WO2018152712A1 - Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule - Google Patents

Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule Download PDF

Info

Publication number
WO2018152712A1
WO2018152712A1 PCT/CN2017/074438 CN2017074438W WO2018152712A1 WO 2018152712 A1 WO2018152712 A1 WO 2018152712A1 CN 2017074438 W CN2017074438 W CN 2017074438W WO 2018152712 A1 WO2018152712 A1 WO 2018152712A1
Authority
WO
WIPO (PCT)
Prior art keywords
module
steering wheel
vehicle
main control
control module
Prior art date
Application number
PCT/CN2017/074438
Other languages
English (en)
Chinese (zh)
Inventor
张跃
张烈帅
雷夏飞
冯治蒙
张拓
Original Assignee
深圳市岩尚科技有限公司
清华大学深圳研究生院
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 深圳市岩尚科技有限公司, 清华大学深圳研究生院 filed Critical 深圳市岩尚科技有限公司
Priority to PCT/CN2017/074438 priority Critical patent/WO2018152712A1/fr
Priority to CN201780001970.5A priority patent/CN107979985B/zh
Publication of WO2018152712A1 publication Critical patent/WO2018152712A1/fr

Links

Images

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A61B5/0205—Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
    • A61B5/02055—Simultaneously evaluating both cardiovascular condition and temperature
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
    • A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/02—Detecting, measuring or recording pulse, heart rate, blood pressure or blood flow; Combined pulse/heart-rate/blood pressure determination; Evaluating a cardiovascular condition not otherwise provided for, e.g. using combinations of techniques provided for in this group with electrocardiography or electroauscultation; Heart catheters for measuring blood pressure
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
    • A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
    • A61B5/1116—Determining posture transitions
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
    • A61B5/316—Modalities, i.e. specific diagnostic methods
    • A61B5/318—Heart-related electrical modalities, e.g. electrocardiography [ECG]
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6893—Cars
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/74—Details of notification to user or communication with user or patient ; user input means
    • A61B5/746—Alarms related to a physiological condition, e.g. details of setting alarm thresholds or avoiding false alarms

Definitions

  • the utility model relates to a device for use in a motor vehicle, in particular to a vehicle health and safety driving assistance device.
  • the steering wheel is often operated with one hand, such as one-handed driving or smoking, in order to be comfortable, and even more, in the process of driving, the hands are separated from the steering wheel, and over time, poor driving habits are developed. It poses a major security risk to one's life and others' lives and property.
  • an auxiliary health and safety driving device which can effectively prevent a situation in which a similar device is misjudged.
  • An in-vehicle health and safety driving assistance device comprising a steering wheel cover that fits a steering wheel of a vehicle, wherein the steering wheel cover has an electrode on the surface thereof as an external medium for collecting an electrocardiographic signal;
  • the device body includes a power supply module, a main control module, an electrocardiographic acquisition processing module, a storage module, and an attitude sensor module;
  • the power supply module is responsible for supplying power to the entire device, and the main control module respectively
  • the electrical collection processing module, the storage module, and the attitude sensor module are connected, and the ECG acquisition processing module is further connected to the electrode.
  • the device body further includes a wireless transmission module, and the wireless transmission module is connected to the main control module for wirelessly communicating with the smart terminal and/or the first auxiliary device and/or the second auxiliary device.
  • a first auxiliary device is further included, and the first auxiliary device is wirelessly connected to the device body for detecting whether the hand is operating the gear operating lever.
  • the first auxiliary device is a touch sensing device and/or an auxiliary bracelet.
  • the ECG acquisition processing module includes an ECG acquisition module and a data processing module, and the ECG acquisition module is an internal circuit connected to the electrode, and collects an ECG signal through the electrode; the data processing module is used to The ECG signal is processed.
  • the electrodes are two strip electrodes, and the lengths are respectively close to the semicircle of the steering wheel.
  • the steering wheel sleeve is provided with one of the following devices:
  • a pressure detecting device is disposed in the steering wheel sleeve, and the pressure detecting device is connected to the main control module;
  • the steering wheel cover is further provided with a pulse wave sensor, and the pulse wave detecting device is connected to the main control module;
  • the steering wheel cover is further provided with a temperature sensor, and the temperature sensor is connected to the main control module;
  • the steering wheel cover is further provided with a skin sensor, and the skin sensor is connected to the main control module;
  • the steering wheel cover is further provided with a sweat sensor, and the sweat sensor is connected to the main control module;
  • the steering wheel cover is further provided with an environment multi-parameter detector, and the environment multi-parameter detector is connected to the main control module.
  • a miniature camera is connected to the main body of the device for obtaining facial features of the driver to determine the fatigue state of the driver;
  • An alcohol detecting device is further connected to the main body of the device, and the alcohol detecting device is connected to the main control module. even;
  • the device body leads an electronic switch to be connected to the ignition circuit of the automobile;
  • the device body further includes an alarm module, and the alarm module is connected to the main control module;
  • the device body further includes a remote communication module, and the remote communication module is connected to the main control module.
  • the second auxiliary device includes a patch type collecting device for collecting an EEG signal, and the second auxiliary device is wirelessly connected to the device body.
  • a vehicle driving behavior improvement system based on an in-vehicle terminal and a server end comprising the in-vehicle health and safety driving assistance device as described above, wherein the in-vehicle terminal directly transmits user data to the server end through an online or offline method, or through an intelligent terminal Indirectly transferred to the server.
  • the utility model has the beneficial effects that when the automobile is in a state of turning, shifting, etc., the driver may have a one-handed operation gap, the electrode cannot detect the ECG signal, and when the attitude sensor module detects that the automobile is in the above state, the main control The module will judge the normal driving operation, thereby effectively avoiding the situation that the driver's normal operation of the steering wheel while the vehicle is turning and shifting is judged to be a bad driving habit.
  • FIG. 1 is a schematic diagram of an in-vehicle health and safety driving assistance device according to Embodiment 1 of the present invention.
  • FIG. 2 is a block diagram showing the structure of a device body according to Embodiment 1 of the present invention.
  • Embodiment 3 is a method of ECG identification that can be employed in Embodiment 1 of the present invention.
  • Embodiment 4 is a first method of ECG identity authentication that can be employed in Embodiment 1 of the present invention.
  • FIG. 5 is a second method of ECG identity authentication that can be adopted in Embodiment 1 of the present invention.
  • Embodiment 6 is a third method of ECG identity authentication that can be employed in Embodiment 1 of the present invention.
  • Embodiment 7 is a blood pressure data calculation method applicable to Embodiment 7 of the present invention.
  • Fig. 8 is a configuration diagram of a vehicle driving behavior improvement system according to a fifteenth embodiment of the present invention.
  • the in-vehicle health and safety driving assistance device of the first embodiment includes a steering wheel cover and an apparatus main body 2.
  • the structure of the steering wheel cover can refer to the structural design of the common steering wheel cover, and the surface is covered with two elongated electrodes 1 as an external medium for collecting ECG signals in contact with the hand.
  • the elongated electrode 1 can increase the range of ECG signals that can be acquired in different driving actions and different grip steering positions.
  • the electrode 1 is preferably made of a conductive silica gel electrode, that is, a nickel-coated copper powder, a silver powder or the like is uniformly doped in the silica gel, and conductive graphite or acetylene black is also added.
  • the device body 2 is fixed to the inner side of the steering wheel by a snap.
  • the device body 2 includes a power supply module 23 , a main control module 22 , and an ECG acquisition processing module 20 including an ECG acquisition module 201 , a data processing module 202 , a storage module 21 , and an attitude sensor module 24 .
  • the power supply module 23 inside the device body 2 is used to supply power to the entire device.
  • the device in this embodiment will normally be in a standby state, and rely on the built-in rechargeable battery to maintain its navigation. In normal use, it is better to connect with the USB power supply port on the car through the USB cable to avoid the situation that the power is exhausted during use;
  • the ECG acquisition module 201 acts as an internal circuit connected to the electrode 1, and collects the heart through the electrode 1.
  • the data processing module 202 is configured to process the ECG signal, such as filtering processing, and the like;
  • the storage module 21 is configured to store and temporarily store the operational data of the user personal information, the usage record, and the like;
  • the main control module 22 functions as a device.
  • the brain controls the whole system, including data analysis for conversion to digital signals, such as analysis of posture data, ECG identity authentication, arrhythmia analysis, etc., combined with the analysis results to judge the abnormal situation of the driver, and the analysis and judgment results are recorded in In the storage module 21.
  • data analysis for conversion to digital signals such as analysis of posture data, ECG identity authentication, arrhythmia analysis, etc.
  • the ECG acquisition processing module 20 collects the driver's ECG signal through the electrode 1, and determines whether it is the owner or the owner authorized the driver through the ECG identity authentication. During the entire driving process, the ECG acquisition will continue, and the driver will be able to detect whether the driver is driving in both hands in real time through the signal acquisition. The collected ECG signals will also determine whether the ECG signal is abnormal through subsequent arrhythmia analysis. If the continuous time such as continuous arrhythmia events such as tachycardia is detected within 2 minutes, the main control module will judge the user itself. The body has a health hazard and the user data is recorded in the storage module 21.
  • the user can perform ECG identification and authentication through the data processing module by using any of the following ECG identification methods or three ECG identity authentication methods.
  • the data processing module is used to perform ECG identification:
  • the method for ECG identification is as shown in FIG. 3, and includes a model training phase and a real-time testing phase.
  • the model training phase includes the following steps: B1, preprocessing, and segment extraction: performing an ECG signal for training. Position acquisition, pre-processing the collected ECG signals, segmenting the pre-processed ECG signals to obtain multiple feature segments; B2, fully automatic feature extraction layer training: based on fully automatic extraction feature network pairs The feature segments are trained by the fully automatic feature extraction layer and the fully connected layer of the fully automatic extraction training module, and the fully automatic feature extraction layer after training is extracted as a feature extractor;
  • the real-time test phase includes the following steps: B3, pre- Processing and fragment extraction: the ECG signal to be identified is collected at any position, and the collected ECG signals are preprocessed, and the pre-processed ECG signals are extracted to obtain a plurality of feature segments; B4, features Identification: parallel feature extraction of the ECG signals to be identified by multiple feature extractors trained in the training phase of the model, Characterized taken parallel to
  • the preprocessing and fragment processing comprises the following steps: B5: filtering the ECG signal; B6: determining the length of the window including at least one ECG information on the intercepted ECG signal; B7: determining according to a good window length, a sliding window, and an ECG window of a corresponding length is cut from an arbitrary position of the ECG signal; B8: dividing the ECG window into a plurality of fixed length segments to obtain a plurality of the feature segments.
  • the segment length of the feature segment is less than or equal to the length of the electrocardiogram window.
  • the fully automatic feature extraction layer includes a plurality of convolution layers and a maximum pool layer
  • the method includes the following steps: B21: pairing the feature segments by using the plurality of convolution layers Performing parallel convolution to obtain a plurality of vector values; B22: a plurality of the vector values generate depth fusion features through the maximum pool layer; B23: the depth fusion features are trained and classified by the fully connected layer, and output classification is determined
  • the fully automatic feature extraction layer is extracted as the feature extractor based on the classification judgment result.
  • step B23 when the training recognition rate is greater than the threshold, the training is stopped, the depth fusion feature is extracted, and the fully automatic feature extraction layer composed of the depth fusion feature is extracted as Feature extractor, otherwise continue training.
  • step B2 according to the collection condition of the ECG signal in the step B1, if the ECG signal can be continuously collected, the fully automatic feature extraction layer is further trained, and when the threshold is reached, the original feature extractor is replaced. .
  • step B4 the method includes the following steps: B41, feature extraction, performing parallel feature extraction on the ECG signals to be recognized according to the plurality of feature extractors, and obtaining a depth fusion feature of the ECG signal to be identified.
  • B42. Feature classification, the depth fusion feature of the ECG signal to be identified is classified in parallel by a plurality of classifiers according to the category number of the ECG signal to be identified, and the identity recognition is completed.
  • the classifier in the model training phase, is a nonlinear classifier, and further includes training the nonlinear classifier, including: the depth fusion feature extracted in step B41.
  • the category number above trains the predetermined nonlinear classifier using a nonlinear classifier training module.
  • step B4 the identification is performed by a plurality of non-linear classifiers for preliminary identification, and the step of performing a final identification process by feature voting: voting with the highest entropy, statistical preliminary identity
  • the entropy value of each category in the identification is determined, and the category number corresponding to the maximum entropy value is used as the final recognition result according to the calculated entropy value.
  • the first method used by the data processing module to perform ECG authentication is the first method used by the data processing module to perform ECG authentication:
  • the method for authenticating the ECG is as shown in FIG. 4, and includes a pre-processing step, a feature extraction step, and an authentication step, wherein the pre-processing step includes filtering the ECG signal collected by the electrode to eliminate interference.
  • the feature extraction step includes detecting each reference point in the electrocardiographic signal to extract a quasi-periodic heart beat signal as the original electrocardiographic feature, and performing segmentation waveform correction on the heart beat, and then using the PCA dimension reduction and extracting the coefficient feature as The final ECG feature, the authentication step includes using a template matching based method to determine if the test sample is successfully authenticated.
  • the respective reference points include a P wave start point (Ps), a P wave end point (Pe), an R wave peak (R), a J wave start point (J), a T wave peak (Tp), and a T of the heart beat.
  • Wave end point (Te) in the feature extraction step, the reference point detection and the waveform segmentation are performed by:
  • the ECG signal determines the position of the R wave of the heart beat by wavelet transform, or determines the rough position of the R wave of the heart beat by the minimum value of the second-order differential signal of the ECG signal, and then determines the rough position of the R wave.
  • the point at which the first-order differential signal is closest to zero, and the position of the R-peak (R) is located accordingly;
  • T peak Tp
  • Tp T-wave end point
  • segmentation waveform correction is performed by segmentation resampling the heartbeat signal, wherein each P-band is upsampled, and the P-band duration is extended after upsampling.
  • the duration of each P-band is unified to 460-500 milliseconds; the duration of each QRS band remains unchanged; for each T-band, the J-Tp segment and the Tp-Tp segment are down-sampled respectively, so that each T-band is resampled
  • the length of each of the two segments is unified to 10-20 milliseconds.
  • PAC(X) is a PCA dimensionality reduction for the signal X after the waveform
  • LDA is a linear discriminant analysis for the signal X after the waveform
  • DCT is a discrete cosine transform of the signal X after the waveform.
  • each axis coefficient whose retention contribution rate is above a set threshold is extracted as a coefficient feature, and the set threshold is preferably 99%.
  • the second method used by the data processing module to perform ECG authentication is the second method used by the data processing module to perform ECG authentication:
  • the method for authenticating the ECG is as shown in FIG. 5, and the steps include: including ECG extraction and ECG authentication, the ECG extraction includes: C11, preprocessing the ECG signal collected by the electrode, and detecting the R wave Position, intercept QT band; C12, the intercepted QT band adopts autocorrelation transform algorithm for feature extraction, and obtain ECG autocorrelation sequence; C13, the acquired ECG autocorrelation sequence is reduced by orthogonal polynomial fitting regression, Generating a feature template; C14, selecting and evaluating an optimal ECG feature template from the generated feature template; C15, obtaining an optimal threshold from the ECG optimal feature template.
  • the ECG certification includes: C21, preprocessing the electrocardiographic signal collected by the electrode, detecting the R wave position, and intercepting the QT band; C22, extracting the extracted QT band using an autocorrelation transform algorithm to obtain the ECG self-correlation Correlation sequence; C23, the obtained ECG autocorrelation sequence is subjected to dimensionality reduction by orthogonal polynomial fitting regression to generate a feature template; C24, the generated feature template is compared with the ECG optimal feature template, according to the best The threshold completes the authentication.
  • the dimension reduction generation feature template described by the orthogonal polynomial fitting regression described in step C14 or step C24 is obtained by approximating the ECG autocorrelation sequence by a polynomial, and the representation by the feature template is obtained.
  • the ECG autocorrelation sequence is described.
  • the polynomial is a 0 + a 1 f 1 (x i ) + a 2 f 2 (x i ) + ...
  • A (a 0 , a 1 , a 2 , ..., a k ) T
  • F i (1, f 1 (x i ), f 2 (x i ), ..., f k (x i )) T
  • i 0, 1, 2, 3, ..., M-1, where 1, f 1 (x i ), f 2 (x i ), ..., f k ( x i ) are 0 times, 1 time, 2 times, ..., k times orthogonal polynomials of x, respectively which is f is the sampling frequency of the ECG signal.
  • the ECG optimal feature template described in step C15 is obtained by using the leave-one method, and the discriminant is Where D(A i , A j ) represents a distance metric between the feature vector A i and the feature vector A j ; Indicates that 1 is taken when the distance between the feature A i and the feature A j is less than the preset threshold THD, otherwise 0 is taken; the value of THD is the average value of the distance between the n feature vectors, and i, j is 1 to n. I ⁇ j.
  • the third method used by the data processing module to perform ECG authentication is the third method used by the data processing module to perform ECG authentication:
  • the method for authenticating the ECG is as shown in FIG. 6.
  • the steps include: D1: pre-processing the collected ECG signals in the pre-processing and intercepting QT wave module, detecting the R wave position, and intercepting the QT wave;
  • the intercepted QT wave generates a sparse feature by using a differentiated dictionary learning algorithm for sparse representation in multiple ECG feature extraction and data processing modules;
  • D3 the generated sparse feature is fuzzy matched in the template matching module based on the optimal threshold, and is completed.
  • Initial certification after which the certification is completed based on the highest entropy vote.
  • step D2 is performed prior to said preliminary authentication in step D3
  • the sparse feature is compressed in the plurality of ECG feature extraction and data processing modules and transmitted to the third-party authentication device, and then decompressed into the sparse feature described in step D2.
  • the distinguishing dictionary learning algorithm for sparse representation described in step D2 comprises:
  • J (D, C) is the solved dictionary D and the sparse feature C
  • Verif (X i , X j , D, C i , C j ) is the feature distinguishing attribute
  • ⁇ is the sparsity degree coefficient
  • ⁇ is the regularization.
  • the coefficients, ⁇ and ⁇ have values ranging from 0 to 1;
  • X i and X j represent the i-th and j-th QT waves, respectively, and C i and C j represent the sparse features corresponding to X i and X j , respectively.
  • dm is a minimum distance between the different types of settings, label (X i) X i represents the class number;
  • X (X 1 , X 2 , . . . , X n ) represents n QT waves;
  • D (d 1 , d 2 , . . . , d l ) represents the dimension of the dictionary, and l is greater than 1 Any value;
  • T represents transpose of matrices.
  • the search process for the optimal threshold described in step D3 is to search using Euclidean distance, which is based on frequency.
  • the attitude sensor module 24 used in this embodiment is a nine-axis sensor, and the current driving state can be judged by the collected attitude data, and the driving state includes straight running, turning, rapid acceleration, sudden braking, and the like. When it is determined that there is frequent sudden acceleration, sudden braking, etc. during driving, it will be recorded as a bad driving habit.
  • the running state is straight and non-shifting state
  • the user operates the steering wheel or hands to leave the steering wheel with one hand, and if the electrocardiographic signal is not detected by the electrode 1 after a certain time (for example, 15s), the main control module 22 judges that the driving is poor. Habitually, and recorded in the storage module 21. When the car turns, the driver's hands are on the steering wheel.
  • the electrode 1 cannot detect the ECG signal, and when the posture sensor module 24 detects that the driving state is a turning, the main control module 22 judges.
  • the attitude sensor 24 can be used to judge the speed change of the car itself. If the speed changes beyond a certain threshold, it is considered that the shift operation is at this time.
  • the control module 22 determines that it is a normal driving operation.
  • Embodiment 2 is to increase the accuracy of the driving behavior judgment, the in-vehicle health and safety driving assistance device further includes a first auxiliary device; the device body 2 further includes a wireless transmission module, and the wireless transmission module is connected to the main control module 22 for User data is sent to the intelligent terminal and receives monitoring data transmitted by the first auxiliary device.
  • the first auxiliary device can be a touch sensing device. For example, a touch sensor and a corresponding power supply and wireless transmission part are added on the top of the gear lever, and when a hand touch is detected, a signal is transmitted to the apparatus body 2 by wireless, and during this period, it is judged as a normal driving operation.
  • the touch sensor can detect the contact between the hand and the gear lever by pressure detection of the pressure sensor or by the photoelectric sensor being blocked by light.
  • the first auxiliary device can be an auxiliary bracelet. Wearing a wristband in a one-handed wrist, an attitude sensor is used to detect the state of the hand in the wristband, and when the one-handed motion is detected to comply with the action of the operating gear operating lever, the wristband sends a signal to the main body 2 through the wireless transmission portion. During this period of time, it is a normal driving operation.
  • the first auxiliary device may also be a combined application of the two.
  • a pulse wave sensor is further disposed on the auxiliary wristband for detecting pulse wave information at the wrist.
  • the wristband transmits the pulse wave information to the device body 2 wirelessly, and the master control module 22 of the device body 2 determines the driver's health condition. Since the hands often move on the steering wheel while driving, many times the touch sensing area on the steering wheel cover cannot sense the corresponding finger contact, and the physiological condition information cannot be collected.
  • the pulse wave sensor on the wristband ensures that the pulse wave signal acquisition is completed throughout the driving process.
  • the vehicle health and safety driving assistance device can transmit the user data to the intelligent terminal through the wireless transmission module.
  • the smart terminal can be a user's mobile phone, a tablet, a car mobile device, or a general-purpose computer. Users can transfer their personal data to the smart terminal for viewing in real time.
  • the steering wheel cover of Embodiment 3 is provided with a pressure detecting device for collecting the steering force of the driver's hand.
  • a pressure detecting device for collecting the steering force of the driver's hand.
  • heart rate variability analysis is performed on the collected ECG signals, and the driver's fatigue is given a comprehensive evaluation in combination with the steering wheel pressure.
  • the pressure detecting device also serves as a triggering device for the on-board health and safety driving assistance device from standby to normal operation. For example, when the driver holds the steering wheel to prepare the vehicle to start, the pressure detecting device detects additional pressure. Activate the entire device to start work, and then start follow-up work, such as identity verification through ECG detection.
  • Embodiment 4 is to increase the fatigue detection accuracy, and obtain more driver physiological information for safe and healthy judgment, and further includes a second auxiliary device for performing brain electrical detection.
  • a patch-type acquisition device with a wireless transmission module the driver can attach the acquisition device to the head, activate the device, and collect brain electrical signals.
  • the collected EEG signals are wirelessly transmitted to the device body 2, and subsequent EEG signal analysis is performed to judge the driver's fatigue level.
  • EEG signals can also make predictions and judgments on brain diseases.
  • the device body 2 of Embodiment 5 is further connected with a micro camera such as an infrared sensitive CCD camera to capture the driver's face to acquire an image, and filters the influence of visible light through an infrared band pass filter.
  • a micro camera such as an infrared sensitive CCD camera to capture the driver's face to acquire an image, and filters the influence of visible light through an infrared band pass filter.
  • An alcohol sensor such as an MQ-3 alcohol sensor is further connected to the apparatus main body 2 of Embodiment 6 to conveniently collect the gas exhaled by the driver.
  • the purpose is to detect the concentration of alcohol gas exhaled by the driver.
  • the alcohol sensor 3 output can be input to the main control module 22 through the AD converter.
  • the alcohol sensor 3 will perform multiple tests within a certain period of time (such as 2 minutes) when the car is started, and the average value is taken as the detection result. If the threshold value is exceeded, it will be judged as drunk driving; since drunkenness often leads to an increase in heart rate, real-time ECG detection The result will also be used as a reference in the judgment of drunk driving.
  • the steering wheel cover of Embodiment 7 is provided with a pulse wave sensor for collecting driver pulse wave signal data. Since the position of the steering wheel is constantly changing during driving, in order to collect the pulse wave signal data to the maximum extent, the embodiment respectively sets a pulse wave sensor on both sides of the steering wheel, and the pulse wave sensor is adjacent to the touch sensor, and the touch sensor senses The signal is sent when the finger touches, and the pulse wave sensor starts to work to acquire the pulse wave signal data.
  • the collected pulse wave data can obtain health parameter information such as pulse, blood pressure and blood oxygen saturation of the driver through subsequent data analysis, and the main control module 22 comprehensively judges the health status of the driver.
  • the blood pressure data of the user can be obtained by the data processing module using the following calculation method for obtaining blood pressure data based on the pulse wave data.
  • the blood pressure data calculation method is as shown in FIG. 4, and includes the steps of establishing a plurality of regression equations and calculating a blood pressure value, wherein the steps of establishing a plurality of regression equations include: A11, acquiring a pulse wave and a corresponding blood pressure value; A12, The pulse wave obtained by the preprocessing; A13, extracting the pulse wave feature point from the preprocessed pulse wave, and acquiring the global characteristic parameter value of the pulse wave; A14, using the acquired global characteristic parameter value of the pulse wave and Corresponding blood pressure values are established by randomly selecting a set of regression test sets consisting of a test set and a training set; A15, obtaining a global optimal regression equation for each set of regression test sets; A16, evaluating and screening out A high-accuracy regression equation; A17, assigning a corresponding weight to the highly accurate regression equation; the steps of calculating the blood pressure value include: A21, acquiring a pulse wave; A22, preprocessing the collected pulse wave; A23, from the pre
  • the globally optimal regression equation is obtained in step A15 using stepwise regression analysis; the stepwise regression analysis analyzes the training set in a global traversal manner.
  • the pulse wave feature points described in step A13 or step A23 include an aortic valve open point, a systolic maximum pressure point, a heavy beat wave start point, and a heavy beat wave highest pressure point;
  • the wave feature points include smoothing processing of the pulse wave, and the smoothing processing adopts a three-point line smoothing process.
  • the step of extracting the aortic valve opening point and the systolic maximum pressure point comprises: a1. acquiring all generalized extreme points of the pulse wave and obtaining an extreme point set; b1. determining an aortic valve opening point, The threshold value of the highest pressure point difference in the systolic period; c1. The pulse opening point and the highest pressure point in the systolic period are determined and extracted according to the threshold value.
  • the extreme point judgment condition in step a1 is: (Pc[i] - Pc[i-1]) * (Pc[i+1] - Pc[i]) ⁇ 0, Pc represents the beat wave data point.
  • the discriminant formula for determining and extracting the pulse opening point and the systolic maximum pressure point according to the threshold is ext[i+1]-ext[i]>thd, 1 ⁇ i ⁇ len-1, Ext[i] represents the ith extreme point, ext[i+1] represents the i+1th extreme point, thd represents the threshold of the aortic valve opening point, the highest pressure point difference during systole, and len represents the extreme value.
  • the steps of extracting the starting point of the beat wave and the highest pressure point of the beat wave wave include: a2, a period interval of dividing the pulse wave; b2, determining a starting point of the beat wave, and a highest pressure point of the beat wave. a pulse wave period interval; c2, extracting the starting point of the beat wave by calculating a set of average slope angle change index values of each point in the pulse wave period interval where the peak of the beat wave and the highest pressure point of the beat wave are located, Heavy stroke The highest pressure point of the wave.
  • acquiring the pulse wave global feature parameter value in step A13 or step A23 includes removing the outlier value and averaging each feature parameter set for removing the outlier value;
  • the pulse wave global feature parameter value includes global Systolic time ratio, global main wave height, global relative gorge relative height, global tremor wave relative height, global systolic area ratio, global main wave rising slope and global K value; The Weiler method is carried out.
  • the expression of the regression equation is where param is the set of final selection parameters, coef is the set of corresponding parameters of each parameter, cont is a constant term, lenParam is the number of selected parameters, and BPest is the estimated blood pressure value.
  • the steering wheel cover of Embodiment 8 is provided with a temperature sensor for detecting the body temperature of the driver and transmitting the collected body temperature information to the main control module.
  • the steering wheel cover of Embodiment 9 is provided with a skin sensor for collecting skin information of the driver and transmitting the collected skin information to the main control module.
  • skin properties such as dry skin, oily skin, neutral skin, etc. can be obtained, and information such as the degree of skin aging can also be obtained.
  • the RGB white light, the PL polarized light and the UV ultraviolet light emitting and imaging device are added on the front side, and the user RGB high-precision image, the PL high-precision image and the UV high-precision image are collected, and the user skin information can be obtained through the comprehensive analysis of the three spectra.
  • the sensor is slightly recessed inwardly to allow for a larger area of skin image to be acquired for improved analysis accuracy.
  • the steering wheel cover of the embodiment 10 further includes a sweat sensor for collecting various physiological parameter data in the driver's sweat, and transmitting the collected physiological parameter data to the main control module.
  • the sweat sensor measures glucose in the sweat, allowing the device to acquire the user's blood glucose data in a non-invasive manner. It can further detect electrolytes, sodium, lactic acid and protein in sweat to give some indications of the physical condition. Standard. For example, combined with an analysis algorithm, remind users when they need to replenish water, how much they need to drink, whether they should drink water or drink sports drinks. In addition, the quality of the collected ECG/EEG signal can also be evaluated accordingly. When the electrolyte content is high, the conductivity is better, and the collected ECG/EEG signals are more accurate.
  • the steering wheel cover of Embodiment 11 is further provided with an environmental multi-parameter detector, the environment detector comprising a temperature and humidity sensor, an optical sensor and an optical air quality sensor for detecting environmental parameters and transmitting the environmental parameter data to the main Control module.
  • the temperature and humidity sensor can be selected from a resistive type and a capacitive type.
  • the intensity of the ultraviolet light can be measured by embedding the optical sensor.
  • the optical air quality sensor By embedding the optical air quality sensor, the intensity of the ambient light as well as the amount and size of the respirable particles as well as the air mass concentration can be determined.
  • the laser sensor is selected.
  • the sensor is composed of a red laser and a diode. The laser sensor generates a specific laser beam.
  • the signal is detected by the ultra-sensitive digital circuit module, and the signal data is intelligent.
  • the particle count and particle size are obtained by recognition and analysis.
  • the particle size distribution and the mass concentration conversion formula are obtained, and the mass concentration unified with the official unit is finally obtained.
  • the detected data is sent to the intelligent terminal by using the wireless transmission module, and the environment analysis report can be seen through the analysis of the application. Users can use air quality to plan their own activities, such as not choosing to go out when air pollution is serious.
  • the apparatus body 2 of Embodiment 12 also leads to an electronic switch connected to the vehicle ignition circuit.
  • the electronic switch can only be turned on when the identity authentication passes, and the electronic switch connected to the ignition circuit can be started normally, otherwise the car will always be in an unfired state and play the purpose of anti-theft.
  • the device body 2 of Embodiment 13 further includes an alarm module, and the alarm module is connected to the main control module 22 for reminding and alerting the user or attracting attention of the surrounding people.
  • the alarm module is controlled to perform an alarm, including: identity authentication failure; alcohol concentration exceeds a certain degree; fatigue driving; abnormal electrocardiogram information or abnormal health condition; single straight and non-shift operation Leave the steering wheel with your hands or hands for more than a certain amount of time.
  • the alarm module can flash an alarm for the speaker or LED.
  • the device body 2 of Embodiment 14 further includes a remote communication module, such as a sim card installed, for data transmission through 3G, 4G.
  • a remote communication module such as a sim card installed, for data transmission through 3G, 4G.
  • an emergency contact can be set to automatically send a message to the emergency contact in the event of an abnormal condition.
  • Insurance companies can automatically obtain user driving information in real time through remote information transmission, without the need for users to manually upload operations, and remotely remind users of bad driving habits in real time to promote safe driving.
  • Embodiment 15 is shown in FIG. 8 as an improvement of driving behavior of a vehicle based on a vehicle terminal and a server.
  • the system, the in-vehicle terminal includes the in-vehicle health and safety driving assistance device as described above.
  • insurers can require users to copy the stored user data and judgments to a designated location at a fixed time (such as three months), and extract the evaluation of the users, especially It is the alarm situation and the driving status and physiological information at that time, so that the user's driving habits are evaluated, and the amount of the next period premium is judged. Upload and save user data and evaluation results on the server side. Users have the option to improve driving habits based on changes in premiums.
  • the user can also choose to wirelessly transmit the data to the intelligent terminal first, and the smart terminal can connect to the Internet through a wireless local area network (such as WIFI), or directly transmit to the insurance by using a remote communication method (such as 3G, 4G). Enterprise server side.
  • WIFI wireless local area network
  • a remote communication method such as 3G, 4G.
  • Enterprise server side the insurance company's adjustment of user premiums is mainly based on the number of vehicle accidents, and the information on user driving habits can fundamentally reflect the trend of vehicle risk, which has important reference significance for insurance companies to determine premiums.
  • the probability of compensation is also reduced.
  • the ultimate goal is to promote the development of good driving habits.

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Veterinary Medicine (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Physics & Mathematics (AREA)
  • Public Health (AREA)
  • Pathology (AREA)
  • Physiology (AREA)
  • Cardiology (AREA)
  • Artificial Intelligence (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Psychiatry (AREA)
  • Signal Processing (AREA)
  • Pulmonology (AREA)
  • Dentistry (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)

Abstract

L'invention concerne un dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule, comprenant : un couvercle de volant, qui adhère à un volant d'un véhicule et qui est caractérisé en ce qu'une électrode (1) est disposée sur une surface du couvercle de volant en vue d'agir en tant que milieu externe destiné à être utilisé dans la collecte d'un signal d'électrocardiogramme ; et un corps principal d'équipement (2) qui est fixé au volant, une partie interne du corps principal d'équipement comprenant un module d'alimentation électrique (23), un module de commande principal (22), un module de collecte et de traitement d'électrocardiogramme (20), un module de stockage (21) et un module de capteur de posture (24) ; le module d'alimentation électrique (23) est chargé de fournir de l'électricité à l'ensemble du dispositif ; le module de commande principal (22) est connecté au module de collecte et de traitement d'électrocardiogramme (20), au module de stockage (21) et au module de capteur de posture (24) respectivement ; le module de collecte et de traitement d'électrocardiogramme (20) est également connecté à l'électrode (1). Comme le module de capteur de posture (24) peut déterminer un état de fonctionnement, en combinant ce dernier avec le module de collecte et de traitement d'électrocardiogramme (20), la détection de la posture de conduite d'un conducteur est plus raisonnable et précise, ce qui permet d'empêcher efficacement la situation dans laquelle il est déterminé que le maniement normal d'un volant par un conducteur est une mauvaise habitude de conduite lors de la rotation d'un véhicule ou lors d'un changement de vitesse.
PCT/CN2017/074438 2017-02-22 2017-02-22 Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule WO2018152712A1 (fr)

Priority Applications (2)

Application Number Priority Date Filing Date Title
PCT/CN2017/074438 WO2018152712A1 (fr) 2017-02-22 2017-02-22 Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule
CN201780001970.5A CN107979985B (zh) 2017-02-22 2017-02-22 一种车载健康安全驾驶辅助装置

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2017/074438 WO2018152712A1 (fr) 2017-02-22 2017-02-22 Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule

Publications (1)

Publication Number Publication Date
WO2018152712A1 true WO2018152712A1 (fr) 2018-08-30

Family

ID=62006231

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/074438 WO2018152712A1 (fr) 2017-02-22 2017-02-22 Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule

Country Status (2)

Country Link
CN (1) CN107979985B (fr)
WO (1) WO2018152712A1 (fr)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108437792A (zh) * 2018-05-17 2018-08-24 滨州学院 预防酒后驾驶的装置和方法
CN108583674A (zh) * 2018-06-09 2018-09-28 深圳市中智仿真科技有限公司 一种具有体征监测功能的方向盘
CN109410524B (zh) * 2018-12-06 2021-07-09 四川大学锦城学院 一种驾驶员疲劳监测系统及其监测方法
CN111488964B (zh) * 2019-01-29 2024-07-16 北京市商汤科技开发有限公司 图像处理方法及装置、神经网络训练方法及装置
CN109858178A (zh) * 2019-02-26 2019-06-07 重庆交通大学 一种基于智能手环的营运车辆驾驶员疲劳预警方法
US10776643B1 (en) * 2019-08-28 2020-09-15 Robert Bosch Gmbh Vehicular airborne particulate matter detection system
CN110477888A (zh) * 2019-09-25 2019-11-22 江苏启润科技有限公司 车载人体多参数监测终端
CN110720904A (zh) * 2019-11-11 2020-01-24 沃立(常州)医疗科技有限公司 车载用心电信号采集装置
CN113071504A (zh) * 2021-05-12 2021-07-06 嘉兴温芯智能科技有限公司 驾驶员脱手和健康检测方法、装置、方向盘和保护套
CN113274029A (zh) * 2021-05-25 2021-08-20 安徽安凯汽车股份有限公司 一种客车驾驶员生命体征信息监测系统
CN113693578B (zh) * 2021-08-26 2024-06-14 中国第一汽车股份有限公司 一种心率估计方法、装置、设备、系统及存储介质
CN113834994B (zh) * 2021-10-27 2024-06-18 均胜均安汽车电子(上海)有限公司 一种离手检测方向盘的模拟触摸装置

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030142041A1 (en) * 2002-01-30 2003-07-31 Delphi Technologies, Inc. Eye tracking/HUD system
US6822573B2 (en) * 2002-01-18 2004-11-23 Intelligent Mechatronic Systems Inc. Drowsiness detection system
CN102490701A (zh) * 2011-12-02 2012-06-13 哈尔滨工业大学 一种可监控驾驶者身体和心理状态的安全驾驶监控装置
CN103021134A (zh) * 2012-12-10 2013-04-03 郭文浩 汽车疲劳驾驶监测报警装置
CN203995930U (zh) * 2014-01-06 2014-12-10 沈青云 一种公交车安全动作识别预警装置

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI511092B (zh) * 2013-03-27 2015-12-01 原相科技股份有限公司 用於載人行動載具的安全監控裝置及安全監控方法
JP6422058B2 (ja) * 2015-04-15 2018-11-14 本田技研工業株式会社 把持検出装置
CN105522962B (zh) * 2015-12-29 2018-01-09 徐承柬 一种脱手驾驶行为提醒系统
CN106379320A (zh) * 2016-09-06 2017-02-08 浙江吉利控股集团有限公司 一种车辆安全驾驶提醒系统及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US6822573B2 (en) * 2002-01-18 2004-11-23 Intelligent Mechatronic Systems Inc. Drowsiness detection system
US20030142041A1 (en) * 2002-01-30 2003-07-31 Delphi Technologies, Inc. Eye tracking/HUD system
CN102490701A (zh) * 2011-12-02 2012-06-13 哈尔滨工业大学 一种可监控驾驶者身体和心理状态的安全驾驶监控装置
CN103021134A (zh) * 2012-12-10 2013-04-03 郭文浩 汽车疲劳驾驶监测报警装置
CN203995930U (zh) * 2014-01-06 2014-12-10 沈青云 一种公交车安全动作识别预警装置

Also Published As

Publication number Publication date
CN107979985A (zh) 2018-05-01
CN107979985B (zh) 2021-02-23

Similar Documents

Publication Publication Date Title
WO2018152712A1 (fr) Dispositif d'aide à la conduite de santé et de sécurité, monté sur véhicule
Wang et al. Channel selection method for EEG emotion recognition using normalized mutual information
CN109726771B (zh) 异常驾驶检测模型建立方法、装置及存储介质
CN110276273B (zh) 融合面部特征与图像脉搏心率估计的驾驶员疲劳检测方法
Reddy et al. Real-time driver drowsiness detection for embedded system using model compression of deep neural networks
Kong et al. A system of driving fatigue detection based on machine vision and its application on smart device
CN110151203B (zh) 基于多级雪崩式卷积递归网络eeg分析的疲劳驾驶识别方法
EP2698112B1 (fr) Détermination de contraintes en temps réel d'un individu
US20090062679A1 (en) Categorizing perceptual stimuli by detecting subconcious responses
CN111797662A (zh) 评估驾驶者的疲劳分数的方法
CN110123314A (zh) 基于脑电信号判断大脑专注放松状态的方法
Hayawi et al. Driver's drowsiness monitoring and alarming auto-system based on EOG signals
CN109009017A (zh) 一种智能健康监测系统及其数据处理方法
CN109875584A (zh) 驾驶员生理疲劳的检测方法及其警报系统
CN111553617A (zh) 基于虚拟场景中认知力的操控工效分析方法、设备及系统
CN109567832A (zh) 一种基于智能手环的检测愤怒驾驶状态的方法及系统
CN109840451A (zh) 一种基于心电身份识别的智能支付可穿戴环及其支付方法
CN109875583A (zh) 一种基于ar技术的疲劳驾驶检测系统及方法
Ukwuoma et al. Deep learning review on drivers drowsiness detection
CN117520826B (zh) 一种基于可穿戴设备的多模态情绪识别方法及系统
CN111281403B (zh) 一种基于嵌入式设备的细粒度人体疲劳检测方法及设备
Zhou et al. An Improved Random Forest Algorithm-Based Fatigue Recognition with Multi-Physical Feature
Utomo et al. Driver fatigue prediction using different sensor data with deep learning
KR20200061016A (ko) 얼굴 피부 영상을 이용한 우울증 지수 측정 및 진단 방법
CN114492656A (zh) 一种基于计算机视觉和传感器的疲劳度监测系统

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17898247

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17898247

Country of ref document: EP

Kind code of ref document: A1