CN109801475A - Method for detecting fatigue driving, device and computer readable storage medium - Google Patents
Method for detecting fatigue driving, device and computer readable storage medium Download PDFInfo
- Publication number
- CN109801475A CN109801475A CN201910094526.3A CN201910094526A CN109801475A CN 109801475 A CN109801475 A CN 109801475A CN 201910094526 A CN201910094526 A CN 201910094526A CN 109801475 A CN109801475 A CN 109801475A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- information
- driver
- fatigue driving
- 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
Landscapes
- Traffic Control Systems (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a kind of method for detecting fatigue driving, device and computer readable storage medium, the method for detecting fatigue driving obtains the eye video information of driver the following steps are included: when detecting that vehicle is in driving status；According to the eye video information, the eye-closing period of the driver is obtained；Detect whether the eye-closing period is greater than or equal to preset duration；If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；Based on the brain electric information, detect whether the driver belongs to fatigue state；If the driver belongs to fatigue state, alarm is issued.Through the invention, whether in a state of fatigue driver can be detected, and when detecting that driver is in a state of fatigue in vehicle travel process, issue alarm, facilitated driver and improve attention, reduce the probability that traffic accident occurs, improve traffic safety.
Description
Technical field
The present invention relates to safe driving technical field more particularly to method for detecting fatigue driving, device and computer-readable
Storage medium.
Background technique
With the development of China's economic society, the growth that highway in China road construction is advanced by leaps and bounds, automobile and driver's
Quantity is also swift and violent therewith to be increased, and while offering convenience to daily life, the frequent generation of traffic accident is also brought to society
Great loss.
In order to reduce traffic accident and reduce casualties, for the dangerous drivings behavior such as drunk driving, hypervelocity, overload
Effective regulatory measure is formulated.But other than the behaviors such as drunk driving, hypervelocity, overload are easy to cause traffic accident, fatigue
Driving is also easy to cause traffic accident.
Currently, being normally based on the characteristic information of driver face and eyes, Fatigue Assessment is carried out, but due to everyone
Biological characteristic be different, therefore the current state of mind can not accurately be judged according to the external manifestation of a people, led
Causing assessment result, there are large errors, just cannot achieve and are effectively supervised to fatigue driving.
Summary of the invention
The main purpose of the present invention is to provide a kind of method for detecting fatigue driving, device and computer-readable storage mediums
Matter, it is intended to the technical issues of solution in the prior art can not effectively supervise fatigue driving behavior.
To achieve the above object, the present invention provides a kind of method for detecting fatigue driving, the method for detecting fatigue driving packet
Include following steps:
When detecting that vehicle is in driving status, the eye video information of driver is obtained；
According to the eye video information, the eye-closing period of the driver is obtained；
Detect whether the eye-closing period is greater than or equal to preset duration；
If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；
Based on the brain electric information, detect whether the driver belongs to fatigue state；
If the driver belongs to fatigue state, alarm is issued.
Optionally, if after the step of driver belongs to fatigue state, issues alarm, further includes:
It obtains vehicle and is presently in position, position is presently in based on the vehicle, whether detection, which currently meets vehicle, is stopped
By condition；
If currently meeting vehicle parking condition, vehicle parking instruction is exported；
When the duration at the time point of distance output vehicle parking instruction reaches preset duration, whether detection vehicle, which is in, is stopped
By state；
If vehicle is not at resting state, the identity information of the vehicle and real-time position information are sent to preset
Equipment.
Optionally, the acquisition vehicle is presently in position, is presently in position based on the vehicle, detection it is current whether
After the step of meeting vehicle parking condition, further includes:
If being currently unsatisfactory for vehicle parking condition, position is presently in based on the vehicle, determines target anchor point；
The navigation information for being presently in position to the target anchor point by the vehicle is generated, and exports the navigation letter
Breath.
Optionally, described to generate the navigation information that position to the target anchor point is presently in by the vehicle and defeated
Out after the step of navigation information, further includes:
Whether corresponding with the navigation information wheelpath route for detecting the vehicle be consistent；
If the wheelpath of vehicle route corresponding with the navigation information is inconsistent, by the identity of the vehicle
Information and real-time position information are sent to preset device.
Optionally, described the step of being presently in position based on the vehicle, determined target anchor point, includes:
It is presently in position based on the vehicle, from optional anchor point, vehicle described in selected distance is presently in position
Set nearest target anchor point.
Optionally, described to be based on the brain electric information, detect that the step of whether driver belongs to fatigue state includes:
The brain electric information is sent to preset neural network model, and based on the neural network model to the brain
The corresponding classification of power information is identified, recognition result is obtained；
If recognition result is fatigue type brain electric information, the driver belongs to fatigue state；
If recognition result is awake type brain electric information, the driver belongs to waking state.
Optionally, described that the brain electric information is sent to preset neural network model, and it is based on the neural network
The step of model identifies the brain electric information include:
Denoising is carried out to the brain electric information, the brain electric information after denoising is sent to preset nerve
Network model, and the brain electric information after denoising is identified based on the neural network model.
Optionally, if the driver includes: the step of belonging to fatigue state, issue alarm
If the driver belongs to fatigue state, preset alarm audio is played, and opens double flashing lights of the vehicle.
In addition, to achieve the above object, the present invention also provides a kind of fatigue driving detection device, the fatigue driving detection
Device includes: the fatigue driving inspection that memory, processor and being stored in can be run on the memory and on the processor
Ranging sequence, the fatigue driving detection program realize method for detecting fatigue driving as described above when being executed by the processor
Step.
In addition, to achieve the above object, it is described computer-readable the present invention also provides a kind of computer readable storage medium
Fatigue driving detection program is stored on storage medium, the fatigue driving detection program realizes institute as above when being executed by processor
The step of method for detecting fatigue driving stated.
In the present invention, when detecting that vehicle is in driving status, the eye video information of driver is obtained；According to described
Eye video information obtains the eye-closing period of the driver；Detect whether the eye-closing period is greater than or equal to preset duration；
If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；Based on the brain electric information,
Detect whether the driver belongs to fatigue state；If the driver belongs to fatigue state, alarm is issued.By this hair
It is bright, whether in a state of fatigue driver can be detected, and detecting that driver is in a state of fatigue in vehicle travel process
When, alarm is issued, facilitates driver and improves attention, reduces the probability that traffic accident occurs, improves traffic safety.
Detailed description of the invention
Fig. 1 is the fatigue driving detection device structural schematic diagram for the hardware running environment that the embodiment of the present invention is related to；
Fig. 2 is the flow diagram of method for detecting fatigue driving first embodiment of the present invention；
Fig. 3 is the human eyes structure schematic diagram in one embodiment of method for detecting fatigue driving of the present invention；
Fig. 4 is a blink period corresponding EAR result signal in one embodiment of method for detecting fatigue driving of the present invention
Figure；
Fig. 5 is the flow diagram of method for detecting fatigue driving second embodiment of the present invention；
Fig. 6 is the flow diagram of method for detecting fatigue driving 3rd embodiment of the present invention；
Fig. 7 is the flow diagram of method for detecting fatigue driving fourth embodiment of the present invention；
Fig. 8 is the refinement flow diagram of step S50 in Fig. 2.
The embodiments will be further described with reference to the accompanying drawings for the realization, the function and the advantages of the object of the present invention.
Specific embodiment
It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, it is not intended to limit the present invention.
As shown in FIG. 1, FIG. 1 is the fatigue driving detection device knots for the hardware running environment that the embodiment of the present invention is related to
Structure schematic diagram.
As shown in Figure 1, the fatigue driving detection device may include: processor 1001, such as CPU, network interface 1004,
User interface 1003, memory 1005, communication bus 1002.Wherein, communication bus 1002 is for realizing between these components
Connection communication.User interface 1003 may include display screen (Display), input unit such as keyboard (Keyboard), optional
User interface 1003 can also include standard wireline interface and wireless interface.Network interface 1004 optionally may include standard
Wireline interface, wireless interface (such as WI-FI interface).Memory 1005 can be high speed RAM memory, be also possible to stable
Memory (non-volatile memory), such as magnetic disk storage.Memory 1005 optionally can also be independently of aforementioned
The storage device of processor 1001.
It will be understood by those skilled in the art that fatigue driving detection device structure shown in Fig. 1 is not constituted to fatigue
The restriction for driving detection device may include perhaps combining certain components or different than illustrating more or fewer components
Component layout.
As shown in Figure 1, as may include that operating system, network are logical in a kind of memory 1005 of computer storage medium
Believe that module, Subscriber Interface Module SIM and fatigue driving detect program.
In fatigue driving detection device shown in Fig. 1, network interface 1004 is mainly used for connecting background server, and rear
Platform server carries out data communication；User interface 1003 is mainly used for connecting client (user terminal), carries out data with client
Communication；And processor 1001 can be used for that the fatigue driving stored in memory 1005 is called to detect program, and execute following behaviour
Make:
When detecting that vehicle is in driving status, the eye video information of driver is obtained；
According to the eye video information, the eye-closing period of the driver is obtained；
Detect whether the eye-closing period is greater than or equal to preset duration；
If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；
Based on the brain electric information, detect whether the driver belongs to fatigue state；
If the driver belongs to fatigue state, alarm is issued.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
It obtains vehicle and is presently in position, position is presently in based on the vehicle, whether detection, which currently meets vehicle, is stopped
By condition；
If currently meeting vehicle parking condition, vehicle parking instruction is exported；
When the duration at the time point of distance output vehicle parking instruction reaches preset duration, whether detection vehicle, which is in, is stopped
By state；
If vehicle is not at resting state, the identity information of the vehicle and real-time position information are sent to preset
Equipment.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
If being currently unsatisfactory for vehicle parking condition, position is presently in based on the vehicle, determines target anchor point；
The navigation information for being presently in position to the target anchor point by the vehicle is generated, and exports the navigation letter
Breath.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
Whether corresponding with the navigation information wheelpath route for detecting the vehicle be consistent；
If the wheelpath of vehicle route corresponding with the navigation information is inconsistent, by the identity of the vehicle
Information and real-time position information are sent to preset device.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
It is presently in position based on the vehicle, from optional anchor point, vehicle described in selected distance is presently in position
Set nearest target anchor point.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
The brain electric information is sent to preset neural network model, and based on the neural network model to the brain
The corresponding classification of power information is identified, recognition result is obtained；
If recognition result is fatigue type brain electric information, the driver belongs to fatigue state；
If recognition result is awake type brain electric information, the driver belongs to waking state.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
Denoising is carried out to the brain electric information, the brain electric information after denoising is sent to preset nerve
Network model, and the brain electric information after denoising is identified based on the neural network model.
Further, processor 1001 can call the fatigue driving stored in memory 1005 to detect program, also execute
It operates below:
If the driver belongs to fatigue state, preset alarm audio is played, and opens double flashing lights of the vehicle.
It is the flow diagram of method for detecting fatigue driving first embodiment of the present invention referring to Fig. 2, Fig. 2.
In one embodiment, method for detecting fatigue driving includes:
Step S10 obtains the eye video information of driver when detecting that vehicle is in driving status；
In one embodiment of the invention, fatigue driving detection device can determine vehicle when detecting automobile engine starting
In driving status, controlling camera, (setting of specific position is configured according to the actual situation, specific position to specific position
To drive human face position) it shoots, obtain the eye video information of driver.For example, automobile electricity can be pre-established
The communication connection of control system and fatigue driving detection device, when automobile electric control system detects automobile engine starting, notice
Fatigue driving detection device engine is in starting state, when fatigue driving detection device receives automobile electric control system transmission
After notification information, judge that vehicle is in driving status, (setting of specific position is according to practical feelings to specific position for control camera
Condition is configured, and specific position may be configured as driving human face position) it shoots, the picture then obtained from shooting
In, ocular is positioned and is extracted, the eye video information of driver is obtained.
It, can (OTSU algorithm be by Japanese scholars OTSU in 1979 by OTSU algorithm in an alternate embodiment of the present invention
A kind of pair of image that year proposes carries out the highly effective algorithm of binaryzation) initial threshold is set by pretreated image binaryzation, it adjusts
Whole threshold value is positioning human eye using the geometrical relationship of human face characteristic point, thus from shooting to adapt to the face under different condition
To picture in, obtain the eye video information of driver.
Step S20 obtains the eye-closing period of the driver according to the eye video information；
Step S30, detects whether the eye-closing period is greater than or equal to preset duration；
It, can be by writing Python after obtaining eye video information in the present embodiment, OpenCV and dlib code is held
Blink in row detection video flowing (i.e. eye video information).Referring to Fig. 3, Fig. 3 is that method for detecting fatigue driving one of the present invention is real
Apply the human eyes structure schematic diagram in example.As shown in figure 3, since left eye angle, then surrounding should by eyes by 6 coordinate representations
The rest part in region shows that coordinate is respectively P clockwise1、P2、P3、P4、P5、P6, by eye length-width ratio equation, obtain eye
Eyeball aspect ratio EAR.Wherein
Since the length-width ratio of eyes is generally constant when eyes open, but can be rapid when blinking
Drop to zero.As shown in figure 4, Fig. 4 is corresponding for a blink period in one embodiment of method for detecting fatigue driving of the present invention
EAR result schematic diagram.As shown in figure 4, time T1~T2, corresponding EAR is zero, i.e. T1~T2 period, and eyes are in closed form
State, in this blink period, the eye-closing period of driver is T2-T1.
Based on the above principles, it can obtain in eye video information, each blink period corresponding eye-closing period.This implementation
In example, when obtaining eye-closing period, eye-closing period is compared with preset duration, if eye-closing period is greater than or equal to default
It is long, then carry out step S40, if eye-closing period is less than preset duration, by the eye-closing period obtained next time and preset duration into
Row compares, until carrying out step S40 when detecting that current eye-closing period is greater than or equal to preset duration, otherwise obtaining again
Eye-closing period next time, repeats the above steps.
In the present embodiment, preset duration is configured according to the actual situation.For example, current studies have shown that people is normal
Under state, during a blink, eyelid closing time is between 0.2S~0.3S, therefore, can set preset duration to
0.4S, if detecting, the eye-closing period of driver is greater than or equal to 0.4S, illustrates that driver is likely to be at fatigue state.
Step S40 obtains the brain electric information of the driver if the eye-closing period is greater than or equal to preset duration；
In the present embodiment, if detecting, the eye-closing period of driver is greater than or equal to preset duration, illustrates that driver can
Can be in a state of fatigue, then further obtain the brain electric information of driver.
In an alternate embodiment of the present invention, it can be and pre-establish the logical of brain wave acquisition equipment and fatigue driving detection device
News connection sends starting and refers to when fatigue driving detection device detects the eye-closing period of driving more than or equal to preset duration
It enables to brain wave acquisition equipment, when brain wave acquisition equipment receives the enabled instruction, acquires the brain electric information of current driver, simultaneously
The brain electric information collected is sent to fatigue driving detection device.I.e. brain wave acquisition equipment carries out brain electric information acquisition simultaneously
Work and brain electric information send work.
Step S50 is based on the brain electric information, detects whether the driver belongs to fatigue state；
In the present embodiment, several brain electric information samples can be first passed through in advance, neural network model is trained.For example, adopting
The brain electric information for collecting human body under N number of waking state obtains N number of waking state brain electric information sample, acquires N number of fatigue state servant
The brain electric information of body obtains N number of fatigue state brain electric information sample, by N number of waking state brain electric information sample and N number of tired
Labor state brain electric information sample, is trained neural network model, so that the neural network model that training obtains can recognize that
Brain electric information belongs to waking state brain electric information or fatigue state brain electric information.In the present embodiment, to neural network model
It is trained and can refer to existing neural network model training method, this will not be repeated here.
In the present embodiment, the brain electric information that will currently obtain, the neural network model after being input to training, for the nerve
Network model identifies brain electric information, obtains recognition result.
Step S60 issues alarm if the driver belongs to fatigue state.
In the present embodiment, if neural network model recognize brain electric information be fatigue type brain electric information when, judge to drive
Genus Homo then issues alarm in fatigue state.In the present embodiment, the mode for issuing alarm, which may is that, plays preset audio, such as broadcasts
It puts " attention please be improved ", and the double flashing lights of unlocking vehicle；Control vibrator vibration, and the double flashing lights of unlocking vehicle.
In the present embodiment, when detecting that vehicle is in driving status, the eye video information of driver is obtained；According to institute
Eye video information is stated, the eye-closing period of the driver is obtained；When detecting the eye-closing period and whether being greater than or equal to default
It is long；If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；Based on the brain telecommunications
Breath, detects whether the driver belongs to fatigue state；If the driver belongs to fatigue state, alarm is issued.Pass through this
Whether in a state of fatigue embodiment can detect driver, and detecting driver in fatigue in vehicle travel process
When state, alarm is issued, facilitates driver and improves attention, reduces the probability that traffic accident occurs, improves traffic safety.
It further, is the flow diagram of method for detecting fatigue driving second embodiment of the present invention referring to Fig. 5, Fig. 5.
In one embodiment of method for detecting fatigue driving of the present invention, after step S60 further include:
Step S70 obtains vehicle and is presently in position, is presently in position based on the vehicle, whether detection is current full
Sufficient vehicle parking condition；
In the present embodiment, it can obtain vehicle by the GPS module on vehicle and be presently in position, and it is current to detect vehicle
Whether present position belongs to the section that can stop, if vehicle is presently in position and belongs to the section that can stop, currently meets vehicle and stops
By condition, otherwise, it is currently unsatisfactory for vehicle parking condition.
Step S80 exports vehicle parking instruction if currently meeting vehicle parking condition；
In the present embodiment, if currently meeting vehicle parking condition, vehicle parking instruction is exported.For example, when vehicle is current
Present position belongs to when can stop section, plays the audio file (i.e. output vehicle parking instruction) of " asking pulling over observing ".
Step S90, when the duration at the time point of distance output vehicle parking instruction reaches preset duration, detection vehicle is
It is no to be in resting state；
Step S100, if vehicle is not at resting state, by the identity information and real-time position information of the vehicle
It is sent to preset device.
In the present embodiment, belong to the section that can stop since vehicle is presently in position, after output vehicle parking instruction, drives
Vehicle parking can be completed in a short time by sailing people, therefore, when the duration at the time point of distance output vehicle parking instruction reaches pre-
If when duration (preset duration can be configured according to actual needs, such as be set as 5 minutes), whether detection vehicle, which is in, is stopped
By state.
In the present embodiment, detection vehicle whether be in resting state may is that detection vehicle whether the engine is off, or
Whether the speed for detecting vehicle is zero.If detecting the tail-off of vehicle or detecting that car speed is zero, vehicle is determined
Be in resting state；If detecting that the engine of vehicle is in the open state or detecting that the speed of vehicle is not zero, sentence
Disconnected vehicle is not at resting state.
In the present embodiment, if vehicle is not at resting state, illustrate driver in fatigue driving, then by the identity of vehicle
Information and real-time position information are sent to preset device.
In the present embodiment, the identity information of vehicle can be pre-stored in fatigue driving detection device, the identity letter of vehicle
Breath may include: the driver's license information of the license plate number of vehicle, the affiliated people of vehicle.Preset device can be the service of traffic control department
Device.When the server of traffic control department receives the identity information and real-time position information of vehicle, can record the vehicle, there are tired
Please the behavior sailed deducts points to the driver's license of the affiliated people of vehicle, and the publication vehicle of the real time position based on vehicle intercepts and appoints
Business avoids fatigue driving from causing traffic accident to relevant staff for manually being intercepted to the vehicle.
It further, is the flow diagram of method for detecting fatigue driving 3rd embodiment of the present invention referring to Fig. 6, Fig. 6.
In one embodiment of method for detecting fatigue driving of the present invention, after step S70, further includes:
Step S110 is presently in position based on the vehicle, determines target if being currently unsatisfactory for vehicle parking condition
Anchor point；
Step S120 generates the navigation information for being presently in position to the target anchor point by the vehicle, and exports
The navigation information.
In the present embodiment, if vehicle is presently in position and is not belonging to the section that can stop, position is presently in based on vehicle,
It looks for vehicle and is presently in dockable position around position, and determined from dockable position and be presently in position apart from vehicle
A nearest position is set, as target anchor point.The navigation information that position to target anchor point is presently in by vehicle is generated,
And export navigation information.
In the present embodiment, when detecting driver fatigue, and after outputting alarm, if detecting, vehicle is currently unsatisfactory for stopping
Condition is then presently in position based on vehicle, looks for target anchor point for vehicle, and generate and stopped by being presently in position to target
By the navigation of point, exports navigation information and rest so that driver is rapidly achieved target anchor point, improve traffic safety.
It further, is the flow diagram of method for detecting fatigue driving fourth embodiment of the present invention referring to Fig. 7, Fig. 7.
In one embodiment of method for detecting fatigue driving of the present invention, after step S120, further includes:
Whether corresponding with the navigation information step S130, the wheelpath route for detecting the vehicle be consistent；
Step S140 will be described if the wheelpath of vehicle route corresponding with the navigation information is inconsistent
The identity information and real-time position information of vehicle are sent to preset device.
In the present embodiment, after exporting navigation information, driver should travel in accordance with navigation information.Therefore, it is exporting
After navigation information, whether corresponding with navigation information the wheelpath route for detecting vehicle be consistent, if unanimously, illustrating driver
Target anchor point is just being gone to, if inconsistent, is illustrating that driver does not go to target anchor point in accordance with the instruction of navigation information, then
The identity information of vehicle and real-time position information are sent to preset device.In the present embodiment, the identity information of vehicle can be pre-
It is first stored in fatigue driving detection device, the identity information of vehicle may include: that the license plate number of vehicle, the affiliated people of vehicle drive
Sail card information.Preset device can be the server of traffic control department.The server of traffic control department receives the identity information of vehicle
And when real-time position information, can record the vehicle, there are the behaviors of fatigue driving, detain the driver's license of the affiliated people of vehicle
Point, and the publication vehicle of the real time position based on vehicle intercepts task to relevant staff, for carrying out manually to the vehicle
It intercepts, fatigue driving is avoided to cause traffic accident.
Further, described that position is presently in based on the vehicle in one embodiment of method for detecting fatigue driving of the present invention
The step of setting, determining target anchor point include:
It is presently in position based on the vehicle, from optional anchor point, vehicle described in selected distance is presently in position
Set nearest target anchor point.
In the present embodiment, if vehicle is presently in position and is not belonging to the section that can stop, position is presently in based on vehicle,
It looks for vehicle and is presently in dockable position around position, and determined from dockable position and be presently in position apart from vehicle
A nearest position is set, as target anchor point.The navigation information that position to target anchor point is presently in by vehicle is generated,
And export navigation information.
In the present embodiment, when detecting driver fatigue, and after outputting alarm, if detecting, vehicle is currently unsatisfactory for stopping
Condition is then presently in position based on vehicle, looks for target anchor point for vehicle, and generate and stopped by being presently in position to target
By the navigation of point, exports navigation information and rest so that driver is rapidly achieved target anchor point, improve traffic safety.
It further, is the refinement flow diagram of step S50 in Fig. 2 referring to Fig. 8, Fig. 8.
In one embodiment of method for detecting fatigue driving of the present invention, step S50 includes:
The brain electric information is sent to preset neural network model, and is based on the neural network mould by step S501
Type identifies the corresponding classification of the brain electric information, obtains recognition result；
Step S502, if recognition result is fatigue type brain electric information, the driver belongs to fatigue state；
Step S503, if recognition result is awake type brain electric information, the driver belongs to waking state.
In the present embodiment, several brain electric information samples can be first passed through in advance, neural network model is trained.For example, adopting
The brain electric information for collecting human body under N number of waking state obtains N number of waking state brain electric information sample, acquires N number of fatigue state servant
The brain electric information of body obtains N number of fatigue state brain electric information sample, by N number of waking state brain electric information sample and N number of tired
Labor state brain electric information sample, is trained neural network model, so that the neural network model that training obtains can recognize that
Brain electric information belongs to waking state brain electric information or fatigue state brain electric information.In the present embodiment, to neural network model
It is trained and can refer to existing neural network model training method, this will not be repeated here.
In the present embodiment, the brain electric information that will currently obtain, the neural network model after being input to training, for the nerve
Network model identifies brain electric information, obtains recognition result.
Further, in one embodiment of method for detecting fatigue driving of the present invention, step S501 includes:
Denoising is carried out to the brain electric information, the brain electric information after denoising is sent to preset nerve
Network model, and the brain electric information after denoising is identified based on the neural network model.
In the present embodiment, before brain electric information is sent to preset neural network model, brain electric information can be gone
It makes an uproar processing.For example, 0-20Hz low-frequency noise is filtered out using low pass or band logical (20-450Hz) filter, using Wavelet Denoising Method or certainly
Adaptive filtering algorithm removes 50Hz or so Hz noise and other high-frequency noises.Brain electric information after denoising is sent
To preset neural network model, the accuracy of the recognition result of neural network model can be improved.
Further, in one embodiment of method for detecting fatigue driving of the present invention, step S60 includes:
If the driver belongs to fatigue state, preset alarm audio is played, and opens double flashing lights of the vehicle.
In the present embodiment, if neural network model recognize brain electric information be fatigue type brain electric information when, judge to drive
Genus Homo then issues alarm in fatigue state.In the present embodiment, the mode for issuing alarm, which may is that, plays preset audio, such as broadcasts
It puts " attention please be improved ", and the double flashing lights of unlocking vehicle；Control vibrator vibration, and the double flashing lights of unlocking vehicle.
In the present embodiment, the attention that preset alarm audio helps to improve driver, double sudden strains of a muscle of unlocking vehicle are played
Lamp informs other vehicles and maintains safe distance with current vehicle, to reduce the probability of traffic accident generation.
In addition, the embodiment of the present invention also proposes a kind of computer readable storage medium, the computer readable storage medium
On be stored with fatigue driving detection program, fatigue driving detection program realizes fatigue as described above when being executed by processor
The step of driving detection method.
Each implementation of the specific embodiment of computer readable storage medium of the present invention and above-mentioned method for detecting fatigue driving
Example is essentially identical, and this will not be repeated here.
It should be noted that, in this document, the terms "include", "comprise" or its any other variant are intended to non-row
His property includes, so that the process, method, article or the system that include a series of elements not only include those elements, and
And further include other elements that are not explicitly listed, or further include for this process, method, article or system institute it is intrinsic
Element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that including being somebody's turn to do
There is also other identical elements in the process, method of element, article or system.
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Through the above description of the embodiments, those skilled in the art can be understood that above-described embodiment side
Method can be realized by means of software and necessary general hardware platform, naturally it is also possible to by hardware, but in many cases
The former is more preferably embodiment.Based on this understanding, technical solution of the present invention substantially in other words does the prior art
The part contributed out can be embodied in the form of software products, which is stored in one as described above
In storage medium (such as ROM/RAM, magnetic disk, CD), including some instructions are used so that terminal device (it can be mobile phone,
Computer, server, air conditioner or network equipment etc.) execute method described in each embodiment of the present invention.
The above is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of method for detecting fatigue driving, which is characterized in that the method for detecting fatigue driving the following steps are included:
When detecting that vehicle is in driving status, the eye video information of driver is obtained；
According to the eye video information, the eye-closing period of the driver is obtained；
Detect whether the eye-closing period is greater than or equal to preset duration；
If the eye-closing period is greater than or equal to preset duration, the brain electric information of the driver is obtained；
Based on the brain electric information, detect whether the driver belongs to fatigue state；
If the driver belongs to fatigue state, alarm is issued.
2. method for detecting fatigue driving as described in claim 1, which is characterized in that if the driver belongs to tired shape
State, then after the step of issuing alarm, further includes:
It obtains vehicle and is presently in position, position is presently in based on the vehicle, whether detection currently meets vehicle parking item
Part；
If currently meeting vehicle parking condition, vehicle parking instruction is exported；
When the duration at the time point of distance output vehicle parking instruction reaches preset duration, whether detection vehicle is in stop shape
State；
If vehicle is not at resting state, the identity information of the vehicle and real-time position information are sent to pre- install
It is standby.
3. method for detecting fatigue driving as claimed in claim 2, which is characterized in that the acquisition vehicle is presently in position,
Position is presently in based on the vehicle, after the step of whether detection currently meets vehicle parking condition, further includes:
If being currently unsatisfactory for vehicle parking condition, position is presently in based on the vehicle, determines target anchor point；
The navigation information for being presently in position to the target anchor point by the vehicle is generated, and exports the navigation information.
4. method for detecting fatigue driving as claimed in claim 3, which is characterized in that the generation is presently in by the vehicle
Position to the target anchor point navigation information, and after the step of exporting the navigation information, further includes:
Whether corresponding with the navigation information wheelpath route for detecting the vehicle be consistent；
If the wheelpath of vehicle route corresponding with the navigation information is inconsistent, by the identity information of the vehicle
And real-time position information is sent to preset device.
5. method for detecting fatigue driving as claimed in claim 3, which is characterized in that described to be presently in position based on the vehicle
The step of setting, determining target anchor point include:
It is presently in position based on the vehicle, from optional anchor point, vehicle described in selected distance is presently in position most
Close target anchor point.
6. method for detecting fatigue driving as described in claim 1, which is characterized in that described to be based on the brain electric information, detection
The step of whether driver belongs to fatigue state include:
The brain electric information is sent to preset neural network model, and based on the neural network model to the brain telecommunications
It ceases corresponding classification to be identified, obtains recognition result；
If recognition result is fatigue type brain electric information, the driver belongs to fatigue state；
If recognition result is awake type brain electric information, the driver belongs to waking state.
7. method for detecting fatigue driving as claimed in claim 6, which is characterized in that it is described the brain electric information is sent to it is pre-
The neural network model set, and the step of being identified based on the neural network model to the brain electric information includes:
Denoising is carried out to the brain electric information, the brain electric information after denoising is sent to preset neural network
Model, and the brain electric information after denoising is identified based on the neural network model.
8. method for detecting fatigue driving as described in claim 1, which is characterized in that if the driver belongs to tired shape
State, then the step of issuing alarm include:
If the driver belongs to fatigue state, preset alarm audio is played, and opens double flashing lights of the vehicle.
9. a kind of fatigue driving detection device, which is characterized in that the fatigue driving detection device includes: memory, processor
And it is stored in the fatigue driving detection program that can be run on the memory and on the processor, the fatigue driving detection
It realizes when program is executed by the processor such as the step of method for detecting fatigue driving described in any item of the claim 1 to 8.
10. a kind of computer readable storage medium, which is characterized in that be stored with fatigue on the computer readable storage medium and drive
Detection program is sailed, the fatigue driving detection program is realized when being executed by processor as described in any item of the claim 1 to 8
The step of method for detecting fatigue driving.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094526.3A CN109801475A (en) | 2019-01-30 | 2019-01-30 | Method for detecting fatigue driving, device and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910094526.3A CN109801475A (en) | 2019-01-30 | 2019-01-30 | Method for detecting fatigue driving, device and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109801475A true CN109801475A (en) | 2019-05-24 |
Family
ID=66559172
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910094526.3A Pending CN109801475A (en) | 2019-01-30 | 2019-01-30 | Method for detecting fatigue driving, device and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109801475A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381652A (en) * | 2019-07-08 | 2019-10-25 | 武汉诚信卓远科技发展有限公司 | Lamps intelligent control method, equipment and computer readable storage medium |
| CN112754498A (en) * | 2021-01-11 | 2021-05-07 | 一汽解放汽车有限公司 | Driver fatigue detection method, device, equipment and storage medium |
| CN112785813A (en) * | 2019-11-08 | 2021-05-11 | 上海博泰悦臻电子设备制造有限公司 | Driving time reminding method and device |
| CN113844455A (en) * | 2021-08-27 | 2021-12-28 | 奇瑞汽车股份有限公司 | Method and device for braking a vehicle while the driver is tired |
| CN114241589A (en) * | 2022-02-28 | 2022-03-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Bus driver violation judgment method and device based on vehicle-mounted video |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814137A (en) * | 2010-03-25 | 2010-08-25 | 浙江工业大学 | Driver fatigue monitor system based on infrared eye state identification |
| CN101916495A (en) * | 2010-08-19 | 2010-12-15 | 北京中交兴路信息科技有限公司 | Vehicle DAS (Driver Assistant System) and method |
| CN103700217A (en) * | 2014-01-07 | 2014-04-02 | 广州市鸿慧电子科技有限公司 | Fatigue driving detecting system and method based on human eye and wheel path characteristics |
| CN103989471A (en) * | 2014-05-08 | 2014-08-20 | 东北大学 | Fatigue driving detection system and method based on EEG identification |
| CN104840204A (en) * | 2015-04-10 | 2015-08-19 | 京东方科技集团股份有限公司 | Fatigue driving monitoring method and equipment |
| CN105069977A (en) * | 2015-07-28 | 2015-11-18 | 宋婉毓 | Reminding device and reminding method for preventing fatigue driving |
| CN105740847A (en) * | 2016-03-02 | 2016-07-06 | 同济大学 | Fatigue grade discrimination algorithm based on driver eye portion identification and vehicle driving track |
| CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
| CN106529496A (en) * | 2016-11-24 | 2017-03-22 | 广西大学 | Locomotive driver real-time video fatigue detection method |
| CN206561805U (en) * | 2017-02-22 | 2017-10-17 | 深圳市百智康科技有限公司 | A kind of anti-fatigue-driving car-mounted device |
| CN108099785A (en) * | 2017-12-25 | 2018-06-01 | 芜湖皖江知识产权运营中心有限公司 | A kind of traffic control method applied in intelligent vehicle |
-
2019
- 2019-01-30 CN CN201910094526.3A patent/CN109801475A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101814137A (en) * | 2010-03-25 | 2010-08-25 | 浙江工业大学 | Driver fatigue monitor system based on infrared eye state identification |
| CN101916495A (en) * | 2010-08-19 | 2010-12-15 | 北京中交兴路信息科技有限公司 | Vehicle DAS (Driver Assistant System) and method |
| CN103700217A (en) * | 2014-01-07 | 2014-04-02 | 广州市鸿慧电子科技有限公司 | Fatigue driving detecting system and method based on human eye and wheel path characteristics |
| CN103989471A (en) * | 2014-05-08 | 2014-08-20 | 东北大学 | Fatigue driving detection system and method based on EEG identification |
| CN104840204A (en) * | 2015-04-10 | 2015-08-19 | 京东方科技集团股份有限公司 | Fatigue driving monitoring method and equipment |
| CN105069977A (en) * | 2015-07-28 | 2015-11-18 | 宋婉毓 | Reminding device and reminding method for preventing fatigue driving |
| CN105740847A (en) * | 2016-03-02 | 2016-07-06 | 同济大学 | Fatigue grade discrimination algorithm based on driver eye portion identification and vehicle driving track |
| CN106504475A (en) * | 2016-10-15 | 2017-03-15 | 北海益生源农贸有限责任公司 | Method for detecting fatigue driving based on EEG signals |
| CN106529496A (en) * | 2016-11-24 | 2017-03-22 | 广西大学 | Locomotive driver real-time video fatigue detection method |
| CN206561805U (en) * | 2017-02-22 | 2017-10-17 | 深圳市百智康科技有限公司 | A kind of anti-fatigue-driving car-mounted device |
| CN108099785A (en) * | 2017-12-25 | 2018-06-01 | 芜湖皖江知识产权运营中心有限公司 | A kind of traffic control method applied in intelligent vehicle |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110381652A (en) * | 2019-07-08 | 2019-10-25 | 武汉诚信卓远科技发展有限公司 | Lamps intelligent control method, equipment and computer readable storage medium |
| CN112785813A (en) * | 2019-11-08 | 2021-05-11 | 上海博泰悦臻电子设备制造有限公司 | Driving time reminding method and device |
| CN112754498A (en) * | 2021-01-11 | 2021-05-07 | 一汽解放汽车有限公司 | Driver fatigue detection method, device, equipment and storage medium |
| CN113844455A (en) * | 2021-08-27 | 2021-12-28 | 奇瑞汽车股份有限公司 | Method and device for braking a vehicle while the driver is tired |
| CN114241589A (en) * | 2022-02-28 | 2022-03-25 | 深圳市城市交通规划设计研究中心股份有限公司 | Bus driver violation judgment method and device based on vehicle-mounted video |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109801475A (en) | Method for detecting fatigue driving, device and computer readable storage medium | |
| WO2020078465A1 (en) | Method and device for driving state analysis, driver monitoring system and vehicle | |
| WO2020078464A1 (en) | Driving state detection method and apparatus, driver monitoring system, and vehicle | |
| WO2019232972A1 (en) | Driving management method and system, vehicle-mounted intelligent system, electronic device and medium | |
| CN106335432A (en) | Smart rearview mirror with driving assistant system, control system and processing method | |
| CN109646024A (en) | Method for detecting fatigue driving, device and computer readable storage medium | |
| JP2020525884A (en) | Vehicle control method and system, in-vehicle intelligent system, electronic device and medium | |
| CN104183091A (en) | System for adjusting sensitivity of fatigue driving early warning system in self-adaptive mode | |
| CN102752458A (en) | Driver fatigue detection mobile phone and unit | |
| CN105788028A (en) | Automobile data recorder with fatigue driving pre-warning function | |
| US20180229654A1 (en) | Sensing application use while driving | |
| Xu et al. | Sober-Drive: A smartphone-assisted drowsy driving detection system | |
| CN104859559B (en) | The control method and device of interior environment | |
| CN209795467U (en) | Fatigue driving detection system and vehicle | |
| CN110588548A (en) | Method for preventing fatigue driving and vehicle driving management system | |
| CN106157537A (en) | Anti-fatigue-driving system | |
| CN113239754A (en) | Dangerous driving behavior detection and positioning method and system applied to Internet of vehicles | |
| CN109606376A (en) | A kind of safe driving Activity recognition system based on vehicle intelligent terminal | |
| CN110525450A (en) | A kind of method and system adjusting vehicle-mounted voice sensitivity | |
| CN107933461A (en) | In-car identification fusing device and method based on single camera | |
| CN113312958B (en) | Method and device for adjusting dispatch priority based on driver state | |
| CN204706141U (en) | Wearable device | |
| CN106919123A (en) | A kind of method and system of bus emergency braking | |
| CN206039557U (en) | Driving situation monitoring system | |
| CN115762048A (en) | Emergency call method and device, vehicle-mounted terminal and storage medium |
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: 20190524 |
|
| RJ01 | Rejection of invention patent application after publication |