CN105726046B - A kind of driver's alertness condition detection method - Google Patents
A kind of driver's alertness condition detection method Download PDFInfo
- Publication number
- CN105726046B CN105726046B CN201610066988.0A CN201610066988A CN105726046B CN 105726046 B CN105726046 B CN 105726046B CN 201610066988 A CN201610066988 A CN 201610066988A CN 105726046 B CN105726046 B CN 105726046B
- Authority
- CN
- China
- Prior art keywords
- driver
- eeg
- eeg signals
- processing module
- alertness
- 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.)
- Active
Links
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/16—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state
- A61B5/18—Devices for psychotechnics; Testing reaction times ; Devices for evaluating the psychological state for vehicle drivers or machine operators
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/369—Electroencephalography [EEG]
-
- 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
- A61B5/7253—Details of waveform analysis characterised by using transforms
- A61B5/7257—Details of waveform analysis characterised by using transforms using Fourier transforms
-
- 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
- A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Veterinary Medicine (AREA)
- Surgery (AREA)
- Psychiatry (AREA)
- Public Health (AREA)
- General Health & Medical Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Psychology (AREA)
- Physiology (AREA)
- Child & Adolescent Psychology (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Developmental Disabilities (AREA)
- Hospice & Palliative Care (AREA)
- Educational Technology (AREA)
- Social Psychology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of driver's alertness condition detection methods, are related to driver's active safety technologies field.It can efficiently solve when driver is in fatigue driving and prompt alarm problem.It mainly includes the following steps that：Utilize chip, Radio Transmission Technology and peripheral circuit EEG Processing module, acquisition driver is in awake or fatigue state EEG signals data and is acquired, by collected data edition redundant dictionary, the EEG signals of different periods in driver drives vehicle way are acquired in real time, EEG Processing module is transferred to by Radio Transmission Technology；EEG signals use wavelet transform (DWT) algorithm denoising, the feature extraction of the down-sampling, EEG signals of EEG signals, the pattern classification of driver's alertness state, if judgement is that there are fatigue driving situations by driver, control signal is then exported, the alarming device that control is located on pilot set shakes driver or buzzing is reminded.It is mainly used for fatigue warning of driving over a long distance.
Description
Technical field
The present invention relates to driver's active safety technologies fields.
Technical background
Traffic safety problem has become global problem.Recognize that the whole world is annual by consulting literatures data
Because the number of traffic accident death is about 500,000.Being on the increase due to the automobile in city in recent years, since driver is tired
Please traffic accident caused by sailing also is significantly increased therewith.
Judgement declines when driver is in fatigue driving, slow in reacting and operation error increases.Driver is in light
During micro- fatigue, it may appear that gear shift not in time, it is inaccurate；When driver is in moderate fatigue, operational motion is dull, sometimes even meeting
Forget to operate；It is often subconscious to operate or short time sleep phenomenon occur when driver is in severe fatigue, it can be lost when serious
Go the control ability to vehicle.During driver fatigue, it may appear that blurred vision aches all over, acts stiff, trick and swell or have
Energy is not concentrated, is slow in reacting, thinking deeply phenomena such as not thorough, rhembasmus, anxiety, irritability.If still driving vehicle reluctantly,
It may lead to traffic accident.Alertness detection currently for driver is concentrated mainly on three aspects：First, lead to
The bio signal of detection human body is crossed, arranges such as EEG signals, electromyography signal, heart rate, the alertness state of human body is judged with this；
2nd, by detecting the action of human body, such as the alertness state moved to judge human body that head is moved；3rd, by detecting human body
Frequency of wink detect the alertness state of human body.
And the human body alertness detection based on EEG signals is " gold standard " in alertness detection, relative to other lifes
For managing signal, activity of brain itself can be more directly reacted, and with higher temporal resolution.China Patent Publication No.
It is disclosed " high-speed train driving person's alertness detection method based on image surface and eye movement analysis " for CN102622600A.It is main
It is the image surface with driver and the alertness state of eye movement analysis driver, and the present invention is based on driver's EEG signals
Alertness is analyzed, and has more preferably accuracy.Brain electricity of the Chinese patent of Publication No. CN102058413B based on wavelet transformation
Signal alertness detection method.Its use wavelet function obtain EEG signals sequence wavelet coefficient characteristic value as feature
Collection, then with random forest method feature set is ranked up simplify after obtained using sample training support vector machines, and using training
Support vector machines to EEG signals carry out alertness detection.The Chinese patent application of application number 201520878190.7 discloses
A kind of wearable driver's eeg signal acquisition headband.Its construction primarily directed to electroencephalogramsignal signal collection equipment has been done accordingly
Description, the processing of EEG signals is described in detail with algorithm, the purpose of the application needs to utilize " headband "
It realizes.
Invention content
The object of the present invention is to provide a kind of driver's alertness condition detection methods, it can be efficiently solved at driver
Alarm problem is prompted when fatigue driving.
The technical scheme adopted by the invention for realizing the object of the invention is：A kind of driver's alertness condition detection method,
Include the following steps：
1st, a kind of driver's alertness condition detection method, includes the following steps：
The first step, constructing function module
Using including having the development board of the dsp chip TMS320F28335 of wireless transmission function, build at EEG signals
Manage module；
The acquisition of second step, driver's EEG signals
First, one eeg signal acquisition headband of the head-mount of driver is in awake or fatigue state to driver
EEG signals data be acquired, by collected data edition redundant dictionary, and be stored in EEG Processing module；
Secondly, the EEG signals of different periods in driver drives vehicle way are acquired in real time, collected driver's EEG signals lead to
It crosses Radio Transmission Technology and is transferred to EEG Processing module；
The denoising of third step, EEG signals
EEG Processing module uses wavelet transform (DWT) algorithm pair to the EEG signals of collected driver
Original EEG signals carry out 6 layers of decomposition of a 5dB small echo, obtain subband wavelet details coefficient (Di, i=1,2,3,4,5,6)
With approximation coefficient (Ai, i=1,2,3,4,5,6)；By rebuilding decomposition coefficient D3, D4, D5, D6Remove the low frequency in original signal
With High-frequency Interference so as to obtain useful EEG signals；
The down-sampling of 4th step, EEG signals
EEG Processing module carries out the EEG signals by the driver after denoising down-sampling processing, sampling frequency
Rate is 128Hz；
The feature extraction of 5th step, EEG signals
EEG Processing module carries out based on Fast Fourier Transform (FFT) the EEG signals after down-sampling processing
(FFT) feature extraction of algorithm, fft algorithm are 128 points；
The pattern classification of 6th step, driver's alertness state
EEG Processing module carries out the EEG signals of the driver Jing Guo feature extraction sparse point based on K-SVD
Class represents the pattern classification of algorithm, obtains the alertness state class (y) of driver；
Class (y)=argmini||y-Dα′i||2
Wherein y is data D=[D to be sorteda,Dd] be driver's alertness state redundant dictionary, DaAt driver
In the redundant dictionary of waking state, DdIt is in the redundant dictionary of fatigue state for driver, α is data to be sorted, the sparse system of y
Number；
7th step, warning reminding
Driver's alertness state that EEG Processing module transmits, if it is that there are fatigue driving feelings by driver to judge
Condition then exports control signal, and the alarming device that control is located on pilot set shakes driver or buzzing is reminded.
Compared with prior art, the beneficial effects of the invention are as follows：
First, the fft algorithm of N=128 is employed in feature extraction phases, is calculated than traditional discrete Fourier transform (DFT)
Method is compared, and greatly reduces calculation amount so that the feature extraction time is only 1/37 of DFT algorithms about, entire so as to reduce
The time of process.
2nd, classified in the pattern classification stage using the rarefaction representation based on K-SVD and calculated.The purpose of sparse signal representation is exactly
Signal is represented with atom as few as possible, can obtain the more succinct expression side of signal in given super complete dictionary
Formula, so as to which us be made more easily to obtain the information contained in signal, K-SVD is a kind of dictionary training algorithm of classics, according to
According to error minimum principle, SVD decomposition is carried out to error term, select to make the decomposition item of error minimum as newer dictionary atom with
Corresponding atomic, the solution by continuous iteration so as to be optimized.
Description of the drawings
The alertness detection algorithm based on EEG signals that Fig. 1 is the present invention realizes flow chart.
Fig. 2 compares figure for EEG signals of the present invention in the forward and backward time domain of denoising.
Fig. 3 compares figure for EEG signals of the present invention in the forward and backward frequency domain of denoising.
Fig. 4 is waking state and fatigue state time domain comparison diagram after EEG signals denoising of the present invention.
Fig. 5 is waking state and fatigue state frequency domain comparison diagram after EEG signals denoising of the present invention.
Specific implementation method
Embodiment one, the experimental subjects are a tired driver driven through three hours or more, are denoted as driver 1.
Its specific implementation method is that a kind of driver's alertness condition detection method includes the following steps：
A, the acquisition of driver's EEG signals
One eeg signal acquisition cap of head-mount of driver, driver's eeg signal acquisition cap pair in driving
The EEG signals of driver are acquired, and obtain the EEG signals f of driver 11, and the driver's EEG signals f acquired1Pass through
Radio Transmission Technology is transferred to EEG Processing module；
B, the denoising of driver's EEG signals
EEG Processing module is to the EEG signals f of the collected driver of eeg signal acquisition cap1With DWT algorithms
Denoising is carried out, obtains driver's EEG signals g after denoising1；
C, the down-sampling of driver's EEG signals
EEG Processing module is to the EEG signals g by the driver after denoising1Down-sampling processing is carried out, is obtained
Driver's EEG signals k after down-sampling1, to reduce the data volume of sample；
D, the feature extraction of driver's EEG signals
EEG Processing module is to driver's EEG signals k after down-sampling processing1It carries out based on quick Fu
In leaf transformation (FFT) algorithm feature extraction, obtain data Y to be sorted1；
E, the pattern classification of driver's alertness state
EEG Processing module carries out the EEG signals of the driver Jing Guo feature extraction sparse point based on K-SVD
Class represents the pattern classification of algorithm, obtains the alertness state class (y) of driver；
Class (y)=argmini||Y1-Dα′i||2
Wherein Y1For data to be sorted, D=[Da,Dd] be driver status redundant dictionary, DaIt is in clear for driver
The redundant dictionary for the state of waking up, DdThe redundant dictionary of fatigue state is in for driver, α is the sparse coefficient of data y to be sorted；
Obtained result is in fatigue state for driver, and the confidence level of test is 0.9565.
Embodiment two/tri-/tetra- repeats the operation of more than A~E steps.
The method of the present invention see the table below driver's alertness detection test result.
| Driver numbers | 1 | 2 | 3 | 4 |
| Experimental result | Fatigue | Fatigue | Fatigue | It is awake |
| Confidence level | 0.9565 | 0.9504 | 0.9647 | 0.9387 |
As it can be seen that the present invention has higher confidence level in the detection of driver's alertness.
Claims (1)
1. a kind of driver's alertness condition detection method, includes the following steps：
The first step, constructing function module
Using including having the development board of the dsp chip TMS320F28335 of wireless transmission function, EEG Processing mould is built
Block；
The acquisition of second step, driver's EEG signals
First, one eeg signal acquisition headband of the head-mount of driver is in driver in awake or fatigue state brain
Electrical signal data is acquired, and by collected data edition redundant dictionary, and is existed in storage EEG Processing module；Its
It is secondary, the EEG signals of different periods in driver drives vehicle way are acquired in real time, collected driver's EEG signals pass through
Radio Transmission Technology is transferred to EEG Processing module；
The denoising of third step, EEG signals
EEG Processing module is to the EEG signals of collected driver with wavelet transform (DWT) algorithm to original
EEG signals carry out 6 layers of decomposition of a 5dB small echo, obtain subband wavelet details coefficient (Di, i=1,2,3,4,5,6) and it is near
Like coefficient (Ai, i=1,2,3,4,5,6)；By rebuilding decomposition coefficient D3, D4, D5, D6Remove the low frequency and high frequency in original signal
Interference is so as to obtain useful EEG signals；
The down-sampling of 4th step, EEG signals
To carrying out down-sampling processing by the EEG signals of the driver after denoising, sample frequency is EEG Processing module
128Hz；
The feature extraction of 5th step, EEG signals
EEG Processing module carries out based on Fast Fourier Transform (FFT) (FFT) EEG signals after down-sampling processing
The feature extraction of algorithm, fast fourier transform algorithm are 128 points；
The pattern classification of 6th step, driver's alertness state
EEG Processing module carries out the EEG signals of the driver Jing Guo feature extraction the sparse classification chart based on K-SVD
Show the pattern classification of algorithm, obtain the alertness state class (y) of driver；
Class (y)=argmini||y-Dα'i||2
Wherein y is data D=[D to be sorteda,Dd] be driver's alertness state redundant dictionary, DaIt is in clear for driver
The redundant dictionary for the state of waking up, DdThe redundant dictionary of fatigue state is in for driver, α is the sparse coefficient of data y to be sorted；
7th step, warning reminding
Driver's alertness state that EEG Processing module transmits, if judging to be driver there are fatigue driving situation,
Output control signal, the alarming device that control is located on pilot set shakes driver or buzzing is reminded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066988.0A CN105726046B (en) | 2016-01-29 | 2016-01-29 | A kind of driver's alertness condition detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610066988.0A CN105726046B (en) | 2016-01-29 | 2016-01-29 | A kind of driver's alertness condition detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105726046A CN105726046A (en) | 2016-07-06 |
| CN105726046B true CN105726046B (en) | 2018-06-19 |
Family
ID=56247181
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610066988.0A Active CN105726046B (en) | 2016-01-29 | 2016-01-29 | A kind of driver's alertness condition detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105726046B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106562787A (en) * | 2016-10-28 | 2017-04-19 | 许昌学院 | High-altitude outward bound training monitoring system based on surface electromyogram signals |
| CN108498092B (en) * | 2017-02-28 | 2021-09-14 | 中国航天员科研训练中心 | Error early warning method and system based on electroencephalogram characteristics |
| CN106919956A (en) * | 2017-03-09 | 2017-07-04 | 温州大学 | Brain wave age forecasting system based on random forest |
| CN107334481B (en) * | 2017-05-15 | 2020-04-28 | 清华大学 | Driving distraction detection method and system |
| CN112041910B (en) * | 2018-03-30 | 2023-08-18 | 索尼半导体解决方案公司 | Information processing apparatus, mobile device, method, and program |
| CN108742603A (en) * | 2018-04-03 | 2018-11-06 | 山东大学 | It is a kind of using kernel function and dictionary to the brain electric detection method and device of learning model |
| CN111227851A (en) * | 2018-11-29 | 2020-06-05 | 天津职业技术师范大学 | Driver alertness detection mechanism based on electroencephalogram signals, detection method and application |
| CN110464371A (en) * | 2019-08-29 | 2019-11-19 | 苏州中科先进技术研究院有限公司 | Method for detecting fatigue driving and system based on machine learning |
| CN110811573A (en) * | 2019-10-29 | 2020-02-21 | 依脉人工智能医疗科技(天津)有限公司 | Device and method for regulating and controlling brain alertness based on photoelectric pulse feedback |
| CN111242065B (en) * | 2020-01-17 | 2020-10-13 | 江苏润杨汽车零部件制造有限公司 | Portable vehicle-mounted intelligent driving system |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2303627A4 (en) * | 2008-07-18 | 2015-07-29 | Optalert Pty Ltd | Alertness sensing device |
| CN102119857B (en) * | 2011-02-15 | 2012-09-19 | 陕西师范大学 | Electroencephalogram detecting system and method for fatigue driving on basis of matching pursuit algorithm |
| CN102274032A (en) * | 2011-05-10 | 2011-12-14 | 北京师范大学 | Driver fatigue detection system based on electroencephalographic (EEG) signals |
| WO2013008305A1 (en) * | 2011-07-11 | 2013-01-17 | トヨタ自動車株式会社 | Eyelid detection device |
| CN105011932A (en) * | 2015-08-11 | 2015-11-04 | 西安科技大学 | Fatigue driving electroencephalogram monitoring method based on degree of meditation and degree of concentration |
-
2016
- 2016-01-29 CN CN201610066988.0A patent/CN105726046B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN105726046A (en) | 2016-07-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105726046B (en) | A kind of driver's alertness condition detection method | |
| Sadiq et al. | Motor imagery EEG signals decoding by multivariate empirical wavelet transform-based framework for robust brain–computer interfaces | |
| Zheng et al. | A multimodal approach to estimating vigilance using EEG and forehead EOG | |
| CN207979669U (en) | Vehicle multi-mode formula biological response system | |
| Monteiro et al. | Using EEG for mental fatigue assessment: A comprehensive look into the current state of the art | |
| Murugan et al. | Detection and analysis: Driver state with electrocardiogram (ECG) | |
| da Silveira et al. | Automated drowsiness detection through wavelet packet analysis of a single EEG channel | |
| Chai et al. | Driver fatigue classification with independent component by entropy rate bound minimization analysis in an EEG-based system | |
| Lin et al. | Generalized EEG-based drowsiness prediction system by using a self-organizing neural fuzzy system | |
| Ahmad et al. | Drowsy driver identification using eye blink detection | |
| Islam et al. | Multiband tangent space mapping and feature selection for classification of EEG during motor imagery | |
| Belakhdar et al. | Single-channel-based automatic drowsiness detection architecture with a reduced number of EEG features | |
| Wu et al. | Driving behaviour‐based event data recorder | |
| Majumder et al. | On-board drowsiness detection using EEG: Current status and future prospects | |
| Khare et al. | Automatic drowsiness detection based on variational non-linear chirp mode decomposition using electroencephalogram signals | |
| EP3932303A1 (en) | Method and system for detecting attention | |
| Thirunavukkarasu et al. | A smart HMI for driving safety using emotion prediction of EEG signals | |
| Lu et al. | Effects of route familiarity on drivers’ psychological conditions: Based on driving behaviour and driving environment | |
| Chen et al. | Driver vigilance detection for high-speed rail using fusion of multiple physiological signals and deep learning | |
| Liu et al. | Unsupervised fNIRS feature extraction with CAE and ESN autoencoder for driver cognitive load classification | |
| Hossan et al. | A smart system for driver's fatigue detection, remote notification and semi-automatic parking of vehicles to prevent road accidents | |
| Wang et al. | EEG-based closed-loop neurofeedback for attention monitoring and training in young adults | |
| Singh et al. | Physical and physiological drowsiness detection methods | |
| Zeng et al. | Classifying driving fatigue by using EEG signals | |
| Uyulan et al. | Entropy-based feature extraction technique in conjunction with wavelet packet transform for multi-mental task classification |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20201203 Address after: 215134 south side of the 3rd floor, R & D building, China auto parts industrial base, No. 19, aighao Road, Weitang Town, Xiangcheng District, Suzhou City, Jiangsu Province Patentee after: Suzhou Zhenwei Town Construction Development Co., Ltd Address before: 610031 Sichuan City, Chengdu Province, No. two North Ring Road, No. 111 Patentee before: SOUTHWEST JIAOTONG University |