CN109875582A - Driving fatigue detection method and system - Google Patents
Driving fatigue detection method and system Download PDFInfo
- Publication number
- CN109875582A CN109875582A CN201910076624.4A CN201910076624A CN109875582A CN 109875582 A CN109875582 A CN 109875582A CN 201910076624 A CN201910076624 A CN 201910076624A CN 109875582 A CN109875582 A CN 109875582A
- Authority
- CN
- China
- Prior art keywords
- fatigue
- driver
- vector
- eeg signals
- value
- 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
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of driving fatigue detection method and systems, this method comprises: acquiring the EEG signals of driver by electroencephalogramsignal signal collection equipment；Collected EEG signals are calculated, to obtain fatigue state value, and the fatigue state value is sent to mobile terminal and is shown；The fatigue state value is compared with the off-line analysis result prestored, to judge whether driver is currently in a state of fatigue；If driver is currently at fatigue state, it then controls alarm set and issues fatigue prompting, and the current geographic position and current time of current EEG signals and driver are uploaded to server and saved, and the fatigue state of driver is shown in map interface by the monitoring client of the server.The present invention promotes fatigue driving accuracy in detection, reduces the harm of fatigue driving.
Description
Technical field
The present invention relates to driving safety technical fields, more particularly to a kind of driving fatigue detection method and system.
Background technique
Driver information acquisition, information processing and manipulation caused by driving fatigue refers to due to continuous driving for a long time
The phenomenon that ability declines.Driver is during long-duration driving, and Yi Yinfa driving fatigue is anti-to emergency event so as to cause it
Extension between seasonable, influences driving safety.In order to avoid driving fatigue it is necessary to when there is fatigue state in driver to driving
Member is reminded.
In passenger traffic, especially long-distance passenger transportation, due to the driving that driver is uninteresting for a long time, it is easy to there is fatigue, and it is this
Fatigue driving is that long-distance passenger transportation the main reason for accident occurs and pernicious friendship occurs especially on the road of some complexity again
Interpreter thus frequently occur, therefore in order to be avoided that this traffic accident as caused by fatigue driving, fatigue is carried out to driver
Detection is particularly important, and is nowadays had much to the method for driver fatigue state detection, but has the shortcomings that respective, such as is had
Based on position of driver, the detection methods such as steering wheel dynamics are held, this detection method accuracy rate is low；Have based on vehicle driving trace
Detection method, this detection method requires have detector on highway, but many complex road conditions are not, at high cost now,
And accuracy rate is low；There is the detection method based on physiological driver's feature, such as frequency of nodding, facial expression, eyes etc., this
The accuracy rate that kind detected is low, and false detection rate is high.Therefore, existing detection method is not particularly suited for the fatigue detecting of driver,
It is particularly unsuitable for the fatigue driving detection of long-distance passenger transportation driver.
Summary of the invention
For this purpose, an object of the present invention is to provide a kind of driving fatigue detection method, to promote fatigue driving detection
Accuracy reduces the harm of fatigue driving.
A kind of driving fatigue detection method, comprising:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value, and the fatigue state value are sent to
Mobile terminal is shown；
The fatigue state value is compared with the off-line analysis result prestored, to judge whether driver is currently in
Fatigue state；
If driver is currently at fatigue state, controls alarm set and issue fatigue and remind, and by current brain telecommunications
Number and the current geographic position and current time of driver be uploaded to server and save, and pass through the server
Monitoring client is shown the fatigue state of driver in map interface.
The driving fatigue detection method provided according to the present invention, at least has the advantages that
(1) EEG signals are the direct external reactions of brain states, are detected using EEG signals to driver fatigue
The state of driver can be really reacted, discrimination is high；
(2) it is shown by the way that fatigue state value is sent to mobile terminal, driver can be allowed to understand oneself in real time
State, promoted safety；
(3) by the way that the current geographic position of current EEG signals and driver and current time are uploaded to service
Device is saved, and is shown in map interface to the fatigue state of driver by the monitoring client of server, Neng Gourang
Traffic control department intuitively monitors local driver tired driving state in real time, to carry out external intervention and prompting, reduces tired
Please the harm sailed.
In addition, above-mentioned driving fatigue detection method according to the present invention, can also have the following additional technical features:
Further, described that collected EEG signals are calculated, the step of to obtain fatigue state value in, use
The method of Sample Entropy calculates fatigue state value, specifically includes:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals
For { Xi}={ X1,X2…Xn, total length is denoted as N, if Embedded dimensions m and similar tolerance r, according to original EEG signals reconstruct one
A similar tolerance r and m dimensional vector
Xi=[Xi,Xi+1,....Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from sum
The ratio of N-m-1, is denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series
Is defined as:
When N is Finite Number, above formula is expressed as:
Further, the off-line analysis result is obtained using following methods:
It according to sample frequency truncated data, is saved for once testing for H hours EEG signals, obtains 2 M*N
Vector, wherein 2 indicate two leads of driver's forehead, M is the sample number of H hour, and N is sample frequency, calculates each sample
Entropy finally obtain the vector of 2 M, for a driver, acquire S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
Further, described pair of obtained discretization entropy progress matrix calculates the step of obtaining fatigue threshold and specifically wraps
It includes:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with two o'clock
Mean value replace, vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation and becomes
Then gesture carries out dimension unification, to obtain fatigue threshold.
Further, the step of dimension unification specifically includes:
Acquire the smallest dimension of S experiment；
The vector for being greater than the smallest dimension is left out the several values in front, to keep dimension unification；
To two matrixes, according to vector is classified as, the Fisher distance between two neighboring vector, calculation method are asked are as follows:
Wherein, the mean value of μ representation vector, the standard deviation of σ representation vector；
To obtained vector maximizing, be calculated apart from maximum two adjacent vectors, and select maximum value as
Fatigue threshold.
Further, the method also includes:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value；
At interval of preset time, the current geographic position and current time of the fatigue state value and driver are uploaded
To server；
The fatigue state of driver is shown in map interface by the monitoring client of the server, different is tired
Labor state value is shown in map interface by different colors.
It is accurate to promote fatigue driving detection it is another object of the present invention to propose a kind of driving fatigue detection system
Degree, reduces the harm of fatigue driving.
A kind of driving fatigue detection system, the system comprises:
Signal acquisition module, for acquiring the EEG signals of driver by electroencephalogramsignal signal collection equipment；
Sending module is calculated, for calculating collected EEG signals, to obtain fatigue state value, and will be described
Fatigue state value is sent to mobile terminal and is shown；
Judgment module is compared, for comparing the fatigue state value with the off-line analysis result prestored, with judgement
Whether driver is currently in a state of fatigue；
Uploading module is reminded, if being currently at fatigue state for driver, alarm set is controlled and issues fatigue prompting,
And the current geographic position and current time of current EEG signals and driver are uploaded to server and saved, and
The fatigue state of driver is shown in map interface by the monitoring client of the server.
The driving fatigue detection system provided according to the present invention, at least has the advantages that
(1) EEG signals are the direct external reactions of brain states, are detected using EEG signals to driver fatigue
The state of driver can be really reacted, discrimination is high；
(2) it is shown by the way that fatigue state value is sent to mobile terminal, driver can be allowed to understand oneself in real time
State, promoted safety；
(3) by the way that the current geographic position of current EEG signals and driver and current time are uploaded to service
Device is saved, and is shown in map interface to the fatigue state of driver by the monitoring client of server, Neng Gourang
Traffic control department intuitively monitors local driver tired driving state in real time, to carry out external intervention and prompting, reduces tired
Please the harm sailed.
In addition, above-mentioned driving fatigue detection system according to the present invention, can also have the following additional technical features:
Further, the calculating sending module is specifically used for:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals
For { Xi}={ X1,X2…Xn, total length is denoted as N, if Embedded dimensions m and similar tolerance r, according to original EEG signals reconstruct one
A similar tolerance r and m dimensional vector
Xi=[Xi,Xi+1,····Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from sum
The ratio of N-m-1, is denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series
Is defined as:
When N is Finite Number, above formula is expressed as:
Further, the comparison judgment module is specifically used for:
It according to sample frequency truncated data, is saved for once testing for H hours EEG signals, obtains 2 M*N
Vector, wherein 2 indicate two leads of driver's forehead, M is the sample number of H hour, and N is sample frequency, calculates each sample
Entropy finally obtain the vector of 2 M, for a driver, acquire S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
Further, the comparison judgment module is specifically used for:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with two o'clock
Mean value replace, vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation and becomes
Then gesture carries out dimension unification, to obtain fatigue threshold.
Detailed description of the invention
The above-mentioned and/or additional aspect and advantage of the embodiment of the present invention are from the description of the embodiment in conjunction with the following figures
It will be apparent and be readily appreciated that, in which:
Fig. 1 is the flow chart of driving fatigue detection method according to a first embodiment of the present invention；
Fig. 2 is the structural schematic diagram of driving fatigue detection system according to a second embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art
Every other embodiment obtained without making creative work, shall fall within the protection scope of the present invention.
Referring to Fig. 1, the driving fatigue detection method that first embodiment of the invention proposes, including step S101~S103:
S101 acquires the EEG signals of driver by electroencephalogramsignal signal collection equipment.
Wherein, it specifically can use portable electroencephalogramsignal signal collection equipment (such as the two lead brain telecommunications of forehead of neurosky
Number acquisition equipment) acquisition two lead of driver's forehead EEG signals, multiple continuous acquisition is carried out to driver, EEG signals
Transmission mode includes wire transmission mode, also includes wireless transmission such as bluetooth, network.
Sample frequency may be configured as 126Hz, 512Hz, 1024Hz, be also possible to the integers such as 200Hz, 500Hz, 1000Hz frequency
Rate can be selected, herein with no restrictions according to the actual situation with frequency.Collected EEG signals are stored in buffering first
In area, after saving a period of time, then data processing is carried out.Signal is transmitted to data processing module by receiving module；
S102 calculates collected EEG signals, to obtain fatigue state value, and the fatigue state value is sent out
It send to mobile terminal and is shown.
Wherein, the fatigue state value which calculates can be the synchronism between two lead signals, be also possible to two
The feature of a lead signals.
When it is implemented, calculate collected EEG signals, the step of to obtain fatigue state value in, can adopt
Fatigue state value is calculated with the method for Sample Entropy, is specifically included:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals
For { Xi}={ X1, X2…Xn, total length is denoted as N, if Embedded dimensions m and similar tolerance r, according to original EEG signals reconstruct one
A similar tolerance r and m dimensional vector
Xi=[Xi,Xi+1,....Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from sum
The ratio of N-m-1, is denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series
Is defined as:
When N is Finite Number, above formula is expressed as:
Mobile terminal can be the intelligent mobile terminals such as the mobile phone of user, PDA, and fatigue state value is sent to mobile terminal
It is shown, driver can be allowed to know the fatigue state of oneself constantly.
The fatigue state value is compared with the off-line analysis result prestored, is to judge driver currently by S103
It is no in a state of fatigue.
Wherein, off-line analysis result needs obtain and are stored in local in advance, when it is implemented, off-line analysis result can be with
It is obtained using following methods:
It according to sample frequency truncated data, is saved for once testing for H hours EEG signals, obtains 2 M*N
Vector, wherein 2 indicate two leads of driver's forehead, M is the sample number of H hour, and N is sample frequency, calculates each sample
Entropy finally obtain the vector of 2 M, for a driver, acquire S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
Wherein, described pair of obtained discretization entropy progress matrix calculates the step of obtaining fatigue threshold and specifically includes:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with two o'clock
Mean value replace, vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation and becomes
Then gesture carries out dimension unification, to obtain fatigue threshold.
The step of dimension unification, specifically includes:
Acquire the smallest dimension of S experiment；
The vector for being greater than the smallest dimension is left out the several values in front, to keep dimension unification；
To two matrixes, according to vector is classified as, the Fisher distance between two neighboring vector, calculation method are asked are as follows:
Wherein, the mean value of μ representation vector, the standard deviation of σ representation vector；
To obtained vector maximizing, be calculated apart from maximum two adjacent vectors, and select maximum value as
Threshold in fatigue.
The calculation method of off-line analysis result is illustrated below with one:
With golden imperial 45 middle buses, equipment is acquired using 8 lead portable brain electrics, setting sample frequency is 1000Hz,
Mobile terminal uses certain smart phone, and transmission network selects vehicle-mounted wifi, adopts every time in the storage buffering of smart phone for one
Sample period, that is, 1000, for data using not stacked system, test route is long-distance high speed, after the time is 12 noon, often
3 hours of secondary continuous driving, driver are 0.7 according to recommendation, the fatigue state value of input.Fatigue mechanisms method is using step
The method of Sample Entropy described in S102 carries out.
Then, off-line analysis is carried out according to the parameter of setting (including m, r) first, it is right according to sample frequency truncated data
It is saved in primary experiment for 3 hours EEG signals, obtains the vector of 2 10800*1000, wherein 2 indicate driver
Two lead of forehead, 10800 be the sample number of 3 hours, and 1000 be sample frequency, and the entropy for calculating each sample finally obtains 2
A 10800 vector (wherein entropy parameter m=2, r=0.25) acquires 10 samples as offline point for a driver
Analyse sample；
To 2 matrix datas, discretization is carried out to retain the method for 2 decimals；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis as a result, specifically including:
With preset step-length a cycle calculations step S1~S2, wherein a=0.01:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with two o'clock
Mean value replace, vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Above-mentioned steps calculate the tired changes of entropy trend in 3 hours of available driver, because there is 10 experiments,
So last available 10 variation tendencies, due to the 2 smaller dimension vector of above-mentioned calculating, obtained result is tested 10 times
And it is different, in order to calculate threshold value, by its dimension unification, step is
Acquire the smallest dimension of 10 experiments；
The vector for being greater than the smallest dimension is left out the several values in front, (reason is that data are leaned on to keep dimension unification
Preceding, the fatigue state probability occurred where the time is small, and a hour later occurs for fatigue state maximum probability), this implementation
Obtaining two vector dimensions is 21 and 19 respectively；That is two matrixes 21*10 and 19*10 are obtained.Wherein 21 and 19 be meter
Obtained dimension, 10 be ten experiments.
To two matrixes, according to vector is classified as, the Fisher distance between two neighboring vector, calculation method are asked are as follows:
Wherein, the mean value of μ representation vector, the standard deviation of σ representation vector；
To obtained vector maximizing, be calculated apart from maximum two adjacent vectors, and select maximum value as
Fatigue threshold.Specifically, last 2 samples have obtained the vector of 20 peacekeepings 18 dimension in the present embodiment, maximum are asked to two vectors
Value, can be calculated apart from maximum two adjacent vectors, what this implementation obtained is 16 and 11, that is to say, that for an electricity
Meta position is maximum when pole is 16 and 17, and meta position is maximum when being 11 and 12 for an other electrode, for 17 times of first electrode
Position selects maximum value as threshold value, and for second electrode, meta position maximum value is as threshold value when selecting 12.This implementation two values point
It is not 0.68 and 0.57.
Finally determine the fatigue threshold of alarm are as follows: if left side electrode is more than 0.68, then deciding that driver is currently at
Fatigue state, if the right electrode is more than 0.57, determine driver be currently at fatigue state, as long as when it is implemented, the two its
One of be more than threshold value, decide that driver is currently at fatigue state.It, can be in addition, it is contemplated that the subjective feeling of driver
Increase subject's input value, as correction, such as subject's input value is 0.7.
S104 controls alarm set and issues fatigue and remind, and by current brain if driver is currently at fatigue state
The current geographic position and current time of electric signal and driver are uploaded to server and save, and pass through the service
The monitoring client of device is shown the fatigue state of driver in map interface.
Wherein, after carrying out off-line analysis, the fatigue threshold of the right and left electrode has been obtained, has been 0.68,0.57 respectively,
0.7 input value as user makes reference as dynamic adjustment.Then be open to traffic test, and driver is in identical road conditions
With on the time drive 3 hours, entropy of calculatings per second, if continuously there is no be more than threshold value the case where, per minute hair
Send a fatigue state value, geographical location (can realize by GPS) and time to server, if the feelings more than threshold value occur
The EEG signals of this second are then also sent to server and are saved by condition；If driver is dissatisfied to the alarm value, illustrate the threshold
It is worth too low, which is increased, is adjusted by input value, increasing degree is, for example, 0.02.
If determining driver is currently at fatigue state (entropy calculated has been more than fatigue threshold), prompting is controlled
Device issues fatigue and reminds, and specifically can be the various ways such as sound, flash of light.
In addition, as an alternative embodiment, the driving fatigue detection method of the present embodiment can also include:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value；
At interval of preset time, e.g. at interval of 5 minutes, by the fatigue state value and the current geographic of driver
Position and current time are uploaded to server；
The fatigue state of driver is shown in map interface by the monitoring client of the server, different is tired
Labor state value is shown in map interface by different colors, and traffic jam situation schematic diagram on map is similar to, if
Fatigue state value is lower than fatigue threshold, just with the position of green display current driver's；If fatigue state value is equal to fatigue threshold,
It is just shown with yellow, shows the position of current driver's；If fatigue state value is greater than fatigue threshold, just currently driven with red display
The position for the person of sailing, so as to allow traffic control department intuitively to monitor local driver tired driving state in real time, to carry out
External intervention and prompting reduce the harm of fatigue driving.
According to driving fatigue detection method provided in this embodiment, at least have the advantages that
(1) EEG signals are the direct external reactions of brain states, are detected using EEG signals to driver fatigue
The state of driver can be really reacted, discrimination is high；
(2) it is shown by the way that fatigue state value is sent to mobile terminal, driver can be allowed to understand oneself in real time
State, promoted safety；
(3) by the way that the current geographic position of current EEG signals and driver and current time are uploaded to service
Device is saved, and is shown in map interface to the fatigue state of driver by the monitoring client of server, Neng Gourang
Traffic control department intuitively monitors local driver tired driving state in real time, to carry out external intervention and prompting, reduces tired
Please the harm sailed.
In addition, driving fatigue detection method provided in this embodiment is more suitable for the fatigue driving detection of car class driver, this
Be because, one, motor bus driver is usually Professional drivers, therefore is easy to forcing to wear fatigue detecting equipment；Second is that driver
Space it is big, be easily placed detection device；Third is that the In-vehicle networking facility that motor bus carries is complete, transmission speed is fast.
Referring to Fig. 2, based on the same inventive concept, the driving fatigue detection system that second embodiment of the invention proposes, institute
The system of stating includes:
Signal acquisition module 10, for acquiring the EEG signals of driver by electroencephalogramsignal signal collection equipment；
Sending module 20 is calculated, for calculating collected EEG signals, to obtain fatigue state value, and by institute
It states fatigue state value and is sent to mobile terminal and shown；
Judgment module 30 is compared, for comparing the fatigue state value with the off-line analysis result prestored, to sentence
Whether disconnected driver is currently in a state of fatigue；
Uploading module 40 is reminded, if being currently at fatigue state for driver, alarm set sending fatigue is controlled and mentions
It wakes up, and the current geographic position and current time of current EEG signals and driver is uploaded to server and saved,
And the fatigue state of driver is shown in map interface by the monitoring client of the server.
Wherein, the calculating sending module 20 is specifically used for:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals
For { Xi}={ X1, X2…Xn, total length is denoted as N, if Embedded dimensions m and similar tolerance r, according to original EEG signals reconstruct one
A similar tolerance r and m dimensional vector
Xi=[Xi,Xi+1,····Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from sum
The ratio of N-m-1, is denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series
Is defined as:
When N is Finite Number, above formula is expressed as:
Wherein, the comparison judgment module 30 is specifically used for:
It according to sample frequency truncated data, is saved for once testing for H hours EEG signals, obtains 2 M*N
Vector, wherein 2 indicate two leads of driver's forehead, M is the sample number of H hour, and N is sample frequency, calculates each sample
Entropy finally obtain the vector of 2 M, for a driver, acquire S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
Wherein, the comparison judgment module 30 is specifically used for:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with two o'clock
Mean value replace, vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation and becomes
Then gesture carries out dimension unification, to obtain fatigue threshold.
Wherein, the step of dimension unification specifically includes:
Acquire the smallest dimension of S experiment；
The vector for being greater than the smallest dimension is left out the several values in front, to keep dimension unification；
To two matrixes, according to vector is classified as, the Fisher distance between two neighboring vector, calculation method are asked are as follows:
Wherein, the mean value of μ representation vector, the standard deviation of σ representation vector；
To obtained vector maximizing, be calculated apart from maximum two adjacent vectors, and select maximum value as
Fatigue threshold.
In the present embodiment, further includes:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value；
The prompting uploading module 40 is also used at interval of preset time, by working as the fatigue state value and driver
Preceding geographical location and current time are uploaded to server, by the monitoring client of the server to driver's in map interface
Fatigue state is shown, and different fatigue state values is shown in map interface by different colors.
According to driving fatigue detection system provided in this embodiment, at least have the advantages that
(1) EEG signals are the direct external reactions of brain states, are detected using EEG signals to driver fatigue
The state of driver can be really reacted, discrimination is high；
(2) it is shown by the way that fatigue state value is sent to mobile terminal, driver can be allowed to understand oneself in real time
State, promoted safety；
(3) by the way that the current geographic position of current EEG signals and driver and current time are uploaded to service
Device is saved, and is shown in map interface to the fatigue state of driver by the monitoring client of server, Neng Gourang
Traffic control department intuitively monitors local driver tired driving state in real time, to carry out external intervention and prompting, reduces tired
Please the harm sailed.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system, including the system of processor or other can be held from instruction
The instruction fetch of row system, device or equipment and the system executed instruction) it uses, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium ", which can be, any may include, stores, communicates, propagates or pass
Defeated program is for instruction execution system, device or equipment or the dress used in conjunction with these instruction execution systems, device or equipment
It sets.
The more specific example (non-exhaustive list) of computer-readable medium include the following: there are one or more wirings
Electrical connection section (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only memory
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can then be edited, be interpreted or when necessary with it for example by carrying out optical scanner to paper or other media
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each section of the invention can be realized with hardware, software, firmware or their combination.Above-mentioned
In embodiment, software that multiple steps or method can be executed in memory and by suitable instruction execution system with storage
Or firmware is realized.It, and in another embodiment, can be under well known in the art for example, if realized with hardware
Any one of column technology or their combination are realized: logic gates specifically for realizing logic function to data-signal
Discrete logic, with suitable combinational logic gate circuit specific integrated circuit, programmable gate array (PGA), scene
Programmable gate array (FPGA) etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
Centainly refer to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be any
One or more embodiment or examples in can be combined in any suitable manner.
Although an embodiment of the present invention has been shown and described, it will be understood by those skilled in the art that: not
A variety of change, modification, replacement and modification can be carried out to these embodiments in the case where being detached from the principle of the present invention and objective, this
The range of invention is defined by the claims and their equivalents.
Claims (10)
1. a kind of driving fatigue detection method, which is characterized in that the described method includes:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value, and the fatigue state value are sent to movement
Terminal is shown；
The fatigue state value is compared with the off-line analysis result prestored, to judge driver currently whether in fatigue
State；
If driver is currently at fatigue state, control alarm set issue fatigue remind, and by current EEG signals, with
And the current geographic position and current time of driver is uploaded to server and saves, and passes through the monitoring client of the server
The fatigue state of driver is shown in map interface.
2. driving fatigue detection method according to claim 1, which is characterized in that it is described to collected EEG signals into
Row calculates, the step of to obtain fatigue state value in, fatigue state value is calculated using the method for Sample Entropy, is specifically included:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals are { Xi}
={ X1,X2…Xn, total length is denoted as N, similar according to original EEG signals reconstruct one if Embedded dimensions m and similar tolerance r
Tolerance r and m dimensional vector
Xi=[Xi,Xi+1,....Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from total N-m-1
Ratio, be denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series defines
Are as follows:
When N is Finite Number, above formula is expressed as:
3. driving fatigue detection method according to claim 1, which is characterized in that the off-line analysis result is using following
Method obtains:
According to sample frequency truncated data, saved for once testing for H hours EEG signals, obtain 2 M*N to
Amount, wherein 2 indicate two lead of driver's forehead, and M is the sample number of H hour, and N is sample frequency, calculates the entropy of each sample
Value finally obtains the vector of 2 M, for a driver, acquires S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
4. driving fatigue detection method according to claim 3, which is characterized in that described pair of obtained discretization entropy into
The step of row matrix calculating obtains fatigue threshold specifically includes:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with the equal of two o'clock
Value replaces, and vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation tendency,
Then dimension unification is carried out, to obtain fatigue threshold.
5. driving fatigue detection method according to claim 4, which is characterized in that the step of dimension unification is specific
Include:
Acquire the smallest dimension of S experiment；
The vector for being greater than the smallest dimension is left out the several values in front, to keep dimension unification；
To two matrixes, according to vector is classified as, the Fisher distance between two neighboring vector, calculation method are asked are as follows:
Wherein, the mean value of μ representation vector, the standard deviation of σ representation vector；
It to obtained vector maximizing, is calculated apart from maximum two adjacent vectors, and selects maximum value as fatigue
Threshold value.
6. according to claim 1 to driving fatigue detection method described in 5 any one, which is characterized in that the method is also wrapped
It includes:
The EEG signals of driver are acquired by electroencephalogramsignal signal collection equipment；
Collected EEG signals are calculated, to obtain fatigue state value；
At interval of preset time, the current geographic position and current time of the fatigue state value and driver are uploaded to clothes
Business device；
The fatigue state of driver is shown in map interface by the monitoring client of the server, different tired shapes
State value is shown in map interface by different colors.
7. a kind of driving fatigue detection system, which is characterized in that the system comprises:
Signal acquisition module, for acquiring the EEG signals of driver by electroencephalogramsignal signal collection equipment；
Sending module is calculated, for calculating collected EEG signals, to obtain fatigue state value, and by the fatigue
State value is sent to mobile terminal and is shown；
Judgment module is compared, for comparing the fatigue state value with the off-line analysis result prestored, to judge to drive
Whether member is current in a state of fatigue；
Uploading module is reminded, if being currently at fatigue state for driver, alarm set is controlled and issues fatigue prompting, and will
The current geographic position and current time of current EEG signals and driver are uploaded to server and save, and pass through
The monitoring client of the server is shown the fatigue state of driver in map interface.
8. driving fatigue detection system according to claim 7, which is characterized in that the calculating sending module is specifically used
In:
According to the original EEG signals of the multiple continuous acquisition driver of preset sample frequency, wherein original EEG signals are { Xi}
={ X1,X2…Xn, total length is denoted as N, similar according to original EEG signals reconstruct one if Embedded dimensions m and similar tolerance r
Tolerance r and m dimensional vector
Xi=[Xi,Xi+1,....Xi+m-1]
Define xiWith xjBetween distance dijFor the maximum value of the two corresponding element absolute difference, i.e.,
dij=d [xi,xj]=max [| xi+k-xj+k|]
k∈(0,m-1)
To each i, X is calculatediWith its complement vector distance dij, count dijLess than the number of r and this number and apart from total N-m-1
Ratio, be denoted asIt asks againAverage value Bm(r), i.e.,
It again to dimension m+1, repeats the above steps, obtainsCalculate average value Bm+1(r)；The Sample Entropy of original series defines
Are as follows:
When N is Finite Number, above formula is expressed as:
9. driving fatigue detection system according to claim 7, which is characterized in that the comparison judgment module is specifically used
In:
According to sample frequency truncated data, saved for once testing for H hours EEG signals, obtain 2 M*N to
Amount, wherein 2 indicate two lead of driver's forehead, and M is the sample number of H hour, and N is sample frequency, calculates the entropy of each sample
Value finally obtains the vector of 2 M, for a driver, acquires S sample as off-line analysis sample；
To 2 matrix datas, discretization is carried out to retain the method for default position decimal；
Matrix is carried out to obtained discretization entropy and calculates acquisition fatigue threshold, as off-line analysis result.
10. driving fatigue detection system according to claim 9, which is characterized in that the comparison judgment module is specifically used
In:
With preset step-length a cycle calculations step S1~S2:
S1 calculates the difference in vector between two neighboring point, if difference is less than or equal to a, the two points are with the equal of two o'clock
Value replaces, and vector dimension subtracts one；If two differences are greater than a, continue to calculate next point；
S2 meets one of following condition, then end loop:
(1) a=0.3；
(2) final vector becomes 4 dimensional vectors；
After end loop, 2 lesser vectors of dimension are finally obtained；
Tired changes of entropy trend of the driver within H hour is calculated in above-mentioned steps, finally obtains S variation tendency,
Then dimension unification is carried out, to obtain fatigue threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076624.4A CN109875582A (en) | 2019-01-26 | 2019-01-26 | Driving fatigue detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910076624.4A CN109875582A (en) | 2019-01-26 | 2019-01-26 | Driving fatigue detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109875582A true CN109875582A (en) | 2019-06-14 |
Family
ID=66927134
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910076624.4A Pending CN109875582A (en) | 2019-01-26 | 2019-01-26 | Driving fatigue detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109875582A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN114052747A (en) * | 2020-08-10 | 2022-02-18 | 西安领跑网络传媒科技股份有限公司 | Brain state adjusting method and device, computer equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0638193B1 (en) * | 1992-04-21 | 1998-09-02 | Promotions S.A. | Method for supervising the level of alertness of a person |
| CN105286890A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Driver sleepy state monitoring method based on electroencephalogram signal |
| CN108407813A (en) * | 2018-01-25 | 2018-08-17 | 惠州市德赛西威汽车电子股份有限公司 | A kind of antifatigue safe driving method of vehicle based on big data |
-
2019
- 2019-01-26 CN CN201910076624.4A patent/CN109875582A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0638193B1 (en) * | 1992-04-21 | 1998-09-02 | Promotions S.A. | Method for supervising the level of alertness of a person |
| CN105286890A (en) * | 2015-09-22 | 2016-02-03 | 江西科技学院 | Driver sleepy state monitoring method based on electroencephalogram signal |
| CN108407813A (en) * | 2018-01-25 | 2018-08-17 | 惠州市德赛西威汽车电子股份有限公司 | A kind of antifatigue safe driving method of vehicle based on big data |
Non-Patent Citations (1)
| Title |
|---|
| 王海玉 等: "基于独立成分分析降噪与集成分类器的疲劳脑电分析", 《科学技术与工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111803065A (en) * | 2020-06-23 | 2020-10-23 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN111803065B (en) * | 2020-06-23 | 2023-12-26 | 北方工业大学 | Dangerous traffic scene identification method and system based on electroencephalogram data |
| CN114052747A (en) * | 2020-08-10 | 2022-02-18 | 西安领跑网络传媒科技股份有限公司 | Brain state adjusting method and device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10525984B2 (en) | Systems and methods for using an attention buffer to improve resource allocation management | |
| EP1891490B1 (en) | Dialogue system | |
| US9283847B2 (en) | System and method to monitor and alert vehicle operator of impairment | |
| CN112534625B (en) | Diagnostic device, diagnostic method, and storage medium | |
| US20160101785A1 (en) | Driving characteristics diagnosis device, driving characteristics diagnosis system, driving characteristics diagnosis method, information output device, and information output method | |
| US20070013498A1 (en) | Device for warning the driver of a vehicle | |
| EP2811474A1 (en) | Method and system for inferring the behaviour or state of the driver of a vehicle, use method and computer program for carrying out said method | |
| CN109716411A (en) | Method and apparatus to monitor the activity level of driver | |
| US20210166502A1 (en) | Using vehicle electrical system monitored values | |
| CN104512423A (en) | System for informing functions of vehicle | |
| KR101692054B1 (en) | A Vehicle management system using digital cluster | |
| DE102016215251A1 (en) | Method for operating a navigation device of a motor vehicle | |
| CN109875582A (en) | Driving fatigue detection method and system | |
| US11941314B2 (en) | Display control device and display control method | |
| US11383640B2 (en) | Techniques for automatically reducing annoyance levels of drivers when using driver monitoring systems | |
| KR102435346B1 (en) | Driver's Health Scanning System and Alarming Method Using It | |
| CN112797996A (en) | Vehicle navigation method, device, equipment and medium | |
| CN117465474A (en) | Method, device, equipment and storage medium for detecting vehicle driving | |
| KR101324082B1 (en) | Cognitive Workload Estimation System using Driving Performance and Physiological Data | |
| CN117104256A (en) | Vehicle risk event monitoring method, device, computer equipment and storage medium | |
| CN113687900B (en) | Display method for vehicle-mounted screen and electronic equipment | |
| DE102022115531A1 (en) | Method for determining the attention of a user of a motor vehicle, computer program, data processing device and motor vehicle | |
| US20180180679A1 (en) | Non-contact intelligent battery sensing system and method | |
| CN110942591B (en) | Driving safety reminding system and method | |
| CN107507294A (en) | Wheelpath monitoring method and terminal device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |