A method and apparatus for monitoring a driver's physiological parameters

Abstract

This application provides a method and apparatus for monitoring driver physiological parameters, relating to the fields of automotive electronics technology and intelligent health monitoring. The method includes: acquiring non-contact and contact physiological data of the driver; processing the non-contact and contact physiological data separately to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data; determining the validity status of the contact physiological data based on signal quality indicators; and if the validity status is valid, determining the driver's physiological parameters based on the second set of measured physiological parameters and the first set of estimated physiological parameters. This application effectively solves the problems of low accuracy and blind spots inherent in single monitoring methods, significantly improving the continuity and reliability of driver physiological monitoring and providing accurate data support for driving safety.

Description

Technical Field

[0001] This application relates to the fields of automotive electronics technology and intelligent health monitoring, and more specifically, to a method and device for monitoring driver physiological parameters. Background Technology

[0002] Driven by the development of smart cockpit technology, driver monitoring systems have become a core technology for driving safety. Existing solutions mostly employ non-contact visual perception combined with remote photoelectric volumetric imaging technology. This involves using onboard cameras to capture facial images and extract physiological parameters such as heart rate and blood oxygenation, while simultaneously identifying fatigue and distraction. Monitoring schemes that integrate visual images and physiological signals have also been proposed to improve the comprehensiveness of monitoring. However, purely visual non-contact detection is easily affected by ambient light, facial occlusion, and vehicle vibration, resulting in low parameter detection accuracy and failing to meet the needs of medical-grade monitoring. Summary of the Invention

[0003] The purpose of this application is to provide a method and device for monitoring driver physiological parameters, which solves the above-mentioned problems existing in the prior art and can realize high-precision, blind-spot-free continuous monitoring of driver physiological parameters.

[0004] Firstly, a method for monitoring driver physiological parameters is provided, which may include: Acquire non-contact and contact physiological data of drivers; The non-contact physiological data and the contact physiological data are processed respectively to obtain the first set of estimated physiological parameters corresponding to the non-contact physiological data and the second set of measured physiological parameters corresponding to the contact physiological data. The validity status of the contact physiological data is determined based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

[0005] In one possible implementation, processing the non-contact physiological data includes: The non-contact physiological data is processed by facial region localization, physiological feature extraction, and signal filtering to obtain the first set of estimated physiological parameters.

[0006] In one possible implementation, processing the contact-based physiological data includes: The contact-based physiological data are processed by signal amplification, noise reduction, and feature point detection to obtain the second set of physiological parameter measurements.

[0007] In one possible implementation, determining the validity status of the contact physiological data based on signal quality indicators includes: The impedance and signal-to-noise ratio of the bioelectrical signal in the contact physiological data, as well as the AC / DC component ratio and waveform characteristics of the photoplethysmography pulse wave signal, were detected respectively. When the signal quality indicators of both the bioelectric signal and the photoplethysmography signal meet the preset threshold, the validity status of the contact physiological data is determined to be valid.

[0008] In one possible implementation, the driver's physiological parameters are determined based on the second set of measured physiological parameters and the first set of estimated physiological parameters, including: Calculate the deviation between the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters; Based on the aforementioned deviation, the parameters of the model or algorithm used to estimate physiological parameters from the non-contact physiological data are adjusted, and the second set of physiological parameter measurements are used as the driver's physiological parameters.

[0009] In one possible implementation, the method further includes: If the validity status is invalid, then the estimated physiological parameters obtained by processing the acquired non-contact physiological data based on the adjusted model or algorithm are output as the driver's physiological parameters.

[0010] In one possible implementation, adjusting the parameters of the model or algorithm used to estimate physiological parameters from the non-contact physiological data includes: The deviation is used as an error signal and combined with the feature vector of the non-contact physiological data. The weight vector of the adaptive filter is iteratively updated according to a preset learning rate to adjust the parameters of the model or algorithm for estimating physiological parameters in the non-contact physiological data.

[0011] Secondly, a device for monitoring driver physiological parameters is provided, the device including: The acquisition unit is used to acquire the driver's non-contact physiological data and contact physiological data; The processing unit is used to process the non-contact physiological data and the contact physiological data respectively to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data. The determining unit is used to determine the validity status of the contact physiological data based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

[0012] Thirdly, an electronic device is provided, which includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements any of the steps described in the first aspect above.

[0013] Fourthly, a computer-readable storage medium is provided, wherein a computer program is stored therein, and when executed by a processor, the computer program implements the steps of any of the methods described in the first aspect above.

[0014] This application provides a method and apparatus for monitoring driver physiological parameters. The method includes: acquiring non-contact physiological data and contact physiological data of the driver; processing the non-contact and contact physiological data separately to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data; determining the validity status of the contact physiological data based on the signal quality index; and if the validity status is valid, determining the driver's physiological parameters based on the second set of measured physiological parameters and the first set of estimated physiological parameters. This application effectively solves the problems of low accuracy and blind spots in single monitoring methods, and can significantly improve the continuity and reliability of driver physiological monitoring, providing accurate data support for driving safety. Attached Figure Description

[0015] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 A flowchart illustrating a method for monitoring driver physiological parameters provided in this application embodiment; Figure 2 This is a schematic diagram of the sensor layout of the steering wheel rim provided in an embodiment of this application; Figure 3 A waveform diagram of driver physiological parameter monitoring data fusion based on adaptive calibration provided in the embodiments of this application; Figure 4 A schematic diagram of the structure of a driver physiological parameter monitoring device provided in an embodiment of this application; Figure 5This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0017] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.

[0018] Driven by the development of smart cockpit technology, driver monitoring systems have become a core technology for driving safety. Existing solutions mostly employ non-contact visual perception combined with remote photoelectric volumetric imaging technology. This involves using onboard cameras to capture facial images and extract physiological parameters such as heart rate and blood oxygenation, while simultaneously identifying fatigue and distraction. Monitoring schemes that integrate visual images and physiological signals have also been proposed to improve the comprehensiveness of monitoring. However, purely visual non-contact detection is easily affected by ambient light, facial occlusion, and vehicle vibration, resulting in low parameter detection accuracy and failing to meet the needs of medical-grade monitoring.

[0019] Therefore, this application provides a method for monitoring driver physiological parameters, which solves the above-mentioned problems existing in the prior art and can realize high-precision, blind-spot-free continuous monitoring of driver physiological parameters.

[0020] The preferred embodiments of this application are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are for illustration and explanation only and are not intended to limit this application. Furthermore, the embodiments and features in the embodiments of this application can be combined with each other without conflict.

[0021] Figure 1 This is a flowchart illustrating a method for monitoring driver physiological parameters provided in an embodiment of this application. Figure 1 As shown, the method may include: Step S110: Obtain the driver's non-contact physiological data and contact physiological data.

[0022] Non-contact physiological data is collected by the Driver Monitoring System (DMS) camera integrated into the roof or dashboard of the vehicle's cockpit. The DMS camera is an RGB infrared dual-mode camera that captures video stream data of the driver's facial area at a maximum resolution of 1080p and a sampling rate of 30fps. This video stream data is transmitted via LVDS or Gigabit Ethernet interface. Combination Figure 2As shown, contact-based physiological data is collected by ECG and PPG sensors integrated into the grip areas at the 3 and 9 o'clock positions of the car steering wheel rim. The dry electrode ECG sensor collects the driver's electrocardiogram (ECG) analog signal at a sampling rate of 1 kHz and a bandwidth of 0.5 Hz to 40 Hz, while the reflective PPG sensor collects the driver's photoplethysmography (PPG) analog signal at a sampling rate of 25 Hz. The ECG and PPG analog signals together serve as contact-based physiological data. This contact-based physiological data is transmitted to the signal conditioning circuit via a slip ring connector or wireless power supply and data transmission technology, and then transmitted via a CAN bus or dedicated wiring harness. Furthermore, the reflective PPG sensor features a dual-light source design, using a 660 nm red LED and an 880 nm infrared LED as the light sources, and a PD204 photodiode as the photodetector. The sensor sampling rate is 25 Hz, enabling accurate acquisition of the simulated blood flow pulsation signal from the driver's palm.

[0023] The non-contact and contact physiological data collected above are assigned a unified millisecond-level global timestamp based on hardware, which enables synchronous collection and time dimension alignment of multi-source physiological data and ensures the temporal consistency of subsequent data processing.

[0024] In some embodiments, the ECG sensor is not limited to dry electrode type, but can also use wet electrode, textile electrode, and all types of electrodes can achieve effective acquisition of electrocardiogram signals and adapt to different steering wheel materials and driver grip habits. The light source of the PPG sensor is not limited to 660nm red LED + 880nm infrared LED, but can also use green LED. Green light is more suitable for palm blood flow signal acquisition and steering wheel grip area monitoring scenarios. A bioimpedance (BIA) sensor can be added and integrated into the steering wheel or seat area to estimate physiological parameters such as driver body fat percentage and dehydration status, expanding the monitoring dimensions. A microphone sensor can also be added and integrated into the vehicle cabin to monitor characteristics such as snoring and abnormal breathing sounds of the driver, and help to determine the driver's fatigue and health status. Driver-worn devices can also be used to replace the contact sensors on the steering wheel. The ECG and PPG signals collected by the wearable devices can be transmitted to the vehicle processing unit via wireless communication technology, enabling remote collection and fusion of contact-based physiological data.

[0025] Step S120: Process the non-contact physiological data and the contact physiological data respectively to obtain the first set of estimated physiological parameters corresponding to the non-contact physiological data and the second set of measured physiological parameters corresponding to the contact physiological data.

[0026] Specifically, processing non-contact physiological data includes: The process involves facial region localization, physiological feature extraction, and signal filtering of non-contact physiological data to obtain the first set of estimated physiological parameters. This process includes: using the BlazeFace lightweight face detection algorithm based on convolutional neural networks to analyze the facial video stream of the non-contact physiological data in real time, locating and extracting the effective facial region of the driver, selecting areas with thin skin and rich blood vessels such as the forehead and cheeks; then, extracting weak skin color change signals reflecting the driver's physiological activities from the located effective facial region, and using a blind source separation algorithm to separate the skin color change signals, separating the effective physiological signals from interference signals caused by ambient light and facial micro-movements; finally, bandpass filtering is applied to the separated effective physiological signals, with the filter frequency band set to 0.8Hz-3.0Hz, corresponding to the normal range of human heart rate 48-180 BPM. After filtering out non-target frequency components, the algorithm calculates the first set of estimated physiological parameters, which includes at least a heart rate estimate. and estimated respiratory rate .

[0027] Processing of contact-based physiological data includes: The contact-based physiological data were amplified, denoised, and processed with feature point detection to obtain the second set of physiological parameter measurements. Contact-based physiological data includes analog ECG signals and analog PEP (photoplethysmography) signals. After targeted processing of each type of signal, corresponding physiological parameters are obtained, forming a second set of physiological parameter measurements. Specifically: the acquired raw analog ECG and raw analog PEP signals are transmitted to a signal conditioning circuit. The signal conditioning circuit performs preliminary amplification of the two types of analog electrical signals to increase the signal amplitude and ensure the signal validity for subsequent processing. Then, the amplified analog ECG signal is first filtered through a 0.5Hz high-pass filter to eliminate baseline drift interference, and then filtered through a 40Hz low-pass filter to remove high-frequency noise from the vehicle's electrical system and environmental clutter. The amplified analog PEP signal is first smoothed using a moving average filter, and then wavelet transform is used to remove motion artifacts caused by minor driver hand movements, resulting in an interference-free analog PEP waveform. Finally, the Pan-Tompkins algorithm is used to detect the QRS complex and accurately calculate the R-wave peak interval to obtain a high-precision heart rate measurement. and heart rate variability For the denoised photoplethysmography (PPG) analog signal, feature points such as systolic and diastolic peaks are extracted from the waveform. The time intervals and amplitude changes between these feature points are calculated to obtain the heart rate measurement. and blood oxygen saturation measurement value .

[0028] The heart rate measurement, heart rate variability measurement, and blood oxygen saturation measurement obtained from the above processing are integrated to obtain the second set of physiological parameter measurement values. Among them, the heart rate measurement value calculated by the electrocardiogram simulation signal is used as the core heart rate gold standard, and the heart rate measurement value calculated by the photoplethysmography pulse wave simulation signal is used for cross-validation.

[0029] Step S130: Determine the validity status of the contact physiological data based on the signal quality indicators of the contact physiological data.

[0030] Specifically, the impedance and signal-to-noise ratio of bioelectrical signals in contact physiological data, as well as the AC / DC component ratio and waveform characteristics of photoplethysmography pulse wave signals, were detected respectively. When the signal quality indicators of both bioelectrical signals and photoplethysmography (PPG) signals meet the preset thresholds, the validity status of the contact physiological data is determined to be valid.

[0031] In other words, the interelectrode impedance and R-wave signal-to-noise ratio of the bioelectrical signal (ECG) and the ratio of AC to DC components and waveform characteristics of the photoplethysmography (PPG) signal in the contact-based physiological data are detected separately. Pre-set signal quality thresholds are established for each detection indicator. When all signal quality detection indicators of the ECG and PPG signals meet the corresponding preset thresholds, the contact-based physiological data is deemed valid. If any detection indicator of any signal fails to meet the corresponding preset threshold, the contact-based physiological data is deemed invalid. The preset safety thresholds for various physiological parameters are stored in a local lookup table, and these thresholds can be personalized based on the driver's basic profile information, specifically adjusted according to the driver's age, medical history, and baseline physiological characteristics, to achieve targeted monitoring of the driver's health status. Based on the validity status determination results, the driver's physiological parameters are determined in the following two cases: A. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

[0032] Furthermore, based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters, the driver's physiological parameters are determined, including: Calculate the deviation between the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters; Based on the bias, the parameters of the model or algorithm used to estimate physiological parameters from non-contact physiological data are adjusted, and the second set of physiological parameter measurements are used as the driver's physiological parameters.

[0033] Adjusting the parameters of the model or algorithm used to estimate physiological parameters from non-contact physiological data, including: The deviation is used as an error signal combined with the feature vector of non-contact physiological data. The weight vector of the adaptive filter is iteratively updated according to a preset learning rate to adjust the parameters of the model or algorithm for estimating physiological parameters from non-contact physiological data. In other words, the weight vector of the adaptive filter is iteratively updated in real time according to a preset learning rate factor. Through the dynamic adjustment of the weight vector, the parameters of the model or algorithm used to estimate physiological parameters from non-contact physiological data are optimized, so that the estimated values ​​of physiological parameters corresponding to non-contact physiological data infinitely approach the high-precision measurement values ​​corresponding to contact physiological data.

[0034] Instantaneous deviation is the heart rate measurement value corresponding to contact physiological data. (usually with) Gold Label The difference between the heart rate estimate (used for cross-validation) and the heart rate estimate corresponding to non-contact physiological data at the same time t is calculated using the following formula:

[0035] The iterative update formula for the adaptive filter weight vector is:

[0036] in, This is the input feature vector of the non-contact physiological parameter estimation model or algorithm, specifically the sequence of pixel value changes in the region of interest on the driver's face. μ is a preset learning rate factor, which is 0.01 in this embodiment. w(t+1) is the filter weight vector at time t+1, and w(t) is the filter weight vector at time t. Through continuous learning, the learning rate is adjusted to achieve the desired learning rate. Approaching infinitely when contact is effective. Thus, even in the event of contact failure, DMS alone can output high-precision results.

[0037] B. If the validity status is invalid, output the estimated physiological parameters obtained by processing the acquired non-contact physiological data based on the model or algorithm with adjusted parameters, as the driver's physiological parameters.

[0038] Specifically, the system automatically switches to a pure visual monitoring mode, calls the latest weight vector w of the adaptive filter after the above iterations, substitutes the latest weight vector w into the model or algorithm used to estimate physiological parameters from non-contact physiological data, and re-performs face region localization, physiological feature extraction and signal filtering on the real-time acquired non-contact physiological data to obtain the non-contact physiological parameter estimation value after parameter adjustment, and outputs the corrected physiological parameter estimation value as the driver's physiological parameter, thereby realizing seamless and continuous monitoring of the driver's physiological parameters.

[0039] In the above process, the preset threshold for ECG signal quality is: the inter-electrode impedance is below 500kΩ for 2 seconds and the detected R-wave signal-to-noise ratio (SNR) is greater than 10dB; the preset threshold for PPG signal quality is: the ratio of AC to DC components (AC / DC) of the PPG signal is greater than 0.1% for 2 seconds and the characteristic points such as the systolic peak and diastolic peak of the PPG waveform are clearly distinguishable; in the second set of physiological parameter measurements, the heart rate measurement value calculated from the ECG signal is used as the core heart rate gold standard, and the heart rate measurement value calculated from the PPG signal is used for cross-validation.

[0040] In summary, combining Figure 3 As shown, the system first simultaneously collects both non-contact and contact physiological data from the driver. Then, it continuously monitors the signal quality indicators of the contact physiological data and determines its validity. If the contact physiological data is valid, it outputs high-precision contact physiological parameter measurements and uses these measurements to calibrate and compensate the estimation model for the non-contact physiological parameters online, optimizing the estimated non-contact physiological parameters. If the contact physiological data is invalid, it directly outputs the corrected estimated non-contact physiological parameters. Finally, the system outputs the fused, continuous, and stable final physiological parameters of the driver. Verified in a standard testing environment, the mean absolute error (MAE) of heart rate monitoring after fusion using the driver physiological parameter monitoring method of this application can be reduced to below 3 beats / minute. Compared to a single DMS visual monitoring scheme (heart rate monitoring MAE > 5 beats / minute), the heart rate monitoring accuracy is improved by more than 40%, meeting the quasi-medical-grade driver physiological parameter monitoring requirements.

[0041] In some embodiments, the fused final physiological parameters are compared in real time with preset personalized safety thresholds to determine whether the driver's physiological and driving state is abnormal. The specific abnormality determination rules are as follows: if the heart rate is higher than 120 beats / minute or lower than 50 beats / minute for 10 seconds, it is determined to be tachycardia or bradycardia; if the RMSSD index of HRV is significantly lower than the driver's personal baseline level for 5 consecutive minutes, it is determined to be mental fatigue or excessive stress.

[0042] For different levels of anomalies, corresponding multimodal early warning and feedback actions are initiated, specifically divided into three levels of early warning: When mild driver distraction or early fatigue is detected, a Level 1 warning is triggered: a coffee cup warning icon is displayed via the head-up display (HUD) to provide a visual reminder; When moderate driver fatigue or persistent abnormal heart rate is detected, a level 2 warning is triggered: triggering a multi-dimensional warning by automatically lowering the temperature of the vehicle's air conditioning, playing rousing music through the vehicle's audio system, and generating tactile vibrations through the vibration motors of the steering wheel or seat, thus achieving a combined warning of vision, hearing, and touch. When severe driver fatigue, sudden arrhythmia, or severely impaired driving ability is detected, a Level 3 warning is triggered: the vehicle's Advanced Driver Assistance System (ADAS) is immediately activated, the vehicle is controlled to decelerate smoothly, the hazard lights are automatically turned on, and the vehicle is eventually brought to a stop in a safe lane. The system also automatically dials an emergency rescue number to achieve emergency intervention for driving safety.

[0043] In some embodiments, the data fusion processing can adopt a centralized architecture, in which a central processing unit processes all the collected physiological data; or it can adopt a distributed architecture, in which the DMS module and the steering wheel contact sensor module are each configured with a preprocessing unit to complete the initial data processing, and then the processing results are uploaded to the central processing unit for final fusion. Both architectures can achieve effective fusion of multimodal data. The fusion of multimodal physiological data can be achieved at different levels. It can be achieved by fusing the original PPG waveform and video skin color signal at the signal level, or by fusing extracted physiological features such as heart rate value and HRV feature at the feature level, or by having non-contact and contact monitoring modules independently judge the driver's health status at the decision level, and then voting to fuse the judgment results. The fusion method at each level can be flexibly selected according to the vehicle's computing resources.

[0044] The monitoring method of this application is not only applicable to the monitoring of the driver's physiological parameters, but can also be extended to the monitoring of the health status of the front passenger and rear passengers. By deploying monitoring modules at corresponding locations in the vehicle, real-time monitoring of the physiological parameters of all occupants in the vehicle can be achieved. The driver's physiological parameters monitored in this application can be used for real-time warnings in the vehicle, and the data can be encrypted and uploaded to the cloud server to form a long-term health record for the driver. The data can also be synchronized with the driver's smartphone app to provide the driver with a report on the health trend of physiological parameters. This application can be linked with the vehicle's infotainment system to automatically recommend soothing or invigorating music and adjust the infotainment content based on the driver's monitored physiological parameters such as heart rate and stress level, thus achieving personalized adaptation of the infotainment system.

[0045] This application provides a method for monitoring driver physiological parameters. The method includes: acquiring non-contact and contact physiological data of the driver; processing the non-contact and contact physiological data separately to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data; determining the validity status of the contact physiological data based on the signal quality of the non-contact physiological data; if the validity status is valid, determining the driver's physiological parameters based on the second set of measured physiological parameters and the first set of estimated physiological parameters. This application effectively solves the problems of low accuracy and blind spots in single monitoring methods, and can significantly improve the continuity and reliability of driver physiological monitoring, providing accurate data support for driving safety.

[0046] Corresponding to the above method, embodiments of this application also provide a device for monitoring driver physiological parameters, such as... Figure 4 As shown, the device includes: Acquisition unit 410 is used to acquire the driver's non-contact physiological data and contact physiological data; The processing unit 420 is used to process the non-contact physiological data and the contact physiological data respectively to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data. The determining unit 430 is used to determine the validity status of the contact physiological data based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

[0047] The functions of each unit of the driver physiological parameter monitoring device provided in the above embodiments of this application can be implemented through the above methods and steps. Therefore, the specific working process and beneficial effects of each unit in the driver physiological parameter monitoring device provided in the embodiments of this application will not be repeated here.

[0048] This application also provides an electronic device, such as... Figure 5 As shown, it includes a processor 510, a communication interface 520, a memory 530, and a communication bus 540, wherein the processor 510, the communication interface 520, and the memory 530 communicate with each other through the communication bus 540.

[0049] Memory 530 is used to store computer programs; When the processor 510 executes the program stored in the memory 530, it performs the following steps: Acquire non-contact and contact physiological data of drivers; The non-contact physiological data and the contact physiological data are processed respectively to obtain the first set of estimated physiological parameters corresponding to the non-contact physiological data and the second set of measured physiological parameters corresponding to the contact physiological data. The validity status of the contact physiological data is determined based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

[0050] The communication bus mentioned above can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus can be divided into address bus, data bus, control bus, etc. For ease of illustration, only one thick line is used to represent it in the diagram, but this does not mean that there is only one bus or one type of bus.

[0051] The communication interface is used for communication between the aforementioned electronic devices and other devices.

[0052] The memory may include random access memory (RAM) or non-volatile memory (NVM), such as at least one disk storage device. Optionally, the memory may also be at least one storage device located remotely from the aforementioned processor.

[0053] The processors mentioned above can be general-purpose processors, including central processing units (CPUs), network processors (NPs), etc.; they can also be digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components.

[0054] The implementation methods and beneficial effects of the various components of the electronic device in the above embodiments for solving the problem can be found in [reference needed]. Figure 1The steps in the illustrated embodiments are used to implement the electronic device. Therefore, the specific working process and beneficial effects of the electronic device provided in this application will not be repeated here.

[0055] In another embodiment provided in this application, a computer-readable storage medium is also provided, which stores instructions that, when executed on a computer, cause the computer to perform a method for monitoring driver physiological parameters as described in any of the above embodiments.

[0056] In another embodiment provided in this application, a computer program product containing instructions is also provided, which, when run on a computer, causes the computer to perform a method for monitoring driver physiological parameters as described in any of the above embodiments.

[0057] Those skilled in the art will understand that the embodiments in this application can be provided as methods, systems, or computer program products. Therefore, the embodiments in this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the embodiments in this application can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0058] This application describes embodiments of methods, apparatus (systems), and computer program products according to embodiments of this application with reference to flowchart illustrations and / or block diagrams. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0059] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0060] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0061] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this application do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected," "coupled," or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0062] Although preferred embodiments have been described in this application, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the embodiments in this application are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments in this application.

[0063] Obviously, those skilled in the art can make various modifications and variations to the embodiments of this application without departing from the spirit and scope of the embodiments of this application. Therefore, if these modifications and variations to the embodiments of this application fall within the scope of the embodiments of this application and their equivalents, then these modifications and variations are also intended to be included in the embodiments of this application.

Claims

1. A method for monitoring physiological parameters of a driver, characterized in that, The method includes: Acquire non-contact and contact physiological data of drivers; The non-contact physiological data and the contact physiological data are processed respectively to obtain the first set of estimated physiological parameters corresponding to the non-contact physiological data and the second set of measured physiological parameters corresponding to the contact physiological data. The validity status of the contact physiological data is determined based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

2. The method as described in claim 1, characterized in that, Processing the non-contact physiological data includes: The non-contact physiological data is processed by facial region localization, physiological feature extraction, and signal filtering to obtain the first set of estimated physiological parameters.

3. The method as described in claim 1, characterized in that, Processing the contact-based physiological data includes: The contact-based physiological data are processed by signal amplification, noise reduction, and feature point detection to obtain the second set of physiological parameter measurements.

4. The method as described in claim 1, characterized in that, Determining the validity status of the contact physiological data based on signal quality indicators includes: The impedance and signal-to-noise ratio of the bioelectrical signal in the contact physiological data, as well as the AC / DC component ratio and waveform characteristics of the photoplethysmography pulse wave signal, were detected respectively. When the signal quality indicators of both the bioelectric signal and the photoplethysmography signal meet the preset threshold, the validity status of the contact physiological data is determined to be valid.

5. The method as described in claim 1, characterized in that, Based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters, the driver's physiological parameters are determined, including: Calculate the deviation between the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters; Based on the aforementioned deviation, the parameters of the model or algorithm used to estimate physiological parameters from the non-contact physiological data are adjusted, and the second set of physiological parameter measurements are used as the driver's physiological parameters.

6. The method as described in claim 5, characterized in that, The method further includes: If the validity status is invalid, then the estimated physiological parameters obtained by processing the acquired non-contact physiological data based on the adjusted model or algorithm are output as the driver's physiological parameters.

7. The method as described in claim 5, characterized in that, Based on the aforementioned deviation, the parameters of the model or algorithm used to estimate physiological parameters from the non-contact physiological data are adjusted, including: The deviation is used as an error signal and combined with the feature vector of the non-contact physiological data. The weight vector of the adaptive filter is iteratively updated according to a preset learning rate to adjust the parameters of the model or algorithm for estimating physiological parameters in the non-contact physiological data.

8. A device for monitoring driver physiological parameters, characterized in that, The device includes: The acquisition unit is used to acquire the driver's non-contact physiological data and contact physiological data; The processing unit is used to process the non-contact physiological data and the contact physiological data respectively to obtain a first set of estimated physiological parameters corresponding to the non-contact physiological data and a second set of measured physiological parameters corresponding to the contact physiological data. The determining unit is used to determine the validity status of the contact physiological data based on the signal quality index of the contact physiological data. If the validity status is valid, then the driver's physiological parameters are determined based on the measured values ​​of the second set of physiological parameters and the estimated values ​​of the first set of physiological parameters.

9. An electronic device, characterized in that, The electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; A processor, when executing a program stored in memory, implements the steps of the method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method described in any one of claims 1-7.

Images