CN106297194A - A kind of fatigue drive of car monitoring system - Google Patents
A kind of fatigue drive of car monitoring system Download PDFInfo
- Publication number
- CN106297194A CN106297194A CN201610891026.9A CN201610891026A CN106297194A CN 106297194 A CN106297194 A CN 106297194A CN 201610891026 A CN201610891026 A CN 201610891026A CN 106297194 A CN106297194 A CN 106297194A
- Authority
- CN
- China
- Prior art keywords
- signal
- module
- filter
- electric capacity
- fatigue
- Prior art date
- Legal status (The legal status 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 status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/02—Alarms for ensuring the safety of persons
- G08B21/06—Alarms for ensuring the safety of persons indicating a condition of sleep, e.g. anti-dozing alarms
-
- 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
- A61B5/024—Detecting, measuring or recording pulse rate or heart rate
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/08—Detecting, measuring or recording devices for evaluating the respiratory organs
-
- 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
- A61B5/725—Details of waveform analysis using specific filters therefor, e.g. Kalman or adaptive filters
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Public Health (AREA)
- Pathology (AREA)
- Veterinary Medicine (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Molecular Biology (AREA)
- Physiology (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Biophysics (AREA)
- Cardiology (AREA)
- Pulmonology (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Signal Processing (AREA)
- Measuring Pulse, Heart Rate, Blood Pressure Or Blood Flow (AREA)
Abstract
The invention discloses a kind of fatigue drive of car monitoring system, doppler radar unit for detecting physiological driver's signal intensity is installed in driver's cabin, doppler radar unit includes doppler radar sensor, power module, signal pre-processing module, difference amplifier, active band-pass filter, breathe and heartbeat signal separation module and MCU module, wherein, doppler radar sensor is for launching continuous wave radar signal output low frequency signal to torso model, low frequency signal is successively after multilevel signal processes, MCU module obtains human body respiration signal and heartbeat signal and the change according to breath signal and heartbeat signal judges whether driver is in fatigue driving state.Compared with prior art, present invention firstly provides the degree of fatigue using Doppler measurement technique monitoring driver, and increase detection steering wheel angle information in systems, processed by multi-source information and improve fatigue driving certainty of measurement.
Description
Technical field
The present invention relates to fatigue driving monitoring field, particularly relate to a kind of fatigue drive of car based on bio-signal acquisition
Monitoring system.
Background technology
Fatigue driving is to cause one of modal reason of vehicle accident in the world.According to WHO's (World Health Organization (WHO))
Report, the people having more than 1,300,000 every year dies from vehicle accident, has the people of 2,000 ten thousand to 5 thousand ten thousand because vehicle accident suffers non-lethal
Injury.Wherein, the fatal traffic accident of about 20% is caused by fatigue driving.If it is possible to research and development are a kind of certainly
The system of dynamic detection fatigue driving, it is possible to avoid substantial amounts of death by accident.
In order to prevent the generation of this kind of accident, the system of effective monitoring fatigue driving is necessary, can be in thing
Therefore remind driver before occurring, such that it is able to avoid or reduce the generation of this type of vehicle accident.Driving fatigue is mental, physical
The technical fatigue simultaneously participated in.Due to driver's action repeatedly, continuously, and the number of times repeated is too many so that it is physiology, psychology
Certain change of upper generation, occurs driving the phenomenon that function is low, mainly shows as distractibility, doze off, and the visual field narrows, letter
Breath leakage is seen, reaction and judgement is blunt, and driver behavior is slipped up or completely loses driving ability.
In existing research, many research worker all think that following physiological signal can be used to detection fatigue, including: electroencephalogram
(EEG), electrocardiogram (ECG), electro-oculogram (EOG), breath signal and electrodermal activity (EDA) etc..Test proves, uses physiology
The reliability of the degree of fatigue of signal detection driver and degree of accuracy are the highest, because it can reflect driver really
The situation of body interior.Meanwhile, physiological signal will change at tired commitment, and therefore using physiological signal is inspection
Survey the most suitable method of fatigue driving and error rate is low, make in this way can alerting drivers timely, thus reduce
Many road traffic accidents.But, prior art physiological detection generally uses the mode of contact measurement, and these technology need
Adhesive electrodes with driver, and this is also unpractical while being typically to be disliked by driver.
In order to overcome above-mentioned technological deficiency, Doppler radar technique realizes contactless bio-signal acquisition becomes ability
Territory study hotspot.Doppler radar, has another name called pulse Doppler radar, is usually operated at pulse-triggered pattern, is that a kind of utilization is many
General Le effect detects the position of moving target and the radar of speed of related movement.In prior art, Doppler radar is widely used in
Military field and civil area, such as airborne early warning, navigation, missile guidance, Satellite Tracking, battle reconnaissance, target range measurement, weapon
Etc. military aspect, and human body sensing, gate control system, test the speed the civil areas such as range finding.But, due to the spy of bio-signal acquisition
Different property, it is difficult to general for prior art doppler radar module is directly applied to bio-signal acquisition;Because breathing and heart beating being believed
Number the faintest, it is easy to be submerged in noise and the clutter of radar, use prior art Doppler radar routine application circuit
The contactless detection of the vital signss such as the breathing to human body and heart beating cannot be realized.Therefore, those skilled in the art are the most logical
Accuracy of identification and the sensitivity of crossing improvement radar reach to apply requirement, this considerably increases and realize difficulty, cost on also simultaneously
It is greatly improved.
Therefore, for drawbacks described above present in currently available technology, it is necessary to study in fact, to provide a kind of scheme,
Solve defect present in prior art.
Summary of the invention
In view of this, necessary offer a kind of fatigue drive of car monitoring system, general Doppler radar is applied to
Fatigue driving detects, and is operated in continuous wave mode and carries out signal processing by multi-stage filter circuit, thus realizing driving
The non-contact detection of member's physiological signal, and then judge whether fatigue driving.
In order to overcome the defect of prior art, technical scheme is as follows:
A kind of fatigue drive of car monitoring system, is provided with for detecting physiological driver's signal intensity in driver's cabin
Doppler radar unit, described doppler radar unit includes that doppler radar sensor, power module, signal are pre-
Processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module and MCU module, wherein, described
Power module is used for system power supply;Described doppler radar sensor is for launching continuous wave radar signal to torso model and connecing
Receiving output-response human body respiration and the low frequency signal of heart beating change after echo-signal processes, described low frequency signal is successively through institute
State signal pre-processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module and MCU module letter
After number processing, described MCU module obtains human body respiration signal and heartbeat signal and according to described breath signal and heartbeat signal
Change judges whether driver is in fatigue driving state;
Described signal pre-processing module includes voltage follower and passive filter, and described voltage follower is for input
Signal carries out voltage follow, and described passive filter is for filtering the DC component in input signal;
Described difference amplifier is for being amplified input signal and eliminating common-mode noise;
Described active band-pass filter is for being amplified input signal and eliminating differential mode noise;
Described breathing and heartbeat signal separation module include voltage movement circuit, analog-digital converter and digital filter, institute
State voltage movement circuit for the voltage range by the voltage movement of input signal to applicable digital-to-analogue conversion;Described analog-digital converter
For analog quantity being converted into discrete digital quantity;Described digital filter uses digital filtering technique at frequency domain to breath signal
Separate with heartbeat signal.
Preferably, described doppler radar unit also includes acousto-optic warning module, described acousto-optic warning module and institute
State MCU module to be connected, when described MCU module judges that driver is in fatigue driving state, control described acousto-optic warning mould
Block sends sound and light alarm signal.
Preferably, described MCU module is connected with vehicle-mounted computer, acquired human body respiration signal and heartbeat signal is sent
To vehicle-mounted computer.
Preferably, described doppler radar unit also includes wireless communication module, described wireless communication module and institute
Stating MCU module to be connected, described MCU module is connected with vehicle-mounted computer wirelessly by described wireless communication module.
Preferably, also including the angle measurement unit being arranged in steering wheel, described angle measurement unit is used for the side of detection
Changing to dish angle, described MCU module or institute's vehicle-mounted computer obtain steering wheel angle variable quantity, when steering wheel angle variable quantity is little
When preset value, described MCU module or the change of institute's vehicle-mounted computer continuous detecting physiological driver's signal.
Preferably, the microwave Doppler radar that described doppler radar sensor uses working frequency range to be 10.525GHz is visited
Survey device probe sensor HB100 module.
Preferably, described passive filter be band connection frequency be the passive RC filter of 0.1Hz-150Hz.
Preferably, the band connection frequency of described active band-pass filter is 0.1Hz-10Hz.
Preferably, described active band-pass filter is filtered by quadravalence Butterworth LPF and second order Butterworth high pass
Ripple device is constituted.
Preferably, during described digital filter uses FIR filter, iir filter or Digital Filtering with Zero Phase Error
Any one.
Compared with prior art, technical scheme has following technical effect that
(1) present invention firstly provides and use the degree of fatigue of Doppler measurement technique monitoring driver, by will be by many
General Le radar sensor is operated in continuous wave mode, and respective design multi-stage filter circuit, thus realizes non-contact detecting human body
Physiological signal, and realize fatigue driving monitoring by physiological signal change during analysis driver fatigue.
(2) increase detection steering wheel angle information the most in systems, processed by multi-source information and improve fatigue driving
Accuracy of measurement.
(3) active filter uses Butterworth filter, and Butterworth filter passable frequency response curve is smooth,
Decline slowly at suppressed frequency band, it is to avoid distorted signals, the amplification of signal can be realized while filtering, improve the signal to noise ratio of signal,
Realize undistorted amplification of signal to filter.Digital filter uses zero phase iir filter to isolate breathing and heartbeat signal, reduces
While operand, eliminate the phase distortion of signal, improve driving fatigue and drive the real-time of detection.
Accompanying drawing explanation
Fig. 1 is radar echo signal detection torso model expansion model.
Fig. 2 is the theory diagram of automobile fatigue drive of car of the present invention monitoring system.
Fig. 3 is the theory diagram of doppler radar unit in the present invention.
Fig. 4 is extreme learning machine illustraton of model.
Fig. 5 is the oscillogram (level of fatigue 0) of normal driving physiological signal and hand-wheel signal.
Fig. 6 is to drive the physiological signal under alert status and the oscillogram (level of fatigue 1) of hand-wheel signal.
Fig. 7 is to drive the physiological signal under drowsy state and the oscillogram (level of fatigue 2) of hand-wheel signal.
Fig. 8 is to drive the physiological signal under notable drowsy state and the oscillogram (level of fatigue 3) of hand-wheel signal.
Fig. 9 is to drive the physiological signal under extreme drowsy state and the oscillogram (level of fatigue 4) of hand-wheel signal.
Figure 10 is the circuit theory diagrams of radar power supply in power module.
Figure 11 is the circuit theory diagrams of amplifier power supply in power module.
Figure 12 is the circuit theory diagrams of digital power in power module.
Figure 13 is the circuit theory diagrams of ADC reference power supply in power module.
Figure 14 is the circuit theory diagrams of signal pre-processing module of the present invention.
Figure 15 is the circuit theory diagrams of a kind of embodiment of difference amplifier of the present invention.
Figure 16 is the circuit theory diagrams of a kind of embodiment of active band-pass filter of the present invention.
Figure 17 is the circuit theory diagrams of voltage movement circuit.
Figure 18 is the circuit theory diagrams of analog-digital converter.
Figure 19 is FIR and IIR filtering separates the contrast of breath signal time domain.
Figure 20 is FIR and IIR filtering separates the contrast of breath signal frequency domain.
Figure 21 is zero-phase filtering breath signal time-domain diagram.
Figure 22 is zero-phase filtering heartbeat signal time-domain diagram.
Figure 23 breath signal and heartbeat signal separation frequency domain figure.
Specific examples below will further illustrate the present invention in conjunction with above-mentioned accompanying drawing.
Detailed description of the invention
The fatigue drive of car monitoring system provided the present invention below with reference to accompanying drawing is described further.
Research find, human body when fatigue state, its breathe and heart rate signal all can decline, therefore by breathe and
Heart rate signal can accurately judge the fatigue state of human body.In order to overcome prior art to use touch sensor detection physiology letter
Number technological deficiency, applicant proposes to be applied to Doppler radar general for prior art contactless fatigue driving inspection first
Survey field.
Doppler radar be widely used in airborne early warning, navigation, missile guidance, Satellite Tracking, battle reconnaissance, target range measurement,
The military fields such as weapon.Its operation principle can be expressed as follows: when sky is scanned by the impulse wave of radar emission one fixed frequency, as
Running into moving target, the frequency of echo is poor with the frequency frequency of occurrences of transmitted wave, referred to as Doppler frequency.According to Doppler frequency
Size, the target diametrically movement velocity to radar can be measured;According to launching pulse and the time difference of reception, can measure
The distance of target.Therefore, the Doppler radar of military domain is usually operated at pulse mode, detects work by detection difference on the frequency
Moving-target.In prior art, Doppler radar also has the application at civil area, such as, utilizes Doppler radar (Doppler
Radar) the microwave detector for moving object HB100 microwave module of principle design, is widely used in automatic door control switch, safety
The places such as crime prevention system, the automatic video recording control system of ATM Automatic Teller Machine, train automatic signal.But, this type of Doppler
During radar application in civil area, it is common that detect frequency after output signal being directly amplified, then according to frequency size
Obtain and speculate human motion speed.
Doppler radar sensor can eliminate the shadow of particular medium (such as cloth, silk etc.) in specific distance range
Ring, the fine motion change of detection torso model, therefrom get physiological parameter information, it is achieved the detection of contactless physiological signal.
Contactless monitoring system overcomes the shortcoming of traditional physiological monitoring system, has noncontact, remote monitoring, operation simple
Etc. advantage, obtain increasing concern in fields such as clinical medicine, disaster medicine, military medicine, city anti-terrorisms, had wide
General application prospect.But, doppler radar sensor is realized contactless physiology in research by those skilled in the art
During signal detection, it is typically directed to design high accuracy of identification and highly sensitive doppler radar sensor, reality has been significantly greatly increased
Existing difficulty.
On the basis of existing technology, applicant is found by repeatedly theoretical and experimental study, and continuous wave radar is with human body
Thoracic cavity as detection target, through chest cavity movement return radar emission signal can produce phase-modulation, the radar received returns
Ripple signal, through phase demodulating, extracts the phase information being associated with chest cavity movement, according to phase information from demodulating information
The breathing of change reflection tester and the situation of change of heart beating.
See Fig. 1, show radar echo signal detection torso model expansion model, it is now assumed that radar emission signal T (t)
For
T (t)=cos [2 π f0t+Φ(t)] (1)
F in formula0Being radar emission signal frequency, Φ (t) is phase noise.
If chest cavity movement amplitude is x (t), radar sensor to human body distance is d0, launch radar signal to thoracic wall away from
From for d (t), then round trip delay time isDue to the chest cavity movement cycleThen adjust through radar reflection
Reception signal R (t) after system is:
Reception echo-signal R (t) is multiplied after low-pass filtering with radar emission signal T (t) and demodulates modulated signal, obtains
Taking baseband signal is:
In formulaIt is residual phase noise,It is radar and the decision of human body spacing
Intrinsic phase shift.When θ isOdd-multiple time, x (t) < < λ, can obtain:
Wherein ΔΦ (t) is the DC component that fixing target produces, formula (4) can obtain chest displacement x (t) and export with base band
Amplitude linear.But, the thoracic cavity fine motion displacement scope that human normal is breathed and heart beating causes is only 4-15mm, and
In prior art, doppler radar module is in the application in dual-use field, and the resolution of mobile object is at least 0.1 meter;
Meanwhile, the breathing of normal person and palmic rate are respectively 0.15~0.4Hz and 0.83~1.5Hz, frequency spectrum closely, in time domain
In be difficult to breath signal and heartbeat signal are distinguished.By formula (4) it is recognized that while human normal breathes the breast caused with heart beating
Fine motion displacement scope in chamber is less, as long as choosing suitable Doppler radar operating frequency, it is possible to well detection thoracic cavity fine motion
Signal;Although the frequency of breath signal and heartbeat signal is closely, as long as selecting suitable sample frequency, still can distinguish and exhaling
Inhale signal and heartbeat signal, owing to weak output signal and frequency separation are not it is obvious that how filtering interference signals extracts useful number
The number of it is believed that is the key solving the technology of the present invention problem.
In order to solve above-mentioned technical problem, see Fig. 2, show the former of a kind of fatigue drive of car of present invention monitoring system
Reason block diagram, the doppler radar unit for detecting physiological driver's signal intensity is installed in driver's cabin, by
Driver thoracic cavity sends doppler radar signal, thus realizes noncontact fatigue driving monitoring.
In a preferred embodiment, doppler radar unit also includes acousto-optic warning module, acousto-optic warning mould
Block is connected with described MCU module, when MCU module judges that driver is in fatigue driving state, controls acousto-optic warning module
Send sound and light alarm signal.Thus reach the technique effect reminding driver to take a good rest.
In a preferred embodiment, MCU module is connected with vehicle-mounted computer, by acquired human body respiration signal and the heart
Jump signal and be sent to vehicle-mounted computer.Stored and process breathing and the situation of heart beating change of driver by vehicle-mounted computer, by
The function that the big data of vehicle-mounted computer process and store improves the accuracy of detection of physiological signal, and can monitor fatigue driving in real time.
Further, doppler radar unit also includes wireless communication module, and wireless communication module is connected with MCU module, MCU
Module is connected with vehicle-mounted computer wirelessly by wireless communication module.Wireless communication module uses 2.4G wireless module
NRF24L01。
Finding in applicant's research, driver's steering wheel rotation the most by a small margin constantly adjusts vehicle under normal circumstances
Lateral displacement position with keep vehicle travel the center in track all the time.When driver is drowsy, micro-on steering wheel
Revising data can be less than data during normal driving.Do not considering that track is changed, only consider steering wheel rotation by a small margin (SWM,
Between 0.5-5 degree) in the case of, tired driver is compared with normal driver, and the number of times of steering wheel rotation is less.So,
The degree of fatigue of driver can pass through wheel steering SWM's (steering wheel movement) to a certain extent
Angle reflects.
In order to realize accurately monitoring fatigue driving, in a preferred embodiment, native system also includes being arranged on direction
Angle measurement unit in dish, angle measurement unit is used for detecting steering wheel angle change, MCU module or institute's vehicle-mounted computer and obtains
Steering wheel angle variable quantity, when steering wheel angle variable quantity is less than preset value, MCU module or institute's vehicle-mounted computer continuous detecting are driven
The change of the person's of sailing physiological signal.In reality, typically when steering wheel angle variable quantity is less than 1 degree in 1 second, intercept driver 30
Second physiological signal carry out data analysis, once physiological signal vary more than predetermined threshold value, it is judged that driver is in fatigue and drives
Sail state.
Use technique scheme, by steering wheel angle information and the use processing of physiological driver's signal, from
And effectively overcome the mobile interference of human body in driving;Meanwhile, by real-time storage physiological signal, can when carrying out data analysis
Choose suitable data length in time and carry out data process, thus improve data processing speed.
See Fig. 3, show the theory diagram of doppler radar unit of the present invention, sense including Doppler radar
Device, power module, signal pre-processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module and
MCU module, wherein, power module is used for system power supply;Doppler radar sensor is for launching continuous wave thunder to torso model
Reaching signal and receive output-response human body respiration and the low frequency signal of heart beating change after echo-signal processes, low frequency signal depends on
Secondary through signal pre-processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module and MCU module
After signal processing, MCU module obtains human body respiration signal and heartbeat signal and the change according to breath signal and heartbeat signal is sentenced
Whether disconnected driver is in fatigue driving state.
Although theoretical proof human body breath signal under fatigue state and non-fatigue state and heartbeat signal have significantly
Difference, but the research carrying out fatigue driving decision algorithm under true driving environment has the biggest challenge, also only identifies
The fatigue driving decision algorithm that precision is high just has actual application value.
In prior art, using expert analysis mode method based on face video, the method is the most practical driver
Fatigue state evaluation methodology.The method by one group of trained expert according to the facial expression of driver and head pose to it
Fatigue state is marked.Concrete operation step is: be video segment by driver's face video slicing;Several scoring expert's roots
Rub one's eyes according to driver, scratch face, yawn, closed-eye time, adjustment posture etc. are tired characterizes, by random sequence, video segment is carried out
Marking, the average of several expert analysis mode is as the tired score of this section of video.Driver's fatigue degree's grade is carried out by this system
Classification, specific requirement is as shown in table 1 below:
Table 1: driver's fatigue degree's grade classification and description thereof
In order to realize accurate fatigue driving detection, the present invention is using neural network machine identification module, neural network machine
Device identification module can be arranged in MCU module or vehicle-mounted computer.Before using, need first by neural network machine identification module
Train.In the present invention, the breath signal first expert analysis mode classification based on face video completed and heartbeat signal
Input neural network learning, thus the data model of each level of fatigue is determined at neural network machine identification module.Thus
When actual fatigue driving judges, level of fatigue can be judged according to the breath signal of input and heartbeat signal.
In the present invention, neural network machine identification module uses extreme learning machine illustraton of model, sees Fig. 4, show pole
Limit learning machine illustraton of model, the rudimentary algorithm of extreme learning machine model is as described below:
N: training sample sum
Hidden layer unit number
Dimension (i.e. input and the length of the output vector) (x of n, m: input and output layerj,tj), j=1,2 ..., N: instruction
Practice sample, wherein
xj=(xj1,xj2,...,xjn)T∈Rn,tj=(tj1,tj2,...,tjn)T∈Rm
All output vectors are got up by row spelling, available overall output matrix
oj, j=1,2 ..., N: with mark tjCorresponding actual output vector;
Weight matrix between input layer and hidden layer, the vectorial w that wherein i-th row of W is correspondingi=
(wi1,wi2,...,win)T
Represent the weight vector connecting hidden layer i-th unit with input block;
Bias vector, biRepresent the threshold value of i-th hidden unit;
Weight matrix between hidden layer and output layer, the vectorial β that wherein i-th row of β is correspondingi=
(βi1,βi2,...,βim)T
Representing the weight vector connecting hidden layer i-th unit with output unit, matrix β can be written as piecemeal shape by row
Formula:
G (x) is activation primitive.
Mathematically, the model of the SLFNs of standard is
Wherein wi·xjRepresent wiAnd xjInner product.
Model above zero error to be made approach above-mentioned N number of sample, then
I.e. there is W, β and b so that
Utilizing matrix form to represent, above-mentioned expression formula can be reduced to
H β=T
In general SLFNs learning algorithm, the bias vector b of input weights W and hidden unit needs constantly to be adjusted by iteration
Whole refreshing, when learning algorithm starts, the value of any given W and b, calculate H with it and make its holding constant, so, we
Have only to determine that parameter beta is the most permissible.Therefore, when W and b fixes, it is equivalent to ask the least square solution of formula equationI.e.
Correlation theorem according to Moore-Penrose generalized inverse matrix and LS solution of the least norm obtains β=H+T
Given training sample setActivation primitive g (x), hidden unit number
The process that realizes of ELM algorithm can be summarized as: first, is randomly assigned input weights and the threshold value of network;Secondly, meter
Calculate hidden layer neuron output matrix;Finally, according to β=H+T calculates output weight matrix.According to above reasoning process, we can
Knowing, ELM does not has the iterative step during traditional neural computing, therefore considerably reduces the training time.
In order to verify the actual techniques effect of the present invention, having recruited 8 tested drivers in the experiment test stage, the age exists
Between 22-60 year.Healthy, audition is normal, without anerythrochloropsia.Ensure that the sleep of abundance, experiment are front 24 little before the experiments
Time interior do not take any zest article.Every driver carries out twice drive simulation experiment every day: all drivers are often
It same time tests, and notifies driver's preparing experiment before experiment, it is desirable to driver forbids driving in 24 hours on pretreatment
Sail people drink, tea and coffee.Experimental selection 12:00 at noon and 20:00 in evening proceeds by, each lasting about two hours,
This time period people is typically easiest to be in the state of feeling sleepy, and therefore can observe driver in of short duration two hours
Tired whole process from regaining consciousness to be absorbed in.Requiring in experimentation to keep environment quiet, the photographic head being arranged in driving cabin is used
Have recorded driver's facial expression information, image acquisition rates is 30Hz, and the data collecting system record of testing stand is driven
People's breath signal, heart rate signal, human mobile signal, steering wheel small angle tower signal, the big angular signal of steering wheel, sample frequency is equal
For 50Hz.
Video signal and MCU gather signal and synchronize, and are split a length of 30 seconds by the video signal every section gathered, use expert
The degree of fatigue of driver is given a mark by standards of grading, the physiological signal judging basis gathered as radar.The physiology synchronized
Signal is divided into five class signals according to based on face video experts standards of grading, and the most corresponding 5 class degree of fatigues use numeral labelling
For 0-4, a length of 30 seconds of every segment data, breathing and heartbeat signal under every kind of degree of fatigue gather 100 groups of data respectively, extract
Go out the breath signal mean frequency value of every segment data, breath signal frequency mean-square value, breath signal amplitude equalizing value, breath signal amplitude
Mean-square value, heartbeat signal mean frequency value, heartbeat signal amplitude equalizing value, heartbeat signal amplitude mean-square value are as extreme learning machine algorithm
Input sample, by sample learning training until in the range of meeting error requirements, obtaining exporting weights.In Single Chip Microcomputer (SCM) system pair
Extreme learning machine carries out algorithm realization, determines training output weights, in driver tests, gathers radar signal, be filtered
Extract signal characteristic, classified by extreme learning machine, for classification results, point out to driver's difference.Fig. 5 to 9 is to adopt
The breathing of collection driver fatigue in various degree and heartbeat signal variation diagram, as seen from the figure, by neural network machine identification energy
Enough well differentiation degree of fatigues at different levels.
Hereinafter the design principle of fatigue driving detecting system hardware configuration of the present invention is described again in detail.
In prior art, Doppler radar operating frequency range is 2~75GHz, and the present invention combines radar resolution, penetrates
The factors such as barrier ability, volume size and power consumption, choose the doppler radar sensor that operating frequency is 10.525GHz.
Specially using HB100 microwave module commonly used in the prior art, this module is to utilize Doppler radar (Doppler Radar)
The microwave detector for moving object of principle design, is mainly used in automatic door control switch, safety and protection system, ATM carry automatically
The places such as the automatic video recording control system of money machine, train automatic signal.HB100 is the 10.525GHz microwave Doppler of standard
Radar detedtor, internal by FET medium DRO microwave concussion source (10.525GHz), power divider, transmitting antenna, reception sky
The circuit compositions such as line, frequency mixer, cymoscope, it is 35mA at continuous direct current supply MODE of operation electric current, and gross output is little
In 15mW.Launching antenna and be outwardly directed transmitting microwave, reflected when running into object, echo is received by reception antenna, then arrives
Blender mixes with the wave of oscillation, and the low frequency signal after mixing, detection has reacted the speed that object moves.Employing prior art is general
Detecting module, greatly reduce cost and development difficulty.Prior art, generally uses HB100 module detection human motion,
Namely the low frequency signal exporting it directly amplifies and detect the frequency of this signal, thus calculate human body according to frequency values
Translational speed, usual investigative range is more than 20 meters.But, in the application of the present invention, human normal breathing and heart beating cause
Fine motion displacement scope in thoracic cavity is only 4-15mm, and the intensity of various noise signals is considerably beyond useful signal, therefore, uses tradition
Application circuit cannot detect physiological signal.The present invention in order to by HB100 module application in bio-signal acquisition, devise three grades
Filter circuit, thus realize the detection of breath signal and heartbeat signal, setting of doppler radar unit described in detail below
Meter principle.
In order to improve the accuracy of detection of system, in power module designs, need to take into full account the undulatory property of voltage, and
The powerful electric current interference to system during starting.Therefore need to choose Width funtion input voltage stabilizing chip, radar signal output is the faintest, electricity
Source module pays particular attention to power supply ripple and noise problem, not only includes digital circuits section due to system, also comprise
The analog portions such as A/D conversion, low level signal amplification, need to isolate digital power and analog power, therefore separately design radar power supply, fortune
Discharge source, digital power and ADC reference power supply.
See Figure 10, show the circuit theory diagrams of radar power supply in power module, including the first power interface P1, first
Electric fuse F1, the first transient diode TVS1, the first diode D1, the 6th electrochemical capacitor C6, the 7th electric capacity C7, the second electric capacity
C2, the 5th power supply chip U5, the 14th electric capacity C14, the 15th tantalum electric capacity C15, wherein, the crus secunda of power interface P1 and first
One end of electric fuse F1 is connected, the other end of the first electric fuse and one end of the first transient diode TVS1 and the first diode
The anode of D1 is connected, the negative terminal of the first diode D1 and the anode of the 6th electrochemical capacitor C6, one end of the 7th electric capacity C7,
Five power supply chip the 5th pins, the 8th pin are connected, and first pin of power interface P1 and the first transient diode TVS1's is another
One end, the negative terminal of the 6th electrochemical capacitor C6, the other end of the 7th electric capacity C7, the 6th pin of the 5th power supply chip U5 and the 7th pipe
Foot and three-prong are connected with simulation ground end jointly, first pin of the second electric capacity C2 and the 4th of the 5th power supply chip U5 the
Pin is connected, and the other end of the second electric capacity C2 is connected with first pin of the 5th power supply chip U5 and the second pin, the
First foot of 14 electric capacity C14 and the anode of the 15th tantalum electric capacity C15 are connected, first pin of the 5th power supply chip U5 and the
Two pins are connected, and the other end of the 14th electric capacity C14 and the negative terminal of the 15th tantalum electric capacity C15 are connected with holding with simulating jointly
Connect.
In foregoing circuit, the 5th power supply chip U5 sample LT1763CS8-5, output 5V power supply to radar chip power supply,
This chip is a low noise, low voltage difference micropower regulator.Being 20 μ VRMS in 10Hz-100KHz output noise, Width funtion is defeated
Entering scope 1.8V to 20V, have low-down standby current 1 μ A, inside had stream and overheat protective function, with Switching Power Supply
Compare, have the advantages that Ripple Noise is little.Use MF-R09009 that circuit is carried out overcurrent protection at power interface end, and hold
At Kou, a TVS pipe in parallel, plays a very good protection to power supply overvoltage pulse, and power end one diode of series connection prevents electricity
Source reversal connection, shields to rear class whole system.For reducing ripple interference, at each power supply chip plus a high frequency decoupling
Electric capacity, adds a high-frequency bypass capacitor on each electrochemical capacitor side.
Owing to single supply amplifier of powering can reduce low frequency characteristic, single supply amplifier input/output signal scope can reduce,
Amplifier becomes more sensitive to internal and external error source, and simultaneously in low pressure single supply device, gain accuracy also can drop
Low, the present invention considers and passes through experimental verification, and final sampling selects dual power supply to power to amplifier.See Figure 11, show
The circuit theory diagrams of amplifier power supply in power module, including the 13rd electric capacity C13, the 3rd power supply chip U3, the 18th electric capacity
C18, the 4th resistance R4, the 5th resistance R5, the 16th electric capacity C16, the 17th electric capacity C17, the 19th electric capacity C19, the 6th resistance
R6, the 3rd resistance R3, the 20th electrochemical capacitor C20, the 21st electric capacity C21, the first resistance R1, the 4th power supply chip U4,
One electric capacity C1, the second inductance L2, the second diode D2, the 11st electrochemical capacitor C11, the 12nd electric capacity C12, wherein, the 13rd
First foot of electric capacity C13 one end and the 3rd power supply chip U3, the 3rd foot, the 5th foot are connected, one end of the 18th electric capacity and the
4th foot of three power supply chip U3 is connected, one end of the 16th electric capacity C16 and one end of the 17th electric capacity C17, the 3rd power supply
Tenth foot of chip, the 11st foot are connected, and one end of the 4th resistance R4 is connected with the 9th foot of the 3rd power supply chip, and the 5th
One end of resistance R5 is connected with the other end, the octal of the 3rd power supply chip U3 of the 4th resistance R4, the 13rd electric capacity C13's
The other end and the other end of the 18th electric capacity C18, the other end of the 5th resistance R5, the other end of the 16th electric capacity C16, the 17th
The other end of electric capacity C17 is connected with simulation ground jointly;19th electric capacity C19 one end and one end of the 3rd resistance R3, the 6th electricity
Resistance one end of R6, the 4th power supply chip U4 the 3rd foot are connected, the other end of the 3rd resistance R3 and the 20th electrochemical capacitor C20's
Anode, the crus secunda of the 4th power supply chip U4 are connected, one end of the 21st electric capacity C21 and the 4th of the 4th power supply chip U4 the
Foot is connected, and one end of the first resistance R1 is connected with anise, one end of the first electric capacity C1 of the 4th power supply chip U4, and second
The anode of diode D2 and the 5th foot of the 4th power supply chip U4, the negative terminal of the 11st electric capacity C11, one end phase of the 12nd electric capacity
Connecting, negative terminal and the 7th foot of the 4th power supply chip U4, one end of the second inductance L2 of the second diode D2 are connected, and the 19th
The other end of electric capacity C19 and the other end of the 6th resistance R6, the 20th electrolysis negative terminal of C20, the other end of the 21st C21,
The other end of the first electric capacity C1, the other end of the second inductance L2, the anode of the 11st electric capacity C11, the 12nd electric capacity C12 another
End is connected with simulation ground jointly.
In foregoing circuit, the 3rd power supply chip U3 uses LP38798SDX_ADJ and the 4th power supply chip U4 to use
TPS6735 voltage stabilizing chip, thus realize exporting positive and negative 5V power supply supply amplifier, wherein positive 5V power supply gives A/D chip power supply simultaneously.
LP38798SDX_ADJ is that a Width funtion inputs 3.0V-20V, is 5 μ VRMS in 10Hz-100KHz output noise, TPS6735
Input voltage range 4V-6.2V, quiescent dissipation reaches 1 μ A.So amplifier power supply required precision can be met.
See Figure 12, show the circuit theory diagrams of digital power in power module, including the 3rd electric capacity C3, the first power supply
Chip U1, the first inductance L1, the second resistance R2, the 8th electric capacity C8, the 9th electric capacity C9, wherein, the 3rd electric capacity C3 one end and first
The crus secunda of power supply chip U1, the 3rd foot are connected, second resistance R2 one end and the octal and the tenth of the first power supply chip U1
Foot, one end of the first inductance L1, one end of the 8th electric capacity, one end of the 9th electric capacity are connected, the other end of the first inductance L1 with
9th foot of the first power supply chip U1 is connected, the other end of the 3rd electric capacity C3 and the 4th foot of the first power supply chip U1, the 9th
Foot, the tenth foot, the 7th foot, the other end of the second resistance R2, the other end of the 8th electric capacity, the other end of the 9th electric capacity jointly and count
It is connected word.
First power supply chip U1 uses Ti chip TPS62177DGCR chip, to single-chip microcomputer and wireless module NRF24L01
Power supply.This chip input voltage scope 4.7V-28V, input current is up to 500mA, and in a sleep mode, quiescent current only has
4.8 μ A, there are overtemperature protection, short-circuit protection etc. in inside.
See Figure 13, show the circuit theory diagrams of ADC base modules in power module, including the 4th electric capacity C4, the 5th
Electric capacity C5, the second reference power supply chip U2, the tenth electric capacity C10, wherein, one end of the 4th electric capacity C4 and the one of the 5th electric capacity C5
End, the second reference power supply chip U2 crus secunda are connected, one end of the tenth electric capacity C10 and the second reference power supply chip U2 the 6th foot
Be connected, the other end of the 4th electric capacity C4 and the other end of the 5th electric capacity C5, the 4th foot of the second reference power supply chip U2, the tenth
The other end of electric capacity is connected with simulation ground jointly.
Second reference power supply chip U2 uses 16 Precision A/D C transducers, digital output change 1LSB, corresponding simulation electricity
Buckling turns to 76 μ V.Therefore needing higher reference voltage source, ADR445 reference voltage chip has ultra-low noise, high accuracy and low
Temperature drifting performance.Power source change peak-to-peak value only has 2.25 μ V, can meet data acquisition system.
Further, signal pre-processing module includes voltage follower and passive filter, and voltage follower is for defeated
Entering signal and carry out voltage follow, passive filter is for filtering the DC component in input signal.
Torso model fine motion change causes doppler radar sensor output signal to change amplitude range 1-20mV, has width
Spending the features such as low, noise big, carrying load ability difference, input signal carries out voltage follow eliminates output impedance influences, and raising is driven
Kinetic force;Radar signal is radiofrequency signal, and the spurious signal in space is excessive, can cause that the amplifier of rear end is saturated even to be damaged,
In order to prevent owing to DC component causes amplifier saturated, passive filter is used DC component to be filtered.
See Figure 14, show the circuit theory diagrams of a kind of embodiment of signal pre-processing module of the present invention, including: second
Radar module P2, the 13rd resistance R13, the 33rd electric capacity C33, the 9th integrated transporting discharging U9, the 26th resistance R26, second
19 electric capacity C29, the 25th resistance R25, the 19th resistance R19, the 34th electrochemical capacitor C34, wherein, the second radar mould
Block P2 uses HB100 module, the 3rd foot of the second radar module P2 and one end of the 13rd resistance R13, the 9th integrated transporting discharging U9
Crus secunda be connected, the crus secunda of the second radar module P2 and one end of the 33rd electric capacity C33 are connected, the 26th electricity
Resistance one end is connected with the 4th foot of the 9th integrated transporting discharging U9, the of the other end of the 26th resistance and the 9th integrated transporting discharging U9
One foot, one end of the 29th electric capacity C29 are connected, the other end of the 29th electric capacity C29 and the one of the 25th resistance R25
End, one end of the 19th resistance R19, the anode of the 34th electrochemical capacitor are connected, the 3rd foot of the 3rd radar module P3 with
The other end of the 33rd electric capacity, the crus secunda of the 9th integrated transporting discharging U9, the other end of the 25th resistance R25, the 34th
The negative terminal of electrochemical capacitor is connected with simulation ground jointly.
The principle of foregoing circuit is as follows, and owing to radar signal output impedance is high, carrying load ability is low, in order to impedance is easier to
Coupling, front end uses TLV2631 to constitute voltage follower and not only provides high input impedance and low output impedance.The most also
Play an isolation buffer effect, reduce the signal processing impact on microwave front-end, it is ensured that the signal to noise ratio of input signal, also
Wave filter can be more easily designed anti-aliasing when of design for rear class.And radar emission electromagnetic wave is on fixing object
Time, electromagnetic wave echo will not produce Doppler frequency, and its echo-signal occurs at zero frequency, is embodied in the signal received straight
In flow component, additionally, radar is radiofrequency signal, the spurious signal in space is excessive, can cause that the amplifier of rear end is saturated even to be damaged
Bad, in order to prevent owing to DC component causes amplifier saturated, it is necessary to DC component is filtered.In order to be further ensured that signal has
There is high signal to noise ratio, be 0.1Hz-150Hz passive RC filter following outfan design frequency, owing to heart beating letter breathed by radar
Number frequency is higher than 0.1Hz, designs RC Frequency point 0.1Hz be less than, and choosing of RC resistance is also required to pay special attention to, if selected
The input resistance taken is excessive, then at this time the thermal noise of resistance will be very big, can exceed the input voltage noise level of amplifier,
Rear class is amplified interference relatively big, so to choose big input capacitance as far as possible, the biggest input capacitance, leakage current is relatively big,
Rear class amplifying circuit can be caused the most saturated.So electric capacity needs to choose the ceramic disc capacitor that leakage current is less herein.
Further, difference amplifier is for being amplified input signal and eliminating common-mode noise;Radar signal is passed through
During primary amplification, centre has been mingled with much noise.If primary amplifier amplification is excessive, easily cause the full of signal
With.On the other hand in order to reduce the impact of signal source, it is necessary to improve the input impedance of amplifier, main for radar signal interference
Deriving from common mode disturbances, primary amplifier Main Function is to eliminate common-mode noise.The present invention uses Differential Input mode, in reality
In the system of border, noise is mostly presented in common mode.For Differential Input, it is possible to effectively eliminate common-mode noise, thus
A big chunk noise in signal can be removed.
For integrated transporting discharging, critically important performance indications are exactly common mode rejection ratio CMRR.It is defined as follows:
Wherein AvdAnd AvsRepresent amplifier respectively to difference mode signal and the amplification of common-mode signal.Excellent in one of the present invention
Select in embodiment, use instrument amplifier.Comparing with common integrated transporting discharging, instrument amplifier has higher
Common mode rejection ratio.The CMRR of physiology amplifier typically requires 60dB-80dB, specifically the instrument of selection Analog Device company
The CMRR of instrument amplifier AD627 reaches 83dB.AD627 provides flexible user to select, by a non-essential resistance, it is possible to arrange
Gain, maximum programming gain can reach 1000, is a rail-to-rail low-power consumption instrument amplifier, has very high cmrr,
There is the widest supply district (± 18V), when being operated in dual power supply, it is possible to rail to rail exports, be the ideal of signal amplification
Select.When working at low supply voltages, rail to rail output stage makes dynamic range reach maximum.Ultralow power consumption, is suitable for
Application scenario in portable low power-consumption equipment.
See Figure 15, show the circuit theory diagrams of a kind of embodiment of difference amplifier of the present invention, including: the 24th
Resistance R24, the 36th electric capacity C36, the 39th electric capacity C39, the 29th resistance R29, the 12nd integration instrument put U12,
37 electric capacity C37, the 38th electric capacity C38, the 18th resistance R18, the 24th electric capacity C24, the 25th electric capacity C25,
18th resistance R18, the 38th electric capacity C38, wherein, the 24th resistance R24 one end and the one of the 31st electric capacity C31
Hold, the 12nd integration instrument puts the 3rd foot of U12, the 36th electric capacity C36 one end is connected, the 36th electric capacity C36 other end
Put the crus secunda of U12 with the 12nd integration instrument, one end of the 39th electric capacity C39, one end of the 29th resistance are connected, and
The octal that U12 is put with the 12nd integration instrument in one end of 18 resistance R18 is connected, the other end of the 18th resistance R18 and
12 integration instruments are put first foot of U12 and are connected, the 24th electric capacity C24 one end is connected with the 25th electric capacity C25 one end,
12nd integration instrument is put U12 the 7th foot and is connected, the 37th electric capacity C37 one end and the 38th electric capacity C38 one end, the 12nd
Integration instrument is put the 4th foot of U12 and is connected, the 39th electric capacity C39 other end and the other end of the 29th resistance R29, second
The other end of 14 electric capacity C24, the other end of the 25th electric capacity C25, the other end of the 39th electric capacity C39, the 38th
The other end of electric capacity C38 is connected with simulation ground jointly.Thus, AD627 Output Voltage Formula: VO=(5+ (200K Ω/R18))
Vi, it is achieved signal amplifies.
Further, active band-pass filter is for being amplified input signal and eliminating differential mode noise;Radar signal
After difference amplifier, common mode disturbances noise can well be eliminated.But the most substantial portion of noise is with difference
The form of mould enters late-class circuit.Power supply noise, DC baseline drift noise and power frequency when these noises comprise startup are done
Disturb noise.So needing the signal after selecting suitable wave filter that primary is amplified to be filtered, in order to overcome passive filtering electricity
The shortcoming of road consumption signal energy, uses the active power filtering being made up of amplifier and resistance-capacitance network, improves filtering performance.Relatively
For passive filtering, owing to there being the addition of amplifier, active filter can not only carry out power back-off, moreover it is possible to while filtering
Being amplified signal, amplifier also can play buffering and the effect of isolation simultaneously.In conjunction with breathe and heartbeat signal frequency and
Human body forcing frequency, the present invention use active low-pass filter and high pass filter to constitute band that frequency is 0.1Hz-10Hz leads to
Wave filter.
According to wave filter amplitude-frequency and the difference of phase-frequency characteristic, it is broadly divided into following several according to active filter transmission characteristic
Class:
Butterworth filter: the amplitude of amplitude frequency curve is the most smooth within passband, by passband to stopband attenuation steepness relatively
Slow, phase-frequency characteristic is nonlinear, is the most flat amplitude filter.
Chebyshev filter: in passband, has equal ripple.Cut-off frequency decay steepness is than the Butterworth of same exponent number
The steeper phase response of characteristic is non-linear, but poor than than Butterworth is.
Bessel filter: time-delay characteristics are the most smooth, amplitude-frequency characteristic flat region is less, slow from passband to stopband attenuation
Slowly.The amplitude-frequency characteristic of Bessel filter is poorer than Butterworth or Chebyshev filter.
Elliptic function filter: equal ripple all occurs in passband and stopband.Elliptic function filter relatively other classes
The wave filter of type has the cut-off frequency decay steepness of steepest.But its time-delay characteristics are good not as first three.
Native system design requires that wave filter amplitude frequency curve is the most smooth in passband, and it is special to have good intermediate zone
Property.Applicant is on the basis of more above-mentioned wave filter actual performance, and final selection uses butterworth filter, and Bart is fertile hereby
Wave filter is all-pole filter, so in the all-pole filter of n rank, as opinion amplitude-frequency characteristic at w=0, then Bart
Butterworth wave filter is the most straight, therefore Butterworth filter maximally-flat, Bart in referred to as maximally flat wave filter has passband
The phase characteristic phase shift better than the Chebyshev of same exponent number, anti-Chebyshev and elliptic function filter of Butterworth wave filter and frequency
It is smaller that the linear relationship of rate affects, it is possible to achieve preferably signal filtering effect and less signal attenuation, it is adaptable to thunder
Reach and breathe the removal of noise in heartbeat signal.
In a preferred embodiment, for shortening intermediate zone, filter Hz noise, improve filter attenuation gain, this
Invention uses second order butterworth high pass filter and quadravalence Butterworth LPF composition bank of filters to enter signal
Row amplifies filtering, sees Figure 16, show the circuit theory diagrams of a kind of embodiment of active band-pass filter of the present invention, including:
20th resistance R20, the 30th resistance R30, the 9th resistance R9, the 27th resistance R27, the 16th resistance R16, the 17th electricity
Resistance R17, the 7th resistance R7, the 21st resistance R21, the 22nd resistance R22, the 8th resistance R8, the 26th electric capacity C26,
26th electric capacity C26, the 27th electric capacity C27, the 32nd electric capacity C32, the 22nd electric capacity C22, the 35th electric capacity
C35, the 23rd electric capacity C23, electric capacity C, the 8th integrated transporting discharging U8, the tenth integrated transporting discharging U10, the 11st integrated transporting discharging U11,
Wherein, the 26th electric capacity C26 one end is connected with one end, one end of the 9th resistance R9 of the 27th electric capacity C27, and the 20th
The other end and the 3rd foot of the 8th integrated transporting discharging U8, one end of the 20th resistance R20 of seven electric capacity C27 are connected, the 9th resistance
The other end of R9 and first foot of the 8th integrated transporting discharging U8, the 27th resistance R27 one end, one end phase of the 16th resistance R16
Connecting, one end of the other end of the 27th resistance R27 and the 4th foot of the 8th integrated transporting discharging U8, the 30th resistance R30 is connected
Connect, the other end of the 16th resistance R16 and the 32nd electric capacity C32 one end, one end of the 7th resistance R7, the 17th resistance R17
One end is connected, the 17th resistance R17 and the 4th foot of the tenth integrated transporting discharging U10, one end of the 22nd electric capacity C22 are connected
Connect, the other end of the 7th resistance R7 and the other end of the 22nd electric capacity C22, first foot of the tenth integrated transporting discharging U10, the 20th
One resistance R21 one end is connected, the other end of the 21st resistance R21 and the 35th electric capacity C35 one end, the 22nd resistance
R22 one end, one end of the 8th resistance R8 are connected, the other end of the 22nd resistance R22 and the of the 11st integrated transporting discharging U11
Four feet, one end of the 23rd electric capacity C23 are connected, the other end of the 8th resistance R8 and the other end of the 23rd electric capacity C23,
First foot of the 11st integrated transporting discharging U11 is connected, the 20th resistance R20 other end and the 30th resistance other end, the 30th
The two electric capacity C32 other ends, the 35th electric capacity C35 other end are connected with simulation ground jointly.
In foregoing circuit, two second order multiterminal feedback (MFB) low pass filter cascades are utilized to constitute fourth order low-pass wave filter,
The open-loop voltage gain and the input impedance that use integrated transporting discharging are the highest, and output impedance ratio is relatively low, after constituting active filter circuit
Also there is certain voltage amplification and cushioning effect.Choose ButterWorth unlimited gain multiple feedback low pass filter, as
Second order filter structure, this feedback topology structure has high selectivity and precipitous excessive band, can produce more simultaneously
Reasonably device value, namely resistance capacitance is in available scope, can select low-cost and high-precision device.Voltage controlled voltage source
High pass filter, uses homophase connection, and filter input impedance is high, and output impedance is low, is equivalent to a voltage source, its circuit
Can be stable, gain easily regulates.
(MFB) low pass filter is fed back for single second order multiterminal, special according to Kirchhoff's theorem and negative feedback amplifier
Property can obtain:
Wherein K is filter gain, ωcFor filter cutoff frequency, B and C is normalization coefficient.
Normalization coefficient B=1.414, C=1 can be obtained according to unlimited gain multiple feedback circuit topological structure, experience advise
Then select C32It is similar to 10/fc, by design objective cut-off frequency fc=10Hz, can obtain C32=1uF, filter gain 1 He respectively
10, low-pass filter circuit device parameters is as shown in table 1.Simulation analysis can obtain the response of low pass filter amplitude-frequency characteristic, its 3dB cut-off frequency
For 8.237Hz, meet design requirement.It is specifically related to parameter as shown in the table.
Table 2 low-pass filter circuit component parameter type selecting
Voltage controlled voltage source circuit of high pass filter design principle is, utilizes RC filter circuit and in-phase proportion amplifying circuit group
Becoming second order voltage controlled voltage source high pass filter, it is high that this wave filter has input impedance, the feature that output impedance is low.Butterworth is high
The transmission function of bandpass filter is such as
Wherein K is filter gain, ωcFor filter cutoff frequency.
According to design objective, cut-off frequency fc=0.1Hz, filter gain K=10, at f=0.1fcTime, it is desirable to amplitude declines
Subtract more than 30dB, make R9=R20=R, C26=C27=C, fc=1/ (2 π RC).High-pass filtering circuit component parameter such as table 2 institute
Show.Simulation result is the amplitude-frequency response of voltage controlled voltage source high pass filter, and its 3dB cut-off frequency is 0.099Hz, and pass-band performance is satisfied to be set
Meter requirement, physical circuit device parameters is as shown in table 3 below.
Table 3 high-pass filtering circuit component parameter type selecting
Further, breathe and heartbeat signal separation module includes voltage movement circuit, analog-digital converter and digital filtering
Device.Owing to amplifying circuit uses dual power supply amplifier, the amplitude of oscillation of signal becomes big, and positive negative level also occurs in output signal, unavoidably
Make troubles for rear class ADC converter sampling, change so needing, by voltage movement circuit, signal level moved ADC
The signal input range that device allows.
See Figure 17, show the circuit theory diagrams of voltage movement circuit, including: the 28th electric capacity C28, the 30th electricity
Hold C30, the tenth resistance R10, the 14th resistance R14, the 12nd resistance R12, the 23rd resistance R23, the 28th resistance
R28, the 11st resistance R11, the 15th resistance R15, the 6th integrated transporting discharging U6, the 7th integrated transporting discharging U7, the 3rd diode D3,
Four diode D4, wherein, the tenth resistance R10 one end and one end of the 14th resistance R14, one end of the 28th electric capacity C28, the
3rd foot of six integrated transporting discharging U6 is connected, the 6th integrated transporting discharging U6 the 4th foot and the 6th integrated transporting discharging U6 the first foot, the 12nd
One end of resistance R12 is connected, the other end of the 12nd resistance R12 and one end of the 11st resistance R11, the 7th integrated transporting discharging U7
The 3rd foot be connected, the 23rd resistance R23 one end and one end of the 28th resistance R28, the of the 7th integrated transporting discharging U7
Four feet are connected, the other end of the 28th resistance R28 and first foot of the 7th integrated transporting discharging U7, the one of the 15th resistance R15
End is connected, the other end of the 15th resistance R15 and one end of the 30th electric capacity C30, the anode of the 3rd diode D3, the four or two
The negative terminal of pole pipe D4 is connected, the other end of the 14th resistance R14 and the other end of the 28th electric capacity C28, the 11st resistance
The other end of R11, the other end of the 30th electric capacity C30, the anode of the 4th diode D4 are connected with simulation ground jointly.
In foregoing circuit, radar signal sampling amplifier OPA188 after band-pass filter constitutes calculus of differences electricity
Road, at the positive input superposition constant voltage source of amplifier, constitutes voltage movement circuit, and wherein voltage source uses amplifier
TLV2631 constitutes voltage follower and produces benchmark 2.5V voltage source.WhereinSo pass through voltage movement
Output negative level signal can be moved positive level.Output signal adds two diodes of D3, D4, and anti-stop signal is excessive to amplifier
Cause damage, also ensure that output signal is in the range of ADC converter input voltage.
Analog-digital converter for being converted into discrete digital quantity by analog quantity, and native system design radar signal output signal is frequently
Rate is far below 20Hz, and sample frequency is set to 50Hz, and conversion speed is relatively low, it is possible to use the a/d converter of common switching rate.
Radar signal amplify output comprise breathing and heartbeat signal, for ensure following digital Filtering Processing can be good at separate breathe and
Heartbeat signal, this is accomplished by selecting high-resolution and multichannel a/d converter.
See Figure 18, show the circuit theory diagrams of analog-digital converter, including: the 43rd electric capacity C43, the 42nd electricity
Hold C42, the 44th electric capacity C44, the 48th electric capacity C48, the 49th electric capacity C49, the 40th electric capacity C40, the 35th
Resistance R35, the 32nd resistance R32, the 13rd AD conversion chip U13, wherein, one end and the 4th of the 43rd electric capacity C43
One end of 12 electric capacity C42, the 9th foot of the 13rd AD conversion chip U13 are connected, one end of the 44th electric capacity C44 and the
Tenth foot of 13 AD conversion chip U13 is connected, one end of the 48th electric capacity C48 one end and the 49th electric capacity C49, the
One end of 35 resistance, the 13rd foot of the 13rd AD conversion chip U13 are connected, the 40th electric capacity C40 one end and the tenth
16th foot of three AD conversion chip U13 is connected, one end of the 32nd resistance R32 and the 13rd AD conversion chip U13
First foot is connected, the other end of the 43rd electric capacity C43 and the other end of the 42nd electric capacity C42, the 44th electric capacity
The other end, the 11st foot of the 13rd AD conversion chip U13, the 12nd foot, the other end of the 48th electric capacity C48, the 40th
The other end of nine electric capacity is connected with simulation ground jointly.The other end of the 40th electric capacity C40 be digitally connected.
Wherein, using Maxim MAX1167 analog-digital converter, this chip is low-power consumption, multichannel, 16 Approach by inchmeal
Pattern number converter (ADC), when 10kps, electric current only 185 μ A.There is internal reference and outside reference is available and carry
There is interface compatible for a high speed SPI/QSPI/.MAX1167 uses single+5V analog power work, and has independent numeral electricity
Source, it is allowed to the direct Digital Logic interface with+2.7V to+5.5V.MAX1167 external reference voltage source is high-precision AD R445,
There is the highest degree of stability.The dynamic property of MAX1167 excellence and low-power consumption, it is sufficient to meet wanting of current system A/D converter
Ask.
Digital filter uses digital filtering technique to separate breath signal and heartbeat signal at frequency domain.In the present invention
In a kind of preferred implementation, digital filter uses in FIR filter, iir filter or Digital Filtering with Zero Phase Error
Any one.The design principle of three kinds of digital filters is described in detail in detail separately below.
FIR (Finite Impulse Response) wave filter is to have limit for length's unit impulse response wave filter, and it can be
Having strict linear phase-frequency characteristic while ensureing any amplitude-frequency characteristic, its unit sample respo is time-limited simultaneously, because of
And wave filter is stable system.Due to the breathing in physiological signal, heartbeat signal, energy is concentrated mainly near zero-frequency, adopts
It must is fulfilled for claimed below with traditional digital filter:
(1) breathe, the frequency band range of heartbeat signal is concentrated mainly on 0.1Hz-4Hz, and therefore the bandwidth of wave filter must be non-
The narrowest, concentrate on the echo signal of low-frequency range detecting energy
(2) in order to filter the noise jamming outside useful signal frequency band range and noise, in frequency domain, the intermediate zone of wave filter
Sinking speed is very fast, to obtain steeper intermediate zone, reduces the wave rear of wave filter as far as possible.
In the present invention, the design objective of physiological signal wave filter is as shown in table 4 below.
Table 4: physiological signal wave filter design objective
Two kinds of Direct Method of Design of FIR filter are windowing Fourier space method and frequency sampling method.In design filtering
During device, after the type of selected digital filter, next will estimate to meet the filtering required for given Filter specification
The exponent number of device.In order to reduce the complexity of calculating, filter order should be elected as and obtain smallest positive integral more than or equal to this estimated value.
The type of window function w (n) and the value of length of window N is depended on the performance of filter of window function metht design.?
In filter design procedure, after the type of selected digital filter, next will estimate needed for meeting given Filter specification
The filter order wanted.For reducing the complexity calculated, filter order should be elected as and obtain more than or equal to this estimated value
Small integer.Some scholars propose the minimum equation that index direct estimation filter order is N from numbers below wave filter
Such as Kaiser equation: set normalization passband rim angle frequencies omegap, normalization stopband rim angle frequencies omegas, peaked passband ripple δp,
And peak value stopband ripple δs.Kaiser equation:
Wherein, frequencies omegapAnd ωsIt is called passband edge frequency and stopband edge frequency.δpAnd δsIt is referred to as passband and resistance
The error capacitance i.e. peak waviness of band.
And peaked passband ripple quantity αp=-20lg (1-δp) dB, minimum stop-band attenuation αs=-20lg (δs)dB。
If sample frequency is ft, fp and fs is passband and stopband edge frequency, then the normalization border in units of radian
Angular frequency can be expressed as:
Thus can estimate the length of window of practical filter according to Kaiser, can then proceed in intermediate zone and stopband
Attenuation, selects window function form.Choosing of window function should meet: in the case of ensureing that stopband attenuation meets requirement, to the greatest extent
Measure the window function selecting main lobe narrow to obtain steeper intermediate zone;Reduce the relative amplitude of the maximum secondary lobe of window spectrum to reduce ripple as far as possible
Stricture of vagina peak value.Table 5 is the performance indications of various window function.
Table 5 window function performance indications
Breathing can be calculated according to Kaiser equation and heartbeat signal window function length N smallest positive integral value is respectively as follows: 227
With 302.The window function that can meet close to meeting according to stopband maximum gain has Hanning window and Hamming window, due to breath signal and
Heartbeat signal is very close in the spectral peak of frequency domain, it is therefore desirable to choose the window function that a frequency resolution is high.Hanning window and
Hamming window broadly falls into raised cosine window, is characterized in that secondary lobe is revealed few.The two is compared, and it is peaceful that the main lobe of Hamming window is slightly narrower than the Chinese
Window, and the first side lobe attenuation speed of Hamming window is faster than Hanning window, above-mentioned 2 frequency resolutions all causing Hamming window are better than
Hanning window, therefore selects Hamming window as filter window function.
Iir digital filter is referred to as recursion filter, uses in recursion type structure, i.e. structure with feedback control loop.IIR
Filter operation structure generally by time delay, be multiplied by the elementary operation such as coefficient and addition and form, Direct-type, just accurate can be combined into
Type, cascade connection type, four kinds of versions of parallel connection type, all have feedback circuit.For iir digital filter, the most frequently used design hands
Section is that the design objective of digital filter is changed into Design of Analog Filter index, so that it is determined that meet the simulation of these indexs
The transmission function of wave filter, then retells it and is converted to the transmission function of required digital filter.Its advantage is available with
The analog filter form of some classics is rapidly completed design.Conventional analog filter has Butterworth (Butterworth)
Wave filter, Chebyshev (Chebyshev) wave filter, ellipse (Ellipse) wave filter, Bezier (Bessel) wave filter etc..
Digital filter and analog filter are tied in a hundred and one ways, and the conversion between them is the conversion of s plane and z-plane, turn
The basic mode changed is exactly Impulse invariance procedure and Bilinear transformation method.Elliptic filter, it is to use elliptic method to design
The analog filter of low pass, the high pass of numeral, low pass, band be logical and the wave filter of band resistance then to use the method for conversion to obtain.?
In the design of analog filter, the design of elliptic filter is a kind of method the most complicated in several filter design method,
But the exponent number of the wave filter that it is designed is minimum, and its intermediate zone is narrow.Elliptic filter is compared other kinds of
Wave filter, has passband and the stop band ripple of minimum under conditions of exponent number is identical, and it is identical with the fluctuation of stopband at passband.
Using elliptic filter, can obtain minimum exponent number, it is achieved given wave filter technology index, elliptic filter needs
The amount of calculation wanted is minimum.Based on Matlab filter design toolbox FDATOOL, a filter parameter ibid joint design parameter one
In the case of cause, the elliptic filter exponent number minimum extracting breath signal only needs 8 rank, for extracting the oval filter of heartbeat signal
Ripple device exponent number minimum has only to 14 rank, it can be seen that operand is far smaller than FIR filter exponent number.
See Figure 19 and Figure 20, show and be respectively adopted FIR filter and iir filter is filtered separating breath signal
Time domain and frequency domain comparison diagram, from the point of view of experimental result, in the signal contrast of time domain and frequency domain, FIR filter and iir filter
Can efficiently separate out breath signal, FIR filtered signal phase-frequency characteristic is good, easily realizes linear phase, but required filtering
Device exponent number is high, and computing memory element is many, and signal delay is bigger.Iir filter realizes same design index parameter, has wave filter
The features such as exponent number is few, and required computing memory element is few, and operand is few, but there is severe phase distortion in filtered signal.
For the pluses and minuses of above two filtering method, the present invention is optimized on the basis of IIR filtering method and improves
Rear proposition zero phase iir filter, thus reach signal phase distortion is completely eliminated.
First the ultimate principle of zero phase iir filter makes signal sequence forward obtain what first time filtered by wave filter
Output, then carries out time domain upset by the output sequence of filtering for the first time, and the sequence after time domain being overturn is by same filtering
Device carries out secondary filtering, and the output after secondary filtering carries out time domain upset again, so can utilize forward time series and turn over
Turn time series to be cancelled out each other by phase shift during wave filter, thus realize the zero phase-shift of filter result.Assume that filter function is H
(z), the z of list entries is changed to X (z), then zero-phase filtering process can be expressed as follows:
Y1(ejω)=X (ejω)H(ejω);
Y2(ejω)=e-jω(N-1)Y1(e-jω);
Y3(ejω)=Y2(ejω)H(ejω);
Y4(ejω)=e-jω(N-1)Y3(e-jω);
Having above formula to derive can obtain, finally entering output can be expressed as:
Y(ejω)=X (ejω)|H(ejω)|2
Thus can realize zero phase-shift filtering, can be seen that x sequence is and square being multiplied, therefore of filter function from formula
The exponent number of wave filter can double, and because square being multiplied, so comparing compared to other filtering, the amplitude of signal can drop
Low.
Seeing Figure 21 and 22, show breath signal and heartbeat signal time-domain diagram after zero-phase filtering, Figure 23 is for breathing letter
Number and heartbeat signal separation frequency domain figure, it can be seen that zero-phase filtering on the one hand signal amplitude has portion than primary signal
Dividing decay, on the other hand the exponent number of wave filter also can double, but for hundreds of rank that FIR filtering calculates exponent number, rank
Number is the least, and amount of calculation can be substantially reduced, furthermore to signal time domain truncation during owing to filtering, signal boundary can be caused to lose
Very, after using 8 rank wave filter for breath signal, re-using zero-phase filtering exponent number can increase to 16 rank, signal both sides
Distorted signals, each loss 16 point data.But generally speaking amplitude fading is not it is obvious that both sides signal boundary loses whole letter
Number impact is not very big, and the extraction to amplitude of respiration frequency does not has a significant impact, it is possible to effectively extract signal characteristic.
The explanation of above example is only intended to help to understand method and the core concept thereof of the present invention.It is right to it should be pointed out that,
For those skilled in the art, under the premise without departing from the principles of the invention, it is also possible to the present invention is carried out
Some improvement and modification, these improve and modify in the protection domain also falling into the claims in the present invention.
Described above to the disclosed embodiments, makes professional and technical personnel in the field be capable of or uses the present invention.
Multiple amendment to these embodiments will be apparent from for those skilled in the art, as defined herein
General Principle can realize without departing from the spirit or scope of the present invention in other embodiments.Therefore, the present invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and principles disclosed herein and features of novelty phase one
The widest scope caused.
Claims (10)
1. a fatigue drive of car monitoring system, it is characterised in that be provided with in driver's cabin for detecting physiological driver
The doppler radar unit of signal intensity, described doppler radar unit includes doppler radar sensor, power supply
Module, signal pre-processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module and MCU mould
Block, wherein, described power module is used for system power supply;Described doppler radar sensor is for launching continuous wave to torso model
Radar signal also receives output-response human body respiration and the low frequency signal of heart beating change, described low frequency after echo-signal processes
Signal is successively through described signal pre-processing module, difference amplifier, active band-pass filter, breathing and heartbeat signal separation module
After MCU module signal processing, described MCU module obtain human body respiration signal and heartbeat signal and according to described breath signal and
The change of heartbeat signal judges whether driver is in fatigue driving state;
Described signal pre-processing module includes voltage follower and passive filter, and described voltage follower is for input signal
Carrying out voltage follow, described passive filter is for filtering the DC component in input signal;
Described difference amplifier is for being amplified input signal and eliminating common-mode noise;
Described active band-pass filter is for being amplified input signal and eliminating differential mode noise;
Described breathing and heartbeat signal separation module include voltage movement circuit, analog-digital converter and digital filter, described electricity
Flat circuit of moving is for the voltage range by the voltage movement of input signal to applicable digital-to-analogue conversion;Described analog-digital converter is used for
Analog quantity is converted into discrete digital quantity;Described digital filter uses digital filtering technique at frequency domain to breath signal and the heart
Jump signal to separate.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described doppler radar list
Unit also includes that acousto-optic warning module, described acousto-optic warning module are connected with described MCU module, when described MCU module judges to drive
When the person of sailing is in fatigue driving state, controls described acousto-optic warning module and send sound and light alarm signal.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described MCU module and vehicle mounted electric
Brain is connected, and acquired human body respiration signal and heartbeat signal are sent to vehicle-mounted computer.
Fatigue drive of car the most according to claim 3 monitoring system, it is characterised in that described doppler radar list
Unit also includes that wireless communication module, described wireless communication module are connected with described MCU module, and described MCU module is by described
Wireless communication module is connected with vehicle-mounted computer wirelessly.
Fatigue drive of car the most according to claim 3 monitoring system, it is characterised in that also include being arranged in steering wheel
Angle measurement unit, described angle measurement unit is used for detecting steering wheel angle change, described MCU module or institute's vehicle-mounted computer
Obtaining steering wheel angle variable quantity, when steering wheel angle variable quantity is less than preset value, described MCU module or institute's vehicle-mounted computer are even
The change of continuous detection physiological driver's signal.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described doppler radar sensor
The microwave Doppler radar detedtor probe sensor HB100 module using working frequency range to be 10.525GHz.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described passive filter is passband
Frequency is the passive RC filter of 0.1Hz-150Hz.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described active band-pass filter
Band connection frequency is 0.1Hz-10Hz.
Fatigue drive of car the most according to claim 8 monitoring system, it is characterised in that described active band-pass filter by
Quadravalence Butterworth LPF and second order butterworth high pass filter are constituted.
Fatigue drive of car the most according to claim 1 monitoring system, it is characterised in that described digital filter uses
Any one in FIR filter, iir filter or Digital Filtering with Zero Phase Error.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610891026.9A CN106297194A (en) | 2016-10-13 | 2016-10-13 | A kind of fatigue drive of car monitoring system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610891026.9A CN106297194A (en) | 2016-10-13 | 2016-10-13 | A kind of fatigue drive of car monitoring system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106297194A true CN106297194A (en) | 2017-01-04 |
Family
ID=57718613
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610891026.9A Pending CN106297194A (en) | 2016-10-13 | 2016-10-13 | A kind of fatigue drive of car monitoring system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106297194A (en) |
Cited By (16)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107316532A (en) * | 2017-05-27 | 2017-11-03 | 西南交通大学 | The method of testing and system of dispatcher's inferential capability |
CN107331122A (en) * | 2017-07-27 | 2017-11-07 | 上海蔚来汽车有限公司 | Driver tired driving monitoring method and monitoring system |
CN107845258A (en) * | 2017-10-23 | 2018-03-27 | 惠州Tcl移动通信有限公司 | A kind of intelligent identification Method of fatigue driving, device and storage medium |
CN109606375A (en) * | 2018-12-26 | 2019-04-12 | 苏州智华汽车电子有限公司 | A method of improving safe driving |
CN110009869A (en) * | 2019-04-01 | 2019-07-12 | 珠海格力电器股份有限公司 | Monitoring method, the device and system of action message |
CN110065499A (en) * | 2019-04-03 | 2019-07-30 | 森思泰克河北科技有限公司 | Real-time driving fatigue monitoring system |
CN110223686A (en) * | 2019-05-31 | 2019-09-10 | 联想(北京)有限公司 | Audio recognition method, speech recognition equipment and electronic equipment |
CN110450784A (en) * | 2019-07-30 | 2019-11-15 | 深圳普捷利科技有限公司 | A kind of driver status monitoring method and system based on fmcw radar |
CN110558966A (en) * | 2019-08-12 | 2019-12-13 | 平安科技(深圳)有限公司 | Pulse detection device |
CN110667595A (en) * | 2019-10-14 | 2020-01-10 | 深圳迈睿智能科技有限公司 | Monitoring method and monitoring system for physical state of vehicle driver |
CN111209815A (en) * | 2019-12-28 | 2020-05-29 | 杭州电子科技大学 | Non-contact fatigue driving detection method of BP neural network based on momentum optimization |
CN111568406A (en) * | 2020-05-26 | 2020-08-25 | 湖南森鹰科技有限公司 | Fatigue and health monitoring equipment |
CN111968341A (en) * | 2020-08-21 | 2020-11-20 | 无锡威孚高科技集团股份有限公司 | Fatigue driving detection system and method |
CN113593185A (en) * | 2021-07-30 | 2021-11-02 | 上海交通大学宁波人工智能研究院 | Non-contact office worker fatigue detection system and method |
CN115137941A (en) * | 2022-06-21 | 2022-10-04 | 北京中科心研科技有限公司 | Emergency awakening method and system based on fatigue recognition model and electrical stimulation |
TWI785378B (en) * | 2020-09-03 | 2022-12-01 | 雲云科技股份有限公司 | Optical image physiological monitoring system with radar detection assistance |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102715920A (en) * | 2012-07-06 | 2012-10-10 | 电子科技大学 | Detection method for vital signs of human body target |
CN103738239A (en) * | 2013-12-23 | 2014-04-23 | 青岛润鑫伟业科贸有限公司 | Driving state detection system |
US20140276090A1 (en) * | 2011-03-14 | 2014-09-18 | American Vehcular Sciences Llc | Driver health and fatigue monitoring system and method using optics |
CN104057896A (en) * | 2013-03-20 | 2014-09-24 | 厦门歌乐电子企业有限公司 | Vehicle-mounted reminding device |
US9129505B2 (en) * | 1995-06-07 | 2015-09-08 | American Vehicular Sciences Llc | Driver fatigue monitoring system and method |
WO2015160272A1 (en) * | 2014-04-14 | 2015-10-22 | Novelic D.O.O. | Mm-wave radar driver fatigue sensor apparatus |
CN105342571A (en) * | 2015-12-09 | 2016-02-24 | 许昌学院 | Intelligent terminal power supply integrated health measurement and assessment system and assessment method thereof |
-
2016
- 2016-10-13 CN CN201610891026.9A patent/CN106297194A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9129505B2 (en) * | 1995-06-07 | 2015-09-08 | American Vehicular Sciences Llc | Driver fatigue monitoring system and method |
US20140276090A1 (en) * | 2011-03-14 | 2014-09-18 | American Vehcular Sciences Llc | Driver health and fatigue monitoring system and method using optics |
CN102715920A (en) * | 2012-07-06 | 2012-10-10 | 电子科技大学 | Detection method for vital signs of human body target |
CN104057896A (en) * | 2013-03-20 | 2014-09-24 | 厦门歌乐电子企业有限公司 | Vehicle-mounted reminding device |
CN103738239A (en) * | 2013-12-23 | 2014-04-23 | 青岛润鑫伟业科贸有限公司 | Driving state detection system |
WO2015160272A1 (en) * | 2014-04-14 | 2015-10-22 | Novelic D.O.O. | Mm-wave radar driver fatigue sensor apparatus |
CN105342571A (en) * | 2015-12-09 | 2016-02-24 | 许昌学院 | Intelligent terminal power supply integrated health measurement and assessment system and assessment method thereof |
Non-Patent Citations (2)
Title |
---|
李佳晖等: ""基于雷达式非接触生命参数监测系统的安全带设计"", 《科技创新与应用》 * |
胡治等: ""非接触呼吸与心跳监护装置的研制"", 《中国医疗器械杂志》 * |
Cited By (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107316532A (en) * | 2017-05-27 | 2017-11-03 | 西南交通大学 | The method of testing and system of dispatcher's inferential capability |
CN107331122A (en) * | 2017-07-27 | 2017-11-07 | 上海蔚来汽车有限公司 | Driver tired driving monitoring method and monitoring system |
CN107845258B (en) * | 2017-10-23 | 2021-09-14 | 惠州Tcl移动通信有限公司 | Intelligent recognition method and device for fatigue driving and storage medium |
CN107845258A (en) * | 2017-10-23 | 2018-03-27 | 惠州Tcl移动通信有限公司 | A kind of intelligent identification Method of fatigue driving, device and storage medium |
CN109606375A (en) * | 2018-12-26 | 2019-04-12 | 苏州智华汽车电子有限公司 | A method of improving safe driving |
CN110009869A (en) * | 2019-04-01 | 2019-07-12 | 珠海格力电器股份有限公司 | Monitoring method, the device and system of action message |
CN110065499A (en) * | 2019-04-03 | 2019-07-30 | 森思泰克河北科技有限公司 | Real-time driving fatigue monitoring system |
CN110223686A (en) * | 2019-05-31 | 2019-09-10 | 联想(北京)有限公司 | Audio recognition method, speech recognition equipment and electronic equipment |
CN110450784A (en) * | 2019-07-30 | 2019-11-15 | 深圳普捷利科技有限公司 | A kind of driver status monitoring method and system based on fmcw radar |
CN110558966A (en) * | 2019-08-12 | 2019-12-13 | 平安科技(深圳)有限公司 | Pulse detection device |
CN110667595A (en) * | 2019-10-14 | 2020-01-10 | 深圳迈睿智能科技有限公司 | Monitoring method and monitoring system for physical state of vehicle driver |
CN111209815A (en) * | 2019-12-28 | 2020-05-29 | 杭州电子科技大学 | Non-contact fatigue driving detection method of BP neural network based on momentum optimization |
CN111209815B (en) * | 2019-12-28 | 2023-08-22 | 杭州电子科技大学 | Non-contact fatigue driving detection method based on BP neural network with momentum optimization |
CN111568406A (en) * | 2020-05-26 | 2020-08-25 | 湖南森鹰科技有限公司 | Fatigue and health monitoring equipment |
CN111968341A (en) * | 2020-08-21 | 2020-11-20 | 无锡威孚高科技集团股份有限公司 | Fatigue driving detection system and method |
TWI785378B (en) * | 2020-09-03 | 2022-12-01 | 雲云科技股份有限公司 | Optical image physiological monitoring system with radar detection assistance |
CN113593185A (en) * | 2021-07-30 | 2021-11-02 | 上海交通大学宁波人工智能研究院 | Non-contact office worker fatigue detection system and method |
CN113593185B (en) * | 2021-07-30 | 2022-11-15 | 上海交通大学宁波人工智能研究院 | Non-contact office worker fatigue detection system and method |
CN115137941A (en) * | 2022-06-21 | 2022-10-04 | 北京中科心研科技有限公司 | Emergency awakening method and system based on fatigue recognition model and electrical stimulation |
CN115137941B (en) * | 2022-06-21 | 2024-05-03 | 北京中科心研科技有限公司 | Emergency awakening method and system based on fatigue recognition model and electric stimulation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106297194A (en) | A kind of fatigue drive of car monitoring system | |
CN106491156A (en) | A kind of fatigue drive of car detection method based on Multi-source Information Fusion | |
CN106264501A (en) | A kind of bio-signal acquisition system based on continuous wave Doppler radar | |
CN106264502B (en) | A kind of contactless bio-signal acquisition method | |
Xiao et al. | Wearable heart rate monitoring intelligent sports bracelet based on Internet of things | |
Boric-Lubecke et al. | Doppler radar physiological sensing | |
Xiong et al. | Differential enhancement method for robust and accurate heart rate monitoring via microwave vital sign sensing | |
CN106821347A (en) | A kind of life detection radar breathing of FMCW broadbands and heartbeat signal extraction algorithm | |
CN102058411B (en) | UVB based multi-channel radar life detection instrument | |
CN103337132B (en) | Tumble detection method for human body based on 3-axis acceleration sensor | |
CN102715920B (en) | Detection method for vital signs of human body target | |
CN104644143A (en) | Non-contact life sign monitoring system | |
CN103690169B (en) | Respiratory information detecting method | |
CN110491515A (en) | Driving managing and control system and method based on vehicle-mounted human multi-parameter monitoring terminal | |
CN101491443A (en) | Relational model of driver fatigue and vehicle riding trail | |
CN206239402U (en) | A kind of fatigue drive of car real-time detecting system based on DSP | |
Shi et al. | Contactless person identification using cardiac radar signals | |
Yang et al. | In-car multiple targets vital sign monitoring using location-based VMD algorithm | |
CN113273978B (en) | Ultra-wideband radar-based human body respiration and heartbeat frequency detection method | |
Xing et al. | Dwatch: A reliable and low-power drowsiness detection system for drivers based on mobile devices | |
Liu et al. | Non-contact human fatigue assessment system based on millimeter wave radar | |
Qiao et al. | Learning-refined integral null space pursuit algorithm for noncontact multisubjects vital signs measurements using SFCW-UWB and IR-UWB radar | |
Chinh et al. | Short time cardio-vascular pulses estimation for dengue fever screening via continuous-wave Doppler radar using empirical mode decomposition and continuous wavelet transform | |
Shintomi et al. | Effectiveness of the heartbeat interval error and compensation method on heart rate variability analysis | |
Jing et al. | Harmonics and intermodulation products-based fuzzy logic (HIPBFL) algorithm for vital sign frequency estimation using a UWB radar |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170104 |
|
RJ01 | Rejection of invention patent application after publication |