Driver health monitoring and early warning method and system

Abstract

The invention discloses a driver health monitoring and early warning method and system, and belongs to the technical field of automobile intelligent cabins, and the method comprises the steps: calling camera data in a DMS in an intelligent cabin, positioning the chest of a driver, and obtaining three-dimensional coordinates of the chest part of the driver in a driving cabin space; adjusting a millimeter wave radar integrated in a steering wheel to send a radar signal by combining the three-dimensional coordinates positioned to the chest part; receiving an echo signal of the radar signal interfered by the fluctuating cavity motion of the thoracic cavity part; carrying out real-time extraction on a respiration signal and a heartbeat signal based on the echo signal to obtain a vital sign signal; performing feature extraction on the vital sign signals to obtain vital sign parameters; analyzing the vital sign parameters; and when the vital sign parameter exceeds a threshold value, sending an exception handling request. According to the method, cardiopulmonary data of a driver are analyzed, and occurrence of sudden cardiopulmonary diseases such as inhibitory respiration and heartbeat pause is judged in advance.

Description

Technical Field

[0001] The present invention belongs to the technical field of automobile intelligent cockpits, and in particular relates to a driver health monitoring and early warning method and system. Background Art

[0002] With the increasing positioning of smart cockpits in modern automotive products and the rapid development of automotive chip computing power, conventional monitoring of driver fatigue, distraction and dangerous driving can no longer meet people's needs. Current technical solutions also lack effective monitoring of the driver's key vital signs and cannot assess the driver's physical condition in real time. Therefore, they cannot avoid the risk of safety hazards to the driver and other traffic participants due to sudden apnea and heart disease. Summary of the invention

[0003] The present invention aims to solve the problem of monitoring the key vital signs of a driver and provide a driver health monitoring and early warning method and system. The method analyzes the driver's cardiopulmonary data and determines in advance the occurrence of critical abnormal conditions such as sudden cardiopulmonary diseases, such as inhibited breathing and cardiac arrest.

[0004] In order to solve the above technical problems, the technical solution adopted by the present invention is: In a first aspect, the present invention provides a driver health monitoring and early warning method, comprising: Call the camera data in the DMS in the smart cockpit to locate the driver's chest and obtain the three-dimensional coordinates of the driver's chest in the cockpit space; Combined with the three-dimensional coordinates of the chest cavity, the millimeter-wave radar integrated in the steering wheel is adjusted to send radar signals; the echo signal of the radar signal after interference from the chest cavity movement is received; Extracting a respiratory signal and a heartbeat signal in real time based on the echo signal to obtain a vital sign signal; Extract features of vital sign signals to obtain vital sign parameters; Analyze the vital sign parameters; when the vital sign parameters exceed a threshold, send an exception handling request.

[0005] As a further improvement of the present invention, the method of calling the camera data in the DMS in the smart cockpit to locate the driver's chest cavity and obtain the three-dimensional coordinates of the driver's chest in the cockpit space includes: The camera function in the smart cockpit is called to determine the vertical position of the driver's chest. Combined with the specific situation of the driver's seat adjustment, the driver's plane position is determined to obtain the three-dimensional coordinates of the driver's chest in the cockpit space.

[0006] As a further improvement of the present invention, the method of adjusting the radar signal sent by the millimeter-wave radar integrated in the steering wheel in combination with the three-dimensional coordinates located at the chest cavity part includes: Combined with the three-dimensional coordinates of the driver's chest in the cockpit space, the gimbal base and transmission power of the millimeter-wave radar integrated in the steering wheel are adjusted to adjust the direction and signal strength of radar signal detection, so that the cross-section of the radar's effective detection area covers the driver's chest position, so as to perform adaptive adjustment of the radar position; After adaptive adjustment, the radar signal is sent to the driver's chest.

[0007] As a further improvement of the present invention, the receiving of the echo signal of the radar signal after the interference of the chest cavity movement includes: After sending a radar signal to the driver's chest, an echo signal of the radar signal after interference from chest cavity movement is received; Verify the echo quality of the radar signal after the interference of the chest cavity movement. When the quality meets the requirements, judge the quality of the detection signal after the radar positioning adjustment to obtain the echo signal whose detection signal quality meets the requirements.

[0008] As a further improvement of the present invention, the real-time extraction of the respiratory signal and the heartbeat signal based on the echo signal to obtain the vital sign signal includes: Performing noise reduction processing on the echo signal; The echo signal after noise reduction is subjected to vital sign signal optimization processing, which includes noise elimination, movement compensation strategy processing to eliminate random body motion, heartbeat signal enhancement algorithm to enhance heartbeat signal, respiratory harmonic reduction algorithm to reduce respiratory harmonics, and vital sign signal real-time extraction algorithm to separate respiratory heartbeat to obtain vital sign signal.

[0009] As a further improvement of the present invention, the feature extraction of the vital sign signal to obtain the vital sign parameter is to calculate the vital sign signal through the real-time vital sign signal extraction algorithm to obtain the vital sign signal; The real-time vital sign signal extraction algorithm is based on the real-time vital sign signal extraction algorithm of PKISS-EWT, and includes: Input vital sign signals; Performing prior knowledge calculation on the vital sign signal and preprocessing the signal using known physiological and medical knowledge; Use normalized Fourier transform to convert the original time domain signal into a frequency domain signal to obtain the spectrum peak; The spectrum is divided into different intervals using improved spectrum segmentation, each interval corresponds to a specific frequency component; Wavelet transform is applied to each frequency band of the signal, outputting extracted vital sign information including respiratory rate and heart rate.

[0010] As a further improvement of the present invention, the analyzing of the vital sign parameters; when the vital sign parameters exceed a threshold, sending an exception handling request comprises: Situation 1: Fatigue driving. At this time, the driver's breathing rate and heart rate exceed the fatigue driving threshold, and a warning is issued to the driver; Case 2: Dangerous driving. At this time, the driver's breathing rate and heart rate are beyond the dangerous driving threshold, and an emergency call is automatically made, and the autonomous driving system intervenes.

[0011] In a second aspect, the present invention provides a driver health monitoring and early warning system, comprising: An acquisition module, used to acquire a user's instruction to start a simulation scenario and display a simulation scenario type generated based on a scenario model preset by the vehicle system; A scenario generation module is used to construct a simulation scenario and set roles based on the simulation scenario type and roles selected by the user, and to generate a virtual dialogue scenario; The voice synthesis module is used to analyze the user's voice characteristics and emotional state in the virtual dialogue scene based on the user's language and expression content, and dynamically adjust the simulation situation construction and role setting; according to the voice characteristics and emotional state, select the appropriate voice synthesis role from the on-board voice database to represent the voice of the other party's role; The speech and logic generation module is used to generate the speech and logic of the other party's role based on the user's language and expression content using a large language model; The situation simulation module is used to provide instant situation simulation feedback of the other role based on the synthesized role and the generated words and logic of the other role, combined with real-time analysis of the user's voice characteristics and emotional state.

[0012] In a third aspect, the present invention provides an electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the driver health monitoring and early warning method when executing the computer program.

[0013] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the driver health monitoring and early warning method is implemented.

[0014] In a fifth aspect, the present invention provides a computer program product, which includes computer instructions, and is characterized in that the computer instructions instruct a computer to execute the driver health monitoring and early warning method.

[0015] The beneficial effects of the present invention compared with the prior art are as follows: The present invention integrates an optical camera and combines it with the position information of the main driver's seat in the cockpit for comprehensive three-dimensional positioning, so that the effective detection position of the millimeter-wave radar can be accurately radiated to the driver's chest cavity; the millimeter-wave radar is integrated into the steering wheel to avoid excessive influence on the driver's driving activities, and the driver's health detection can be achieved contactlessly at a relatively low cost without affecting the aesthetics of the cockpit; the driver's cardiopulmonary data is analyzed to judge in advance the occurrence of critical abnormal conditions such as sudden cardiopulmonary diseases, such as inhibited breathing and cardiac arrest, so as to issue early warnings and link the intelligent driving system to take measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the embodiments of the present invention or the drawings of related technical solutions in the prior art are introduced below. It should be understood that the drawings introduced below are only for the convenience of clearly describing some embodiments of the technical solutions of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0017] Figure 1 This is a flowchart of the driver health monitoring and early warning method in an embodiment of the present application; Figure 2 This is a flow chart of the continuous wave radar vital sign signal optimization method in an embodiment of the present application; Figure 3 This is a time domain effect comparison diagram of the heartbeat enhancement algorithm in the embodiment of this application; Figure 4 This is a comparison diagram of the frequency domain effect of the heartbeat enhancement algorithm in the embodiment of this application; Figure 5 This is a spectrum comparison diagram of the signal before and after the notch in the embodiment of the present application; Figure 6 This is a flow chart of the real-time vital sign signal extraction algorithm in the embodiment of the present application; Figure 7 The heartbeat signal extracted in the embodiment of the present application is compared with the standard heartbeat signal of the sensor; Figure 8 The respiratory signal extracted in the embodiment of the present application is compared with the standard respiratory signal of the sensor; Fig. 9 A driver health monitoring and early warning system provided by the present invention; Fig.10 A schematic diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0018] The embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and are not to be construed as limitations of the present invention. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.

[0019] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific content of the technical solution.

[0020] The system is used to simulate and analyze emotional processing and expression training in complex interpersonal scenarios such as disputes, interviews, and debates. The system combines natural language processing (NLP), sentiment analysis, and speech recognition technologies to help users improve their expression and emotional management abilities in real interpersonal conflicts, interviews, debates, and other situations through in-car situation simulations.

[0021] The present invention provides a driver health monitoring and early warning method, such as Figure 1 As shown, including: S101, calling the camera data in the DMS in the smart cockpit to locate the driver's chest and obtain the three-dimensional coordinates of the driver's chest in the cockpit space; S102, combining the three-dimensional coordinates of the chest cavity portion, adjusting the millimeter wave radar integrated in the steering wheel to send a radar signal; receiving an echo signal of the radar signal after interference with the chest cavity motion; S103, extracting a respiratory signal and a heartbeat signal in real time based on the echo signal to obtain a vital sign signal; S104, extracting features from vital sign signals to obtain vital sign parameters; S105, analyzing the vital sign parameters; when the vital sign parameters exceed a threshold, sending an exception handling request.

[0022] The present invention acquires camera data and locates the chest cavity. The DMS (Driver Monitoring System) in the smart cockpit: The DMS system is usually integrated inside the vehicle to monitor the driver's status, such as fatigue, distraction, etc. It usually includes sensors such as cameras to capture images of the driver's face and upper body.

[0023] Furthermore, chest positioning is to locate the driver's chest through the image captured by the camera using computer vision technology (such as deep learning algorithms). This usually involves steps such as image preprocessing, feature extraction, and bounding box detection to determine the position of the chest in the image. The three-dimensional coordinate calculation combines the position, angle, and field of view of the camera, as well as the position of the chest in the image, and uses stereo vision or depth estimation technology to calculate the three-dimensional coordinates of the chest in the cockpit space.

[0024] Furthermore, the millimeter-wave radar signal is adjusted and received. The millimeter-wave radar has the characteristics of strong penetration and good anti-interference ability, and is suitable for monitoring the vital signs of the driver. It can detect the position and speed of an object by sending and receiving radar signals. According to the three-dimensional coordinates of the chest cavity, the emission direction of the millimeter-wave radar is adjusted so that it can accurately illuminate the driver's chest cavity. After the radar signal is irradiated to the chest cavity, it will be interfered by the chest cavity ups and downs (such as breathing and heartbeat) to form an echo signal. These echo signals are received and recorded by the radar.

[0025] As an example, the vital sign signal extraction and analysis process uses signal processing technology (such as filtering, Fourier transform, etc.) to process the echo signal and extract the respiratory signal and heartbeat signal. The extracted vital sign signal is subjected to feature extraction, such as respiratory frequency, heart rate, etc., to obtain the vital sign parameters.

[0026] Furthermore, abnormal analysis compares vital sign parameters with preset thresholds to determine whether there are abnormalities. For example, breathing rate is too fast or too slow, heart rate is too high or too low, etc. When vital sign parameters exceed the threshold, the system sends an abnormal processing request. This may include sounding an alarm, displaying a warning message to the driver, or even automatically taking measures (such as slowing down, stopping, etc.) to ensure the safety of the driver and the vehicle.

[0027] The present invention can monitor the driver's vital signs in real time and detect abnormal conditions in time through the combination of DMS and millimeter-wave radar. This monitoring method does not require direct contact with the driver, avoiding the discomfort and interference that may be caused by traditional monitoring methods. Using advanced computer vision and signal processing technology, high-precision vital sign monitoring and abnormality detection can be achieved. By real-time monitoring and analysis of the driver's vital signs, timely measures can be taken before the driver has health problems to improve driving safety. The entire monitoring process is automatically completed by the intelligent system without manual intervention, which improves the intelligence level of the system. Therefore, the use of DMS and millimeter-wave radar in the smart cockpit to monitor the driver's vital signs has the advantages of real-time monitoring, non-contact, high precision, safety and intelligence. This monitoring method helps to detect the driver's health problems in time, improve driving safety, and provide a new technical path for the development of intelligent driving.

[0028] The present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0029] The present invention provides a driver cardiopulmonary health monitoring algorithm that integrates a camera and a millimeter-wave radar. By calling the camera function in the cockpit and combining the position of the driver's seat, the wireless signal of the millimeter-wave radar is accurately positioned to the driver's chest. The respiratory signal and heartbeat signal are extracted by detecting the rise and fall of the human chest, and vital sign parameters such as respiratory rate, heart rate, and heart rate variability are extracted. After analyzing the data, reminders are issued and emergency measures are taken.

[0030] The driver health monitoring and early warning method steps mainly include: Chest positioning: The camera function in the DMS (fatigue monitoring system) in the smart cockpit is called to determine the vertical position of the driver's chest. Combined with the specific situation of the driver's seat adjustment, the driver's plane position is determined. The two methods are combined to output the three-dimensional coordinates of the driver's chest in the cockpit space to guide the next millimeter-wave radar detection direction; Radar adjustment: Combined with the three-dimensional coordinates of the chest cavity, the direction and signal strength of radar signal detection are adjusted by adjusting the pan-tilt base and transmission power of the millimeter-wave radar integrated in the steering wheel; Signal verification: Verify the echo quality of the radar signal after the interference of the chest cavity movement, and judge the quality of the detection signal after the radar positioning adjustment, including the intensity of clutter noise, random body movement and arm occlusion.

[0031] Vital sign extraction: Real-time extraction of respiratory and heartbeat signals is completed through a series of related algorithms, including: elimination of random body motion, noise elimination, heartbeat signal enhancement, respiratory harmonic reduction, and respiratory and heartbeat separation; Analysis and prediction: Extract features from vital signs signals extracted in real time, including respiratory rate, heart rate, respiratory rhythm changes, heart rate variability, etc. Analyze the extracted vital sign parameters and predict possible abnormal situations so that timely measures can be taken; Abnormal alarm: Based on the analysis of vital sign parameters, the occurrence of serious conditions such as suppressed breathing and cardiac arrest is predicted, an alarm is issued for the abnormality, emergency contacts and emergency numbers are contacted, and the intelligent driving system is linked, such as turning on the double flash, longitudinal deceleration, and lateral speed pulling over.

[0032] When the radar base receives the comprehensive positioning coordinates of the camera and the driver's seat, it controls the gimbal to adjust the position and the power of the transmitting antenna so that the cross-section of the radar's effective detection area covers the driver's chest position as much as possible, completing the adaptive adjustment of the radar position.

[0033] As a specific embodiment, the real-time extraction method of vital sign signals includes three parts: data preprocessing, signal optimization and signal extraction, specifically including: 1) Noise reduction algorithm.

[0034] 2) If Figure 2 As shown, the radar signal emitted by the continuous wave radar system is processed by filter selection and signal noise reduction, and then the filter order is adjusted and the time shift compensation strategy is performed to obtain the respiratory frequency estimation value and the filtered signal. The filtered signal is processed by the heartbeat signal enhancement algorithm to obtain the enhanced signal. The enhanced signal and the respiratory frequency estimation value are processed by the respiratory harmonic reduction algorithm together to obtain the optimized signal. The optimized signal is subjected to the real-time vital sign signal extraction algorithm to obtain the vital sign signal optimization signal. The specific steps are as follows: like Figure 2 As shown in the figure, the process of using the continuous wave radar system for real-time extraction of vital sign signals includes the steps of radar signal acquisition, filter selection and time shift compensation, signal noise reduction, respiratory frequency estimation, filter signal enhancement, respiratory harmonic reduction, heartbeat signal enhancement, etc.

[0035] Radar signal: The radar system emits electromagnetic waves, which are reflected back after encountering a target (such as a human body). The received reflected signal contains information such as the distance, speed and angle of the target.

[0036] Filter order: In signal processing, filters are used to remove unwanted frequency components and retain useful signals. The order of the filter determines the complexity of its filtering performance. The higher the order, the narrower the filter transition band, but the greater the phase delay.

[0037] Filter selection and time-shift compensation strategy: Selecting the right filter is critical to the quality of the signal. Time-shift compensation strategy is used to correct phase errors caused by signal propagation delay or system delay.

[0038] Signal noise reduction: Radar signals are subject to various noise interference during transmission and reception. The noise reduction step uses various algorithms (such as Wiener filtering, wavelet transform, etc.) to reduce noise and improve the signal-to-noise ratio.

[0039] Respiratory rate estimation: Using the filtered signal, the respiratory rate can be estimated. This is usually done by analyzing the periodicity of the signal, for example using Fourier transform or autocorrelation analysis.

[0040] Filtered signal enhancement: The enhancement step aims to increase the amplitude of specific components in the signal, such as by gain adjustment or using specific filters to highlight breathing or heartbeat signals.

[0041] Respiratory harmonic reduction: Respiratory signals may contain multiple harmonic components. Reducing these harmonics can reduce the complexity of the signal and make the main respiratory frequency component more obvious.

[0042] Heartbeat signal enhancement: Heartbeat signals may be masked by other physiological or non-physiological noises. Enhancing heartbeat signals can help monitor heart rate and heart rate variability more accurately.

[0043] Real-time extraction algorithm for vital signs: An algorithm for real-time extraction of vital signs has been developed. This algorithm can continuously monitor and analyze breathing and heartbeat signals, providing real-time data for medical monitoring and health assessment.

[0044] The process and effect diagram of the vital sign signal optimization algorithm are as follows: Figures 2 to 5 As shown in the figure, the key to the whole process is to accurately process and analyze radar signals to extract accurate vital signs information. This method has broad application prospects in fields such as remote health monitoring, emergency rescue and sleep research.

[0045] Among them, in the vital sign signal optimization algorithm: the heartbeat signal enhancement algorithm adopts a heartbeat signal enhancement algorithm based on a cubic spline interpolation function; the respiratory harmonic reduction algorithm adopts a respiratory harmonic reduction algorithm based on an adaptive BLMS notch filter.

[0046] The definition formula of the interpolation point of the cubic spline interpolation function is:

[0047] These conditions are often used to detect peaks or valleys in a signal, which is important in many applications such as electrocardiogram (ECG) signal analysis, speech processing, or any application where significant changes in a signal need to be identified.

[0048] First condition: This condition checks at time t i The signal value at S x ( t i ) is greater than the value of the previous and next time point, and greater than the average of the values ​​of the 32 time points before and after it. This means t i is a local maximum because it is larger than the values ​​in its immediate neighbors and in the surrounding small area.

[0049] Second condition: This condition checks at time t i The signal value at (S x (t j)) is less than the value of the previous and next time point, and less than the average of the values ​​of the 32 time points before and after it. This means t i is a local minimum because it is smaller than the values ​​in its immediate neighbors and in the surrounding small area.

[0050] In both conditions, a window of 32 time points was used to calculate the local average, which helped smooth the signal and identify more significant extreme points. This approach can reduce the impact of noise and improve the accuracy of detection.

[0051] The filter weight coefficient update process of the BLMS algorithm can be expressed as:

[0052] An update equation for the Recursive Least Squares (RLS) algorithm, which is used to estimate model parameters online. The RLS algorithm is an adaptive filtering technique widely used in signal processing and system identification.

[0053] The transfer function of the residual output of the dual-frequency adaptive notch filter and the input signal can be derived:

[0054] The transfer function of a second-order digital filter is commonly used in signal processing and control systems. The transfer function describes the relationship between the output and input of a system. This transfer function describes a second-order digital filter. By adjusting these parameters, a filter with specific frequency characteristics can be designed.

[0055] Real-time extraction algorithm of vital signs based on PKISS-EWT. Figure 6 As shown, the following steps are included: The vital sign signal extraction process based on the PKISS-EWT (Pulse Keying based on Improved Signal Subspace for Empirical Wavelet Transform) algorithm. This process includes inputting vital sign signals, prior knowledge calculation, optimizing signal transformation, spectrum peak analysis, segmentation intervals, improved spectrum segmentation, wavelet transformation, and finally outputting the extraction results. The following is an analysis and explanation of the principle of this process: Inputting vital sign signals: This is the starting point of the entire process, which involves obtaining vital sign signals such as electrocardiogram (ECG) signals, pulse oximetry (SpO2) signals, or respiratory movement signals from sensors or data acquisition devices.

[0056] Prior knowledge calculation: In this step, the algorithm uses known physiological and medical knowledge to pre-process the signal. This may include operations such as noise removal, filtering, and normalization to improve the accuracy of subsequent processing.

[0057] Optimize signal transformation: This step involves converting the original signal into a form that is more suitable for analysis. For example, a Fourier transform might be used to convert a time domain signal into a frequency domain signal so that periodic components in the signal can be more easily identified and analyzed.

[0058] Spectral peak analysis: In the frequency domain, the algorithm looks for spectral peaks in the signal, which represent the main frequency components in the signal. For vital signs, these peaks are usually related to the frequency of heartbeat and breathing.

[0059] Split interval: Based on the spectrum peak, the algorithm will split the spectrum into different intervals, each of which corresponds to a specific frequency component. This helps the subsequent wavelet transform to process each frequency component more accurately.

[0060] Improved spectrum segmentation: This step is a further optimization of the spectrum segmentation, which may involve finer frequency band division to ensure that the wavelet transform can more accurately capture subtle changes in the signal.

[0061] Wavelet transform: Empirical wavelet transform (EWT) is applied to each frequency band of the signal. EWT is an adaptive time-frequency analysis method that can select the most appropriate wavelet basis according to the local characteristics of the signal, thereby more effectively separating and extracting different components in the signal.

[0062] Output extraction results: Output extracted vital signs information, such as estimated respiratory rate and heart rate. This information can be used for real-time monitoring, health assessment, or further medical analysis.

[0063] The core of the whole process is to use the adaptability and flexibility of EWT to process nonlinear and non-stationary vital sign signals, so as to accurately extract key information from the signals. This method has important application value in the fields of medical monitoring and health assessment.

[0064] Among them, the wavelet construction empirical wavelet function and empirical scaling function can be expressed as:

[0065] The process and effect diagram of the real-time extraction algorithm of vital signs signals are as follows: Figures 6 to 8 shown.

[0066] According to the analysis of the characteristics of vital signs signals, situation one: fatigue driving. At this time, the driver's breathing rate and heart rate are in an abnormal state, which may be due to long-term driving or physical discomfort. The driver is warned to reduce speed or park nearby to adjust his body. Situation two: dangerous driving. At this time, the driver is in an emergency state and may suddenly suffer from inhibited breathing or cardiac arrest. At this time, the emergency number is automatically dialed and the automatic driving system intervenes to assist the driver to pull over or automatically navigate to the nearest clinic.

[0067] The second object of the present invention is to provide a driver health monitoring and early warning system. Fig. 9 The flowchart of the system includes: The coordinate positioning module 100 is used to call the camera data in the DMS in the smart cockpit to locate the driver's chest and obtain the three-dimensional coordinates of the driver's chest in the cockpit space; The transmitting and receiving module 200 is used to adjust the radar signal sent by the millimeter-wave radar integrated in the steering wheel in combination with the three-dimensional coordinates located at the chest cavity; and receive the echo signal of the radar signal after the interference of the chest cavity movement; A real-time extraction module 300, used for extracting a respiratory signal and a heartbeat signal in real time based on the echo signal to obtain a vital sign signal; The feature extraction module 400 is used to extract features from vital sign signals to obtain vital sign parameters; The analysis and processing module 500 is used to analyze the vital sign parameters; when the vital sign parameters exceed the threshold, an exception processing request is sent.

[0068] The system is based on the above-mentioned driver health monitoring and early warning method.

[0069] like Fig.10 As shown, the third purpose of the embodiment of the present invention is to provide an electronic device, including a memory 701, a processor 702, and a computer program stored in the memory 701 and executable on the processor, wherein the processor implements the driver health monitoring and early warning method when executing the computer program. It also includes a communication interface 703 and a bus 704.

[0070] A fourth objective of an embodiment of the present invention is to provide a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the driver health monitoring and early warning method is implemented.

[0071] A fifth objective of an embodiment of the present invention is to provide a computer program product, which includes computer instructions, and is characterized in that the computer instructions instruct a computer to execute the driver health monitoring and early warning method.

[0072] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0073] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0074] The present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, readable storage media, optical storage, etc.) containing computer-usable program codes.

[0075] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0076] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0077] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A driver health monitoring and early warning method, characterized in that: include: Call the camera data in the DMS in the smart cockpit to locate the driver's chest and obtain the three-dimensional coordinates of the driver's chest in the cockpit space; Combined with the three-dimensional coordinates of the chest cavity, the millimeter-wave radar integrated in the steering wheel is adjusted to send radar signals; the echo signal of the radar signal after interference from the chest cavity movement is received; Extracting a respiratory signal and a heartbeat signal in real time based on the echo signal to obtain a vital sign signal; Extract features of vital sign signals to obtain vital sign parameters; Analyze the vital sign parameters; when the vital sign parameters exceed a threshold, send an exception handling request.

2. A driver health monitoring and early warning method according to claim 1, characterized in that: The method of calling the camera data in the DMS in the smart cockpit to locate the driver's chest cavity and obtain the three-dimensional coordinates of the driver's chest in the cockpit space includes: The camera function in the smart cockpit is called to determine the vertical position of the driver's chest. Combined with the specific situation of the driver's seat adjustment, the driver's plane position is determined to obtain the three-dimensional coordinates of the driver's chest in the cockpit space.

3. A driver health monitoring and early warning method according to claim 1, characterized in that: The method combines the three-dimensional coordinates of the chest cavity and adjusts the radar signal sent by the millimeter-wave radar integrated in the steering wheel, including: Combined with the three-dimensional coordinates of the driver's chest in the cockpit space, the gimbal base and transmission power of the millimeter-wave radar integrated in the steering wheel are adjusted to adjust the direction and signal strength of radar signal detection, so that the cross-section of the radar's effective detection area covers the driver's chest position, so as to perform adaptive adjustment of the radar position; After adaptive adjustment, the radar signal is sent to the driver's chest.

4. A driver health monitoring and early warning method according to claim 1, characterized in that: The receiving of the echo signal of the radar signal after interference by the movement of the thoracic cavity comprises: After sending a radar signal to the driver's chest, an echo signal of the radar signal after interference from chest cavity movement is received; Verify the echo quality of the radar signal after the interference of the chest cavity movement. When the quality meets the requirements, judge the quality of the detection signal after the radar positioning adjustment to obtain the echo signal whose detection signal quality meets the requirements.

5. A driver health monitoring and early warning method according to claim 1, characterized in that: The real-time extraction of the respiratory signal and the heartbeat signal based on the echo signal to obtain the vital sign signal includes: Performing noise reduction processing on the echo signal; The echo signal after noise reduction is subjected to vital sign signal optimization processing, which includes noise elimination, movement compensation strategy processing to eliminate random body motion, heartbeat signal enhancement algorithm to enhance heartbeat signal, respiratory harmonic reduction algorithm to reduce respiratory harmonics, and vital sign signal real-time extraction algorithm to separate respiratory heartbeat to obtain vital sign signal.

6. A driver health monitoring and early warning method according to claim 1, characterized in that: The feature extraction of the vital sign signal to obtain the vital sign parameter is to obtain the vital sign signal by calculating the vital sign signal optimization signal through a real-time vital sign signal extraction algorithm; The real-time vital sign signal extraction algorithm is based on the real-time vital sign signal extraction algorithm of PKISS-EWT, and includes: Input vital sign signals; Performing prior knowledge calculation on the vital sign signal and preprocessing the signal using known physiological and medical knowledge; Use normalized Fourier transform to convert the original time domain signal into a frequency domain signal to obtain the spectrum peak; The spectrum is divided into different intervals using improved spectrum segmentation, each interval corresponds to a specific frequency component; Wavelet transform is applied to each frequency band of the signal, outputting extracted vital sign information including respiratory rate and heart rate.

7. A driver health monitoring and early warning method according to claim 1, characterized in that: The analyzing of the vital sign parameters; when the vital sign parameters exceed a threshold, sending an exception handling request includes: Situation 1: Fatigue driving. At this time, the driver's breathing rate and heart rate exceed the fatigue driving threshold, and a warning is issued to the driver; Case 2: Dangerous driving. At this time, the driver's breathing rate and heart rate are beyond the dangerous driving threshold, and an emergency call is automatically made, and the autonomous driving system intervenes.

8. A driver health monitoring and early warning system, characterized in that: include: The coordinate positioning module is used to call the camera data in the DMS in the smart cockpit to locate the driver's chest and obtain the three-dimensional coordinates of the driver's chest in the cockpit space; The transmitting and receiving module is used to adjust the radar signal sent by the millimeter-wave radar integrated in the steering wheel in combination with the three-dimensional coordinates located at the chest cavity; and receive the echo signal of the radar signal after the interference of the chest cavity movement; A real-time extraction module, used for extracting a respiratory signal and a heartbeat signal in real time based on the echo signal to obtain a vital sign signal; A feature extraction module is used to extract features from vital sign signals to obtain vital sign parameters; The analysis and processing module is used to analyze the vital sign parameters; when the vital sign parameters exceed the threshold, an exception processing request is sent.

9. An electronic device, characterized in that: The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the driver health monitoring and early warning method as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the driver health monitoring and early warning method according to any one of claims 1 to 7 is implemented.

Images