartbeat signal or breathing signal of the person in the car is not zero in the vehicle non-driving scenario, an alarm message is generated to prompt the driver. In this way, the driver can avoid leaving children or the elderly in the car with high temperature, and can also avoid problems such as property theft caused by outsiders breaking into the car.

[0100] Next, a complete description of a radar-based heart rate monitoring process for people in a vehicle provided in an embodiment of the present application is provided. The radar echo signal received by the radar installed in the vehicle is subjected to a fast Fourier transform, and the phase signal of the range gate where the human target is located and the range gates nearby are determined; then, the spatial features of the phase signal of the range gate where the human target is located and the range gates nearby are extracted; the timing features are extracted from the extracted spatial features; the heartbeat signal of the people in the vehicle is obtained according to the timing features, and then the heart rate of the people in the vehicle is obtained. Because the phase signal of the range gate where the human target is located and the range gates nearby are comprehensively considered when extracting the heartbeat signal, and the spatial features and timing features of the phase signal are fully utilized, the accuracy of the heartbeat signal extraction is improved, thereby ensuring the accuracy of heart rate monitoring.

[0101] The embodiment of the present application provides a radar-based in-vehicle heart rate monitoring system, comprising:

[0102] A signal acquisition module is used to acquire radar echo signals for monitoring the vital signs of people in the vehicle;

[0103] A phase signal extraction module is used to determine the phase signals of the range gate where the human target is located and the range gates nearby according to the acquired radar echo signal;

[0104] The heartbeat signal extraction module is used to extract the spatial features of the phase signals of the range gate where the human target is located and the range gates near it; extract the time series features from the extracted spatial features; and obtain the heartbeat signal of the person in the car based on the time series features;

[0105] The heart rate determination module is used to obtain the heart rate of the occupant of the vehicle based on the heartbeat signal of the occupant of the vehicle.

[0106] It should be noted that: the above embodiment provides a radar-based in-vehicle heart rate monitoring system, when performing in-vehicle heart rate monitoring, only uses the division of the above-mentioned functional modules as an example. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the system is divided into different functional modules to complete all or part of the functions described above. In addition, the above embodiment provides a radar-based in-vehicle heart rate monitoring system and a radar-based in-vehicle heart rate monitoring method embodiment, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.

[0107] An embodiment of the present application provides a computer device, the device comprising:

[0108] a processor adapted to execute a computer program;

[0109] A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, a radar-based heart rate monitoring method for a person in a vehicle disclosed in Example 1 is implemented.

[0110] An embodiment of the present application provides a computer-readable storage medium, which stores a computer program. The computer program is suitable for being loaded by a processor and executing a radar-based in-vehicle heart rate monitoring method disclosed in Example 1.

[0111] A computer program product provided in an embodiment of the present application includes a computer program. When the computer program is executed by a processor, a radar-based method for monitoring the heart rate of a person in a vehicle disclosed in Embodiment 1 is implemented.

[0112] The method provided in the application embodiment can be directly embodied as a hardware processor, or can be executed by a combination of hardware and software modules in the processor. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware. To avoid repetition, it will not be described in detail here.

[0113] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with this embodiment can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0114] Although the above describes the specific implementation mode of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without creative work are still within the scope of protection of the present invention.

Claims

1. A radar-based method for monitoring the heart rate of people in a vehicle, characterized in that: include: Obtain radar echo signals for monitoring the vital signs of people in the vehicle; According to the acquired radar echo signal, determine the phase signal of the range gate where the human target is located and the range gates nearby; Extract the spatial characteristics of the phase signals of the range gate where the human target is located and its nearby range gates; Extracting temporal features from the extracted spatial features; Obtain the heartbeat signal of the person in the car according to the time series characteristics; The heart rate of the occupant is obtained according to the heartbeat signal of the occupant.

2. The radar-based heart rate monitoring method for a person in a vehicle as claimed in claim 1, characterized in that: Perform range-dimensional fast Fourier transform on the radar echo signal to obtain a frequency-domain signal; The frequency domain signal is stored in a two-dimensional matrix R, which includes two dimensions: a slow time dimension and a fast time dimension; Calculate the variance of the matrix R along the slow time dimension; The maximum value of the variance is determined along the fast time dimension. The maximum value is the range gate where the person is located. The range gates on the left and right sides of the range gate where the person is located are the range gates near the range gate where the person is located. Phase extraction and de-wrapping are performed on the frequency domain signals at the range gate where the human target is located and the range gates nearby to obtain the phase signals of the range gate where the human target is located and the range gates nearby.

3. A radar-based heart rate monitoring method for a person in a vehicle as claimed in claim 2, characterized in that: The I / Q signal of the radar echo signal is compensated and filtered to obtain a compensated filtered signal; the compensated filtered signal is subjected to a distance-dimensional fast Fourier transform to obtain a frequency-domain signal.

4. The radar-based heart rate monitoring method for a person in a vehicle as claimed in claim 1, characterized in that: A convolutional neural network is used to extract the spatial features of the phase signals of the range gate where the human target is located and its nearby range gates. A bidirectional long short-term memory neural network is used to extract the temporal features from the extracted spatial features.

5. The radar-based heart rate monitoring method for a person in a vehicle as claimed in claim 1, characterized in that: In the time domain of the heartbeat signal, the peak values ​​with amplitudes greater than the set heartbeat signal threshold are searched, and the average time interval of these peak values ​​is calculated to obtain the heartbeat cycle and heart rate.

6. The radar-based heart rate monitoring method for a person in a vehicle as claimed in claim 1, characterized in that: Determine whether the heart rate of the people in the car is abnormal; when the heart rate of the people in the car is abnormal, an alarm message is issued.

7. A radar-based in-vehicle heart rate monitoring system, characterized in that: include: A signal acquisition module is used to acquire radar echo signals for monitoring the vital signs of people in the vehicle; A phase signal extraction module is used to determine the phase signals of the range gate where the human target is located and the range gates nearby according to the acquired radar echo signal; The heartbeat signal extraction module is used to extract the spatial features of the phase signals of the range gate where the human target is located and the range gates nearby; and extract the time series features from the extracted spatial features; Obtain the heartbeat signal of the person in the car according to the time series characteristics; The heart rate determination module is used to obtain the heart rate of the occupant of the vehicle based on the heartbeat signal of the occupant of the vehicle.

8. An electronic device, characterized in that: The device comprises: a processor adapted to execute a computer program; A computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium, and when the computer program is executed by the processor, the radar-based heart rate monitoring method for occupants in a vehicle as described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing a radar-based in-vehicle occupant heart rate monitoring method as described in any one of claims 1-6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, it implements the radar-based heart rate monitoring method for occupants in a vehicle as described in any one of claims 1 to 6.

Images